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 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.50.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1e6f93af978ca3e0da131470358ad39b6f2d6152a77f417f8691089cc04032
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0821f5c163f970b2799e8ab48553799fa758284a36fcb8a96ce81c099b1117ba
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950d04c4de4edd3a11ae7c76a5655b66f4d2a42f687f133fddda50f26250eccd
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df9f9d00e3bd915f67900485559d6d04f9d67f6f05c9f2f543e1e8dd532b455
+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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02643f00207dfc5ed248992486bde04314c21dca556bf65ce520690962b8db63
+size 11422965

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 32000,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1714 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 42.849557522123895,
+  "eval_steps": 5000,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17699115044247787,
+      "grad_norm": 3.7271776676935064,
+      "learning_rate": 2.785515320334262e-07,
+      "loss": 0.8908,
+      "step": 10
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 3.670737329981903,
+      "learning_rate": 5.571030640668524e-07,
+      "loss": 0.9077,
+      "step": 20
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "grad_norm": 2.5209641167492456,
+      "learning_rate": 8.356545961002786e-07,
+      "loss": 0.9111,
+      "step": 30
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 1.7589966584950831,
+      "learning_rate": 1.1142061281337048e-06,
+      "loss": 0.851,
+      "step": 40
+    },
+    {
+      "epoch": 0.8849557522123894,
+      "grad_norm": 0.9269797048205026,
+      "learning_rate": 1.392757660167131e-06,
+      "loss": 0.7817,
+      "step": 50
+    },
+    {
+      "epoch": 1.0707964601769913,
+      "grad_norm": 0.7581016735069944,
+      "learning_rate": 1.6713091922005572e-06,
+      "loss": 0.8326,
+      "step": 60
+    },
+    {
+      "epoch": 1.247787610619469,
+      "grad_norm": 0.5609083123432701,
+      "learning_rate": 1.9498607242339835e-06,
+      "loss": 0.6992,
+      "step": 70
+    },
+    {
+      "epoch": 1.424778761061947,
+      "grad_norm": 0.44823390625971854,
+      "learning_rate": 2.2284122562674097e-06,
+      "loss": 0.6624,
+      "step": 80
+    },
+    {
+      "epoch": 1.6017699115044248,
+      "grad_norm": 0.42125861316536894,
+      "learning_rate": 2.506963788300836e-06,
+      "loss": 0.6426,
+      "step": 90
+    },
+    {
+      "epoch": 1.7787610619469025,
+      "grad_norm": 0.35815370826987114,
+      "learning_rate": 2.785515320334262e-06,
+      "loss": 0.6128,
+      "step": 100
+    },
+    {
+      "epoch": 1.9557522123893807,
+      "grad_norm": 0.4577270620590399,
+      "learning_rate": 3.064066852367688e-06,
+      "loss": 0.6093,
+      "step": 110
+    },
+    {
+      "epoch": 2.1415929203539825,
+      "grad_norm": 0.34913913967622867,
+      "learning_rate": 3.3426183844011143e-06,
+      "loss": 0.6398,
+      "step": 120
+    },
+    {
+      "epoch": 2.3185840707964602,
+      "grad_norm": 0.38180716811578924,
+      "learning_rate": 3.6211699164345405e-06,
+      "loss": 0.5584,
+      "step": 130
+    },
+    {
+      "epoch": 2.495575221238938,
+      "grad_norm": 0.369627211366021,
+      "learning_rate": 3.899721448467967e-06,
+      "loss": 0.5709,
+      "step": 140
+    },
+    {
+      "epoch": 2.672566371681416,
+      "grad_norm": 0.3620391150396922,
+      "learning_rate": 4.178272980501394e-06,
+      "loss": 0.5367,
+      "step": 150
+    },
+    {
+      "epoch": 2.849557522123894,
+      "grad_norm": 0.3783946938245177,
+      "learning_rate": 4.456824512534819e-06,
+      "loss": 0.5493,
+      "step": 160
+    },
+    {
+      "epoch": 3.0353982300884956,
+      "grad_norm": 0.3583783631314861,
+      "learning_rate": 4.735376044568246e-06,
+      "loss": 0.5843,
+      "step": 170
+    },
+    {
+      "epoch": 3.2123893805309733,
+      "grad_norm": 0.3828611223359035,
+      "learning_rate": 5.013927576601672e-06,
+      "loss": 0.515,
+      "step": 180
+    },
+    {
+      "epoch": 3.3893805309734515,
+      "grad_norm": 0.3834571050098614,
+      "learning_rate": 5.292479108635098e-06,
+      "loss": 0.5032,
+      "step": 190
+    },
+    {
+      "epoch": 3.566371681415929,
+      "grad_norm": 0.4546286324545871,
+      "learning_rate": 5.571030640668524e-06,
+      "loss": 0.5078,
+      "step": 200
+    },
+    {
+      "epoch": 3.7433628318584073,
+      "grad_norm": 0.35842721167138686,
+      "learning_rate": 5.849582172701951e-06,
+      "loss": 0.5045,
+      "step": 210
+    },
+    {
+      "epoch": 3.920353982300885,
+      "grad_norm": 0.3721307952764144,
+      "learning_rate": 6.128133704735376e-06,
+      "loss": 0.4889,
+      "step": 220
+    },
+    {
+      "epoch": 4.106194690265487,
+      "grad_norm": 0.3486734629862048,
+      "learning_rate": 6.406685236768803e-06,
+      "loss": 0.5256,
+      "step": 230
+    },
+    {
+      "epoch": 4.283185840707965,
+      "grad_norm": 0.35747967960235744,
+      "learning_rate": 6.685236768802229e-06,
+      "loss": 0.4733,
+      "step": 240
+    },
+    {
+      "epoch": 4.460176991150442,
+      "grad_norm": 0.3460872307860064,
+      "learning_rate": 6.963788300835655e-06,
+      "loss": 0.4636,
+      "step": 250
+    },
+    {
+      "epoch": 4.6371681415929205,
+      "grad_norm": 0.35573355527709355,
+      "learning_rate": 7.242339832869081e-06,
