Upload folder using huggingface_hub

checkpoint-12208/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-my-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-12208/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-12208/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df84468fd3a3d3cad8f3cbd095cc977b60979893e73c93d5ee09fb2379222010
+size 4842817304

checkpoint-12208/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-12208/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304

checkpoint-12208/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-12208/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-12208/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f092152489dd4cdc6cfd8f3503c64362660fb56a4d37d0a9fa01152ca2902b5
+size 3662865184

checkpoint-12208/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f548b485cc3226866ffd6a1621789aeb3bf01f2f59db2a067a734f44c1a8749
+size 2317729920

checkpoint-12208/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30737946624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-12208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98bcc05e6cbe58b16d26af4816839243a8911e23f3b60bef8b4236a64614b30e
+size 16728842070

checkpoint-12208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-12208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe644ed33a3c4139223f0857a985127f3e6fbaa8c89fa14b57671b49ca52c21
+size 1064

checkpoint-12208/trainer_state.json

@@ -0,0 +1,2784 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.30584226876440523,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000776630924942379,
+      "grad_norm": 23.55321502685547,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 8.3443,
+      "step": 31
+    },
+    {
+      "epoch": 0.001553261849884758,
+      "grad_norm": 14.414477348327637,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.198,
+      "step": 62
+    },
+    {
+      "epoch": 0.002329892774827137,
+      "grad_norm": 10.739773750305176,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 5.8639,
+      "step": 93
+    },
+    {
+      "epoch": 0.003106523699769516,
+      "grad_norm": 5.378795623779297,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 4.8222,
+      "step": 124
+    },
+    {
+      "epoch": 0.003883154624711895,
+      "grad_norm": 8.51831340789795,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.1983,
+      "step": 155
+    },
+    {
+      "epoch": 0.004659785549654274,
+      "grad_norm": 6.32632303237915,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 3.8598,
+      "step": 186
+    },
+    {
+      "epoch": 0.005436416474596653,
+      "grad_norm": 5.590794563293457,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 3.6646,
+      "step": 217
+    },
+    {
+      "epoch": 0.006213047399539032,
+      "grad_norm": 5.9275383949279785,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.5212,
+      "step": 248
+    },
+    {
+      "epoch": 0.006989678324481411,
+      "grad_norm": 5.041291236877441,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.3936,
+      "step": 279
+    },
+    {
+      "epoch": 0.00776630924942379,
+      "grad_norm": 4.923459529876709,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.2713,
+      "step": 310
+    },
+    {
+      "epoch": 0.00854294017436617,
+      "grad_norm": 8.011459350585938,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.2,
+      "step": 341
+    },
+    {
+      "epoch": 0.009319571099308548,
+      "grad_norm": 5.261505603790283,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.1255,
+      "step": 372
+    },
+    {
+      "epoch": 0.010096202024250926,
+      "grad_norm": 5.004406452178955,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 3.0726,
+      "step": 403
+    },
+    {
+      "epoch": 0.010872832949193306,
+      "grad_norm": 4.326263427734375,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 2.9682,
+      "step": 434
+    },
+    {
+      "epoch": 0.011649463874135685,
+      "grad_norm": 4.251937389373779,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 2.9215,
+      "step": 465
+    },
+    {
+      "epoch": 0.012426094799078065,
+      "grad_norm": 4.35053825378418,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 2.8902,
+      "step": 496
+    },
+    {
+      "epoch": 0.013202725724020443,
+      "grad_norm": 4.316098690032959,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 2.8521,
+      "step": 527
+    },
+    {
+      "epoch": 0.013979356648962823,
+      "grad_norm": 5.536881446838379,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 2.8058,
+      "step": 558
+    },
+    {
+      "epoch": 0.014755987573905201,
+      "grad_norm": 3.759843111038208,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 2.7438,
+      "step": 589
+    },
+    {
+      "epoch": 0.01553261849884758,
+      "grad_norm": 4.057703018188477,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 2.7508,
+      "step": 620
+    },
+    {
+      "epoch": 0.01630924942378996,
+      "grad_norm": 3.427708625793457,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 2.7046,
+      "step": 651
+    },
+    {
+      "epoch": 0.01708588034873234,
+      "grad_norm": 3.9012484550476074,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 2.6706,
+      "step": 682
+    },
+    {
+      "epoch": 0.017862511273674716,
+      "grad_norm": 3.388504981994629,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 2.6377,
+      "step": 713
+    },
+    {
+      "epoch": 0.018639142198617096,
+      "grad_norm": 3.2011327743530273,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.6214,
+      "step": 744
+    },
+    {
+      "epoch": 0.019415773123559476,
+      "grad_norm": 3.5897209644317627,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.6045,
+      "step": 775
+    },
+    {
+      "epoch": 0.020192404048501852,
+      "grad_norm": 3.386697769165039,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.6066,
+      "step": 806
+    },
+    {
+      "epoch": 0.020969034973444232,
+      "grad_norm": 2.9135866165161133,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.5697,
+      "step": 837
+    },
+    {
+      "epoch": 0.021745665898386612,
+      "grad_norm": 9.212065696716309,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.5773,
+      "step": 868
+    },
+    {
+      "epoch": 0.022522296823328992,
+      "grad_norm": 3.0339765548706055,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.5453,
+      "step": 899
+    },
+    {
+      "epoch": 0.02329892774827137,
+      "grad_norm": 2.8007607460021973,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.5297,
+      "step": 930
+    },
+    {
+      "epoch": 0.02407555867321375,
+      "grad_norm": 3.251768112182617,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.5273,
+      "step": 961
+    },
+    {
+      "epoch": 0.02485218959815613,
+      "grad_norm": 3.357011079788208,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.4896,
+      "step": 992
+    },
+    {
+      "epoch": 0.025628820523098506,
+      "grad_norm": 2.6069107055664062,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.4718,
+      "step": 1023
+    },
+    {
+      "epoch": 0.026405451448040886,
+      "grad_norm": 4.663620948791504,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.4338,
+      "step": 1054
+    },
+    {
+      "epoch": 0.027182082372983266,
+      "grad_norm": 3.819638252258301,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.4848,
+      "step": 1085
+    },
+    {
+      "epoch": 0.027958713297925646,
+      "grad_norm": 2.6367456912994385,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.4415,
+      "step": 1116
+    },
+    {
+      "epoch": 0.028735344222868022,
+      "grad_norm": 2.6118173599243164,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.4341,
+      "step": 1147
+    },
+    {
+      "epoch": 0.029511975147810402,
+      "grad_norm": 9.820366859436035,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.3773,
+      "step": 1178
+    },
+    {
+      "epoch": 0.030288606072752782,
+      "grad_norm": 38.890506744384766,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.3966,
+      "step": 1209
+    },
+    {
+      "epoch": 0.03106523699769516,
+      "grad_norm": 2.5037872791290283,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.3421,
+      "step": 1240
+    },
+    {
+      "epoch": 0.03184186792263754,
+      "grad_norm": 2.426544189453125,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.3568,
+      "step": 1271
+    },
+    {
+      "epoch": 0.03261849884757992,
+      "grad_norm": 2.5375614166259766,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.3314,
+      "step": 1302
+    },
+    {
+      "epoch": 0.0333951297725223,
+      "grad_norm": 3.555330276489258,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.3262,
+      "step": 1333
+    },
+    {
+      "epoch": 0.03417176069746468,
+      "grad_norm": 2.2571263313293457,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.3167,
+      "step": 1364
+    },
+    {
+      "epoch": 0.03494839162240705,
+      "grad_norm": 2.184305429458618,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.2936,
+      "step": 1395
+    },
+    {
+      "epoch": 0.03572502254734943,
+      "grad_norm": 2.8295061588287354,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.3033,
+      "step": 1426
+    },
+    {
+      "epoch": 0.03650165347229181,
+      "grad_norm": 2.0241498947143555,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.2833,
+      "step": 1457
+    },
+    {
+      "epoch": 0.03727828439723419,
+      "grad_norm": 2.0029919147491455,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.2663,
+      "step": 1488
+    },
+    {
+      "epoch": 0.03805491532217657,
+      "grad_norm": 2.033773899078369,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.2597,
+      "step": 1519
+    },
+    {
+      "epoch": 0.03883154624711895,
+      "grad_norm": 2.047210216522217,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 2.2231,
+      "step": 1550
+    },
+    {
+      "epoch": 0.03960817717206133,
+      "grad_norm": 2.032099485397339,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.2411,
+      "step": 1581
+    },
+    {
+      "epoch": 0.040384808097003705,
+      "grad_norm": 1.8384301662445068,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.2409,
+      "step": 1612
+    },
+    {
+      "epoch": 0.041161439021946085,
+      "grad_norm": 1.721187710762024,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.193,
+      "step": 1643
+    },
+    {
+      "epoch": 0.041938069946888465,
+      "grad_norm": 1.8869743347167969,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.1917,
+      "step": 1674
+    },
+    {
+      "epoch": 0.042714700871830845,
+      "grad_norm": 1.796583652496338,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.1794,
+      "step": 1705
+    },
+    {
+      "epoch": 0.043491331796773225,
+      "grad_norm": 1.6308804750442505,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.1854,
+      "step": 1736
+    },
+    {
+      "epoch": 0.044267962721715605,
+      "grad_norm": 1.683474063873291,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 2.1797,
+      "step": 1767
+    },
+    {
+      "epoch": 0.045044593646657985,
+      "grad_norm": 1.7442835569381714,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 2.1695,
+      "step": 1798
+    },
+    {
+      "epoch": 0.04582122457160036,
+      "grad_norm": 1.704970359802246,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 2.1365,
+      "step": 1829
+    },
+    {
+      "epoch": 0.04659785549654274,
+      "grad_norm": 1.7213023900985718,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 2.1524,
+      "step": 1860
+    },
+    {
+      "epoch": 0.04737448642148512,
+      "grad_norm": 4.01851224899292,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 2.1171,
+      "step": 1891
+    },
+    {
+      "epoch": 0.0481511173464275,
+      "grad_norm": 1.5619858503341675,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 2.1608,
+      "step": 1922
+    },
+    {
+      "epoch": 0.04892774827136988,
+      "grad_norm": 1.684493064880371,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 2.1278,
+      "step": 1953
+    },
+    {
+      "epoch": 0.04970437919631226,
+      "grad_norm": 1.660992980003357,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 2.1136,
+      "step": 1984
+    },
+    {
+      "epoch": 0.05048101012125464,
+      "grad_norm": 1.5491065979003906,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 2.1086,
+      "step": 2015
+    },
+    {
+      "epoch": 0.05125764104619701,
+      "grad_norm": 1.5400840044021606,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 2.1069,
+      "step": 2046
+    },
+    {
+      "epoch": 0.05203427197113939,
+      "grad_norm": 1.5687416791915894,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 2.0888,
+      "step": 2077
+    },
+    {
+      "epoch": 0.05281090289608177,
+      "grad_norm": 1.5218935012817383,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 2.1032,
+      "step": 2108
+    },
+    {
+      "epoch": 0.05358753382102415,
+      "grad_norm": 1.763666033744812,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 2.0799,
+      "step": 2139
+    },
+    {
+      "epoch": 0.05436416474596653,
+      "grad_norm": 1.5606274604797363,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 2.0614,
+      "step": 2170
+    },
+    {
+      "epoch": 0.05514079567090891,
+      "grad_norm": 1.4900213479995728,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 2.0565,
+      "step": 2201
+    },
+    {
+      "epoch": 0.05591742659585129,
+      "grad_norm": 1.4454214572906494,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 2.0381,
+      "step": 2232
+    },
+    {
+      "epoch": 0.056694057520793664,
+      "grad_norm": 1.4872742891311646,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 2.0227,
+      "step": 2263
+    },
+    {
+      "epoch": 0.057470688445736044,
+      "grad_norm": 1.4538527727127075,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 2.0395,
+      "step": 2294
+    },
+    {
+      "epoch": 0.058247319370678424,
+      "grad_norm": 1.432769536972046,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 2.0352,
+      "step": 2325
+    },
+    {
+      "epoch": 0.059023950295620804,
+      "grad_norm": 1.4535977840423584,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 2.0341,
+      "step": 2356
+    },
+    {
+      "epoch": 0.059800581220563184,
+      "grad_norm": 1.4004398584365845,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 2.0185,
+      "step": 2387
+    },
+    {
+      "epoch": 0.060577212145505564,
+      "grad_norm": 1.433273434638977,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 2.036,
+      "step": 2418
+    },
+    {
+      "epoch": 0.06135384307044794,
+      "grad_norm": 1.3791290521621704,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 2.0421,
+      "step": 2449
+    },
+    {
+      "epoch": 0.06213047399539032,
+      "grad_norm": 2.008694648742676,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.9948,
+      "step": 2480
+    },
+    {
+      "epoch": 0.0629071049203327,
+      "grad_norm": 1.3773164749145508,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 2.0158,
+      "step": 2511
+    },
+    {
+      "epoch": 0.06368373584527508,
+      "grad_norm": 1.4489777088165283,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 2.0216,
+      "step": 2542
+    },
+    {
+      "epoch": 0.06446036677021745,
+      "grad_norm": 2.1266908645629883,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.9962,
+      "step": 2573
+    },
+    {
+      "epoch": 0.06523699769515984,
+      "grad_norm": 1.3704332113265991,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.9801,
+      "step": 2604
+    },
+    {
+      "epoch": 0.06601362862010221,
+      "grad_norm": 1.3643279075622559,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.9902,
+      "step": 2635
+    },
+    {
+      "epoch": 0.0667902595450446,
+      "grad_norm": 1.3495409488677979,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.993,
+      "step": 2666
+    },
+    {
+      "epoch": 0.06756689046998697,
+      "grad_norm": 1.3918874263763428,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.9782,
+      "step": 2697
+    },
+    {
+      "epoch": 0.06834352139492936,
+      "grad_norm": 1.3205535411834717,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.9638,
+      "step": 2728
+    },
+    {
+      "epoch": 0.06912015231987173,
+      "grad_norm": 1.3123114109039307,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.9826,
+      "step": 2759
+    },
+    {
+      "epoch": 0.0698967832448141,
+      "grad_norm": 1.3138995170593262,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.9938,
+      "step": 2790
+    },
+    {
+      "epoch": 0.07067341416975649,
+      "grad_norm": 1.2964009046554565,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.9924,
+      "step": 2821
+    },
+    {
+      "epoch": 0.07145004509469886,
