Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "LlamaForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128258,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 128259
+}

global_step3116/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed255e363cec9881712bc9abb0f6b53082421e84fe96518c4f942b40f75d961
+size 9638291340

global_step3116/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cdcb48dc48588706394a97a6d5ddc610c675e0fbb488b7511b3c0d12622a0f2
+size 9638291340

global_step3116/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2caf0739331ac82afe7fba74dd98d5eec70c3aae9f94d258323e757ba4c94e9c
+size 9638291340

global_step3116/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006636f827c58d9e9c0d6096d9b54754477696a75badd28d39b347e8204e59d6
+size 9638291340

global_step3116/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83652c548721ebf150fa3a8f641e1fdf361ad906ae33fdf9314613a2b1c779fa
+size 130513

global_step3116/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6060d530a2f884d0caa940c316eee10f214ec8e94449c937bc435aa215d9316c
+size 130513

global_step3116/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e057b59d908df91b4fd8ce62443251e086b6e0a1b01b21e5a80574cbefeec3bd
+size 130513

global_step3116/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b4b07c2d31eff9eca2f7f23ec47115c9b09320025333b665be63b7ce81958a
+size 130513

latest

@@ -0,0 +1 @@
+global_step3116

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec9b6da4cbc87ccaf4acda77ab3e510715dc7d84ffe0e5adb9532fb83719e22
+size 4965817528

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010880aee35ff36621a00c18d927cad5c43de908aa4da5857be6cb1c355432ee
+size 1459736184

model.safetensors.index.json

@@ -0,0 +1,262 @@
+{
+  "metadata": {
+    "total_size": 6425524224
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b184f8fc9facd6e4a6513602952b43b9446784300c3ea2da72aefb029f93aac1
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937f07b3f415f537fbc809c70f15f64b8410cd6a07adbe7d246f5ca7359b3b49
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e3f7eacec877950b3dad99b106bf80da30203dda6159b06f954c15b7f5d367
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a5087a11a5f0a226f1607ec68740ea6baa2599559138de38da40f89dd666683
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09dae88f23edd61c89b0e78fb7a2351b628d2ebbd8dea832de49acd6b9ccc3d
+size 1064

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|pad|>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d9fd6f8a3b531fcd3641d24db47ac67d512a3ab36abfe835934d19cff30a8d
+size 17210480

tokenizer_config.json

@@ -0,0 +1,2094 @@
+{
+  "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": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "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": "<|eom_id|>",
+      "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": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128257": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128258": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|pad|>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ '<|begin_of_text|>' }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>\\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ '<|end_of_text|>' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

