Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151646,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.5.6",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_length": 131072,
+  "pad_token_id": 151654,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84ef017ac2d82fd651decdb8b7efddf22283316c63f660bfc9c255f486a17d9
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c365c0529a1bebc6465fa48dce83ea47114d01025a7f446226ab611afe3486ff
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d5db4361442bdad1c3b7022baec23094ef2f88684a44936eb0928eb024c93b
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e041c953254cc61917aa3fe03aefe185e86d191f6c51a6d8f6f4c56586e20e3
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecefbb3f17bb76b6655eb0157c98b5287c17fa4b4c72a6b9068b0823ce9fd18d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240d692f2e08509e1c7611e2fe82f12b4e9e0eb675aecec368740f9c35395afb
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<｜User｜>' + message['content'] }}{% elif message['role'] == 'assistant' and message['content'] is not none %}{{ '<｜Assistant｜>' + message['content'] + '<｜end▁of▁sentence｜>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2036 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2860,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017497812773403325,
+      "grad_norm": 4.1875,
+      "learning_rate": 2.0930232558139536e-06,
+      "loss": 1.0581,
+      "step": 10
+    },
+    {
+      "epoch": 0.03499562554680665,
+      "grad_norm": 3.328125,
+      "learning_rate": 4.418604651162791e-06,
+      "loss": 1.0503,
+      "step": 20
+    },
+    {
+      "epoch": 0.05249343832020997,
+      "grad_norm": 2.71875,
+      "learning_rate": 6.744186046511628e-06,
+      "loss": 0.9804,
+      "step": 30
+    },
+    {
+      "epoch": 0.0699912510936133,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.069767441860465e-06,
+      "loss": 0.8786,
+      "step": 40
+    },
+    {
+      "epoch": 0.08748906386701662,
+      "grad_norm": 1.0,
+      "learning_rate": 1.1395348837209304e-05,
+      "loss": 0.8081,
+      "step": 50
+    },
+    {
+      "epoch": 0.10498687664041995,
+      "grad_norm": 0.8203125,
+      "learning_rate": 1.372093023255814e-05,
+      "loss": 0.8047,
+      "step": 60
+    },
+    {
+      "epoch": 0.12248468941382328,
+      "grad_norm": 0.765625,
+      "learning_rate": 1.6046511627906977e-05,
+      "loss": 0.7453,
+      "step": 70
+    },
+    {
+      "epoch": 0.1399825021872266,
+      "grad_norm": 0.8125,
+      "learning_rate": 1.8372093023255815e-05,
+      "loss": 0.7581,
+      "step": 80
+    },
+    {
+      "epoch": 0.15748031496062992,
+      "grad_norm": 0.734375,
+      "learning_rate": 2.0697674418604654e-05,
+      "loss": 0.7399,
+      "step": 90
+    },
+    {
+      "epoch": 0.17497812773403323,
+      "grad_norm": 0.71875,
+      "learning_rate": 2.3023255813953492e-05,
+      "loss": 0.7476,
+      "step": 100
+    },
+    {
+      "epoch": 0.19247594050743658,
+      "grad_norm": 0.7109375,
+      "learning_rate": 2.5348837209302327e-05,
+      "loss": 0.7247,
+      "step": 110
+    },
+    {
+      "epoch": 0.2099737532808399,
+      "grad_norm": 0.81640625,
+      "learning_rate": 2.7674418604651166e-05,
+      "loss": 0.7179,
+      "step": 120
+    },
+    {
+      "epoch": 0.2274715660542432,
+      "grad_norm": 0.77734375,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 0.6949,
+      "step": 130
+    },
+    {
+      "epoch": 0.24496937882764655,
+      "grad_norm": 0.82421875,
+      "learning_rate": 3.232558139534884e-05,
+      "loss": 0.7043,
+      "step": 140
+    },
+    {
+      "epoch": 0.26246719160104987,
+      "grad_norm": 0.69921875,
+      "learning_rate": 3.4651162790697674e-05,
+      "loss": 0.6934,
+      "step": 150
+    },
+    {
+      "epoch": 0.2799650043744532,
+      "grad_norm": 0.6796875,
+      "learning_rate": 3.697674418604651e-05,
+      "loss": 0.6993,
+      "step": 160
+    },
+    {
+      "epoch": 0.2974628171478565,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.930232558139535e-05,
+      "loss": 0.7027,
+      "step": 170
+    },
+    {
+      "epoch": 0.31496062992125984,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.9999858083836754e-05,
+      "loss": 0.6935,
+      "step": 180
+    },
+    {
+      "epoch": 0.3324584426946632,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.999916298964876e-05,
+      "loss": 0.7137,
+      "step": 190
+    },
+    {
+      "epoch": 0.34995625546806647,
+      "grad_norm": 0.7578125,
+      "learning_rate": 3.999788867354247e-05,
+      "loss": 0.6916,
+      "step": 200
+    },
+    {
+      "epoch": 0.3674540682414698,
+      "grad_norm": 0.69921875,
+      "learning_rate": 3.9996035176526014e-05,
+      "loss": 0.6947,
+      "step": 210
+    },
+    {
+      "epoch": 0.38495188101487315,
+      "grad_norm": 0.77734375,
+      "learning_rate": 3.9993602558245834e-05,
+      "loss": 0.7045,
+      "step": 220
+    },
+    {
+      "epoch": 0.40244969378827644,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.9990590896984766e-05,
+      "loss": 0.7016,
+      "step": 230
+    },
+    {
+      "epoch": 0.4199475065616798,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.998700028965957e-05,
+      "loss": 0.7072,
+      "step": 240
+    },
+    {
+      "epoch": 0.4374453193350831,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.9982830851817736e-05,
+      "loss": 0.6986,
+      "step": 250
+    },
+    {
+      "epoch": 0.4549431321084864,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.997808271763385e-05,
+      "loss": 0.6804,
+      "step": 260
+    },
+    {
+      "epoch": 0.47244094488188976,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.997275603990519e-05,
+      "loss": 0.7016,
+      "step": 270
+    },
+    {
+      "epoch": 0.4899387576552931,
+      "grad_norm": 0.703125,
+      "learning_rate": 3.996685099004686e-05,
+      "loss": 0.6921,
+      "step": 280
+    },
+    {
+      "epoch": 0.5074365704286964,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.996036775808628e-05,
+      "loss": 0.6857,
+      "step": 290
+    },
+    {