+      "grad_norm": 1.3010739088058472,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.9592,
+      "step": 2852
+    },
+    {
+      "epoch": 0.07222667601964125,
+      "grad_norm": 1.2549103498458862,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.9394,
+      "step": 2883
+    },
+    {
+      "epoch": 0.07300330694458362,
+      "grad_norm": 1.3198585510253906,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.989,
+      "step": 2914
+    },
+    {
+      "epoch": 0.07377993786952601,
+      "grad_norm": 1.3653398752212524,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.9499,
+      "step": 2945
+    },
+    {
+      "epoch": 0.07455656879446838,
+      "grad_norm": 4.606905937194824,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.9504,
+      "step": 2976
+    },
+    {
+      "epoch": 0.07533319971941076,
+      "grad_norm": 1.2823129892349243,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.9483,
+      "step": 3007
+    },
+    {
+      "epoch": 0.07610983064435314,
+      "grad_norm": 1.2803308963775635,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.9604,
+      "step": 3038
+    },
+    {
+      "epoch": 0.07688646156929552,
+      "grad_norm": 1.2765967845916748,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.941,
+      "step": 3069
+    },
+    {
+      "epoch": 0.0776630924942379,
+      "grad_norm": 2.622286796569824,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.9426,
+      "step": 3100
+    },
+    {
+      "epoch": 0.07843972341918028,
+      "grad_norm": 1.231387972831726,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.9416,
+      "step": 3131
+    },
+    {
+      "epoch": 0.07921635434412266,
+      "grad_norm": 1.2499909400939941,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.9226,
+      "step": 3162
+    },
+    {
+      "epoch": 0.07999298526906504,
+      "grad_norm": 1.296276330947876,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.935,
+      "step": 3193
+    },
+    {
+      "epoch": 0.08076961619400741,
+      "grad_norm": 1.2642258405685425,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.9185,
+      "step": 3224
+    },
+    {
+      "epoch": 0.0815462471189498,
+      "grad_norm": 1.2396386861801147,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.9361,
+      "step": 3255
+    },
+    {
+      "epoch": 0.08232287804389217,
+      "grad_norm": 1.1811271905899048,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.9276,
+      "step": 3286
+    },
+    {
+      "epoch": 0.08309950896883456,
+      "grad_norm": 1.2897577285766602,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.9277,
+      "step": 3317
+    },
+    {
+      "epoch": 0.08387613989377693,
+      "grad_norm": 1.1453903913497925,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.9109,
+      "step": 3348
+    },
+    {
+      "epoch": 0.08465277081871932,
+      "grad_norm": 1.1600992679595947,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.9248,
+      "step": 3379
+    },
+    {
+      "epoch": 0.08542940174366169,
+      "grad_norm": 1.234217882156372,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.9236,
+      "step": 3410
+    },
+    {
+      "epoch": 0.08620603266860406,
+      "grad_norm": 1.1933766603469849,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.9284,
+      "step": 3441
+    },
+    {
+      "epoch": 0.08698266359354645,
+      "grad_norm": 1.2087618112564087,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.8971,
+      "step": 3472
+    },
+    {
+      "epoch": 0.08775929451848882,
+      "grad_norm": 1.227864146232605,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.9353,
+      "step": 3503
+    },
+    {
+      "epoch": 0.08853592544343121,
+      "grad_norm": 1.2828229665756226,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.9085,
+      "step": 3534
+    },
+    {
+      "epoch": 0.08931255636837358,
+      "grad_norm": 1.2086588144302368,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.9044,
+      "step": 3565
+    },
+    {
+      "epoch": 0.09008918729331597,
+      "grad_norm": 1.1942152976989746,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.9182,
+      "step": 3596
+    },
+    {
+      "epoch": 0.09086581821825834,
+      "grad_norm": 1.2399394512176514,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.8943,
+      "step": 3627
+    },
+    {
+      "epoch": 0.09164244914320072,
+      "grad_norm": 1.227376937866211,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.8881,
+      "step": 3658
+    },
+    {
+      "epoch": 0.0924190800681431,
+      "grad_norm": 1.1314102411270142,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.8878,
+      "step": 3689
+    },
+    {
+      "epoch": 0.09319571099308548,
+      "grad_norm": 1.192134141921997,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.8857,
+      "step": 3720
+    },
+    {
+      "epoch": 0.09397234191802786,
+      "grad_norm": 1.1905503273010254,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.8701,
+      "step": 3751
+    },
+    {
+      "epoch": 0.09474897284297024,
+      "grad_norm": 1.2335184812545776,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.8741,
+      "step": 3782
+    },
+    {
+      "epoch": 0.09552560376791262,
+      "grad_norm": 1.1403234004974365,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.8658,
+      "step": 3813
+    },
+    {
+      "epoch": 0.096302234692855,
+      "grad_norm": 1.1734315156936646,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.8724,
+      "step": 3844
+    },
+    {
+      "epoch": 0.09707886561779737,
+      "grad_norm": 1.2637231349945068,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.867,
+      "step": 3875
+    },
+    {
+      "epoch": 0.09785549654273976,
+      "grad_norm": 1.1608805656433105,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.8764,
+      "step": 3906
+    },
+    {
+      "epoch": 0.09863212746768213,
+      "grad_norm": 1.1562029123306274,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.8612,
+      "step": 3937
+    },
+    {
+      "epoch": 0.09940875839262452,
+      "grad_norm": 1.1918668746948242,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.866,
+      "step": 3968
+    },
+    {
+      "epoch": 0.10018538931756689,
+      "grad_norm": 1.180206537246704,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.849,
+      "step": 3999
+    },
+    {
+      "epoch": 0.10096202024250928,
+      "grad_norm": 1.0747199058532715,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.8547,
+      "step": 4030
+    },
+    {
+      "epoch": 0.10173865116745165,
+      "grad_norm": 1.103786826133728,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.864,
+      "step": 4061
+    },
+    {
+      "epoch": 0.10251528209239402,
+      "grad_norm": 1.1390912532806396,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.8669,
+      "step": 4092
+    },
+    {
+      "epoch": 0.10329191301733641,
+      "grad_norm": 1.1488468647003174,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.8445,
+      "step": 4123
+    },
+    {
+      "epoch": 0.10406854394227878,
+      "grad_norm": 1.1589927673339844,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.8529,
+      "step": 4154
+    },
+    {
+      "epoch": 0.10484517486722117,
+      "grad_norm": 1.1793478727340698,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.8818,
+      "step": 4185
+    },
+    {
+      "epoch": 0.10562180579216354,
+      "grad_norm": 1.165292739868164,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.8425,
+      "step": 4216
+    },
+    {
+      "epoch": 0.10639843671710593,
+      "grad_norm": 1.105946660041809,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.8327,
+      "step": 4247
+    },
+    {
+      "epoch": 0.1071750676420483,
+      "grad_norm": 1.1690527200698853,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.8428,
+      "step": 4278
+    },
+    {
+      "epoch": 0.10795169856699068,
+      "grad_norm": 1.1106913089752197,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.839,
+      "step": 4309
+    },
+    {
+      "epoch": 0.10872832949193306,
+      "grad_norm": 1.1590090990066528,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.8658,
+      "step": 4340
+    },
+    {
+      "epoch": 0.10950496041687544,
+      "grad_norm": 1.1315875053405762,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.8282,
+      "step": 4371
+    },
+    {
+      "epoch": 0.11028159134181782,
+      "grad_norm": 1.6055009365081787,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.8294,
+      "step": 4402
+    },
+    {
+      "epoch": 0.1110582222667602,
+      "grad_norm": 1.1236201524734497,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.8325,
+      "step": 4433
+    },
+    {
+      "epoch": 0.11183485319170258,
+      "grad_norm": 1.0830161571502686,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.8451,
+      "step": 4464
+    },
+    {
+      "epoch": 0.11261148411664496,
+      "grad_norm": 1.1663005352020264,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.8349,
+      "step": 4495
+    },
+    {
+      "epoch": 0.11338811504158733,
+      "grad_norm": 1.2522406578063965,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.8162,
+      "step": 4526
+    },
+    {
+      "epoch": 0.11416474596652972,
+      "grad_norm": 1.1271142959594727,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.8348,
+      "step": 4557
+    },
+    {
+      "epoch": 0.11494137689147209,
+      "grad_norm": 1.053753137588501,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.8376,
+      "step": 4588
+    },
+    {
+      "epoch": 0.11571800781641448,
+      "grad_norm": 1.1469056606292725,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.8248,
+      "step": 4619
+    },
+    {
+      "epoch": 0.11649463874135685,
+      "grad_norm": 1.116128921508789,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.8454,
+      "step": 4650
+    },
+    {
+      "epoch": 0.11727126966629922,
+      "grad_norm": 1.0742651224136353,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.8231,
+      "step": 4681
+    },
+    {
+      "epoch": 0.11804790059124161,
+      "grad_norm": 1.101657748222351,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.8421,
+      "step": 4712
+    },
+    {
+      "epoch": 0.11882453151618398,
+      "grad_norm": 1.0891473293304443,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.8053,
+      "step": 4743
+    },
+    {
+      "epoch": 0.11960116244112637,
+      "grad_norm": 1.1044034957885742,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.8184,
+      "step": 4774
+    },
+    {
+      "epoch": 0.12037779336606874,
+      "grad_norm": 1.0644783973693848,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.8237,
+      "step": 4805
+    },
+    {
+      "epoch": 0.12115442429101113,
+      "grad_norm": 1.0427252054214478,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.8189,
+      "step": 4836
+    },
+    {
+      "epoch": 0.1219310552159535,
+      "grad_norm": 1.0806516408920288,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.7958,
+      "step": 4867
+    },
+    {
+      "epoch": 0.12270768614089587,
+      "grad_norm": 1.092581868171692,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.8229,
+      "step": 4898
+    },
+    {
+      "epoch": 0.12348431706583826,
+      "grad_norm": 1.0858657360076904,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.8165,
+      "step": 4929
+    },
+    {
+      "epoch": 0.12426094799078063,
+      "grad_norm": 1.073818325996399,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.8352,
+      "step": 4960
+    },
+    {
+      "epoch": 0.125037578915723,
+      "grad_norm": 1.069009780883789,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.8,
+      "step": 4991
+    },
+    {
+      "epoch": 0.1258142098406654,
+      "grad_norm": 1.0416266918182373,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.8224,
+      "step": 5022
+    },
+    {
+      "epoch": 0.12659084076560778,
+      "grad_norm": 1.093551516532898,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.8005,
+      "step": 5053
+    },
+    {
+      "epoch": 0.12736747169055015,
+      "grad_norm": 1.026353359222412,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.844,
+      "step": 5084
+    },
+    {
+      "epoch": 0.12814410261549253,
+      "grad_norm": 1.102858304977417,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.8045,
+      "step": 5115
+    },
+    {
+      "epoch": 0.1289207335404349,
+      "grad_norm": 1.0537272691726685,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.8054,
+      "step": 5146
+    },
+    {
+      "epoch": 0.1296973644653773,
+      "grad_norm": 1.0389387607574463,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.7734,
+      "step": 5177
+    },
+    {
+      "epoch": 0.13047399539031967,
+      "grad_norm": 1.0274319648742676,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.788,
+      "step": 5208
+    },
+    {
+      "epoch": 0.13125062631526205,
+      "grad_norm": 1.0932128429412842,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.7813,
+      "step": 5239
+    },
+    {
+      "epoch": 0.13202725724020442,
+      "grad_norm": 1.0294640064239502,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.81,
+      "step": 5270
+    },
+    {
+      "epoch": 0.13280388816514682,
+      "grad_norm": 1.0617210865020752,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.8017,
+      "step": 5301
+    },
+    {
+      "epoch": 0.1335805190900892,
+      "grad_norm": 1.0657798051834106,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.7884,
+      "step": 5332
+    },
+    {
+      "epoch": 0.13435715001503157,
+      "grad_norm": 0.9954230189323425,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.7848,
+      "step": 5363
+    },
+    {
+      "epoch": 0.13513378093997394,
+      "grad_norm": 1.117066740989685,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.7984,
+      "step": 5394
+    },
+    {
+      "epoch": 0.13591041186491631,
+      "grad_norm": 1.0706870555877686,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.8008,
+      "step": 5425
+    },
+    {
+      "epoch": 0.13668704278985871,
+      "grad_norm": 1.063238501548767,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.7754,
+      "step": 5456
+    },
+    {
+      "epoch": 0.1374636737148011,
+      "grad_norm": 1.0702152252197266,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.8037,
+      "step": 5487
+    },
+    {
+      "epoch": 0.13824030463974346,
+      "grad_norm": 1.0318788290023804,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.8174,
+      "step": 5518
+    },
+    {
+      "epoch": 0.13901693556468583,
+      "grad_norm": 1.0097755193710327,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.7648,
+      "step": 5549
+    },
+    {
+      "epoch": 0.1397935664896282,
+      "grad_norm": 1.063873291015625,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.809,
+      "step": 5580
+    },
+    {
+      "epoch": 0.1405701974145706,
+      "grad_norm": 1.0409623384475708,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.7853,
+      "step": 5611
+    },
+    {
+      "epoch": 0.14134682833951298,
+      "grad_norm": 1.0131454467773438,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.7759,
+      "step": 5642
+    },
+    {
+      "epoch": 0.14212345926445535,
+      "grad_norm": 1.1056182384490967,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.7959,
+      "step": 5673
+    },
+    {
+      "epoch": 0.14290009018939773,
+      "grad_norm": 1.0572400093078613,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.7597,
+      "step": 5704
+    },
+    {
+      "epoch": 0.14367672111434013,
+      "grad_norm": 1.0375362634658813,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.7719,
+      "step": 5735
+    },
+    {
+      "epoch": 0.1444533520392825,
+      "grad_norm": 1.0238806009292603,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.7966,
+      "step": 5766
+    },
+    {
+      "epoch": 0.14522998296422487,
+      "grad_norm": 1.0335805416107178,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.7805,
+      "step": 5797
+    },
+    {
+      "epoch": 0.14600661388916725,
+      "grad_norm": 1.08907151222229,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.7905,
+      "step": 5828
+    },
+    {
+      "epoch": 0.14678324481410962,
+      "grad_norm": 1.0151680707931519,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.7766,
+      "step": 5859
+    },
+    {
+      "epoch": 0.14755987573905202,
+      "grad_norm": 0.9963664412498474,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.7708,
+      "step": 5890
+    },
+    {
+      "epoch": 0.1483365066639944,
+      "grad_norm": 1.0762684345245361,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.7998,
+      "step": 5921
+    },
+    {
+      "epoch": 0.14911313758893677,
+      "grad_norm": 1.1151126623153687,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.782,
+      "step": 5952
+    },
+    {
+      "epoch": 0.14988976851387914,