trainer_state.json

@@ -0,0 +1,2211 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9997593647228684,
+  "eval_steps": 500,
+  "global_step": 3116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003208470361755033,
+      "grad_norm": 6.442734116834532,
+      "learning_rate": 1.9942233632862646e-05,
+      "loss": 0.646,
+      "step": 10
+    },
+    {
+      "epoch": 0.006416940723510066,
+      "grad_norm": 16.670848007363354,
+      "learning_rate": 1.9878048780487806e-05,
+      "loss": 0.5538,
+      "step": 20
+    },
+    {
+      "epoch": 0.0096254110852651,
+      "grad_norm": 5.007229537641644,
+      "learning_rate": 1.9813863928112966e-05,
+      "loss": 0.5532,
+      "step": 30
+    },
+    {
+      "epoch": 0.012833881447020133,
+      "grad_norm": 6.381096528206163,
+      "learning_rate": 1.974967907573813e-05,
+      "loss": 0.5403,
+      "step": 40
+    },
+    {
+      "epoch": 0.016042351808775165,
+      "grad_norm": 3.202143132985174,
+      "learning_rate": 1.968549422336329e-05,
+      "loss": 0.5484,
+      "step": 50
+    },
+    {
+      "epoch": 0.0192508221705302,
+      "grad_norm": 5.974056462183794,
+      "learning_rate": 1.962130937098845e-05,
+      "loss": 0.5738,
+      "step": 60
+    },
+    {
+      "epoch": 0.022459292532285232,
+      "grad_norm": 8.235054035652611,
+      "learning_rate": 1.955712451861361e-05,
+      "loss": 0.5311,
+      "step": 70
+    },
+    {
+      "epoch": 0.025667762894040266,
+      "grad_norm": 8.918082235487985,
+      "learning_rate": 1.9492939666238767e-05,
+      "loss": 0.5128,
+      "step": 80
+    },
+    {
+      "epoch": 0.0288762332557953,
+      "grad_norm": 7.299533718731339,
+      "learning_rate": 1.942875481386393e-05,
+      "loss": 0.5444,
+      "step": 90
+    },
+    {
+      "epoch": 0.03208470361755033,
+      "grad_norm": 6.793642690075093,
+      "learning_rate": 1.936456996148909e-05,
+      "loss": 0.4792,
+      "step": 100
+    },
+    {
+      "epoch": 0.03529317397930536,
+      "grad_norm": 5.35608624427688,
+      "learning_rate": 1.930038510911425e-05,
+      "loss": 0.4838,
+      "step": 110
+    },
+    {
+      "epoch": 0.0385016443410604,
+      "grad_norm": 8.214012839502532,
+      "learning_rate": 1.923620025673941e-05,
+      "loss": 0.4947,
+      "step": 120
+    },
+    {
+      "epoch": 0.04171011470281543,
+      "grad_norm": 17.30363857344939,
+      "learning_rate": 1.9172015404364574e-05,
+      "loss": 0.539,
+      "step": 130
+    },
+    {
+      "epoch": 0.044918585064570464,
+      "grad_norm": 5.2411969812270405,
+      "learning_rate": 1.910783055198973e-05,
+      "loss": 0.4976,
+      "step": 140
+    },
+    {
+      "epoch": 0.0481270554263255,
+      "grad_norm": 5.825912105537252,
+      "learning_rate": 1.904364569961489e-05,
+      "loss": 0.5374,
+      "step": 150
+    },
+    {
+      "epoch": 0.05133552578808053,
+      "grad_norm": 7.038630553849513,
+      "learning_rate": 1.897946084724005e-05,
+      "loss": 0.4682,
+      "step": 160
+    },
+    {
+      "epoch": 0.054543996149835565,
+      "grad_norm": 5.686461374890298,
+      "learning_rate": 1.8915275994865214e-05,
+      "loss": 0.5205,
+      "step": 170
+    },
+    {
+      "epoch": 0.0577524665115906,
+      "grad_norm": 5.179564550909498,
+      "learning_rate": 1.8851091142490375e-05,
+      "loss": 0.491,
+      "step": 180
+    },
+    {
+      "epoch": 0.06096093687334563,
+      "grad_norm": 8.463629137447528,
+      "learning_rate": 1.8786906290115535e-05,
+      "loss": 0.5228,
+      "step": 190
+    },
+    {
+      "epoch": 0.06416940723510066,
+      "grad_norm": 4.011565557460287,
+      "learning_rate": 1.8722721437740695e-05,
+      "loss": 0.479,
+      "step": 200
+    },
+    {
+      "epoch": 0.06737787759685569,
+      "grad_norm": 7.7055557079808805,
+      "learning_rate": 1.8658536585365855e-05,
+      "loss": 0.4687,
+      "step": 210
+    },
+    {
+      "epoch": 0.07058634795861073,
+      "grad_norm": 6.724744753360089,
+      "learning_rate": 1.8594351732991015e-05,
+      "loss": 0.4818,
+      "step": 220
+    },
+    {
+      "epoch": 0.07379481832036576,
+      "grad_norm": 4.678677086919036,
+      "learning_rate": 1.8530166880616175e-05,
+      "loss": 0.5139,
+      "step": 230
+    },
+    {
+      "epoch": 0.0770032886821208,
+      "grad_norm": 9.311365908507138,
+      "learning_rate": 1.8465982028241335e-05,
+      "loss": 0.4747,
+      "step": 240
+    },
+    {
+      "epoch": 0.08021175904387583,
+      "grad_norm": 4.443842779885137,
+      "learning_rate": 1.8401797175866495e-05,
+      "loss": 0.4891,
+      "step": 250
+    },
+    {
+      "epoch": 0.08342022940563086,
+      "grad_norm": 8.33835692877245,
+      "learning_rate": 1.833761232349166e-05,
+      "loss": 0.47,
+      "step": 260
+    },
+    {
+      "epoch": 0.0866286997673859,
+      "grad_norm": 6.389873022971522,
+      "learning_rate": 1.827342747111682e-05,
+      "loss": 0.4484,
+      "step": 270
+    },
+    {
+      "epoch": 0.08983717012914093,
+      "grad_norm": 7.274203538153994,
+      "learning_rate": 1.820924261874198e-05,
+      "loss": 0.4517,
+      "step": 280
+    },
+    {
+      "epoch": 0.09304564049089596,
+      "grad_norm": 3.978695084684557,
+      "learning_rate": 1.814505776636714e-05,
+      "loss": 0.4807,
+      "step": 290
+    },
+    {
+      "epoch": 0.096254110852651,
+      "grad_norm": 5.846527325287561,
+      "learning_rate": 1.80808729139923e-05,
+      "loss": 0.4572,
+      "step": 300
+    },
+    {
+      "epoch": 0.09946258121440603,
+      "grad_norm": 4.899874671814943,
+      "learning_rate": 1.801668806161746e-05,
+      "loss": 0.4337,
+      "step": 310
+    },
+    {
+      "epoch": 0.10267105157616106,
+      "grad_norm": 7.441397827942358,
+      "learning_rate": 1.795250320924262e-05,
+      "loss": 0.4794,
+      "step": 320
+    },
+    {
+      "epoch": 0.1058795219379161,
+      "grad_norm": 4.8167626402693,
+      "learning_rate": 1.788831835686778e-05,
+      "loss": 0.4547,
+      "step": 330
+    },
+    {
+      "epoch": 0.10908799229967113,
+      "grad_norm": 4.830906300715028,
+      "learning_rate": 1.7824133504492943e-05,
+      "loss": 0.4155,
+      "step": 340
+    },
+    {
+      "epoch": 0.11229646266142616,
+      "grad_norm": 2.783779241391255,
+      "learning_rate": 1.7759948652118103e-05,
+      "loss": 0.4254,
+      "step": 350
+    },
+    {
+      "epoch": 0.1155049330231812,
+      "grad_norm": 4.482561979814794,
+      "learning_rate": 1.7695763799743263e-05,
+      "loss": 0.5048,
+      "step": 360
+    },
+    {
+      "epoch": 0.11871340338493623,
+      "grad_norm": 4.736082727818665,
+      "learning_rate": 1.763157894736842e-05,
+      "loss": 0.4088,
+      "step": 370
+    },
+    {
+      "epoch": 0.12192187374669126,
+      "grad_norm": 3.540097005993698,
+      "learning_rate": 1.7567394094993584e-05,
+      "loss": 0.5214,
+      "step": 380
+    },
+    {
+      "epoch": 0.1251303441084463,
+      "grad_norm": 4.695488227787937,
+      "learning_rate": 1.7503209242618744e-05,
+      "loss": 0.4434,
+      "step": 390
+    },
+    {
+      "epoch": 0.12833881447020132,
+      "grad_norm": 3.7024498981669662,
+      "learning_rate": 1.7439024390243904e-05,
+      "loss": 0.5021,
+      "step": 400
+    },
+    {
+      "epoch": 0.13154728483195635,
+      "grad_norm": 2.707105021471608,
+      "learning_rate": 1.7374839537869064e-05,
+      "loss": 0.4844,
+      "step": 410
+    },
+    {
+      "epoch": 0.13475575519371139,
+      "grad_norm": 5.70948950157765,
+      "learning_rate": 1.7310654685494224e-05,
+      "loss": 0.4903,
+      "step": 420
+    },
+    {
+      "epoch": 0.13796422555546642,
+      "grad_norm": 3.696922556933147,
+      "learning_rate": 1.7246469833119384e-05,
+      "loss": 0.4441,
+      "step": 430
+    },
+    {
+      "epoch": 0.14117269591722145,
+      "grad_norm": 4.483329616797758,
+      "learning_rate": 1.7182284980744544e-05,
