Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-2242/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9991829458515933,
+    "total_flos": 5.790417620582793e+18,
+    "train_loss": 0.36008237901805873,
+    "train_runtime": 20584.0534,
+    "train_samples": 53851,
+    "train_samples_per_second": 5.232,
+    "train_steps_per_second": 0.109
+}

checkpoint-2242/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-2242/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.1"
+}

checkpoint-2242/global_step2242/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e02dff4ebc0b50c30d804005ac4cc935ad8b613c1fca63cf8e2f655b09ca1e
+size 24090788620

checkpoint-2242/global_step2242/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc96368cc1325de2242a2ef4b21a6ee9a32e520729aff0f60b6439bc9538814a
+size 24090788620

checkpoint-2242/global_step2242/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0117f2531f7cc4350b7ed32606aa28c1881a8550427a91857daf0b40b3e5c59f
+size 24090788620

checkpoint-2242/global_step2242/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92002fe1925fbc18d26678db32e85727339f6b1ce7905737eff870c98f4b4735
+size 24090788620

checkpoint-2242/global_step2242/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd84a69d4b263c043d81e0e6fd262ce1a8bd5875127c1123993fa57bd0798437
+size 149093

checkpoint-2242/global_step2242/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3659d6f9e352d9e1c52c465c469889cd671c74c0f57460a49edec01013912e1f
+size 149093

checkpoint-2242/global_step2242/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ef4763af3b1d81faa00b0ffbec05e5642909fbb534c6f331f0bf58e85b9e0b
+size 149093

checkpoint-2242/global_step2242/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9754a83b27a92641bc9742b1d97c5b0c9a596e74d46294a691b5daebb6ca3688
+size 149093

checkpoint-2242/latest

@@ -0,0 +1 @@
+global_step2242

checkpoint-2242/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291e07ffb6d2d2a2b7fc1c221ab8cd07b7a0babf3660b5a622235bc5632df950
+size 4976698672

checkpoint-2242/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b082a30443feee88f5dcea38a7b25a37c3ba508381ffb25dda22e363f6201ea0
+size 4999802720

checkpoint-2242/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde08fffd72f6e2f4212d7a32f6c6b9e24e43deb69e8d9119847d57bb758b64e
+size 4915916176

checkpoint-2242/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119f2e377c58d48a02bf9040fe74adec6e477704aa2a53fec311efbecdd56840
+size 1168138808

checkpoint-2242/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-2242/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3efc1297de4c091df0ce029b94b093303c6664acbe15cebf0bc4fcf5b634ef08
+size 15024

checkpoint-2242/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90723be69870b57d02b7de51b0968f763d925550e0fee1dc323c24542ca60d95
+size 15024

checkpoint-2242/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04fd57176d70c19f516f26239322540ea8d5921591f325ee68076f3f17a6dc3f
+size 15024

checkpoint-2242/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86381847bd7289e05f3ba002e3523f844366a1fb5be0a85c930b081162082e40
+size 15024

checkpoint-2242/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a03b4495793a394eaf5178fb7edd99040dbd38eb65a8f7c8d0b8e054758a34
+size 1064

checkpoint-2242/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-2242/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd751a4191592ee601080b532d487e2444024e3205900acca92b7c94791e29dd
+size 17210060

checkpoint-2242/tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-2242/trainer_state.json

