Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.45.1"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc219a5c232b10aeac7f67d3e65a6c3d6c03465823f5e2b752c4db1add6ad21e
+size 4976687216

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497e8613c3dca124676bbd90fd6c93477808d3255b325adc7a96074194a36dfb
+size 4778622352

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c25656b215f7e2cefc4e3ec49584936d9dca4bd52e852c999dd2e2b688ed08ab
+size 4932743960

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8105997b28fea3703d0886cb23114e8d1f0a08077750753776939736f5bf097
+size 4932743992

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a644ff14152fc5a93be019d46fe416871ae8d0ad2d67615f91089f1887aac886
+size 4998852296

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8cbb3c6b4d112f23af6c318dced149a8e377adde6bfa9d7bb27350e10acf86
+size 3662865184

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5cccfd82649d6d895d64c85ad439cbf04a4a30d76936b119b704a622d16a039
+size 2179989632

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1328 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 0,
+  "global_step": 185,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005405405405405406,
+      "grad_norm": 4.0049285888671875,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.4543,
+      "step": 1
+    },
+    {
+      "epoch": 0.010810810810810811,
+      "grad_norm": 3.6172754764556885,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.4798,
+      "step": 2
+    },
+    {
+      "epoch": 0.016216216216216217,
+      "grad_norm": 15.047930717468262,
+      "learning_rate": 0.0001,
+      "loss": 2.3166,
+      "step": 3
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 30.211719512939453,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 3.0968,
+      "step": 4
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 85.43743133544922,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 9.2485,
+      "step": 5
+    },
+    {
+      "epoch": 0.032432432432432434,
+      "grad_norm": 31.648372650146484,
+      "learning_rate": 0.0002,
+      "loss": 5.6812,
+      "step": 6
+    },
+    {
+      "epoch": 0.03783783783783784,
+      "grad_norm": 28.307153701782227,
+      "learning_rate": 0.00019899441340782124,
+      "loss": 4.923,
+      "step": 7
+    },
+    {
+      "epoch": 0.043243243243243246,
+      "grad_norm": 72.10746002197266,
+      "learning_rate": 0.00019798882681564247,
+      "loss": 5.2033,
+      "step": 8
+    },
+    {
+      "epoch": 0.04864864864864865,
+      "grad_norm": 245.99508666992188,
+      "learning_rate": 0.00019698324022346367,
+      "loss": 4.7967,
+      "step": 9
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 19.966106414794922,
+      "learning_rate": 0.00019597765363128493,
+      "loss": 4.4746,
+      "step": 10
+    },
+    {
+      "epoch": 0.05945945945945946,
+      "grad_norm": 13.21216869354248,
+      "learning_rate": 0.00019497206703910616,
+      "loss": 3.853,
+      "step": 11
+    },
+    {
+      "epoch": 0.06486486486486487,
+      "grad_norm": 22.403423309326172,
+      "learning_rate": 0.00019396648044692737,
+      "loss": 3.8436,
+      "step": 12
+    },
+    {
+      "epoch": 0.07027027027027027,
+      "grad_norm": 19.907819747924805,
+      "learning_rate": 0.0001929608938547486,
+      "loss": 3.4515,
+      "step": 13
+    },
+    {
+      "epoch": 0.07567567567567568,
+      "grad_norm": 13.797648429870605,
+      "learning_rate": 0.00019195530726256985,
+      "loss": 3.1302,
+      "step": 14
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": 13.124836921691895,
+      "learning_rate": 0.00019094972067039108,
+      "loss": 2.9113,
+      "step": 15
+    },
+    {
+      "epoch": 0.08648648648648649,
+      "grad_norm": 5.7703022956848145,
+      "learning_rate": 0.0001899441340782123,