+      "loss": 0.5387,
+      "step": 440
+    },
+    {
+      "epoch": 0.14438116627897649,
+      "grad_norm": 3.394450035525867,
+      "learning_rate": 1.7118100128369705e-05,
+      "loss": 0.4662,
+      "step": 450
+    },
+    {
+      "epoch": 0.14758963664073152,
+      "grad_norm": 8.726490331816862,
+      "learning_rate": 1.7053915275994865e-05,
+      "loss": 0.4507,
+      "step": 460
+    },
+    {
+      "epoch": 0.15079810700248655,
+      "grad_norm": 4.353194363650416,
+      "learning_rate": 1.6989730423620028e-05,
+      "loss": 0.4526,
+      "step": 470
+    },
+    {
+      "epoch": 0.1540065773642416,
+      "grad_norm": 3.950021174504244,
+      "learning_rate": 1.692554557124519e-05,
+      "loss": 0.4821,
+      "step": 480
+    },
+    {
+      "epoch": 0.15721504772599662,
+      "grad_norm": 3.5715866632711832,
+      "learning_rate": 1.686136071887035e-05,
+      "loss": 0.4288,
+      "step": 490
+    },
+    {
+      "epoch": 0.16042351808775165,
+      "grad_norm": 3.8300844137879917,
+      "learning_rate": 1.679717586649551e-05,
+      "loss": 0.5043,
+      "step": 500
+    },
+    {
+      "epoch": 0.1636319884495067,
+      "grad_norm": 3.6133285758576235,
+      "learning_rate": 1.673299101412067e-05,
+      "loss": 0.4682,
+      "step": 510
+    },
+    {
+      "epoch": 0.16684045881126172,
+      "grad_norm": 6.472583456901733,
+      "learning_rate": 1.666880616174583e-05,
+      "loss": 0.4002,
+      "step": 520
+    },
+    {
+      "epoch": 0.17004892917301676,
+      "grad_norm": 3.701841978979134,
+      "learning_rate": 1.660462130937099e-05,
+      "loss": 0.5022,
+      "step": 530
+    },
+    {
+      "epoch": 0.1732573995347718,
+      "grad_norm": 4.773360444080344,
+      "learning_rate": 1.654043645699615e-05,
+      "loss": 0.5066,
+      "step": 540
+    },
+    {
+      "epoch": 0.17646586989652682,
+      "grad_norm": 13.276543301213977,
+      "learning_rate": 1.6476251604621313e-05,
+      "loss": 0.4648,
+      "step": 550
+    },
+    {
+      "epoch": 0.17967434025828186,
+      "grad_norm": 8.185811344239216,
+      "learning_rate": 1.6412066752246473e-05,
+      "loss": 0.4597,
+      "step": 560
+    },
+    {
+      "epoch": 0.1828828106200369,
+      "grad_norm": 3.870551639158725,
+      "learning_rate": 1.6347881899871633e-05,
+      "loss": 0.4644,
+      "step": 570
+    },
+    {
+      "epoch": 0.18609128098179192,
+      "grad_norm": 2.9435165160063628,
+      "learning_rate": 1.6283697047496793e-05,
+      "loss": 0.4996,
+      "step": 580
+    },
+    {
+      "epoch": 0.18929975134354696,
+      "grad_norm": 5.242572609854114,
+      "learning_rate": 1.6219512195121953e-05,
+      "loss": 0.4465,
+      "step": 590
+    },
+    {
+      "epoch": 0.192508221705302,
+      "grad_norm": 3.296578668491081,
+      "learning_rate": 1.6155327342747113e-05,
+      "loss": 0.404,
+      "step": 600
+    },
+    {
+      "epoch": 0.19571669206705702,
+      "grad_norm": 5.090117348527818,
+      "learning_rate": 1.6091142490372273e-05,
+      "loss": 0.4277,
+      "step": 610
+    },
+    {
+      "epoch": 0.19892516242881206,
+      "grad_norm": 2.888476032144689,
+      "learning_rate": 1.6026957637997433e-05,
+      "loss": 0.4783,
+      "step": 620
+    },
+    {
+      "epoch": 0.2021336327905671,
+      "grad_norm": 4.135431165940949,
+      "learning_rate": 1.5962772785622594e-05,
+      "loss": 0.4236,
+      "step": 630
+    },
+    {
+      "epoch": 0.20534210315232213,
+      "grad_norm": 4.833487869831366,
+      "learning_rate": 1.5898587933247757e-05,
+      "loss": 0.504,
+      "step": 640
+    },
+    {
+      "epoch": 0.20855057351407716,
+      "grad_norm": 4.282352689606544,
+      "learning_rate": 1.5834403080872917e-05,
+      "loss": 0.4277,
+      "step": 650
+    },
+    {
+      "epoch": 0.2117590438758322,
+      "grad_norm": 6.760216642975651,
+      "learning_rate": 1.5770218228498074e-05,
+      "loss": 0.4916,
+      "step": 660
+    },
+    {
+      "epoch": 0.21496751423758723,
+      "grad_norm": 4.349450853536778,
+      "learning_rate": 1.5706033376123234e-05,
+      "loss": 0.4863,
+      "step": 670
+    },
+    {
+      "epoch": 0.21817598459934226,
+      "grad_norm": 8.907091580804641,
+      "learning_rate": 1.5641848523748397e-05,
+      "loss": 0.4454,
+      "step": 680
+    },
+    {
+      "epoch": 0.2213844549610973,
+      "grad_norm": 12.495791509691397,
+      "learning_rate": 1.5577663671373558e-05,
+      "loss": 0.4374,
+      "step": 690
+    },
+    {
+      "epoch": 0.22459292532285233,
+      "grad_norm": 4.162195469033971,
+      "learning_rate": 1.5513478818998718e-05,
+      "loss": 0.398,
+      "step": 700
+    },
+    {
+      "epoch": 0.22780139568460736,
+      "grad_norm": 4.9440877367494585,
+      "learning_rate": 1.5449293966623878e-05,
+      "loss": 0.4386,
+      "step": 710
+    },
+    {
+      "epoch": 0.2310098660463624,
+      "grad_norm": 3.3193418621579194,
+      "learning_rate": 1.5385109114249038e-05,
+      "loss": 0.3993,
+      "step": 720
+    },
+    {
+      "epoch": 0.23421833640811743,
+      "grad_norm": 3.388886050375809,
+      "learning_rate": 1.5320924261874198e-05,
+      "loss": 0.3915,
+      "step": 730
+    },
+    {
+      "epoch": 0.23742680676987246,
+      "grad_norm": 3.758493220998932,
+      "learning_rate": 1.525673940949936e-05,
+      "loss": 0.4452,
+      "step": 740
+    },
+    {
+      "epoch": 0.2406352771316275,
+      "grad_norm": 5.132628959411491,
+      "learning_rate": 1.519255455712452e-05,
+      "loss": 0.3703,
+      "step": 750
+    },
+    {
+      "epoch": 0.24384374749338253,
+      "grad_norm": 6.2691579411030025,
+      "learning_rate": 1.5128369704749682e-05,
+      "loss": 0.4158,
+      "step": 760
+    },
+    {
+      "epoch": 0.24705221785513756,
+      "grad_norm": 4.103316818662405,
+      "learning_rate": 1.5064184852374842e-05,
+      "loss": 0.4233,
+      "step": 770
+    },
+    {
+      "epoch": 0.2502606882168926,
+      "grad_norm": 6.0422539237827975,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.4278,
+      "step": 780
+    },
+    {
+      "epoch": 0.2534691585786476,
+      "grad_norm": 2.7653877942568954,
+      "learning_rate": 1.493581514762516e-05,
+      "loss": 0.4095,
+      "step": 790
+    },
+    {
+      "epoch": 0.25667762894040264,
+      "grad_norm": 4.114902146610447,
+      "learning_rate": 1.487163029525032e-05,
+      "loss": 0.4584,
+      "step": 800
+    },
+    {
+      "epoch": 0.25988609930215767,
+      "grad_norm": 5.28663521958676,
+      "learning_rate": 1.4807445442875482e-05,
+      "loss": 0.4368,
+      "step": 810
+    },
+    {
+      "epoch": 0.2630945696639127,
+      "grad_norm": 3.8311121578946303,
+      "learning_rate": 1.4743260590500643e-05,
+      "loss": 0.4107,
+      "step": 820
+    },
+    {
+      "epoch": 0.26630304002566774,
+      "grad_norm": 3.318670161966376,
+      "learning_rate": 1.4679075738125803e-05,
+      "loss": 0.4245,
+      "step": 830
+    },
+    {
+      "epoch": 0.26951151038742277,
+      "grad_norm": 4.755364543588735,
+      "learning_rate": 1.4614890885750963e-05,
+      "loss": 0.4787,
+      "step": 840
+    },
+    {
+      "epoch": 0.2727199807491778,
+      "grad_norm": 2.786479482223897,
+      "learning_rate": 1.4550706033376125e-05,
+      "loss": 0.4336,
+      "step": 850
+    },
+    {
+      "epoch": 0.27592845111093284,
+      "grad_norm": 4.070784873347869,
+      "learning_rate": 1.4486521181001285e-05,
+      "loss": 0.4123,
+      "step": 860
+    },
+    {
+      "epoch": 0.27913692147268787,
+      "grad_norm": 5.342176013467221,
+      "learning_rate": 1.4422336328626445e-05,
+      "loss": 0.4497,
+      "step": 870
+    },
+    {
+      "epoch": 0.2823453918344429,
+      "grad_norm": 2.881520241461501,
+      "learning_rate": 1.4358151476251605e-05,
+      "loss": 0.4872,
+      "step": 880
+    },
+    {
+      "epoch": 0.28555386219619794,