@@ -0,0 +1,3192 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9991829458515933,
+  "eval_steps": 500,
+  "global_step": 2242,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000891331798261903,
+      "grad_norm": 1.9037784957265278,
+      "learning_rate": 4.444444444444445e-08,
+      "loss": 2.0985,
+      "step": 1
+    },
+    {
+      "epoch": 0.004456658991309515,
+      "grad_norm": 2.041848097696368,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 2.1176,
+      "step": 5
+    },
+    {
+      "epoch": 0.00891331798261903,
+      "grad_norm": 1.948478886522995,
+      "learning_rate": 4.444444444444445e-07,
+      "loss": 2.1163,
+      "step": 10
+    },
+    {
+      "epoch": 0.013369976973928544,
+      "grad_norm": 1.2537062422839984,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 1.9595,
+      "step": 15
+    },
+    {
+      "epoch": 0.01782663596523806,
+      "grad_norm": 0.7428497382948752,
+      "learning_rate": 8.88888888888889e-07,
+      "loss": 1.753,
+      "step": 20
+    },
+    {
+      "epoch": 0.022283294956547576,
+      "grad_norm": 0.8283681781487435,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.3909,
+      "step": 25
+    },
+    {
+      "epoch": 0.02673995394785709,
+      "grad_norm": 0.36636499270519984,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.0722,
+      "step": 30
+    },
+    {
+      "epoch": 0.031196612939166604,
+      "grad_norm": 0.26139683469044633,
+      "learning_rate": 1.5555555555555558e-06,
+      "loss": 0.8856,
+      "step": 35
+    },
+    {
+      "epoch": 0.03565327193047612,
+      "grad_norm": 0.25123645705965264,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 0.7828,
+      "step": 40
+    },
+    {
+      "epoch": 0.040109930921785636,
+      "grad_norm": 0.21827339412974361,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.7277,
+      "step": 45
+    },
+    {
+      "epoch": 0.04456658991309515,
+      "grad_norm": 0.184310768975577,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.6973,
+      "step": 50
+    },
+    {
+      "epoch": 0.04902324890440467,
+      "grad_norm": 0.15756594573320623,
+      "learning_rate": 2.4444444444444447e-06,
+      "loss": 0.6115,
+      "step": 55
+    },
+    {
+      "epoch": 0.05347990789571418,
+      "grad_norm": 0.1495421231449033,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.5526,
+      "step": 60
+    },
+    {
+      "epoch": 0.05793656688702369,
+      "grad_norm": 0.11563000336226048,
+      "learning_rate": 2.888888888888889e-06,
+      "loss": 0.553,
+      "step": 65
+    },
+    {
+      "epoch": 0.06239322587833321,
+      "grad_norm": 0.11747617404049002,
+      "learning_rate": 3.1111111111111116e-06,
+      "loss": 0.5422,
+      "step": 70
+    },
+    {
+      "epoch": 0.06684988486964273,
+      "grad_norm": 0.124912316735415,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.5342,
+      "step": 75
+    },
+    {
+      "epoch": 0.07130654386095224,
+      "grad_norm": 0.11219727658791885,
+      "learning_rate": 3.555555555555556e-06,
+      "loss": 0.506,
+      "step": 80
+    },
+    {
+      "epoch": 0.07576320285226175,
+      "grad_norm": 0.13707586211382092,
+      "learning_rate": 3.777777777777778e-06,
+      "loss": 0.4776,
+      "step": 85
+    },
+    {
+      "epoch": 0.08021986184357127,
+      "grad_norm": 0.14849136857556636,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.4592,
+      "step": 90
+    },
+    {
+      "epoch": 0.08467652083488078,
+      "grad_norm": 0.13619871874828954,
+      "learning_rate": 4.222222222222223e-06,
+      "loss": 0.4622,
+      "step": 95
+    },
+    {
+      "epoch": 0.0891331798261903,
+      "grad_norm": 0.11869279856425284,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.4518,
+      "step": 100
+    },
+    {
+      "epoch": 0.09358983881749981,
+      "grad_norm": 0.12992883840039074,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.4115,
+      "step": 105
+    },
+    {
+      "epoch": 0.09804649780880934,
+      "grad_norm": 0.1023382558423108,
+      "learning_rate": 4.888888888888889e-06,
+      "loss": 0.4397,
+      "step": 110
+    },
+    {
+      "epoch": 0.10250315680011884,
+      "grad_norm": 0.12320266344355456,
+      "learning_rate": 5.1111111111111115e-06,
+      "loss": 0.4409,
+      "step": 115
+    },
+    {
+      "epoch": 0.10695981579142835,
+      "grad_norm": 0.11198962480183935,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.4436,
+      "step": 120
+    },
+    {
+      "epoch": 0.11141647478273788,
+      "grad_norm": 0.10145699193523927,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.4338,
+      "step": 125
+    },
+    {
+      "epoch": 0.11587313377404738,
+      "grad_norm": 0.09900502716310512,
+      "learning_rate": 5.777777777777778e-06,
+      "loss": 0.4208,
+      "step": 130
+    },
+    {
+      "epoch": 0.12032979276535691,
+      "grad_norm": 0.08614271297265043,
+      "learning_rate": 6e-06,
+      "loss": 0.4089,
+      "step": 135
+    },
+    {
+      "epoch": 0.12478645175666642,
+      "grad_norm": 0.07806255577197463,
+      "learning_rate": 6.222222222222223e-06,
+      "loss": 0.3945,
+      "step": 140
+    },
+    {
+      "epoch": 0.12924311074797593,
+      "grad_norm": 0.07178671408430405,
+      "learning_rate": 6.444444444444445e-06,
+      "loss": 0.3889,
+      "step": 145
+    },
+    {
+      "epoch": 0.13369976973928546,
+      "grad_norm": 0.08445699462456596,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.4131,
+      "step": 150
+    },
+    {
+      "epoch": 0.13815642873059497,
+      "grad_norm": 0.0853269964638284,
+      "learning_rate": 6.88888888888889e-06,
+      "loss": 0.4053,
+      "step": 155
+    },
+    {
+      "epoch": 0.14261308772190448,
+      "grad_norm": 0.0776450305961035,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 0.3882,
+      "step": 160
+    },
+    {
+      "epoch": 0.147069746713214,
+      "grad_norm": 0.08066465881766263,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.4148,
+      "step": 165
+    },
+    {
+      "epoch": 0.1515264057045235,
+      "grad_norm": 0.08075299908764268,
+      "learning_rate": 7.555555555555556e-06,
+      "loss": 0.4014,
+      "step": 170
+    },
+    {
+      "epoch": 0.15598306469583303,
+      "grad_norm": 0.08146641337838845,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.4067,
+      "step": 175
+    },
+    {
+      "epoch": 0.16043972368714254,
+      "grad_norm": 0.06545943489756188,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.3913,
+      "step": 180
+    },
+    {
+      "epoch": 0.16489638267845205,
+      "grad_norm": 0.07220259387677776,
+      "learning_rate": 8.222222222222222e-06,
+      "loss": 0.4169,
+      "step": 185
+    },
+    {
+      "epoch": 0.16935304166976156,
+      "grad_norm": 0.0666745164016267,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 0.4203,
+      "step": 190
+    },
+    {
+      "epoch": 0.17380970066107107,
+      "grad_norm": 0.08104266749063946,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.3586,
+      "step": 195
+    },
+    {
+      "epoch": 0.1782663596523806,
+      "grad_norm": 0.06500061012271417,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.3844,
+      "step": 200
+    },
+    {
+      "epoch": 0.18272301864369012,
+      "grad_norm": 0.06438217840061684,
+      "learning_rate": 9.111111111111112e-06,
+      "loss": 0.4154,
+      "step": 205
+    },
+    {
+      "epoch": 0.18717967763499962,
+      "grad_norm": 0.07013299670767151,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.3874,
+      "step": 210
+    },
+    {
+      "epoch": 0.19163633662630913,
+      "grad_norm": 0.07168242323487646,
+      "learning_rate": 9.555555555555556e-06,
+      "loss": 0.3849,
+      "step": 215
+    },
+    {
+      "epoch": 0.19609299561761867,
+      "grad_norm": 0.05932657135991667,
+      "learning_rate": 9.777777777777779e-06,
+      "loss": 0.3672,
+      "step": 220
+    },
+    {
+      "epoch": 0.20054965460892818,
+      "grad_norm": 0.07058592680145803,
+      "learning_rate": 1e-05,
+      "loss": 0.387,
+      "step": 225
+    },
+    {
+      "epoch": 0.2050063136002377,
+      "grad_norm": 0.051067467997344705,
+      "learning_rate": 9.999848376760494e-06,
+      "loss": 0.3826,
+      "step": 230
+    },
+    {
+      "epoch": 0.2094629725915472,
+      "grad_norm": 0.06816795236315125,
+      "learning_rate": 9.999393516237815e-06,
+      "loss": 0.3931,
+      "step": 235
+    },
+    {
+      "epoch": 0.2139196315828567,
+      "grad_norm": 0.06395745969231853,
+      "learning_rate": 9.998635446018936e-06,
+      "loss": 0.4009,
+      "step": 240
+    },
+    {
+      "epoch": 0.21837629057416624,
+      "grad_norm": 0.0713711836562236,
+      "learning_rate": 9.997574212080282e-06,
+      "loss": 0.3793,
+      "step": 245
+    },
+    {
+      "epoch": 0.22283294956547575,
+      "grad_norm": 0.0698163755701484,
+      "learning_rate": 9.996209878784942e-06,
+      "loss": 0.397,
+      "step": 250
+    },
+    {
+      "epoch": 0.22728960855678526,
+      "grad_norm": 0.0682706528712552,
+      "learning_rate": 9.99454252887877e-06,
+      "loss": 0.405,
+      "step": 255
+    },
+    {
+      "epoch": 0.23174626754809477,
+      "grad_norm": 0.06445770501449549,
+      "learning_rate": 9.992572263485365e-06,
+      "loss": 0.3502,
+      "step": 260
+    },
+    {
+      "epoch": 0.2362029265394043,
+      "grad_norm": 0.06470981088114686,
+      "learning_rate": 9.990299202099934e-06,
+      "loss": 0.415,
+      "step": 265
+    },
+    {
+      "epoch": 0.24065958553071382,
+      "grad_norm": 0.05884297180052234,
+      "learning_rate": 9.987723482582052e-06,
+      "loss": 0.3891,
+      "step": 270
+    },
+    {
+      "epoch": 0.24511624452202332,
+      "grad_norm": 0.05013087545524401,
+      "learning_rate": 9.98484526114729e-06,
+      "loss": 0.4081,
+      "step": 275
+    },
+    {
+      "epoch": 0.24957290351333283,
+      "grad_norm": 0.05965101051743905,
+      "learning_rate": 9.981664712357756e-06,
+      "loss": 0.367,
+      "step": 280
+    },
+    {
+      "epoch": 0.25402956250464237,
+      "grad_norm": 0.06332324890343168,
+      "learning_rate": 9.97818202911149e-06,
+      "loss": 0.3821,
+      "step": 285
+    },
+    {
+      "epoch": 0.25848622149595185,
+      "grad_norm": 0.06434539140174649,
+      "learning_rate": 9.974397422630781e-06,
+      "loss": 0.4017,
+      "step": 290
+    },
+    {
+      "epoch": 0.2629428804872614,
+      "grad_norm": 0.047968388544284014,
+      "learning_rate": 9.970311122449348e-06,
+      "loss": 0.3785,
+      "step": 295
+    },
+    {
+      "epoch": 0.2673995394785709,
+      "grad_norm": 0.05355639391449654,
+      "learning_rate": 9.965923376398414e-06,
+      "loss": 0.3829,
+      "step": 300
+    },
+    {
+      "epoch": 0.2718561984698804,
+      "grad_norm": 0.05997351126022962,
+      "learning_rate": 9.961234450591692e-06,
+      "loss": 0.3834,
+      "step": 305
+    },
+    {
+      "epoch": 0.27631285746118994,
+      "grad_norm": 0.06439261526987958,
+      "learning_rate": 9.956244629409231e-06,
+      "loss": 0.3473,
+      "step": 310
+    },
+    {
+      "epoch": 0.2807695164524994,
+      "grad_norm": 0.048664469272370746,
+      "learning_rate": 9.950954215480168e-06,
+      "loss": 0.3883,
+      "step": 315
+    },
+    {
+      "epoch": 0.28522617544380896,
+      "grad_norm": 0.06106240669926854,
+      "learning_rate": 9.945363529664385e-06,
+      "loss": 0.3671,
+      "step": 320
+    },
+    {
+      "epoch": 0.2896828344351185,
+      "grad_norm": 0.06560525566792794,
+      "learning_rate": 9.93947291103304e-06,
+      "loss": 0.3872,
+      "step": 325
+    },
+    {
+      "epoch": 0.294139493426428,
+      "grad_norm": 0.051890916918650776,
+      "learning_rate": 9.933282716848001e-06,
+      "loss": 0.3881,
+      "step": 330
+    },
+    {
+      "epoch": 0.2985961524177375,
+      "grad_norm": 0.05177493540298683,
+      "learning_rate": 9.92679332254019e-06,
+      "loss": 0.3688,
+      "step": 335
+    },
+    {
+      "epoch": 0.303052811409047,
+      "grad_norm": 0.05169465457227038,
+      "learning_rate": 9.920005121686802e-06,
+      "loss": 0.3742,
+      "step": 340
+    },
+    {
+      "epoch": 0.30750947040035653,
+      "grad_norm": 0.05433225521681918,
+      "learning_rate": 9.912918525987437e-06,
+      "loss": 0.3672,
+      "step": 345
+    },
+    {
+      "epoch": 0.31196612939166607,
+      "grad_norm": 0.05227372498869847,
+      "learning_rate": 9.905533965239133e-06,
+      "loss": 0.3674,
+      "step": 350
+    },
+    {
+      "epoch": 0.31642278838297555,
+      "grad_norm": 0.04827464212259707,
+      "learning_rate": 9.897851887310304e-06,
+      "loss": 0.386,
+      "step": 355
+    },
+    {
+      "epoch": 0.3208794473742851,
+      "grad_norm": 0.04786866328513665,
+      "learning_rate": 9.88987275811356e-06,
+      "loss": 0.3888,
+      "step": 360
+    },
+    {
+      "epoch": 0.32533610636559457,
+      "grad_norm": 0.05117403335251474,
+      "learning_rate": 9.881597061577473e-06,
+      "loss": 0.371,
+      "step": 365
+    },
+    {
+      "epoch": 0.3297927653569041,
+      "grad_norm": 0.05209023655644307,
+      "learning_rate": 9.873025299617207e-06,
+      "loss": 0.3554,
+      "step": 370
+    },
+    {
+      "epoch": 0.33424942434821364,
+      "grad_norm": 0.04620493946724755,
+      "learning_rate": 9.86415799210409e-06,
+      "loss": 0.339,
+      "step": 375
+    },
+    {
+      "epoch": 0.3387060833395231,
+      "grad_norm": 0.04972442705458662,
+      "learning_rate": 9.854995676834078e-06,
+      "loss": 0.3381,
+      "step": 380
+    },
+    {
+      "epoch": 0.34316274233083266,
+      "grad_norm": 0.04902183301719761,
+      "learning_rate": 9.845538909495142e-06,
+      "loss": 0.3473,
+      "step": 385
+    },
+    {
+      "epoch": 0.34761940132214214,
+      "grad_norm": 0.048588732980178,
+      "learning_rate": 9.835788263633559e-06,
+      "loss": 0.3715,
+      "step": 390
+    },
+    {
+      "epoch": 0.3520760603134517,
+      "grad_norm": 0.0518211854230867,
+      "learning_rate": 9.825744330619136e-06,
+      "loss": 0.335,
+      "step": 395
+    },
+    {
+      "epoch": 0.3565327193047612,
+      "grad_norm": 0.04470995877402061,
+      "learning_rate": 9.815407719609336e-06,
+      "loss": 0.3576,
+      "step": 400
+    },
+    {
+      "epoch": 0.3609893782960707,
+      "grad_norm": 0.046718917610627575,
+      "learning_rate": 9.804779057512337e-06,
+      "loss": 0.3844,
+      "step": 405
+    },
+    {
+      "epoch": 0.36544603728738023,
+      "grad_norm": 0.04487868027034623,
+      "learning_rate": 9.793858988949013e-06,
+      "loss": 0.3651,
+      "step": 410
+    },
+    {
+      "epoch": 0.36990269627868977,
+      "grad_norm": 0.04508769734592565,
+      "learning_rate": 9.782648176213832e-06,
+      "loss": 0.3327,
+      "step": 415
+    },
+    {
+      "epoch": 0.37435935526999925,
+      "grad_norm": 0.047550358889489414,
+      "learning_rate": 9.77114729923469e-06,
+      "loss": 0.3845,
+      "step": 420
+    },
+    {
+      "epoch": 0.3788160142613088,
+      "grad_norm": 0.04522521563643231,
+      "learning_rate": 9.759357055531677e-06,
+      "loss": 0.3758,
+      "step": 425
+    },
+    {
+      "epoch": 0.38327267325261827,
+      "grad_norm": 0.046807592924263536,
+      "learning_rate": 9.747278160174773e-06,
+      "loss": 0.3684,
+      "step": 430
+    },
+    {
+      "epoch": 0.3877293322439278,
+      "grad_norm": 0.04945346042475437,
+      "learning_rate": 9.734911345740476e-06,
+      "loss": 0.374,
+      "step": 435
+    },
+    {
+      "epoch": 0.39218599123523734,
+      "grad_norm": 0.04507829141189117,
+      "learning_rate": 9.72225736226737e-06,
+      "loss": 0.3719,
+      "step": 440
+    },
+    {
+      "epoch": 0.3966426502265468,
+      "grad_norm": 0.05375175462388905,
+      "learning_rate": 9.709316977210641e-06,
+      "loss": 0.3738,
+      "step": 445
+    },
+    {
+      "epoch": 0.40109930921785636,
+      "grad_norm": 0.04178366229734565,
+      "learning_rate": 9.696090975395535e-06,
+      "loss": 0.35,
+      "step": 450
+    },
+    {
+      "epoch": 0.40555596820916584,
+      "grad_norm": 0.04307772924393916,
+      "learning_rate": 9.682580158969744e-06,
+      "loss": 0.3647,
+      "step": 455
+    },
+    {
+      "epoch": 0.4100126272004754,
+      "grad_norm": 0.04607844523886918,
+      "learning_rate": 9.66878534735477e-06,
+      "loss": 0.3422,
+      "step": 460
+    },
+    {
+      "epoch": 0.4144692861917849,
+      "grad_norm": 0.042361601709353026,
+      "learning_rate": 9.654707377196226e-06,
+      "loss": 0.3282,
+      "step": 465
+    },
+    {
+      "epoch": 0.4189259451830944,
+      "grad_norm": 0.05012304389062508,
+      "learning_rate": 9.640347102313086e-06,
+      "loss": 0.3872,
+      "step": 470
+    },
+    {
+      "epoch": 0.42338260417440393,
+      "grad_norm": 0.04177143585248632,
+      "learning_rate": 9.625705393645913e-06,
+      "loss": 0.332,
+      "step": 475
+    },
+    {
+      "epoch": 0.4278392631657134,
+      "grad_norm": 0.04105439567860185,
+      "learning_rate": 9.61078313920402e-06,
+      "loss": 0.3683,
+      "step": 480
+    },
+    {
+      "epoch": 0.43229592215702295,
+      "grad_norm": 0.04188596881105404,
+      "learning_rate": 9.595581244011638e-06,
+      "loss": 0.3764,
+      "step": 485
+    },
+    {
+      "epoch": 0.4367525811483325,
+      "grad_norm": 0.04374077499179829,
+      "learning_rate": 9.580100630053e-06,
+      "loss": 0.3585,
+      "step": 490
+    },
+    {
+      "epoch": 0.44120924013964197,
+      "grad_norm": 0.0435642556725744,
+      "learning_rate": 9.564342236216444e-06,
+      "loss": 0.3673,
+      "step": 495
+    },
+    {
+      "epoch": 0.4456658991309515,
+      "grad_norm": 0.04616615791848655,
+      "learning_rate": 9.54830701823746e-06,
+      "loss": 0.343,
+      "step": 500
+    },
+    {
+      "epoch": 0.450122558122261,
+      "grad_norm": 0.05116268160745142,
+      "learning_rate": 9.531995948640722e-06,
+      "loss": 0.3682,
+      "step": 505
+    },
+    {
+      "epoch": 0.4545792171135705,
+      "grad_norm": 0.045000388036651476,
+      "learning_rate": 9.515410016681119e-06,
+      "loss": 0.3673,
+      "step": 510
+    },
+    {
+      "epoch": 0.45903587610488006,
+      "grad_norm": 0.039981904676462336,
+      "learning_rate": 9.498550228283745e-06,
+      "loss": 0.3573,
+      "step": 515
+    },
+    {
+      "epoch": 0.46349253509618954,
+      "grad_norm": 0.05079247509194735,
+      "learning_rate": 9.48141760598289e-06,
+      "loss": 0.3358,
+      "step": 520
+    },
+    {
+      "epoch": 0.4679491940874991,
+      "grad_norm": 0.04339754696474626,
+      "learning_rate": 9.464013188860034e-06,
+      "loss": 0.3697,
+      "step": 525
+    },
+    {
+      "epoch": 0.4724058530788086,
+      "grad_norm": 0.05672032368874533,
+      "learning_rate": 9.44633803248082e-06,
+      "loss": 0.3609,
+      "step": 530
+    },
+    {
+      "epoch": 0.4768625120701181,
+      "grad_norm": 0.03968689567244294,
+      "learning_rate": 9.428393208831035e-06,
+      "loss": 0.3782,
+      "step": 535
+    },
+    {
+      "epoch": 0.48131917106142763,
+      "grad_norm": 0.03823591428746807,
+      "learning_rate": 9.410179806251597e-06,
+      "loss": 0.3676,
+      "step": 540
+    },
+    {
+      "epoch": 0.4857758300527371,
+      "grad_norm": 0.04953625328978311,
+      "learning_rate": 9.391698929372545e-06,
+      "loss": 0.3843,
+      "step": 545
+    },
+    {
+      "epoch": 0.49023248904404665,
+      "grad_norm": 0.043174962416537774,
+      "learning_rate": 9.372951699046048e-06,
+      "loss": 0.3537,
+      "step": 550
+    },
+    {
+      "epoch": 0.4946891480353562,
+      "grad_norm": 0.037737887971063026,
+      "learning_rate": 9.353939252278425e-06,
+      "loss": 0.3559,
+      "step": 555
+    },
+    {
+      "epoch": 0.49914580702666567,
+      "grad_norm": 0.03944313396062169,
+      "learning_rate": 9.334662742161185e-06,
+      "loss": 0.3486,
+      "step": 560
+    },
+    {
+      "epoch": 0.5036024660179752,
+      "grad_norm": 0.040982285416120506,
+      "learning_rate": 9.315123337801088e-06,
+      "loss": 0.3833,
+      "step": 565
+    },
+    {
+      "epoch": 0.5080591250092847,
+      "grad_norm": 0.05250003442053583,
+      "learning_rate": 9.295322224249251e-06,
+      "loss": 0.3835,
+      "step": 570
+    },
+    {
+      "epoch": 0.5125157840005943,
+      "grad_norm": 0.04762096881101235,
+      "learning_rate": 9.275260602429268e-06,
+      "loss": 0.3655,
+      "step": 575
+    },
+    {
+      "epoch": 0.5169724429919037,
+      "grad_norm": 0.04042638366958117,
+      "learning_rate": 9.254939689064374e-06,
+      "loss": 0.3524,
+      "step": 580
+    },
+    {
+      "epoch": 0.5214291019832132,
+      "grad_norm": 0.03853478933299392,
+      "learning_rate": 9.234360716603654e-06,
+      "loss": 0.3344,
+      "step": 585
+    },
+    {
+      "epoch": 0.5258857609745228,
+      "grad_norm": 0.04253231208243496,
+      "learning_rate": 9.213524933147297e-06,
+      "loss": 0.3518,
+      "step": 590
+    },
+    {
+      "epoch": 0.5303424199658323,
+      "grad_norm": 0.03781916769626258,
+      "learning_rate": 9.1924336023709e-06,
+      "loss": 0.3581,
+      "step": 595
+    },
+    {
+      "epoch": 0.5347990789571418,
+      "grad_norm": 0.042956152801003476,
+      "learning_rate": 9.171088003448816e-06,
+      "loss": 0.3751,
+      "step": 600
+    },
+    {
+      "epoch": 0.5392557379484513,
+      "grad_norm": 0.042733495391241834,
+      "learning_rate": 9.149489430976592e-06,
+      "loss": 0.3735,
+      "step": 605
+    },
+    {
+      "epoch": 0.5437123969397608,
+      "grad_norm": 0.038555605729189334,
+      "learning_rate": 9.12763919489244e-06,
+      "loss": 0.3343,
+      "step": 610
+    },
+    {
+      "epoch": 0.5481690559310703,
+      "grad_norm": 0.04878126396745322,
+      "learning_rate": 9.105538620397786e-06,
+      "loss": 0.3693,
+      "step": 615
+    },
+    {
+      "epoch": 0.5526257149223799,
+      "grad_norm": 0.0388842791468199,
+      "learning_rate": 9.083189047876917e-06,
+      "loss": 0.3319,
+      "step": 620
+    },
+    {
+      "epoch": 0.5570823739136894,
+      "grad_norm": 0.045281525903800586,
+      "learning_rate": 9.060591832815663e-06,
+      "loss": 0.3483,
+      "step": 625
+    },
+    {
+      "epoch": 0.5615390329049988,
+      "grad_norm": 0.037306006153875235,
+      "learning_rate": 9.037748345719206e-06,
+      "loss": 0.3715,
+      "step": 630
+    },
+    {
+      "epoch": 0.5659956918963084,
+      "grad_norm": 0.04232483585848596,
+      "learning_rate": 9.014659972028954e-06,
+      "loss": 0.3784,
+      "step": 635
+    },
+    {
+      "epoch": 0.5704523508876179,
+      "grad_norm": 0.04366418393202621,
+      "learning_rate": 8.991328112038508e-06,
+      "loss": 0.3421,
+      "step": 640
+    },
+    {
+      "epoch": 0.5749090098789275,
+      "grad_norm": 0.042775684521190016,
+      "learning_rate": 8.96775418080875e-06,
+      "loss": 0.3641,
+      "step": 645
+    },
+    {
+      "epoch": 0.579365668870237,
+      "grad_norm": 0.03905324730933948,
+      "learning_rate": 8.943939608082008e-06,
+      "loss": 0.326,
+      "step": 650
+    },
+    {
+      "epoch": 0.5838223278615464,
+      "grad_norm": 0.0439109485141227,
+      "learning_rate": 8.919885838195346e-06,
+      "loss": 0.38,
+      "step": 655
+    },
+    {
+      "epoch": 0.588278986852856,
+      "grad_norm": 0.040278188616367915,
+      "learning_rate": 8.895594329992971e-06,
+      "loss": 0.3554,
+      "step": 660
+    },
+    {
+      "epoch": 0.5927356458441655,
+      "grad_norm": 0.04296489937369988,
+      "learning_rate": 8.871066556737749e-06,
+      "loss": 0.3515,
+      "step": 665
+    },
+    {
+      "epoch": 0.597192304835475,
+      "grad_norm": 0.03219193900520065,
+      "learning_rate": 8.846304006021853e-06,
+      "loss": 0.3065,
+      "step": 670
+    },
+    {
+      "epoch": 0.6016489638267846,
+      "grad_norm": 0.03750987603517473,
+      "learning_rate": 8.82130817967655e-06,
+      "loss": 0.3753,
+      "step": 675
+    },
+    {
+      "epoch": 0.606105622818094,
+      "grad_norm": 0.045258173403080484,
+      "learning_rate": 8.796080593681104e-06,
+      "loss": 0.375,
+      "step": 680
+    },
+    {
+      "epoch": 0.6105622818094035,
+      "grad_norm": 0.03803993220538302,
+      "learning_rate": 8.77062277807084e-06,
+      "loss": 0.356,
+      "step": 685
+    },
+    {
+      "epoch": 0.6150189408007131,
+      "grad_norm": 0.04095600232061625,
+      "learning_rate": 8.744936276844348e-06,
+      "loss": 0.3482,
+      "step": 690
+    },
+    {
+      "epoch": 0.6194755997920226,
+      "grad_norm": 0.04108431793653308,
+      "learning_rate": 8.719022647869839e-06,
+      "loss": 0.3558,
+      "step": 695
+    },
+    {
+      "epoch": 0.6239322587833321,
+      "grad_norm": 0.04300826921850201,
+      "learning_rate": 8.692883462790664e-06,
+      "loss": 0.347,
+      "step": 700
+    },
+    {
+      "epoch": 0.6283889177746416,
+      "grad_norm": 0.04147196857931913,
+      "learning_rate": 8.666520306929987e-06,
+      "loss": 0.3391,
+      "step": 705
+    },
+    {
+      "epoch": 0.6328455767659511,
+      "grad_norm": 0.03487134011785261,
+      "learning_rate": 8.639934779194647e-06,
+      "loss": 0.3232,
+      "step": 710
+    },
+    {
+      "epoch": 0.6373022357572606,
+      "grad_norm": 0.03649852892645952,
+      "learning_rate": 8.613128491978181e-06,
+      "loss": 0.3223,
+      "step": 715
+    },
+    {
+      "epoch": 0.6417588947485702,
+      "grad_norm": 0.04596879876204484,
+      "learning_rate": 8.586103071063034e-06,
+      "loss": 0.3733,
+      "step": 720
+    },
+    {
+      "epoch": 0.6462155537398797,
+      "grad_norm": 0.04225087710012865,
+      "learning_rate": 8.558860155521948e-06,
+      "loss": 0.3584,
+      "step": 725
+    },
+    {
+      "epoch": 0.6506722127311891,
+      "grad_norm": 0.040614068313829625,
+      "learning_rate": 8.53140139761857e-06,
+      "loss": 0.3778,
+      "step": 730
+    },
+    {
+      "epoch": 0.6551288717224987,
+      "grad_norm": 0.038923901123470606,
+      "learning_rate": 8.50372846270723e-06,
+      "loss": 0.355,
+      "step": 735
+    },
+    {
+      "epoch": 0.6595855307138082,
+      "grad_norm": 0.04003805383028198,
+      "learning_rate": 8.475843029131942e-06,
+      "loss": 0.3446,
+      "step": 740
+    },
+    {
+      "epoch": 0.6640421897051177,
+      "grad_norm": 0.03817113093765007,
+      "learning_rate": 8.447746788124618e-06,
+      "loss": 0.3533,
+      "step": 745
+    },
+    {
+      "epoch": 0.6684988486964273,
+      "grad_norm": 0.03946386120647576,
+      "learning_rate": 8.419441443702485e-06,
+      "loss": 0.3385,
+      "step": 750
+    },
+    {
+      "epoch": 0.6729555076877367,
+      "grad_norm": 0.04594980639856022,
+      "learning_rate": 8.390928712564754e-06,
+      "loss": 0.3468,