+      "grad_norm": 0.9970519542694092,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.7779,
+      "step": 5983
+    },
+    {
+      "epoch": 0.1506663994388215,
+      "grad_norm": 1.0146524906158447,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.7631,
+      "step": 6014
+    },
+    {
+      "epoch": 0.15144303036376391,
+      "grad_norm": 1.0554558038711548,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.7729,
+      "step": 6045
+    },
+    {
+      "epoch": 0.1522196612887063,
+      "grad_norm": 1.0413624048233032,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.79,
+      "step": 6076
+    },
+    {
+      "epoch": 0.15299629221364866,
+      "grad_norm": 1.07778000831604,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.787,
+      "step": 6107
+    },
+    {
+      "epoch": 0.15377292313859103,
+      "grad_norm": 1.0084989070892334,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.7695,
+      "step": 6138
+    },
+    {
+      "epoch": 0.1545495540635334,
+      "grad_norm": 1.0067577362060547,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.7611,
+      "step": 6169
+    },
+    {
+      "epoch": 0.1553261849884758,
+      "grad_norm": 1.0149894952774048,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.7734,
+      "step": 6200
+    },
+    {
+      "epoch": 0.15610281591341818,
+      "grad_norm": 0.996447741985321,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.7609,
+      "step": 6231
+    },
+    {
+      "epoch": 0.15687944683836055,
+      "grad_norm": 1.0334714651107788,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.7725,
+      "step": 6262
+    },
+    {
+      "epoch": 0.15765607776330293,
+      "grad_norm": 0.949685275554657,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.7597,
+      "step": 6293
+    },
+    {
+      "epoch": 0.15843270868824533,
+      "grad_norm": 1.0946801900863647,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.755,
+      "step": 6324
+    },
+    {
+      "epoch": 0.1592093396131877,
+      "grad_norm": 1.0390102863311768,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.7755,
+      "step": 6355
+    },
+    {
+      "epoch": 0.15998597053813007,
+      "grad_norm": 0.974733293056488,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.7619,
+      "step": 6386
+    },
+    {
+      "epoch": 0.16076260146307245,
+      "grad_norm": 1.0192877054214478,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.7676,
+      "step": 6417
+    },
+    {
+      "epoch": 0.16153923238801482,
+      "grad_norm": 1.0147426128387451,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.7473,
+      "step": 6448
+    },
+    {
+      "epoch": 0.16231586331295722,
+      "grad_norm": 1.0231157541275024,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.766,
+      "step": 6479
+    },
+    {
+      "epoch": 0.1630924942378996,
+      "grad_norm": 0.9995896816253662,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.7594,
+      "step": 6510
+    },
+    {
+      "epoch": 0.16386912516284197,
+      "grad_norm": 0.9674972295761108,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.7347,
+      "step": 6541
+    },
+    {
+      "epoch": 0.16464575608778434,
+      "grad_norm": 0.9876355528831482,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.748,
+      "step": 6572
+    },
+    {
+      "epoch": 0.1654223870127267,
+      "grad_norm": 1.0107293128967285,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.7743,
+      "step": 6603
+    },
+    {
+      "epoch": 0.1661990179376691,
+      "grad_norm": 0.9731600284576416,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.7515,
+      "step": 6634
+    },
+    {
+      "epoch": 0.1669756488626115,
+      "grad_norm": 0.9843081831932068,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.7498,
+      "step": 6665
+    },
+    {
+      "epoch": 0.16775227978755386,
+      "grad_norm": 0.9850636720657349,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.7563,
+      "step": 6696
+    },
+    {
+      "epoch": 0.16852891071249623,
+      "grad_norm": 0.964599609375,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.7699,
+      "step": 6727
+    },
+    {
+      "epoch": 0.16930554163743863,
+      "grad_norm": 0.9415149688720703,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.745,
+      "step": 6758
+    },
+    {
+      "epoch": 0.170082172562381,
+      "grad_norm": 0.9608363509178162,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.7519,
+      "step": 6789
+    },
+    {
+      "epoch": 0.17085880348732338,
+      "grad_norm": 0.9133123159408569,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.7432,
+      "step": 6820
+    },
+    {
+      "epoch": 0.17163543441226575,
+      "grad_norm": 0.943702220916748,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.7231,
+      "step": 6851
+    },
+    {
+      "epoch": 0.17241206533720813,
+      "grad_norm": 0.9676947593688965,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.7563,
+      "step": 6882
+    },
+    {
+      "epoch": 0.17318869626215053,
+      "grad_norm": 0.964959442615509,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.7514,
+      "step": 6913
+    },
+    {
+      "epoch": 0.1739653271870929,
+      "grad_norm": 1.0078297853469849,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.7538,
+      "step": 6944
+    },
+    {
+      "epoch": 0.17474195811203527,
+      "grad_norm": 0.9631285071372986,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.7363,
+      "step": 6975
+    },
+    {
+      "epoch": 0.17551858903697765,
+      "grad_norm": 0.9542151093482971,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.753,
+      "step": 7006
+    },
+    {
+      "epoch": 0.17629521996192002,
+      "grad_norm": 0.9770635366439819,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.7435,
+      "step": 7037
+    },
+    {
+      "epoch": 0.17707185088686242,
+      "grad_norm": 0.979009211063385,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.7591,
+      "step": 7068
+    },
+    {
+      "epoch": 0.1778484818118048,
+      "grad_norm": 0.9663967490196228,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.7129,
+      "step": 7099
+    },
+    {
+      "epoch": 0.17862511273674717,
+      "grad_norm": 1.0181857347488403,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.7396,
+      "step": 7130
+    },
+    {
+      "epoch": 0.17940174366168954,
+      "grad_norm": 1.0090553760528564,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.7488,
+      "step": 7161
+    },
+    {
+      "epoch": 0.18017837458663194,
+      "grad_norm": 1.0095964670181274,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.7342,
+      "step": 7192
+    },
+    {
+      "epoch": 0.1809550055115743,
+      "grad_norm": 0.994108259677887,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.7445,
+      "step": 7223
+    },
+    {
+      "epoch": 0.18173163643651669,
+      "grad_norm": 0.9566254019737244,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.7272,
+      "step": 7254
+    },
+    {
+      "epoch": 0.18250826736145906,
+      "grad_norm": 0.9655300974845886,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.7112,
+      "step": 7285
+    },
+    {
+      "epoch": 0.18328489828640143,
+      "grad_norm": 0.9693655371665955,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.74,
+      "step": 7316
+    },
+    {
+      "epoch": 0.18406152921134383,
+      "grad_norm": 0.9668208956718445,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.7239,
+      "step": 7347
+    },
+    {
+      "epoch": 0.1848381601362862,
+      "grad_norm": 1.0193735361099243,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.7273,
+      "step": 7378
+    },
+    {
+      "epoch": 0.18561479106122858,
+      "grad_norm": 0.9525153636932373,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.7356,
+      "step": 7409
+    },
+    {
+      "epoch": 0.18639142198617095,
+      "grad_norm": 0.9590099453926086,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.7296,
+      "step": 7440
+    },
+    {
+      "epoch": 0.18716805291111333,
+      "grad_norm": 0.9519559741020203,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.7183,
+      "step": 7471
+    },
+    {
+      "epoch": 0.18794468383605573,
+      "grad_norm": 0.9692674279212952,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.7329,
+      "step": 7502
+    },
+    {
+      "epoch": 0.1887213147609981,
+      "grad_norm": 0.9676815271377563,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.7194,
+      "step": 7533
+    },
+    {
+      "epoch": 0.18949794568594047,
+      "grad_norm": 0.9612167477607727,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.7297,
+      "step": 7564
+    },
+    {
+      "epoch": 0.19027457661088285,
+      "grad_norm": 0.9661709666252136,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.728,
+      "step": 7595
+    },
+    {
+      "epoch": 0.19105120753582525,
+      "grad_norm": 0.95663982629776,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.7387,
+      "step": 7626
+    },
+    {
+      "epoch": 0.19182783846076762,
+      "grad_norm": 0.9469471573829651,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.7034,
+      "step": 7657
+    },
+    {
+      "epoch": 0.19260446938571,
+      "grad_norm": 1.03744637966156,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.7394,
+      "step": 7688
+    },
+    {
+      "epoch": 0.19338110031065237,
+      "grad_norm": 0.932919979095459,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.7113,
+      "step": 7719
+    },
+    {
+      "epoch": 0.19415773123559474,
+      "grad_norm": 0.9527629017829895,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.7228,
+      "step": 7750
+    },
+    {
+      "epoch": 0.19493436216053714,
+      "grad_norm": 0.9649306535720825,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.7434,
+      "step": 7781
+    },
+    {
+      "epoch": 0.1957109930854795,
+      "grad_norm": 0.9027903079986572,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.7022,
+      "step": 7812
+    },
+    {
+      "epoch": 0.19648762401042189,
+      "grad_norm": 0.9486429691314697,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.7277,
+      "step": 7843
+    },
+    {
+      "epoch": 0.19726425493536426,
+      "grad_norm": 0.9951580762863159,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.7354,
+      "step": 7874
+    },
+    {
+      "epoch": 0.19804088586030663,
+      "grad_norm": 0.984990656375885,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.7247,
+      "step": 7905
+    },
+    {
+      "epoch": 0.19881751678524903,
+      "grad_norm": 1.0146019458770752,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.7048,
+      "step": 7936
+    },
+    {
+      "epoch": 0.1995941477101914,
+      "grad_norm": 0.9386274814605713,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.7035,
+      "step": 7967
+    },
+    {
+      "epoch": 0.20037077863513378,
+      "grad_norm": 0.9656661152839661,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.7138,
+      "step": 7998
+    },
+    {
+      "epoch": 0.20114740956007615,
+      "grad_norm": 0.9721409678459167,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.7174,
+      "step": 8029
+    },
+    {
+      "epoch": 0.20192404048501855,
+      "grad_norm": 0.9685981869697571,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.7162,
+      "step": 8060
+    },
+    {
+      "epoch": 0.20270067140996093,
+      "grad_norm": 0.9472204446792603,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.7068,
+      "step": 8091
+    },
+    {
+      "epoch": 0.2034773023349033,
+      "grad_norm": 0.9472411870956421,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.7244,
+      "step": 8122
+    },
+    {
+      "epoch": 0.20425393325984567,
+      "grad_norm": 0.9380378723144531,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.7169,
+      "step": 8153
+    },
+    {
+      "epoch": 0.20503056418478804,
+      "grad_norm": 0.9613087177276611,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.7108,
+      "step": 8184
+    },
+    {
+      "epoch": 0.20580719510973045,
+      "grad_norm": 0.9507735967636108,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.7147,
+      "step": 8215
+    },
+    {
+      "epoch": 0.20658382603467282,
+      "grad_norm": 0.9669816493988037,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.7058,
+      "step": 8246
+    },
+    {
+      "epoch": 0.2073604569596152,
+      "grad_norm": 0.8880124688148499,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.7049,
+      "step": 8277
+    },
+    {
+      "epoch": 0.20813708788455756,
+      "grad_norm": 4.802671909332275,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.7349,
+      "step": 8308
+    },
+    {
+      "epoch": 0.20891371880949994,
+      "grad_norm": 0.9394221901893616,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.6932,
+      "step": 8339
+    },
+    {
+      "epoch": 0.20969034973444234,
+      "grad_norm": 0.9521833062171936,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.695,
+      "step": 8370
+    },
+    {
+      "epoch": 0.2104669806593847,
+      "grad_norm": 0.9627339839935303,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.7329,
+      "step": 8401
+    },
+    {
+      "epoch": 0.21124361158432708,
+      "grad_norm": 0.9096025228500366,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.6885,
+      "step": 8432
+    },
+    {
+      "epoch": 0.21202024250926946,
+      "grad_norm": 0.9301928877830505,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.7112,
+      "step": 8463
+    },
+    {
+      "epoch": 0.21279687343421186,
+      "grad_norm": 1.0362213850021362,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.7061,
+      "step": 8494
+    },
+    {
+      "epoch": 0.21357350435915423,
+      "grad_norm": 1.986802339553833,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.7095,
+      "step": 8525
+    },
+    {
+      "epoch": 0.2143501352840966,
+      "grad_norm": 0.9070325493812561,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.7087,
+      "step": 8556
+    },
+    {
+      "epoch": 0.21512676620903898,
+      "grad_norm": 0.985433042049408,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.7176,
+      "step": 8587
+    },
+    {
+      "epoch": 0.21590339713398135,
+      "grad_norm": 0.9339021444320679,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.6823,
+      "step": 8618
+    },
+    {
+      "epoch": 0.21668002805892375,
+      "grad_norm": 0.9413474798202515,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.7205,
+      "step": 8649
+    },
+    {
+      "epoch": 0.21745665898386612,
+      "grad_norm": 1.023187279701233,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.6943,
+      "step": 8680
+    },
+    {
+      "epoch": 0.2182332899088085,
+      "grad_norm": 0.9431496262550354,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.7012,
+      "step": 8711
+    },
+    {
+      "epoch": 0.21900992083375087,
+      "grad_norm": 0.9386807680130005,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.7069,
+      "step": 8742
+    },
+    {
+      "epoch": 0.21978655175869324,
+      "grad_norm": 0.9307882785797119,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.6914,
+      "step": 8773
+    },
+    {
+      "epoch": 0.22056318268363564,
+      "grad_norm": 1.0440980195999146,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.6892,
+      "step": 8804
+    },
+    {
+      "epoch": 0.22133981360857802,
+      "grad_norm": 0.9271411895751953,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.7117,
+      "step": 8835
+    },
+    {
+      "epoch": 0.2221164445335204,
+      "grad_norm": 0.9182149767875671,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.7092,
+      "step": 8866
+    },
+    {
+      "epoch": 0.22289307545846276,
+      "grad_norm": 0.9707378149032593,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.7055,
+      "step": 8897
+    },
+    {
+      "epoch": 0.22366970638340516,
+      "grad_norm": 0.9413692951202393,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.6968,
+      "step": 8928
+    },
+    {
+      "epoch": 0.22444633730834754,
+      "grad_norm": 1.1943906545639038,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.7174,
+      "step": 8959
+    },
+    {
+      "epoch": 0.2252229682332899,
+      "grad_norm": 0.9508203268051147,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.6941,
+      "step": 8990
+    },
+    {
+      "epoch": 0.22599959915823228,
+      "grad_norm": 0.9774237275123596,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.6996,
+      "step": 9021
+    },
+    {
+      "epoch": 0.22677623008317466,
+      "grad_norm": 0.9906953573226929,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.7186,
+      "step": 9052
+    },
+    {
+      "epoch": 0.22755286100811706,
+      "grad_norm": 0.966076135635376,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.6828,
+      "step": 9083
+    },
+    {
+      "epoch": 0.22832949193305943,