+      "loss": 2.63,
+      "step": 16
+    },
+    {
+      "epoch": 0.0918918918918919,
+      "grad_norm": 10.830033302307129,
+      "learning_rate": 0.00018893854748603352,
+      "loss": 2.3445,
+      "step": 17
+    },
+    {
+      "epoch": 0.0972972972972973,
+      "grad_norm": 6.587128162384033,
+      "learning_rate": 0.00018793296089385475,
+      "loss": 2.4421,
+      "step": 18
+    },
+    {
+      "epoch": 0.10270270270270271,
+      "grad_norm": 8.627386093139648,
+      "learning_rate": 0.000186927374301676,
+      "loss": 2.55,
+      "step": 19
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 6.208451747894287,
+      "learning_rate": 0.0001859217877094972,
+      "loss": 2.3098,
+      "step": 20
+    },
+    {
+      "epoch": 0.11351351351351352,
+      "grad_norm": 3.859027624130249,
+      "learning_rate": 0.00018491620111731844,
+      "loss": 2.1369,
+      "step": 21
+    },
+    {
+      "epoch": 0.11891891891891893,
+      "grad_norm": 4.324620723724365,
+      "learning_rate": 0.00018391061452513967,
+      "loss": 2.2362,
+      "step": 22
+    },
+    {
+      "epoch": 0.12432432432432433,
+      "grad_norm": 4.892393112182617,
+      "learning_rate": 0.00018290502793296093,
+      "loss": 2.1266,
+      "step": 23
+    },
+    {
+      "epoch": 0.12972972972972974,
+      "grad_norm": 5.422415733337402,
+      "learning_rate": 0.00018189944134078213,
+      "loss": 2.0899,
+      "step": 24
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 5.536099910736084,
+      "learning_rate": 0.00018089385474860333,
+      "loss": 1.9812,
+      "step": 25
+    },
+    {
+      "epoch": 0.14054054054054055,
+      "grad_norm": 3.9717321395874023,
+      "learning_rate": 0.0001798882681564246,
+      "loss": 1.8578,
+      "step": 26
+    },
+    {
+      "epoch": 0.14594594594594595,
+      "grad_norm": 4.257945537567139,
+      "learning_rate": 0.00017888268156424582,
+      "loss": 1.9502,
+      "step": 27
+    },
+    {
+      "epoch": 0.15135135135135136,
+      "grad_norm": 3.4768412113189697,
+      "learning_rate": 0.00017787709497206705,
+      "loss": 1.8821,
+      "step": 28
+    },
+    {
+      "epoch": 0.15675675675675677,
+      "grad_norm": 5.640548229217529,
+      "learning_rate": 0.00017687150837988826,
+      "loss": 1.8934,
+      "step": 29
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 3.2775862216949463,
+      "learning_rate": 0.00017586592178770951,
+      "loss": 1.7708,
+      "step": 30
+    },
+    {
+      "epoch": 0.16756756756756758,
+      "grad_norm": 3.5710699558258057,
+      "learning_rate": 0.00017486033519553075,
+      "loss": 1.7744,
+      "step": 31
+    },
+    {
+      "epoch": 0.17297297297297298,
+      "grad_norm": 2.6257646083831787,
+      "learning_rate": 0.00017385474860335198,
+      "loss": 1.6934,
+      "step": 32
+    },
+    {
+      "epoch": 0.1783783783783784,
+      "grad_norm": 3.9629523754119873,
+      "learning_rate": 0.00017284916201117318,
+      "loss": 1.7363,
+      "step": 33
+    },
+    {
+      "epoch": 0.1837837837837838,
+      "grad_norm": 2.3908259868621826,
+      "learning_rate": 0.00017184357541899444,
+      "loss": 1.7277,
+      "step": 34
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "grad_norm": 2.75465989112854,
+      "learning_rate": 0.00017083798882681567,
+      "loss": 1.7093,
+      "step": 35
+    },
+    {
+      "epoch": 0.1945945945945946,
+      "grad_norm": 8.39667797088623,
+      "learning_rate": 0.00016983240223463687,
+      "loss": 1.8453,
+      "step": 36
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 55.12360382080078,
+      "learning_rate": 0.0001688268156424581,
+      "loss": 2.7956,
+      "step": 37
+    },
+    {
+      "epoch": 0.20540540540540542,
+      "grad_norm": 7.613361358642578,
+      "learning_rate": 0.00016782122905027933,