+      "step": 755
+    },
+    {
+      "epoch": 0.6774121666790462,
+      "grad_norm": 0.037734409170981406,
+      "learning_rate": 8.362210323988486e-06,
+      "loss": 0.3142,
+      "step": 760
+    },
+    {
+      "epoch": 0.6818688256703558,
+      "grad_norm": 0.04135989239417575,
+      "learning_rate": 8.33328801972373e-06,
+      "loss": 0.3512,
+      "step": 765
+    },
+    {
+      "epoch": 0.6863254846616653,
+      "grad_norm": 0.040399706529750154,
+      "learning_rate": 8.30416355388787e-06,
+      "loss": 0.3441,
+      "step": 770
+    },
+    {
+      "epoch": 0.6907821436529749,
+      "grad_norm": 0.04632767114532932,
+      "learning_rate": 8.274838692859249e-06,
+      "loss": 0.3492,
+      "step": 775
+    },
+    {
+      "epoch": 0.6952388026442843,
+      "grad_norm": 0.0466278822946521,
+      "learning_rate": 8.245315215170036e-06,
+      "loss": 0.3634,
+      "step": 780
+    },
+    {
+      "epoch": 0.6996954616355938,
+      "grad_norm": 0.03854497108096806,
+      "learning_rate": 8.215594911398366e-06,
+      "loss": 0.3818,
+      "step": 785
+    },
+    {
+      "epoch": 0.7041521206269034,
+      "grad_norm": 0.03807528541379026,
+      "learning_rate": 8.185679584059733e-06,
+      "loss": 0.3399,
+      "step": 790
+    },
+    {
+      "epoch": 0.7086087796182129,
+      "grad_norm": 0.039364528432836096,
+      "learning_rate": 8.155571047497675e-06,
+      "loss": 0.3471,
+      "step": 795
+    },
+    {
+      "epoch": 0.7130654386095224,
+      "grad_norm": 0.04009146302797121,
+      "learning_rate": 8.125271127773728e-06,
+      "loss": 0.317,
+      "step": 800
+    },
+    {
+      "epoch": 0.717522097600832,
+      "grad_norm": 0.037371893337503514,
+      "learning_rate": 8.09478166255669e-06,
+      "loss": 0.3371,
+      "step": 805
+    },
+    {
+      "epoch": 0.7219787565921414,
+      "grad_norm": 0.034113185631526655,
+      "learning_rate": 8.064104501011154e-06,
+      "loss": 0.3316,
+      "step": 810
+    },
+    {
+      "epoch": 0.7264354155834509,
+      "grad_norm": 0.041522627293234436,
+      "learning_rate": 8.033241503685366e-06,
+      "loss": 0.346,
+      "step": 815
+    },
+    {
+      "epoch": 0.7308920745747605,
+      "grad_norm": 0.04352859369847954,
+      "learning_rate": 8.00219454239838e-06,
+      "loss": 0.3493,
+      "step": 820
+    },
+    {
+      "epoch": 0.73534873356607,
+      "grad_norm": 0.040392710281690065,
+      "learning_rate": 7.970965500126534e-06,
+      "loss": 0.3506,
+      "step": 825
+    },
+    {
+      "epoch": 0.7398053925573795,
+      "grad_norm": 0.037788817713187726,
+      "learning_rate": 7.93955627088925e-06,
+      "loss": 0.3449,
+      "step": 830
+    },
+    {
+      "epoch": 0.744262051548689,
+      "grad_norm": 0.03913978671424209,
+      "learning_rate": 7.907968759634165e-06,
+      "loss": 0.3416,
+      "step": 835
+    },
+    {
+      "epoch": 0.7487187105399985,
+      "grad_norm": 0.03647678211671544,
+      "learning_rate": 7.876204882121592e-06,
+      "loss": 0.3632,
+      "step": 840
+    },
+    {
+      "epoch": 0.753175369531308,
+      "grad_norm": 0.03824752767359855,
+      "learning_rate": 7.844266564808333e-06,
+      "loss": 0.3506,
+      "step": 845
+    },
+    {
+      "epoch": 0.7576320285226176,
+      "grad_norm": 0.04193412196826429,
+      "learning_rate": 7.812155744730842e-06,
+      "loss": 0.3514,
+      "step": 850
+    },
+    {
+      "epoch": 0.7620886875139271,
+      "grad_norm": 0.03719881876463841,
+      "learning_rate": 7.779874369387747e-06,
+      "loss": 0.3744,
+      "step": 855
+    },
+    {
+      "epoch": 0.7665453465052365,
+      "grad_norm": 0.039523606403741154,
+      "learning_rate": 7.747424396621728e-06,
+      "loss": 0.3464,
+      "step": 860
+    },
+    {
+      "epoch": 0.7710020054965461,
+      "grad_norm": 0.038967790741718966,
+      "learning_rate": 7.71480779450078e-06,
+      "loss": 0.3522,
+      "step": 865
+    },
+    {
+      "epoch": 0.7754586644878556,
+      "grad_norm": 0.0338399453339563,
+      "learning_rate": 7.682026541198859e-06,
+      "loss": 0.3175,
+      "step": 870
+    },
+    {
+      "epoch": 0.7799153234791651,
+      "grad_norm": 0.03838893499453238,
+      "learning_rate": 7.649082624875889e-06,
+      "loss": 0.371,
+      "step": 875
+    },
+    {
+      "epoch": 0.7843719824704747,
+      "grad_norm": 0.03582979505427013,
+      "learning_rate": 7.615978043557195e-06,
+      "loss": 0.3545,
+      "step": 880
+    },
+    {
+      "epoch": 0.7888286414617841,
+      "grad_norm": 0.03627985350213129,
+      "learning_rate": 7.582714805012326e-06,
+      "loss": 0.3474,
+      "step": 885
+    },
+    {
+      "epoch": 0.7932853004530936,
+      "grad_norm": 0.03850554835854682,
+      "learning_rate": 7.549294926633273e-06,
+      "loss": 0.3464,
+      "step": 890
+    },
+    {
+      "epoch": 0.7977419594444032,
+      "grad_norm": 0.03875905385241387,
+      "learning_rate": 7.515720435312124e-06,
+      "loss": 0.3536,
+      "step": 895
+    },
+    {
+      "epoch": 0.8021986184357127,
+      "grad_norm": 0.03902115614104229,
+      "learning_rate": 7.481993367318139e-06,
+      "loss": 0.3494,
+      "step": 900
+    },
+    {
+      "epoch": 0.8066552774270223,
+      "grad_norm": 0.042663509463480305,
+      "learning_rate": 7.4481157681742376e-06,
+      "loss": 0.3693,
+      "step": 905
+    },
+    {
+      "epoch": 0.8111119364183317,
+      "grad_norm": 0.03463878522652425,
+      "learning_rate": 7.414089692532953e-06,
+      "loss": 0.3597,
+      "step": 910
+    },
+    {
+      "epoch": 0.8155685954096412,
+      "grad_norm": 0.04096150483153926,
+      "learning_rate": 7.379917204051812e-06,
+      "loss": 0.3594,
+      "step": 915
+    },
+    {
+      "epoch": 0.8200252544009508,
+      "grad_norm": 0.04402866398417241,
+      "learning_rate": 7.3456003752681755e-06,
+      "loss": 0.3414,
+      "step": 920
+    },
+    {
+      "epoch": 0.8244819133922603,
+      "grad_norm": 0.04139811223309286,
+      "learning_rate": 7.311141287473545e-06,
+      "loss": 0.3224,
+      "step": 925
+    },
+    {
+      "epoch": 0.8289385723835698,
+      "grad_norm": 0.06645909647569262,
+      "learning_rate": 7.276542030587328e-06,
+      "loss": 0.3456,
+      "step": 930
+    },
+    {
+      "epoch": 0.8333952313748793,
+      "grad_norm": 0.044636161342359676,
+      "learning_rate": 7.2418047030300905e-06,
+      "loss": 0.3353,
+      "step": 935
+    },
+    {
+      "epoch": 0.8378518903661888,
+      "grad_norm": 0.035318060235713856,
+      "learning_rate": 7.206931411596288e-06,
+      "loss": 0.3288,
+      "step": 940
+    },
+    {
+      "epoch": 0.8423085493574983,
+      "grad_norm": 0.03828050355505084,
+      "learning_rate": 7.171924271326483e-06,
+      "loss": 0.3707,
+      "step": 945
+    },
+    {
+      "epoch": 0.8467652083488079,
+      "grad_norm": 0.042224528093265754,
+      "learning_rate": 7.136785405379088e-06,
+      "loss": 0.3595,
+      "step": 950
+    },
+    {
+      "epoch": 0.8512218673401174,
+      "grad_norm": 0.04480625231480598,
+      "learning_rate": 7.101516944901576e-06,
+      "loss": 0.3619,
+      "step": 955
+    },
+    {
+      "epoch": 0.8556785263314268,
+      "grad_norm": 0.03576964869540681,
+      "learning_rate": 7.066121028901236e-06,
+      "loss": 0.3464,
+      "step": 960
+    },
+    {
+      "epoch": 0.8601351853227364,
+      "grad_norm": 0.030991978553480678,
+      "learning_rate": 7.030599804115452e-06,
+      "loss": 0.3607,
+      "step": 965
+    },
+    {
+      "epoch": 0.8645918443140459,
+      "grad_norm": 0.03650657693648493,
+      "learning_rate": 6.99495542488149e-06,
+      "loss": 0.3547,
+      "step": 970
+    },
+    {
+      "epoch": 0.8690485033053554,
+      "grad_norm": 0.039958685112108004,
+      "learning_rate": 6.95919005300585e-06,
+      "loss": 0.3435,
+      "step": 975
+    },
+    {
+      "epoch": 0.873505162296665,
+      "grad_norm": 0.04077064091002527,
+      "learning_rate": 6.923305857633153e-06,
+      "loss": 0.3351,
+      "step": 980
+    },
+    {
+      "epoch": 0.8779618212879744,
+      "grad_norm": 0.03587466267665625,
+      "learning_rate": 6.887305015114576e-06,
+      "loss": 0.3512,
+      "step": 985
+    },
+    {
+      "epoch": 0.8824184802792839,
+      "grad_norm": 0.034539337349791706,
+      "learning_rate": 6.851189708875867e-06,
+      "loss": 0.3696,
+      "step": 990
+    },
+    {
+      "epoch": 0.8868751392705935,
+      "grad_norm": 0.038997841115035806,
+      "learning_rate": 6.8149621292849175e-06,
+      "loss": 0.3254,
+      "step": 995
+    },
+    {
+      "epoch": 0.891331798261903,
+      "grad_norm": 0.038220707196931394,
+      "learning_rate": 6.7786244735189186e-06,
+      "loss": 0.3629,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8957884572532125,
+      "grad_norm": 0.0434042294031072,
+      "learning_rate": 6.742178945431101e-06,
+      "loss": 0.3354,
+      "step": 1005
+    },
+    {
+      "epoch": 0.900245116244522,
+      "grad_norm": 0.03433600018730854,
+      "learning_rate": 6.705627755417083e-06,
+      "loss": 0.3963,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9047017752358315,
+      "grad_norm": 0.03903725290243943,
+      "learning_rate": 6.668973120280797e-06,
+      "loss": 0.3546,
+      "step": 1015
+    },
+    {
+      "epoch": 0.909158434227141,
+      "grad_norm": 0.038365695036849674,
+      "learning_rate": 6.632217263100053e-06,
+      "loss": 0.3375,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9136150932184506,
+      "grad_norm": 0.03990475305692419,
+      "learning_rate": 6.5953624130917035e-06,
+      "loss": 0.3331,
+      "step": 1025
+    },
+    {
+      "epoch": 0.9180717522097601,
+      "grad_norm": 0.040794399359075834,
+      "learning_rate": 6.558410805476451e-06,
+      "loss": 0.3458,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9225284112010697,
+      "grad_norm": 0.03912702525863214,
+      "learning_rate": 6.521364681343273e-06,
+      "loss": 0.3524,
+      "step": 1035
+    },
+    {
+      "epoch": 0.9269850701923791,
+      "grad_norm": 0.03661850369975111,
+      "learning_rate": 6.484226287513512e-06,
+      "loss": 0.3718,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9314417291836886,
+      "grad_norm": 0.03440847203779226,
+      "learning_rate": 6.446997876404603e-06,
+      "loss": 0.3533,
+      "step": 1045
+    },
+    {
+      "epoch": 0.9358983881749982,
+      "grad_norm": 0.037084675468021515,
+      "learning_rate": 6.409681705893461e-06,
+      "loss": 0.3707,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9403550471663077,
+      "grad_norm": 0.03106927125420908,
+      "learning_rate": 6.37228003917955e-06,
+      "loss": 0.3331,
+      "step": 1055
+    },
+    {
+      "epoch": 0.9448117061576172,
+      "grad_norm": 0.043893802285259104,
+      "learning_rate": 6.3347951446476194e-06,
+      "loss": 0.3375,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9492683651489267,
+      "grad_norm": 0.03789346876693591,
+      "learning_rate": 6.297229295730125e-06,
+      "loss": 0.3574,
+      "step": 1065
+    },
+    {
+      "epoch": 0.9537250241402362,
+      "grad_norm": 0.04123920807743081,
+      "learning_rate": 6.2595847707693505e-06,
+      "loss": 0.3607,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9581816831315457,
+      "grad_norm": 0.03746001686079855,
+      "learning_rate": 6.221863852879224e-06,
+      "loss": 0.3497,
+      "step": 1075
+    },
+    {
+      "epoch": 0.9626383421228553,
+      "grad_norm": 0.037332308666625603,
+      "learning_rate": 6.184068829806853e-06,
+      "loss": 0.3406,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9670950011141648,
+      "grad_norm": 0.03600032344614023,
+      "learning_rate": 6.146201993793772e-06,
+      "loss": 0.334,
+      "step": 1085
+    },
+    {
+      "epoch": 0.9715516601054742,
+      "grad_norm": 0.03913531342479123,
+      "learning_rate": 6.10826564143692e-06,
+      "loss": 0.3239,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9760083190967838,
+      "grad_norm": 0.044657313605693603,
+      "learning_rate": 6.0702620735493535e-06,
+      "loss": 0.3517,
+      "step": 1095
+    },
+    {
+      "epoch": 0.9804649780880933,
+      "grad_norm": 0.036697071260256314,
+      "learning_rate": 6.0321935950207e-06,
+      "loss": 0.364,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9849216370794028,
+      "grad_norm": 0.047007092034447036,
+      "learning_rate": 5.994062514677377e-06,
+      "loss": 0.3365,
+      "step": 1105
+    },
+    {
+      "epoch": 0.9893782960707124,
+      "grad_norm": 0.038567817770514705,
+      "learning_rate": 5.9558711451425555e-06,
+      "loss": 0.3437,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9938349550620218,
+      "grad_norm": 0.046535006533488465,
+      "learning_rate": 5.917621802695903e-06,
+      "loss": 0.3674,
+      "step": 1115
+    },
+    {
+      "epoch": 0.9982916140533313,
+      "grad_norm": 0.044782400881786595,
+      "learning_rate": 5.879316807133103e-06,
+      "loss": 0.3539,
+      "step": 1120
+    },
+    {
+      "epoch": 0.9991829458515933,
+      "eval_loss": 0.3121582567691803,
+      "eval_runtime": 28.1501,
+      "eval_samples_per_second": 19.325,
+      "eval_steps_per_second": 4.831,
+      "step": 1121
+    },
+    {
+      "epoch": 1.0035653271930476,
+      "grad_norm": 0.035018958725684814,
+      "learning_rate": 5.840958481625163e-06,
+      "loss": 0.3768,
+      "step": 1125
+    },
+    {
+      "epoch": 1.0080219861843571,
+      "grad_norm": 0.08275303281391562,
+      "learning_rate": 5.8025491525775125e-06,
+      "loss": 0.3373,
+      "step": 1130
+    },
+    {
+      "epoch": 1.0124786451756667,
+      "grad_norm": 0.036690917598704145,
+      "learning_rate": 5.764091149488912e-06,
+      "loss": 0.3191,
+      "step": 1135
+    },
+    {
+      "epoch": 1.0169353041669762,
+      "grad_norm": 0.038089309373433904,
+      "learning_rate": 5.725586804810166e-06,
+      "loss": 0.3377,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0213919631582857,
+      "grad_norm": 0.04219155515782442,
+      "learning_rate": 5.687038453802663e-06,
+      "loss": 0.33,
+      "step": 1145
+    },
+    {
+      "epoch": 1.0258486221495953,
+      "grad_norm": 0.03643779050650904,
+      "learning_rate": 5.648448434396747e-06,
+      "loss": 0.3352,
+      "step": 1150
+    },
+    {
+      "epoch": 1.0303052811409048,
+      "grad_norm": 0.044990286569605006,
+      "learning_rate": 5.609819087049923e-06,
+      "loss": 0.3233,
+      "step": 1155
+    },
+    {
+      "epoch": 1.0347619401322141,
+      "grad_norm": 0.0673142495663998,
+      "learning_rate": 5.571152754604901e-06,
+      "loss": 0.3164,
+      "step": 1160
+    },
+    {
+      "epoch": 1.0392185991235237,
+      "grad_norm": 0.044924920507469504,
+      "learning_rate": 5.5324517821475165e-06,
+      "loss": 0.3234,
+      "step": 1165
+    },
+    {
+      "epoch": 1.0436752581148332,
+      "grad_norm": 0.04520885855234551,
+      "learning_rate": 5.493718516864496e-06,
+      "loss": 0.3572,
+      "step": 1170
+    },
+    {
+      "epoch": 1.0481319171061427,
+      "grad_norm": 0.0488015684618307,
+      "learning_rate": 5.454955307901103e-06,
+      "loss": 0.3286,
+      "step": 1175
+    },
+    {
+      "epoch": 1.0525885760974523,
+      "grad_norm": 0.043929046851137146,
+      "learning_rate": 5.416164506218662e-06,
+      "loss": 0.3347,
+      "step": 1180
+    },
+    {
+      "epoch": 1.0570452350887618,
+      "grad_norm": 0.039430384622077694,
+      "learning_rate": 5.3773484644519825e-06,
+      "loss": 0.346,
+      "step": 1185
+    },
+    {
+      "epoch": 1.0615018940800713,
+      "grad_norm": 0.050917021723215446,
+      "learning_rate": 5.338509536766662e-06,
+      "loss": 0.3502,
+      "step": 1190
+    },
+    {
+      "epoch": 1.0659585530713809,
+      "grad_norm": 0.0432190687785534,
+      "learning_rate": 5.299650078716313e-06,
+      "loss": 0.343,
+      "step": 1195
+    },
+    {
+      "epoch": 1.0704152120626904,
+      "grad_norm": 0.05235380991950498,
+      "learning_rate": 5.260772447099704e-06,
+      "loss": 0.3179,
+      "step": 1200
+    },
+    {
+      "epoch": 1.074871871054,
+      "grad_norm": 0.043917180636865144,
+      "learning_rate": 5.2218789998178125e-06,
+      "loss": 0.3098,
+      "step": 1205
+    },
+    {
+      "epoch": 1.0793285300453093,
+      "grad_norm": 0.039598233352694974,
+      "learning_rate": 5.182972095730828e-06,
+      "loss": 0.3299,
+      "step": 1210
+    },
+    {
+      "epoch": 1.0837851890366188,
+      "grad_norm": 0.03914796341413229,
+      "learning_rate": 5.144054094515088e-06,
+      "loss": 0.3191,
+      "step": 1215
+    },
+    {
+      "epoch": 1.0882418480279283,
+      "grad_norm": 0.04563116912150565,
+      "learning_rate": 5.1051273565199564e-06,
+      "loss": 0.3465,
+      "step": 1220
+    },
+    {
+      "epoch": 1.0926985070192379,
+      "grad_norm": 0.04488310022064193,
+      "learning_rate": 5.0661942426246825e-06,
+      "loss": 0.3336,
+      "step": 1225
+    },
+    {
+      "epoch": 1.0971551660105474,
+      "grad_norm": 0.045624300677554144,
+      "learning_rate": 5.0272571140952076e-06,
+      "loss": 0.3366,
+      "step": 1230
+    },
+    {
+      "epoch": 1.101611825001857,
+      "grad_norm": 0.04547698828207826,
+      "learning_rate": 4.988318332440958e-06,
+      "loss": 0.3401,
+      "step": 1235
+    },
+    {
+      "epoch": 1.1060684839931665,
+      "grad_norm": 0.0352328063030309,
+      "learning_rate": 4.949380259271618e-06,
+      "loss": 0.3429,
+      "step": 1240
+    },
+    {
+      "epoch": 1.110525142984476,
+      "grad_norm": 0.03628153680973482,
+      "learning_rate": 4.910445256153909e-06,
+      "loss": 0.3685,
+      "step": 1245
+    },
+    {
+      "epoch": 1.1149818019757856,
+      "grad_norm": 0.05406284923018293,
+      "learning_rate": 4.871515684468348e-06,
+      "loss": 0.3255,
+      "step": 1250
+    },
+    {
+      "epoch": 1.119438460967095,
+      "grad_norm": 0.04417976412734551,
+      "learning_rate": 4.832593905266045e-06,
+      "loss": 0.3255,
+      "step": 1255
+    },
+    {
+      "epoch": 1.1238951199584046,
+      "grad_norm": 0.04882094138393501,
+      "learning_rate": 4.793682279125504e-06,
+      "loss": 0.3233,
+      "step": 1260
+    },
+    {
+      "epoch": 1.128351778949714,
+      "grad_norm": 0.04666808909953559,
+      "learning_rate": 4.754783166009443e-06,
+      "loss": 0.3381,
+      "step": 1265
+    },
+    {
+      "epoch": 1.1328084379410235,
+      "grad_norm": 0.0393273395144626,
+      "learning_rate": 4.715898925121683e-06,
+      "loss": 0.3362,
+      "step": 1270
+    },
+    {
+      "epoch": 1.137265096932333,
+      "grad_norm": 0.042614792670262726,
+      "learning_rate": 4.677031914764052e-06,
+      "loss": 0.3565,
+      "step": 1275
+    },
+    {
+      "epoch": 1.1417217559236426,
+      "grad_norm": 0.04265242813984368,
+      "learning_rate": 4.638184492193357e-06,
+      "loss": 0.3391,
+      "step": 1280
+    },
+    {
+      "epoch": 1.146178414914952,
+      "grad_norm": 0.05253572445021966,
+      "learning_rate": 4.59935901347842e-06,
+      "loss": 0.3444,
+      "step": 1285
+    },
+    {
+      "epoch": 1.1506350739062616,
+      "grad_norm": 0.04661513504414531,
+      "learning_rate": 4.560557833357188e-06,
+      "loss": 0.3324,
+      "step": 1290
+    },
+    {
+      "epoch": 1.1550917328975712,
+      "grad_norm": 0.05181632502738739,
+      "learning_rate": 4.521783305093906e-06,
+      "loss": 0.3593,
+      "step": 1295
+    },
+    {
+      "epoch": 1.1595483918888807,
+      "grad_norm": 0.043190087583387604,
+      "learning_rate": 4.483037780336411e-06,
+      "loss": 0.3313,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1640050508801902,
+      "grad_norm": 0.04699548343789582,
+      "learning_rate": 4.444323608973498e-06,
+      "loss": 0.3235,
+      "step": 1305
+    },
+    {
+      "epoch": 1.1684617098714996,
+      "grad_norm": 0.04832144947499993,
+      "learning_rate": 4.4056431389923925e-06,
+      "loss": 0.3249,
+      "step": 1310
+    },
+    {
+      "epoch": 1.172918368862809,
+      "grad_norm": 0.049877024800225496,
+      "learning_rate": 4.366998716336364e-06,
+      "loss": 0.3289,
+      "step": 1315
+    },
+    {
+      "epoch": 1.1773750278541186,
+      "grad_norm": 0.050518314153578,
+      "learning_rate": 4.328392684762432e-06,
+      "loss": 0.3227,
+      "step": 1320
+    },
+    {
+      "epoch": 1.1818316868454282,
+      "grad_norm": 0.05274930662575011,
+      "learning_rate": 4.289827385699225e-06,
+      "loss": 0.3389,
+      "step": 1325
+    },
+    {
+      "epoch": 1.1862883458367377,
+      "grad_norm": 0.04314769892456159,
+      "learning_rate": 4.251305158104973e-06,
+      "loss": 0.3325,
+      "step": 1330
+    },
+    {
+      "epoch": 1.1907450048280472,
+      "grad_norm": 0.05744060663520273,
+      "learning_rate": 4.212828338325655e-06,
+      "loss": 0.3501,
+      "step": 1335
+    },
+    {
+      "epoch": 1.1952016638193568,
+      "grad_norm": 0.04788383703548173,
+      "learning_rate": 4.174399259953292e-06,
+      "loss": 0.3182,
+      "step": 1340
+    },
+    {
+      "epoch": 1.1996583228106663,
+      "grad_norm": 0.05322839124311334,
+      "learning_rate": 4.136020253684426e-06,
+      "loss": 0.3236,
+      "step": 1345
+    },
+    {
+      "epoch": 1.2041149818019758,
+      "grad_norm": 0.04192717948800928,
+      "learning_rate": 4.097693647178765e-06,
+      "loss": 0.3116,
+      "step": 1350
+    },
+    {
+      "epoch": 1.2085716407932854,
+      "grad_norm": 0.07466924907391985,
+      "learning_rate": 4.059421764917998e-06,
+      "loss": 0.336,
+      "step": 1355
+    },
+    {
+      "epoch": 1.213028299784595,
+      "grad_norm": 0.047779612339586844,
+      "learning_rate": 4.021206928064837e-06,
+      "loss": 0.3199,
+      "step": 1360
+    },
+    {
+      "epoch": 1.2174849587759042,
+      "grad_norm": 0.04890716812809991,
+      "learning_rate": 3.983051454322227e-06,
+      "loss": 0.3042,
+      "step": 1365
+    },
+    {
+      "epoch": 1.2219416177672138,
+      "grad_norm": 0.05622057359534205,
+      "learning_rate": 3.944957657792779e-06,
+      "loss": 0.315,
+      "step": 1370
+    },
+    {
+      "epoch": 1.2263982767585233,
+      "grad_norm": 0.05816972903766055,
+      "learning_rate": 3.906927848838428e-06,
+      "loss": 0.3447,
+      "step": 1375
+    },
+    {
+      "epoch": 1.2308549357498328,
+      "grad_norm": 0.0521170519743598,
+      "learning_rate": 3.868964333940308e-06,
+      "loss": 0.3287,
+      "step": 1380
+    },
+    {
+      "epoch": 1.2353115947411424,
+      "grad_norm": 0.05613111708237626,
+      "learning_rate": 3.83106941555886e-06,
+      "loss": 0.3514,
+      "step": 1385
+    },
+    {
+      "epoch": 1.239768253732452,
+      "grad_norm": 0.05079823220287822,
+      "learning_rate": 3.7932453919942002e-06,
+      "loss": 0.2976,
+      "step": 1390
+    },
+    {
+      "epoch": 1.2442249127237615,
+      "grad_norm": 0.04588237737238143,
+      "learning_rate": 3.7554945572467262e-06,
+      "loss": 0.3429,
+      "step": 1395
+    },
+    {
+      "epoch": 1.248681571715071,
+      "grad_norm": 0.06835690002137525,
+      "learning_rate": 3.7178192008779746e-06,
+      "loss": 0.3251,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2531382307063805,
+      "grad_norm": 0.050609979224703276,
+      "learning_rate": 3.6802216078717825e-06,
+      "loss": 0.3403,
+      "step": 1405
+    },
+    {
+      "epoch": 1.2575948896976898,
+      "grad_norm": 0.053908001625159505,
+      "learning_rate": 3.642704058495691e-06,
+      "loss": 0.3237,
+      "step": 1410
+    },
+    {
+      "epoch": 1.2620515486889996,
+      "grad_norm": 0.06722754734917484,
+      "learning_rate": 3.6052688281626448e-06,
+      "loss": 0.3298,
+      "step": 1415
+    },
+    {
+      "epoch": 1.266508207680309,
+      "grad_norm": 0.04804813484670096,
+      "learning_rate": 3.5679181872930067e-06,
+      "loss": 0.3137,
+      "step": 1420
+    },
+    {
+      "epoch": 1.2709648666716185,
+      "grad_norm": 0.052833907520638754,
+      "learning_rate": 3.5306544011768414e-06,
+      "loss": 0.3503,
+      "step": 1425
+    },
+    {
+      "epoch": 1.275421525662928,
+      "grad_norm": 0.05272400381575242,
+      "learning_rate": 3.493479729836534e-06,
+      "loss": 0.3093,
+      "step": 1430
+    },
+    {
+      "epoch": 1.2798781846542375,
+      "grad_norm": 0.0580236610090227,
+      "learning_rate": 3.4563964278897267e-06,
+      "loss": 0.3576,
+      "step": 1435
+    },
+    {
+      "epoch": 1.284334843645547,
+      "grad_norm": 0.06013873751374385,
+      "learning_rate": 3.4194067444125645e-06,
+      "loss": 0.3231,
+      "step": 1440
+    },
+    {
+      "epoch": 1.2887915026368566,
+      "grad_norm": 0.056386412770539907,
+      "learning_rate": 3.3825129228033043e-06,
+      "loss": 0.3109,
+      "step": 1445
+    },
+    {
+      "epoch": 1.2932481616281661,
+      "grad_norm": 0.05917179185232147,
+      "learning_rate": 3.3457172006462486e-06,
+      "loss": 0.3454,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2977048206194757,
+      "grad_norm": 0.051639399606407455,
+      "learning_rate": 3.3090218095760296e-06,
+      "loss": 0.3448,
+      "step": 1455
+    },
+    {
+      "epoch": 1.3021614796107852,
+      "grad_norm": 0.04783319813503841,
+      "learning_rate": 3.272428975142279e-06,
+      "loss": 0.2983,
+      "step": 1460
+    },
+    {
+      "epoch": 1.3066181386020945,
+      "grad_norm": 0.05087706067935069,
+      "learning_rate": 3.235940916674636e-06,
+      "loss": 0.3224,
+      "step": 1465
+    },
+    {
+      "epoch": 1.311074797593404,
+      "grad_norm": 0.0531382115416805,
+      "learning_rate": 3.19955984714815e-06,
+      "loss": 0.3081,
+      "step": 1470
+    },
+    {
+      "epoch": 1.3155314565847136,
+      "grad_norm": 0.060724547940211995,
+      "learning_rate": 3.1632879730490705e-06,
+      "loss": 0.309,
+      "step": 1475
+    },
+    {
+      "epoch": 1.3199881155760231,
+      "grad_norm": 0.05180410376030714,
+      "learning_rate": 3.127127494241018e-06,
+      "loss": 0.3412,
+      "step": 1480
+    },
+    {
+      "epoch": 1.3244447745673327,
+      "grad_norm": 0.06436906484669133,
+      "learning_rate": 3.091080603831568e-06,
+      "loss": 0.3304,
+      "step": 1485
+    },
+    {
+      "epoch": 1.3289014335586422,
+      "grad_norm": 0.06141323563691381,
+      "learning_rate": 3.055149488039239e-06,
+      "loss": 0.3482,
+      "step": 1490
+    },
+    {
+      "epoch": 1.3333580925499517,
+      "grad_norm": 0.05073605621235636,
+      "learning_rate": 3.0193363260609045e-06,
+      "loss": 0.3118,
+      "step": 1495
+    },
+    {
+      "epoch": 1.3378147515412613,
+      "grad_norm": 0.06151762054710644,
+      "learning_rate": 2.983643289939614e-06,
+      "loss": 0.353,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3422714105325708,