+      "grad_norm": 0.9266401529312134,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.6969,
+      "step": 9114
+    },
+    {
+      "epoch": 0.2291061228580018,
+      "grad_norm": 0.8797683119773865,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.6835,
+      "step": 9145
+    },
+    {
+      "epoch": 0.22988275378294418,
+      "grad_norm": 0.92194664478302,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.7028,
+      "step": 9176
+    },
+    {
+      "epoch": 0.23065938470788655,
+      "grad_norm": 0.9278755187988281,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.6853,
+      "step": 9207
+    },
+    {
+      "epoch": 0.23143601563282895,
+      "grad_norm": 0.9345482587814331,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.6879,
+      "step": 9238
+    },
+    {
+      "epoch": 0.23221264655777132,
+      "grad_norm": 0.9217596054077148,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.679,
+      "step": 9269
+    },
+    {
+      "epoch": 0.2329892774827137,
+      "grad_norm": 0.9330849647521973,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.6891,
+      "step": 9300
+    },
+    {
+      "epoch": 0.23376590840765607,
+      "grad_norm": 0.923973023891449,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.6929,
+      "step": 9331
+    },
+    {
+      "epoch": 0.23454253933259844,
+      "grad_norm": 0.9245807528495789,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.7162,
+      "step": 9362
+    },
+    {
+      "epoch": 0.23531917025754084,
+      "grad_norm": 0.9212767481803894,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.7169,
+      "step": 9393
+    },
+    {
+      "epoch": 0.23609580118248322,
+      "grad_norm": 0.9439975023269653,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.6869,
+      "step": 9424
+    },
+    {
+      "epoch": 0.2368724321074256,
+      "grad_norm": 0.9876207709312439,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.6989,
+      "step": 9455
+    },
+    {
+      "epoch": 0.23764906303236796,
+      "grad_norm": 0.8833792805671692,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.6917,
+      "step": 9486
+    },
+    {
+      "epoch": 0.23842569395731036,
+      "grad_norm": 0.9133450388908386,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.7038,
+      "step": 9517
+    },
+    {
+      "epoch": 0.23920232488225274,
+      "grad_norm": 0.8729329705238342,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.672,
+      "step": 9548
+    },
+    {
+      "epoch": 0.2399789558071951,
+      "grad_norm": 0.892375111579895,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.6829,
+      "step": 9579
+    },
+    {
+      "epoch": 0.24075558673213748,
+      "grad_norm": 0.8939517140388489,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.6965,
+      "step": 9610
+    },
+    {
+      "epoch": 0.24153221765707986,
+      "grad_norm": 0.8656035661697388,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.7063,
+      "step": 9641
+    },
+    {
+      "epoch": 0.24230884858202226,
+      "grad_norm": 0.8904181122779846,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.6719,
+      "step": 9672
+    },
+    {
+      "epoch": 0.24308547950696463,
+      "grad_norm": 0.9176281690597534,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.6648,
+      "step": 9703
+    },
+    {
+      "epoch": 0.243862110431907,
+      "grad_norm": 0.9038643836975098,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.6756,
+      "step": 9734
+    },
+    {
+      "epoch": 0.24463874135684938,
+      "grad_norm": 0.9255871772766113,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.6752,
+      "step": 9765
+    },
+    {
+      "epoch": 0.24541537228179175,
+      "grad_norm": 0.9124768972396851,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.6982,
+      "step": 9796
+    },
+    {
+      "epoch": 0.24619200320673415,
+      "grad_norm": 0.9149096608161926,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.6692,
+      "step": 9827
+    },
+    {
+      "epoch": 0.24696863413167652,
+      "grad_norm": 0.9468510150909424,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.6775,
+      "step": 9858
+    },
+    {
+      "epoch": 0.2477452650566189,
+      "grad_norm": 1.2210197448730469,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.692,
+      "step": 9889
+    },
+    {
+      "epoch": 0.24852189598156127,
+      "grad_norm": 0.9717695116996765,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.6583,
+      "step": 9920
+    },
+    {
+      "epoch": 0.24929852690650367,
+      "grad_norm": 0.9524528980255127,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.6606,
+      "step": 9951
+    },
+    {
+      "epoch": 0.250075157831446,
+      "grad_norm": 0.937414824962616,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.7063,
+      "step": 9982
+    },
+    {
+      "epoch": 0.2508517887563884,
+      "grad_norm": 0.9392083883285522,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.6813,
+      "step": 10013
+    },
+    {
+      "epoch": 0.2516284196813308,
+      "grad_norm": 0.9055363535881042,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.6622,
+      "step": 10044
+    },
+    {
+      "epoch": 0.25240505060627316,
+      "grad_norm": 0.8967134356498718,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.7052,
+      "step": 10075
+    },
+    {
+      "epoch": 0.25318168153121556,
+      "grad_norm": 0.9304991364479065,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.6779,
+      "step": 10106
+    },
+    {
+      "epoch": 0.2539583124561579,
+      "grad_norm": 0.9946010708808899,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.6727,
+      "step": 10137
+    },
+    {
+      "epoch": 0.2547349433811003,
+      "grad_norm": 0.936072051525116,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.6861,
+      "step": 10168
+    },
+    {
+      "epoch": 0.2555115743060427,
+      "grad_norm": 0.9157513380050659,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.6871,
+      "step": 10199
+    },
+    {
+      "epoch": 0.25628820523098506,
+      "grad_norm": 0.8980918526649475,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.674,
+      "step": 10230
+    },
+    {
+      "epoch": 0.25706483615592746,
+      "grad_norm": 0.9256001114845276,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.6858,
+      "step": 10261
+    },
+    {
+      "epoch": 0.2578414670808698,
+      "grad_norm": 0.8827298879623413,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.6734,
+      "step": 10292
+    },
+    {
+      "epoch": 0.2586180980058122,
+      "grad_norm": 0.9297879338264465,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.6648,
+      "step": 10323
+    },
+    {
+      "epoch": 0.2593947289307546,
+      "grad_norm": 0.91744065284729,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.6713,
+      "step": 10354
+    },
+    {
+      "epoch": 0.26017135985569695,
+      "grad_norm": 0.949213445186615,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.6633,
+      "step": 10385
+    },
+    {
+      "epoch": 0.26094799078063935,
+      "grad_norm": 0.9231769442558289,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.6815,
+      "step": 10416
+    },
+    {
+      "epoch": 0.2617246217055817,
+      "grad_norm": 0.9055944681167603,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.6621,
+      "step": 10447
+    },
+    {
+      "epoch": 0.2625012526305241,
+      "grad_norm": 1.7065776586532593,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.6832,
+      "step": 10478
+    },
+    {
+      "epoch": 0.2632778835554665,
+      "grad_norm": 0.9098711013793945,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.7106,
+      "step": 10509
+    },
+    {
+      "epoch": 0.26405451448040884,
+      "grad_norm": 0.9403277635574341,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.708,
+      "step": 10540
+    },
+    {
+      "epoch": 0.26483114540535124,
+      "grad_norm": 0.9076827168464661,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.6571,
+      "step": 10571
+    },
+    {
+      "epoch": 0.26560777633029364,
+      "grad_norm": 0.9140092730522156,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.6626,
+      "step": 10602
+    },
+    {
+      "epoch": 0.266384407255236,
+      "grad_norm": 0.9277907013893127,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.6625,
+      "step": 10633
+    },
+    {
+      "epoch": 0.2671610381801784,
+      "grad_norm": 0.9199085831642151,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.663,
+      "step": 10664
+    },
+    {
+      "epoch": 0.26793766910512073,
+      "grad_norm": 0.9358407855033875,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.6743,
+      "step": 10695
+    },
+    {
+      "epoch": 0.26871430003006314,
+      "grad_norm": 0.8855702877044678,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.6619,
+      "step": 10726
+    },
+    {
+      "epoch": 0.26949093095500554,
+      "grad_norm": 0.9157874584197998,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.6772,
+      "step": 10757
+    },
+    {
+      "epoch": 0.2702675618799479,
+      "grad_norm": 0.9023963809013367,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.6559,
+      "step": 10788
+    },
+    {
+      "epoch": 0.2710441928048903,
+      "grad_norm": 0.9174203872680664,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.6393,
+      "step": 10819
+    },
+    {
+      "epoch": 0.27182082372983263,
+      "grad_norm": 0.9019688963890076,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.6763,
+      "step": 10850
+    },
+    {
+      "epoch": 0.27259745465477503,
+      "grad_norm": 0.8955567479133606,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.6679,
+      "step": 10881
+    },
+    {
+      "epoch": 0.27337408557971743,
+      "grad_norm": 0.9326659440994263,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.6765,
+      "step": 10912
+    },
+    {
+      "epoch": 0.2741507165046598,
+      "grad_norm": 0.8885530233383179,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.674,
+      "step": 10943
+    },
+    {
+      "epoch": 0.2749273474296022,
+      "grad_norm": 0.909267783164978,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.6602,
+      "step": 10974
+    },
+    {
+      "epoch": 0.2757039783545445,
+      "grad_norm": 0.9005350470542908,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.6628,
+      "step": 11005
+    },
+    {
+      "epoch": 0.2764806092794869,
+      "grad_norm": 0.919683575630188,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.6647,
+      "step": 11036
+    },
+    {
+      "epoch": 0.2772572402044293,
+      "grad_norm": 0.8954905867576599,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.6763,
+      "step": 11067
+    },
+    {
+      "epoch": 0.27803387112937167,
+      "grad_norm": 0.9120632410049438,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.6552,
+      "step": 11098
+    },
+    {
+      "epoch": 0.27881050205431407,
+      "grad_norm": 0.9041403532028198,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.6604,
+      "step": 11129
+    },
+    {
+      "epoch": 0.2795871329792564,
+      "grad_norm": 0.9149596095085144,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.6666,
+      "step": 11160
+    },
+    {
+      "epoch": 0.2803637639041988,
+      "grad_norm": 0.9379541277885437,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.654,
+      "step": 11191
+    },
+    {
+      "epoch": 0.2811403948291412,
+      "grad_norm": 0.8942285180091858,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.6558,
+      "step": 11222
+    },
+    {
+      "epoch": 0.28191702575408356,
+      "grad_norm": 0.9407718181610107,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.6574,
+      "step": 11253
+    },
+    {
+      "epoch": 0.28269365667902596,
+      "grad_norm": 0.9167685508728027,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.6767,
+      "step": 11284
+    },
+    {
+      "epoch": 0.2834702876039683,
+      "grad_norm": 0.8957439661026001,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.6846,
+      "step": 11315
+    },
+    {
+      "epoch": 0.2842469185289107,
+      "grad_norm": 0.9044497609138489,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.6323,
+      "step": 11346
+    },
+    {
+      "epoch": 0.2850235494538531,
+      "grad_norm": 0.9024799466133118,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.682,
+      "step": 11377
+    },
+    {
+      "epoch": 0.28580018037879545,
+      "grad_norm": 0.9126555323600769,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.6802,
+      "step": 11408
+    },
+    {
+      "epoch": 0.28657681130373786,
+      "grad_norm": 0.924310564994812,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.6568,
+      "step": 11439
+    },
+    {
+      "epoch": 0.28735344222868026,
+      "grad_norm": 0.8566572666168213,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.6682,
+      "step": 11470
+    },
+    {
+      "epoch": 0.2881300731536226,
+      "grad_norm": 0.8287222981452942,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.6484,
+      "step": 11501
+    },
+    {
+      "epoch": 0.288906704078565,
+      "grad_norm": 1.0163201093673706,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.635,
+      "step": 11532
+    },
+    {
+      "epoch": 0.28968333500350735,
+      "grad_norm": 0.8813551068305969,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.6654,
+      "step": 11563
+    },
+    {
+      "epoch": 0.29045996592844975,
+      "grad_norm": 0.8688541650772095,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.6787,
+      "step": 11594
+    },
+    {
+      "epoch": 0.29123659685339215,
+      "grad_norm": 0.8820333480834961,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.6418,
+      "step": 11625
+    },
+    {
+      "epoch": 0.2920132277783345,
+      "grad_norm": 0.9284527897834778,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.6727,
+      "step": 11656
+    },
+    {
+      "epoch": 0.2927898587032769,
+      "grad_norm": 0.8665077090263367,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.6377,
+      "step": 11687
+    },
+    {
+      "epoch": 0.29356648962821924,
+      "grad_norm": 0.9927760362625122,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.6628,
+      "step": 11718
+    },
+    {
+      "epoch": 0.29434312055316164,
+      "grad_norm": 0.9006340503692627,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.6589,
+      "step": 11749
+    },
+    {
+      "epoch": 0.29511975147810404,
+      "grad_norm": 0.9278168082237244,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.6519,
+      "step": 11780
+    },
+    {
+      "epoch": 0.2958963824030464,
+      "grad_norm": 0.9146036505699158,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.6541,
+      "step": 11811
+    },
+    {
+      "epoch": 0.2966730133279888,
+      "grad_norm": 0.8698804378509521,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.6722,
+      "step": 11842
+    },
+    {
+      "epoch": 0.29744964425293113,
+      "grad_norm": 0.9304215312004089,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.6392,
+      "step": 11873
+    },
+    {
+      "epoch": 0.29822627517787353,
+      "grad_norm": 0.8917405605316162,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.6373,
+      "step": 11904
+    },
+    {
+      "epoch": 0.29900290610281594,
+      "grad_norm": 0.9075546860694885,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.6401,
+      "step": 11935
+    },
+    {
+      "epoch": 0.2997795370277583,
+      "grad_norm": 0.9235963225364685,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.667,
+      "step": 11966
+    },
+    {
+      "epoch": 0.3005561679527007,
+      "grad_norm": 0.9514668583869934,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.6654,
+      "step": 11997
+    },
+    {
+      "epoch": 0.301332798877643,
+      "grad_norm": 0.8843172192573547,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.6609,
+      "step": 12028
+    },
+    {
+      "epoch": 0.3021094298025854,
+      "grad_norm": 0.9325070977210999,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.6392,
+      "step": 12059
+    },
+    {
+      "epoch": 0.30288606072752783,
+      "grad_norm": 0.8855581879615784,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.6607,
+      "step": 12090
+    },
+    {
+      "epoch": 0.3036626916524702,
+      "grad_norm": 0.9044367671012878,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.6417,
+      "step": 12121
+    },
+    {
+      "epoch": 0.3044393225774126,
+      "grad_norm": 0.9446975588798523,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.6279,
+      "step": 12152
+    },
+    {
+      "epoch": 0.3052159535023549,
+      "grad_norm": 0.8764945864677429,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.6297,
+      "step": 12183
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.526741678122336e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:648c03a879cd4197b7658fa4d1110b979eef2c447adce1165e90fb225ceb553d
+size 5304