+      "epoch": 0.5249343832020997,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.995330655265704e-05,
+      "loss": 0.6967,
+      "step": 300
+    },
+    {
+      "epoch": 0.5424321959755031,
+      "grad_norm": 0.72265625,
+      "learning_rate": 3.994566760099221e-05,
+      "loss": 0.6969,
+      "step": 310
+    },
+    {
+      "epoch": 0.5599300087489064,
+      "grad_norm": 0.59765625,
+      "learning_rate": 3.9937451148917e-05,
+      "loss": 0.6862,
+      "step": 320
+    },
+    {
+      "epoch": 0.5774278215223098,
+      "grad_norm": 0.625,
+      "learning_rate": 3.992865746084089e-05,
+      "loss": 0.695,
+      "step": 330
+    },
+    {
+      "epoch": 0.594925634295713,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.991928681974908e-05,
+      "loss": 0.7036,
+      "step": 340
+    },
+    {
+      "epoch": 0.6124234470691163,
+      "grad_norm": 0.734375,
+      "learning_rate": 3.9909339527193416e-05,
+      "loss": 0.7064,
+      "step": 350
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.989881590328265e-05,
+      "loss": 0.6768,
+      "step": 360
+    },
+    {
+      "epoch": 0.647419072615923,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.98877162866722e-05,
+      "loss": 0.7161,
+      "step": 370
+    },
+    {
+      "epoch": 0.6649168853893264,
+      "grad_norm": 0.625,
+      "learning_rate": 3.9876041034553165e-05,
+      "loss": 0.6731,
+      "step": 380
+    },
+    {
+      "epoch": 0.6824146981627297,
+      "grad_norm": 0.65625,
+      "learning_rate": 3.9863790522640926e-05,
+      "loss": 0.6905,
+      "step": 390
+    },
+    {
+      "epoch": 0.6999125109361329,
+      "grad_norm": 0.66796875,
+      "learning_rate": 3.9850965145162954e-05,
+      "loss": 0.7067,
+      "step": 400
+    },
+    {
+      "epoch": 0.7174103237095363,
+      "grad_norm": 0.6015625,
+      "learning_rate": 3.983756531484622e-05,
+      "loss": 0.6982,
+      "step": 410
+    },
+    {
+      "epoch": 0.7349081364829396,
+      "grad_norm": 0.59375,
+      "learning_rate": 3.9823591462903856e-05,
+      "loss": 0.6932,
+      "step": 420
+    },
+    {
+      "epoch": 0.752405949256343,
+      "grad_norm": 0.6953125,
+      "learning_rate": 3.9809044039021295e-05,
+      "loss": 0.7004,
+      "step": 430
+    },
+    {
+      "epoch": 0.7699037620297463,
+      "grad_norm": 0.63671875,
+      "learning_rate": 3.979392351134178e-05,
+      "loss": 0.7002,
+      "step": 440
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "grad_norm": 0.63671875,
+      "learning_rate": 3.977823036645132e-05,
+      "loss": 0.7065,
+      "step": 450
+    },
+    {
+      "epoch": 0.8048993875765529,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.976196510936307e-05,
+      "loss": 0.692,
+      "step": 460
+    },
+    {
+      "epoch": 0.8223972003499562,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.9745128263500976e-05,
+      "loss": 0.6847,
+      "step": 470
+    },
+    {
+      "epoch": 0.8398950131233596,
+      "grad_norm": 0.75,
+      "learning_rate": 3.972772037068303e-05,
+      "loss": 0.6868,
+      "step": 480
+    },
+    {
+      "epoch": 0.8573928258967629,
+      "grad_norm": 0.69140625,
+      "learning_rate": 3.970974199110378e-05,
+      "loss": 0.6727,
+      "step": 490
+    },
+    {
+      "epoch": 0.8748906386701663,
+      "grad_norm": 0.54296875,
+      "learning_rate": 3.9691193703316336e-05,
+      "loss": 0.69,
+      "step": 500
+    },
+    {
+      "epoch": 0.8923884514435696,
+      "grad_norm": 0.578125,
+      "learning_rate": 3.9672076104213706e-05,
+      "loss": 0.6696,
+      "step": 510
+    },
+    {
+      "epoch": 0.9098862642169728,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.965238980900965e-05,
+      "loss": 0.6852,
+      "step": 520
+    },
+    {
+      "epoch": 0.9273840769903762,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.963213545121881e-05,
+      "loss": 0.6852,
+      "step": 530
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "grad_norm": 0.63671875,
+      "learning_rate": 3.9611313682636395e-05,
+      "loss": 0.6907,
+      "step": 540
+    },
+    {
+      "epoch": 0.9623797025371829,
+      "grad_norm": 0.59375,
+      "learning_rate": 3.9589925173317165e-05,
+      "loss": 0.6753,
+      "step": 550
+    },
+    {
+      "epoch": 0.9798775153105862,
+      "grad_norm": 0.63671875,
+      "learning_rate": 3.956797061155386e-05,
+      "loss": 0.6796,
+      "step": 560
+    },
+    {
+      "epoch": 0.9973753280839895,
+      "grad_norm": 0.640625,
+      "learning_rate": 3.954545070385508e-05,
+      "loss": 0.6875,
+      "step": 570
+    },
+    {
+      "epoch": 1.0139982502187226,
+      "grad_norm": 0.59765625,
+      "learning_rate": 3.952236617492253e-05,
+      "loss": 0.6204,
+      "step": 580
+    },
+    {
+      "epoch": 1.031496062992126,
+      "grad_norm": 0.59765625,
+      "learning_rate": 3.94987177676277e-05,
+      "loss": 0.5968,
+      "step": 590
+    },
+    {
+      "epoch": 1.0489938757655293,
+      "grad_norm": 0.671875,
+      "learning_rate": 3.947450624298799e-05,
+      "loss": 0.6147,
+      "step": 600
+    },
+    {
+      "epoch": 1.0664916885389326,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.944973238014215e-05,
+      "loss": 0.6052,
+      "step": 610
+    },
+    {
+      "epoch": 1.083989501312336,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.942439697632528e-05,
+      "loss": 0.6152,
+      "step": 620
+    },
+    {
+      "epoch": 1.1014873140857393,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.9398500846843136e-05,
+      "loss": 0.622,
+      "step": 630
+    },
+    {
+      "epoch": 1.1189851268591426,
+      "grad_norm": 0.578125,
+      "learning_rate": 3.9372044825045905e-05,
+      "loss": 0.6361,
+      "step": 640
+    },
+    {
+      "epoch": 1.136482939632546,
+      "grad_norm": 0.5703125,
+      "learning_rate": 3.934502976230138e-05,
+      "loss": 0.6015,
+      "step": 650
+    },
+    {
+      "epoch": 1.1539807524059493,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.9317456527967566e-05,
+      "loss": 0.6231,
+      "step": 660
+    },
+    {
+      "epoch": 1.1714785651793527,
+      "grad_norm": 0.640625,
+      "learning_rate": 3.92893260093647e-05,