+      "grad_norm": 0.0812926316126211,
+      "learning_rate": 2.9480725444328763e-06,
+      "loss": 0.3642,
+      "step": 1505
+    },
+    {
+      "epoch": 1.3467280695238801,
+      "grad_norm": 0.05677065462915271,
+      "learning_rate": 2.9126262468813602e-06,
+      "loss": 0.329,
+      "step": 1510
+    },
+    {
+      "epoch": 1.35118472851519,
+      "grad_norm": 0.05518140834166454,
+      "learning_rate": 2.877306547078045e-06,
+      "loss": 0.2899,
+      "step": 1515
+    },
+    {
+      "epoch": 1.3556413875064992,
+      "grad_norm": 0.056017531551750585,
+      "learning_rate": 2.842115587137855e-06,
+      "loss": 0.3043,
+      "step": 1520
+    },
+    {
+      "epoch": 1.3600980464978087,
+      "grad_norm": 0.06536315700251481,
+      "learning_rate": 2.8070555013677305e-06,
+      "loss": 0.3018,
+      "step": 1525
+    },
+    {
+      "epoch": 1.3645547054891183,
+      "grad_norm": 0.06137584376324279,
+      "learning_rate": 2.772128416137181e-06,
+      "loss": 0.2912,
+      "step": 1530
+    },
+    {
+      "epoch": 1.3690113644804278,
+      "grad_norm": 0.058100040167798406,
+      "learning_rate": 2.7373364497493315e-06,
+      "loss": 0.2794,
+      "step": 1535
+    },
+    {
+      "epoch": 1.3734680234717374,
+      "grad_norm": 0.07619482744511352,
+      "learning_rate": 2.7026817123124456e-06,
+      "loss": 0.309,
+      "step": 1540
+    },
+    {
+      "epoch": 1.377924682463047,
+      "grad_norm": 0.0602222443408102,
+      "learning_rate": 2.6681663056119413e-06,
+      "loss": 0.3248,
+      "step": 1545
+    },
+    {
+      "epoch": 1.3823813414543564,
+      "grad_norm": 0.06509968172306801,
+      "learning_rate": 2.63379232298293e-06,
+      "loss": 0.3449,
+      "step": 1550
+    },
+    {
+      "epoch": 1.386838000445666,
+      "grad_norm": 0.06683684546365645,
+      "learning_rate": 2.599561849183255e-06,
+      "loss": 0.3022,
+      "step": 1555
+    },
+    {
+      "epoch": 1.3912946594369755,
+      "grad_norm": 0.0796435434481212,
+      "learning_rate": 2.5654769602670438e-06,
+      "loss": 0.3372,
+      "step": 1560
+    },
+    {
+      "epoch": 1.3957513184282848,
+      "grad_norm": 0.071737403463626,
+      "learning_rate": 2.531539723458808e-06,
+      "loss": 0.3226,
+      "step": 1565
+    },
+    {
+      "epoch": 1.4002079774195946,
+      "grad_norm": 0.0628814888060204,
+      "learning_rate": 2.4977521970280632e-06,
+      "loss": 0.3054,
+      "step": 1570
+    },
+    {
+      "epoch": 1.4046646364109039,
+      "grad_norm": 0.0664126755234312,
+      "learning_rate": 2.4641164301644916e-06,
+      "loss": 0.3163,
+      "step": 1575
+    },
+    {
+      "epoch": 1.4091212954022134,
+      "grad_norm": 0.0691268006065538,
+      "learning_rate": 2.4306344628536677e-06,
+      "loss": 0.292,
+      "step": 1580
+    },
+    {
+      "epoch": 1.413577954393523,
+      "grad_norm": 0.08254717009005777,
+      "learning_rate": 2.3973083257533337e-06,
+      "loss": 0.2964,
+      "step": 1585
+    },
+    {
+      "epoch": 1.4180346133848325,
+      "grad_norm": 0.0664448970280554,
+      "learning_rate": 2.364140040070233e-06,
+      "loss": 0.3013,
+      "step": 1590
+    },
+    {
+      "epoch": 1.422491272376142,
+      "grad_norm": 0.06641276103365941,
+      "learning_rate": 2.3311316174375385e-06,
+      "loss": 0.3088,
+      "step": 1595
+    },
+    {
+      "epoch": 1.4269479313674516,
+      "grad_norm": 0.08218794135414882,
+      "learning_rate": 2.2982850597928353e-06,
+      "loss": 0.3015,
+      "step": 1600
+    },
+    {
+      "epoch": 1.431404590358761,
+      "grad_norm": 0.06405949653118427,
+      "learning_rate": 2.2656023592567168e-06,
+      "loss": 0.3161,
+      "step": 1605
+    },
+    {
+      "epoch": 1.4358612493500706,
+      "grad_norm": 0.07949199345356144,
+      "learning_rate": 2.2330854980119524e-06,
+      "loss": 0.3018,
+      "step": 1610
+    },
+    {
+      "epoch": 1.4403179083413802,
+      "grad_norm": 0.074973629780883,
+      "learning_rate": 2.2007364481832827e-06,
+      "loss": 0.286,
+      "step": 1615
+    },
+    {
+      "epoch": 1.4447745673326895,
+      "grad_norm": 0.06978140375268374,
+      "learning_rate": 2.168557171717795e-06,
+      "loss": 0.3029,
+      "step": 1620
+    },
+    {
+      "epoch": 1.449231226323999,
+      "grad_norm": 0.060658080118647636,
+      "learning_rate": 2.1365496202659503e-06,
+      "loss": 0.2996,
+      "step": 1625
+    },
+    {
+      "epoch": 1.4536878853153086,
+      "grad_norm": 0.07246627865043749,
+      "learning_rate": 2.104715735063201e-06,
+      "loss": 0.2961,
+      "step": 1630
+    },
+    {
+      "epoch": 1.458144544306618,
+      "grad_norm": 0.07791853687083404,
+      "learning_rate": 2.0730574468122683e-06,
+      "loss": 0.3244,
+      "step": 1635
+    },
+    {
+      "epoch": 1.4626012032979276,
+      "grad_norm": 0.083758493641139,
+      "learning_rate": 2.0415766755660444e-06,
+      "loss": 0.3449,
+      "step": 1640
+    },
+    {
+      "epoch": 1.4670578622892372,
+      "grad_norm": 0.08124328287993272,
+      "learning_rate": 2.010275330611132e-06,
+      "loss": 0.3335,
+      "step": 1645
+    },
+    {
+      "epoch": 1.4715145212805467,
+      "grad_norm": 0.0699592628852485,
+      "learning_rate": 1.9791553103520624e-06,
+      "loss": 0.3101,
+      "step": 1650
+    },
+    {
+      "epoch": 1.4759711802718563,
+      "grad_norm": 0.05596234972263472,
+      "learning_rate": 1.9482185021961506e-06,
+      "loss": 0.3062,
+      "step": 1655
+    },
+    {
+      "epoch": 1.4804278392631658,
+      "grad_norm": 0.06327709166815214,
+      "learning_rate": 1.917466782439024e-06,
+      "loss": 0.2714,
+      "step": 1660
+    },
+    {
+      "epoch": 1.484884498254475,
+      "grad_norm": 0.09193245610034326,
+      "learning_rate": 1.88690201615083e-06,
+      "loss": 0.3015,
+      "step": 1665
+    },
+    {
+      "epoch": 1.4893411572457849,
+      "grad_norm": 0.116065810706921,
+      "learning_rate": 1.8565260570631244e-06,
+      "loss": 0.3023,
+      "step": 1670
+    },
+    {
+      "epoch": 1.4937978162370942,
+      "grad_norm": 0.06085779115348225,
+      "learning_rate": 1.82634074745643e-06,
+      "loss": 0.2793,
+      "step": 1675
+    },
+    {
+      "epoch": 1.4982544752284037,
+      "grad_norm": 0.07726951500485736,
+      "learning_rate": 1.7963479180485204e-06,
+      "loss": 0.2952,
+      "step": 1680
+    },
+    {
+      "epoch": 1.5027111342197133,
+      "grad_norm": 0.08737288468078919,
+      "learning_rate": 1.7665493878833807e-06,
+      "loss": 0.3074,
+      "step": 1685
+    },
+    {
+      "epoch": 1.5071677932110228,
+      "grad_norm": 0.07717042291948013,
+      "learning_rate": 1.736946964220877e-06,
+      "loss": 0.3265,
+      "step": 1690
+    },
+    {
+      "epoch": 1.5116244522023323,
+      "grad_norm": 0.09959612155824546,
+      "learning_rate": 1.7075424424271604e-06,
+      "loss": 0.2923,
+      "step": 1695
+    },
+    {
+      "epoch": 1.5160811111936419,
+      "grad_norm": 0.07789019553417695,
+      "learning_rate": 1.678337605865773e-06,
+      "loss": 0.3185,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5205377701849514,
+      "grad_norm": 0.09414331699116586,
+      "learning_rate": 1.6493342257894845e-06,
+      "loss": 0.3291,
+      "step": 1705
+    },
+    {
+      "epoch": 1.5249944291762607,
+      "grad_norm": 0.09880867896025543,
+      "learning_rate": 1.6205340612328707e-06,
+      "loss": 0.311,
+      "step": 1710
+    },
+    {
+      "epoch": 1.5294510881675705,
+      "grad_norm": 0.07951318628953609,
+      "learning_rate": 1.591938858905634e-06,
+      "loss": 0.303,
+      "step": 1715
+    },
+    {
+      "epoch": 1.5339077471588798,
+      "grad_norm": 0.07982777318332517,
+      "learning_rate": 1.5635503530866563e-06,
+      "loss": 0.2811,
+      "step": 1720
+    },
+    {
+      "epoch": 1.5383644061501895,
+      "grad_norm": 0.08550606994115802,
+      "learning_rate": 1.5353702655188257e-06,
+      "loss": 0.2993,
+      "step": 1725
+    },
+    {
+      "epoch": 1.5428210651414989,
+      "grad_norm": 0.08986128570256782,
+      "learning_rate": 1.5074003053046105e-06,
+      "loss": 0.3038,
+      "step": 1730
+    },
+    {
+      "epoch": 1.5472777241328084,
+      "grad_norm": 0.06401529887840299,
+      "learning_rate": 1.4796421688023975e-06,
+      "loss": 0.2757,
+      "step": 1735
+    },
+    {
+      "epoch": 1.551734383124118,
+      "grad_norm": 0.09741957746810867,
+      "learning_rate": 1.4520975395236215e-06,
+      "loss": 0.3062,
+      "step": 1740
+    },
+    {
+      "epoch": 1.5561910421154275,
+      "grad_norm": 0.07760428621549359,
+      "learning_rate": 1.4247680880306513e-06,
+      "loss": 0.3317,
+      "step": 1745
+    },
+    {
+      "epoch": 1.560647701106737,
+      "grad_norm": 0.08909029154183626,
+      "learning_rate": 1.3976554718354723e-06,
+      "loss": 0.318,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5651043600980465,
+      "grad_norm": 0.10011564881446526,
+      "learning_rate": 1.3707613352991656e-06,
+      "loss": 0.2931,
+      "step": 1755
+    },
+    {
+      "epoch": 1.569561019089356,
+      "grad_norm": 0.08176423100104935,
+      "learning_rate": 1.344087309532175e-06,
+      "loss": 0.2894,
+      "step": 1760
+    },
+    {
+      "epoch": 1.5740176780806654,
+      "grad_norm": 0.07307560261614855,
+      "learning_rate": 1.3176350122953763e-06,
+      "loss": 0.2867,
+      "step": 1765
+    },
+    {
+      "epoch": 1.5784743370719752,
+      "grad_norm": 0.12191262928713528,
+      "learning_rate": 1.2914060479019707e-06,
+      "loss": 0.3202,
+      "step": 1770
+    },
+    {
+      "epoch": 1.5829309960632845,
+      "grad_norm": 0.09026660529628,
+      "learning_rate": 1.2654020071201795e-06,
+      "loss": 0.3106,
+      "step": 1775
+    },
+    {
+      "epoch": 1.5873876550545942,
+      "grad_norm": 0.09053383432158335,
+      "learning_rate": 1.239624467076762e-06,
+      "loss": 0.2984,
+      "step": 1780
+    },
+    {
+      "epoch": 1.5918443140459035,
+      "grad_norm": 0.10384705796359629,
+      "learning_rate": 1.2140749911613703e-06,
+      "loss": 0.3184,
+      "step": 1785
+    },
+    {
+      "epoch": 1.596300973037213,
+      "grad_norm": 0.09677144301192052,
+      "learning_rate": 1.1887551289317284e-06,
+      "loss": 0.3159,
+      "step": 1790
+    },
+    {
+      "epoch": 1.6007576320285226,
+      "grad_norm": 0.08758929393810426,
+      "learning_rate": 1.163666416019647e-06,
+      "loss": 0.2917,
+      "step": 1795
+    },
+    {
+      "epoch": 1.6052142910198322,
+      "grad_norm": 0.08976099626976211,
+      "learning_rate": 1.1388103740379009e-06,
+      "loss": 0.3137,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6096709500111417,
+      "grad_norm": 0.09589145787287572,
+      "learning_rate": 1.114188510487928e-06,
+      "loss": 0.2672,
+      "step": 1805
+    },
+    {
+      "epoch": 1.614127609002451,
+      "grad_norm": 0.0898571951688524,
+      "learning_rate": 1.0898023186684188e-06,
+      "loss": 0.2821,
+      "step": 1810
+    },
+    {
+      "epoch": 1.6185842679937608,
+      "grad_norm": 0.10084905972281838,
+      "learning_rate": 1.06565327758473e-06,
+      "loss": 0.3108,
+      "step": 1815
+    },
+    {
+      "epoch": 1.62304092698507,
+      "grad_norm": 0.09625652044207637,
+      "learning_rate": 1.0417428518592015e-06,
+      "loss": 0.2797,
+      "step": 1820
+    },
+    {
+      "epoch": 1.6274975859763798,
+      "grad_norm": 0.13668108404773008,
+      "learning_rate": 1.018072491642313e-06,
+      "loss": 0.3249,
+      "step": 1825
+    },
+    {
+      "epoch": 1.6319542449676891,
+      "grad_norm": 0.1094276650717538,
+      "learning_rate": 9.946436325247438e-07,
+      "loss": 0.3072,
+      "step": 1830
+    },
+    {
+      "epoch": 1.6364109039589987,
+      "grad_norm": 0.09417653715028669,
+      "learning_rate": 9.71457695450303e-07,
+      "loss": 0.2896,
+      "step": 1835
+    },
+    {
+      "epoch": 1.6408675629503082,
+      "grad_norm": 0.10106662883357638,
+      "learning_rate": 9.485160866297433e-07,
+      "loss": 0.2978,
+      "step": 1840
+    },
+    {
+      "epoch": 1.6453242219416178,
+      "grad_norm": 0.10438310063745738,
+      "learning_rate": 9.25820197455487e-07,
+      "loss": 0.2821,
+      "step": 1845
+    },
+    {
+      "epoch": 1.6497808809329273,
+      "grad_norm": 0.10535335881946876,
+      "learning_rate": 9.033714044172281e-07,
+      "loss": 0.294,
+      "step": 1850
+    },
+    {
+      "epoch": 1.6542375399242368,
+      "grad_norm": 0.0889200936563808,
+      "learning_rate": 8.811710690184566e-07,
+      "loss": 0.262,
+      "step": 1855
+    },
+    {
+      "epoch": 1.6586941989155464,
+      "grad_norm": 0.10455279564530415,
+      "learning_rate": 8.592205376938834e-07,
+      "loss": 0.2817,
+      "step": 1860
+    },
+    {
+      "epoch": 1.6631508579068557,
+      "grad_norm": 0.11318390537590481,
+      "learning_rate": 8.375211417277717e-07,
+      "loss": 0.3045,
+      "step": 1865
+    },
+    {
+      "epoch": 1.6676075168981654,
+      "grad_norm": 0.088743004174387,
+      "learning_rate": 8.160741971732084e-07,
+      "loss": 0.2697,
+      "step": 1870
+    },
+    {
+      "epoch": 1.6720641758894748,
+      "grad_norm": 0.12499336666614728,
+      "learning_rate": 7.948810047722793e-07,
+      "loss": 0.2856,
+      "step": 1875
+    },
+    {
+      "epoch": 1.6765208348807845,
+      "grad_norm": 0.11172684998831532,
+      "learning_rate": 7.739428498771761e-07,
+      "loss": 0.2658,
+      "step": 1880
+    },
+    {
+      "epoch": 1.6809774938720938,
+      "grad_norm": 0.12595234706288227,
+      "learning_rate": 7.532610023722509e-07,
+      "loss": 0.2732,
+      "step": 1885
+    },
+    {
+      "epoch": 1.6854341528634034,
+      "grad_norm": 0.09689191794827777,
+      "learning_rate": 7.328367165969907e-07,
+      "loss": 0.3044,
+      "step": 1890
+    },
+    {
+      "epoch": 1.689890811854713,
+      "grad_norm": 0.11874605920811564,
+      "learning_rate": 7.126712312699435e-07,
+      "loss": 0.3221,
+      "step": 1895
+    },
+    {
+      "epoch": 1.6943474708460224,
+      "grad_norm": 0.08766218268129858,
+      "learning_rate": 6.927657694135959e-07,
+      "loss": 0.2814,
+      "step": 1900
+    },
+    {
+      "epoch": 1.698804129837332,
+      "grad_norm": 0.10403913380960049,
+      "learning_rate": 6.731215382801903e-07,
+      "loss": 0.3007,
+      "step": 1905
+    },
+    {
+      "epoch": 1.7032607888286415,
+      "grad_norm": 0.12394080523133466,
+      "learning_rate": 6.53739729278513e-07,
+      "loss": 0.2685,
+      "step": 1910
+    },
+    {
+      "epoch": 1.707717447819951,
+      "grad_norm": 0.09220124360987444,
+      "learning_rate": 6.346215179016297e-07,
+      "loss": 0.2999,
+      "step": 1915
+    },
+    {
+      "epoch": 1.7121741068112604,
+      "grad_norm": 0.09256443041488645,
+      "learning_rate": 6.157680636555996e-07,
+      "loss": 0.2921,
+      "step": 1920
+    },
+    {
+      "epoch": 1.7166307658025701,
+      "grad_norm": 0.11801980704813507,
+      "learning_rate": 5.971805099891437e-07,
+      "loss": 0.2952,
+      "step": 1925
+    },
+    {
+      "epoch": 1.7210874247938794,
+      "grad_norm": 0.11500014463950178,
+      "learning_rate": 5.788599842243043e-07,
+      "loss": 0.2757,
+      "step": 1930
+    },
+    {
+      "epoch": 1.7255440837851892,
+      "grad_norm": 0.12909046401480123,
+      "learning_rate": 5.608075974880678e-07,
+      "loss": 0.2783,
+      "step": 1935
+    },
+    {
+      "epoch": 1.7300007427764985,
+      "grad_norm": 0.10409707004186307,
+      "learning_rate": 5.430244446449762e-07,
+      "loss": 0.2853,
+      "step": 1940
+    },
+    {
+      "epoch": 1.734457401767808,
+      "grad_norm": 0.11009184273146726,
+      "learning_rate": 5.255116042307267e-07,
+      "loss": 0.2712,
+      "step": 1945
+    },
+    {
+      "epoch": 1.7389140607591176,
+      "grad_norm": 0.16597411522897149,
+      "learning_rate": 5.0827013838676e-07,
+      "loss": 0.3097,
+      "step": 1950
+    },
+    {
+      "epoch": 1.7433707197504271,
+      "grad_norm": 0.10555291444735147,
+      "learning_rate": 4.91301092795835e-07,
+      "loss": 0.3001,
+      "step": 1955
+    },
+    {
+      "epoch": 1.7478273787417367,
+      "grad_norm": 0.12464546891723725,
+      "learning_rate": 4.746054966186192e-07,
+      "loss": 0.2955,
+      "step": 1960
+    },
+    {
+      "epoch": 1.752284037733046,
+      "grad_norm": 0.11277180986490198,
+      "learning_rate": 4.581843624312643e-07,
+      "loss": 0.2643,
+      "step": 1965
+    },
+    {
+      "epoch": 1.7567406967243557,
+      "grad_norm": 0.09867908839152027,
+      "learning_rate": 4.4203868616399305e-07,
+      "loss": 0.312,
+      "step": 1970
+    },
+    {
+      "epoch": 1.761197355715665,
+      "grad_norm": 0.11312294922723523,
+      "learning_rate": 4.261694470407024e-07,
+      "loss": 0.2754,
+      "step": 1975
+    },
+    {
+      "epoch": 1.7656540147069748,
+      "grad_norm": 0.10862426439391781,
+      "learning_rate": 4.1057760751957056e-07,
+      "loss": 0.291,
+      "step": 1980
+    },
+    {
+      "epoch": 1.7701106736982841,
+      "grad_norm": 0.13833325552109443,
+      "learning_rate": 3.9526411323468403e-07,
+      "loss": 0.3009,
+      "step": 1985
+    },
+    {
+      "epoch": 1.7745673326895937,
+      "grad_norm": 0.11648729127760897,
+      "learning_rate": 3.802298929386872e-07,
+      "loss": 0.2948,
+      "step": 1990
+    },
+    {
+      "epoch": 1.7790239916809032,
+      "grad_norm": 0.10832697002551062,
+      "learning_rate": 3.6547585844645574e-07,
+      "loss": 0.264,
+      "step": 1995
+    },
+    {
+      "epoch": 1.7834806506722127,
+      "grad_norm": 0.1129159601097704,
+      "learning_rate": 3.510029045797897e-07,
+      "loss": 0.2814,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7879373096635223,
+      "grad_norm": 0.12881883038121175,
+      "learning_rate": 3.368119091131511e-07,
+      "loss": 0.2961,
+      "step": 2005
+    },
+    {
+      "epoch": 1.7923939686548318,
+      "grad_norm": 0.11915967567506883,
+      "learning_rate": 3.2290373272041984e-07,
+      "loss": 0.2847,
+      "step": 2010
+    },
+    {
+      "epoch": 1.7968506276461413,
+      "grad_norm": 0.14883545803777695,
+      "learning_rate": 3.0927921892270173e-07,
+      "loss": 0.3072,
+      "step": 2015
+    },
+    {
+      "epoch": 1.8013072866374507,
+      "grad_norm": 0.14935341192789242,
+      "learning_rate": 2.9593919403716254e-07,
+      "loss": 0.2585,
+      "step": 2020
+    },
+    {
+      "epoch": 1.8057639456287604,
+      "grad_norm": 0.10091752925214101,
+      "learning_rate": 2.8288446712691985e-07,
+      "loss": 0.2927,
+      "step": 2025
+    },
+    {
+      "epoch": 1.8102206046200697,
+      "grad_norm": 0.1272686505517032,
+      "learning_rate": 2.701158299519652e-07,
+      "loss": 0.297,
+      "step": 2030
+    },
+    {
+      "epoch": 1.8146772636113795,
+      "grad_norm": 0.11235244093503088,
+      "learning_rate": 2.5763405692115326e-07,
+      "loss": 0.2834,
+      "step": 2035
+    },
+    {
+      "epoch": 1.8191339226026888,
+      "grad_norm": 0.13526604911761567,
+      "learning_rate": 2.454399050452283e-07,
+      "loss": 0.296,
+      "step": 2040
+    },
+    {
+      "epoch": 1.8235905815939983,
+      "grad_norm": 0.13280050999221021,
+      "learning_rate": 2.335341138909142e-07,
+      "loss": 0.2717,
+      "step": 2045
+    },
+    {
+      "epoch": 1.8280472405853079,
+      "grad_norm": 0.12814019839952007,
+      "learning_rate": 2.219174055360612e-07,
+      "loss": 0.2717,
+      "step": 2050
+    },
+    {
+      "epoch": 1.8325038995766174,
+      "grad_norm": 0.11817894924930601,
+      "learning_rate": 2.1059048452584996e-07,
+      "loss": 0.2735,
+      "step": 2055
+    },
+    {
+      "epoch": 1.836960558567927,
+      "grad_norm": 0.12820739048926352,
+      "learning_rate": 1.9955403783006255e-07,
+      "loss": 0.2726,
+      "step": 2060
+    },
+    {
+      "epoch": 1.8414172175592363,
+      "grad_norm": 0.14570257294552771,
+      "learning_rate": 1.888087348014217e-07,
+      "loss": 0.2526,
+      "step": 2065
+    },
+    {
+      "epoch": 1.845873876550546,
+      "grad_norm": 0.09484685178822737,
+      "learning_rate": 1.7835522713498644e-07,
+      "loss": 0.2592,
+      "step": 2070
+    },
+    {
+      "epoch": 1.8503305355418553,
+      "grad_norm": 0.11168612744194842,
+      "learning_rate": 1.6819414882863704e-07,
+      "loss": 0.3027,
+      "step": 2075
+    },
+    {
+      "epoch": 1.854787194533165,
+      "grad_norm": 0.13169293315087485,
+      "learning_rate": 1.5832611614461757e-07,
+      "loss": 0.2576,
+      "step": 2080
+    },
+    {
+      "epoch": 1.8592438535244744,
+      "grad_norm": 0.13264409398535437,
+      "learning_rate": 1.4875172757216006e-07,
+      "loss": 0.2808,
+      "step": 2085
+    },
+    {
+      "epoch": 1.863700512515784,
+      "grad_norm": 0.11349693321653709,
+      "learning_rate": 1.394715637911903e-07,
+      "loss": 0.2588,
+      "step": 2090
+    },
+    {
+      "epoch": 1.8681571715070935,
+      "grad_norm": 0.14216886029418724,
+      "learning_rate": 1.3048618763710609e-07,
+      "loss": 0.2886,
+      "step": 2095
+    },
+    {
+      "epoch": 1.872613830498403,
+      "grad_norm": 0.11190825927177947,
+      "learning_rate": 1.2179614406664374e-07,
+      "loss": 0.2806,
+      "step": 2100
+    },
+    {
+      "epoch": 1.8770704894897126,
+      "grad_norm": 0.13139481283283222,
+      "learning_rate": 1.1340196012482652e-07,
+      "loss": 0.2701,
+      "step": 2105
+    },
+    {
+      "epoch": 1.881527148481022,
+      "grad_norm": 0.13212149531161754,
+      "learning_rate": 1.0530414491299823e-07,
+      "loss": 0.2976,
+      "step": 2110
+    },
+    {
+      "epoch": 1.8859838074723316,
+      "grad_norm": 0.14761056178281307,
+      "learning_rate": 9.75031895579509e-08,
+      "loss": 0.2851,
+      "step": 2115
+    },
+    {
+      "epoch": 1.890440466463641,
+      "grad_norm": 0.11807804154726727,
+      "learning_rate": 8.999956718213187e-08,
+      "loss": 0.2675,
+      "step": 2120
+    },
+    {
+      "epoch": 1.8948971254549507,
+      "grad_norm": 0.13153250275786837,
+      "learning_rate": 8.279373287495452e-08,
+      "loss": 0.2756,
+      "step": 2125
+    },
+    {
+      "epoch": 1.89935378444626,
+      "grad_norm": 0.12010506744054632,
+      "learning_rate": 7.588612366519588e-08,
+      "loss": 0.2755,
+      "step": 2130
+    },
+    {
+      "epoch": 1.9038104434375698,
+      "grad_norm": 0.13595444122630035,
+      "learning_rate": 6.927715849448902e-08,
+      "loss": 0.2621,
+      "step": 2135
+    },
+    {
+      "epoch": 1.908267102428879,
+      "grad_norm": 0.11969702875665357,
+      "learning_rate": 6.296723819191886e-08,
+      "loss": 0.2619,
+      "step": 2140
+    },
+    {
+      "epoch": 1.9127237614201886,
+      "grad_norm": 0.12713767895060166,
+      "learning_rate": 5.695674544970775e-08,
+      "loss": 0.2646,
+      "step": 2145
+    },
+    {
+      "epoch": 1.9171804204114982,
+      "grad_norm": 0.1512438174845061,
+      "learning_rate": 5.124604480000739e-08,
+      "loss": 0.2861,
+      "step": 2150
+    },
+    {
+      "epoch": 1.9216370794028077,
+      "grad_norm": 0.15063267518774118,
+      "learning_rate": 4.5835482592792026e-08,
+      "loss": 0.276,
+      "step": 2155
+    },
+    {
+      "epoch": 1.9260937383941172,
+      "grad_norm": 0.12516539105766297,
+      "learning_rate": 4.072538697484807e-08,
+      "loss": 0.288,
+      "step": 2160
+    },
+    {
+      "epoch": 1.9305503973854268,
+      "grad_norm": 0.12187069090426104,
+      "learning_rate": 3.591606786987667e-08,
+      "loss": 0.2864,
+      "step": 2165
+    },
+    {
+      "epoch": 1.9350070563767363,
+      "grad_norm": 0.10855277743154071,
+      "learning_rate": 3.1407816959695416e-08,
+      "loss": 0.2978,
+      "step": 2170
+    },
+    {
+      "epoch": 1.9394637153680456,
+      "grad_norm": 0.133314659297753,
+      "learning_rate": 2.720090766654693e-08,
+      "loss": 0.2864,
+      "step": 2175
+    },
+    {
+      "epoch": 1.9439203743593554,
+      "grad_norm": 0.1263650702337354,
+      "learning_rate": 2.3295595136517136e-08,
+      "loss": 0.2737,
+      "step": 2180
+    },
+    {
+      "epoch": 1.9483770333506647,
+      "grad_norm": 0.1343875450088774,
+      "learning_rate": 1.9692116224060976e-08,
+      "loss": 0.2624,
+      "step": 2185
+    },
+    {
+      "epoch": 1.9528336923419745,
+      "grad_norm": 0.12031351113756965,
+      "learning_rate": 1.639068947763722e-08,
+      "loss": 0.277,
+      "step": 2190
+    },
+    {
+      "epoch": 1.9572903513332838,
+      "grad_norm": 0.12928344033539446,
+      "learning_rate": 1.3391515126452426e-08,
+      "loss": 0.2739,
+      "step": 2195
+    },
+    {
+      "epoch": 1.9617470103245933,
+      "grad_norm": 0.12874880789823828,
+      "learning_rate": 1.0694775068320063e-08,
+      "loss": 0.2622,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9662036693159028,
+      "grad_norm": 0.17186304444380732,
+      "learning_rate": 8.30063285862437e-09,
+      "loss": 0.2909,
+      "step": 2205
+    },
+    {
+      "epoch": 1.9706603283072124,
+      "grad_norm": 0.1309907572097109,
+      "learning_rate": 6.209233700406048e-09,
+      "loss": 0.277,
+      "step": 2210
+    },
+    {
+      "epoch": 1.975116987298522,
+      "grad_norm": 0.1365092145131148,
+      "learning_rate": 4.4207044355493164e-09,
+      "loss": 0.2629,
+      "step": 2215
+    },
+    {
+      "epoch": 1.9795736462898312,
+      "grad_norm": 0.12156842653941813,
+      "learning_rate": 2.935153537096391e-09,
+      "loss": 0.2658,
+      "step": 2220
+    },
+    {
+      "epoch": 1.984030305281141,
+      "grad_norm": 0.1263668031483968,
+      "learning_rate": 1.7526711026621957e-09,
+      "loss": 0.2805,
+      "step": 2225
+    },
+    {
+      "epoch": 1.9884869642724503,
+      "grad_norm": 0.13239230121316822,
+      "learning_rate": 8.733288489737312e-10,
+      "loss": 0.2822,
+      "step": 2230
+    },
+    {
+      "epoch": 1.99294362326376,
+      "grad_norm": 0.13212067705172323,
+      "learning_rate": 2.9718010751966784e-10,
+      "loss": 0.2625,
+      "step": 2235
+    },
+    {
+      "epoch": 1.9974002822550694,
+      "grad_norm": 0.13697820005606215,
+      "learning_rate": 2.4259821315153476e-11,
+      "loss": 0.2635,
+      "step": 2240
+    },
+    {
+      "epoch": 1.9991829458515933,
+      "eval_loss": 0.2551692724227905,
+      "eval_runtime": 27.6419,
+      "eval_samples_per_second": 19.68,
+      "eval_steps_per_second": 4.92,
+      "step": 2242
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2242,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.790417620582793e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2242/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568aa6232c9b4866a8ba747cb2b279ea41d9e166425cbf32eb692501480cf04f
+size 7288