checkpoint-15260/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-my-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-15260/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-15260/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9af6b83c7265c8934a0a13c749b8791a1be5ce417a617441cba8db175ffb312
+size 4842817304

checkpoint-15260/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-15260/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304

checkpoint-15260/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-15260/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-15260/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5df2048e8ed46f28ebf3874f11f569260b04f9653f6b34dc6a7a542e8104f9
+size 3662865184

checkpoint-15260/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a9fbb8917d68d2246e2eda8d0e6823a38ce1dbbdba4b902fd5db3d1d8b4921
+size 2317729920

checkpoint-15260/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30737946624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-15260/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e822a1992f54e6e4c3c598b3e1be486625c4fc1ac6d57e4d70389a5180755d32
+size 16728842070

checkpoint-15260/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-15260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce335347efaebf038b8915bc0a8d2d587a4a1aa08ad0e015b4bc7cc4fba634e
+size 1064

checkpoint-15260/trainer_state.json

@@ -0,0 +1,3477 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.38230283595550657,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000776630924942379,
+      "grad_norm": 23.55321502685547,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 8.3443,
+      "step": 31
+    },
+    {
+      "epoch": 0.001553261849884758,
+      "grad_norm": 14.414477348327637,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.198,
+      "step": 62
+    },
+    {
+      "epoch": 0.002329892774827137,
+      "grad_norm": 10.739773750305176,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 5.8639,
+      "step": 93
+    },
+    {
+      "epoch": 0.003106523699769516,
+      "grad_norm": 5.378795623779297,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 4.8222,
+      "step": 124
+    },
+    {
+      "epoch": 0.003883154624711895,
+      "grad_norm": 8.51831340789795,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.1983,
+      "step": 155
+    },
+    {
+      "epoch": 0.004659785549654274,
+      "grad_norm": 6.32632303237915,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 3.8598,
+      "step": 186
+    },
+    {
+      "epoch": 0.005436416474596653,
+      "grad_norm": 5.590794563293457,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 3.6646,
+      "step": 217
+    },
+    {
+      "epoch": 0.006213047399539032,
+      "grad_norm": 5.9275383949279785,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.5212,
+      "step": 248
+    },
+    {
+      "epoch": 0.006989678324481411,
+      "grad_norm": 5.041291236877441,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.3936,
+      "step": 279
+    },
+    {
+      "epoch": 0.00776630924942379,
+      "grad_norm": 4.923459529876709,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.2713,
+      "step": 310
+    },
+    {
+      "epoch": 0.00854294017436617,
+      "grad_norm": 8.011459350585938,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.2,
+      "step": 341
+    },
+    {
+      "epoch": 0.009319571099308548,
+      "grad_norm": 5.261505603790283,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.1255,
+      "step": 372
+    },
+    {
+      "epoch": 0.010096202024250926,
+      "grad_norm": 5.004406452178955,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 3.0726,
+      "step": 403
+    },
+    {
+      "epoch": 0.010872832949193306,
+      "grad_norm": 4.326263427734375,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 2.9682,
+      "step": 434
+    },
+    {
+      "epoch": 0.011649463874135685,
+      "grad_norm": 4.251937389373779,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 2.9215,
+      "step": 465
+    },
+    {
+      "epoch": 0.012426094799078065,
+      "grad_norm": 4.35053825378418,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 2.8902,
+      "step": 496
+    },
+    {
+      "epoch": 0.013202725724020443,
+      "grad_norm": 4.316098690032959,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 2.8521,
+      "step": 527
+    },
+    {
+      "epoch": 0.013979356648962823,
+      "grad_norm": 5.536881446838379,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 2.8058,
+      "step": 558
+    },
+    {
+      "epoch": 0.014755987573905201,
+      "grad_norm": 3.759843111038208,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 2.7438,
+      "step": 589
+    },
+    {
+      "epoch": 0.01553261849884758,
+      "grad_norm": 4.057703018188477,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 2.7508,
+      "step": 620
+    },
+    {
+      "epoch": 0.01630924942378996,
+      "grad_norm": 3.427708625793457,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 2.7046,
+      "step": 651
+    },
+    {
+      "epoch": 0.01708588034873234,
+      "grad_norm": 3.9012484550476074,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 2.6706,
+      "step": 682
+    },
+    {
+      "epoch": 0.017862511273674716,
+      "grad_norm": 3.388504981994629,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 2.6377,
+      "step": 713
+    },
+    {
+      "epoch": 0.018639142198617096,
+      "grad_norm": 3.2011327743530273,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.6214,
+      "step": 744
+    },
+    {
+      "epoch": 0.019415773123559476,
+      "grad_norm": 3.5897209644317627,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.6045,
+      "step": 775
+    },
+    {
+      "epoch": 0.020192404048501852,
+      "grad_norm": 3.386697769165039,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.6066,
+      "step": 806
+    },
+    {
+      "epoch": 0.020969034973444232,
+      "grad_norm": 2.9135866165161133,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.5697,
+      "step": 837
+    },
+    {
+      "epoch": 0.021745665898386612,
+      "grad_norm": 9.212065696716309,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.5773,
+      "step": 868
+    },
+    {
+      "epoch": 0.022522296823328992,
+      "grad_norm": 3.0339765548706055,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.5453,
+      "step": 899
+    },
+    {
+      "epoch": 0.02329892774827137,
+      "grad_norm": 2.8007607460021973,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.5297,
+      "step": 930
+    },
+    {
+      "epoch": 0.02407555867321375,
+      "grad_norm": 3.251768112182617,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.5273,
+      "step": 961
+    },
+    {
+      "epoch": 0.02485218959815613,
+      "grad_norm": 3.357011079788208,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.4896,
+      "step": 992
+    },
+    {
+      "epoch": 0.025628820523098506,
+      "grad_norm": 2.6069107055664062,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.4718,
+      "step": 1023
+    },
+    {
+      "epoch": 0.026405451448040886,
+      "grad_norm": 4.663620948791504,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.4338,
+      "step": 1054
+    },
+    {
+      "epoch": 0.027182082372983266,
+      "grad_norm": 3.819638252258301,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.4848,
+      "step": 1085
+    },
+    {
+      "epoch": 0.027958713297925646,
+      "grad_norm": 2.6367456912994385,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.4415,
+      "step": 1116
+    },
+    {
+      "epoch": 0.028735344222868022,
+      "grad_norm": 2.6118173599243164,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.4341,
+      "step": 1147
+    },
+    {
+      "epoch": 0.029511975147810402,
+      "grad_norm": 9.820366859436035,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.3773,
+      "step": 1178
+    },
+    {
+      "epoch": 0.030288606072752782,
+      "grad_norm": 38.890506744384766,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.3966,
+      "step": 1209
+    },
+    {
+      "epoch": 0.03106523699769516,
+      "grad_norm": 2.5037872791290283,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.3421,
+      "step": 1240
+    },
+    {
+      "epoch": 0.03184186792263754,
+      "grad_norm": 2.426544189453125,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.3568,
+      "step": 1271
+    },
+    {
+      "epoch": 0.03261849884757992,
+      "grad_norm": 2.5375614166259766,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.3314,
+      "step": 1302
+    },
+    {
+      "epoch": 0.0333951297725223,
+      "grad_norm": 3.555330276489258,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.3262,
+      "step": 1333
+    },
+    {
+      "epoch": 0.03417176069746468,
+      "grad_norm": 2.2571263313293457,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.3167,
+      "step": 1364
+    },
+    {
+      "epoch": 0.03494839162240705,
+      "grad_norm": 2.184305429458618,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.2936,
+      "step": 1395
+    },
+    {
+      "epoch": 0.03572502254734943,
+      "grad_norm": 2.8295061588287354,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.3033,
+      "step": 1426
+    },
+    {
+      "epoch": 0.03650165347229181,
+      "grad_norm": 2.0241498947143555,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.2833,
+      "step": 1457
+    },
+    {
+      "epoch": 0.03727828439723419,
+      "grad_norm": 2.0029919147491455,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.2663,
+      "step": 1488
+    },
+    {
+      "epoch": 0.03805491532217657,
+      "grad_norm": 2.033773899078369,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.2597,
+      "step": 1519
+    },
+    {
+      "epoch": 0.03883154624711895,
+      "grad_norm": 2.047210216522217,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 2.2231,
+      "step": 1550
+    },
+    {
+      "epoch": 0.03960817717206133,
+      "grad_norm": 2.032099485397339,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.2411,
+      "step": 1581
+    },
+    {
+      "epoch": 0.040384808097003705,
+      "grad_norm": 1.8384301662445068,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.2409,
+      "step": 1612
+    },
+    {
+      "epoch": 0.041161439021946085,
+      "grad_norm": 1.721187710762024,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.193,
+      "step": 1643
+    },
+    {
+      "epoch": 0.041938069946888465,
+      "grad_norm": 1.8869743347167969,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.1917,
+      "step": 1674
+    },
+    {
+      "epoch": 0.042714700871830845,
+      "grad_norm": 1.796583652496338,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.1794,
+      "step": 1705
+    },
+    {
+      "epoch": 0.043491331796773225,
+      "grad_norm": 1.6308804750442505,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.1854,
+      "step": 1736
+    },
+    {
+      "epoch": 0.044267962721715605,
+      "grad_norm": 1.683474063873291,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 2.1797,
+      "step": 1767
+    },
+    {
+      "epoch": 0.045044593646657985,
+      "grad_norm": 1.7442835569381714,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 2.1695,
+      "step": 1798
+    },
+    {
+      "epoch": 0.04582122457160036,
+      "grad_norm": 1.704970359802246,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 2.1365,
+      "step": 1829
+    },
+    {
+      "epoch": 0.04659785549654274,
+      "grad_norm": 1.7213023900985718,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 2.1524,
+      "step": 1860
+    },
+    {
+      "epoch": 0.04737448642148512,
+      "grad_norm": 4.01851224899292,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 2.1171,
+      "step": 1891
+    },
+    {
+      "epoch": 0.0481511173464275,
+      "grad_norm": 1.5619858503341675,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 2.1608,
+      "step": 1922
+    },
+    {
+      "epoch": 0.04892774827136988,
+      "grad_norm": 1.684493064880371,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 2.1278,
+      "step": 1953
+    },
+    {
+      "epoch": 0.04970437919631226,
+      "grad_norm": 1.660992980003357,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 2.1136,
+      "step": 1984
+    },
+    {
+      "epoch": 0.05048101012125464,
+      "grad_norm": 1.5491065979003906,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 2.1086,
+      "step": 2015
+    },
+    {
+      "epoch": 0.05125764104619701,
+      "grad_norm": 1.5400840044021606,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 2.1069,
+      "step": 2046
+    },
+    {
+      "epoch": 0.05203427197113939,
+      "grad_norm": 1.5687416791915894,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 2.0888,
+      "step": 2077
+    },
+    {
+      "epoch": 0.05281090289608177,
+      "grad_norm": 1.5218935012817383,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 2.1032,
+      "step": 2108
+    },
+    {
+      "epoch": 0.05358753382102415,
+      "grad_norm": 1.763666033744812,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 2.0799,
+      "step": 2139
+    },
+    {
+      "epoch": 0.05436416474596653,
+      "grad_norm": 1.5606274604797363,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 2.0614,
+      "step": 2170
+    },
+    {
+      "epoch": 0.05514079567090891,
+      "grad_norm": 1.4900213479995728,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 2.0565,
+      "step": 2201
+    },
+    {
+      "epoch": 0.05591742659585129,
+      "grad_norm": 1.4454214572906494,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 2.0381,
+      "step": 2232
+    },
+    {
+      "epoch": 0.056694057520793664,
+      "grad_norm": 1.4872742891311646,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 2.0227,
+      "step": 2263
+    },
+    {
+      "epoch": 0.057470688445736044,
+      "grad_norm": 1.4538527727127075,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 2.0395,
+      "step": 2294
+    },
+    {
+      "epoch": 0.058247319370678424,
+      "grad_norm": 1.432769536972046,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 2.0352,
+      "step": 2325
+    },
+    {
+      "epoch": 0.059023950295620804,
+      "grad_norm": 1.4535977840423584,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 2.0341,
+      "step": 2356
+    },
+    {
+      "epoch": 0.059800581220563184,
+      "grad_norm": 1.4004398584365845,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 2.0185,
+      "step": 2387
+    },
+    {
+      "epoch": 0.060577212145505564,
+      "grad_norm": 1.433273434638977,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 2.036,
+      "step": 2418
+    },
+    {
+      "epoch": 0.06135384307044794,
+      "grad_norm": 1.3791290521621704,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 2.0421,
+      "step": 2449
+    },
+    {
+      "epoch": 0.06213047399539032,
+      "grad_norm": 2.008694648742676,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.9948,
+      "step": 2480
+    },
+    {
+      "epoch": 0.0629071049203327,
+      "grad_norm": 1.3773164749145508,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 2.0158,
+      "step": 2511
+    },
+    {
+      "epoch": 0.06368373584527508,
+      "grad_norm": 1.4489777088165283,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 2.0216,
+      "step": 2542
+    },
+    {
+      "epoch": 0.06446036677021745,
+      "grad_norm": 2.1266908645629883,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.9962,
+      "step": 2573
+    },
+    {
+      "epoch": 0.06523699769515984,
+      "grad_norm": 1.3704332113265991,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.9801,
+      "step": 2604
+    },
+    {
+      "epoch": 0.06601362862010221,
+      "grad_norm": 1.3643279075622559,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.9902,
+      "step": 2635
+    },
+    {
+      "epoch": 0.0667902595450446,
+      "grad_norm": 1.3495409488677979,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.993,
+      "step": 2666
+    },
+    {
+      "epoch": 0.06756689046998697,
+      "grad_norm": 1.3918874263763428,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.9782,
+      "step": 2697
+    },
+    {
+      "epoch": 0.06834352139492936,
+      "grad_norm": 1.3205535411834717,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.9638,
+      "step": 2728
+    },
+    {
+      "epoch": 0.06912015231987173,
+      "grad_norm": 1.3123114109039307,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.9826,
+      "step": 2759
+    },
+    {
+      "epoch": 0.0698967832448141,
+      "grad_norm": 1.3138995170593262,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.9938,
+      "step": 2790
+    },
+    {
+      "epoch": 0.07067341416975649,
+      "grad_norm": 1.2964009046554565,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.9924,
+      "step": 2821
+    },
+    {
+      "epoch": 0.07145004509469886,
+      "grad_norm": 1.3010739088058472,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.9592,
+      "step": 2852
+    },
+    {
+      "epoch": 0.07222667601964125,
+      "grad_norm": 1.2549103498458862,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.9394,
+      "step": 2883
+    },
+    {
+      "epoch": 0.07300330694458362,
+      "grad_norm": 1.3198585510253906,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.989,
+      "step": 2914
+    },
+    {
+      "epoch": 0.07377993786952601,
+      "grad_norm": 1.3653398752212524,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.9499,
+      "step": 2945
+    },
+    {
+      "epoch": 0.07455656879446838,
+      "grad_norm": 4.606905937194824,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.9504,
+      "step": 2976
+    },
+    {
+      "epoch": 0.07533319971941076,
+      "grad_norm": 1.2823129892349243,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.9483,
+      "step": 3007
+    },
+    {
+      "epoch": 0.07610983064435314,
+      "grad_norm": 1.2803308963775635,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.9604,
+      "step": 3038
+    },
+    {
+      "epoch": 0.07688646156929552,
+      "grad_norm": 1.2765967845916748,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.941,
+      "step": 3069
+    },
+    {
+      "epoch": 0.0776630924942379,
+      "grad_norm": 2.622286796569824,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.9426,
+      "step": 3100
+    },
+    {
+      "epoch": 0.07843972341918028,
+      "grad_norm": 1.231387972831726,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.9416,
+      "step": 3131
+    },
+    {
+      "epoch": 0.07921635434412266,
+      "grad_norm": 1.2499909400939941,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.9226,
+      "step": 3162
+    },
+    {
+      "epoch": 0.07999298526906504,
+      "grad_norm": 1.296276330947876,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.935,
+      "step": 3193
+    },
+    {
+      "epoch": 0.08076961619400741,
+      "grad_norm": 1.2642258405685425,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.9185,
+      "step": 3224
+    },
+    {
+      "epoch": 0.0815462471189498,
+      "grad_norm": 1.2396386861801147,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.9361,
+      "step": 3255
+    },
+    {
+      "epoch": 0.08232287804389217,
+      "grad_norm": 1.1811271905899048,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.9276,
+      "step": 3286
+    },
+    {
+      "epoch": 0.08309950896883456,
+      "grad_norm": 1.2897577285766602,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.9277,
+      "step": 3317
+    },
+    {
+      "epoch": 0.08387613989377693,
+      "grad_norm": 1.1453903913497925,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.9109,
+      "step": 3348
+    },
+    {
+      "epoch": 0.08465277081871932,
+      "grad_norm": 1.1600992679595947,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.9248,
+      "step": 3379
+    },
+    {
+      "epoch": 0.08542940174366169,
+      "grad_norm": 1.234217882156372,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.9236,
+      "step": 3410
+    },
+    {
+      "epoch": 0.08620603266860406,
+      "grad_norm": 1.1933766603469849,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.9284,
+      "step": 3441
+    },
+    {
+      "epoch": 0.08698266359354645,
+      "grad_norm": 1.2087618112564087,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.8971,
+      "step": 3472
+    },
+    {
+      "epoch": 0.08775929451848882,
+      "grad_norm": 1.227864146232605,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.9353,
+      "step": 3503
+    },
+    {
+      "epoch": 0.08853592544343121,
+      "grad_norm": 1.2828229665756226,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.9085,
+      "step": 3534
+    },
+    {
+      "epoch": 0.08931255636837358,
+      "grad_norm": 1.2086588144302368,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.9044,
+      "step": 3565
+    },
+    {
+      "epoch": 0.09008918729331597,
+      "grad_norm": 1.1942152976989746,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.9182,
+      "step": 3596
+    },
+    {
+      "epoch": 0.09086581821825834,
+      "grad_norm": 1.2399394512176514,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.8943,
+      "step": 3627
+    },
+    {
+      "epoch": 0.09164244914320072,
+      "grad_norm": 1.227376937866211,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.8881,
+      "step": 3658
+    },
+    {
+      "epoch": 0.0924190800681431,
+      "grad_norm": 1.1314102411270142,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.8878,
+      "step": 3689
+    },
+    {
+      "epoch": 0.09319571099308548,