+      "loss": 0.6325,
+      "step": 670
+    },
+    {
+      "epoch": 1.188976377952756,
+      "grad_norm": 0.58203125,
+      "learning_rate": 3.926063911174673e-05,
+      "loss": 0.6,
+      "step": 680
+    },
+    {
+      "epoch": 1.2064741907261591,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.92313967582721e-05,
+      "loss": 0.6158,
+      "step": 690
+    },
+    {
+      "epoch": 1.2239720034995625,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.9201599889974155e-05,
+      "loss": 0.6184,
+      "step": 700
+    },
+    {
+      "epoch": 1.2414698162729658,
+      "grad_norm": 0.6015625,
+      "learning_rate": 3.917124946573076e-05,
+      "loss": 0.6159,
+      "step": 710
+    },
+    {
+      "epoch": 1.2589676290463692,
+      "grad_norm": 0.57421875,
+      "learning_rate": 3.91403464622335e-05,
+      "loss": 0.6221,
+      "step": 720
+    },
+    {
+      "epoch": 1.2764654418197725,
+      "grad_norm": 0.640625,
+      "learning_rate": 3.910889187395622e-05,
+      "loss": 0.6393,
+      "step": 730
+    },
+    {
+      "epoch": 1.2939632545931758,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.9076886713123056e-05,
+      "loss": 0.6168,
+      "step": 740
+    },
+    {
+      "epoch": 1.3114610673665792,
+      "grad_norm": 0.578125,
+      "learning_rate": 3.9044332009675816e-05,
+      "loss": 0.611,
+      "step": 750
+    },
+    {
+      "epoch": 1.3289588801399825,
+      "grad_norm": 0.66796875,
+      "learning_rate": 3.901122881124087e-05,
+      "loss": 0.625,
+      "step": 760
+    },
+    {
+      "epoch": 1.3464566929133859,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.897757818309543e-05,
+      "loss": 0.6196,
+      "step": 770
+    },
+    {
+      "epoch": 1.3639545056867892,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.8943381208133266e-05,
+      "loss": 0.6451,
+      "step": 780
+    },
+    {
+      "epoch": 1.3814523184601923,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.890863898682984e-05,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.3989501312335957,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.887335263720693e-05,
+      "loss": 0.6182,
+      "step": 800
+    },
+    {
+      "epoch": 1.416447944006999,
+      "grad_norm": 0.57421875,
+      "learning_rate": 3.883752329479662e-05,
+      "loss": 0.6206,
+      "step": 810
+    },
+    {
+      "epoch": 1.4339457567804024,
+      "grad_norm": 0.65625,
+      "learning_rate": 3.880115211260478e-05,
+      "loss": 0.6068,
+      "step": 820
+    },
+    {
+      "epoch": 1.4514435695538057,
+      "grad_norm": 0.52734375,
+      "learning_rate": 3.876424026107394e-05,
+      "loss": 0.6221,
+      "step": 830
+    },
+    {
+      "epoch": 1.468941382327209,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.872678892804563e-05,
+      "loss": 0.6118,
+      "step": 840
+    },
+    {
+      "epoch": 1.4864391951006124,
+      "grad_norm": 0.60546875,
+      "learning_rate": 3.868879931872218e-05,
+      "loss": 0.6137,
+      "step": 850
+    },
+    {
+      "epoch": 1.5039370078740157,
+      "grad_norm": 0.58203125,
+      "learning_rate": 3.865027265562789e-05,
+      "loss": 0.61,
+      "step": 860
+    },
+    {
+      "epoch": 1.521434820647419,
+      "grad_norm": 0.60546875,
+      "learning_rate": 3.8611210178569746e-05,
+      "loss": 0.6285,
+      "step": 870
+    },
+    {
+      "epoch": 1.5389326334208224,
+      "grad_norm": 0.59765625,
+      "learning_rate": 3.857161314459745e-05,
+      "loss": 0.6211,
+      "step": 880
+    },
+    {
+      "epoch": 1.5564304461942258,
+      "grad_norm": 0.58203125,
+      "learning_rate": 3.853148282796306e-05,
+      "loss": 0.6291,
+      "step": 890
+    },
+    {
+      "epoch": 1.5739282589676291,
+      "grad_norm": 0.59375,
+      "learning_rate": 3.849082052007988e-05,
+      "loss": 0.6074,
+      "step": 900
+    },
+    {
+      "epoch": 1.5914260717410325,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.844962752948099e-05,
+      "loss": 0.6314,
+      "step": 910
+    },
+    {
+      "epoch": 1.6089238845144358,
+      "grad_norm": 0.5859375,
+      "learning_rate": 3.8407905181777095e-05,
+      "loss": 0.6167,
+      "step": 920
+    },
+    {
+      "epoch": 1.6264216972878391,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.836565481961386e-05,
+      "loss": 0.6235,
+      "step": 930
+    },
+    {
+      "epoch": 1.6439195100612425,
+      "grad_norm": 0.5859375,
+      "learning_rate": 3.8322877802628704e-05,
+      "loss": 0.6106,
+      "step": 940
+    },
+    {
+      "epoch": 1.6614173228346458,
+      "grad_norm": 0.5546875,
+      "learning_rate": 3.827957550740711e-05,
+      "loss": 0.6041,
+      "step": 950
+    },
+    {
+      "epoch": 1.678915135608049,
+      "grad_norm": 0.59375,
+      "learning_rate": 3.82357493274382e-05,
+      "loss": 0.6176,
+      "step": 960
+    },
+    {
+      "epoch": 1.6964129483814523,
+      "grad_norm": 0.5625,
+      "learning_rate": 3.8191400673070034e-05,
+      "loss": 0.6105,
+      "step": 970
+    },
+    {
+      "epoch": 1.7139107611548556,
+      "grad_norm": 0.55859375,
+      "learning_rate": 3.81465309714641e-05,
+      "loss": 0.6278,
+      "step": 980
+    },
+    {
+      "epoch": 1.731408573928259,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.810114166654948e-05,
+      "loss": 0.6189,
+      "step": 990
+    },
+    {
+      "epoch": 1.7489063867016623,
+      "grad_norm": 0.66796875,
+      "learning_rate": 3.805523421897633e-05,
+      "loss": 0.6299,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7664041994750657,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.800881010606889e-05,
+      "loss": 0.6059,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7839020122484688,
+      "grad_norm": 0.58203125,
+      "learning_rate": 3.7961870821777946e-05,
+      "loss": 0.6199,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8013998250218721,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.791441787663276e-05,
+      "loss": 0.5948,
+      "step": 1030
+    },
+    {
+      "epoch": 1.8188976377952755,
+      "grad_norm": 0.55859375,
+      "learning_rate": 3.786645279769244e-05,