+      "loss": 0.4623,
+      "step": 260
+    },
+    {
+      "epoch": 4.814159292035399,
+      "grad_norm": 0.35666347655438735,
+      "learning_rate": 7.5208913649025075e-06,
+      "loss": 0.4602,
+      "step": 270
+    },
+    {
+      "epoch": 4.991150442477876,
+      "grad_norm": 0.3564250144229788,
+      "learning_rate": 7.799442896935934e-06,
+      "loss": 0.4542,
+      "step": 280
+    },
+    {
+      "epoch": 5.176991150442478,
+      "grad_norm": 0.4025504652700621,
+      "learning_rate": 8.07799442896936e-06,
+      "loss": 0.4659,
+      "step": 290
+    },
+    {
+      "epoch": 5.353982300884955,
+      "grad_norm": 0.5428520516662031,
+      "learning_rate": 8.356545961002787e-06,
+      "loss": 0.4285,
+      "step": 300
+    },
+    {
+      "epoch": 5.530973451327434,
+      "grad_norm": 0.3928994965730304,
+      "learning_rate": 8.635097493036211e-06,
+      "loss": 0.4226,
+      "step": 310
+    },
+    {
+      "epoch": 5.707964601769912,
+      "grad_norm": 0.3850485302130108,
+      "learning_rate": 8.913649025069639e-06,
+      "loss": 0.4148,
+      "step": 320
+    },
+    {
+      "epoch": 5.88495575221239,
+      "grad_norm": 0.37058941523915273,
+      "learning_rate": 9.192200557103064e-06,
+      "loss": 0.4285,
+      "step": 330
+    },
+    {
+      "epoch": 6.070796460176991,
+      "grad_norm": 0.41682139676536206,
+      "learning_rate": 9.470752089136492e-06,
+      "loss": 0.4465,
+      "step": 340
+    },
+    {
+      "epoch": 6.247787610619469,
+      "grad_norm": 0.3924739843860392,
+      "learning_rate": 9.749303621169918e-06,
+      "loss": 0.3838,
+      "step": 350
+    },
+    {
+      "epoch": 6.424778761061947,
+      "grad_norm": 0.35592567356404897,
+      "learning_rate": 9.9999976276417e-06,
+      "loss": 0.3893,
+      "step": 360
+    },
+    {
+      "epoch": 6.601769911504425,
+      "grad_norm": 0.4159187900771811,
+      "learning_rate": 9.999712947369595e-06,
+      "loss": 0.3803,
+      "step": 370
+    },
+    {
+      "epoch": 6.778761061946903,
+      "grad_norm": 0.3857300466302711,
+      "learning_rate": 9.998953826391322e-06,
+      "loss": 0.38,
+      "step": 380
+    },
+    {
+      "epoch": 6.95575221238938,
+      "grad_norm": 0.3886065884171291,
+      "learning_rate": 9.997720336742596e-06,
+      "loss": 0.376,
+      "step": 390
+    },
+    {
+      "epoch": 7.1415929203539825,
+      "grad_norm": 0.3475659029068151,
+      "learning_rate": 9.996012595473676e-06,
+      "loss": 0.3883,
+      "step": 400
+    },
+    {
+      "epoch": 7.31858407079646,
+      "grad_norm": 0.3540420584120781,
+      "learning_rate": 9.993830764638262e-06,
+      "loss": 0.3335,
+      "step": 410
+    },
+    {
+      "epoch": 7.495575221238938,
+      "grad_norm": 0.4449981740267561,
+      "learning_rate": 9.991175051278111e-06,
+      "loss": 0.3323,
+      "step": 420
+    },
+    {
+      "epoch": 7.672566371681416,
+      "grad_norm": 0.3696907704775234,
+      "learning_rate": 9.988045707403394e-06,
+      "loss": 0.3359,
+      "step": 430
+    },
+    {
+      "epoch": 7.849557522123893,
+      "grad_norm": 0.38034972332442196,
+      "learning_rate": 9.984443029968786e-06,
+      "loss": 0.3211,
+      "step": 440
+    },
+    {
+      "epoch": 8.035398230088495,
+      "grad_norm": 0.4056044711686268,
+      "learning_rate": 9.980367360845278e-06,
+      "loss": 0.3434,
+      "step": 450
+    },
+    {
+      "epoch": 8.212389380530974,
+      "grad_norm": 0.3627220637163369,
+      "learning_rate": 9.975819086787743e-06,
+      "loss": 0.2758,
+      "step": 460
+    },
+    {
+      "epoch": 8.389380530973451,
+      "grad_norm": 0.3775354605167603,
+      "learning_rate": 9.970798639398228e-06,
+      "loss": 0.2768,
+      "step": 470
+    },
+    {
+      "epoch": 8.56637168141593,
+      "grad_norm": 0.45650386261945936,
+      "learning_rate": 9.965306495085005e-06,
+      "loss": 0.2773,
+      "step": 480
+    },
+    {
+      "epoch": 8.743362831858407,
+      "grad_norm": 0.3307082905256443,
+      "learning_rate": 9.959343175017362e-06,
+      "loss": 0.2718,
+      "step": 490
+    },
+    {
+      "epoch": 8.920353982300885,
+      "grad_norm": 0.3563870745711318,
+      "learning_rate": 9.952909245076141e-06,
+      "loss": 0.2737,
+      "step": 500
+    },
+    {
+      "epoch": 9.106194690265486,
+      "grad_norm": 0.5312131657692304,
+      "learning_rate": 9.946005315800047e-06,
+      "loss": 0.259,
+      "step": 510
+    },
+    {
+      "epoch": 9.283185840707965,
+      "grad_norm": 0.3897340271825655,
+      "learning_rate": 9.93863204232771e-06,
+      "loss": 0.2069,
+      "step": 520
+    },
+    {
+      "epoch": 9.460176991150442,
+      "grad_norm": 0.4074984143767453,
+      "learning_rate": 9.930790124335511e-06,
+      "loss": 0.2071,
+      "step": 530
+    },
+    {
+      "epoch": 9.63716814159292,
+      "grad_norm": 0.4025232487404969,
+      "learning_rate": 9.922480305971193e-06,
+      "loss": 0.2098,
+      "step": 540
+    },
+    {
+      "epoch": 9.814159292035399,
+      "grad_norm": 0.40076309227670925,
+      "learning_rate": 9.91370337578325e-06,
+      "loss": 0.2206,
+      "step": 550
+    },
+    {
+      "epoch": 9.991150442477876,
+      "grad_norm": 0.41455073775483275,
+      "learning_rate": 9.904460166646084e-06,
+      "loss": 0.2127,
+      "step": 560
+    },
+    {
+      "epoch": 10.176991150442477,
+      "grad_norm": 0.5102932920719749,
+      "learning_rate": 9.894751555680988e-06,