+      "grad_norm": 1.192134141921997,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.8857,
+      "step": 3720
+    },
+    {
+      "epoch": 0.09397234191802786,
+      "grad_norm": 1.1905503273010254,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.8701,
+      "step": 3751
+    },
+    {
+      "epoch": 0.09474897284297024,
+      "grad_norm": 1.2335184812545776,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.8741,
+      "step": 3782
+    },
+    {
+      "epoch": 0.09552560376791262,
+      "grad_norm": 1.1403234004974365,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.8658,
+      "step": 3813
+    },
+    {
+      "epoch": 0.096302234692855,
+      "grad_norm": 1.1734315156936646,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.8724,
+      "step": 3844
+    },
+    {
+      "epoch": 0.09707886561779737,
+      "grad_norm": 1.2637231349945068,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.867,
+      "step": 3875
+    },
+    {
+      "epoch": 0.09785549654273976,
+      "grad_norm": 1.1608805656433105,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.8764,
+      "step": 3906
+    },
+    {
+      "epoch": 0.09863212746768213,
+      "grad_norm": 1.1562029123306274,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.8612,
+      "step": 3937
+    },
+    {
+      "epoch": 0.09940875839262452,
+      "grad_norm": 1.1918668746948242,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.866,
+      "step": 3968
+    },
+    {
+      "epoch": 0.10018538931756689,
+      "grad_norm": 1.180206537246704,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.849,
+      "step": 3999
+    },
+    {
+      "epoch": 0.10096202024250928,
+      "grad_norm": 1.0747199058532715,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.8547,
+      "step": 4030
+    },
+    {
+      "epoch": 0.10173865116745165,
+      "grad_norm": 1.103786826133728,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.864,
+      "step": 4061
+    },
+    {
+      "epoch": 0.10251528209239402,
+      "grad_norm": 1.1390912532806396,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.8669,
+      "step": 4092
+    },
+    {
+      "epoch": 0.10329191301733641,
+      "grad_norm": 1.1488468647003174,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.8445,
+      "step": 4123
+    },
+    {
+      "epoch": 0.10406854394227878,
+      "grad_norm": 1.1589927673339844,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.8529,
+      "step": 4154
+    },
+    {
+      "epoch": 0.10484517486722117,
+      "grad_norm": 1.1793478727340698,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.8818,
+      "step": 4185
+    },
+    {
+      "epoch": 0.10562180579216354,
+      "grad_norm": 1.165292739868164,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.8425,
+      "step": 4216
+    },
+    {
+      "epoch": 0.10639843671710593,
+      "grad_norm": 1.105946660041809,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.8327,
+      "step": 4247
+    },
+    {
+      "epoch": 0.1071750676420483,
+      "grad_norm": 1.1690527200698853,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.8428,
+      "step": 4278
+    },
+    {
+      "epoch": 0.10795169856699068,
+      "grad_norm": 1.1106913089752197,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.839,
+      "step": 4309
+    },
+    {
+      "epoch": 0.10872832949193306,
+      "grad_norm": 1.1590090990066528,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.8658,
+      "step": 4340
+    },
+    {
+      "epoch": 0.10950496041687544,
+      "grad_norm": 1.1315875053405762,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.8282,
+      "step": 4371
+    },
+    {
+      "epoch": 0.11028159134181782,
+      "grad_norm": 1.6055009365081787,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.8294,
+      "step": 4402
+    },
+    {
+      "epoch": 0.1110582222667602,
+      "grad_norm": 1.1236201524734497,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.8325,
+      "step": 4433
+    },
+    {
+      "epoch": 0.11183485319170258,
+      "grad_norm": 1.0830161571502686,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.8451,
+      "step": 4464
+    },
+    {
+      "epoch": 0.11261148411664496,
+      "grad_norm": 1.1663005352020264,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.8349,
+      "step": 4495
+    },
+    {
+      "epoch": 0.11338811504158733,
+      "grad_norm": 1.2522406578063965,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.8162,
+      "step": 4526
+    },
+    {
+      "epoch": 0.11416474596652972,
+      "grad_norm": 1.1271142959594727,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.8348,
+      "step": 4557
+    },
+    {
+      "epoch": 0.11494137689147209,
+      "grad_norm": 1.053753137588501,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.8376,
+      "step": 4588
+    },
+    {
+      "epoch": 0.11571800781641448,
+      "grad_norm": 1.1469056606292725,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.8248,
+      "step": 4619
+    },
+    {
+      "epoch": 0.11649463874135685,
+      "grad_norm": 1.116128921508789,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.8454,
+      "step": 4650
+    },
+    {
+      "epoch": 0.11727126966629922,
+      "grad_norm": 1.0742651224136353,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.8231,
+      "step": 4681
+    },
+    {
+      "epoch": 0.11804790059124161,
+      "grad_norm": 1.101657748222351,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.8421,
+      "step": 4712
+    },
+    {
+      "epoch": 0.11882453151618398,
+      "grad_norm": 1.0891473293304443,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.8053,
+      "step": 4743
+    },
+    {
+      "epoch": 0.11960116244112637,
+      "grad_norm": 1.1044034957885742,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.8184,
+      "step": 4774
+    },
+    {
+      "epoch": 0.12037779336606874,
+      "grad_norm": 1.0644783973693848,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.8237,
+      "step": 4805
+    },
+    {
+      "epoch": 0.12115442429101113,
+      "grad_norm": 1.0427252054214478,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.8189,
+      "step": 4836
+    },
+    {
+      "epoch": 0.1219310552159535,
+      "grad_norm": 1.0806516408920288,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.7958,
+      "step": 4867
+    },
+    {
+      "epoch": 0.12270768614089587,
+      "grad_norm": 1.092581868171692,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.8229,
+      "step": 4898
+    },
+    {
+      "epoch": 0.12348431706583826,
+      "grad_norm": 1.0858657360076904,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.8165,
+      "step": 4929
+    },
+    {
+      "epoch": 0.12426094799078063,
+      "grad_norm": 1.073818325996399,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.8352,
+      "step": 4960
+    },
+    {
+      "epoch": 0.125037578915723,
+      "grad_norm": 1.069009780883789,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.8,
+      "step": 4991
+    },
+    {
+      "epoch": 0.1258142098406654,
+      "grad_norm": 1.0416266918182373,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.8224,
+      "step": 5022
+    },
+    {
+      "epoch": 0.12659084076560778,
+      "grad_norm": 1.093551516532898,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.8005,
+      "step": 5053
+    },
+    {
+      "epoch": 0.12736747169055015,
+      "grad_norm": 1.026353359222412,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.844,
+      "step": 5084
+    },
+    {
+      "epoch": 0.12814410261549253,
+      "grad_norm": 1.102858304977417,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.8045,
+      "step": 5115
+    },
+    {
+      "epoch": 0.1289207335404349,
+      "grad_norm": 1.0537272691726685,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.8054,
+      "step": 5146
+    },
+    {
+      "epoch": 0.1296973644653773,
+      "grad_norm": 1.0389387607574463,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.7734,
+      "step": 5177
+    },
+    {
+      "epoch": 0.13047399539031967,
+      "grad_norm": 1.0274319648742676,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.788,
+      "step": 5208
+    },
+    {
+      "epoch": 0.13125062631526205,
+      "grad_norm": 1.0932128429412842,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.7813,
+      "step": 5239
+    },
+    {
+      "epoch": 0.13202725724020442,
+      "grad_norm": 1.0294640064239502,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.81,
+      "step": 5270
+    },
+    {
+      "epoch": 0.13280388816514682,
+      "grad_norm": 1.0617210865020752,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.8017,
+      "step": 5301
+    },
+    {
+      "epoch": 0.1335805190900892,
+      "grad_norm": 1.0657798051834106,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.7884,
+      "step": 5332
+    },
+    {
+      "epoch": 0.13435715001503157,
+      "grad_norm": 0.9954230189323425,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.7848,
+      "step": 5363
+    },
+    {
+      "epoch": 0.13513378093997394,
+      "grad_norm": 1.117066740989685,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.7984,
+      "step": 5394
+    },
+    {
+      "epoch": 0.13591041186491631,
+      "grad_norm": 1.0706870555877686,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.8008,
+      "step": 5425
+    },
+    {
+      "epoch": 0.13668704278985871,
+      "grad_norm": 1.063238501548767,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.7754,
+      "step": 5456
+    },
+    {
+      "epoch": 0.1374636737148011,
+      "grad_norm": 1.0702152252197266,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.8037,
+      "step": 5487
+    },
+    {
+      "epoch": 0.13824030463974346,
+      "grad_norm": 1.0318788290023804,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.8174,
+      "step": 5518
+    },
+    {
+      "epoch": 0.13901693556468583,
+      "grad_norm": 1.0097755193710327,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.7648,
+      "step": 5549
+    },
+    {
+      "epoch": 0.1397935664896282,
+      "grad_norm": 1.063873291015625,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.809,
+      "step": 5580
+    },
+    {
+      "epoch": 0.1405701974145706,
+      "grad_norm": 1.0409623384475708,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.7853,
+      "step": 5611
+    },
+    {
+      "epoch": 0.14134682833951298,
+      "grad_norm": 1.0131454467773438,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.7759,
+      "step": 5642
+    },
+    {
+      "epoch": 0.14212345926445535,
+      "grad_norm": 1.1056182384490967,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.7959,
+      "step": 5673
+    },
+    {
+      "epoch": 0.14290009018939773,
+      "grad_norm": 1.0572400093078613,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.7597,
+      "step": 5704
+    },
+    {
+      "epoch": 0.14367672111434013,
+      "grad_norm": 1.0375362634658813,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.7719,
+      "step": 5735
+    },
+    {
+      "epoch": 0.1444533520392825,
+      "grad_norm": 1.0238806009292603,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.7966,
+      "step": 5766
+    },
+    {
+      "epoch": 0.14522998296422487,
+      "grad_norm": 1.0335805416107178,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.7805,
+      "step": 5797
+    },
+    {
+      "epoch": 0.14600661388916725,
+      "grad_norm": 1.08907151222229,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.7905,
+      "step": 5828
+    },
+    {
+      "epoch": 0.14678324481410962,
+      "grad_norm": 1.0151680707931519,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.7766,
+      "step": 5859
+    },
+    {
+      "epoch": 0.14755987573905202,
+      "grad_norm": 0.9963664412498474,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.7708,
+      "step": 5890
+    },
+    {
+      "epoch": 0.1483365066639944,
+      "grad_norm": 1.0762684345245361,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.7998,
+      "step": 5921
+    },
+    {
+      "epoch": 0.14911313758893677,
+      "grad_norm": 1.1151126623153687,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.782,
+      "step": 5952
+    },
+    {
+      "epoch": 0.14988976851387914,
+      "grad_norm": 0.9970519542694092,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.7779,
+      "step": 5983
+    },
+    {
+      "epoch": 0.1506663994388215,
+      "grad_norm": 1.0146524906158447,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.7631,
+      "step": 6014
+    },
+    {
+      "epoch": 0.15144303036376391,
+      "grad_norm": 1.0554558038711548,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.7729,
+      "step": 6045
+    },
+    {
+      "epoch": 0.1522196612887063,
+      "grad_norm": 1.0413624048233032,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.79,
+      "step": 6076
+    },
+    {
+      "epoch": 0.15299629221364866,
+      "grad_norm": 1.07778000831604,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.787,
+      "step": 6107
+    },
+    {
+      "epoch": 0.15377292313859103,
+      "grad_norm": 1.0084989070892334,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.7695,
+      "step": 6138
+    },
+    {
+      "epoch": 0.1545495540635334,
+      "grad_norm": 1.0067577362060547,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.7611,
+      "step": 6169
+    },
+    {
+      "epoch": 0.1553261849884758,
+      "grad_norm": 1.0149894952774048,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.7734,
+      "step": 6200
+    },
+    {
+      "epoch": 0.15610281591341818,
+      "grad_norm": 0.996447741985321,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.7609,
+      "step": 6231
+    },
+    {
+      "epoch": 0.15687944683836055,
+      "grad_norm": 1.0334714651107788,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.7725,
+      "step": 6262
+    },
+    {
+      "epoch": 0.15765607776330293,
+      "grad_norm": 0.949685275554657,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.7597,
+      "step": 6293
+    },
+    {
+      "epoch": 0.15843270868824533,
+      "grad_norm": 1.0946801900863647,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.755,
+      "step": 6324
+    },
+    {
+      "epoch": 0.1592093396131877,
+      "grad_norm": 1.0390102863311768,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.7755,
+      "step": 6355
+    },
+    {
+      "epoch": 0.15998597053813007,
+      "grad_norm": 0.974733293056488,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.7619,
+      "step": 6386
+    },
+    {
+      "epoch": 0.16076260146307245,
+      "grad_norm": 1.0192877054214478,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.7676,
+      "step": 6417
+    },
+    {
+      "epoch": 0.16153923238801482,
+      "grad_norm": 1.0147426128387451,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.7473,
+      "step": 6448
+    },
+    {
+      "epoch": 0.16231586331295722,
+      "grad_norm": 1.0231157541275024,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.766,
+      "step": 6479
+    },
+    {
+      "epoch": 0.1630924942378996,
+      "grad_norm": 0.9995896816253662,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.7594,
+      "step": 6510
+    },
+    {
+      "epoch": 0.16386912516284197,
+      "grad_norm": 0.9674972295761108,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.7347,
+      "step": 6541
+    },
+    {
+      "epoch": 0.16464575608778434,
+      "grad_norm": 0.9876355528831482,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.748,
+      "step": 6572
+    },
+    {
+      "epoch": 0.1654223870127267,
+      "grad_norm": 1.0107293128967285,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.7743,
+      "step": 6603
+    },
+    {
+      "epoch": 0.1661990179376691,
+      "grad_norm": 0.9731600284576416,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.7515,
+      "step": 6634
+    },
+    {
+      "epoch": 0.1669756488626115,
+      "grad_norm": 0.9843081831932068,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.7498,
+      "step": 6665
+    },
+    {
+      "epoch": 0.16775227978755386,
+      "grad_norm": 0.9850636720657349,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.7563,
+      "step": 6696
+    },
+    {
+      "epoch": 0.16852891071249623,
+      "grad_norm": 0.964599609375,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.7699,
+      "step": 6727
+    },
+    {
+      "epoch": 0.16930554163743863,
+      "grad_norm": 0.9415149688720703,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.745,
+      "step": 6758
+    },
+    {
+      "epoch": 0.170082172562381,
+      "grad_norm": 0.9608363509178162,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.7519,
+      "step": 6789
+    },
+    {
+      "epoch": 0.17085880348732338,
+      "grad_norm": 0.9133123159408569,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.7432,
+      "step": 6820
+    },
+    {
+      "epoch": 0.17163543441226575,
+      "grad_norm": 0.943702220916748,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.7231,
+      "step": 6851
+    },
+    {
+      "epoch": 0.17241206533720813,
+      "grad_norm": 0.9676947593688965,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.7563,
+      "step": 6882
+    },
+    {
+      "epoch": 0.17318869626215053,
+      "grad_norm": 0.964959442615509,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.7514,
+      "step": 6913
+    },
+    {
+      "epoch": 0.1739653271870929,
+      "grad_norm": 1.0078297853469849,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.7538,
+      "step": 6944
+    },
+    {
+      "epoch": 0.17474195811203527,
+      "grad_norm": 0.9631285071372986,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.7363,
+      "step": 6975
+    },
+    {
+      "epoch": 0.17551858903697765,
+      "grad_norm": 0.9542151093482971,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.753,
+      "step": 7006
+    },
+    {
+      "epoch": 0.17629521996192002,
+      "grad_norm": 0.9770635366439819,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.7435,
+      "step": 7037
+    },
+    {
+      "epoch": 0.17707185088686242,
+      "grad_norm": 0.979009211063385,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.7591,
+      "step": 7068
+    },
+    {
+      "epoch": 0.1778484818118048,
+      "grad_norm": 0.9663967490196228,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.7129,
+      "step": 7099
+    },
+    {
+      "epoch": 0.17862511273674717,
+      "grad_norm": 1.0181857347488403,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.7396,
+      "step": 7130
+    },
+    {
+      "epoch": 0.17940174366168954,
+      "grad_norm": 1.0090553760528564,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.7488,
+      "step": 7161
+    },
+    {
+      "epoch": 0.18017837458663194,
+      "grad_norm": 1.0095964670181274,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.7342,
+      "step": 7192
+    },
+    {
+      "epoch": 0.1809550055115743,
+      "grad_norm": 0.994108259677887,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.7445,
+      "step": 7223
+    },
+    {
+      "epoch": 0.18173163643651669,
+      "grad_norm": 0.9566254019737244,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.7272,
+      "step": 7254
+    },
+    {
+      "epoch": 0.18250826736145906,
+      "grad_norm": 0.9655300974845886,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.7112,
+      "step": 7285
+    },
+    {
+      "epoch": 0.18328489828640143,
+      "grad_norm": 0.9693655371665955,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.74,
+      "step": 7316
+    },
+    {
+      "epoch": 0.18406152921134383,
+      "grad_norm": 0.9668208956718445,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.7239,
+      "step": 7347
+    },
+    {
+      "epoch": 0.1848381601362862,
+      "grad_norm": 1.0193735361099243,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.7273,
+      "step": 7378
+    },
+    {
+      "epoch": 0.18561479106122858,
+      "grad_norm": 0.9525153636932373,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.7356,
+      "step": 7409
+    },
+    {
+      "epoch": 0.18639142198617095,
+      "grad_norm": 0.9590099453926086,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.7296,
+      "step": 7440
+    },
+    {
+      "epoch": 0.18716805291111333,
+      "grad_norm": 0.9519559741020203,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.7183,
+      "step": 7471
+    },
+    {
+      "epoch": 0.18794468383605573,
+      "grad_norm": 0.9692674279212952,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.7329,
+      "step": 7502
+    },
+    {
+      "epoch": 0.1887213147609981,
+      "grad_norm": 0.9676815271377563,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.7194,
+      "step": 7533
+    },
+    {
+      "epoch": 0.18949794568594047,
+      "grad_norm": 0.9612167477607727,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.7297,
+      "step": 7564
+    },
+    {
+      "epoch": 0.19027457661088285,
+      "grad_norm": 0.9661709666252136,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.728,
+      "step": 7595
+    },
+    {
+      "epoch": 0.19105120753582525,
+      "grad_norm": 0.95663982629776,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.7387,
+      "step": 7626
+    },
+    {
+      "epoch": 0.19182783846076762,
+      "grad_norm": 0.9469471573829651,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.7034,
+      "step": 7657
+    },
+    {
+      "epoch": 0.19260446938571,
+      "grad_norm": 1.03744637966156,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.7394,
+      "step": 7688
+    },
+    {
+      "epoch": 0.19338110031065237,
+      "grad_norm": 0.932919979095459,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.7113,