+      "loss": 0.608,
+      "step": 1040
+    },
+    {
+      "epoch": 1.8363954505686788,
+      "grad_norm": 0.63671875,
+      "learning_rate": 3.781797712849683e-05,
+      "loss": 0.6327,
+      "step": 1050
+    },
+    {
+      "epoch": 1.8538932633420822,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.7768992429016796e-05,
+      "loss": 0.6392,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8713910761154855,
+      "grad_norm": 0.546875,
+      "learning_rate": 3.7719500275604074e-05,
+      "loss": 0.6359,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.7669502260940495e-05,
+      "loss": 0.6156,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9063867016622922,
+      "grad_norm": 0.5390625,
+      "learning_rate": 3.761899999398677e-05,
+      "loss": 0.6142,
+      "step": 1090
+    },
+    {
+      "epoch": 1.9238845144356955,
+      "grad_norm": 0.62890625,
+      "learning_rate": 3.756799509993069e-05,
+      "loss": 0.6282,
+      "step": 1100
+    },
+    {
+      "epoch": 1.9413823272090989,
+      "grad_norm": 0.63671875,
+      "learning_rate": 3.751648922013482e-05,
+      "loss": 0.6388,
+      "step": 1110
+    },
+    {
+      "epoch": 1.9588801399825022,
+      "grad_norm": 0.578125,
+      "learning_rate": 3.746448401208373e-05,
+      "loss": 0.612,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9763779527559056,
+      "grad_norm": 0.54296875,
+      "learning_rate": 3.7411981149330575e-05,
+      "loss": 0.622,
+      "step": 1130
+    },
+    {
+      "epoch": 1.993875765529309,
+      "grad_norm": 0.625,
+      "learning_rate": 3.735898232144331e-05,
+      "loss": 0.6204,
+      "step": 1140
+    },
+    {
+      "epoch": 2.010498687664042,
+      "grad_norm": 0.609375,
+      "learning_rate": 3.7305489233950284e-05,
+      "loss": 0.5708,
+      "step": 1150
+    },
+    {
+      "epoch": 2.027996500437445,
+      "grad_norm": 0.6953125,
+      "learning_rate": 3.725150360828537e-05,
+      "loss": 0.5258,
+      "step": 1160
+    },
+    {
+      "epoch": 2.0454943132108485,
+      "grad_norm": 0.609375,
+      "learning_rate": 3.7197027181732556e-05,
+      "loss": 0.5357,
+      "step": 1170
+    },
+    {
+      "epoch": 2.062992125984252,
+      "grad_norm": 0.57421875,
+      "learning_rate": 3.714206170737003e-05,
+      "loss": 0.5301,
+      "step": 1180
+    },
+    {
+      "epoch": 2.080489938757655,
+      "grad_norm": 0.640625,
+      "learning_rate": 3.708660895401381e-05,
+      "loss": 0.5334,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0979877515310585,
+      "grad_norm": 0.6015625,
+      "learning_rate": 3.703067070616076e-05,
+      "loss": 0.5308,
+      "step": 1200
+    },
+    {
+      "epoch": 2.115485564304462,
+      "grad_norm": 0.53515625,
+      "learning_rate": 3.697424876393122e-05,
+      "loss": 0.5243,
+      "step": 1210
+    },
+    {
+      "epoch": 2.1329833770778652,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.6917344943011043e-05,
+      "loss": 0.5139,
+      "step": 1220
+    },
+    {
+      "epoch": 2.1504811898512686,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.685996107459317e-05,
+      "loss": 0.533,
+      "step": 1230
+    },
+    {
+      "epoch": 2.167979002624672,
+      "grad_norm": 0.65625,
+      "learning_rate": 3.680209900531872e-05,
+      "loss": 0.5098,
+      "step": 1240
+    },
+    {
+      "epoch": 2.1854768153980753,
+      "grad_norm": 0.6015625,
+      "learning_rate": 3.6743760597217536e-05,
+      "loss": 0.5318,
+      "step": 1250
+    },
+    {
+      "epoch": 2.2029746281714786,
+      "grad_norm": 0.59375,
+      "learning_rate": 3.668494772764828e-05,
+      "loss": 0.5223,
+      "step": 1260
+    },
+    {
+      "epoch": 2.220472440944882,
+      "grad_norm": 0.59765625,
+      "learning_rate": 3.662566228923805e-05,
+      "loss": 0.5241,
+      "step": 1270
+    },
+    {
+      "epoch": 2.2379702537182853,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.656590618982138e-05,
+      "loss": 0.5249,
+      "step": 1280
+    },
+    {
+      "epoch": 2.2554680664916886,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.650568135237897e-05,
+      "loss": 0.5412,
+      "step": 1290
+    },
+    {
+      "epoch": 2.272965879265092,
+      "grad_norm": 0.66796875,
+      "learning_rate": 3.644498971497569e-05,
+      "loss": 0.53,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2904636920384953,
+      "grad_norm": 0.67578125,
+      "learning_rate": 3.63838332306983e-05,
+      "loss": 0.5382,
+      "step": 1310
+    },
+    {
+      "epoch": 2.3079615048118987,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.6322213867592536e-05,
+      "loss": 0.5278,
+      "step": 1320
+    },
+    {
+      "epoch": 2.325459317585302,
+      "grad_norm": 0.98828125,
+      "learning_rate": 3.626013360859982e-05,
+      "loss": 0.5409,
+      "step": 1330
+    },
+    {
+      "epoch": 2.3429571303587053,
+      "grad_norm": 0.64453125,
+      "learning_rate": 3.619759445149341e-05,
+      "loss": 0.5277,
+      "step": 1340
+    },
+    {
+      "epoch": 2.3604549431321082,
+      "grad_norm": 0.55078125,
+      "learning_rate": 3.613459840881415e-05,
+      "loss": 0.5344,
+      "step": 1350
+    },
+    {
+      "epoch": 2.377952755905512,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.607114750780568e-05,
+      "loss": 0.5364,
+      "step": 1360
+    },
+    {
+      "epoch": 2.395450568678915,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.6007243790349205e-05,
+      "loss": 0.5238,
+      "step": 1370
+    },
+    {
+      "epoch": 2.4129483814523183,
+      "grad_norm": 0.57421875,
+      "learning_rate": 3.594288931289778e-05,
+      "loss": 0.5322,
+      "step": 1380
+    },
+    {
+      "epoch": 2.4304461942257216,
+      "grad_norm": 0.59765625,
+      "learning_rate": 3.587808614641015e-05,
+      "loss": 0.5418,
+      "step": 1390
+    },
+    {
+      "epoch": 2.447944006999125,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.581283637628409e-05,
+      "loss": 0.537,
+      "step": 1400
+    },
+    {
+      "epoch": 2.4654418197725283,
+      "grad_norm": 0.609375,
+      "learning_rate": 3.574714210228929e-05,