+      "grad_norm": 4.478805078448799,
+      "learning_rate": 1.4293966623876767e-05,
+      "loss": 0.3984,
+      "step": 890
+    },
+    {
+      "epoch": 0.28876233255795297,
+      "grad_norm": 6.101899594897867,
+      "learning_rate": 1.4229781771501927e-05,
+      "loss": 0.4628,
+      "step": 900
+    },
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 3.0826453501277715,
+      "learning_rate": 1.4165596919127087e-05,
+      "loss": 0.4432,
+      "step": 910
+    },
+    {
+      "epoch": 0.29517927328146304,
+      "grad_norm": 2.4770273632891953,
+      "learning_rate": 1.4101412066752247e-05,
+      "loss": 0.506,
+      "step": 920
+    },
+    {
+      "epoch": 0.2983877436432181,
+      "grad_norm": 3.422572341295809,
+      "learning_rate": 1.4037227214377409e-05,
+      "loss": 0.3826,
+      "step": 930
+    },
+    {
+      "epoch": 0.3015962140049731,
+      "grad_norm": 6.410925492330843,
+      "learning_rate": 1.3973042362002569e-05,
+      "loss": 0.4976,
+      "step": 940
+    },
+    {
+      "epoch": 0.30480468436672814,
+      "grad_norm": 3.702470810813249,
+      "learning_rate": 1.390885750962773e-05,
+      "loss": 0.3977,
+      "step": 950
+    },
+    {
+      "epoch": 0.3080131547284832,
+      "grad_norm": 4.496582483074578,
+      "learning_rate": 1.384467265725289e-05,
+      "loss": 0.3427,
+      "step": 960
+    },
+    {
+      "epoch": 0.3112216250902382,
+      "grad_norm": 5.771712327672755,
+      "learning_rate": 1.378048780487805e-05,
+      "loss": 0.4011,
+      "step": 970
+    },
+    {
+      "epoch": 0.31443009545199324,
+      "grad_norm": 6.116944263448949,
+      "learning_rate": 1.3716302952503211e-05,
+      "loss": 0.3832,
+      "step": 980
+    },
+    {
+      "epoch": 0.3176385658137483,
+      "grad_norm": 5.217590349147242,
+      "learning_rate": 1.3652118100128371e-05,
+      "loss": 0.4484,
+      "step": 990
+    },
+    {
+      "epoch": 0.3208470361755033,
+      "grad_norm": 6.326859919098317,
+      "learning_rate": 1.3587933247753531e-05,
+      "loss": 0.4238,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32405550653725834,
+      "grad_norm": 3.6100683655298518,
+      "learning_rate": 1.3523748395378692e-05,
+      "loss": 0.4521,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3272639768990134,
+      "grad_norm": 8.35582852568852,
+      "learning_rate": 1.3459563543003853e-05,
+      "loss": 0.4277,
+      "step": 1020
+    },
+    {
+      "epoch": 0.3304724472607684,
+      "grad_norm": 6.127881803928465,
+      "learning_rate": 1.3395378690629014e-05,
+      "loss": 0.3845,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33368091762252344,
+      "grad_norm": 5.346412016792554,
+      "learning_rate": 1.3331193838254172e-05,
+      "loss": 0.3598,
+      "step": 1040
+    },
+    {
+      "epoch": 0.3368893879842785,
+      "grad_norm": 5.518712653284187,
+      "learning_rate": 1.3267008985879332e-05,
+      "loss": 0.4684,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3400978583460335,
+      "grad_norm": 3.0171159430683647,
+      "learning_rate": 1.3202824133504496e-05,
+      "loss": 0.402,
+      "step": 1060
+    },
+    {
+      "epoch": 0.34330632870778854,
+      "grad_norm": 3.4525267211589585,
+      "learning_rate": 1.3138639281129654e-05,
+      "loss": 0.4587,
+      "step": 1070
+    },
+    {
+      "epoch": 0.3465147990695436,
+      "grad_norm": 4.923842642383016,
+      "learning_rate": 1.3074454428754814e-05,
+      "loss": 0.4231,
+      "step": 1080
+    },
+    {
+      "epoch": 0.3497232694312986,
+      "grad_norm": 3.982906316656253,
+      "learning_rate": 1.3010269576379974e-05,
+      "loss": 0.419,
+      "step": 1090
+    },
+    {
+      "epoch": 0.35293173979305364,
+      "grad_norm": 3.9801555228114998,
+      "learning_rate": 1.2946084724005136e-05,
+      "loss": 0.3668,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3561402101548087,
+      "grad_norm": 4.030778915107762,
+      "learning_rate": 1.2881899871630296e-05,
+      "loss": 0.3739,
+      "step": 1110
+    },
+    {
+      "epoch": 0.3593486805165637,
+      "grad_norm": 6.386525169017585,
+      "learning_rate": 1.2817715019255456e-05,
+      "loss": 0.4972,
+      "step": 1120
+    },
+    {
+      "epoch": 0.36255715087831875,
+      "grad_norm": 4.20862662435033,
+      "learning_rate": 1.2753530166880616e-05,
+      "loss": 0.4154,
+      "step": 1130
+    },
+    {
+      "epoch": 0.3657656212400738,
+      "grad_norm": 4.858924338028923,
+      "learning_rate": 1.2689345314505778e-05,
+      "loss": 0.4478,
+      "step": 1140
+    },
+    {
+      "epoch": 0.3689740916018288,
+      "grad_norm": 5.608430455111102,
+      "learning_rate": 1.2625160462130938e-05,
+      "loss": 0.4599,
+      "step": 1150
+    },
+    {
+      "epoch": 0.37218256196358385,
+      "grad_norm": 5.911587578207529,
+      "learning_rate": 1.2560975609756098e-05,
+      "loss": 0.3869,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3753910323253389,
+      "grad_norm": 4.283524740830092,
+      "learning_rate": 1.2496790757381259e-05,
+      "loss": 0.3837,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3785995026870939,
+      "grad_norm": 6.821302089832709,
+      "learning_rate": 1.2432605905006419e-05,
+      "loss": 0.442,
+      "step": 1180
+    },
+    {
+      "epoch": 0.38180797304884895,
+      "grad_norm": 5.085358904961751,
+      "learning_rate": 1.236842105263158e-05,
+      "loss": 0.3264,
+      "step": 1190
+    },
+    {
+      "epoch": 0.385016443410604,
+      "grad_norm": 4.605248058627308,
+      "learning_rate": 1.230423620025674e-05,
+      "loss": 0.3895,
+      "step": 1200
+    },
+    {
+      "epoch": 0.388224913772359,
+      "grad_norm": 3.477144602759826,
+      "learning_rate": 1.22400513478819e-05,
+      "loss": 0.4405,
+      "step": 1210
+    },
+    {
+      "epoch": 0.39143338413411405,
+      "grad_norm": 4.706693999402434,
+      "learning_rate": 1.2175866495507061e-05,
+      "loss": 0.4102,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3946418544958691,
+      "grad_norm": 3.204192427462165,
+      "learning_rate": 1.2111681643132223e-05,
+      "loss": 0.4244,
+      "step": 1230
+    },
+    {
+      "epoch": 0.3978503248576241,
+      "grad_norm": 5.415400158823864,
+      "learning_rate": 1.2047496790757383e-05,
+      "loss": 0.389,
+      "step": 1240
+    },
+    {
+      "epoch": 0.40105879521937915,
+      "grad_norm": 4.1016299695920555,
+      "learning_rate": 1.1983311938382543e-05,
+      "loss": 0.4348,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4042672655811342,
+      "grad_norm": 5.0119293140447265,
+      "learning_rate": 1.1919127086007703e-05,
+      "loss": 0.4076,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4074757359428892,
+      "grad_norm": 3.1843597604004144,
+      "learning_rate": 1.1854942233632865e-05,
+      "loss": 0.4093,
+      "step": 1270
+    },
+    {
+      "epoch": 0.41068420630464425,
+      "grad_norm": 3.243310369644707,
+      "learning_rate": 1.1790757381258025e-05,
+      "loss": 0.3996,
+      "step": 1280
+    },
+    {
+      "epoch": 0.4138926766663993,
+      "grad_norm": 6.5805185922112654,
+      "learning_rate": 1.1726572528883185e-05,
+      "loss": 0.4443,
+      "step": 1290
+    },
+    {
+      "epoch": 0.4171011470281543,
+      "grad_norm": 3.5901965588799833,
+      "learning_rate": 1.1662387676508344e-05,
+      "loss": 0.4222,
+      "step": 1300
+    },
+    {
+      "epoch": 0.42030961738990935,
+      "grad_norm": 3.5975503587085513,
+      "learning_rate": 1.1598202824133507e-05,
+      "loss": 0.3803,
+      "step": 1310
+    },
+    {
+      "epoch": 0.4235180877516644,
+      "grad_norm": 3.8370137218295612,
+      "learning_rate": 1.1534017971758667e-05,
+      "loss": 0.377,
+      "step": 1320
+    },
+    {
+      "epoch": 0.4267265581134194,
+      "grad_norm": 6.055162453845242,
+      "learning_rate": 1.1469833119383826e-05,
+      "loss": 0.4371,