+      "loss": 0.1734,
+      "step": 570
+    },
+    {
+      "epoch": 10.353982300884956,
+      "grad_norm": 0.4418337454980142,
+      "learning_rate": 9.884578464172901e-06,
+      "loss": 0.1449,
+      "step": 580
+    },
+    {
+      "epoch": 10.530973451327434,
+      "grad_norm": 0.4645857386852471,
+      "learning_rate": 9.873941857482988e-06,
+      "loss": 0.149,
+      "step": 590
+    },
+    {
+      "epoch": 10.70796460176991,
+      "grad_norm": 0.44701917165189714,
+      "learning_rate": 9.862842744957037e-06,
+      "loss": 0.1445,
+      "step": 600
+    },
+    {
+      "epoch": 10.88495575221239,
+      "grad_norm": 0.4403519944347269,
+      "learning_rate": 9.85128217982967e-06,
+      "loss": 0.154,
+      "step": 610
+    },
+    {
+      "epoch": 11.070796460176991,
+      "grad_norm": 0.5432759091413589,
+      "learning_rate": 9.8392612591244e-06,
+      "loss": 0.1399,
+      "step": 620
+    },
+    {
+      "epoch": 11.247787610619469,
+      "grad_norm": 0.5393334729442735,
+      "learning_rate": 9.826781123549542e-06,
+      "loss": 0.0932,
+      "step": 630
+    },
+    {
+      "epoch": 11.424778761061948,
+      "grad_norm": 0.48955527875730576,
+      "learning_rate": 9.813842957389953e-06,
+      "loss": 0.1005,
+      "step": 640
+    },
+    {
+      "epoch": 11.601769911504425,
+      "grad_norm": 0.48039084849076596,
+      "learning_rate": 9.800447988394657e-06,
+      "loss": 0.0971,
+      "step": 650
+    },
+    {
+      "epoch": 11.778761061946902,
+      "grad_norm": 0.4790835393900875,
+      "learning_rate": 9.786597487660336e-06,
+      "loss": 0.1004,
+      "step": 660
+    },
+    {
+      "epoch": 11.955752212389381,
+      "grad_norm": 0.4287760706346846,
+      "learning_rate": 9.772292769510718e-06,
+      "loss": 0.098,
+      "step": 670
+    },
+    {
+      "epoch": 12.141592920353983,
+      "grad_norm": 0.5206942431108207,
+      "learning_rate": 9.75753519137185e-06,
+      "loss": 0.078,
+      "step": 680
+    },
+    {
+      "epoch": 12.31858407079646,
+      "grad_norm": 0.5235873880865046,
+      "learning_rate": 9.742326153643285e-06,
+      "loss": 0.0607,
+      "step": 690
+    },
+    {
+      "epoch": 12.495575221238939,
+      "grad_norm": 0.37417943883916716,
+      "learning_rate": 9.726667099565202e-06,
+      "loss": 0.0589,
+      "step": 700
+    },
+    {
+      "epoch": 12.672566371681416,
+      "grad_norm": 0.46680212830420037,
+      "learning_rate": 9.710559515081446e-06,
+      "loss": 0.0602,
+      "step": 710
+    },
+    {
+      "epoch": 12.849557522123893,
+      "grad_norm": 0.44256818209773113,
+      "learning_rate": 9.69400492869852e-06,
+      "loss": 0.0614,
+      "step": 720
+    },
+    {
+      "epoch": 13.035398230088495,
+      "grad_norm": 0.3392248898765409,
+      "learning_rate": 9.677004911340539e-06,
+      "loss": 0.0603,
+      "step": 730
+    },
+    {
+      "epoch": 13.212389380530974,
+      "grad_norm": 0.5068038205049078,
+      "learning_rate": 9.659561076200173e-06,
+      "loss": 0.0376,
+      "step": 740
+    },
+    {
+      "epoch": 13.389380530973451,
+      "grad_norm": 0.3566307973050844,
+      "learning_rate": 9.64167507858554e-06,
+      "loss": 0.0358,
+      "step": 750
+    },
+    {
+      "epoch": 13.56637168141593,
+      "grad_norm": 0.4251538821475592,
+      "learning_rate": 9.62334861576315e-06,
+      "loss": 0.0358,
+      "step": 760
+    },
+    {
+      "epoch": 13.743362831858407,
+      "grad_norm": 0.3816800016697675,
+      "learning_rate": 9.604583426796837e-06,
+      "loss": 0.0373,
+      "step": 770
+    },
+    {
+      "epoch": 13.920353982300885,
+      "grad_norm": 0.372768545921348,
+      "learning_rate": 9.585381292382734e-06,
+      "loss": 0.036,
+      "step": 780
+    },
+    {
+      "epoch": 14.106194690265486,
+      "grad_norm": 0.41177583770525134,
+      "learning_rate": 9.565744034680291e-06,
+      "loss": 0.032,
+      "step": 790
+    },
+    {
+      "epoch": 14.283185840707965,
+      "grad_norm": 0.330859615956022,
+      "learning_rate": 9.545673517139376e-06,
+      "loss": 0.022,
+      "step": 800
+    },
+    {
+      "epoch": 14.460176991150442,
+      "grad_norm": 0.3292330167120311,
+      "learning_rate": 9.52517164432343e-06,
+      "loss": 0.0216,
+      "step": 810
+    },
+    {
+      "epoch": 14.63716814159292,
+      "grad_norm": 0.3367773688229168,
+      "learning_rate": 9.50424036172875e-06,
+      "loss": 0.0217,
+      "step": 820
+    },
+    {
+      "epoch": 14.814159292035399,
+      "grad_norm": 0.3825032388799719,
+      "learning_rate": 9.482881655599867e-06,
+      "loss": 0.0232,
+      "step": 830
+    },
+    {
+      "epoch": 14.991150442477876,
+      "grad_norm": 0.3596880534313284,
+      "learning_rate": 9.461097552741065e-06,
+      "loss": 0.0213,
+      "step": 840
+    },
+    {
+      "epoch": 15.176991150442477,
+      "grad_norm": 0.33569920428582833,
+      "learning_rate": 9.438890120324049e-06,
+      "loss": 0.0162,
+      "step": 850
+    },
+    {
+      "epoch": 15.353982300884956,
+      "grad_norm": 0.3222473354568032,
+      "learning_rate": 9.416261465691786e-06,
+      "loss": 0.0148,
+      "step": 860
+    },
+    {
+      "epoch": 15.530973451327434,
+      "grad_norm": 0.31860277340421633,
+      "learning_rate": 9.393213736158532e-06,
+      "loss": 0.0138,
+      "step": 870
+    },
+    {
+      "epoch": 15.70796460176991,
+      "grad_norm": 0.33012842524691205,
+      "learning_rate": 9.369749118806063e-06,
+      "loss": 0.0139,