+      "loss": 0.5286,
+      "step": 1410
+    },
+    {
+      "epoch": 2.4829396325459316,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.5681005438499795e-05,
+      "loss": 0.5196,
+      "step": 1420
+    },
+    {
+      "epoch": 2.500437445319335,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.561442851322599e-05,
+      "loss": 0.5559,
+      "step": 1430
+    },
+    {
+      "epoch": 2.5179352580927383,
+      "grad_norm": 0.59375,
+      "learning_rate": 3.554741346894606e-05,
+      "loss": 0.5325,
+      "step": 1440
+    },
+    {
+      "epoch": 2.5354330708661417,
+      "grad_norm": 0.578125,
+      "learning_rate": 3.5479962462237116e-05,
+      "loss": 0.5368,
+      "step": 1450
+    },
+    {
+      "epoch": 2.552930883639545,
+      "grad_norm": 0.59375,
+      "learning_rate": 3.541207766370572e-05,
+      "loss": 0.5368,
+      "step": 1460
+    },
+    {
+      "epoch": 2.5704286964129484,
+      "grad_norm": 0.73046875,
+      "learning_rate": 3.534376125791807e-05,
+      "loss": 0.5385,
+      "step": 1470
+    },
+    {
+      "epoch": 2.5879265091863517,
+      "grad_norm": 0.54296875,
+      "learning_rate": 3.527501544332972e-05,
+      "loss": 0.5365,
+      "step": 1480
+    },
+    {
+      "epoch": 2.605424321959755,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.520584243221479e-05,
+      "loss": 0.5439,
+      "step": 1490
+    },
+    {
+      "epoch": 2.6229221347331584,
+      "grad_norm": 0.5390625,
+      "learning_rate": 3.5136244450594814e-05,
+      "loss": 0.5214,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6404199475065617,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.506622373816706e-05,
+      "loss": 0.5334,
+      "step": 1510
+    },
+    {
+      "epoch": 2.657917760279965,
+      "grad_norm": 0.55859375,
+      "learning_rate": 3.499578254823249e-05,
+      "loss": 0.544,
+      "step": 1520
+    },
+    {
+      "epoch": 2.6754155730533684,
+      "grad_norm": 0.54296875,
+      "learning_rate": 3.4924923147623265e-05,
+      "loss": 0.5254,
+      "step": 1530
+    },
+    {
+      "epoch": 2.6929133858267718,
+      "grad_norm": 0.71484375,
+      "learning_rate": 3.485364781662974e-05,
+      "loss": 0.536,
+      "step": 1540
+    },
+    {
+      "epoch": 2.710411198600175,
+      "grad_norm": 0.66796875,
+      "learning_rate": 3.478195884892712e-05,
+      "loss": 0.5471,
+      "step": 1550
+    },
+    {
+      "epoch": 2.7279090113735784,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.4709858551501664e-05,
+      "loss": 0.5235,
+      "step": 1560
+    },
+    {
+      "epoch": 2.745406824146982,
+      "grad_norm": 0.58203125,
+      "learning_rate": 3.463734924457638e-05,
+      "loss": 0.5486,
+      "step": 1570
+    },
+    {
+      "epoch": 2.7629046369203847,
+      "grad_norm": 0.5625,
+      "learning_rate": 3.4564433261536446e-05,
+      "loss": 0.5218,
+      "step": 1580
+    },
+    {
+      "epoch": 2.7804024496937885,
+      "grad_norm": 0.5703125,
+      "learning_rate": 3.449111294885407e-05,
+      "loss": 0.5256,
+      "step": 1590
+    },
+    {
+      "epoch": 2.7979002624671914,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.4417390666012966e-05,
+      "loss": 0.5296,
+      "step": 1600
+    },
+    {
+      "epoch": 2.815398075240595,
+      "grad_norm": 0.57421875,
+      "learning_rate": 3.434326878543246e-05,
+      "loss": 0.5365,
+      "step": 1610
+    },
+    {
+      "epoch": 2.832895888013998,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.426874969239113e-05,
+      "loss": 0.5226,
+      "step": 1620
+    },
+    {
+      "epoch": 2.850393700787402,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.419383578495005e-05,
+      "loss": 0.5351,
+      "step": 1630
+    },
+    {
+      "epoch": 2.8678915135608047,
+      "grad_norm": 0.625,
+      "learning_rate": 3.411852947387559e-05,
+      "loss": 0.5297,
+      "step": 1640
+    },
+    {
+      "epoch": 2.885389326334208,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.40428331825619e-05,
+      "loss": 0.5248,
+      "step": 1650
+    },
+    {
+      "epoch": 2.9028871391076114,
+      "grad_norm": 0.60546875,
+      "learning_rate": 3.3966749346952856e-05,
+      "loss": 0.5327,
+      "step": 1660
+    },
+    {
+      "epoch": 2.9203849518810148,
+      "grad_norm": 0.5546875,
+      "learning_rate": 3.389028041546372e-05,
+      "loss": 0.5315,
+      "step": 1670
+    },
+    {
+      "epoch": 2.937882764654418,
+      "grad_norm": 0.6015625,
+      "learning_rate": 3.381342884890231e-05,
+      "loss": 0.5327,
+      "step": 1680
+    },
+    {
+      "epoch": 2.9553805774278215,
+      "grad_norm": 0.60546875,
+      "learning_rate": 3.373619712038985e-05,
+      "loss": 0.5399,
+      "step": 1690
+    },
+    {
+      "epoch": 2.972878390201225,
+      "grad_norm": 0.60546875,
+      "learning_rate": 3.365858771528135e-05,
+      "loss": 0.5307,
+      "step": 1700
+    },
+    {
+      "epoch": 2.990376202974628,
+      "grad_norm": 0.5859375,
+      "learning_rate": 3.358060313108564e-05,
+      "loss": 0.5427,
+      "step": 1710
+    },
+    {
+      "epoch": 3.0069991251093615,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.3502245877384986e-05,
+      "loss": 0.4888,
+      "step": 1720
+    },
+    {
+      "epoch": 3.024496937882765,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.3423518475754376e-05,
+      "loss": 0.4435,
+      "step": 1730
+    },
+    {
+      "epoch": 3.041994750656168,
+      "grad_norm": 0.71875,
+      "learning_rate": 3.33444234596803e-05,
+      "loss": 0.429,
+      "step": 1740
+    },
+    {
+      "epoch": 3.059492563429571,
+      "grad_norm": 0.67578125,
+      "learning_rate": 3.326496337447928e-05,
+      "loss": 0.437,
+      "step": 1750
+    },
+    {
+      "epoch": 3.0769903762029744,
+      "grad_norm": 0.65625,
+      "learning_rate": 3.3185140777215956e-05,
+      "loss": 0.4387,
+      "step": 1760
+    },
+    {
+      "epoch": 3.094488188976378,
+      "grad_norm": 0.7109375,
+      "learning_rate": 3.3104958236620755e-05,
+      "loss": 0.4211,
+      "step": 1770
+    },
+    {
+      "epoch": 3.111986001749781,
+      "grad_norm": 0.58203125,