checkpoint-2242/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291e07ffb6d2d2a2b7fc1c221ab8cd07b7a0babf3660b5a622235bc5632df950
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b082a30443feee88f5dcea38a7b25a37c3ba508381ffb25dda22e363f6201ea0
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde08fffd72f6e2f4212d7a32f6c6b9e24e43deb69e8d9119847d57bb758b64e
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119f2e377c58d48a02bf9040fe74adec6e477704aa2a53fec311efbecdd56840
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd751a4191592ee601080b532d487e2444024e3205900acca92b7c94791e29dd
+size 17210060

tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9991829458515933,
+    "total_flos": 5.790417620582793e+18,
+    "train_loss": 0.36008237901805873,
+    "train_runtime": 20584.0534,
+    "train_samples": 53851,
+    "train_samples_per_second": 5.232,
+    "train_steps_per_second": 0.109
+}

trainer_state.json

@@ -0,0 +1,3201 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9991829458515933,
+  "eval_steps": 500,
+  "global_step": 2242,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000891331798261903,
+      "grad_norm": 1.9037784957265278,
+      "learning_rate": 4.444444444444445e-08,
+      "loss": 2.0985,
+      "step": 1
+    },
+    {
+      "epoch": 0.004456658991309515,
+      "grad_norm": 2.041848097696368,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 2.1176,
+      "step": 5
+    },
+    {
+      "epoch": 0.00891331798261903,
+      "grad_norm": 1.948478886522995,
+      "learning_rate": 4.444444444444445e-07,
+      "loss": 2.1163,
+      "step": 10
+    },
+    {
+      "epoch": 0.013369976973928544,
+      "grad_norm": 1.2537062422839984,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 1.9595,
+      "step": 15
+    },
+    {
+      "epoch": 0.01782663596523806,
+      "grad_norm": 0.7428497382948752,
+      "learning_rate": 8.88888888888889e-07,
+      "loss": 1.753,
+      "step": 20
+    },
+    {
+      "epoch": 0.022283294956547576,
+      "grad_norm": 0.8283681781487435,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.3909,
+      "step": 25
+    },
+    {
+      "epoch": 0.02673995394785709,
+      "grad_norm": 0.36636499270519984,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.0722,
+      "step": 30
+    },
+    {
+      "epoch": 0.031196612939166604,
+      "grad_norm": 0.26139683469044633,
+      "learning_rate": 1.5555555555555558e-06,
+      "loss": 0.8856,
+      "step": 35
+    },
+    {
+      "epoch": 0.03565327193047612,
+      "grad_norm": 0.25123645705965264,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 0.7828,
+      "step": 40
+    },
+    {
+      "epoch": 0.040109930921785636,
+      "grad_norm": 0.21827339412974361,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.7277,
+      "step": 45
+    },
+    {
+      "epoch": 0.04456658991309515,
+      "grad_norm": 0.184310768975577,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.6973,
+      "step": 50
+    },
+    {
+      "epoch": 0.04902324890440467,
+      "grad_norm": 0.15756594573320623,
+      "learning_rate": 2.4444444444444447e-06,
+      "loss": 0.6115,
+      "step": 55
+    },
+    {
+      "epoch": 0.05347990789571418,
+      "grad_norm": 0.1495421231449033,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.5526,
+      "step": 60
+    },
+    {
+      "epoch": 0.05793656688702369,
+      "grad_norm": 0.11563000336226048,
+      "learning_rate": 2.888888888888889e-06,
+      "loss": 0.553,
+      "step": 65
+    },
+    {
+      "epoch": 0.06239322587833321,
+      "grad_norm": 0.11747617404049002,
+      "learning_rate": 3.1111111111111116e-06,
+      "loss": 0.5422,
+      "step": 70
+    },
+    {
+      "epoch": 0.06684988486964273,
+      "grad_norm": 0.124912316735415,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.5342,
+      "step": 75
+    },
+    {
+      "epoch": 0.07130654386095224,
+      "grad_norm": 0.11219727658791885,
+      "learning_rate": 3.555555555555556e-06,
+      "loss": 0.506,
+      "step": 80
+    },
+    {
+      "epoch": 0.07576320285226175,
+      "grad_norm": 0.13707586211382092,
+      "learning_rate": 3.777777777777778e-06,
+      "loss": 0.4776,
+      "step": 85
+    },
+    {
+      "epoch": 0.08021986184357127,
+      "grad_norm": 0.14849136857556636,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.4592,
+      "step": 90
+    },
+    {
+      "epoch": 0.08467652083488078,
+      "grad_norm": 0.13619871874828954,
+      "learning_rate": 4.222222222222223e-06,
+      "loss": 0.4622,
+      "step": 95
+    },
+    {
+      "epoch": 0.0891331798261903,
+      "grad_norm": 0.11869279856425284,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.4518,
+      "step": 100
+    },
+    {
+      "epoch": 0.09358983881749981,
+      "grad_norm": 0.12992883840039074,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.4115,
+      "step": 105
+    },
+    {
+      "epoch": 0.09804649780880934,
+      "grad_norm": 0.1023382558423108,
+      "learning_rate": 4.888888888888889e-06,
+      "loss": 0.4397,
+      "step": 110
+    },
+    {
+      "epoch": 0.10250315680011884,
+      "grad_norm": 0.12320266344355456,
+      "learning_rate": 5.1111111111111115e-06,
+      "loss": 0.4409,
+      "step": 115
+    },
+    {
+      "epoch": 0.10695981579142835,
+      "grad_norm": 0.11198962480183935,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.4436,
+      "step": 120
+    },
+    {
+      "epoch": 0.11141647478273788,
+      "grad_norm": 0.10145699193523927,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.4338,
+      "step": 125
+    },
+    {
+      "epoch": 0.11587313377404738,
+      "grad_norm": 0.09900502716310512,
+      "learning_rate": 5.777777777777778e-06,
+      "loss": 0.4208,
+      "step": 130
+    },
+    {
+      "epoch": 0.12032979276535691,
+      "grad_norm": 0.08614271297265043,
+      "learning_rate": 6e-06,
+      "loss": 0.4089,
+      "step": 135
+    },
+    {
+      "epoch": 0.12478645175666642,
+      "grad_norm": 0.07806255577197463,
+      "learning_rate": 6.222222222222223e-06,
+      "loss": 0.3945,
+      "step": 140
+    },
+    {
+      "epoch": 0.12924311074797593,
+      "grad_norm": 0.07178671408430405,
+      "learning_rate": 6.444444444444445e-06,
+      "loss": 0.3889,
+      "step": 145
+    },
+    {
+      "epoch": 0.13369976973928546,
+      "grad_norm": 0.08445699462456596,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.4131,
+      "step": 150
+    },
+    {
+      "epoch": 0.13815642873059497,
+      "grad_norm": 0.0853269964638284,
+      "learning_rate": 6.88888888888889e-06,
+      "loss": 0.4053,
+      "step": 155
+    },
+    {
+      "epoch": 0.14261308772190448,
+      "grad_norm": 0.0776450305961035,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 0.3882,
+      "step": 160
+    },
+    {
+      "epoch": 0.147069746713214,
+      "grad_norm": 0.08066465881766263,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.4148,
+      "step": 165
+    },
+    {
+      "epoch": 0.1515264057045235,
+      "grad_norm": 0.08075299908764268,
+      "learning_rate": 7.555555555555556e-06,
+      "loss": 0.4014,
+      "step": 170
+    },
+    {
+      "epoch": 0.15598306469583303,
+      "grad_norm": 0.08146641337838845,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.4067,
+      "step": 175
+    },
+    {
+      "epoch": 0.16043972368714254,
+      "grad_norm": 0.06545943489756188,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.3913,
+      "step": 180
+    },
+    {
+      "epoch": 0.16489638267845205,
+      "grad_norm": 0.07220259387677776,
+      "learning_rate": 8.222222222222222e-06,
+      "loss": 0.4169,
+      "step": 185
+    },
+    {
+      "epoch": 0.16935304166976156,
+      "grad_norm": 0.0666745164016267,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 0.4203,
+      "step": 190
+    },
+    {
+      "epoch": 0.17380970066107107,
+      "grad_norm": 0.08104266749063946,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.3586,
+      "step": 195
+    },
+    {
+      "epoch": 0.1782663596523806,
+      "grad_norm": 0.06500061012271417,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.3844,
+      "step": 200
+    },
+    {
+      "epoch": 0.18272301864369012,
+      "grad_norm": 0.06438217840061684,
+      "learning_rate": 9.111111111111112e-06,
+      "loss": 0.4154,
+      "step": 205
+    },
+    {
+      "epoch": 0.18717967763499962,
+      "grad_norm": 0.07013299670767151,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.3874,
+      "step": 210
+    },
+    {
+      "epoch": 0.19163633662630913,
+      "grad_norm": 0.07168242323487646,
+      "learning_rate": 9.555555555555556e-06,
+      "loss": 0.3849,
+      "step": 215
+    },
+    {
+      "epoch": 0.19609299561761867,
+      "grad_norm": 0.05932657135991667,
+      "learning_rate": 9.777777777777779e-06,
+      "loss": 0.3672,
+      "step": 220
+    },
+    {
+      "epoch": 0.20054965460892818,
+      "grad_norm": 0.07058592680145803,
+      "learning_rate": 1e-05,
+      "loss": 0.387,
+      "step": 225
+    },
+    {
+      "epoch": 0.2050063136002377,
+      "grad_norm": 0.051067467997344705,
+      "learning_rate": 9.999848376760494e-06,
+      "loss": 0.3826,
+      "step": 230
+    },
+    {
+      "epoch": 0.2094629725915472,
+      "grad_norm": 0.06816795236315125,
+      "learning_rate": 9.999393516237815e-06,
+      "loss": 0.3931,
+      "step": 235
+    },
+    {
+      "epoch": 0.2139196315828567,
+      "grad_norm": 0.06395745969231853,
+      "learning_rate": 9.998635446018936e-06,
+      "loss": 0.4009,
+      "step": 240
+    },
+    {
+      "epoch": 0.21837629057416624,
+      "grad_norm": 0.0713711836562236,
+      "learning_rate": 9.997574212080282e-06,
+      "loss": 0.3793,
+      "step": 245
+    },
+    {
+      "epoch": 0.22283294956547575,
+      "grad_norm": 0.0698163755701484,
+      "learning_rate": 9.996209878784942e-06,
+      "loss": 0.397,
+      "step": 250
+    },
+    {
+      "epoch": 0.22728960855678526,
+      "grad_norm": 0.0682706528712552,
+      "learning_rate": 9.99454252887877e-06,
+      "loss": 0.405,
+      "step": 255
+    },
+    {
+      "epoch": 0.23174626754809477,
+      "grad_norm": 0.06445770501449549,
+      "learning_rate": 9.992572263485365e-06,
+      "loss": 0.3502,
+      "step": 260
+    },
+    {
+      "epoch": 0.2362029265394043,
+      "grad_norm": 0.06470981088114686,
+      "learning_rate": 9.990299202099934e-06,
+      "loss": 0.415,
+      "step": 265
+    },
+    {
+      "epoch": 0.24065958553071382,
+      "grad_norm": 0.05884297180052234,
+      "learning_rate": 9.987723482582052e-06,
+      "loss": 0.3891,
+      "step": 270
+    },
+    {
+      "epoch": 0.24511624452202332,
+      "grad_norm": 0.05013087545524401,
+      "learning_rate": 9.98484526114729e-06,
+      "loss": 0.4081,
+      "step": 275
+    },
+    {
+      "epoch": 0.24957290351333283,
+      "grad_norm": 0.05965101051743905,
+      "learning_rate": 9.981664712357756e-06,
+      "loss": 0.367,
+      "step": 280
+    },
+    {
+      "epoch": 0.25402956250464237,
+      "grad_norm": 0.06332324890343168,
+      "learning_rate": 9.97818202911149e-06,
+      "loss": 0.3821,
+      "step": 285
+    },
+    {
+      "epoch": 0.25848622149595185,
+      "grad_norm": 0.06434539140174649,
+      "learning_rate": 9.974397422630781e-06,
+      "loss": 0.4017,
+      "step": 290
+    },
+    {
+      "epoch": 0.2629428804872614,
+      "grad_norm": 0.047968388544284014,
+      "learning_rate": 9.970311122449348e-06,
+      "loss": 0.3785,
+      "step": 295
+    },
+    {
+      "epoch": 0.2673995394785709,
+      "grad_norm": 0.05355639391449654,
+      "learning_rate": 9.965923376398414e-06,
+      "loss": 0.3829,
+      "step": 300
+    },
+    {
+      "epoch": 0.2718561984698804,
+      "grad_norm": 0.05997351126022962,
+      "learning_rate": 9.961234450591692e-06,
+      "loss": 0.3834,
+      "step": 305
+    },
+    {
+      "epoch": 0.27631285746118994,
+      "grad_norm": 0.06439261526987958,
+      "learning_rate": 9.956244629409231e-06,
+      "loss": 0.3473,
+      "step": 310
+    },
+    {
+      "epoch": 0.2807695164524994,
+      "grad_norm": 0.048664469272370746,
+      "learning_rate": 9.950954215480168e-06,
+      "loss": 0.3883,
+      "step": 315
+    },
+    {
+      "epoch": 0.28522617544380896,
+      "grad_norm": 0.06106240669926854,
+      "learning_rate": 9.945363529664385e-06,
+      "loss": 0.3671,
+      "step": 320
+    },
+    {
+      "epoch": 0.2896828344351185,
+      "grad_norm": 0.06560525566792794,
+      "learning_rate": 9.93947291103304e-06,
+      "loss": 0.3872,
+      "step": 325
+    },
+    {
+      "epoch": 0.294139493426428,
+      "grad_norm": 0.051890916918650776,
+      "learning_rate": 9.933282716848001e-06,
+      "loss": 0.3881,
+      "step": 330
+    },
+    {
+      "epoch": 0.2985961524177375,
+      "grad_norm": 0.05177493540298683,
+      "learning_rate": 9.92679332254019e-06,
+      "loss": 0.3688,
+      "step": 335
+    },
+    {
+      "epoch": 0.303052811409047,
+      "grad_norm": 0.05169465457227038,
+      "learning_rate": 9.920005121686802e-06,
+      "loss": 0.3742,
+      "step": 340
+    },
+    {
+      "epoch": 0.30750947040035653,
+      "grad_norm": 0.05433225521681918,
+      "learning_rate": 9.912918525987437e-06,
+      "loss": 0.3672,
+      "step": 345
+    },
+    {
+      "epoch": 0.31196612939166607,
+      "grad_norm": 0.05227372498869847,
+      "learning_rate": 9.905533965239133e-06,
+      "loss": 0.3674,
+      "step": 350
+    },
+    {
+      "epoch": 0.31642278838297555,
+      "grad_norm": 0.04827464212259707,
+      "learning_rate": 9.897851887310304e-06,
+      "loss": 0.386,
+      "step": 355
+    },
+    {
+      "epoch": 0.3208794473742851,
+      "grad_norm": 0.04786866328513665,
+      "learning_rate": 9.88987275811356e-06,
+      "loss": 0.3888,
+      "step": 360
+    },
+    {
+      "epoch": 0.32533610636559457,
+      "grad_norm": 0.05117403335251474,
+      "learning_rate": 9.881597061577473e-06,
+      "loss": 0.371,
+      "step": 365
+    },
+    {
+      "epoch": 0.3297927653569041,
+      "grad_norm": 0.05209023655644307,
+      "learning_rate": 9.873025299617207e-06,
+      "loss": 0.3554,
+      "step": 370
+    },
+    {
+      "epoch": 0.33424942434821364,
+      "grad_norm": 0.04620493946724755,
+      "learning_rate": 9.86415799210409e-06,
+      "loss": 0.339,
+      "step": 375
+    },
+    {
+      "epoch": 0.3387060833395231,
+      "grad_norm": 0.04972442705458662,
+      "learning_rate": 9.854995676834078e-06,
+      "loss": 0.3381,
+      "step": 380
+    },
+    {
+      "epoch": 0.34316274233083266,
+      "grad_norm": 0.04902183301719761,
+      "learning_rate": 9.845538909495142e-06,
+      "loss": 0.3473,
+      "step": 385
+    },
+    {
+      "epoch": 0.34761940132214214,
+      "grad_norm": 0.048588732980178,
+      "learning_rate": 9.835788263633559e-06,
+      "loss": 0.3715,
+      "step": 390
+    },
+    {
+      "epoch": 0.3520760603134517,
+      "grad_norm": 0.0518211854230867,
+      "learning_rate": 9.825744330619136e-06,
+      "loss": 0.335,
+      "step": 395
+    },
+    {
+      "epoch": 0.3565327193047612,
+      "grad_norm": 0.04470995877402061,
+      "learning_rate": 9.815407719609336e-06,
+      "loss": 0.3576,
+      "step": 400
+    },
+    {
+      "epoch": 0.3609893782960707,
+      "grad_norm": 0.046718917610627575,
+      "learning_rate": 9.804779057512337e-06,
+      "loss": 0.3844,
+      "step": 405
+    },
+    {
+      "epoch": 0.36544603728738023,
+      "grad_norm": 0.04487868027034623,
+      "learning_rate": 9.793858988949013e-06,
+      "loss": 0.3651,
+      "step": 410
+    },
+    {
+      "epoch": 0.36990269627868977,
+      "grad_norm": 0.04508769734592565,
+      "learning_rate": 9.782648176213832e-06,
+      "loss": 0.3327,
+      "step": 415
+    },
+    {
+      "epoch": 0.37435935526999925,
+      "grad_norm": 0.047550358889489414,
+      "learning_rate": 9.77114729923469e-06,
+      "loss": 0.3845,
+      "step": 420
+    },
+    {
+      "epoch": 0.3788160142613088,
+      "grad_norm": 0.04522521563643231,
+      "learning_rate": 9.759357055531677e-06,
+      "loss": 0.3758,
+      "step": 425
+    },
+    {
+      "epoch": 0.38327267325261827,
+      "grad_norm": 0.046807592924263536,
+      "learning_rate": 9.747278160174773e-06,
+      "loss": 0.3684,
+      "step": 430
+    },
+    {
+      "epoch": 0.3877293322439278,
+      "grad_norm": 0.04945346042475437,
+      "learning_rate": 9.734911345740476e-06,
+      "loss": 0.374,
+      "step": 435
+    },
+    {
+      "epoch": 0.39218599123523734,
+      "grad_norm": 0.04507829141189117,
+      "learning_rate": 9.72225736226737e-06,
+      "loss": 0.3719,
+      "step": 440
+    },
+    {
+      "epoch": 0.3966426502265468,
+      "grad_norm": 0.05375175462388905,
+      "learning_rate": 9.709316977210641e-06,
+      "loss": 0.3738,
+      "step": 445
+    },
+    {
+      "epoch": 0.40109930921785636,
+      "grad_norm": 0.04178366229734565,
+      "learning_rate": 9.696090975395535e-06,
+      "loss": 0.35,
+      "step": 450
+    },
+    {
+      "epoch": 0.40555596820916584,
+      "grad_norm": 0.04307772924393916,
+      "learning_rate": 9.682580158969744e-06,
+      "loss": 0.3647,
+      "step": 455
+    },
+    {
+      "epoch": 0.4100126272004754,
+      "grad_norm": 0.04607844523886918,
+      "learning_rate": 9.66878534735477e-06,
+      "loss": 0.3422,
+      "step": 460
+    },
+    {
+      "epoch": 0.4144692861917849,
+      "grad_norm": 0.042361601709353026,
+      "learning_rate": 9.654707377196226e-06,
+      "loss": 0.3282,
+      "step": 465
+    },
+    {
+      "epoch": 0.4189259451830944,
+      "grad_norm": 0.05012304389062508,
+      "learning_rate": 9.640347102313086e-06,
+      "loss": 0.3872,
+      "step": 470
+    },
+    {
+      "epoch": 0.42338260417440393,
+      "grad_norm": 0.04177143585248632,
+      "learning_rate": 9.625705393645913e-06,
+      "loss": 0.332,
+      "step": 475
+    },
+    {
+      "epoch": 0.4278392631657134,
+      "grad_norm": 0.04105439567860185,
+      "learning_rate": 9.61078313920402e-06,
+      "loss": 0.3683,
+      "step": 480
+    },
+    {
+      "epoch": 0.43229592215702295,
+      "grad_norm": 0.04188596881105404,
+      "learning_rate": 9.595581244011638e-06,
+      "loss": 0.3764,
+      "step": 485
+    },
+    {
+      "epoch": 0.4367525811483325,
+      "grad_norm": 0.04374077499179829,
+      "learning_rate": 9.580100630053e-06,
+      "loss": 0.3585,
+      "step": 490
+    },
+    {
+      "epoch": 0.44120924013964197,
+      "grad_norm": 0.0435642556725744,
+      "learning_rate": 9.564342236216444e-06,
+      "loss": 0.3673,
+      "step": 495
+    },
+    {
+      "epoch": 0.4456658991309515,
+      "grad_norm": 0.04616615791848655,
+      "learning_rate": 9.54830701823746e-06,
+      "loss": 0.343,
+      "step": 500
+    },
+    {
+      "epoch": 0.450122558122261,
+      "grad_norm": 0.05116268160745142,
+      "learning_rate": 9.531995948640722e-06,
+      "loss": 0.3682,
+      "step": 505
+    },
+    {
+      "epoch": 0.4545792171135705,
+      "grad_norm": 0.045000388036651476,
+      "learning_rate": 9.515410016681119e-06,
+      "loss": 0.3673,
+      "step": 510
+    },
+    {
+      "epoch": 0.45903587610488006,
+      "grad_norm": 0.039981904676462336,
+      "learning_rate": 9.498550228283745e-06,
+      "loss": 0.3573,
+      "step": 515
+    },
+    {
+      "epoch": 0.46349253509618954,
+      "grad_norm": 0.05079247509194735,
+      "learning_rate": 9.48141760598289e-06,
+      "loss": 0.3358,
+      "step": 520
+    },
+    {
+      "epoch": 0.4679491940874991,
+      "grad_norm": 0.04339754696474626,
+      "learning_rate": 9.464013188860034e-06,
+      "loss": 0.3697,
+      "step": 525
+    },
+    {
+      "epoch": 0.4724058530788086,
+      "grad_norm": 0.05672032368874533,
+      "learning_rate": 9.44633803248082e-06,
+      "loss": 0.3609,
+      "step": 530
+    },
+    {
+      "epoch": 0.4768625120701181,
+      "grad_norm": 0.03968689567244294,
+      "learning_rate": 9.428393208831035e-06,
+      "loss": 0.3782,
+      "step": 535
+    },
+    {
+      "epoch": 0.48131917106142763,
+      "grad_norm": 0.03823591428746807,
+      "learning_rate": 9.410179806251597e-06,
+      "loss": 0.3676,
+      "step": 540
+    },
+    {
+      "epoch": 0.4857758300527371,
+      "grad_norm": 0.04953625328978311,
+      "learning_rate": 9.391698929372545e-06,
+      "loss": 0.3843,
+      "step": 545
+    },
+    {
+      "epoch": 0.49023248904404665,
+      "grad_norm": 0.043174962416537774,