+      "step": 1330
+    },
+    {
+      "epoch": 0.42993502847517445,
+      "grad_norm": 4.303475483832273,
+      "learning_rate": 1.1405648267008986e-05,
+      "loss": 0.3991,
+      "step": 1340
+    },
+    {
+      "epoch": 0.4331434988369295,
+      "grad_norm": 3.481300920221893,
+      "learning_rate": 1.1341463414634146e-05,
+      "loss": 0.408,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4363519691986845,
+      "grad_norm": 2.70794769803311,
+      "learning_rate": 1.1277278562259308e-05,
+      "loss": 0.4105,
+      "step": 1360
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 4.540637646839311,
+      "learning_rate": 1.1213093709884468e-05,
+      "loss": 0.3762,
+      "step": 1370
+    },
+    {
+      "epoch": 0.4427689099221946,
+      "grad_norm": 3.240923093729635,
+      "learning_rate": 1.1148908857509628e-05,
+      "loss": 0.3198,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4459773802839496,
+      "grad_norm": 4.079516203900489,
+      "learning_rate": 1.1084724005134788e-05,
+      "loss": 0.4255,
+      "step": 1390
+    },
+    {
+      "epoch": 0.44918585064570465,
+      "grad_norm": 4.424913833083467,
+      "learning_rate": 1.102053915275995e-05,
+      "loss": 0.422,
+      "step": 1400
+    },
+    {
+      "epoch": 0.4523943210074597,
+      "grad_norm": 4.215968513158678,
+      "learning_rate": 1.095635430038511e-05,
+      "loss": 0.3717,
+      "step": 1410
+    },
+    {
+      "epoch": 0.4556027913692147,
+      "grad_norm": 7.080680051130726,
+      "learning_rate": 1.089216944801027e-05,
+      "loss": 0.4167,
+      "step": 1420
+    },
+    {
+      "epoch": 0.45881126173096975,
+      "grad_norm": 54.87405885391659,
+      "learning_rate": 1.082798459563543e-05,
+      "loss": 0.3701,
+      "step": 1430
+    },
+    {
+      "epoch": 0.4620197320927248,
+      "grad_norm": 4.745370324575341,
+      "learning_rate": 1.0763799743260592e-05,
+      "loss": 0.4192,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4652282024544798,
+      "grad_norm": 4.072739876459792,
+      "learning_rate": 1.0699614890885752e-05,
+      "loss": 0.3648,
+      "step": 1450
+    },
+    {
+      "epoch": 0.46843667281623486,
+      "grad_norm": 5.361505931287111,
+      "learning_rate": 1.0635430038510912e-05,
+      "loss": 0.3908,
+      "step": 1460
+    },
+    {
+      "epoch": 0.4716451431779899,
+      "grad_norm": 6.609039672159613,
+      "learning_rate": 1.0571245186136072e-05,
+      "loss": 0.3927,
+      "step": 1470
+    },
+    {
+      "epoch": 0.4748536135397449,
+      "grad_norm": 5.257109634802722,
+      "learning_rate": 1.0507060333761234e-05,
+      "loss": 0.3901,
+      "step": 1480
+    },
+    {
+      "epoch": 0.47806208390149996,
+      "grad_norm": 2.959492453957149,
+      "learning_rate": 1.0442875481386394e-05,
+      "loss": 0.3616,
+      "step": 1490
+    },
+    {
+      "epoch": 0.481270554263255,
+      "grad_norm": 4.53017762648938,
+      "learning_rate": 1.0378690629011554e-05,
+      "loss": 0.4099,
+      "step": 1500
+    },
+    {
+      "epoch": 0.48447902462501,
+      "grad_norm": 5.632280418736274,
+      "learning_rate": 1.0314505776636715e-05,
+      "loss": 0.4176,
+      "step": 1510
+    },
+    {
+      "epoch": 0.48768749498676506,
+      "grad_norm": 3.4384598745003627,
+      "learning_rate": 1.0250320924261875e-05,
+      "loss": 0.3586,
+      "step": 1520
+    },
+    {
+      "epoch": 0.4908959653485201,
+      "grad_norm": 3.024437029724823,
+      "learning_rate": 1.0186136071887036e-05,
+      "loss": 0.4255,
+      "step": 1530
+    },
+    {
+      "epoch": 0.4941044357102751,
+      "grad_norm": 2.378291269172342,
+      "learning_rate": 1.0121951219512197e-05,
+      "loss": 0.3958,
+      "step": 1540
+    },
+    {
+      "epoch": 0.49731290607203016,
+      "grad_norm": 4.62474422398616,
+      "learning_rate": 1.0057766367137357e-05,
+      "loss": 0.4006,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5005213764337852,
+      "grad_norm": 3.6745219934625144,
+      "learning_rate": 9.993581514762517e-06,
+      "loss": 0.3682,
+      "step": 1560
+    },
+    {
+      "epoch": 0.5037298467955402,
+      "grad_norm": 4.448848307155705,
+      "learning_rate": 9.929396662387677e-06,
+      "loss": 0.4272,
+      "step": 1570
+    },
+    {
+      "epoch": 0.5069383171572952,
+      "grad_norm": 3.8894278011874235,
+      "learning_rate": 9.865211810012839e-06,
+      "loss": 0.3569,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5101467875190503,
+      "grad_norm": 4.774303748597002,
+      "learning_rate": 9.801026957637997e-06,
+      "loss": 0.3933,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5133552578808053,
+      "grad_norm": 5.045270496853991,
+      "learning_rate": 9.736842105263159e-06,
+      "loss": 0.3719,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5165637282425604,
+      "grad_norm": 4.740584901110403,
+      "learning_rate": 9.672657252888319e-06,
+      "loss": 0.4254,
+      "step": 1610
+    },
+    {
+      "epoch": 0.5197721986043153,
+      "grad_norm": 5.884473992854898,
+      "learning_rate": 9.60847240051348e-06,
+      "loss": 0.4251,
+      "step": 1620
+    },
+    {
+      "epoch": 0.5229806689660704,
+      "grad_norm": 3.4560812191487233,
+      "learning_rate": 9.54428754813864e-06,
+      "loss": 0.3884,
+      "step": 1630
+    },
+    {
+      "epoch": 0.5261891393278254,
+      "grad_norm": 4.436488938480811,
+      "learning_rate": 9.480102695763801e-06,
+      "loss": 0.3791,
+      "step": 1640
+    },
+    {
+      "epoch": 0.5293976096895805,
+      "grad_norm": 5.122741798151655,
+      "learning_rate": 9.415917843388961e-06,
+      "loss": 0.4109,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5326060800513355,
+      "grad_norm": 2.8268137365317694,
+      "learning_rate": 9.351732991014121e-06,
+      "loss": 0.4002,
+      "step": 1660
+    },
+    {
+      "epoch": 0.5358145504130906,
+      "grad_norm": 4.961028503814302,
+      "learning_rate": 9.287548138639282e-06,
+      "loss": 0.4117,
+      "step": 1670
+    },
+    {
+      "epoch": 0.5390230207748455,
+      "grad_norm": 5.913940405056516,
+      "learning_rate": 9.223363286264443e-06,
+      "loss": 0.3837,
+      "step": 1680
+    },
+    {
+      "epoch": 0.5422314911366006,
+      "grad_norm": 4.981120773191797,
+      "learning_rate": 9.159178433889603e-06,
+      "loss": 0.4258,
+      "step": 1690
+    },
+    {
+      "epoch": 0.5454399614983556,
+      "grad_norm": 5.444655853775516,
+      "learning_rate": 9.094993581514764e-06,
+      "loss": 0.4301,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5486484318601107,
+      "grad_norm": 3.848013181214462,
+      "learning_rate": 9.030808729139924e-06,
+      "loss": 0.4004,
+      "step": 1710
+    },
+    {
+      "epoch": 0.5518569022218657,
+      "grad_norm": 2.7256377363961692,
+      "learning_rate": 8.966623876765084e-06,
+      "loss": 0.4199,
+      "step": 1720
+    },
+    {
+      "epoch": 0.5550653725836208,
+      "grad_norm": 3.9591345977979278,
+      "learning_rate": 8.902439024390244e-06,
+      "loss": 0.3923,
+      "step": 1730
+    },
+    {
+      "epoch": 0.5582738429453757,
+      "grad_norm": 3.694097683677857,
+      "learning_rate": 8.838254172015404e-06,
+      "loss": 0.4245,
+      "step": 1740
+    },
+    {
+      "epoch": 0.5614823133071308,
+      "grad_norm": 4.752754487463968,
+      "learning_rate": 8.774069319640566e-06,
+      "loss": 0.3623,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5646907836688858,
+      "grad_norm": 4.933398001346964,
+      "learning_rate": 8.709884467265726e-06,
+      "loss": 0.3529,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5678992540306409,
+      "grad_norm": 4.10267822290099,
+      "learning_rate": 8.645699614890886e-06,
+      "loss": 0.3903,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5711077243923959,
+      "grad_norm": 5.948577818513,