+      "learning_rate": 3.302441833300728e-05,
+      "loss": 0.4265,
+      "step": 1780
+    },
+    {
+      "epoch": 3.1294838145231845,
+      "grad_norm": 0.640625,
+      "learning_rate": 3.2943523658189246e-05,
+      "loss": 0.438,
+      "step": 1790
+    },
+    {
+      "epoch": 3.146981627296588,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.286227681539708e-05,
+      "loss": 0.4379,
+      "step": 1800
+    },
+    {
+      "epoch": 3.164479440069991,
+      "grad_norm": 0.7109375,
+      "learning_rate": 3.278068041919415e-05,
+      "loss": 0.4284,
+      "step": 1810
+    },
+    {
+      "epoch": 3.1819772528433945,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.2698737095392593e-05,
+      "loss": 0.4299,
+      "step": 1820
+    },
+    {
+      "epoch": 3.199475065616798,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.261644948096891e-05,
+      "loss": 0.4351,
+      "step": 1830
+    },
+    {
+      "epoch": 3.216972878390201,
+      "grad_norm": 0.62890625,
+      "learning_rate": 3.2533820223978996e-05,
+      "loss": 0.4336,
+      "step": 1840
+    },
+    {
+      "epoch": 3.2344706911636045,
+      "grad_norm": 0.63671875,
+      "learning_rate": 3.245085198347298e-05,
+      "loss": 0.4376,
+      "step": 1850
+    },
+    {
+      "epoch": 3.251968503937008,
+      "grad_norm": 0.56640625,
+      "learning_rate": 3.236754742940965e-05,
+      "loss": 0.4461,
+      "step": 1860
+    },
+    {
+      "epoch": 3.269466316710411,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.228390924257053e-05,
+      "loss": 0.4472,
+      "step": 1870
+    },
+    {
+      "epoch": 3.2869641294838146,
+      "grad_norm": 0.68359375,
+      "learning_rate": 3.2199940114473615e-05,
+      "loss": 0.4404,
+      "step": 1880
+    },
+    {
+      "epoch": 3.304461942257218,
+      "grad_norm": 0.671875,
+      "learning_rate": 3.211564274728676e-05,
+      "loss": 0.4357,
+      "step": 1890
+    },
+    {
+      "epoch": 3.3219597550306212,
+      "grad_norm": 0.640625,
+      "learning_rate": 3.203101985374069e-05,
+      "loss": 0.4405,
+      "step": 1900
+    },
+    {
+      "epoch": 3.3394575678040246,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.194607415704174e-05,
+      "loss": 0.4524,
+      "step": 1910
+    },
+    {
+      "epoch": 3.356955380577428,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.186080839078423e-05,
+      "loss": 0.4311,
+      "step": 1920
+    },
+    {
+      "epoch": 3.3744531933508313,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.177522529886244e-05,
+      "loss": 0.4257,
+      "step": 1930
+    },
+    {
+      "epoch": 3.3919510061242346,
+      "grad_norm": 0.87109375,
+      "learning_rate": 3.1689327635382374e-05,
+      "loss": 0.4305,
+      "step": 1940
+    },
+    {
+      "epoch": 3.409448818897638,
+      "grad_norm": 0.71875,
+      "learning_rate": 3.160311816457309e-05,
+      "loss": 0.4473,
+      "step": 1950
+    },
+    {
+      "epoch": 3.4269466316710413,
+      "grad_norm": 0.63671875,
+      "learning_rate": 3.151659966069777e-05,
+      "loss": 0.4543,
+      "step": 1960
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 0.59765625,
+      "learning_rate": 3.142977490796441e-05,
+      "loss": 0.4444,
+      "step": 1970
+    },
+    {
+      "epoch": 3.4619422572178475,
+      "grad_norm": 0.65625,
+      "learning_rate": 3.134264670043627e-05,
+      "loss": 0.4543,
+      "step": 1980
+    },
+    {
+      "epoch": 3.4794400699912513,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.125521784194192e-05,
+      "loss": 0.4433,
+      "step": 1990
+    },
+    {
+      "epoch": 3.4969378827646542,
+      "grad_norm": 0.625,
+      "learning_rate": 3.1167491145985035e-05,
+      "loss": 0.4403,
+      "step": 2000
+    },
+    {
+      "epoch": 3.514435695538058,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.107946943565384e-05,
+      "loss": 0.4516,
+      "step": 2010
+    },
+    {
+      "epoch": 3.531933508311461,
+      "grad_norm": 0.66015625,
+      "learning_rate": 3.099115554353027e-05,
+      "loss": 0.4326,
+      "step": 2020
+    },
+    {
+      "epoch": 3.5494313210848643,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.090255231159881e-05,
+      "loss": 0.4309,
+      "step": 2030
+    },
+    {
+      "epoch": 3.5669291338582676,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.081366259115504e-05,
+      "loss": 0.4328,
+      "step": 2040
+    },
+    {
+      "epoch": 3.584426946631671,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.072448924271389e-05,
+      "loss": 0.4333,
+      "step": 2050
+    },
+    {
+      "epoch": 3.6019247594050743,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.063503513591758e-05,
+      "loss": 0.4518,
+      "step": 2060
+    },
+    {
+      "epoch": 3.6194225721784776,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.0545303149443265e-05,
+      "loss": 0.4383,
+      "step": 2070
+    },
+    {
+      "epoch": 3.636920384951881,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.0455296170910404e-05,
+      "loss": 0.436,
+      "step": 2080
+    },
+    {
+      "epoch": 3.6544181977252843,
+      "grad_norm": 0.671875,
+      "learning_rate": 3.0365017096787834e-05,
+      "loss": 0.4363,
+      "step": 2090
+    },
+    {
+      "epoch": 3.6719160104986877,
+      "grad_norm": 0.6484375,
+      "learning_rate": 3.0274468832300576e-05,
+      "loss": 0.4463,
+      "step": 2100
+    },
+    {
+      "epoch": 3.689413823272091,
+      "grad_norm": 0.609375,
+      "learning_rate": 3.0183654291336313e-05,
+      "loss": 0.4533,
+      "step": 2110
+    },
+    {
+      "epoch": 3.7069116360454943,
+      "grad_norm": 0.6796875,
+      "learning_rate": 3.009257639635164e-05,
+      "loss": 0.4255,
+      "step": 2120
+    },
+    {
+      "epoch": 3.7244094488188977,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.0001238078278022e-05,
+      "loss": 0.4452,
+      "step": 2130
+    },
+    {
+      "epoch": 3.741907261592301,
+      "grad_norm": 0.625,
+      "learning_rate": 2.990964227642746e-05,
+      "loss": 0.4344,
+      "step": 2140
+    },
+    {
+      "epoch": 3.7594050743657044,
+      "grad_norm": 0.70703125,