+      "learning_rate": 9.372951699046048e-06,
+      "loss": 0.3537,
+      "step": 550
+    },
+    {
+      "epoch": 0.4946891480353562,
+      "grad_norm": 0.037737887971063026,
+      "learning_rate": 9.353939252278425e-06,
+      "loss": 0.3559,
+      "step": 555
+    },
+    {
+      "epoch": 0.49914580702666567,
+      "grad_norm": 0.03944313396062169,
+      "learning_rate": 9.334662742161185e-06,
+      "loss": 0.3486,
+      "step": 560
+    },
+    {
+      "epoch": 0.5036024660179752,
+      "grad_norm": 0.040982285416120506,
+      "learning_rate": 9.315123337801088e-06,
+      "loss": 0.3833,
+      "step": 565
+    },
+    {
+      "epoch": 0.5080591250092847,
+      "grad_norm": 0.05250003442053583,
+      "learning_rate": 9.295322224249251e-06,
+      "loss": 0.3835,
+      "step": 570
+    },
+    {
+      "epoch": 0.5125157840005943,
+      "grad_norm": 0.04762096881101235,
+      "learning_rate": 9.275260602429268e-06,
+      "loss": 0.3655,
+      "step": 575
+    },
+    {
+      "epoch": 0.5169724429919037,
+      "grad_norm": 0.04042638366958117,
+      "learning_rate": 9.254939689064374e-06,
+      "loss": 0.3524,
+      "step": 580
+    },
+    {
+      "epoch": 0.5214291019832132,
+      "grad_norm": 0.03853478933299392,
+      "learning_rate": 9.234360716603654e-06,
+      "loss": 0.3344,
+      "step": 585
+    },
+    {
+      "epoch": 0.5258857609745228,
+      "grad_norm": 0.04253231208243496,
+      "learning_rate": 9.213524933147297e-06,
+      "loss": 0.3518,
+      "step": 590
+    },
+    {
+      "epoch": 0.5303424199658323,
+      "grad_norm": 0.03781916769626258,
+      "learning_rate": 9.1924336023709e-06,
+      "loss": 0.3581,
+      "step": 595
+    },
+    {
+      "epoch": 0.5347990789571418,
+      "grad_norm": 0.042956152801003476,
+      "learning_rate": 9.171088003448816e-06,
+      "loss": 0.3751,
+      "step": 600
+    },
+    {
+      "epoch": 0.5392557379484513,
+      "grad_norm": 0.042733495391241834,
+      "learning_rate": 9.149489430976592e-06,
+      "loss": 0.3735,
+      "step": 605
+    },
+    {
+      "epoch": 0.5437123969397608,
+      "grad_norm": 0.038555605729189334,
+      "learning_rate": 9.12763919489244e-06,
+      "loss": 0.3343,
+      "step": 610
+    },
+    {
+      "epoch": 0.5481690559310703,
+      "grad_norm": 0.04878126396745322,
+      "learning_rate": 9.105538620397786e-06,
+      "loss": 0.3693,
+      "step": 615
+    },
+    {
+      "epoch": 0.5526257149223799,
+      "grad_norm": 0.0388842791468199,
+      "learning_rate": 9.083189047876917e-06,
+      "loss": 0.3319,
+      "step": 620
+    },
+    {
+      "epoch": 0.5570823739136894,
+      "grad_norm": 0.045281525903800586,
+      "learning_rate": 9.060591832815663e-06,
+      "loss": 0.3483,
+      "step": 625
+    },
+    {
+      "epoch": 0.5615390329049988,
+      "grad_norm": 0.037306006153875235,
+      "learning_rate": 9.037748345719206e-06,
+      "loss": 0.3715,
+      "step": 630
+    },
+    {
+      "epoch": 0.5659956918963084,
+      "grad_norm": 0.04232483585848596,
+      "learning_rate": 9.014659972028954e-06,
+      "loss": 0.3784,
+      "step": 635
+    },
+    {
+      "epoch": 0.5704523508876179,
+      "grad_norm": 0.04366418393202621,
+      "learning_rate": 8.991328112038508e-06,
+      "loss": 0.3421,
+      "step": 640
+    },
+    {
+      "epoch": 0.5749090098789275,
+      "grad_norm": 0.042775684521190016,
+      "learning_rate": 8.96775418080875e-06,
+      "loss": 0.3641,
+      "step": 645
+    },
+    {
+      "epoch": 0.579365668870237,
+      "grad_norm": 0.03905324730933948,
+      "learning_rate": 8.943939608082008e-06,
+      "loss": 0.326,
+      "step": 650
+    },
+    {
+      "epoch": 0.5838223278615464,
+      "grad_norm": 0.0439109485141227,
+      "learning_rate": 8.919885838195346e-06,
+      "loss": 0.38,
+      "step": 655
+    },
+    {
+      "epoch": 0.588278986852856,
+      "grad_norm": 0.040278188616367915,
+      "learning_rate": 8.895594329992971e-06,
+      "loss": 0.3554,
+      "step": 660
+    },
+    {
+      "epoch": 0.5927356458441655,
+      "grad_norm": 0.04296489937369988,
+      "learning_rate": 8.871066556737749e-06,
+      "loss": 0.3515,
+      "step": 665
+    },
+    {
+      "epoch": 0.597192304835475,
+      "grad_norm": 0.03219193900520065,
+      "learning_rate": 8.846304006021853e-06,
+      "loss": 0.3065,
+      "step": 670
+    },
+    {
+      "epoch": 0.6016489638267846,
+      "grad_norm": 0.03750987603517473,
+      "learning_rate": 8.82130817967655e-06,
+      "loss": 0.3753,
+      "step": 675
+    },
+    {
+      "epoch": 0.606105622818094,
+      "grad_norm": 0.045258173403080484,
+      "learning_rate": 8.796080593681104e-06,
+      "loss": 0.375,
+      "step": 680
+    },
+    {
+      "epoch": 0.6105622818094035,
+      "grad_norm": 0.03803993220538302,
+      "learning_rate": 8.77062277807084e-06,
+      "loss": 0.356,
+      "step": 685
+    },
+    {
+      "epoch": 0.6150189408007131,
+      "grad_norm": 0.04095600232061625,
+      "learning_rate": 8.744936276844348e-06,
+      "loss": 0.3482,
+      "step": 690
+    },
+    {
+      "epoch": 0.6194755997920226,
+      "grad_norm": 0.04108431793653308,
+      "learning_rate": 8.719022647869839e-06,
+      "loss": 0.3558,
+      "step": 695
+    },
+    {
+      "epoch": 0.6239322587833321,
+      "grad_norm": 0.04300826921850201,
+      "learning_rate": 8.692883462790664e-06,
+      "loss": 0.347,
+      "step": 700
+    },
+    {
+      "epoch": 0.6283889177746416,
+      "grad_norm": 0.04147196857931913,
+      "learning_rate": 8.666520306929987e-06,
+      "loss": 0.3391,
+      "step": 705
+    },
+    {
+      "epoch": 0.6328455767659511,
+      "grad_norm": 0.03487134011785261,
+      "learning_rate": 8.639934779194647e-06,
+      "loss": 0.3232,
+      "step": 710
+    },
+    {
+      "epoch": 0.6373022357572606,
+      "grad_norm": 0.03649852892645952,
+      "learning_rate": 8.613128491978181e-06,
+      "loss": 0.3223,
+      "step": 715
+    },
+    {
+      "epoch": 0.6417588947485702,
+      "grad_norm": 0.04596879876204484,
+      "learning_rate": 8.586103071063034e-06,
+      "loss": 0.3733,
+      "step": 720
+    },
+    {
+      "epoch": 0.6462155537398797,
+      "grad_norm": 0.04225087710012865,
+      "learning_rate": 8.558860155521948e-06,
+      "loss": 0.3584,
+      "step": 725
+    },
+    {
+      "epoch": 0.6506722127311891,
+      "grad_norm": 0.040614068313829625,
+      "learning_rate": 8.53140139761857e-06,
+      "loss": 0.3778,
+      "step": 730
+    },
+    {
+      "epoch": 0.6551288717224987,
+      "grad_norm": 0.038923901123470606,
+      "learning_rate": 8.50372846270723e-06,
+      "loss": 0.355,
+      "step": 735
+    },
+    {
+      "epoch": 0.6595855307138082,
+      "grad_norm": 0.04003805383028198,
+      "learning_rate": 8.475843029131942e-06,
+      "loss": 0.3446,
+      "step": 740
+    },
+    {
+      "epoch": 0.6640421897051177,
+      "grad_norm": 0.03817113093765007,
+      "learning_rate": 8.447746788124618e-06,
+      "loss": 0.3533,
+      "step": 745
+    },
+    {
+      "epoch": 0.6684988486964273,
+      "grad_norm": 0.03946386120647576,
+      "learning_rate": 8.419441443702485e-06,
+      "loss": 0.3385,
+      "step": 750
+    },
+    {
+      "epoch": 0.6729555076877367,
+      "grad_norm": 0.04594980639856022,
+      "learning_rate": 8.390928712564754e-06,
+      "loss": 0.3468,
+      "step": 755
+    },
+    {
+      "epoch": 0.6774121666790462,
+      "grad_norm": 0.037734409170981406,
+      "learning_rate": 8.362210323988486e-06,
+      "loss": 0.3142,
+      "step": 760
+    },
+    {
+      "epoch": 0.6818688256703558,
+      "grad_norm": 0.04135989239417575,
+      "learning_rate": 8.33328801972373e-06,
+      "loss": 0.3512,
+      "step": 765
+    },
+    {
+      "epoch": 0.6863254846616653,
+      "grad_norm": 0.040399706529750154,
+      "learning_rate": 8.30416355388787e-06,
+      "loss": 0.3441,
+      "step": 770
+    },
+    {
+      "epoch": 0.6907821436529749,
+      "grad_norm": 0.04632767114532932,
+      "learning_rate": 8.274838692859249e-06,
+      "loss": 0.3492,
+      "step": 775
+    },
+    {
+      "epoch": 0.6952388026442843,
+      "grad_norm": 0.0466278822946521,
+      "learning_rate": 8.245315215170036e-06,
+      "loss": 0.3634,
+      "step": 780
+    },
+    {
+      "epoch": 0.6996954616355938,
+      "grad_norm": 0.03854497108096806,
+      "learning_rate": 8.215594911398366e-06,
+      "loss": 0.3818,
+      "step": 785
+    },
+    {
+      "epoch": 0.7041521206269034,
+      "grad_norm": 0.03807528541379026,
+      "learning_rate": 8.185679584059733e-06,
+      "loss": 0.3399,
+      "step": 790
+    },
+    {
+      "epoch": 0.7086087796182129,
+      "grad_norm": 0.039364528432836096,
+      "learning_rate": 8.155571047497675e-06,
+      "loss": 0.3471,
+      "step": 795
+    },
+    {
+      "epoch": 0.7130654386095224,
+      "grad_norm": 0.04009146302797121,
+      "learning_rate": 8.125271127773728e-06,
+      "loss": 0.317,
+      "step": 800
+    },
+    {
+      "epoch": 0.717522097600832,
+      "grad_norm": 0.037371893337503514,
+      "learning_rate": 8.09478166255669e-06,
+      "loss": 0.3371,
+      "step": 805
+    },
+    {
+      "epoch": 0.7219787565921414,
+      "grad_norm": 0.034113185631526655,
+      "learning_rate": 8.064104501011154e-06,
+      "loss": 0.3316,
+      "step": 810
+    },
+    {
+      "epoch": 0.7264354155834509,
+      "grad_norm": 0.041522627293234436,
+      "learning_rate": 8.033241503685366e-06,
+      "loss": 0.346,
+      "step": 815
+    },
+    {
+      "epoch": 0.7308920745747605,
+      "grad_norm": 0.04352859369847954,
+      "learning_rate": 8.00219454239838e-06,
+      "loss": 0.3493,
+      "step": 820
+    },
+    {
+      "epoch": 0.73534873356607,
+      "grad_norm": 0.040392710281690065,
+      "learning_rate": 7.970965500126534e-06,
+      "loss": 0.3506,
+      "step": 825
+    },
+    {
+      "epoch": 0.7398053925573795,
+      "grad_norm": 0.037788817713187726,
+      "learning_rate": 7.93955627088925e-06,
+      "loss": 0.3449,
+      "step": 830
+    },
+    {
+      "epoch": 0.744262051548689,
+      "grad_norm": 0.03913978671424209,
+      "learning_rate": 7.907968759634165e-06,
+      "loss": 0.3416,
+      "step": 835
+    },
+    {
+      "epoch": 0.7487187105399985,
+      "grad_norm": 0.03647678211671544,
+      "learning_rate": 7.876204882121592e-06,
+      "loss": 0.3632,
+      "step": 840
+    },
+    {
+      "epoch": 0.753175369531308,
+      "grad_norm": 0.03824752767359855,
+      "learning_rate": 7.844266564808333e-06,
+      "loss": 0.3506,
+      "step": 845
+    },
+    {
+      "epoch": 0.7576320285226176,
+      "grad_norm": 0.04193412196826429,
+      "learning_rate": 7.812155744730842e-06,
+      "loss": 0.3514,
+      "step": 850
+    },
+    {
+      "epoch": 0.7620886875139271,
+      "grad_norm": 0.03719881876463841,
+      "learning_rate": 7.779874369387747e-06,
+      "loss": 0.3744,
+      "step": 855
+    },
+    {
+      "epoch": 0.7665453465052365,
+      "grad_norm": 0.039523606403741154,
+      "learning_rate": 7.747424396621728e-06,
+      "loss": 0.3464,
+      "step": 860
+    },
+    {
+      "epoch": 0.7710020054965461,
+      "grad_norm": 0.038967790741718966,
+      "learning_rate": 7.71480779450078e-06,
+      "loss": 0.3522,
+      "step": 865
+    },
+    {
+      "epoch": 0.7754586644878556,
+      "grad_norm": 0.0338399453339563,
+      "learning_rate": 7.682026541198859e-06,
+      "loss": 0.3175,
+      "step": 870
+    },
+    {
+      "epoch": 0.7799153234791651,
+      "grad_norm": 0.03838893499453238,
+      "learning_rate": 7.649082624875889e-06,
+      "loss": 0.371,
+      "step": 875
+    },
+    {
+      "epoch": 0.7843719824704747,
+      "grad_norm": 0.03582979505427013,
+      "learning_rate": 7.615978043557195e-06,
+      "loss": 0.3545,
+      "step": 880
+    },
+    {
+      "epoch": 0.7888286414617841,
+      "grad_norm": 0.03627985350213129,
+      "learning_rate": 7.582714805012326e-06,
+      "loss": 0.3474,
+      "step": 885
+    },
+    {
+      "epoch": 0.7932853004530936,
+      "grad_norm": 0.03850554835854682,
+      "learning_rate": 7.549294926633273e-06,
+      "loss": 0.3464,
+      "step": 890
+    },
+    {
+      "epoch": 0.7977419594444032,
+      "grad_norm": 0.03875905385241387,
+      "learning_rate": 7.515720435312124e-06,
+      "loss": 0.3536,
+      "step": 895
+    },
+    {
+      "epoch": 0.8021986184357127,
+      "grad_norm": 0.03902115614104229,
+      "learning_rate": 7.481993367318139e-06,
+      "loss": 0.3494,
+      "step": 900
+    },
+    {
+      "epoch": 0.8066552774270223,
+      "grad_norm": 0.042663509463480305,
+      "learning_rate": 7.4481157681742376e-06,
+      "loss": 0.3693,
+      "step": 905
+    },
+    {
+      "epoch": 0.8111119364183317,
+      "grad_norm": 0.03463878522652425,
+      "learning_rate": 7.414089692532953e-06,
+      "loss": 0.3597,
+      "step": 910
+    },
+    {
+      "epoch": 0.8155685954096412,
+      "grad_norm": 0.04096150483153926,
+      "learning_rate": 7.379917204051812e-06,
+      "loss": 0.3594,
+      "step": 915
+    },
+    {
+      "epoch": 0.8200252544009508,
+      "grad_norm": 0.04402866398417241,
+      "learning_rate": 7.3456003752681755e-06,
+      "loss": 0.3414,
+      "step": 920
+    },
+    {
+      "epoch": 0.8244819133922603,
+      "grad_norm": 0.04139811223309286,
+      "learning_rate": 7.311141287473545e-06,
+      "loss": 0.3224,
+      "step": 925
+    },
+    {
+      "epoch": 0.8289385723835698,
+      "grad_norm": 0.06645909647569262,
+      "learning_rate": 7.276542030587328e-06,
+      "loss": 0.3456,
+      "step": 930
+    },
+    {
+      "epoch": 0.8333952313748793,
+      "grad_norm": 0.044636161342359676,
+      "learning_rate": 7.2418047030300905e-06,
+      "loss": 0.3353,
+      "step": 935
+    },
+    {
+      "epoch": 0.8378518903661888,
+      "grad_norm": 0.035318060235713856,
+      "learning_rate": 7.206931411596288e-06,
+      "loss": 0.3288,
+      "step": 940
+    },
+    {
+      "epoch": 0.8423085493574983,
+      "grad_norm": 0.03828050355505084,
+      "learning_rate": 7.171924271326483e-06,
+      "loss": 0.3707,
+      "step": 945
+    },
+    {
+      "epoch": 0.8467652083488079,
+      "grad_norm": 0.042224528093265754,
+      "learning_rate": 7.136785405379088e-06,
+      "loss": 0.3595,
+      "step": 950
+    },
+    {
+      "epoch": 0.8512218673401174,
+      "grad_norm": 0.04480625231480598,
+      "learning_rate": 7.101516944901576e-06,
+      "loss": 0.3619,
+      "step": 955
+    },
+    {
+      "epoch": 0.8556785263314268,
+      "grad_norm": 0.03576964869540681,
+      "learning_rate": 7.066121028901236e-06,
+      "loss": 0.3464,
+      "step": 960
+    },
+    {
+      "epoch": 0.8601351853227364,
+      "grad_norm": 0.030991978553480678,
+      "learning_rate": 7.030599804115452e-06,
+      "loss": 0.3607,
+      "step": 965
+    },
+    {
+      "epoch": 0.8645918443140459,
+      "grad_norm": 0.03650657693648493,
+      "learning_rate": 6.99495542488149e-06,
+      "loss": 0.3547,
+      "step": 970
+    },
+    {
+      "epoch": 0.8690485033053554,
+      "grad_norm": 0.039958685112108004,
+      "learning_rate": 6.95919005300585e-06,
+      "loss": 0.3435,
+      "step": 975
+    },
+    {
+      "epoch": 0.873505162296665,
+      "grad_norm": 0.04077064091002527,
+      "learning_rate": 6.923305857633153e-06,
+      "loss": 0.3351,
+      "step": 980
+    },
+    {
+      "epoch": 0.8779618212879744,
+      "grad_norm": 0.03587466267665625,
+      "learning_rate": 6.887305015114576e-06,
+      "loss": 0.3512,
+      "step": 985
+    },
+    {
+      "epoch": 0.8824184802792839,
+      "grad_norm": 0.034539337349791706,
+      "learning_rate": 6.851189708875867e-06,
+      "loss": 0.3696,
+      "step": 990
+    },
+    {
+      "epoch": 0.8868751392705935,
+      "grad_norm": 0.038997841115035806,
+      "learning_rate": 6.8149621292849175e-06,
+      "loss": 0.3254,
+      "step": 995
+    },
+    {
+      "epoch": 0.891331798261903,
+      "grad_norm": 0.038220707196931394,
+      "learning_rate": 6.7786244735189186e-06,
+      "loss": 0.3629,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8957884572532125,
+      "grad_norm": 0.0434042294031072,
+      "learning_rate": 6.742178945431101e-06,
+      "loss": 0.3354,
+      "step": 1005
+    },
+    {
+      "epoch": 0.900245116244522,
+      "grad_norm": 0.03433600018730854,
+      "learning_rate": 6.705627755417083e-06,
+      "loss": 0.3963,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9047017752358315,
+      "grad_norm": 0.03903725290243943,
+      "learning_rate": 6.668973120280797e-06,
+      "loss": 0.3546,
+      "step": 1015
+    },
+    {
+      "epoch": 0.909158434227141,
+      "grad_norm": 0.038365695036849674,
+      "learning_rate": 6.632217263100053e-06,
+      "loss": 0.3375,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9136150932184506,
+      "grad_norm": 0.03990475305692419,
+      "learning_rate": 6.5953624130917035e-06,
+      "loss": 0.3331,
+      "step": 1025
+    },
+    {
+      "epoch": 0.9180717522097601,
+      "grad_norm": 0.040794399359075834,
+      "learning_rate": 6.558410805476451e-06,
+      "loss": 0.3458,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9225284112010697,
+      "grad_norm": 0.03912702525863214,
+      "learning_rate": 6.521364681343273e-06,
+      "loss": 0.3524,
+      "step": 1035
+    },
+    {
+      "epoch": 0.9269850701923791,
+      "grad_norm": 0.03661850369975111,
+      "learning_rate": 6.484226287513512e-06,
+      "loss": 0.3718,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9314417291836886,
+      "grad_norm": 0.03440847203779226,
+      "learning_rate": 6.446997876404603e-06,
+      "loss": 0.3533,
+      "step": 1045
+    },
+    {
+      "epoch": 0.9358983881749982,
+      "grad_norm": 0.037084675468021515,
+      "learning_rate": 6.409681705893461e-06,
+      "loss": 0.3707,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9403550471663077,
+      "grad_norm": 0.03106927125420908,
+      "learning_rate": 6.37228003917955e-06,
+      "loss": 0.3331,
+      "step": 1055
+    },
+    {
+      "epoch": 0.9448117061576172,
+      "grad_norm": 0.043893802285259104,
+      "learning_rate": 6.3347951446476194e-06,
+      "loss": 0.3375,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9492683651489267,
+      "grad_norm": 0.03789346876693591,
+      "learning_rate": 6.297229295730125e-06,
+      "loss": 0.3574,
+      "step": 1065
+    },
+    {
+      "epoch": 0.9537250241402362,
+      "grad_norm": 0.04123920807743081,
+      "learning_rate": 6.2595847707693505e-06,
+      "loss": 0.3607,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9581816831315457,
+      "grad_norm": 0.03746001686079855,
+      "learning_rate": 6.221863852879224e-06,
+      "loss": 0.3497,
+      "step": 1075
+    },
+    {
+      "epoch": 0.9626383421228553,
+      "grad_norm": 0.037332308666625603,
+      "learning_rate": 6.184068829806853e-06,
+      "loss": 0.3406,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9670950011141648,
+      "grad_norm": 0.03600032344614023,
+      "learning_rate": 6.146201993793772e-06,
+      "loss": 0.334,
+      "step": 1085
+    },
+    {
+      "epoch": 0.9715516601054742,
+      "grad_norm": 0.03913531342479123,
+      "learning_rate": 6.10826564143692e-06,
+      "loss": 0.3239,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9760083190967838,
+      "grad_norm": 0.044657313605693603,
+      "learning_rate": 6.0702620735493535e-06,
+      "loss": 0.3517,
+      "step": 1095
+    },
+    {
+      "epoch": 0.9804649780880933,
+      "grad_norm": 0.036697071260256314,
+      "learning_rate": 6.0321935950207e-06,
+      "loss": 0.364,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9849216370794028,
+      "grad_norm": 0.047007092034447036,
+      "learning_rate": 5.994062514677377e-06,
+      "loss": 0.3365,
+      "step": 1105
+    },
+    {
+      "epoch": 0.9893782960707124,
+      "grad_norm": 0.038567817770514705,
+      "learning_rate": 5.9558711451425555e-06,
+      "loss": 0.3437,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9938349550620218,
+      "grad_norm": 0.046535006533488465,
+      "learning_rate": 5.917621802695903e-06,
+      "loss": 0.3674,
+      "step": 1115
+    },
+    {
+      "epoch": 0.9982916140533313,
+      "grad_norm": 0.044782400881786595,
+      "learning_rate": 5.879316807133103e-06,
+      "loss": 0.3539,
+      "step": 1120
+    },
+    {
+      "epoch": 0.9991829458515933,
+      "eval_loss": 0.3121582567691803,