+      "learning_rate": 8.581514762516046e-06,
+      "loss": 0.3923,
+      "step": 1780
+    },
+    {
+      "epoch": 0.574316194754151,
+      "grad_norm": 4.32270415025434,
+      "learning_rate": 8.517329910141208e-06,
+      "loss": 0.4162,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5775246651159059,
+      "grad_norm": 4.186201731866516,
+      "learning_rate": 8.453145057766368e-06,
+      "loss": 0.4006,
+      "step": 1800
+    },
+    {
+      "epoch": 0.580733135477661,
+      "grad_norm": 4.818472247869851,
+      "learning_rate": 8.388960205391528e-06,
+      "loss": 0.3841,
+      "step": 1810
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 3.722377675945526,
+      "learning_rate": 8.324775353016688e-06,
+      "loss": 0.4015,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5871500762011711,
+      "grad_norm": 3.581092339067193,
+      "learning_rate": 8.26059050064185e-06,
+      "loss": 0.4194,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5903585465629261,
+      "grad_norm": 3.8711833078388134,
+      "learning_rate": 8.19640564826701e-06,
+      "loss": 0.5039,
+      "step": 1840
+    },
+    {
+      "epoch": 0.5935670169246812,
+      "grad_norm": 5.312406861505809,
+      "learning_rate": 8.13222079589217e-06,
+      "loss": 0.3954,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5967754872864361,
+      "grad_norm": 5.128909473296003,
+      "learning_rate": 8.06803594351733e-06,
+      "loss": 0.3476,
+      "step": 1860
+    },
+    {
+      "epoch": 0.5999839576481912,
+      "grad_norm": 6.225968269360909,
+      "learning_rate": 8.00385109114249e-06,
+      "loss": 0.3918,
+      "step": 1870
+    },
+    {
+      "epoch": 0.6031924280099462,
+      "grad_norm": 4.660989653248528,
+      "learning_rate": 7.93966623876765e-06,
+      "loss": 0.4013,
+      "step": 1880
+    },
+    {
+      "epoch": 0.6064008983717013,
+      "grad_norm": 4.299519878675749,
+      "learning_rate": 7.875481386392811e-06,
+      "loss": 0.3775,
+      "step": 1890
+    },
+    {
+      "epoch": 0.6096093687334563,
+      "grad_norm": 4.680629637314835,
+      "learning_rate": 7.811296534017973e-06,
+      "loss": 0.3612,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6128178390952114,
+      "grad_norm": 4.152954271805758,
+      "learning_rate": 7.747111681643133e-06,
+      "loss": 0.3806,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6160263094569663,
+      "grad_norm": 4.6801179801552415,
+      "learning_rate": 7.682926829268293e-06,
+      "loss": 0.3506,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6192347798187214,
+      "grad_norm": 4.251504275426107,
+      "learning_rate": 7.618741976893453e-06,
+      "loss": 0.3589,
+      "step": 1930
+    },
+    {
+      "epoch": 0.6224432501804764,
+      "grad_norm": 6.009730313403801,
+      "learning_rate": 7.554557124518614e-06,
+      "loss": 0.3968,
+      "step": 1940
+    },
+    {
+      "epoch": 0.6256517205422315,
+      "grad_norm": 3.2723481829787464,
+      "learning_rate": 7.490372272143774e-06,
+      "loss": 0.3936,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6288601909039865,
+      "grad_norm": 4.097990240581078,
+      "learning_rate": 7.426187419768935e-06,
+      "loss": 0.4144,
+      "step": 1960
+    },
+    {
+      "epoch": 0.6320686612657416,
+      "grad_norm": 2.7191742984555995,
+      "learning_rate": 7.362002567394095e-06,
+      "loss": 0.409,
+      "step": 1970
+    },
+    {
+      "epoch": 0.6352771316274965,
+      "grad_norm": 4.40050340710905,
+      "learning_rate": 7.297817715019256e-06,
+      "loss": 0.3526,
+      "step": 1980
+    },
+    {
+      "epoch": 0.6384856019892516,
+      "grad_norm": 3.5711401894801194,
+      "learning_rate": 7.233632862644416e-06,
+      "loss": 0.3865,
+      "step": 1990
+    },
+    {
+      "epoch": 0.6416940723510066,
+      "grad_norm": 5.155189378251862,
+      "learning_rate": 7.169448010269577e-06,
+      "loss": 0.4037,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6449025427127617,
+      "grad_norm": 5.764606055822457,
+      "learning_rate": 7.1052631578947375e-06,
+      "loss": 0.3806,
+      "step": 2010
+    },
+    {
+      "epoch": 0.6481110130745167,
+      "grad_norm": 3.3930437034797585,
+      "learning_rate": 7.0410783055198984e-06,
+      "loss": 0.3951,
+      "step": 2020
+    },
+    {
+      "epoch": 0.6513194834362718,
+      "grad_norm": 4.922727726376936,
+      "learning_rate": 6.9768934531450586e-06,
+      "loss": 0.3847,
+      "step": 2030
+    },
+    {
+      "epoch": 0.6545279537980268,
+      "grad_norm": 2.7890174522963367,
+      "learning_rate": 6.9127086007702195e-06,
+      "loss": 0.3479,
+      "step": 2040
+    },
+    {
+      "epoch": 0.6577364241597818,
+      "grad_norm": 4.412823863289807,
+      "learning_rate": 6.84852374839538e-06,
+      "loss": 0.4173,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6609448945215368,
+      "grad_norm": 5.417820507568683,
+      "learning_rate": 6.784338896020539e-06,
+      "loss": 0.381,
+      "step": 2060
+    },
+    {
+      "epoch": 0.6641533648832919,
+      "grad_norm": 3.8506255680933528,
+      "learning_rate": 6.7201540436457e-06,
+      "loss": 0.3693,
+      "step": 2070
+    },
+    {
+      "epoch": 0.6673618352450469,
+      "grad_norm": 3.5416828656888786,
+      "learning_rate": 6.65596919127086e-06,
+      "loss": 0.358,
+      "step": 2080
+    },
+    {
+      "epoch": 0.670570305606802,
+      "grad_norm": 3.5323170162835775,
+      "learning_rate": 6.591784338896021e-06,
+      "loss": 0.3237,
+      "step": 2090
+    },
+    {
+      "epoch": 0.673778775968557,
+      "grad_norm": 6.128726604158042,
+      "learning_rate": 6.527599486521181e-06,
+      "loss": 0.3859,
+      "step": 2100
+    },
+    {
+      "epoch": 0.676987246330312,
+      "grad_norm": 4.891887980181221,
+      "learning_rate": 6.463414634146342e-06,
+      "loss": 0.3223,
+      "step": 2110
+    },
+    {
+      "epoch": 0.680195716692067,
+      "grad_norm": 3.565557213786112,
+      "learning_rate": 6.399229781771502e-06,
+      "loss": 0.363,
+      "step": 2120
+    },
+    {
+      "epoch": 0.6834041870538221,
+      "grad_norm": 3.4294258572573337,
+      "learning_rate": 6.335044929396663e-06,
+      "loss": 0.3781,
+      "step": 2130
+    },
+    {
+      "epoch": 0.6866126574155771,
+      "grad_norm": 4.518476500237087,
+      "learning_rate": 6.270860077021823e-06,
+      "loss": 0.4325,
+      "step": 2140
+    },
+    {
+      "epoch": 0.6898211277773322,
+      "grad_norm": 4.743599740115472,
+      "learning_rate": 6.206675224646984e-06,
+      "loss": 0.411,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6930295981390872,
+      "grad_norm": 2.5630593956213015,
+      "learning_rate": 6.142490372272144e-06,
+      "loss": 0.3717,
+      "step": 2160
+    },
+    {
+      "epoch": 0.6962380685008422,
+      "grad_norm": 6.2586555195558,
+      "learning_rate": 6.078305519897305e-06,
+      "loss": 0.3561,
+      "step": 2170
+    },
+    {
+      "epoch": 0.6994465388625972,
+      "grad_norm": 4.894715427924892,
+      "learning_rate": 6.0141206675224654e-06,
+      "loss": 0.4164,
+      "step": 2180
+    },
+    {
+      "epoch": 0.7026550092243523,
+      "grad_norm": 3.5252148379990573,
+      "learning_rate": 5.949935815147626e-06,
+      "loss": 0.3209,
+      "step": 2190
+    },
+    {
+      "epoch": 0.7058634795861073,
+      "grad_norm": 3.256470353538883,
+      "learning_rate": 5.885750962772786e-06,
+      "loss": 0.3893,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7090719499478624,
+      "grad_norm": 3.4671867719647573,
+      "learning_rate": 5.821566110397947e-06,
+      "loss": 0.3836,
+      "step": 2210
+    },
+    {
+      "epoch": 0.7122804203096174,
+      "grad_norm": 3.6300469654014806,
+      "learning_rate": 5.757381258023107e-06,
+      "loss": 0.3604,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7154888906713724,
+      "grad_norm": 4.8222353267885545,