+      "loss": 1.9827,
+      "step": 38
+    },
+    {
+      "epoch": 0.21081081081081082,
+      "grad_norm": 4.211851119995117,
+      "learning_rate": 0.00016681564245810056,
+      "loss": 1.8414,
+      "step": 39
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 3.3652498722076416,
+      "learning_rate": 0.0001658100558659218,
+      "loss": 1.8754,
+      "step": 40
+    },
+    {
+      "epoch": 0.22162162162162163,
+      "grad_norm": 4.680253982543945,
+      "learning_rate": 0.00016480446927374302,
+      "loss": 1.8269,
+      "step": 41
+    },
+    {
+      "epoch": 0.22702702702702704,
+      "grad_norm": 2.4161698818206787,
+      "learning_rate": 0.00016379888268156425,
+      "loss": 1.7132,
+      "step": 42
+    },
+    {
+      "epoch": 0.23243243243243245,
+      "grad_norm": 2.6352972984313965,
+      "learning_rate": 0.00016279329608938548,
+      "loss": 1.7756,
+      "step": 43
+    },
+    {
+      "epoch": 0.23783783783783785,
+      "grad_norm": 2.8735787868499756,
+      "learning_rate": 0.00016178770949720671,
+      "loss": 1.7029,
+      "step": 44
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "grad_norm": 2.2981088161468506,
+      "learning_rate": 0.00016078212290502792,
+      "loss": 1.7449,
+      "step": 45
+    },
+    {
+      "epoch": 0.24864864864864866,
+      "grad_norm": 3.6938095092773438,
+      "learning_rate": 0.00015977653631284918,
+      "loss": 1.6877,
+      "step": 46
+    },
+    {
+      "epoch": 0.25405405405405407,
+      "grad_norm": 2.38474702835083,
+      "learning_rate": 0.00015877094972067038,
+      "loss": 1.5995,
+      "step": 47
+    },
+    {
+      "epoch": 0.2594594594594595,
+      "grad_norm": 2.466663360595703,
+      "learning_rate": 0.00015776536312849164,
+      "loss": 1.5037,
+      "step": 48
+    },
+    {
+      "epoch": 0.2648648648648649,
+      "grad_norm": 2.7223317623138428,
+      "learning_rate": 0.00015675977653631284,
+      "loss": 1.5707,
+      "step": 49
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 2.1740567684173584,
+      "learning_rate": 0.0001557541899441341,
+      "loss": 1.5779,
+      "step": 50
+    },
+    {
+      "epoch": 0.2756756756756757,
+      "grad_norm": 2.130438804626465,
+      "learning_rate": 0.0001547486033519553,
+      "loss": 1.581,
+      "step": 51
+    },
+    {
+      "epoch": 0.2810810810810811,
+      "grad_norm": 3.1053080558776855,
+      "learning_rate": 0.00015374301675977656,
+      "loss": 1.6141,
+      "step": 52
+    },
+    {
+      "epoch": 0.2864864864864865,
+      "grad_norm": 2.1347055435180664,
+      "learning_rate": 0.00015273743016759776,
+      "loss": 1.5882,
+      "step": 53
+    },
+    {
+      "epoch": 0.2918918918918919,
+      "grad_norm": 2.012467384338379,
+      "learning_rate": 0.000151731843575419,
+      "loss": 1.5219,
+      "step": 54
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "grad_norm": 2.5574147701263428,
+      "learning_rate": 0.00015072625698324022,
+      "loss": 1.6298,
+      "step": 55
+    },
+    {
+      "epoch": 0.3027027027027027,
+      "grad_norm": 3.091801881790161,
+      "learning_rate": 0.00014972067039106145,
+      "loss": 1.515,
+      "step": 56
+    },
+    {
+      "epoch": 0.3081081081081081,
+      "grad_norm": 2.234355926513672,
+      "learning_rate": 0.00014871508379888268,
+      "loss": 1.5501,
+      "step": 57
+    },
+    {
+      "epoch": 0.31351351351351353,
+      "grad_norm": 3.299154281616211,
+      "learning_rate": 0.00014770949720670391,
+      "loss": 1.6285,
+      "step": 58
+    },
+    {
+      "epoch": 0.31891891891891894,
+      "grad_norm": 2.0043587684631348,
+      "learning_rate": 0.00014670391061452514,
+      "loss": 1.5218,
+      "step": 59
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 2.3809549808502197,