+      "eval_runtime": 28.1501,
+      "eval_samples_per_second": 19.325,
+      "eval_steps_per_second": 4.831,
+      "step": 1121
+    },
+    {
+      "epoch": 1.0035653271930476,
+      "grad_norm": 0.035018958725684814,
+      "learning_rate": 5.840958481625163e-06,
+      "loss": 0.3768,
+      "step": 1125
+    },
+    {
+      "epoch": 1.0080219861843571,
+      "grad_norm": 0.08275303281391562,
+      "learning_rate": 5.8025491525775125e-06,
+      "loss": 0.3373,
+      "step": 1130
+    },
+    {
+      "epoch": 1.0124786451756667,
+      "grad_norm": 0.036690917598704145,
+      "learning_rate": 5.764091149488912e-06,
+      "loss": 0.3191,
+      "step": 1135
+    },
+    {
+      "epoch": 1.0169353041669762,
+      "grad_norm": 0.038089309373433904,
+      "learning_rate": 5.725586804810166e-06,
+      "loss": 0.3377,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0213919631582857,
+      "grad_norm": 0.04219155515782442,
+      "learning_rate": 5.687038453802663e-06,
+      "loss": 0.33,
+      "step": 1145
+    },
+    {
+      "epoch": 1.0258486221495953,
+      "grad_norm": 0.03643779050650904,
+      "learning_rate": 5.648448434396747e-06,
+      "loss": 0.3352,
+      "step": 1150
+    },
+    {
+      "epoch": 1.0303052811409048,
+      "grad_norm": 0.044990286569605006,
+      "learning_rate": 5.609819087049923e-06,
+      "loss": 0.3233,
+      "step": 1155
+    },
+    {
+      "epoch": 1.0347619401322141,
+      "grad_norm": 0.0673142495663998,
+      "learning_rate": 5.571152754604901e-06,
+      "loss": 0.3164,
+      "step": 1160
+    },
+    {
+      "epoch": 1.0392185991235237,
+      "grad_norm": 0.044924920507469504,
+      "learning_rate": 5.5324517821475165e-06,
+      "loss": 0.3234,
+      "step": 1165
+    },
+    {
+      "epoch": 1.0436752581148332,
+      "grad_norm": 0.04520885855234551,
+      "learning_rate": 5.493718516864496e-06,
+      "loss": 0.3572,
+      "step": 1170
+    },
+    {
+      "epoch": 1.0481319171061427,
+      "grad_norm": 0.0488015684618307,
+      "learning_rate": 5.454955307901103e-06,
+      "loss": 0.3286,
+      "step": 1175
+    },
+    {
+      "epoch": 1.0525885760974523,
+      "grad_norm": 0.043929046851137146,
+      "learning_rate": 5.416164506218662e-06,
+      "loss": 0.3347,
+      "step": 1180
+    },
+    {
+      "epoch": 1.0570452350887618,
+      "grad_norm": 0.039430384622077694,
+      "learning_rate": 5.3773484644519825e-06,
+      "loss": 0.346,
+      "step": 1185
+    },
+    {
+      "epoch": 1.0615018940800713,
+      "grad_norm": 0.050917021723215446,
+      "learning_rate": 5.338509536766662e-06,
+      "loss": 0.3502,
+      "step": 1190
+    },
+    {
+      "epoch": 1.0659585530713809,
+      "grad_norm": 0.0432190687785534,
+      "learning_rate": 5.299650078716313e-06,
+      "loss": 0.343,
+      "step": 1195
+    },
+    {
+      "epoch": 1.0704152120626904,
+      "grad_norm": 0.05235380991950498,
+      "learning_rate": 5.260772447099704e-06,
+      "loss": 0.3179,
+      "step": 1200
+    },
+    {
+      "epoch": 1.074871871054,
+      "grad_norm": 0.043917180636865144,
+      "learning_rate": 5.2218789998178125e-06,
+      "loss": 0.3098,
+      "step": 1205
+    },
+    {
+      "epoch": 1.0793285300453093,
+      "grad_norm": 0.039598233352694974,
+      "learning_rate": 5.182972095730828e-06,
+      "loss": 0.3299,
+      "step": 1210
+    },
+    {
+      "epoch": 1.0837851890366188,
+      "grad_norm": 0.03914796341413229,
+      "learning_rate": 5.144054094515088e-06,
+      "loss": 0.3191,
+      "step": 1215
+    },
+    {
+      "epoch": 1.0882418480279283,
+      "grad_norm": 0.04563116912150565,
+      "learning_rate": 5.1051273565199564e-06,
+      "loss": 0.3465,
+      "step": 1220
+    },
+    {
+      "epoch": 1.0926985070192379,
+      "grad_norm": 0.04488310022064193,
+      "learning_rate": 5.0661942426246825e-06,
+      "loss": 0.3336,
+      "step": 1225
+    },
+    {
+      "epoch": 1.0971551660105474,
+      "grad_norm": 0.045624300677554144,
+      "learning_rate": 5.0272571140952076e-06,
+      "loss": 0.3366,
+      "step": 1230
+    },
+    {
+      "epoch": 1.101611825001857,
+      "grad_norm": 0.04547698828207826,
+      "learning_rate": 4.988318332440958e-06,
+      "loss": 0.3401,
+      "step": 1235
+    },
+    {
+      "epoch": 1.1060684839931665,
+      "grad_norm": 0.0352328063030309,
+      "learning_rate": 4.949380259271618e-06,
+      "loss": 0.3429,
+      "step": 1240
+    },
+    {
+      "epoch": 1.110525142984476,
+      "grad_norm": 0.03628153680973482,
+      "learning_rate": 4.910445256153909e-06,
+      "loss": 0.3685,
+      "step": 1245
+    },
+    {
+      "epoch": 1.1149818019757856,
+      "grad_norm": 0.05406284923018293,
+      "learning_rate": 4.871515684468348e-06,
+      "loss": 0.3255,
+      "step": 1250
+    },
+    {
+      "epoch": 1.119438460967095,
+      "grad_norm": 0.04417976412734551,
+      "learning_rate": 4.832593905266045e-06,
+      "loss": 0.3255,
+      "step": 1255
+    },
+    {
+      "epoch": 1.1238951199584046,
+      "grad_norm": 0.04882094138393501,
+      "learning_rate": 4.793682279125504e-06,
+      "loss": 0.3233,
+      "step": 1260
+    },
+    {
+      "epoch": 1.128351778949714,
+      "grad_norm": 0.04666808909953559,
+      "learning_rate": 4.754783166009443e-06,
+      "loss": 0.3381,
+      "step": 1265
+    },
+    {
+      "epoch": 1.1328084379410235,
+      "grad_norm": 0.0393273395144626,
+      "learning_rate": 4.715898925121683e-06,
+      "loss": 0.3362,
+      "step": 1270
+    },
+    {
+      "epoch": 1.137265096932333,
+      "grad_norm": 0.042614792670262726,
+      "learning_rate": 4.677031914764052e-06,
+      "loss": 0.3565,
+      "step": 1275
+    },
+    {
+      "epoch": 1.1417217559236426,
+      "grad_norm": 0.04265242813984368,
+      "learning_rate": 4.638184492193357e-06,
+      "loss": 0.3391,
+      "step": 1280
+    },
+    {
+      "epoch": 1.146178414914952,
+      "grad_norm": 0.05253572445021966,
+      "learning_rate": 4.59935901347842e-06,
+      "loss": 0.3444,
+      "step": 1285
+    },
+    {
+      "epoch": 1.1506350739062616,
+      "grad_norm": 0.04661513504414531,
+      "learning_rate": 4.560557833357188e-06,
+      "loss": 0.3324,
+      "step": 1290
+    },
+    {
+      "epoch": 1.1550917328975712,
+      "grad_norm": 0.05181632502738739,
+      "learning_rate": 4.521783305093906e-06,
+      "loss": 0.3593,
+      "step": 1295
+    },
+    {
+      "epoch": 1.1595483918888807,
+      "grad_norm": 0.043190087583387604,
+      "learning_rate": 4.483037780336411e-06,
+      "loss": 0.3313,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1640050508801902,
+      "grad_norm": 0.04699548343789582,
+      "learning_rate": 4.444323608973498e-06,
+      "loss": 0.3235,
+      "step": 1305
+    },
+    {
+      "epoch": 1.1684617098714996,
+      "grad_norm": 0.04832144947499993,
+      "learning_rate": 4.4056431389923925e-06,
+      "loss": 0.3249,
+      "step": 1310
+    },
+    {
+      "epoch": 1.172918368862809,
+      "grad_norm": 0.049877024800225496,
+      "learning_rate": 4.366998716336364e-06,
+      "loss": 0.3289,
+      "step": 1315
+    },
+    {
+      "epoch": 1.1773750278541186,
+      "grad_norm": 0.050518314153578,
+      "learning_rate": 4.328392684762432e-06,
+      "loss": 0.3227,
+      "step": 1320
+    },
+    {
+      "epoch": 1.1818316868454282,
+      "grad_norm": 0.05274930662575011,
+      "learning_rate": 4.289827385699225e-06,
+      "loss": 0.3389,
+      "step": 1325
+    },
+    {
+      "epoch": 1.1862883458367377,
+      "grad_norm": 0.04314769892456159,
+      "learning_rate": 4.251305158104973e-06,
+      "loss": 0.3325,
+      "step": 1330
+    },
+    {
+      "epoch": 1.1907450048280472,
+      "grad_norm": 0.05744060663520273,
+      "learning_rate": 4.212828338325655e-06,
+      "loss": 0.3501,
+      "step": 1335
+    },
+    {
+      "epoch": 1.1952016638193568,
+      "grad_norm": 0.04788383703548173,
+      "learning_rate": 4.174399259953292e-06,
+      "loss": 0.3182,
+      "step": 1340
+    },
+    {
+      "epoch": 1.1996583228106663,
+      "grad_norm": 0.05322839124311334,
+      "learning_rate": 4.136020253684426e-06,
+      "loss": 0.3236,
+      "step": 1345
+    },
+    {
+      "epoch": 1.2041149818019758,
+      "grad_norm": 0.04192717948800928,
+      "learning_rate": 4.097693647178765e-06,
+      "loss": 0.3116,
+      "step": 1350
+    },
+    {
+      "epoch": 1.2085716407932854,
+      "grad_norm": 0.07466924907391985,
+      "learning_rate": 4.059421764917998e-06,
+      "loss": 0.336,
+      "step": 1355
+    },
+    {
+      "epoch": 1.213028299784595,
+      "grad_norm": 0.047779612339586844,
+      "learning_rate": 4.021206928064837e-06,
+      "loss": 0.3199,
+      "step": 1360
+    },
+    {
+      "epoch": 1.2174849587759042,
+      "grad_norm": 0.04890716812809991,
+      "learning_rate": 3.983051454322227e-06,
+      "loss": 0.3042,
+      "step": 1365
+    },
+    {
+      "epoch": 1.2219416177672138,
+      "grad_norm": 0.05622057359534205,
+      "learning_rate": 3.944957657792779e-06,
+      "loss": 0.315,
+      "step": 1370
+    },
+    {
+      "epoch": 1.2263982767585233,
+      "grad_norm": 0.05816972903766055,
+      "learning_rate": 3.906927848838428e-06,
+      "loss": 0.3447,
+      "step": 1375
+    },
+    {
+      "epoch": 1.2308549357498328,
+      "grad_norm": 0.0521170519743598,
+      "learning_rate": 3.868964333940308e-06,
+      "loss": 0.3287,
+      "step": 1380
+    },
+    {
+      "epoch": 1.2353115947411424,
+      "grad_norm": 0.05613111708237626,
+      "learning_rate": 3.83106941555886e-06,
+      "loss": 0.3514,
+      "step": 1385
+    },
+    {
+      "epoch": 1.239768253732452,
+      "grad_norm": 0.05079823220287822,
+      "learning_rate": 3.7932453919942002e-06,
+      "loss": 0.2976,
+      "step": 1390
+    },
+    {
+      "epoch": 1.2442249127237615,
+      "grad_norm": 0.04588237737238143,
+      "learning_rate": 3.7554945572467262e-06,
+      "loss": 0.3429,
+      "step": 1395
+    },
+    {
+      "epoch": 1.248681571715071,
+      "grad_norm": 0.06835690002137525,
+      "learning_rate": 3.7178192008779746e-06,
+      "loss": 0.3251,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2531382307063805,
+      "grad_norm": 0.050609979224703276,
+      "learning_rate": 3.6802216078717825e-06,
+      "loss": 0.3403,
+      "step": 1405
+    },
+    {
+      "epoch": 1.2575948896976898,
+      "grad_norm": 0.053908001625159505,
+      "learning_rate": 3.642704058495691e-06,
+      "loss": 0.3237,
+      "step": 1410
+    },
+    {
+      "epoch": 1.2620515486889996,
+      "grad_norm": 0.06722754734917484,
+      "learning_rate": 3.6052688281626448e-06,
+      "loss": 0.3298,
+      "step": 1415
+    },
+    {
+      "epoch": 1.266508207680309,
+      "grad_norm": 0.04804813484670096,
+      "learning_rate": 3.5679181872930067e-06,
+      "loss": 0.3137,
+      "step": 1420
+    },
+    {
+      "epoch": 1.2709648666716185,
+      "grad_norm": 0.052833907520638754,
+      "learning_rate": 3.5306544011768414e-06,
+      "loss": 0.3503,
+      "step": 1425
+    },
+    {
+      "epoch": 1.275421525662928,
+      "grad_norm": 0.05272400381575242,
+      "learning_rate": 3.493479729836534e-06,
+      "loss": 0.3093,
+      "step": 1430
+    },
+    {
+      "epoch": 1.2798781846542375,
+      "grad_norm": 0.0580236610090227,
+      "learning_rate": 3.4563964278897267e-06,
+      "loss": 0.3576,
+      "step": 1435
+    },
+    {
+      "epoch": 1.284334843645547,
+      "grad_norm": 0.06013873751374385,
+      "learning_rate": 3.4194067444125645e-06,
+      "loss": 0.3231,
+      "step": 1440
+    },
+    {
+      "epoch": 1.2887915026368566,
+      "grad_norm": 0.056386412770539907,
+      "learning_rate": 3.3825129228033043e-06,
+      "loss": 0.3109,
+      "step": 1445
+    },
+    {
+      "epoch": 1.2932481616281661,
+      "grad_norm": 0.05917179185232147,
+      "learning_rate": 3.3457172006462486e-06,
+      "loss": 0.3454,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2977048206194757,
+      "grad_norm": 0.051639399606407455,
+      "learning_rate": 3.3090218095760296e-06,
+      "loss": 0.3448,
+      "step": 1455
+    },
+    {
+      "epoch": 1.3021614796107852,
+      "grad_norm": 0.04783319813503841,
+      "learning_rate": 3.272428975142279e-06,
+      "loss": 0.2983,
+      "step": 1460
+    },
+    {
+      "epoch": 1.3066181386020945,
+      "grad_norm": 0.05087706067935069,
+      "learning_rate": 3.235940916674636e-06,
+      "loss": 0.3224,
+      "step": 1465
+    },
+    {
+      "epoch": 1.311074797593404,
+      "grad_norm": 0.0531382115416805,
+      "learning_rate": 3.19955984714815e-06,
+      "loss": 0.3081,
+      "step": 1470
+    },
+    {
+      "epoch": 1.3155314565847136,
+      "grad_norm": 0.060724547940211995,
+      "learning_rate": 3.1632879730490705e-06,
+      "loss": 0.309,
+      "step": 1475
+    },
+    {
+      "epoch": 1.3199881155760231,
+      "grad_norm": 0.05180410376030714,
+      "learning_rate": 3.127127494241018e-06,
+      "loss": 0.3412,
+      "step": 1480
+    },
+    {
+      "epoch": 1.3244447745673327,
+      "grad_norm": 0.06436906484669133,
+      "learning_rate": 3.091080603831568e-06,
+      "loss": 0.3304,
+      "step": 1485
+    },
+    {
+      "epoch": 1.3289014335586422,
+      "grad_norm": 0.06141323563691381,
+      "learning_rate": 3.055149488039239e-06,
+      "loss": 0.3482,
+      "step": 1490
+    },
+    {
+      "epoch": 1.3333580925499517,
+      "grad_norm": 0.05073605621235636,
+      "learning_rate": 3.0193363260609045e-06,
+      "loss": 0.3118,
+      "step": 1495
+    },
+    {
+      "epoch": 1.3378147515412613,
+      "grad_norm": 0.06151762054710644,
+      "learning_rate": 2.983643289939614e-06,
+      "loss": 0.353,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3422714105325708,
+      "grad_norm": 0.0812926316126211,
+      "learning_rate": 2.9480725444328763e-06,
+      "loss": 0.3642,
+      "step": 1505
+    },
+    {
+      "epoch": 1.3467280695238801,
+      "grad_norm": 0.05677065462915271,
+      "learning_rate": 2.9126262468813602e-06,
+      "loss": 0.329,
+      "step": 1510
+    },
+    {
+      "epoch": 1.35118472851519,
+      "grad_norm": 0.05518140834166454,
+      "learning_rate": 2.877306547078045e-06,
+      "loss": 0.2899,
+      "step": 1515
+    },
+    {
+      "epoch": 1.3556413875064992,
+      "grad_norm": 0.056017531551750585,
+      "learning_rate": 2.842115587137855e-06,
+      "loss": 0.3043,
+      "step": 1520
+    },
+    {
+      "epoch": 1.3600980464978087,
+      "grad_norm": 0.06536315700251481,
+      "learning_rate": 2.8070555013677305e-06,
+      "loss": 0.3018,
+      "step": 1525
+    },
+    {
+      "epoch": 1.3645547054891183,
+      "grad_norm": 0.06137584376324279,
+      "learning_rate": 2.772128416137181e-06,
+      "loss": 0.2912,
+      "step": 1530
+    },
+    {
+      "epoch": 1.3690113644804278,
+      "grad_norm": 0.058100040167798406,
+      "learning_rate": 2.7373364497493315e-06,
+      "loss": 0.2794,
+      "step": 1535
+    },
+    {
+      "epoch": 1.3734680234717374,
+      "grad_norm": 0.07619482744511352,
+      "learning_rate": 2.7026817123124456e-06,
+      "loss": 0.309,
+      "step": 1540
+    },
+    {
+      "epoch": 1.377924682463047,
+      "grad_norm": 0.0602222443408102,
+      "learning_rate": 2.6681663056119413e-06,
+      "loss": 0.3248,
+      "step": 1545
+    },
+    {
+      "epoch": 1.3823813414543564,
+      "grad_norm": 0.06509968172306801,
+      "learning_rate": 2.63379232298293e-06,
+      "loss": 0.3449,
+      "step": 1550
+    },
+    {
+      "epoch": 1.386838000445666,
+      "grad_norm": 0.06683684546365645,
+      "learning_rate": 2.599561849183255e-06,
+      "loss": 0.3022,
+      "step": 1555
+    },
+    {
+      "epoch": 1.3912946594369755,
+      "grad_norm": 0.0796435434481212,
+      "learning_rate": 2.5654769602670438e-06,
+      "loss": 0.3372,
+      "step": 1560
+    },
+    {
+      "epoch": 1.3957513184282848,
+      "grad_norm": 0.071737403463626,
+      "learning_rate": 2.531539723458808e-06,
+      "loss": 0.3226,
+      "step": 1565
+    },
+    {
+      "epoch": 1.4002079774195946,
+      "grad_norm": 0.0628814888060204,
+      "learning_rate": 2.4977521970280632e-06,
+      "loss": 0.3054,
+      "step": 1570
+    },
+    {
+      "epoch": 1.4046646364109039,
+      "grad_norm": 0.0664126755234312,
+      "learning_rate": 2.4641164301644916e-06,
+      "loss": 0.3163,
+      "step": 1575
+    },
+    {
+      "epoch": 1.4091212954022134,
+      "grad_norm": 0.0691268006065538,
+      "learning_rate": 2.4306344628536677e-06,
+      "loss": 0.292,
+      "step": 1580
+    },
+    {
+      "epoch": 1.413577954393523,
+      "grad_norm": 0.08254717009005777,
+      "learning_rate": 2.3973083257533337e-06,
+      "loss": 0.2964,
+      "step": 1585
+    },
+    {
+      "epoch": 1.4180346133848325,
+      "grad_norm": 0.0664448970280554,
+      "learning_rate": 2.364140040070233e-06,
+      "loss": 0.3013,
+      "step": 1590
+    },
+    {
+      "epoch": 1.422491272376142,
+      "grad_norm": 0.06641276103365941,
+      "learning_rate": 2.3311316174375385e-06,
+      "loss": 0.3088,
+      "step": 1595
+    },
+    {
+      "epoch": 1.4269479313674516,
+      "grad_norm": 0.08218794135414882,
+      "learning_rate": 2.2982850597928353e-06,
+      "loss": 0.3015,
+      "step": 1600
+    },
+    {
+      "epoch": 1.431404590358761,
+      "grad_norm": 0.06405949653118427,
+      "learning_rate": 2.2656023592567168e-06,
+      "loss": 0.3161,
+      "step": 1605
+    },
+    {
+      "epoch": 1.4358612493500706,
+      "grad_norm": 0.07949199345356144,
+      "learning_rate": 2.2330854980119524e-06,
+      "loss": 0.3018,
+      "step": 1610
+    },
+    {
+      "epoch": 1.4403179083413802,
+      "grad_norm": 0.074973629780883,
+      "learning_rate": 2.2007364481832827e-06,
+      "loss": 0.286,
+      "step": 1615
+    },
+    {
+      "epoch": 1.4447745673326895,
+      "grad_norm": 0.06978140375268374,
+      "learning_rate": 2.168557171717795e-06,
+      "loss": 0.3029,
+      "step": 1620
+    },
+    {
+      "epoch": 1.449231226323999,
+      "grad_norm": 0.060658080118647636,
+      "learning_rate": 2.1365496202659503e-06,
+      "loss": 0.2996,
+      "step": 1625
+    },
+    {
+      "epoch": 1.4536878853153086,
+      "grad_norm": 0.07246627865043749,
+      "learning_rate": 2.104715735063201e-06,
+      "loss": 0.2961,
+      "step": 1630
+    },
+    {
+      "epoch": 1.458144544306618,
+      "grad_norm": 0.07791853687083404,
+      "learning_rate": 2.0730574468122683e-06,
+      "loss": 0.3244,
+      "step": 1635
+    },
+    {
+      "epoch": 1.4626012032979276,
+      "grad_norm": 0.083758493641139,
+      "learning_rate": 2.0415766755660444e-06,
+      "loss": 0.3449,
+      "step": 1640
+    },
+    {
+      "epoch": 1.4670578622892372,
+      "grad_norm": 0.08124328287993272,
+      "learning_rate": 2.010275330611132e-06,
+      "loss": 0.3335,
+      "step": 1645
+    },
+    {
+      "epoch": 1.4715145212805467,
+      "grad_norm": 0.0699592628852485,
+      "learning_rate": 1.9791553103520624e-06,
+      "loss": 0.3101,
+      "step": 1650
+    },
+    {
+      "epoch": 1.4759711802718563,
+      "grad_norm": 0.05596234972263472,
+      "learning_rate": 1.9482185021961506e-06,
+      "loss": 0.3062,
+      "step": 1655
+    },
+    {
+      "epoch": 1.4804278392631658,
+      "grad_norm": 0.06327709166815214,
+      "learning_rate": 1.917466782439024e-06,
+      "loss": 0.2714,
+      "step": 1660
+    },
+    {
+      "epoch": 1.484884498254475,
+      "grad_norm": 0.09193245610034326,
+      "learning_rate": 1.88690201615083e-06,
+      "loss": 0.3015,
+      "step": 1665
+    },
+    {
+      "epoch": 1.4893411572457849,
+      "grad_norm": 0.116065810706921,
+      "learning_rate": 1.8565260570631244e-06,
+      "loss": 0.3023,
+      "step": 1670
+    },
+    {
+      "epoch": 1.4937978162370942,
+      "grad_norm": 0.06085779115348225,
+      "learning_rate": 1.82634074745643e-06,
+      "loss": 0.2793,
+      "step": 1675
+    },
+    {
+      "epoch": 1.4982544752284037,
+      "grad_norm": 0.07726951500485736,
+      "learning_rate": 1.7963479180485204e-06,
+      "loss": 0.2952,
+      "step": 1680
+    },
+    {
+      "epoch": 1.5027111342197133,
+      "grad_norm": 0.08737288468078919,
+      "learning_rate": 1.7665493878833807e-06,
+      "loss": 0.3074,
+      "step": 1685
+    },
+    {
+      "epoch": 1.5071677932110228,
+      "grad_norm": 0.07717042291948013,