+      "step": 880
+    },
+    {
+      "epoch": 15.88495575221239,
+      "grad_norm": 0.31060024250404394,
+      "learning_rate": 9.345869840276138e-06,
+      "loss": 0.0139,
+      "step": 890
+    },
+    {
+      "epoch": 16.07079646017699,
+      "grad_norm": 0.29279639999523854,
+      "learning_rate": 9.321578166559202e-06,
+      "loss": 0.0134,
+      "step": 900
+    },
+    {
+      "epoch": 16.24778761061947,
+      "grad_norm": 0.25025457898908915,
+      "learning_rate": 9.296876402779357e-06,
+      "loss": 0.0094,
+      "step": 910
+    },
+    {
+      "epoch": 16.424778761061948,
+      "grad_norm": 0.26581112654153966,
+      "learning_rate": 9.271766892975632e-06,
+      "loss": 0.009,
+      "step": 920
+    },
+    {
+      "epoch": 16.601769911504427,
+      "grad_norm": 0.28504807326383513,
+      "learning_rate": 9.246252019879526e-06,
+      "loss": 0.0086,
+      "step": 930
+    },
+    {
+      "epoch": 16.778761061946902,
+      "grad_norm": 0.26705155273970366,
+      "learning_rate": 9.22033420468893e-06,
+      "loss": 0.009,
+      "step": 940
+    },
+    {
+      "epoch": 16.95575221238938,
+      "grad_norm": 0.29212797270505986,
+      "learning_rate": 9.194015906838345e-06,
+      "loss": 0.0085,
+      "step": 950
+    },
+    {
+      "epoch": 17.141592920353983,
+      "grad_norm": 0.2832856227572913,
+      "learning_rate": 9.167299623765515e-06,
+      "loss": 0.0075,
+      "step": 960
+    },
+    {
+      "epoch": 17.31858407079646,
+      "grad_norm": 0.22059241414450476,
+      "learning_rate": 9.14018789067443e-06,
+      "loss": 0.006,
+      "step": 970
+    },
+    {
+      "epoch": 17.495575221238937,
+      "grad_norm": 0.28049908913714794,
+      "learning_rate": 9.11268328029475e-06,
+      "loss": 0.0063,
+      "step": 980
+    },
+    {
+      "epoch": 17.672566371681416,
+      "grad_norm": 0.2252426153757288,
+      "learning_rate": 9.08478840263767e-06,
+      "loss": 0.0061,
+      "step": 990
+    },
+    {
+      "epoch": 17.849557522123895,
+      "grad_norm": 0.2856905436001316,
+      "learning_rate": 9.05650590474825e-06,
+      "loss": 0.0058,
+      "step": 1000
+    },
+    {
+      "epoch": 18.035398230088497,
+      "grad_norm": 0.18171559344391483,
+      "learning_rate": 9.027838470454222e-06,
+      "loss": 0.0058,
+      "step": 1010
+    },
+    {
+      "epoch": 18.212389380530972,
+      "grad_norm": 0.17446949191807126,
+      "learning_rate": 8.998788820111323e-06,
+      "loss": 0.0039,
+      "step": 1020
+    },
+    {
+      "epoch": 18.38938053097345,
+      "grad_norm": 0.17008467931611163,
+      "learning_rate": 8.969359710345132e-06,
+      "loss": 0.0044,
+      "step": 1030
+    },
+    {
+      "epoch": 18.56637168141593,
+      "grad_norm": 0.24666749937310403,
+      "learning_rate": 8.939553933789499e-06,
+      "loss": 0.0044,
+      "step": 1040
+    },
+    {
+      "epoch": 18.743362831858406,
+      "grad_norm": 0.20151994276390126,
+      "learning_rate": 8.90937431882154e-06,
+      "loss": 0.0038,
+      "step": 1050
+    },
+    {
+      "epoch": 18.920353982300885,
+      "grad_norm": 0.23754785196862227,
+      "learning_rate": 8.878823729293238e-06,
+      "loss": 0.004,
+      "step": 1060
+    },
+    {
+      "epoch": 19.106194690265486,
+      "grad_norm": 0.14117052858029483,
+      "learning_rate": 8.847905064259683e-06,
+      "loss": 0.0037,
+      "step": 1070
+    },
+    {
+      "epoch": 19.283185840707965,
+      "grad_norm": 0.18847378240235996,
+      "learning_rate": 8.816621257703969e-06,
+      "loss": 0.0031,
+      "step": 1080
+    },
+    {
+      "epoch": 19.460176991150444,
+      "grad_norm": 0.17673625219477776,
+      "learning_rate": 8.784975278258783e-06,
+      "loss": 0.0031,
+      "step": 1090
+    },
+    {
+      "epoch": 19.63716814159292,
+      "grad_norm": 0.16513937168636283,
+      "learning_rate": 8.752970128924696e-06,
+      "loss": 0.003,
+      "step": 1100
+    },
+    {
+      "epoch": 19.8141592920354,
+      "grad_norm": 0.1875769935710693,
+      "learning_rate": 8.7206088467852e-06,
+      "loss": 0.0035,
+      "step": 1110
+    },
+    {
+      "epoch": 19.991150442477878,
+      "grad_norm": 0.1942090816977111,
+      "learning_rate": 8.687894502718503e-06,
+      "loss": 0.003,
+      "step": 1120
+    },
+    {
+      "epoch": 20.17699115044248,
+      "grad_norm": 0.16849498809305985,
+      "learning_rate": 8.654830201106133e-06,
+      "loss": 0.0027,
+      "step": 1130
+    },
+    {
+      "epoch": 20.353982300884955,
+      "grad_norm": 0.15254024942857228,
+      "learning_rate": 8.621419079538337e-06,
+      "loss": 0.0025,
+      "step": 1140
+    },
+    {
+      "epoch": 20.530973451327434,
+      "grad_norm": 0.1522681909876635,
+      "learning_rate": 8.587664308516361e-06,
+      "loss": 0.0024,
+      "step": 1150
+    },
+    {
+      "epoch": 20.707964601769913,
+      "grad_norm": 0.14801504967498672,
+      "learning_rate": 8.553569091151576e-06,
+      "loss": 0.0023,
+      "step": 1160
+    },
+    {
+      "epoch": 20.884955752212388,
+      "grad_norm": 0.13105166934570284,
+      "learning_rate": 8.519136662861531e-06,
+      "loss": 0.0023,
+      "step": 1170
+    },
+    {
+      "epoch": 21.07079646017699,
+      "grad_norm": 0.14743879775955487,
+      "learning_rate": 8.484370291062927e-06,
+      "loss": 0.0025,
+      "step": 1180
+    },
+    {
+      "epoch": 21.24778761061947,
+      "grad_norm": 0.1638754042647016,
+      "learning_rate": 8.449273274861566e-06,