+      "learning_rate": 0.00014569832402234638,
+      "loss": 1.4872,
+      "step": 60
+    },
+    {
+      "epoch": 0.32972972972972975,
+      "grad_norm": 2.2580623626708984,
+      "learning_rate": 0.0001446927374301676,
+      "loss": 1.4445,
+      "step": 61
+    },
+    {
+      "epoch": 0.33513513513513515,
+      "grad_norm": 1.822764277458191,
+      "learning_rate": 0.00014368715083798884,
+      "loss": 1.551,
+      "step": 62
+    },
+    {
+      "epoch": 0.34054054054054056,
+      "grad_norm": 1.8461302518844604,
+      "learning_rate": 0.00014268156424581004,
+      "loss": 1.4394,
+      "step": 63
+    },
+    {
+      "epoch": 0.34594594594594597,
+      "grad_norm": 1.7777131795883179,
+      "learning_rate": 0.0001416759776536313,
+      "loss": 1.3559,
+      "step": 64
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 1.775188684463501,
+      "learning_rate": 0.00014067039106145253,
+      "loss": 1.506,
+      "step": 65
+    },
+    {
+      "epoch": 0.3567567567567568,
+      "grad_norm": 1.8579380512237549,
+      "learning_rate": 0.00013966480446927376,
+      "loss": 1.5416,
+      "step": 66
+    },
+    {
+      "epoch": 0.3621621621621622,
+      "grad_norm": 2.0866875648498535,
+      "learning_rate": 0.00013865921787709496,
+      "loss": 1.5526,
+      "step": 67
+    },
+    {
+      "epoch": 0.3675675675675676,
+      "grad_norm": 2.1562321186065674,
+      "learning_rate": 0.00013765363128491622,
+      "loss": 1.4969,
+      "step": 68
+    },
+    {
+      "epoch": 0.372972972972973,
+      "grad_norm": 1.928788185119629,
+      "learning_rate": 0.00013664804469273745,
+      "loss": 1.5515,
+      "step": 69
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 2.124756336212158,
+      "learning_rate": 0.00013564245810055868,
+      "loss": 1.4266,
+      "step": 70
+    },
+    {
+      "epoch": 0.3837837837837838,
+      "grad_norm": 1.4556527137756348,
+      "learning_rate": 0.00013463687150837988,
+      "loss": 1.4718,
+      "step": 71
+    },
+    {
+      "epoch": 0.3891891891891892,
+      "grad_norm": 1.5127558708190918,
+      "learning_rate": 0.00013363128491620111,
+      "loss": 1.4323,
+      "step": 72
+    },
+    {
+      "epoch": 0.3945945945945946,
+      "grad_norm": 1.6139051914215088,
+      "learning_rate": 0.00013262569832402237,
+      "loss": 1.3959,
+      "step": 73
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.1050167083740234,
+      "learning_rate": 0.00013162011173184358,
+      "loss": 1.508,
+      "step": 74
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 2.010802745819092,
+      "learning_rate": 0.0001306145251396648,
+      "loss": 1.4919,
+      "step": 75
+    },
+    {
+      "epoch": 0.41081081081081083,
+      "grad_norm": 5.8437981605529785,
+      "learning_rate": 0.00012960893854748604,
+      "loss": 1.4919,
+      "step": 76
+    },
+    {
+      "epoch": 0.41621621621621624,
+      "grad_norm": 3.061354637145996,
+      "learning_rate": 0.0001286033519553073,
+      "loss": 1.5347,
+      "step": 77
+    },
+    {
+      "epoch": 0.42162162162162165,
+      "grad_norm": 1.7366749048233032,
+      "learning_rate": 0.0001275977653631285,
+      "loss": 1.4741,
+      "step": 78
+    },
+    {
+      "epoch": 0.42702702702702705,
+      "grad_norm": 3.3530421257019043,
+      "learning_rate": 0.00012659217877094973,
+      "loss": 1.5562,
+      "step": 79
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 1.7036885023117065,
+      "learning_rate": 0.00012558659217877096,
+      "loss": 1.467,
+      "step": 80
+    },
+    {
+      "epoch": 0.43783783783783786,
+      "grad_norm": 1.7056543827056885,
+      "learning_rate": 0.00012458100558659222,
+      "loss": 1.5217,
+      "step": 81
+    },
+    {
+      "epoch": 0.44324324324324327,
+      "grad_norm": 1.5444260835647583,