+      "learning_rate": 2.9817791938397902e-05,
+      "loss": 0.4327,
+      "step": 2150
+    },
+    {
+      "epoch": 3.7769028871391077,
+      "grad_norm": 0.66015625,
+      "learning_rate": 2.9725690019978422e-05,
+      "loss": 0.4461,
+      "step": 2160
+    },
+    {
+      "epoch": 3.794400699912511,
+      "grad_norm": 0.6640625,
+      "learning_rate": 2.9633339485054037e-05,
+      "loss": 0.443,
+      "step": 2170
+    },
+    {
+      "epoch": 3.8118985126859144,
+      "grad_norm": 0.6171875,
+      "learning_rate": 2.9540743305510406e-05,
+      "loss": 0.4387,
+      "step": 2180
+    },
+    {
+      "epoch": 3.8293963254593177,
+      "grad_norm": 0.703125,
+      "learning_rate": 2.9447904461138114e-05,
+      "loss": 0.4355,
+      "step": 2190
+    },
+    {
+      "epoch": 3.846894138232721,
+      "grad_norm": 0.625,
+      "learning_rate": 2.9354825939536854e-05,
+      "loss": 0.4425,
+      "step": 2200
+    },
+    {
+      "epoch": 3.864391951006124,
+      "grad_norm": 0.6171875,
+      "learning_rate": 2.9261510736019222e-05,
+      "loss": 0.4518,
+      "step": 2210
+    },
+    {
+      "epoch": 3.8818897637795278,
+      "grad_norm": 0.6171875,
+      "learning_rate": 2.9167961853514368e-05,
+      "loss": 0.4552,
+      "step": 2220
+    },
+    {
+      "epoch": 3.8993875765529307,
+      "grad_norm": 0.71875,
+      "learning_rate": 2.9074182302471347e-05,
+      "loss": 0.4506,
+      "step": 2230
+    },
+    {
+      "epoch": 3.9168853893263345,
+      "grad_norm": 0.703125,
+      "learning_rate": 2.898017510076224e-05,
+      "loss": 0.4388,
+      "step": 2240
+    },
+    {
+      "epoch": 3.9343832020997374,
+      "grad_norm": 0.671875,
+      "learning_rate": 2.8885943273585037e-05,
+      "loss": 0.4373,
+      "step": 2250
+    },
+    {
+      "epoch": 3.9518810148731407,
+      "grad_norm": 0.61328125,
+      "learning_rate": 2.8791489853366284e-05,
+      "loss": 0.4359,
+      "step": 2260
+    },
+    {
+      "epoch": 3.969378827646544,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.8696817879663515e-05,
+      "loss": 0.4538,
+      "step": 2270
+    },
+    {
+      "epoch": 3.9868766404199474,
+      "grad_norm": 0.73046875,
+      "learning_rate": 2.8601930399067393e-05,
+      "loss": 0.4394,
+      "step": 2280
+    },
+    {
+      "epoch": 4.003499562554681,
+      "grad_norm": 0.62109375,
+      "learning_rate": 2.8506830465103723e-05,
+      "loss": 0.4332,
+      "step": 2290
+    },
+    {
+      "epoch": 4.020997375328084,
+      "grad_norm": 0.76953125,
+      "learning_rate": 2.8411521138135154e-05,
+      "loss": 0.3484,
+      "step": 2300
+    },
+    {
+      "epoch": 4.038495188101487,
+      "grad_norm": 0.6015625,
+      "learning_rate": 2.8316005485262717e-05,
+      "loss": 0.3652,
+      "step": 2310
+    },
+    {
+      "epoch": 4.05599300087489,
+      "grad_norm": 0.76171875,
+      "learning_rate": 2.8220286580227093e-05,
+      "loss": 0.3603,
+      "step": 2320
+    },
+    {
+      "epoch": 4.073490813648294,
+      "grad_norm": 0.69921875,
+      "learning_rate": 2.8124367503309736e-05,
+      "loss": 0.3401,
+      "step": 2330
+    },
+    {
+      "epoch": 4.090988626421697,
+      "grad_norm": 0.71875,
+      "learning_rate": 2.802825134123371e-05,
+      "loss": 0.3446,
+      "step": 2340
+    },
+    {
+      "epoch": 4.108486439195101,
+      "grad_norm": 0.7265625,
+      "learning_rate": 2.7931941187064402e-05,
+      "loss": 0.3732,
+      "step": 2350
+    },
+    {
+      "epoch": 4.125984251968504,
+      "grad_norm": 0.66015625,
+      "learning_rate": 2.783544014010993e-05,
+      "loss": 0.3567,
+      "step": 2360
+    },
+    {
+      "epoch": 4.1434820647419075,
+      "grad_norm": 0.765625,
+      "learning_rate": 2.773875130582146e-05,
+      "loss": 0.3575,
+      "step": 2370
+    },
+    {
+      "epoch": 4.16097987751531,
+      "grad_norm": 0.7265625,
+      "learning_rate": 2.764187779569324e-05,
+      "loss": 0.36,
+      "step": 2380
+    },
+    {
+      "epoch": 4.178477690288714,
+      "grad_norm": 0.6875,
+      "learning_rate": 2.7544822727162475e-05,
+      "loss": 0.345,
+      "step": 2390
+    },
+    {
+      "epoch": 4.195975503062117,
+      "grad_norm": 0.6953125,
+      "learning_rate": 2.7447589223509004e-05,
+      "loss": 0.3614,
+      "step": 2400
+    },
+    {
+      "epoch": 4.213473315835521,
+      "grad_norm": 0.6171875,
+      "learning_rate": 2.7350180413754798e-05,
+      "loss": 0.3584,
+      "step": 2410
+    },
+    {
+      "epoch": 4.230971128608924,
+      "grad_norm": 0.68359375,
+      "learning_rate": 2.7252599432563278e-05,
+      "loss": 0.3567,
+      "step": 2420
+    },
+    {
+      "epoch": 4.248468941382328,
+      "grad_norm": 0.66796875,
+      "learning_rate": 2.7154849420138405e-05,
+      "loss": 0.3513,
+      "step": 2430
+    },
+    {
+      "epoch": 4.2659667541557305,
+      "grad_norm": 0.75390625,
+      "learning_rate": 2.7056933522123677e-05,
+      "loss": 0.3572,
+      "step": 2440
+    },
+    {
+      "epoch": 4.283464566929134,
+      "grad_norm": 0.69921875,
+      "learning_rate": 2.695885488950083e-05,
+      "loss": 0.3461,
+      "step": 2450
+    },
+    {
+      "epoch": 4.300962379702537,
+      "grad_norm": 0.76171875,
+      "learning_rate": 2.686061667848852e-05,
+      "loss": 0.3534,
+      "step": 2460
+    },
+    {
+      "epoch": 4.318460192475941,
+      "grad_norm": 0.7578125,
+      "learning_rate": 2.67622220504407e-05,
+      "loss": 0.3608,
+      "step": 2470
+    },
+    {
+      "epoch": 4.335958005249344,
+      "grad_norm": 0.7578125,
+      "learning_rate": 2.6663674171744887e-05,
+      "loss": 0.3549,
+      "step": 2480
+    },
+    {
+      "epoch": 4.353455818022747,
+      "grad_norm": 0.69921875,
+      "learning_rate": 2.6564976213720292e-05,
+      "loss": 0.3533,
+      "step": 2490
+    },
+    {
+      "epoch": 4.3709536307961505,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.646613135251576e-05,
+      "loss": 0.3542,
+      "step": 2500
+    },
+    {
+      "epoch": 4.388451443569553,
+      "grad_norm": 0.859375,
+      "learning_rate": 2.6367142769007533e-05,
+      "loss": 0.3426,