+      "loss": 0.0019,
+      "step": 1190
+    },
+    {
+      "epoch": 21.424778761061948,
+      "grad_norm": 0.1428524275854489,
+      "learning_rate": 8.413848944739282e-06,
+      "loss": 0.0019,
+      "step": 1200
+    },
+    {
+      "epoch": 21.601769911504427,
+      "grad_norm": 0.13186832777609797,
+      "learning_rate": 8.378100662237904e-06,
+      "loss": 0.0019,
+      "step": 1210
+    },
+    {
+      "epoch": 21.778761061946902,
+      "grad_norm": 0.13394117392395247,
+      "learning_rate": 8.342031819640263e-06,
+      "loss": 0.002,
+      "step": 1220
+    },
+    {
+      "epoch": 21.95575221238938,
+      "grad_norm": 0.13314998013772597,
+      "learning_rate": 8.305645839648287e-06,
+      "loss": 0.002,
+      "step": 1230
+    },
+    {
+      "epoch": 22.141592920353983,
+      "grad_norm": 0.11946313669563102,
+      "learning_rate": 8.268946175058214e-06,
+      "loss": 0.0017,
+      "step": 1240
+    },
+    {
+      "epoch": 22.31858407079646,
+      "grad_norm": 0.13692545965091507,
+      "learning_rate": 8.231936308432935e-06,
+      "loss": 0.0017,
+      "step": 1250
+    },
+    {
+      "epoch": 22.495575221238937,
+      "grad_norm": 0.1280253132127409,
+      "learning_rate": 8.194619751771527e-06,
+      "loss": 0.0016,
+      "step": 1260
+    },
+    {
+      "epoch": 22.672566371681416,
+      "grad_norm": 0.14323656703506174,
+      "learning_rate": 8.157000046175984e-06,
+      "loss": 0.0017,
+      "step": 1270
+    },
+    {
+      "epoch": 22.849557522123895,
+      "grad_norm": 0.132872080833497,
+      "learning_rate": 8.119080761515197e-06,
+      "loss": 0.0016,
+      "step": 1280
+    },
+    {
+      "epoch": 23.035398230088497,
+      "grad_norm": 0.09675254792509355,
+      "learning_rate": 8.080865496086177e-06,
+      "loss": 0.0018,
+      "step": 1290
+    },
+    {
+      "epoch": 23.212389380530972,
+      "grad_norm": 0.13055871987919138,
+      "learning_rate": 8.042357876272626e-06,
+      "loss": 0.0014,
+      "step": 1300
+    },
+    {
+      "epoch": 23.38938053097345,
+      "grad_norm": 0.10202870847439023,
+      "learning_rate": 8.003561556200796e-06,
+      "loss": 0.0013,
+      "step": 1310
+    },
+    {
+      "epoch": 23.56637168141593,
+      "grad_norm": 0.10027070765055289,
+      "learning_rate": 7.964480217392739e-06,
+      "loss": 0.0013,
+      "step": 1320
+    },
+    {
+      "epoch": 23.743362831858406,
+      "grad_norm": 0.09963074007081689,
+      "learning_rate": 7.925117568416966e-06,
+      "loss": 0.0013,
+      "step": 1330
+    },
+    {
+      "epoch": 23.920353982300885,
+      "grad_norm": 0.11679760725818564,
+      "learning_rate": 7.885477344536516e-06,
+      "loss": 0.0014,
+      "step": 1340
+    },
+    {
+      "epoch": 24.106194690265486,
+      "grad_norm": 0.0754474545374589,
+      "learning_rate": 7.845563307354506e-06,
+      "loss": 0.0013,
+      "step": 1350
+    },
+    {
+      "epoch": 24.283185840707965,
+      "grad_norm": 0.1253093329096803,
+      "learning_rate": 7.80537924445718e-06,
+      "loss": 0.0011,
+      "step": 1360
+    },
+    {
+      "epoch": 24.460176991150444,
+      "grad_norm": 0.10972348039200527,
+      "learning_rate": 7.764928969054493e-06,
+      "loss": 0.0011,
+      "step": 1370
+    },
+    {
+      "epoch": 24.63716814159292,
+      "grad_norm": 0.34554758886579884,
+      "learning_rate": 7.724216319618257e-06,
+      "loss": 0.0011,
+      "step": 1380
+    },
+    {
+      "epoch": 24.8141592920354,
+      "grad_norm": 0.14420268593428043,
+      "learning_rate": 7.683245159517903e-06,
+      "loss": 0.0011,
+      "step": 1390
+    },
+    {
+      "epoch": 24.991150442477878,
+      "grad_norm": 0.10272004081139009,
+      "learning_rate": 7.642019376653858e-06,
+      "loss": 0.0011,
+      "step": 1400
+    },
+    {
+      "epoch": 25.17699115044248,
+      "grad_norm": 0.10066435427255882,
+      "learning_rate": 7.600542883088629e-06,
+      "loss": 0.001,
+      "step": 1410
+    },
+    {
+      "epoch": 25.353982300884955,
+      "grad_norm": 0.10321823577887183,
+      "learning_rate": 7.5588196146755526e-06,
+      "loss": 0.001,
+      "step": 1420
+    },
+    {
+      "epoch": 25.530973451327434,
+      "grad_norm": 0.09420357679341983,
+      "learning_rate": 7.5168535306853155e-06,
+      "loss": 0.001,
+      "step": 1430
+    },
+    {
+      "epoch": 25.707964601769913,
+      "grad_norm": 0.09068373934441006,
+      "learning_rate": 7.474648613430252e-06,
+      "loss": 0.0011,
+      "step": 1440
+    },
+    {
+      "epoch": 25.884955752212388,
+      "grad_norm": 0.09875146708972135,
+      "learning_rate": 7.432208867886439e-06,
+      "loss": 0.0011,
+      "step": 1450
+    },
+    {
+      "epoch": 26.07079646017699,
+      "grad_norm": 0.08661242865325204,
+      "learning_rate": 7.389538321313652e-06,
+      "loss": 0.0011,
+      "step": 1460
+    },
+    {
+      "epoch": 26.24778761061947,
+      "grad_norm": 0.08825158066362472,
+      "learning_rate": 7.346641022873205e-06,
+      "loss": 0.0009,
+      "step": 1470
+    },
+    {
+      "epoch": 26.424778761061948,
+      "grad_norm": 0.10683045227322636,
+      "learning_rate": 7.303521043243711e-06,
+      "loss": 0.0009,
+      "step": 1480
+    },
+    {
+      "epoch": 26.601769911504427,
+      "grad_norm": 0.12235791354083214,
+      "learning_rate": 7.2601824742347985e-06,
+      "loss": 0.0009,
+      "step": 1490
+    },
+    {
+      "epoch": 26.778761061946902,
+      "grad_norm": 0.08514569373030315,