+      "learning_rate": 0.0001235754189944134,
+      "loss": 1.3959,
+      "step": 82
+    },
+    {
+      "epoch": 0.4486486486486487,
+      "grad_norm": 1.461717963218689,
+      "learning_rate": 0.00012256983240223462,
+      "loss": 1.3684,
+      "step": 83
+    },
+    {
+      "epoch": 0.4540540540540541,
+      "grad_norm": 2.405122756958008,
+      "learning_rate": 0.00012156424581005588,
+      "loss": 1.4736,
+      "step": 84
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 2.271719455718994,
+      "learning_rate": 0.0001205586592178771,
+      "loss": 1.4197,
+      "step": 85
+    },
+    {
+      "epoch": 0.4648648648648649,
+      "grad_norm": 1.6628215312957764,
+      "learning_rate": 0.00011955307262569834,
+      "loss": 1.4345,
+      "step": 86
+    },
+    {
+      "epoch": 0.4702702702702703,
+      "grad_norm": 1.5047897100448608,
+      "learning_rate": 0.00011854748603351954,
+      "loss": 1.4675,
+      "step": 87
+    },
+    {
+      "epoch": 0.4756756756756757,
+      "grad_norm": 2.330070972442627,
+      "learning_rate": 0.0001175418994413408,
+      "loss": 1.5053,
+      "step": 88
+    },
+    {
+      "epoch": 0.4810810810810811,
+      "grad_norm": 1.5151646137237549,
+      "learning_rate": 0.00011653631284916202,
+      "loss": 1.4277,
+      "step": 89
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 2.1238574981689453,
+      "learning_rate": 0.00011553072625698326,
+      "loss": 1.4749,
+      "step": 90
+    },
+    {
+      "epoch": 0.4918918918918919,
+      "grad_norm": 1.6031622886657715,
+      "learning_rate": 0.00011452513966480447,
+      "loss": 1.3802,
+      "step": 91
+    },
+    {
+      "epoch": 0.4972972972972973,
+      "grad_norm": 1.80471932888031,
+      "learning_rate": 0.0001135195530726257,
+      "loss": 1.4286,
+      "step": 92
+    },
+    {
+      "epoch": 0.5027027027027027,
+      "grad_norm": 1.7329200506210327,
+      "learning_rate": 0.00011251396648044694,
+      "loss": 1.4543,
+      "step": 93
+    },
+    {
+      "epoch": 0.5081081081081081,
+      "grad_norm": 2.031339406967163,
+      "learning_rate": 0.00011150837988826817,
+      "loss": 1.3877,
+      "step": 94
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 1.5385271310806274,
+      "learning_rate": 0.00011050279329608939,
+      "loss": 1.3736,
+      "step": 95
+    },
+    {
+      "epoch": 0.518918918918919,
+      "grad_norm": 2.143282413482666,
+      "learning_rate": 0.00010949720670391062,
+      "loss": 1.7171,
+      "step": 96
+    },
+    {
+      "epoch": 0.5243243243243243,
+      "grad_norm": 1.5371496677398682,
+      "learning_rate": 0.00010849162011173184,
+      "loss": 1.3208,
+      "step": 97
+    },
+    {
+      "epoch": 0.5297297297297298,
+      "grad_norm": 2.0396029949188232,
+      "learning_rate": 0.00010748603351955308,
+      "loss": 1.3534,
+      "step": 98
+    },
+    {
+      "epoch": 0.5351351351351351,
+      "grad_norm": 1.9422366619110107,
+      "learning_rate": 0.00010648044692737431,
+      "loss": 1.421,
+      "step": 99
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 1.494828462600708,
+      "learning_rate": 0.00010547486033519554,
+      "loss": 1.2746,
+      "step": 100
+    },
+    {
+      "epoch": 0.5459459459459459,
+      "grad_norm": 2.1698765754699707,
+      "learning_rate": 0.00010446927374301676,
+      "loss": 1.3989,
+      "step": 101
+    },
+    {
+      "epoch": 0.5513513513513514,
+      "grad_norm": 1.3124092817306519,
+      "learning_rate": 0.000103463687150838,
+      "loss": 1.3855,
+      "step": 102
+    },
+    {
+      "epoch": 0.5567567567567567,
+      "grad_norm": 1.4328157901763916,
+      "learning_rate": 0.00010245810055865923,
+      "loss": 1.4112,
+      "step": 103
+    },
+    {
+      "epoch": 0.5621621621621622,
+      "grad_norm": 1.3698210716247559,