+      "step": 7719
+    },
+    {
+      "epoch": 0.19415773123559474,
+      "grad_norm": 0.9527629017829895,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.7228,
+      "step": 7750
+    },
+    {
+      "epoch": 0.19493436216053714,
+      "grad_norm": 0.9649306535720825,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.7434,
+      "step": 7781
+    },
+    {
+      "epoch": 0.1957109930854795,
+      "grad_norm": 0.9027903079986572,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.7022,
+      "step": 7812
+    },
+    {
+      "epoch": 0.19648762401042189,
+      "grad_norm": 0.9486429691314697,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.7277,
+      "step": 7843
+    },
+    {
+      "epoch": 0.19726425493536426,
+      "grad_norm": 0.9951580762863159,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.7354,
+      "step": 7874
+    },
+    {
+      "epoch": 0.19804088586030663,
+      "grad_norm": 0.984990656375885,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.7247,
+      "step": 7905
+    },
+    {
+      "epoch": 0.19881751678524903,
+      "grad_norm": 1.0146019458770752,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.7048,
+      "step": 7936
+    },
+    {
+      "epoch": 0.1995941477101914,
+      "grad_norm": 0.9386274814605713,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.7035,
+      "step": 7967
+    },
+    {
+      "epoch": 0.20037077863513378,
+      "grad_norm": 0.9656661152839661,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.7138,
+      "step": 7998
+    },
+    {
+      "epoch": 0.20114740956007615,
+      "grad_norm": 0.9721409678459167,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.7174,
+      "step": 8029
+    },
+    {
+      "epoch": 0.20192404048501855,
+      "grad_norm": 0.9685981869697571,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.7162,
+      "step": 8060
+    },
+    {
+      "epoch": 0.20270067140996093,
+      "grad_norm": 0.9472204446792603,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.7068,
+      "step": 8091
+    },
+    {
+      "epoch": 0.2034773023349033,
+      "grad_norm": 0.9472411870956421,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.7244,
+      "step": 8122
+    },
+    {
+      "epoch": 0.20425393325984567,
+      "grad_norm": 0.9380378723144531,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.7169,
+      "step": 8153
+    },
+    {
+      "epoch": 0.20503056418478804,
+      "grad_norm": 0.9613087177276611,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.7108,
+      "step": 8184
+    },
+    {
+      "epoch": 0.20580719510973045,
+      "grad_norm": 0.9507735967636108,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.7147,
+      "step": 8215
+    },
+    {
+      "epoch": 0.20658382603467282,
+      "grad_norm": 0.9669816493988037,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.7058,
+      "step": 8246
+    },
+    {
+      "epoch": 0.2073604569596152,
+      "grad_norm": 0.8880124688148499,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.7049,
+      "step": 8277
+    },
+    {
+      "epoch": 0.20813708788455756,
+      "grad_norm": 4.802671909332275,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.7349,
+      "step": 8308
+    },
+    {
+      "epoch": 0.20891371880949994,
+      "grad_norm": 0.9394221901893616,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.6932,
+      "step": 8339
+    },
+    {
+      "epoch": 0.20969034973444234,
+      "grad_norm": 0.9521833062171936,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.695,
+      "step": 8370
+    },
+    {
+      "epoch": 0.2104669806593847,
+      "grad_norm": 0.9627339839935303,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.7329,
+      "step": 8401
+    },
+    {
+      "epoch": 0.21124361158432708,
+      "grad_norm": 0.9096025228500366,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.6885,
+      "step": 8432
+    },
+    {
+      "epoch": 0.21202024250926946,
+      "grad_norm": 0.9301928877830505,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.7112,
+      "step": 8463
+    },
+    {
+      "epoch": 0.21279687343421186,
+      "grad_norm": 1.0362213850021362,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.7061,
+      "step": 8494
+    },
+    {
+      "epoch": 0.21357350435915423,
+      "grad_norm": 1.986802339553833,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.7095,
+      "step": 8525
+    },
+    {
+      "epoch": 0.2143501352840966,
+      "grad_norm": 0.9070325493812561,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.7087,
+      "step": 8556
+    },
+    {
+      "epoch": 0.21512676620903898,
+      "grad_norm": 0.985433042049408,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.7176,
+      "step": 8587
+    },
+    {
+      "epoch": 0.21590339713398135,
+      "grad_norm": 0.9339021444320679,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.6823,
+      "step": 8618
+    },
+    {
+      "epoch": 0.21668002805892375,
+      "grad_norm": 0.9413474798202515,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.7205,
+      "step": 8649
+    },
+    {
+      "epoch": 0.21745665898386612,
+      "grad_norm": 1.023187279701233,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.6943,
+      "step": 8680
+    },
+    {
+      "epoch": 0.2182332899088085,
+      "grad_norm": 0.9431496262550354,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.7012,
+      "step": 8711
+    },
+    {
+      "epoch": 0.21900992083375087,
+      "grad_norm": 0.9386807680130005,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.7069,
+      "step": 8742
+    },
+    {
+      "epoch": 0.21978655175869324,
+      "grad_norm": 0.9307882785797119,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.6914,
+      "step": 8773
+    },
+    {
+      "epoch": 0.22056318268363564,
+      "grad_norm": 1.0440980195999146,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.6892,
+      "step": 8804
+    },
+    {
+      "epoch": 0.22133981360857802,
+      "grad_norm": 0.9271411895751953,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.7117,
+      "step": 8835
+    },
+    {
+      "epoch": 0.2221164445335204,
+      "grad_norm": 0.9182149767875671,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.7092,
+      "step": 8866
+    },
+    {
+      "epoch": 0.22289307545846276,
+      "grad_norm": 0.9707378149032593,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.7055,
+      "step": 8897
+    },
+    {
+      "epoch": 0.22366970638340516,
+      "grad_norm": 0.9413692951202393,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.6968,
+      "step": 8928
+    },
+    {
+      "epoch": 0.22444633730834754,
+      "grad_norm": 1.1943906545639038,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.7174,
+      "step": 8959
+    },
+    {
+      "epoch": 0.2252229682332899,
+      "grad_norm": 0.9508203268051147,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.6941,
+      "step": 8990
+    },
+    {
+      "epoch": 0.22599959915823228,
+      "grad_norm": 0.9774237275123596,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.6996,
+      "step": 9021
+    },
+    {
+      "epoch": 0.22677623008317466,
+      "grad_norm": 0.9906953573226929,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.7186,
+      "step": 9052
+    },
+    {
+      "epoch": 0.22755286100811706,
+      "grad_norm": 0.966076135635376,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.6828,
+      "step": 9083
+    },
+    {
+      "epoch": 0.22832949193305943,
+      "grad_norm": 0.9266401529312134,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.6969,
+      "step": 9114
+    },
+    {
+      "epoch": 0.2291061228580018,
+      "grad_norm": 0.8797683119773865,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.6835,
+      "step": 9145
+    },
+    {
+      "epoch": 0.22988275378294418,
+      "grad_norm": 0.92194664478302,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.7028,
+      "step": 9176
+    },
+    {
+      "epoch": 0.23065938470788655,
+      "grad_norm": 0.9278755187988281,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.6853,
+      "step": 9207
+    },
+    {
+      "epoch": 0.23143601563282895,
+      "grad_norm": 0.9345482587814331,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.6879,
+      "step": 9238
+    },
+    {
+      "epoch": 0.23221264655777132,
+      "grad_norm": 0.9217596054077148,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.679,
+      "step": 9269
+    },
+    {
+      "epoch": 0.2329892774827137,
+      "grad_norm": 0.9330849647521973,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.6891,
+      "step": 9300
+    },
+    {
+      "epoch": 0.23376590840765607,
+      "grad_norm": 0.923973023891449,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.6929,
+      "step": 9331
+    },
+    {
+      "epoch": 0.23454253933259844,
+      "grad_norm": 0.9245807528495789,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.7162,
+      "step": 9362
+    },
+    {
+      "epoch": 0.23531917025754084,
+      "grad_norm": 0.9212767481803894,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.7169,
+      "step": 9393
+    },
+    {
+      "epoch": 0.23609580118248322,
+      "grad_norm": 0.9439975023269653,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.6869,
+      "step": 9424
+    },
+    {
+      "epoch": 0.2368724321074256,
+      "grad_norm": 0.9876207709312439,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.6989,
+      "step": 9455
+    },
+    {
+      "epoch": 0.23764906303236796,
+      "grad_norm": 0.8833792805671692,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.6917,
+      "step": 9486
+    },
+    {
+      "epoch": 0.23842569395731036,
+      "grad_norm": 0.9133450388908386,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.7038,
+      "step": 9517
+    },
+    {
+      "epoch": 0.23920232488225274,
+      "grad_norm": 0.8729329705238342,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.672,
+      "step": 9548
+    },
+    {
+      "epoch": 0.2399789558071951,
+      "grad_norm": 0.892375111579895,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.6829,
+      "step": 9579
+    },
+    {
+      "epoch": 0.24075558673213748,
+      "grad_norm": 0.8939517140388489,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.6965,
+      "step": 9610
+    },
+    {
+      "epoch": 0.24153221765707986,
+      "grad_norm": 0.8656035661697388,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.7063,
+      "step": 9641
+    },
+    {
+      "epoch": 0.24230884858202226,
+      "grad_norm": 0.8904181122779846,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.6719,
+      "step": 9672
+    },
+    {
+      "epoch": 0.24308547950696463,
+      "grad_norm": 0.9176281690597534,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.6648,
+      "step": 9703
+    },
+    {
+      "epoch": 0.243862110431907,
+      "grad_norm": 0.9038643836975098,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.6756,
+      "step": 9734
+    },
+    {
+      "epoch": 0.24463874135684938,
+      "grad_norm": 0.9255871772766113,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.6752,
+      "step": 9765
+    },
+    {
+      "epoch": 0.24541537228179175,
+      "grad_norm": 0.9124768972396851,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.6982,
+      "step": 9796
+    },
+    {
+      "epoch": 0.24619200320673415,
+      "grad_norm": 0.9149096608161926,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.6692,
+      "step": 9827
+    },
+    {
+      "epoch": 0.24696863413167652,
+      "grad_norm": 0.9468510150909424,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.6775,
+      "step": 9858
+    },
+    {
+      "epoch": 0.2477452650566189,
+      "grad_norm": 1.2210197448730469,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.692,
+      "step": 9889
+    },
+    {
+      "epoch": 0.24852189598156127,
+      "grad_norm": 0.9717695116996765,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.6583,
+      "step": 9920
+    },
+    {
+      "epoch": 0.24929852690650367,
+      "grad_norm": 0.9524528980255127,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.6606,
+      "step": 9951
+    },
+    {
+      "epoch": 0.250075157831446,
+      "grad_norm": 0.937414824962616,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.7063,
+      "step": 9982
+    },
+    {
+      "epoch": 0.2508517887563884,
+      "grad_norm": 0.9392083883285522,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.6813,
+      "step": 10013
+    },
+    {
+      "epoch": 0.2516284196813308,
+      "grad_norm": 0.9055363535881042,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.6622,
+      "step": 10044
+    },
+    {
+      "epoch": 0.25240505060627316,
+      "grad_norm": 0.8967134356498718,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.7052,
+      "step": 10075
+    },
+    {
+      "epoch": 0.25318168153121556,
+      "grad_norm": 0.9304991364479065,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.6779,
+      "step": 10106
+    },
+    {
+      "epoch": 0.2539583124561579,
+      "grad_norm": 0.9946010708808899,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.6727,
+      "step": 10137
+    },
+    {
+      "epoch": 0.2547349433811003,
+      "grad_norm": 0.936072051525116,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.6861,
+      "step": 10168
+    },
+    {
+      "epoch": 0.2555115743060427,
+      "grad_norm": 0.9157513380050659,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.6871,
+      "step": 10199
+    },
+    {
+      "epoch": 0.25628820523098506,
+      "grad_norm": 0.8980918526649475,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.674,
+      "step": 10230
+    },
+    {
+      "epoch": 0.25706483615592746,
+      "grad_norm": 0.9256001114845276,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.6858,
+      "step": 10261
+    },
+    {
+      "epoch": 0.2578414670808698,
+      "grad_norm": 0.8827298879623413,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.6734,
+      "step": 10292
+    },
+    {
+      "epoch": 0.2586180980058122,
+      "grad_norm": 0.9297879338264465,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.6648,
+      "step": 10323
+    },
+    {
+      "epoch": 0.2593947289307546,
+      "grad_norm": 0.91744065284729,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.6713,
+      "step": 10354
+    },
+    {
+      "epoch": 0.26017135985569695,
+      "grad_norm": 0.949213445186615,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.6633,
+      "step": 10385
+    },
+    {
+      "epoch": 0.26094799078063935,
+      "grad_norm": 0.9231769442558289,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.6815,
+      "step": 10416
+    },
+    {
+      "epoch": 0.2617246217055817,
+      "grad_norm": 0.9055944681167603,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.6621,
+      "step": 10447
+    },
+    {
+      "epoch": 0.2625012526305241,
+      "grad_norm": 1.7065776586532593,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.6832,
+      "step": 10478
+    },
+    {
+      "epoch": 0.2632778835554665,
+      "grad_norm": 0.9098711013793945,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.7106,
+      "step": 10509
+    },
+    {
+      "epoch": 0.26405451448040884,
+      "grad_norm": 0.9403277635574341,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.708,
+      "step": 10540
+    },
+    {
+      "epoch": 0.26483114540535124,
+      "grad_norm": 0.9076827168464661,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.6571,
+      "step": 10571
+    },
+    {
+      "epoch": 0.26560777633029364,
+      "grad_norm": 0.9140092730522156,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.6626,
+      "step": 10602
+    },
+    {
+      "epoch": 0.266384407255236,
+      "grad_norm": 0.9277907013893127,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.6625,
+      "step": 10633
+    },
+    {
+      "epoch": 0.2671610381801784,
+      "grad_norm": 0.9199085831642151,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.663,
+      "step": 10664
+    },
+    {
+      "epoch": 0.26793766910512073,
+      "grad_norm": 0.9358407855033875,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.6743,
+      "step": 10695
+    },
+    {
+      "epoch": 0.26871430003006314,
+      "grad_norm": 0.8855702877044678,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.6619,
+      "step": 10726
+    },
+    {
+      "epoch": 0.26949093095500554,
+      "grad_norm": 0.9157874584197998,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.6772,
+      "step": 10757
+    },
+    {
+      "epoch": 0.2702675618799479,
+      "grad_norm": 0.9023963809013367,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.6559,
+      "step": 10788
+    },
+    {
+      "epoch": 0.2710441928048903,
+      "grad_norm": 0.9174203872680664,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.6393,
+      "step": 10819
+    },
+    {
+      "epoch": 0.27182082372983263,
+      "grad_norm": 0.9019688963890076,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.6763,
+      "step": 10850
+    },
+    {
+      "epoch": 0.27259745465477503,
+      "grad_norm": 0.8955567479133606,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.6679,
+      "step": 10881
+    },
+    {
+      "epoch": 0.27337408557971743,
+      "grad_norm": 0.9326659440994263,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.6765,
+      "step": 10912
+    },
+    {
+      "epoch": 0.2741507165046598,
+      "grad_norm": 0.8885530233383179,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.674,
+      "step": 10943
+    },
+    {
+      "epoch": 0.2749273474296022,
+      "grad_norm": 0.909267783164978,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.6602,
+      "step": 10974
+    },
+    {
+      "epoch": 0.2757039783545445,
+      "grad_norm": 0.9005350470542908,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.6628,
+      "step": 11005
+    },
+    {
+      "epoch": 0.2764806092794869,
+      "grad_norm": 0.919683575630188,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.6647,
+      "step": 11036
+    },
+    {
+      "epoch": 0.2772572402044293,
+      "grad_norm": 0.8954905867576599,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.6763,
+      "step": 11067
+    },
+    {
+      "epoch": 0.27803387112937167,
+      "grad_norm": 0.9120632410049438,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.6552,
+      "step": 11098
+    },
+    {
+      "epoch": 0.27881050205431407,
+      "grad_norm": 0.9041403532028198,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.6604,
+      "step": 11129
+    },
+    {
+      "epoch": 0.2795871329792564,
+      "grad_norm": 0.9149596095085144,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.6666,
+      "step": 11160
+    },
+    {
+      "epoch": 0.2803637639041988,
+      "grad_norm": 0.9379541277885437,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.654,
+      "step": 11191
+    },
+    {
+      "epoch": 0.2811403948291412,
+      "grad_norm": 0.8942285180091858,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.6558,
+      "step": 11222
+    },
+    {
+      "epoch": 0.28191702575408356,
+      "grad_norm": 0.9407718181610107,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.6574,
+      "step": 11253
+    },
+    {
+      "epoch": 0.28269365667902596,
+      "grad_norm": 0.9167685508728027,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.6767,
+      "step": 11284
+    },
+    {
+      "epoch": 0.2834702876039683,
+      "grad_norm": 0.8957439661026001,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.6846,
+      "step": 11315
+    },
+    {
+      "epoch": 0.2842469185289107,
+      "grad_norm": 0.9044497609138489,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.6323,
+      "step": 11346
+    },
+    {
+      "epoch": 0.2850235494538531,
+      "grad_norm": 0.9024799466133118,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.682,
+      "step": 11377
+    },
+    {
+      "epoch": 0.28580018037879545,
+      "grad_norm": 0.9126555323600769,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.6802,
+      "step": 11408
+    },
+    {
+      "epoch": 0.28657681130373786,
+      "grad_norm": 0.924310564994812,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.6568,
+      "step": 11439
+    },
+    {
+      "epoch": 0.28735344222868026,
+      "grad_norm": 0.8566572666168213,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.6682,
+      "step": 11470
+    },
+    {
+      "epoch": 0.2881300731536226,
+      "grad_norm": 0.8287222981452942,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.6484,
+      "step": 11501
+    },
+    {
+      "epoch": 0.288906704078565,
+      "grad_norm": 1.0163201093673706,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.635,
+      "step": 11532
+    },
+    {
+      "epoch": 0.28968333500350735,
+      "grad_norm": 0.8813551068305969,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.6654,
+      "step": 11563
+    },
+    {
+      "epoch": 0.29045996592844975,
+      "grad_norm": 0.8688541650772095,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.6787,
+      "step": 11594
+    },
+    {
+      "epoch": 0.29123659685339215,
+      "grad_norm": 0.8820333480834961,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.6418,
+      "step": 11625
+    },
+    {
+      "epoch": 0.2920132277783345,
+      "grad_norm": 0.9284527897834778,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.6727,
+      "step": 11656
+    },
+    {
+      "epoch": 0.2927898587032769,
+      "grad_norm": 0.8665077090263367,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.6377,
+      "step": 11687
+    },
+    {
+      "epoch": 0.29356648962821924,