+      "learning_rate": 7.2166294283988315e-06,
+      "loss": 0.001,
+      "step": 1500
+    },
+    {
+      "epoch": 26.95575221238938,
+      "grad_norm": 0.0842159487022361,
+      "learning_rate": 7.172866038640644e-06,
+      "loss": 0.0009,
+      "step": 1510
+    },
+    {
+      "epoch": 27.141592920353983,
+      "grad_norm": 0.08674683001185676,
+      "learning_rate": 7.128896457825364e-06,
+      "loss": 0.0008,
+      "step": 1520
+    },
+    {
+      "epoch": 27.31858407079646,
+      "grad_norm": 0.07909420218918227,
+      "learning_rate": 7.084724858384326e-06,
+      "loss": 0.0008,
+      "step": 1530
+    },
+    {
+      "epoch": 27.495575221238937,
+      "grad_norm": 0.10596594004861332,
+      "learning_rate": 7.04035543191914e-06,
+      "loss": 0.0008,
+      "step": 1540
+    },
+    {
+      "epoch": 27.672566371681416,
+      "grad_norm": 0.0840755602282058,
+      "learning_rate": 6.995792388803929e-06,
+      "loss": 0.001,
+      "step": 1550
+    },
+    {
+      "epoch": 27.849557522123895,
+      "grad_norm": 0.07853861446661353,
+      "learning_rate": 6.9510399577857976e-06,
+      "loss": 0.0009,
+      "step": 1560
+    },
+    {
+      "epoch": 28.035398230088497,
+      "grad_norm": 0.07288196207830411,
+      "learning_rate": 6.906102385583548e-06,
+      "loss": 0.001,
+      "step": 1570
+    },
+    {
+      "epoch": 28.212389380530972,
+      "grad_norm": 0.0687447241728727,
+      "learning_rate": 6.860983936484689e-06,
+      "loss": 0.0007,
+      "step": 1580
+    },
+    {
+      "epoch": 28.38938053097345,
+      "grad_norm": 0.07585751703066541,
+      "learning_rate": 6.815688891940796e-06,
+      "loss": 0.0007,
+      "step": 1590
+    },
+    {
+      "epoch": 28.56637168141593,
+      "grad_norm": 0.06895349895505572,
+      "learning_rate": 6.770221550161214e-06,
+      "loss": 0.0008,
+      "step": 1600
+    },
+    {
+      "epoch": 28.743362831858406,
+      "grad_norm": 0.12402782198503459,
+      "learning_rate": 6.724586225705191e-06,
+      "loss": 0.0008,
+      "step": 1610
+    },
+    {
+      "epoch": 28.920353982300885,
+      "grad_norm": 0.1527989353563491,
+      "learning_rate": 6.678787249072456e-06,
+      "loss": 0.0009,
+      "step": 1620
+    },
+    {
+      "epoch": 29.106194690265486,
+      "grad_norm": 0.06954410595068672,
+      "learning_rate": 6.632828966292279e-06,
+      "loss": 0.0009,
+      "step": 1630
+    },
+    {
+      "epoch": 29.283185840707965,
+      "grad_norm": 0.1073267489136229,
+      "learning_rate": 6.586715738511067e-06,
+      "loss": 0.0009,
+      "step": 1640
+    },
+    {
+      "epoch": 29.460176991150444,
+      "grad_norm": 0.08313874513099292,
+      "learning_rate": 6.540451941578505e-06,
+      "loss": 0.0009,
+      "step": 1650
+    },
+    {
+      "epoch": 29.63716814159292,
+      "grad_norm": 0.12731437056639278,
+      "learning_rate": 6.494041965632335e-06,
+      "loss": 0.0009,
+      "step": 1660
+    },
+    {
+      "epoch": 29.8141592920354,
+      "grad_norm": 0.09692619372507454,
+      "learning_rate": 6.447490214681742e-06,
+      "loss": 0.0009,
+      "step": 1670
+    },
+    {
+      "epoch": 29.991150442477878,
+      "grad_norm": 0.10737775556639746,
+      "learning_rate": 6.400801106189457e-06,
+      "loss": 0.0008,
+      "step": 1680
+    },
+    {
+      "epoch": 30.17699115044248,
+      "grad_norm": 0.10960316406181361,
+      "learning_rate": 6.353979070652555e-06,
+      "loss": 0.0007,
+      "step": 1690
+    },
+    {
+      "epoch": 30.353982300884955,
+      "grad_norm": 0.0828957218344359,
+      "learning_rate": 6.307028551182041e-06,
+      "loss": 0.0009,
+      "step": 1700
+    },
+    {
+      "epoch": 30.530973451327434,
+      "grad_norm": 0.06197924420139391,
+      "learning_rate": 6.259954003081215e-06,
+      "loss": 0.0008,
+      "step": 1710
+    },
+    {
+      "epoch": 30.707964601769913,
+      "grad_norm": 0.13419189832528763,
+      "learning_rate": 6.212759893422908e-06,
+      "loss": 0.0009,
+      "step": 1720
+    },
+    {
+      "epoch": 30.884955752212388,
+      "grad_norm": 0.07335797834009149,
+      "learning_rate": 6.165450700625565e-06,
+      "loss": 0.0009,
+      "step": 1730
+    },
+    {
+      "epoch": 31.07079646017699,
+      "grad_norm": 0.08616596067290054,
+      "learning_rate": 6.118030914028292e-06,
+      "loss": 0.0009,
+      "step": 1740
+    },
+    {
+      "epoch": 31.24778761061947,
+      "grad_norm": 0.11160398222363577,
+      "learning_rate": 6.070505033464835e-06,
+      "loss": 0.0008,
+      "step": 1750
+    },
+    {
+      "epoch": 31.424778761061948,
+      "grad_norm": 0.08223375466647835,
+      "learning_rate": 6.022877568836579e-06,
+      "loss": 0.0008,
+      "step": 1760
+    },
+    {
+      "epoch": 31.601769911504427,
+      "grad_norm": 0.08274688851558104,
+      "learning_rate": 5.975153039684579e-06,
+      "loss": 0.0008,
+      "step": 1770
+    },
+    {
+      "epoch": 31.778761061946902,
+      "grad_norm": 0.0970587549375438,
+      "learning_rate": 5.927335974760699e-06,
+      "loss": 0.0008,
+      "step": 1780
+    },
+    {
+      "epoch": 31.95575221238938,
+      "grad_norm": 0.054546179433890875,
+      "learning_rate": 5.87943091159785e-06,
+      "loss": 0.0007,
+      "step": 1790
+    },
+    {
+      "epoch": 32.14159292035398,
+      "grad_norm": 0.05969746156171825,
+      "learning_rate": 5.831442396079413e-06,
+      "loss": 0.0008,
+      "step": 1800
+    },
+    {
+      "epoch": 32.31858407079646,