+      "learning_rate": 1.736946964220877e-06,
+      "loss": 0.3265,
+      "step": 1690
+    },
+    {
+      "epoch": 1.5116244522023323,
+      "grad_norm": 0.09959612155824546,
+      "learning_rate": 1.7075424424271604e-06,
+      "loss": 0.2923,
+      "step": 1695
+    },
+    {
+      "epoch": 1.5160811111936419,
+      "grad_norm": 0.07789019553417695,
+      "learning_rate": 1.678337605865773e-06,
+      "loss": 0.3185,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5205377701849514,
+      "grad_norm": 0.09414331699116586,
+      "learning_rate": 1.6493342257894845e-06,
+      "loss": 0.3291,
+      "step": 1705
+    },
+    {
+      "epoch": 1.5249944291762607,
+      "grad_norm": 0.09880867896025543,
+      "learning_rate": 1.6205340612328707e-06,
+      "loss": 0.311,
+      "step": 1710
+    },
+    {
+      "epoch": 1.5294510881675705,
+      "grad_norm": 0.07951318628953609,
+      "learning_rate": 1.591938858905634e-06,
+      "loss": 0.303,
+      "step": 1715
+    },
+    {
+      "epoch": 1.5339077471588798,
+      "grad_norm": 0.07982777318332517,
+      "learning_rate": 1.5635503530866563e-06,
+      "loss": 0.2811,
+      "step": 1720
+    },
+    {
+      "epoch": 1.5383644061501895,
+      "grad_norm": 0.08550606994115802,
+      "learning_rate": 1.5353702655188257e-06,
+      "loss": 0.2993,
+      "step": 1725
+    },
+    {
+      "epoch": 1.5428210651414989,
+      "grad_norm": 0.08986128570256782,
+      "learning_rate": 1.5074003053046105e-06,
+      "loss": 0.3038,
+      "step": 1730
+    },
+    {
+      "epoch": 1.5472777241328084,
+      "grad_norm": 0.06401529887840299,
+      "learning_rate": 1.4796421688023975e-06,
+      "loss": 0.2757,
+      "step": 1735
+    },
+    {
+      "epoch": 1.551734383124118,
+      "grad_norm": 0.09741957746810867,
+      "learning_rate": 1.4520975395236215e-06,
+      "loss": 0.3062,
+      "step": 1740
+    },
+    {
+      "epoch": 1.5561910421154275,
+      "grad_norm": 0.07760428621549359,
+      "learning_rate": 1.4247680880306513e-06,
+      "loss": 0.3317,
+      "step": 1745
+    },
+    {
+      "epoch": 1.560647701106737,
+      "grad_norm": 0.08909029154183626,
+      "learning_rate": 1.3976554718354723e-06,
+      "loss": 0.318,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5651043600980465,
+      "grad_norm": 0.10011564881446526,
+      "learning_rate": 1.3707613352991656e-06,
+      "loss": 0.2931,
+      "step": 1755
+    },
+    {
+      "epoch": 1.569561019089356,
+      "grad_norm": 0.08176423100104935,
+      "learning_rate": 1.344087309532175e-06,
+      "loss": 0.2894,
+      "step": 1760
+    },
+    {
+      "epoch": 1.5740176780806654,
+      "grad_norm": 0.07307560261614855,
+      "learning_rate": 1.3176350122953763e-06,
+      "loss": 0.2867,
+      "step": 1765
+    },
+    {
+      "epoch": 1.5784743370719752,
+      "grad_norm": 0.12191262928713528,
+      "learning_rate": 1.2914060479019707e-06,
+      "loss": 0.3202,
+      "step": 1770
+    },
+    {
+      "epoch": 1.5829309960632845,
+      "grad_norm": 0.09026660529628,
+      "learning_rate": 1.2654020071201795e-06,
+      "loss": 0.3106,
+      "step": 1775
+    },
+    {
+      "epoch": 1.5873876550545942,
+      "grad_norm": 0.09053383432158335,
+      "learning_rate": 1.239624467076762e-06,
+      "loss": 0.2984,
+      "step": 1780
+    },
+    {
+      "epoch": 1.5918443140459035,
+      "grad_norm": 0.10384705796359629,
+      "learning_rate": 1.2140749911613703e-06,
+      "loss": 0.3184,
+      "step": 1785
+    },
+    {
+      "epoch": 1.596300973037213,
+      "grad_norm": 0.09677144301192052,
+      "learning_rate": 1.1887551289317284e-06,
+      "loss": 0.3159,
+      "step": 1790
+    },
+    {
+      "epoch": 1.6007576320285226,
+      "grad_norm": 0.08758929393810426,
+      "learning_rate": 1.163666416019647e-06,
+      "loss": 0.2917,
+      "step": 1795
+    },
+    {
+      "epoch": 1.6052142910198322,
+      "grad_norm": 0.08976099626976211,
+      "learning_rate": 1.1388103740379009e-06,
+      "loss": 0.3137,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6096709500111417,
+      "grad_norm": 0.09589145787287572,
+      "learning_rate": 1.114188510487928e-06,
+      "loss": 0.2672,
+      "step": 1805
+    },
+    {
+      "epoch": 1.614127609002451,
+      "grad_norm": 0.0898571951688524,
+      "learning_rate": 1.0898023186684188e-06,
+      "loss": 0.2821,
+      "step": 1810
+    },
+    {
+      "epoch": 1.6185842679937608,
+      "grad_norm": 0.10084905972281838,
+      "learning_rate": 1.06565327758473e-06,
+      "loss": 0.3108,
+      "step": 1815
+    },
+    {
+      "epoch": 1.62304092698507,
+      "grad_norm": 0.09625652044207637,
+      "learning_rate": 1.0417428518592015e-06,
+      "loss": 0.2797,
+      "step": 1820
+    },
+    {
+      "epoch": 1.6274975859763798,
+      "grad_norm": 0.13668108404773008,
+      "learning_rate": 1.018072491642313e-06,
+      "loss": 0.3249,
+      "step": 1825
+    },
+    {
+      "epoch": 1.6319542449676891,
+      "grad_norm": 0.1094276650717538,
+      "learning_rate": 9.946436325247438e-07,
+      "loss": 0.3072,
+      "step": 1830
+    },
+    {
+      "epoch": 1.6364109039589987,
+      "grad_norm": 0.09417653715028669,
+      "learning_rate": 9.71457695450303e-07,
+      "loss": 0.2896,
+      "step": 1835
+    },
+    {
+      "epoch": 1.6408675629503082,
+      "grad_norm": 0.10106662883357638,
+      "learning_rate": 9.485160866297433e-07,
+      "loss": 0.2978,
+      "step": 1840
+    },
+    {
+      "epoch": 1.6453242219416178,
+      "grad_norm": 0.10438310063745738,
+      "learning_rate": 9.25820197455487e-07,
+      "loss": 0.2821,
+      "step": 1845
+    },
+    {
+      "epoch": 1.6497808809329273,
+      "grad_norm": 0.10535335881946876,
+      "learning_rate": 9.033714044172281e-07,
+      "loss": 0.294,
+      "step": 1850
+    },
+    {
+      "epoch": 1.6542375399242368,
+      "grad_norm": 0.0889200936563808,
+      "learning_rate": 8.811710690184566e-07,
+      "loss": 0.262,
+      "step": 1855
+    },
+    {
+      "epoch": 1.6586941989155464,
+      "grad_norm": 0.10455279564530415,
+      "learning_rate": 8.592205376938834e-07,
+      "loss": 0.2817,
+      "step": 1860
+    },
+    {
+      "epoch": 1.6631508579068557,
+      "grad_norm": 0.11318390537590481,
+      "learning_rate": 8.375211417277717e-07,
+      "loss": 0.3045,
+      "step": 1865
+    },
+    {
+      "epoch": 1.6676075168981654,
+      "grad_norm": 0.088743004174387,
+      "learning_rate": 8.160741971732084e-07,
+      "loss": 0.2697,
+      "step": 1870
+    },
+    {
+      "epoch": 1.6720641758894748,
+      "grad_norm": 0.12499336666614728,
+      "learning_rate": 7.948810047722793e-07,
+      "loss": 0.2856,
+      "step": 1875
+    },
+    {
+      "epoch": 1.6765208348807845,
+      "grad_norm": 0.11172684998831532,
+      "learning_rate": 7.739428498771761e-07,
+      "loss": 0.2658,
+      "step": 1880
+    },
+    {
+      "epoch": 1.6809774938720938,
+      "grad_norm": 0.12595234706288227,
+      "learning_rate": 7.532610023722509e-07,
+      "loss": 0.2732,
+      "step": 1885
+    },
+    {
+      "epoch": 1.6854341528634034,
+      "grad_norm": 0.09689191794827777,
+      "learning_rate": 7.328367165969907e-07,
+      "loss": 0.3044,
+      "step": 1890
+    },
+    {
+      "epoch": 1.689890811854713,
+      "grad_norm": 0.11874605920811564,
+      "learning_rate": 7.126712312699435e-07,
+      "loss": 0.3221,
+      "step": 1895
+    },
+    {
+      "epoch": 1.6943474708460224,
+      "grad_norm": 0.08766218268129858,
+      "learning_rate": 6.927657694135959e-07,
+      "loss": 0.2814,
+      "step": 1900
+    },
+    {
+      "epoch": 1.698804129837332,
+      "grad_norm": 0.10403913380960049,
+      "learning_rate": 6.731215382801903e-07,
+      "loss": 0.3007,
+      "step": 1905
+    },
+    {
+      "epoch": 1.7032607888286415,
+      "grad_norm": 0.12394080523133466,
+      "learning_rate": 6.53739729278513e-07,
+      "loss": 0.2685,
+      "step": 1910
+    },
+    {
+      "epoch": 1.707717447819951,
+      "grad_norm": 0.09220124360987444,
+      "learning_rate": 6.346215179016297e-07,
+      "loss": 0.2999,
+      "step": 1915
+    },
+    {
+      "epoch": 1.7121741068112604,
+      "grad_norm": 0.09256443041488645,
+      "learning_rate": 6.157680636555996e-07,
+      "loss": 0.2921,
+      "step": 1920
+    },
+    {
+      "epoch": 1.7166307658025701,
+      "grad_norm": 0.11801980704813507,
+      "learning_rate": 5.971805099891437e-07,
+      "loss": 0.2952,
+      "step": 1925
+    },
+    {
+      "epoch": 1.7210874247938794,
+      "grad_norm": 0.11500014463950178,
+      "learning_rate": 5.788599842243043e-07,
+      "loss": 0.2757,
+      "step": 1930
+    },
+    {
+      "epoch": 1.7255440837851892,
+      "grad_norm": 0.12909046401480123,
+      "learning_rate": 5.608075974880678e-07,
+      "loss": 0.2783,
+      "step": 1935
+    },
+    {
+      "epoch": 1.7300007427764985,
+      "grad_norm": 0.10409707004186307,
+      "learning_rate": 5.430244446449762e-07,
+      "loss": 0.2853,
+      "step": 1940
+    },
+    {
+      "epoch": 1.734457401767808,
+      "grad_norm": 0.11009184273146726,
+      "learning_rate": 5.255116042307267e-07,
+      "loss": 0.2712,
+      "step": 1945
+    },
+    {
+      "epoch": 1.7389140607591176,
+      "grad_norm": 0.16597411522897149,
+      "learning_rate": 5.0827013838676e-07,
+      "loss": 0.3097,
+      "step": 1950
+    },
+    {
+      "epoch": 1.7433707197504271,
+      "grad_norm": 0.10555291444735147,
+      "learning_rate": 4.91301092795835e-07,
+      "loss": 0.3001,
+      "step": 1955
+    },
+    {
+      "epoch": 1.7478273787417367,
+      "grad_norm": 0.12464546891723725,
+      "learning_rate": 4.746054966186192e-07,
+      "loss": 0.2955,
+      "step": 1960
+    },
+    {
+      "epoch": 1.752284037733046,
+      "grad_norm": 0.11277180986490198,
+      "learning_rate": 4.581843624312643e-07,
+      "loss": 0.2643,
+      "step": 1965
+    },
+    {
+      "epoch": 1.7567406967243557,
+      "grad_norm": 0.09867908839152027,
+      "learning_rate": 4.4203868616399305e-07,
+      "loss": 0.312,
+      "step": 1970
+    },
+    {
+      "epoch": 1.761197355715665,
+      "grad_norm": 0.11312294922723523,
+      "learning_rate": 4.261694470407024e-07,
+      "loss": 0.2754,
+      "step": 1975
+    },
+    {
+      "epoch": 1.7656540147069748,
+      "grad_norm": 0.10862426439391781,
+      "learning_rate": 4.1057760751957056e-07,
+      "loss": 0.291,
+      "step": 1980
+    },
+    {
+      "epoch": 1.7701106736982841,
+      "grad_norm": 0.13833325552109443,
+      "learning_rate": 3.9526411323468403e-07,
+      "loss": 0.3009,
+      "step": 1985
+    },
+    {
+      "epoch": 1.7745673326895937,
+      "grad_norm": 0.11648729127760897,
+      "learning_rate": 3.802298929386872e-07,
+      "loss": 0.2948,
+      "step": 1990
+    },
+    {
+      "epoch": 1.7790239916809032,
+      "grad_norm": 0.10832697002551062,
+      "learning_rate": 3.6547585844645574e-07,
+      "loss": 0.264,
+      "step": 1995
+    },
+    {
+      "epoch": 1.7834806506722127,
+      "grad_norm": 0.1129159601097704,
+      "learning_rate": 3.510029045797897e-07,
+      "loss": 0.2814,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7879373096635223,
+      "grad_norm": 0.12881883038121175,
+      "learning_rate": 3.368119091131511e-07,
+      "loss": 0.2961,
+      "step": 2005
+    },
+    {
+      "epoch": 1.7923939686548318,
+      "grad_norm": 0.11915967567506883,
+      "learning_rate": 3.2290373272041984e-07,
+      "loss": 0.2847,
+      "step": 2010
+    },
+    {
+      "epoch": 1.7968506276461413,
+      "grad_norm": 0.14883545803777695,
+      "learning_rate": 3.0927921892270173e-07,
+      "loss": 0.3072,
+      "step": 2015
+    },
+    {
+      "epoch": 1.8013072866374507,
+      "grad_norm": 0.14935341192789242,
+      "learning_rate": 2.9593919403716254e-07,
+      "loss": 0.2585,
+      "step": 2020
+    },
+    {
+      "epoch": 1.8057639456287604,
+      "grad_norm": 0.10091752925214101,
+      "learning_rate": 2.8288446712691985e-07,
+      "loss": 0.2927,
+      "step": 2025
+    },
+    {
+      "epoch": 1.8102206046200697,
+      "grad_norm": 0.1272686505517032,
+      "learning_rate": 2.701158299519652e-07,
+      "loss": 0.297,
+      "step": 2030
+    },
+    {
+      "epoch": 1.8146772636113795,
+      "grad_norm": 0.11235244093503088,
+      "learning_rate": 2.5763405692115326e-07,
+      "loss": 0.2834,
+      "step": 2035
+    },
+    {
+      "epoch": 1.8191339226026888,
+      "grad_norm": 0.13526604911761567,
+      "learning_rate": 2.454399050452283e-07,
+      "loss": 0.296,
+      "step": 2040
+    },
+    {
+      "epoch": 1.8235905815939983,
+      "grad_norm": 0.13280050999221021,
+      "learning_rate": 2.335341138909142e-07,
+      "loss": 0.2717,
+      "step": 2045
+    },
+    {
+      "epoch": 1.8280472405853079,
+      "grad_norm": 0.12814019839952007,
+      "learning_rate": 2.219174055360612e-07,
+      "loss": 0.2717,
+      "step": 2050
+    },
+    {
+      "epoch": 1.8325038995766174,
+      "grad_norm": 0.11817894924930601,
+      "learning_rate": 2.1059048452584996e-07,
+      "loss": 0.2735,
+      "step": 2055
+    },
+    {
+      "epoch": 1.836960558567927,
+      "grad_norm": 0.12820739048926352,
+      "learning_rate": 1.9955403783006255e-07,
+      "loss": 0.2726,
+      "step": 2060
+    },
+    {
+      "epoch": 1.8414172175592363,
+      "grad_norm": 0.14570257294552771,
+      "learning_rate": 1.888087348014217e-07,
+      "loss": 0.2526,
+      "step": 2065
+    },
+    {
+      "epoch": 1.845873876550546,
+      "grad_norm": 0.09484685178822737,
+      "learning_rate": 1.7835522713498644e-07,
+      "loss": 0.2592,
+      "step": 2070
+    },
+    {
+      "epoch": 1.8503305355418553,
+      "grad_norm": 0.11168612744194842,
+      "learning_rate": 1.6819414882863704e-07,
+      "loss": 0.3027,
+      "step": 2075
+    },
+    {
+      "epoch": 1.854787194533165,
+      "grad_norm": 0.13169293315087485,
+      "learning_rate": 1.5832611614461757e-07,
+      "loss": 0.2576,
+      "step": 2080
+    },
+    {
+      "epoch": 1.8592438535244744,
+      "grad_norm": 0.13264409398535437,
+      "learning_rate": 1.4875172757216006e-07,
+      "loss": 0.2808,
+      "step": 2085
+    },
+    {
+      "epoch": 1.863700512515784,
+      "grad_norm": 0.11349693321653709,
+      "learning_rate": 1.394715637911903e-07,
+      "loss": 0.2588,
+      "step": 2090
+    },
+    {
+      "epoch": 1.8681571715070935,
+      "grad_norm": 0.14216886029418724,
+      "learning_rate": 1.3048618763710609e-07,
+      "loss": 0.2886,
+      "step": 2095
+    },
+    {
+      "epoch": 1.872613830498403,
+      "grad_norm": 0.11190825927177947,
+      "learning_rate": 1.2179614406664374e-07,
+      "loss": 0.2806,
+      "step": 2100
+    },
+    {
+      "epoch": 1.8770704894897126,
+      "grad_norm": 0.13139481283283222,
+      "learning_rate": 1.1340196012482652e-07,
+      "loss": 0.2701,
+      "step": 2105
+    },
+    {
+      "epoch": 1.881527148481022,
+      "grad_norm": 0.13212149531161754,
+      "learning_rate": 1.0530414491299823e-07,
+      "loss": 0.2976,
+      "step": 2110
+    },
+    {
+      "epoch": 1.8859838074723316,
+      "grad_norm": 0.14761056178281307,
+      "learning_rate": 9.75031895579509e-08,
+      "loss": 0.2851,
+      "step": 2115
+    },
+    {
+      "epoch": 1.890440466463641,
+      "grad_norm": 0.11807804154726727,
+      "learning_rate": 8.999956718213187e-08,
+      "loss": 0.2675,
+      "step": 2120
+    },
+    {
+      "epoch": 1.8948971254549507,
+      "grad_norm": 0.13153250275786837,
+      "learning_rate": 8.279373287495452e-08,
+      "loss": 0.2756,
+      "step": 2125
+    },
+    {
+      "epoch": 1.89935378444626,
+      "grad_norm": 0.12010506744054632,
+      "learning_rate": 7.588612366519588e-08,
+      "loss": 0.2755,
+      "step": 2130
+    },
+    {
+      "epoch": 1.9038104434375698,
+      "grad_norm": 0.13595444122630035,
+      "learning_rate": 6.927715849448902e-08,
+      "loss": 0.2621,
+      "step": 2135
+    },
+    {
+      "epoch": 1.908267102428879,
+      "grad_norm": 0.11969702875665357,
+      "learning_rate": 6.296723819191886e-08,
+      "loss": 0.2619,
+      "step": 2140
+    },
+    {
+      "epoch": 1.9127237614201886,
+      "grad_norm": 0.12713767895060166,
+      "learning_rate": 5.695674544970775e-08,
+      "loss": 0.2646,
+      "step": 2145
+    },
+    {
+      "epoch": 1.9171804204114982,
+      "grad_norm": 0.1512438174845061,
+      "learning_rate": 5.124604480000739e-08,
+      "loss": 0.2861,
+      "step": 2150
+    },
+    {
+      "epoch": 1.9216370794028077,
+      "grad_norm": 0.15063267518774118,
+      "learning_rate": 4.5835482592792026e-08,
+      "loss": 0.276,
+      "step": 2155
+    },
+    {
+      "epoch": 1.9260937383941172,
+      "grad_norm": 0.12516539105766297,
+      "learning_rate": 4.072538697484807e-08,
+      "loss": 0.288,
+      "step": 2160
+    },
+    {
+      "epoch": 1.9305503973854268,
+      "grad_norm": 0.12187069090426104,
+      "learning_rate": 3.591606786987667e-08,
+      "loss": 0.2864,
+      "step": 2165
+    },
+    {
+      "epoch": 1.9350070563767363,
+      "grad_norm": 0.10855277743154071,
+      "learning_rate": 3.1407816959695416e-08,
+      "loss": 0.2978,
+      "step": 2170
+    },
+    {
+      "epoch": 1.9394637153680456,
+      "grad_norm": 0.133314659297753,
+      "learning_rate": 2.720090766654693e-08,
+      "loss": 0.2864,
+      "step": 2175
+    },
+    {
+      "epoch": 1.9439203743593554,
+      "grad_norm": 0.1263650702337354,
+      "learning_rate": 2.3295595136517136e-08,
+      "loss": 0.2737,
+      "step": 2180
+    },
+    {
+      "epoch": 1.9483770333506647,
+      "grad_norm": 0.1343875450088774,
+      "learning_rate": 1.9692116224060976e-08,
+      "loss": 0.2624,
+      "step": 2185
+    },
+    {
+      "epoch": 1.9528336923419745,
+      "grad_norm": 0.12031351113756965,
+      "learning_rate": 1.639068947763722e-08,
+      "loss": 0.277,
+      "step": 2190
+    },
+    {
+      "epoch": 1.9572903513332838,
+      "grad_norm": 0.12928344033539446,
+      "learning_rate": 1.3391515126452426e-08,
+      "loss": 0.2739,
+      "step": 2195
+    },
+    {
+      "epoch": 1.9617470103245933,
+      "grad_norm": 0.12874880789823828,
+      "learning_rate": 1.0694775068320063e-08,
+      "loss": 0.2622,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9662036693159028,
+      "grad_norm": 0.17186304444380732,
+      "learning_rate": 8.30063285862437e-09,
+      "loss": 0.2909,
+      "step": 2205
+    },
+    {
+      "epoch": 1.9706603283072124,
+      "grad_norm": 0.1309907572097109,
+      "learning_rate": 6.209233700406048e-09,
+      "loss": 0.277,
+      "step": 2210
+    },
+    {
+      "epoch": 1.975116987298522,
+      "grad_norm": 0.1365092145131148,
+      "learning_rate": 4.4207044355493164e-09,
+      "loss": 0.2629,
+      "step": 2215
+    },
+    {
+      "epoch": 1.9795736462898312,
+      "grad_norm": 0.12156842653941813,
+      "learning_rate": 2.935153537096391e-09,
+      "loss": 0.2658,
+      "step": 2220
+    },
+    {
+      "epoch": 1.984030305281141,
+      "grad_norm": 0.1263668031483968,
+      "learning_rate": 1.7526711026621957e-09,
+      "loss": 0.2805,
+      "step": 2225
+    },
+    {
+      "epoch": 1.9884869642724503,
+      "grad_norm": 0.13239230121316822,
+      "learning_rate": 8.733288489737312e-10,
+      "loss": 0.2822,
+      "step": 2230
+    },
+    {
+      "epoch": 1.99294362326376,
+      "grad_norm": 0.13212067705172323,
+      "learning_rate": 2.9718010751966784e-10,
+      "loss": 0.2625,
+      "step": 2235
+    },
+    {
+      "epoch": 1.9974002822550694,
+      "grad_norm": 0.13697820005606215,
+      "learning_rate": 2.4259821315153476e-11,
+      "loss": 0.2635,
+      "step": 2240
+    },
+    {
+      "epoch": 1.9991829458515933,
+      "eval_loss": 0.2551692724227905,
+      "eval_runtime": 27.6419,
+      "eval_samples_per_second": 19.68,
+      "eval_steps_per_second": 4.92,
+      "step": 2242
+    },
+    {
+      "epoch": 1.9991829458515933,
+      "step": 2242,
+      "total_flos": 5.790417620582793e+18,
+      "train_loss": 0.36008237901805873,
+      "train_runtime": 20584.0534,
+      "train_samples_per_second": 5.232,
+      "train_steps_per_second": 0.109
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2242,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.790417620582793e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568aa6232c9b4866a8ba747cb2b279ea41d9e166425cbf32eb692501480cf04f
+size 7288