+      "grad_norm": 0.9927760362625122,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.6628,
+      "step": 11718
+    },
+    {
+      "epoch": 0.29434312055316164,
+      "grad_norm": 0.9006340503692627,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.6589,
+      "step": 11749
+    },
+    {
+      "epoch": 0.29511975147810404,
+      "grad_norm": 0.9278168082237244,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.6519,
+      "step": 11780
+    },
+    {
+      "epoch": 0.2958963824030464,
+      "grad_norm": 0.9146036505699158,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.6541,
+      "step": 11811
+    },
+    {
+      "epoch": 0.2966730133279888,
+      "grad_norm": 0.8698804378509521,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.6722,
+      "step": 11842
+    },
+    {
+      "epoch": 0.29744964425293113,
+      "grad_norm": 0.9304215312004089,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.6392,
+      "step": 11873
+    },
+    {
+      "epoch": 0.29822627517787353,
+      "grad_norm": 0.8917405605316162,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.6373,
+      "step": 11904
+    },
+    {
+      "epoch": 0.29900290610281594,
+      "grad_norm": 0.9075546860694885,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.6401,
+      "step": 11935
+    },
+    {
+      "epoch": 0.2997795370277583,
+      "grad_norm": 0.9235963225364685,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.667,
+      "step": 11966
+    },
+    {
+      "epoch": 0.3005561679527007,
+      "grad_norm": 0.9514668583869934,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.6654,
+      "step": 11997
+    },
+    {
+      "epoch": 0.301332798877643,
+      "grad_norm": 0.8843172192573547,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.6609,
+      "step": 12028
+    },
+    {
+      "epoch": 0.3021094298025854,
+      "grad_norm": 0.9325070977210999,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.6392,
+      "step": 12059
+    },
+    {
+      "epoch": 0.30288606072752783,
+      "grad_norm": 0.8855581879615784,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.6607,
+      "step": 12090
+    },
+    {
+      "epoch": 0.3036626916524702,
+      "grad_norm": 0.9044367671012878,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.6417,
+      "step": 12121
+    },
+    {
+      "epoch": 0.3044393225774126,
+      "grad_norm": 0.9446975588798523,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.6279,
+      "step": 12152
+    },
+    {
+      "epoch": 0.3052159535023549,
+      "grad_norm": 0.8764945864677429,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.6297,
+      "step": 12183
+    },
+    {
+      "epoch": 0.3059925844272973,
+      "grad_norm": 0.8633154034614563,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 1.648,
+      "step": 12214
+    },
+    {
+      "epoch": 0.3067692153522397,
+      "grad_norm": 0.8891461491584778,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 1.6492,
+      "step": 12245
+    },
+    {
+      "epoch": 0.30754584627718207,
+      "grad_norm": 0.8888112306594849,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 1.6507,
+      "step": 12276
+    },
+    {
+      "epoch": 0.30832247720212447,
+      "grad_norm": 0.8980075120925903,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 1.6571,
+      "step": 12307
+    },
+    {
+      "epoch": 0.3090991081270668,
+      "grad_norm": 0.86537104845047,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 1.6331,
+      "step": 12338
+    },
+    {
+      "epoch": 0.3098757390520092,
+      "grad_norm": 0.9001527428627014,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 1.6453,
+      "step": 12369
+    },
+    {
+      "epoch": 0.3106523699769516,
+      "grad_norm": 0.8868582248687744,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 1.6623,
+      "step": 12400
+    },
+    {
+      "epoch": 0.31142900090189396,
+      "grad_norm": 0.899174690246582,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 1.6451,
+      "step": 12431
+    },
+    {
+      "epoch": 0.31220563182683636,
+      "grad_norm": 0.9003099203109741,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 1.6544,
+      "step": 12462
+    },
+    {
+      "epoch": 0.31298226275177876,
+      "grad_norm": 0.8912012577056885,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 1.6579,
+      "step": 12493
+    },
+    {
+      "epoch": 0.3137588936767211,
+      "grad_norm": 0.8915206789970398,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 1.65,
+      "step": 12524
+    },
+    {
+      "epoch": 0.3145355246016635,
+      "grad_norm": 0.9975365400314331,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 1.6506,
+      "step": 12555
+    },
+    {
+      "epoch": 0.31531215552660585,
+      "grad_norm": 0.8904858827590942,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 1.6402,
+      "step": 12586
+    },
+    {
+      "epoch": 0.31608878645154825,
+      "grad_norm": 0.8596284985542297,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 1.6473,
+      "step": 12617
+    },
+    {
+      "epoch": 0.31686541737649065,
+      "grad_norm": 0.8970181345939636,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 1.6347,
+      "step": 12648
+    },
+    {
+      "epoch": 0.317642048301433,
+      "grad_norm": 0.890839695930481,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 1.6323,
+      "step": 12679
+    },
+    {
+      "epoch": 0.3184186792263754,
+      "grad_norm": 0.914010226726532,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 1.6396,
+      "step": 12710
+    },
+    {
+      "epoch": 0.31919531015131775,
+      "grad_norm": 0.8762277960777283,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 1.6057,
+      "step": 12741
+    },
+    {
+      "epoch": 0.31997194107626015,
+      "grad_norm": 0.9001442193984985,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 1.647,
+      "step": 12772
+    },
+    {
+      "epoch": 0.32074857200120255,
+      "grad_norm": 0.8792625069618225,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 1.6441,
+      "step": 12803
+    },
+    {
+      "epoch": 0.3215252029261449,
+      "grad_norm": 0.889738142490387,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 1.6433,
+      "step": 12834
+    },
+    {
+      "epoch": 0.3223018338510873,
+      "grad_norm": 0.9831507205963135,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 1.6635,
+      "step": 12865
+    },
+    {
+      "epoch": 0.32307846477602964,
+      "grad_norm": 0.8929276466369629,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 1.6439,
+      "step": 12896
+    },
+    {
+      "epoch": 0.32385509570097204,
+      "grad_norm": 0.8983376026153564,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 1.641,
+      "step": 12927
+    },
+    {
+      "epoch": 0.32463172662591444,
+      "grad_norm": 0.8629191517829895,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 1.6336,
+      "step": 12958
+    },
+    {
+      "epoch": 0.3254083575508568,
+      "grad_norm": 0.9323459267616272,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 1.6304,
+      "step": 12989
+    },
+    {
+      "epoch": 0.3261849884757992,
+      "grad_norm": 0.8520583510398865,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 1.6277,
+      "step": 13020
+    },
+    {
+      "epoch": 0.32696161940074153,
+      "grad_norm": 0.8893365263938904,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 1.6508,
+      "step": 13051
+    },
+    {
+      "epoch": 0.32773825032568393,
+      "grad_norm": 0.8612290024757385,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 1.6319,
+      "step": 13082
+    },
+    {
+      "epoch": 0.32851488125062633,
+      "grad_norm": 0.9378547072410583,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 1.637,
+      "step": 13113
+    },
+    {
+      "epoch": 0.3292915121755687,
+      "grad_norm": 0.8851338028907776,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 1.6326,
+      "step": 13144
+    },
+    {
+      "epoch": 0.3300681431005111,
+      "grad_norm": 0.9052163362503052,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 1.6507,
+      "step": 13175
+    },
+    {
+      "epoch": 0.3308447740254534,
+      "grad_norm": 0.9593476057052612,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 1.6497,
+      "step": 13206
+    },
+    {
+      "epoch": 0.3316214049503958,
+      "grad_norm": 0.8861746788024902,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 1.6487,
+      "step": 13237
+    },
+    {
+      "epoch": 0.3323980358753382,
+      "grad_norm": 0.8835756778717041,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 1.6328,
+      "step": 13268
+    },
+    {
+      "epoch": 0.33317466680028057,
+      "grad_norm": 0.9133350849151611,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 1.6326,
+      "step": 13299
+    },
+    {
+      "epoch": 0.333951297725223,
+      "grad_norm": 0.8866952657699585,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 1.6418,
+      "step": 13330
+    },
+    {
+      "epoch": 0.3347279286501654,
+      "grad_norm": 0.8961243033409119,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 1.6436,
+      "step": 13361
+    },
+    {
+      "epoch": 0.3355045595751077,
+      "grad_norm": 0.871108889579773,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 1.6205,
+      "step": 13392
+    },
+    {
+      "epoch": 0.3362811905000501,
+      "grad_norm": 0.8666812777519226,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 1.6478,
+      "step": 13423
+    },
+    {
+      "epoch": 0.33705782142499247,
+      "grad_norm": 0.8760045766830444,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 1.63,
+      "step": 13454
+    },
+    {
+      "epoch": 0.33783445234993487,
+      "grad_norm": 0.9416362047195435,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 1.6268,
+      "step": 13485
+    },
+    {
+      "epoch": 0.33861108327487727,
+      "grad_norm": 0.8591843843460083,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 1.6206,
+      "step": 13516
+    },
+    {
+      "epoch": 0.3393877141998196,
+      "grad_norm": 0.9452426433563232,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 1.6351,
+      "step": 13547
+    },
+    {
+      "epoch": 0.340164345124762,
+      "grad_norm": 0.8680084943771362,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 1.6389,
+      "step": 13578
+    },
+    {
+      "epoch": 0.34094097604970436,
+      "grad_norm": 0.8631142973899841,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 1.6198,
+      "step": 13609
+    },
+    {
+      "epoch": 0.34171760697464676,
+      "grad_norm": 0.905168354511261,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 1.6395,
+      "step": 13640
+    },
+    {
+      "epoch": 0.34249423789958916,
+      "grad_norm": 0.8644616007804871,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 1.6282,
+      "step": 13671
+    },
+    {
+      "epoch": 0.3432708688245315,
+      "grad_norm": 0.8989911675453186,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 1.6378,
+      "step": 13702
+    },
+    {
+      "epoch": 0.3440474997494739,
+      "grad_norm": 0.908371090888977,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 1.6152,
+      "step": 13733
+    },
+    {
+      "epoch": 0.34482413067441625,
+      "grad_norm": 0.876471221446991,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 1.6533,
+      "step": 13764
+    },
+    {
+      "epoch": 0.34560076159935865,
+      "grad_norm": 0.879152238368988,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 1.6196,
+      "step": 13795
+    },
+    {
+      "epoch": 0.34637739252430105,
+      "grad_norm": 0.8737320303916931,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 1.6122,
+      "step": 13826
+    },
+    {
+      "epoch": 0.3471540234492434,
+      "grad_norm": 0.894914448261261,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 1.6231,
+      "step": 13857
+    },
+    {
+      "epoch": 0.3479306543741858,
+      "grad_norm": 0.8699216842651367,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 1.6374,
+      "step": 13888
+    },
+    {
+      "epoch": 0.34870728529912814,
+      "grad_norm": 0.8811262249946594,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 1.635,
+      "step": 13919
+    },
+    {
+      "epoch": 0.34948391622407055,
+      "grad_norm": 0.9017398953437805,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 1.6377,
+      "step": 13950
+    },
+    {
+      "epoch": 0.35026054714901295,
+      "grad_norm": 0.8944412469863892,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 1.6401,
+      "step": 13981
+    },
+    {
+      "epoch": 0.3510371780739553,
+      "grad_norm": 0.9429489970207214,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 1.6313,
+      "step": 14012
+    },
+    {
+      "epoch": 0.3518138089988977,
+      "grad_norm": 0.8750442862510681,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 1.6305,
+      "step": 14043
+    },
+    {
+      "epoch": 0.35259043992384004,
+      "grad_norm": 0.8219168782234192,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 1.6289,
+      "step": 14074
+    },
+    {
+      "epoch": 0.35336707084878244,
+      "grad_norm": 0.9778533577919006,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 1.6221,
+      "step": 14105
+    },
+    {
+      "epoch": 0.35414370177372484,
+      "grad_norm": 0.8655532598495483,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 1.6352,
+      "step": 14136
+    },
+    {
+      "epoch": 0.3549203326986672,
+      "grad_norm": 0.8914876580238342,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 1.6283,
+      "step": 14167
+    },
+    {
+      "epoch": 0.3556969636236096,
+      "grad_norm": 0.9823268055915833,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 1.6037,
+      "step": 14198
+    },
+    {
+      "epoch": 0.356473594548552,
+      "grad_norm": 0.8770225048065186,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 1.6199,
+      "step": 14229
+    },
+    {
+      "epoch": 0.35725022547349433,
+      "grad_norm": 0.8294642567634583,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 1.587,
+      "step": 14260
+    },
+    {
+      "epoch": 0.35802685639843673,
+      "grad_norm": 0.8678600192070007,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 1.6006,
+      "step": 14291
+    },
+    {
+      "epoch": 0.3588034873233791,
+      "grad_norm": 0.8829056620597839,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 1.6354,
+      "step": 14322
+    },
+    {
+      "epoch": 0.3595801182483215,
+      "grad_norm": 0.8785590529441833,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 1.6293,
+      "step": 14353
+    },
+    {
+      "epoch": 0.3603567491732639,
+      "grad_norm": 0.8895497918128967,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 1.6121,
+      "step": 14384
+    },
+    {
+      "epoch": 0.3611333800982062,
+      "grad_norm": 0.8808982372283936,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 1.6251,
+      "step": 14415
+    },
+    {
+      "epoch": 0.3619100110231486,
+      "grad_norm": 0.8854517936706543,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 1.617,
+      "step": 14446
+    },
+    {
+      "epoch": 0.36268664194809097,
+      "grad_norm": 0.9169306755065918,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 1.632,
+      "step": 14477
+    },
+    {
+      "epoch": 0.36346327287303337,
+      "grad_norm": 0.9230756163597107,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 1.6227,
+      "step": 14508
+    },
+    {
+      "epoch": 0.3642399037979758,
+      "grad_norm": 0.8728978037834167,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 1.6175,
+      "step": 14539
+    },
+    {
+      "epoch": 0.3650165347229181,
+      "grad_norm": 0.9083303213119507,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 1.6147,
+      "step": 14570
+    },
+    {
+      "epoch": 0.3657931656478605,
+      "grad_norm": 0.8577157855033875,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 1.6357,
+      "step": 14601
+    },
+    {
+      "epoch": 0.36656979657280286,
+      "grad_norm": 0.9495333433151245,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 1.6192,
+      "step": 14632
+    },
+    {
+      "epoch": 0.36734642749774526,
+      "grad_norm": 0.9099650979042053,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 1.6417,
+      "step": 14663
+    },
+    {
+      "epoch": 0.36812305842268767,
+      "grad_norm": 0.8684884905815125,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 1.6171,
+      "step": 14694
+    },
+    {
+      "epoch": 0.36889968934763,
+      "grad_norm": 0.8524884581565857,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 1.6153,
+      "step": 14725
+    },
+    {
+      "epoch": 0.3696763202725724,
+      "grad_norm": 0.9122047424316406,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 1.6223,
+      "step": 14756
+    },
+    {
+      "epoch": 0.37045295119751476,
+      "grad_norm": 0.875884473323822,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 1.6364,
+      "step": 14787
+    },
+    {
+      "epoch": 0.37122958212245716,
+      "grad_norm": 0.8689435720443726,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 1.639,
+      "step": 14818
+    },
+    {
+      "epoch": 0.37200621304739956,
+      "grad_norm": 0.8948261141777039,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 1.6091,
+      "step": 14849
+    },
+    {
+      "epoch": 0.3727828439723419,
+      "grad_norm": 0.8971095085144043,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 1.6527,
+      "step": 14880
+    },
+    {
+      "epoch": 0.3735594748972843,
+      "grad_norm": 0.9517078995704651,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 1.6201,
+      "step": 14911
+    },
+    {
+      "epoch": 0.37433610582222665,
+      "grad_norm": 0.8965676426887512,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 1.6104,
+      "step": 14942
+    },
+    {
+      "epoch": 0.37511273674716905,
+      "grad_norm": 0.9771518707275391,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 1.6329,
+      "step": 14973
+    },
+    {
+      "epoch": 0.37588936767211145,
+      "grad_norm": 0.8746607899665833,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 1.6135,
+      "step": 15004
+    },
+    {
+      "epoch": 0.3766659985970538,
+      "grad_norm": 0.860730767250061,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 1.6163,
+      "step": 15035
+    },
+    {
+      "epoch": 0.3774426295219962,
+      "grad_norm": 0.8879541158676147,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 1.6036,
+      "step": 15066
+    },
+    {
+      "epoch": 0.37821926044693854,
+      "grad_norm": 0.936347246170044,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 1.5914,
+      "step": 15097
+    },
+    {
+      "epoch": 0.37899589137188094,
+      "grad_norm": 0.8772497773170471,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 1.5994,
+      "step": 15128
+    },
+    {
+      "epoch": 0.37977252229682334,
+      "grad_norm": 0.8785439729690552,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 1.6057,
+      "step": 15159
+    },
+    {
+      "epoch": 0.3805491532217657,
+      "grad_norm": 1.1660430431365967,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 1.6257,
+      "step": 15190
+    },
+    {
+      "epoch": 0.3813257841467081,
+      "grad_norm": 0.8710660934448242,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 1.6223,
+      "step": 15221
+    },
+    {
+      "epoch": 0.3821024150716505,
+      "grad_norm": 0.9040597081184387,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 1.6054,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.065842709765292e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:648c03a879cd4197b7658fa4d1110b979eef2c447adce1165e90fb225ceb553d
+size 5304

checkpoint-18312/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-my-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-18312/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-18312/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210f391f3908f81b797a47a1860456f2b9bab5430763968febd704af19250dc3
+size 4842817304

checkpoint-18312/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-18312/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304

checkpoint-18312/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-18312/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-18312/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4c0fa0d75c3a51d66cf2a93c73524ebbf00549cfc610d948a0742de905b52e
+size 3662865184

checkpoint-18312/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2aa42930900022536045ca8f25823d057acb27970c53058a86088f1182ad54
+size 2317729920

checkpoint-18312/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30737946624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-18312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25cc126fedc65e2119d91471139ecdb2345876a0196137095fd826f2da8f30fd
+size 16728842070

checkpoint-18312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-18312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e65c3d6f29e706fd941a38280ce5628189a6998eac6d29abbeab00ad838d00
+size 1064

checkpoint-18312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:648c03a879cd4197b7658fa4d1110b979eef2c447adce1165e90fb225ceb553d
+size 5304

checkpoint-21364/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-my-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-21364/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-21364/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11cd395b0ec517e0f378948b93c882979da04753cc769fcefbcd882622875390
+size 4842817304

checkpoint-21364/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-21364/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304