+      "grad_norm": 0.05018822775479197,
+      "learning_rate": 5.78337498200786e-06,
+      "loss": 0.0007,
+      "step": 1810
+    },
+    {
+      "epoch": 32.49557522123894,
+      "grad_norm": 0.08901463204658712,
+      "learning_rate": 5.735233230672636e-06,
+      "loss": 0.0007,
+      "step": 1820
+    },
+    {
+      "epoch": 32.67256637168141,
+      "grad_norm": 0.07922243579859921,
+      "learning_rate": 5.687021710417308e-06,
+      "loss": 0.0007,
+      "step": 1830
+    },
+    {
+      "epoch": 32.849557522123895,
+      "grad_norm": 0.07354939715718499,
+      "learning_rate": 5.638744996206074e-06,
+      "loss": 0.0006,
+      "step": 1840
+    },
+    {
+      "epoch": 33.0353982300885,
+      "grad_norm": 0.06160878470580236,
+      "learning_rate": 5.590407669189612e-06,
+      "loss": 0.0006,
+      "step": 1850
+    },
+    {
+      "epoch": 33.21238938053097,
+      "grad_norm": 0.06166669775060316,
+      "learning_rate": 5.542014316270377e-06,
+      "loss": 0.0005,
+      "step": 1860
+    },
+    {
+      "epoch": 33.389380530973455,
+      "grad_norm": 0.052889879306465305,
+      "learning_rate": 5.493569529667312e-06,
+      "loss": 0.0006,
+      "step": 1870
+    },
+    {
+      "epoch": 33.56637168141593,
+      "grad_norm": 0.08213350355164716,
+      "learning_rate": 5.445077906480095e-06,
+      "loss": 0.0006,
+      "step": 1880
+    },
+    {
+      "epoch": 33.743362831858406,
+      "grad_norm": 0.08160047999287494,
+      "learning_rate": 5.396544048252893e-06,
+      "loss": 0.0005,
+      "step": 1890
+    },
+    {
+      "epoch": 33.92035398230089,
+      "grad_norm": 0.07583900802666055,
+      "learning_rate": 5.3479725605377065e-06,
+      "loss": 0.0005,
+      "step": 1900
+    },
+    {
+      "epoch": 34.10619469026549,
+      "grad_norm": 0.028472829495580533,
+      "learning_rate": 5.299368052457332e-06,
+      "loss": 0.0005,
+      "step": 1910
+    },
+    {
+      "epoch": 34.283185840707965,
+      "grad_norm": 0.05015747871224623,
+      "learning_rate": 5.250735136267993e-06,
+      "loss": 0.0004,
+      "step": 1920
+    },
+    {
+      "epoch": 34.46017699115044,
+      "grad_norm": 0.05176601714476982,
+      "learning_rate": 5.2020784269216515e-06,
+      "loss": 0.0004,
+      "step": 1930
+    },
+    {
+      "epoch": 34.63716814159292,
+      "grad_norm": 0.037671952173425755,
+      "learning_rate": 5.153402541628097e-06,
+      "loss": 0.0004,
+      "step": 1940
+    },
+    {
+      "epoch": 34.8141592920354,
+      "grad_norm": 0.06647847020125087,
+      "learning_rate": 5.1047120994167855e-06,
+      "loss": 0.0004,
+      "step": 1950
+    },
+    {
+      "epoch": 34.991150442477874,
+      "grad_norm": 0.049900511058573065,
+      "learning_rate": 5.056011720698536e-06,
+      "loss": 0.0005,
+      "step": 1960
+    },
+    {
+      "epoch": 35.176991150442475,
+      "grad_norm": 0.062213088302615654,
+      "learning_rate": 5.007306026827076e-06,
+      "loss": 0.0004,
+      "step": 1970
+    },
+    {
+      "epoch": 35.35398230088496,
+      "grad_norm": 0.05221297387988636,
+      "learning_rate": 4.958599639660508e-06,
+      "loss": 0.0003,
+      "step": 1980
+    },
+    {
+      "epoch": 35.530973451327434,
+      "grad_norm": 0.025844683052233374,
+      "learning_rate": 4.909897181122725e-06,
+      "loss": 0.0004,
+      "step": 1990
+    },
+    {
+      "epoch": 35.70796460176991,
+      "grad_norm": 0.027696973790180324,
+      "learning_rate": 4.861203272764813e-06,
+      "loss": 0.0004,
+      "step": 2000
+    },
+    {
+      "epoch": 35.88495575221239,
+      "grad_norm": 0.030687511235047944,
+      "learning_rate": 4.8125225353265085e-06,
+      "loss": 0.0004,
+      "step": 2010
+    },
+    {
+      "epoch": 36.07079646017699,
+      "grad_norm": 0.04493009791881542,
+      "learning_rate": 4.7638595882977064e-06,
+      "loss": 0.0004,
+      "step": 2020
+    },
+    {
+      "epoch": 36.24778761061947,
+      "grad_norm": 0.01691149961222786,
+      "learning_rate": 4.71521904948011e-06,
+      "loss": 0.0003,
+      "step": 2030
+    },
+    {
+      "epoch": 36.424778761061944,
+      "grad_norm": 0.027515076083035817,
+      "learning_rate": 4.666605534549021e-06,
+      "loss": 0.0003,
+      "step": 2040
+    },
+    {
+      "epoch": 36.60176991150443,
+      "grad_norm": 0.03559173688865591,
+      "learning_rate": 4.618023656615352e-06,
+      "loss": 0.0003,
+      "step": 2050
+    },
+    {
+      "epoch": 36.7787610619469,
+      "grad_norm": 0.04165835396132989,
+      "learning_rate": 4.569478025787869e-06,
+      "loss": 0.0004,
+      "step": 2060
+    },
+    {
+      "epoch": 36.95575221238938,
+      "grad_norm": 0.08306198347880518,
+      "learning_rate": 4.520973248735715e-06,
+      "loss": 0.0004,
+      "step": 2070
+    },
+    {
+      "epoch": 37.14159292035398,
+      "grad_norm": 0.05411026344168162,
+      "learning_rate": 4.472513928251275e-06,
+      "loss": 0.0005,
+      "step": 2080
+    },
+    {
+      "epoch": 37.31858407079646,
+      "grad_norm": 0.05227095996187008,
+      "learning_rate": 4.424104662813396e-06,
+      "loss": 0.0003,
+      "step": 2090
+    },
+    {
+      "epoch": 37.49557522123894,
+      "grad_norm": 0.027806388434303872,
+      "learning_rate": 4.375750046151023e-06,
+      "loss": 0.0003,
+      "step": 2100
+    },
+    {
+      "epoch": 37.67256637168141,
+      "grad_norm": 0.052658952971337866,
+      "learning_rate": 4.3274546668072835e-06,
+      "loss": 0.0003,