+      "learning_rate": 5.693196405648267e-06,
+      "loss": 0.3402,
+      "step": 2230
+    },
+    {
+      "epoch": 0.7186973610331274,
+      "grad_norm": 3.088736996240411,
+      "learning_rate": 5.629011553273428e-06,
+      "loss": 0.3571,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7219058313948825,
+      "grad_norm": 6.468377008869226,
+      "learning_rate": 5.564826700898588e-06,
+      "loss": 0.3857,
+      "step": 2250
+    },
+    {
+      "epoch": 0.7251143017566375,
+      "grad_norm": 4.976006702523603,
+      "learning_rate": 5.500641848523749e-06,
+      "loss": 0.328,
+      "step": 2260
+    },
+    {
+      "epoch": 0.7283227721183926,
+      "grad_norm": 7.44768864343581,
+      "learning_rate": 5.436456996148909e-06,
+      "loss": 0.3415,
+      "step": 2270
+    },
+    {
+      "epoch": 0.7315312424801476,
+      "grad_norm": 6.342940977120239,
+      "learning_rate": 5.37227214377407e-06,
+      "loss": 0.3452,
+      "step": 2280
+    },
+    {
+      "epoch": 0.7347397128419026,
+      "grad_norm": 4.281955030745344,
+      "learning_rate": 5.30808729139923e-06,
+      "loss": 0.4647,
+      "step": 2290
+    },
+    {
+      "epoch": 0.7379481832036576,
+      "grad_norm": 3.678790025410135,
+      "learning_rate": 5.243902439024391e-06,
+      "loss": 0.3742,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7411566535654127,
+      "grad_norm": 3.3547281464794096,
+      "learning_rate": 5.179717586649551e-06,
+      "loss": 0.3835,
+      "step": 2310
+    },
+    {
+      "epoch": 0.7443651239271677,
+      "grad_norm": 5.13222360440861,
+      "learning_rate": 5.115532734274712e-06,
+      "loss": 0.3859,
+      "step": 2320
+    },
+    {
+      "epoch": 0.7475735942889228,
+      "grad_norm": 3.972710625172556,
+      "learning_rate": 5.0513478818998715e-06,
+      "loss": 0.3537,
+      "step": 2330
+    },
+    {
+      "epoch": 0.7507820646506778,
+      "grad_norm": 3.2744384458301687,
+      "learning_rate": 4.9871630295250324e-06,
+      "loss": 0.3793,
+      "step": 2340
+    },
+    {
+      "epoch": 0.7539905350124328,
+      "grad_norm": 3.8532031308587396,
+      "learning_rate": 4.9229781771501926e-06,
+      "loss": 0.3245,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7571990053741878,
+      "grad_norm": 6.097220741982411,
+      "learning_rate": 4.8587933247753535e-06,
+      "loss": 0.4381,
+      "step": 2360
+    },
+    {
+      "epoch": 0.7604074757359429,
+      "grad_norm": 3.6161720053467743,
+      "learning_rate": 4.794608472400514e-06,
+      "loss": 0.3904,
+      "step": 2370
+    },
+    {
+      "epoch": 0.7636159460976979,
+      "grad_norm": 3.2126570713513196,
+      "learning_rate": 4.730423620025675e-06,
+      "loss": 0.3698,
+      "step": 2380
+    },
+    {
+      "epoch": 0.766824416459453,
+      "grad_norm": 4.440937942880446,
+      "learning_rate": 4.666238767650835e-06,
+      "loss": 0.3672,
+      "step": 2390
+    },
+    {
+      "epoch": 0.770032886821208,
+      "grad_norm": 4.034010642616632,
+      "learning_rate": 4.602053915275995e-06,
+      "loss": 0.3453,
+      "step": 2400
+    },
+    {
+      "epoch": 0.773241357182963,
+      "grad_norm": 4.320673481292839,
+      "learning_rate": 4.537869062901156e-06,
+      "loss": 0.3874,
+      "step": 2410
+    },
+    {
+      "epoch": 0.776449827544718,
+      "grad_norm": 5.721110452311635,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.3361,
+      "step": 2420
+    },
+    {
+      "epoch": 0.7796582979064731,
+      "grad_norm": 5.553593669289626,
+      "learning_rate": 4.409499358151477e-06,
+      "loss": 0.3761,
+      "step": 2430
+    },
+    {
+      "epoch": 0.7828667682682281,
+      "grad_norm": 3.5931839661915506,
+      "learning_rate": 4.345314505776637e-06,
+      "loss": 0.3303,
+      "step": 2440
+    },
+    {
+      "epoch": 0.7860752386299832,
+      "grad_norm": 3.191917593220325,
+      "learning_rate": 4.281129653401798e-06,
+      "loss": 0.4581,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7892837089917382,
+      "grad_norm": 2.071662511958508,
+      "learning_rate": 4.216944801026958e-06,
+      "loss": 0.3602,
+      "step": 2460
+    },
+    {
+      "epoch": 0.7924921793534933,
+      "grad_norm": 4.1098396579418015,
+      "learning_rate": 4.152759948652118e-06,
+      "loss": 0.3658,
+      "step": 2470
+    },
+    {
+      "epoch": 0.7957006497152482,
+      "grad_norm": 3.342343894793557,
+      "learning_rate": 4.088575096277279e-06,
+      "loss": 0.3533,
+      "step": 2480
+    },
+    {
+      "epoch": 0.7989091200770033,
+      "grad_norm": 3.501852515883717,
+      "learning_rate": 4.024390243902439e-06,
+      "loss": 0.3086,
+      "step": 2490
+    },
+    {
+      "epoch": 0.8021175904387583,
+      "grad_norm": 5.6740246031343275,
+      "learning_rate": 3.9602053915276e-06,
+      "loss": 0.3619,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8053260608005134,
+      "grad_norm": 3.6625993713157867,
+      "learning_rate": 3.89602053915276e-06,
+      "loss": 0.3536,
+      "step": 2510
+    },
+    {
+      "epoch": 0.8085345311622684,
+      "grad_norm": 4.12817611506417,
+      "learning_rate": 3.8318356867779205e-06,
+      "loss": 0.3552,
+      "step": 2520
+    },
+    {
+      "epoch": 0.8117430015240235,
+      "grad_norm": 6.752665333536269,
+      "learning_rate": 3.767650834403081e-06,
+      "loss": 0.3906,
+      "step": 2530
+    },
+    {
+      "epoch": 0.8149514718857784,
+      "grad_norm": 4.0698833515045765,
+      "learning_rate": 3.7034659820282416e-06,
+      "loss": 0.369,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8181599422475335,
+      "grad_norm": 3.8061893249692167,
+      "learning_rate": 3.639281129653402e-06,
+      "loss": 0.391,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8213684126092885,
+      "grad_norm": 4.2054055524032075,
+      "learning_rate": 3.5750962772785623e-06,
+      "loss": 0.3781,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8245768829710436,
+      "grad_norm": 3.1509974167473294,
+      "learning_rate": 3.510911424903723e-06,
+      "loss": 0.4246,
+      "step": 2570
+    },
+    {
+      "epoch": 0.8277853533327986,
+      "grad_norm": 3.344075353049933,
+      "learning_rate": 3.4467265725288834e-06,
+      "loss": 0.3839,
+      "step": 2580
+    },
+    {
+      "epoch": 0.8309938236945537,
+      "grad_norm": 4.3862748314587625,
+      "learning_rate": 3.382541720154044e-06,
+      "loss": 0.3243,
+      "step": 2590
+    },
+    {
+      "epoch": 0.8342022940563086,
+      "grad_norm": 4.430571971071977,
+      "learning_rate": 3.3183568677792044e-06,
+      "loss": 0.4219,
+      "step": 2600
+    },
+    {
+      "epoch": 0.8374107644180637,
+      "grad_norm": 4.216572691360644,
+      "learning_rate": 3.254172015404365e-06,
+      "loss": 0.3453,
+      "step": 2610
+    },
+    {
+      "epoch": 0.8406192347798187,
+      "grad_norm": 5.730663867597084,
+      "learning_rate": 3.1899871630295255e-06,
+      "loss": 0.3652,
+      "step": 2620
+    },
+    {
+      "epoch": 0.8438277051415738,
+      "grad_norm": 3.152373466591917,
+      "learning_rate": 3.125802310654686e-06,
+      "loss": 0.3761,
+      "step": 2630
+    },
+    {
+      "epoch": 0.8470361755033288,
+      "grad_norm": 4.049903812572876,
+      "learning_rate": 3.061617458279846e-06,
+      "loss": 0.4274,
+      "step": 2640
+    },
+    {
+      "epoch": 0.8502446458650839,
+      "grad_norm": 3.7109620908295002,
+      "learning_rate": 2.9974326059050067e-06,
+      "loss": 0.3575,
+      "step": 2650
+    },
+    {
+      "epoch": 0.8534531162268388,
+      "grad_norm": 6.151962412156622,
+      "learning_rate": 2.9332477535301673e-06,
+      "loss": 0.3935,
+      "step": 2660
+    },
+    {
+      "epoch": 0.8566615865885939,
+      "grad_norm": 2.8483008748019474,
+      "learning_rate": 2.869062901155328e-06,
+      "loss": 0.3327,
+      "step": 2670
+    },
+    {
+      "epoch": 0.8598700569503489,