+      "step": 2510
+    },
+    {
+      "epoch": 4.405949256342957,
+      "grad_norm": 0.66796875,
+      "learning_rate": 2.626801364869693e-05,
+      "loss": 0.3511,
+      "step": 2520
+    },
+    {
+      "epoch": 4.42344706911636,
+      "grad_norm": 0.72265625,
+      "learning_rate": 2.6168747181607795e-05,
+      "loss": 0.3528,
+      "step": 2530
+    },
+    {
+      "epoch": 4.440944881889764,
+      "grad_norm": 0.73046875,
+      "learning_rate": 2.606934656218386e-05,
+      "loss": 0.3491,
+      "step": 2540
+    },
+    {
+      "epoch": 4.458442694663167,
+      "grad_norm": 0.7734375,
+      "learning_rate": 2.5969814989185965e-05,
+      "loss": 0.3563,
+      "step": 2550
+    },
+    {
+      "epoch": 4.475940507436571,
+      "grad_norm": 0.71875,
+      "learning_rate": 2.5870155665589066e-05,
+      "loss": 0.3603,
+      "step": 2560
+    },
+    {
+      "epoch": 4.4934383202099735,
+      "grad_norm": 0.7265625,
+      "learning_rate": 2.5770371798479234e-05,
+      "loss": 0.3525,
+      "step": 2570
+    },
+    {
+      "epoch": 4.510936132983377,
+      "grad_norm": 0.734375,
+      "learning_rate": 2.5670466598950385e-05,
+      "loss": 0.3487,
+      "step": 2580
+    },
+    {
+      "epoch": 4.52843394575678,
+      "grad_norm": 0.71875,
+      "learning_rate": 2.5570443282000974e-05,
+      "loss": 0.3606,
+      "step": 2590
+    },
+    {
+      "epoch": 4.545931758530184,
+      "grad_norm": 0.73046875,
+      "learning_rate": 2.547030506643055e-05,
+      "loss": 0.3569,
+      "step": 2600
+    },
+    {
+      "epoch": 4.563429571303587,
+      "grad_norm": 0.74609375,
+      "learning_rate": 2.5370055174736144e-05,
+      "loss": 0.3509,
+      "step": 2610
+    },
+    {
+      "epoch": 4.580927384076991,
+      "grad_norm": 0.6328125,
+      "learning_rate": 2.5269696833008577e-05,
+      "loss": 0.3549,
+      "step": 2620
+    },
+    {
+      "epoch": 4.5984251968503935,
+      "grad_norm": 0.7265625,
+      "learning_rate": 2.516923327082865e-05,
+      "loss": 0.3521,
+      "step": 2630
+    },
+    {
+      "epoch": 4.615923009623797,
+      "grad_norm": 0.671875,
+      "learning_rate": 2.5068667721163213e-05,
+      "loss": 0.3549,
+      "step": 2640
+    },
+    {
+      "epoch": 4.6334208223972,
+      "grad_norm": 0.7734375,
+      "learning_rate": 2.496800342026112e-05,
+      "loss": 0.3448,
+      "step": 2650
+    },
+    {
+      "epoch": 4.650918635170604,
+      "grad_norm": 0.6640625,
+      "learning_rate": 2.4867243607549085e-05,
+      "loss": 0.3517,
+      "step": 2660
+    },
+    {
+      "epoch": 4.668416447944007,
+      "grad_norm": 0.6953125,
+      "learning_rate": 2.4766391525527436e-05,
+      "loss": 0.3548,
+      "step": 2670
+    },
+    {
+      "epoch": 4.685914260717411,
+      "grad_norm": 0.65234375,
+      "learning_rate": 2.4665450419665783e-05,
+      "loss": 0.3605,
+      "step": 2680
+    },
+    {
+      "epoch": 4.703412073490814,
+      "grad_norm": 0.80078125,
+      "learning_rate": 2.4564423538298567e-05,
+      "loss": 0.3565,
+      "step": 2690
+    },
+    {
+      "epoch": 4.7209098862642165,
+      "grad_norm": 0.69921875,
+      "learning_rate": 2.4463314132520522e-05,
+      "loss": 0.344,
+      "step": 2700
+    },
+    {
+      "epoch": 4.73840769903762,
+      "grad_norm": 0.68359375,
+      "learning_rate": 2.4362125456082058e-05,
+      "loss": 0.3496,
+      "step": 2710
+    },
+    {
+      "epoch": 4.755905511811024,
+      "grad_norm": 0.8125,
+      "learning_rate": 2.426086076528455e-05,
+      "loss": 0.3584,
+      "step": 2720
+    },
+    {
+      "epoch": 4.773403324584427,
+      "grad_norm": 0.6875,
+      "learning_rate": 2.4159523318875562e-05,
+      "loss": 0.3627,
+      "step": 2730
+    },
+    {
+      "epoch": 4.79090113735783,
+      "grad_norm": 0.7734375,
+      "learning_rate": 2.405811637794396e-05,
+      "loss": 0.3585,
+      "step": 2740
+    },
+    {
+      "epoch": 4.808398950131234,
+      "grad_norm": 0.73046875,
+      "learning_rate": 2.3956643205814994e-05,
+      "loss": 0.3651,
+      "step": 2750
+    },
+    {
+      "epoch": 4.8258967629046365,
+      "grad_norm": 0.66796875,
+      "learning_rate": 2.385510706794524e-05,
+      "loss": 0.3537,
+      "step": 2760
+    },
+    {
+      "epoch": 4.84339457567804,
+      "grad_norm": 0.7734375,
+      "learning_rate": 2.375351123181756e-05,
+      "loss": 0.3476,
+      "step": 2770
+    },
+    {
+      "epoch": 4.860892388451443,
+      "grad_norm": 0.75,
+      "learning_rate": 2.365185896683595e-05,
+      "loss": 0.3416,
+      "step": 2780
+    },
+    {
+      "epoch": 4.878390201224847,
+      "grad_norm": 0.7578125,
+      "learning_rate": 2.3550153544220273e-05,
+      "loss": 0.3569,
+      "step": 2790
+    },
+    {
+      "epoch": 4.89588801399825,
+      "grad_norm": 0.69921875,
+      "learning_rate": 2.3448398236901073e-05,
+      "loss": 0.3502,
+      "step": 2800
+    },
+    {
+      "epoch": 4.913385826771654,
+      "grad_norm": 0.77734375,
+      "learning_rate": 2.3346596319414173e-05,
+      "loss": 0.3538,
+      "step": 2810
+    },
+    {
+      "epoch": 4.930883639545057,
+      "grad_norm": 0.67578125,
+      "learning_rate": 2.3244751067795366e-05,
+      "loss": 0.3635,
+      "step": 2820
+    },
+    {
+      "epoch": 4.94838145231846,
+      "grad_norm": 0.71484375,
+      "learning_rate": 2.314286575947494e-05,
+      "loss": 0.3567,
+      "step": 2830
+    },
+    {
+      "epoch": 4.965879265091863,
+      "grad_norm": 0.8515625,
+      "learning_rate": 2.304094367317223e-05,
+      "loss": 0.3293,
+      "step": 2840
+    },
+    {
+      "epoch": 4.983377077865267,
+      "grad_norm": 0.7421875,
+      "learning_rate": 2.293898808879011e-05,
+      "loss": 0.3656,
+      "step": 2850
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.0546875,
+      "learning_rate": 2.2837002287309426e-05,
+      "loss": 0.3726,
+      "step": 2860
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5710,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.691223286459776e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cffae204d474b25399afa15ed455f6c32a372d57de457be86739cb8a364a1e9
+size 5688