+      "step": 2110
+    },
+    {
+      "epoch": 37.849557522123895,
+      "grad_norm": 0.030080205440969073,
+      "learning_rate": 4.279223107704058e-06,
+      "loss": 0.0005,
+      "step": 2120
+    },
+    {
+      "epoch": 38.0353982300885,
+      "grad_norm": 0.05339256914519307,
+      "learning_rate": 4.2310599457071e-06,
+      "loss": 0.0004,
+      "step": 2130
+    },
+    {
+      "epoch": 38.21238938053097,
+      "grad_norm": 0.04425363914132623,
+      "learning_rate": 4.1829697511917146e-06,
+      "loss": 0.0003,
+      "step": 2140
+    },
+    {
+      "epoch": 38.389380530973455,
+      "grad_norm": 0.011312355977019536,
+      "learning_rate": 4.134957087609065e-06,
+      "loss": 0.0004,
+      "step": 2150
+    },
+    {
+      "epoch": 38.56637168141593,
+      "grad_norm": 0.029346947515830845,
+      "learning_rate": 4.087026511053116e-06,
+      "loss": 0.0003,
+      "step": 2160
+    },
+    {
+      "epoch": 38.743362831858406,
+      "grad_norm": 0.042536157363505335,
+      "learning_rate": 4.0391825698283084e-06,
+      "loss": 0.0003,
+      "step": 2170
+    },
+    {
+      "epoch": 38.92035398230089,
+      "grad_norm": 0.03536377347443713,
+      "learning_rate": 3.991429804017944e-06,
+      "loss": 0.0003,
+      "step": 2180
+    },
+    {
+      "epoch": 39.10619469026549,
+      "grad_norm": 0.05886812292462864,
+      "learning_rate": 3.9437727450533605e-06,
+      "loss": 0.0003,
+      "step": 2190
+    },
+    {
+      "epoch": 39.283185840707965,
+      "grad_norm": 0.01648121399449709,
+      "learning_rate": 3.89621591528393e-06,
+      "loss": 0.0004,
+      "step": 2200
+    },
+    {
+      "epoch": 39.46017699115044,
+      "grad_norm": 0.05635714119276726,
+      "learning_rate": 3.848763827547915e-06,
+      "loss": 0.0003,
+      "step": 2210
+    },
+    {
+      "epoch": 39.63716814159292,
+      "grad_norm": 0.009383854914388465,
+      "learning_rate": 3.8014209847442345e-06,
+      "loss": 0.0003,
+      "step": 2220
+    },
+    {
+      "epoch": 39.8141592920354,
+      "grad_norm": 0.05011834839916184,
+      "learning_rate": 3.7541918794051637e-06,
+      "loss": 0.0002,
+      "step": 2230
+    },
+    {
+      "epoch": 39.991150442477874,
+      "grad_norm": 0.05133974792375958,
+      "learning_rate": 3.7070809932700134e-06,
+      "loss": 0.0003,
+      "step": 2240
+    },
+    {
+      "epoch": 40.176991150442475,
+      "grad_norm": 0.018588269742905027,
+      "learning_rate": 3.6600927968598588e-06,
+      "loss": 0.0002,
+      "step": 2250
+    },
+    {
+      "epoch": 40.35398230088496,
+      "grad_norm": 0.07504151811726231,
+      "learning_rate": 3.613231749053304e-06,
+      "loss": 0.0003,
+      "step": 2260
+    },
+    {
+      "epoch": 40.530973451327434,
+      "grad_norm": 0.009247883379305936,
+      "learning_rate": 3.5665022966633678e-06,
+      "loss": 0.0002,
+      "step": 2270
+    },
+    {
+      "epoch": 40.70796460176991,
+      "grad_norm": 0.010786624329556564,
+      "learning_rate": 3.519908874015501e-06,
+      "loss": 0.0002,
+      "step": 2280
+    },
+    {
+      "epoch": 40.88495575221239,
+      "grad_norm": 0.009033335718842525,
+      "learning_rate": 3.473455902526809e-06,
+      "loss": 0.0002,
+      "step": 2290
+    },
+    {
+      "epoch": 41.07079646017699,
+      "grad_norm": 0.006789585965722491,
+      "learning_rate": 3.4271477902864836e-06,
+      "loss": 0.0003,
+      "step": 2300
+    },
+    {
+      "epoch": 41.24778761061947,
+      "grad_norm": 0.011629682271040448,
+      "learning_rate": 3.3809889316375012e-06,
+      "loss": 0.0002,
+      "step": 2310
+    },
+    {
+      "epoch": 41.424778761061944,
+      "grad_norm": 0.016037900332241763,
+      "learning_rate": 3.334983706759627e-06,
+      "loss": 0.0002,
+      "step": 2320
+    },
+    {
+      "epoch": 41.60176991150443,
+      "grad_norm": 0.008455409270455181,
+      "learning_rate": 3.2891364812537686e-06,
+      "loss": 0.0002,
+      "step": 2330
+    },
+    {
+      "epoch": 41.7787610619469,
+      "grad_norm": 0.042022335506453394,
+      "learning_rate": 3.2434516057277055e-06,
+      "loss": 0.0002,
+      "step": 2340
+    },
+    {
+      "epoch": 41.95575221238938,
+      "grad_norm": 0.022526899592221396,
+      "learning_rate": 3.1979334153832486e-06,
+      "loss": 0.0002,
+      "step": 2350
+    },
+    {
+      "epoch": 42.14159292035398,
+      "grad_norm": 0.013477460019272535,
+      "learning_rate": 3.1525862296048446e-06,
+      "loss": 0.0002,
+      "step": 2360
+    },
+    {
+      "epoch": 42.31858407079646,
+      "grad_norm": 0.014364454049260516,
+      "learning_rate": 3.1074143515497114e-06,
+      "loss": 0.0002,
+      "step": 2370
+    },
+    {
+      "epoch": 42.49557522123894,
+      "grad_norm": 0.02250464749159911,
+      "learning_rate": 3.0624220677394854e-06,
+      "loss": 0.0002,
+      "step": 2380
+    },
+    {
+      "epoch": 42.67256637168141,
+      "grad_norm": 0.011861124991493036,
+      "learning_rate": 3.017613647653461e-06,
+      "loss": 0.0002,
+      "step": 2390
+    },
+    {
+      "epoch": 42.849557522123895,
+      "grad_norm": 0.006372525086061116,
+      "learning_rate": 2.9729933433234402e-06,
+      "loss": 0.0002,
+      "step": 2400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 64,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5164849300121846e+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 sha256:966b5824f27e6725d6e141b0a5fd3edec40ac0a3f5796190639f0dfcd39dd159
+size 7672