+      "grad_norm": 3.884150141973327,
+      "learning_rate": 2.8048780487804884e-06,
+      "loss": 0.3222,
+      "step": 2680
+    },
+    {
+      "epoch": 0.863078527312104,
+      "grad_norm": 5.091883011304281,
+      "learning_rate": 2.740693196405648e-06,
+      "loss": 0.4241,
+      "step": 2690
+    },
+    {
+      "epoch": 0.866286997673859,
+      "grad_norm": 6.256322006655992,
+      "learning_rate": 2.6765083440308086e-06,
+      "loss": 0.3896,
+      "step": 2700
+    },
+    {
+      "epoch": 0.8694954680356141,
+      "grad_norm": 3.185423190731702,
+      "learning_rate": 2.612323491655969e-06,
+      "loss": 0.3503,
+      "step": 2710
+    },
+    {
+      "epoch": 0.872703938397369,
+      "grad_norm": 2.501677043437045,
+      "learning_rate": 2.5481386392811297e-06,
+      "loss": 0.308,
+      "step": 2720
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 3.994307293016134,
+      "learning_rate": 2.4839537869062902e-06,
+      "loss": 0.3146,
+      "step": 2730
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 6.3218538833338185,
+      "learning_rate": 2.4197689345314508e-06,
+      "loss": 0.3861,
+      "step": 2740
+    },
+    {
+      "epoch": 0.8823293494826342,
+      "grad_norm": 4.2929895131508875,
+      "learning_rate": 2.3555840821566113e-06,
+      "loss": 0.3514,
+      "step": 2750
+    },
+    {
+      "epoch": 0.8855378198443892,
+      "grad_norm": 5.013441973517175,
+      "learning_rate": 2.2913992297817714e-06,
+      "loss": 0.3394,
+      "step": 2760
+    },
+    {
+      "epoch": 0.8887462902061443,
+      "grad_norm": 4.942588457664286,
+      "learning_rate": 2.227214377406932e-06,
+      "loss": 0.3916,
+      "step": 2770
+    },
+    {
+      "epoch": 0.8919547605678992,
+      "grad_norm": 4.093044885114057,
+      "learning_rate": 2.1630295250320925e-06,
+      "loss": 0.3316,
+      "step": 2780
+    },
+    {
+      "epoch": 0.8951632309296543,
+      "grad_norm": 3.6241454294578044,
+      "learning_rate": 2.098844672657253e-06,
+      "loss": 0.328,
+      "step": 2790
+    },
+    {
+      "epoch": 0.8983717012914093,
+      "grad_norm": 3.7585099242216105,
+      "learning_rate": 2.0346598202824136e-06,
+      "loss": 0.313,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9015801716531644,
+      "grad_norm": 3.092191111039683,
+      "learning_rate": 1.970474967907574e-06,
+      "loss": 0.3207,
+      "step": 2810
+    },
+    {
+      "epoch": 0.9047886420149194,
+      "grad_norm": 7.126196821569378,
+      "learning_rate": 1.9062901155327343e-06,
+      "loss": 0.339,
+      "step": 2820
+    },
+    {
+      "epoch": 0.9079971123766745,
+      "grad_norm": 3.98517835436473,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 0.3119,
+      "step": 2830
+    },
+    {
+      "epoch": 0.9112055827384294,
+      "grad_norm": 5.155996828725616,
+      "learning_rate": 1.7779204107830554e-06,
+      "loss": 0.3524,
+      "step": 2840
+    },
+    {
+      "epoch": 0.9144140531001845,
+      "grad_norm": 6.2418873185093116,
+      "learning_rate": 1.7137355584082157e-06,
+      "loss": 0.3697,
+      "step": 2850
+    },
+    {
+      "epoch": 0.9176225234619395,
+      "grad_norm": 4.93642870905445,
+      "learning_rate": 1.6495507060333762e-06,
+      "loss": 0.3567,
+      "step": 2860
+    },
+    {
+      "epoch": 0.9208309938236946,
+      "grad_norm": 3.4661449590899815,
+      "learning_rate": 1.5853658536585368e-06,
+      "loss": 0.3049,
+      "step": 2870
+    },
+    {
+      "epoch": 0.9240394641854496,
+      "grad_norm": 3.9858026943112046,
+      "learning_rate": 1.5211810012836973e-06,
+      "loss": 0.342,
+      "step": 2880
+    },
+    {
+      "epoch": 0.9272479345472047,
+      "grad_norm": 5.747224506777868,
+      "learning_rate": 1.4569961489088577e-06,
+      "loss": 0.3786,
+      "step": 2890
+    },
+    {
+      "epoch": 0.9304564049089596,
+      "grad_norm": 4.2756510193950135,
+      "learning_rate": 1.3928112965340182e-06,
+      "loss": 0.345,
+      "step": 2900
+    },
+    {
+      "epoch": 0.9336648752707147,
+      "grad_norm": 5.737301674162469,
+      "learning_rate": 1.3286264441591783e-06,
+      "loss": 0.3048,
+      "step": 2910
+    },
+    {
+      "epoch": 0.9368733456324697,
+      "grad_norm": 4.5368921290576125,
+      "learning_rate": 1.2644415917843389e-06,
+      "loss": 0.3373,
+      "step": 2920
+    },
+    {
+      "epoch": 0.9400818159942248,
+      "grad_norm": 6.281727114562743,
+      "learning_rate": 1.2002567394094996e-06,
+      "loss": 0.3713,
+      "step": 2930
+    },
+    {
+      "epoch": 0.9432902863559798,
+      "grad_norm": 4.613863643534097,
+      "learning_rate": 1.13607188703466e-06,
+      "loss": 0.3115,
+      "step": 2940
+    },
+    {
+      "epoch": 0.9464987567177349,
+      "grad_norm": 4.4955128133503415,
+      "learning_rate": 1.0718870346598203e-06,
+      "loss": 0.3544,
+      "step": 2950
+    },
+    {
+      "epoch": 0.9497072270794898,
+      "grad_norm": 6.144202111803078,
+      "learning_rate": 1.0077021822849808e-06,
+      "loss": 0.3419,
+      "step": 2960
+    },
+    {
+      "epoch": 0.9529156974412449,
+      "grad_norm": 3.416734695378003,
+      "learning_rate": 9.435173299101414e-07,
+      "loss": 0.3866,
+      "step": 2970
+    },
+    {
+      "epoch": 0.9561241678029999,
+      "grad_norm": 2.9130051363163507,
+      "learning_rate": 8.793324775353017e-07,
+      "loss": 0.3294,
+      "step": 2980
+    },
+    {
+      "epoch": 0.959332638164755,
+      "grad_norm": 4.1544972260670345,
+      "learning_rate": 8.151476251604621e-07,
+      "loss": 0.337,
+      "step": 2990
+    },
+    {
+      "epoch": 0.96254110852651,
+      "grad_norm": 5.333751729311107,
+      "learning_rate": 7.509627727856227e-07,
+      "loss": 0.3707,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9657495788882651,
+      "grad_norm": 4.224378334244017,
+      "learning_rate": 6.867779204107831e-07,
+      "loss": 0.3266,
+      "step": 3010
+    },
+    {
+      "epoch": 0.96895804925002,
+      "grad_norm": 4.68085662929714,
+      "learning_rate": 6.225930680359436e-07,
+      "loss": 0.3228,
+      "step": 3020
+    },
+    {
+      "epoch": 0.9721665196117751,
+      "grad_norm": 2.44350959307893,
+      "learning_rate": 5.584082156611041e-07,
+      "loss": 0.3038,
+      "step": 3030
+    },
+    {
+      "epoch": 0.9753749899735301,
+      "grad_norm": 5.5263577593599225,
+      "learning_rate": 4.942233632862644e-07,
+      "loss": 0.3073,
+      "step": 3040
+    },
+    {
+      "epoch": 0.9785834603352852,
+      "grad_norm": 5.517219216862406,
+      "learning_rate": 4.30038510911425e-07,
+      "loss": 0.4016,
+      "step": 3050
+    },
+    {
+      "epoch": 0.9817919306970402,
+      "grad_norm": 3.559703237499543,
+      "learning_rate": 3.6585365853658536e-07,
+      "loss": 0.4128,
+      "step": 3060
+    },
+    {
+      "epoch": 0.9850004010587953,
+      "grad_norm": 3.2825888661809057,
+      "learning_rate": 3.0166880616174585e-07,
+      "loss": 0.2873,
+      "step": 3070
+    },
+    {
+      "epoch": 0.9882088714205502,
+      "grad_norm": 3.755613548892917,
+      "learning_rate": 2.374839537869063e-07,
+      "loss": 0.3854,
+      "step": 3080
+    },
+    {
+      "epoch": 0.9914173417823053,
+      "grad_norm": 4.172412303358024,
+      "learning_rate": 1.7329910141206678e-07,
+      "loss": 0.328,
+      "step": 3090
+    },
+    {
+      "epoch": 0.9946258121440603,
+      "grad_norm": 6.547343932529505,
+      "learning_rate": 1.0911424903722721e-07,
+      "loss": 0.3947,
+      "step": 3100
+    },
+    {
+      "epoch": 0.9978342825058154,
+      "grad_norm": 4.624930868093504,
+      "learning_rate": 4.4929396662387685e-08,
+      "loss": 0.3312,
+      "step": 3110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8140295d10baf1d60a18e7be6b9151e7a6f81aa9521c1dc606c2fdf01b6ad32
+size 6904

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)