+      "learning_rate": 0.00010145251396648045,
+      "loss": 1.3152,
+      "step": 104
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 1.291865348815918,
+      "learning_rate": 0.00010044692737430168,
+      "loss": 1.3646,
+      "step": 105
+    },
+    {
+      "epoch": 0.572972972972973,
+      "grad_norm": 1.4178961515426636,
+      "learning_rate": 9.944134078212291e-05,
+      "loss": 1.2852,
+      "step": 106
+    },
+    {
+      "epoch": 0.5783783783783784,
+      "grad_norm": 1.1877104043960571,
+      "learning_rate": 9.843575418994413e-05,
+      "loss": 1.3402,
+      "step": 107
+    },
+    {
+      "epoch": 0.5837837837837838,
+      "grad_norm": 1.4503647089004517,
+      "learning_rate": 9.743016759776537e-05,
+      "loss": 1.3028,
+      "step": 108
+    },
+    {
+      "epoch": 0.5891891891891892,
+      "grad_norm": 1.3877456188201904,
+      "learning_rate": 9.64245810055866e-05,
+      "loss": 1.3231,
+      "step": 109
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 1.4520429372787476,
+      "learning_rate": 9.541899441340782e-05,
+      "loss": 1.2608,
+      "step": 110
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.1344528198242188,
+      "learning_rate": 9.441340782122905e-05,
+      "loss": 1.3409,
+      "step": 111
+    },
+    {
+      "epoch": 0.6054054054054054,
+      "grad_norm": 1.9510555267333984,
+      "learning_rate": 9.34078212290503e-05,
+      "loss": 1.2762,
+      "step": 112
+    },
+    {
+      "epoch": 0.6108108108108108,
+      "grad_norm": 1.6498372554779053,
+      "learning_rate": 9.240223463687152e-05,
+      "loss": 1.3558,
+      "step": 113
+    },
+    {
+      "epoch": 0.6162162162162163,
+      "grad_norm": 1.3852072954177856,
+      "learning_rate": 9.139664804469274e-05,
+      "loss": 1.3515,
+      "step": 114
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 1.516605019569397,
+      "learning_rate": 9.039106145251397e-05,
+      "loss": 1.3595,
+      "step": 115
+    },
+    {
+      "epoch": 0.6270270270270271,
+      "grad_norm": 1.387160062789917,
+      "learning_rate": 8.938547486033519e-05,
+      "loss": 1.2759,
+      "step": 116
+    },
+    {
+      "epoch": 0.6324324324324324,
+      "grad_norm": 1.218645691871643,
+      "learning_rate": 8.837988826815642e-05,
+      "loss": 1.3228,
+      "step": 117
+    },
+    {
+      "epoch": 0.6378378378378379,
+      "grad_norm": 1.1323994398117065,
+      "learning_rate": 8.737430167597766e-05,
+      "loss": 1.3792,
+      "step": 118
+    },
+    {
+      "epoch": 0.6432432432432432,
+      "grad_norm": 1.492294430732727,
+      "learning_rate": 8.63687150837989e-05,
+      "loss": 1.2875,
+      "step": 119
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 1.343035340309143,
+      "learning_rate": 8.536312849162011e-05,
+      "loss": 1.2473,
+      "step": 120
+    },
+    {
+      "epoch": 0.654054054054054,
+      "grad_norm": 1.3583838939666748,
+      "learning_rate": 8.435754189944134e-05,
+      "loss": 1.367,
+      "step": 121
+    },
+    {
+      "epoch": 0.6594594594594595,
+      "grad_norm": 1.4810901880264282,
+      "learning_rate": 8.335195530726259e-05,
+      "loss": 1.3429,
+      "step": 122
+    },
+    {
+      "epoch": 0.6648648648648648,
+      "grad_norm": 1.1570441722869873,
+      "learning_rate": 8.234636871508382e-05,
+      "loss": 1.269,
+      "step": 123
+    },
+    {
+      "epoch": 0.6702702702702703,
+      "grad_norm": 1.2883822917938232,
+      "learning_rate": 8.134078212290503e-05,
+      "loss": 1.2602,
+      "step": 124
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 1.3522834777832031,
+      "learning_rate": 8.033519553072626e-05,
+      "loss": 1.2891,
+      "step": 125
+    },
+    {
+      "epoch": 0.6810810810810811,
+      "grad_norm": 1.0803565979003906,
+      "learning_rate": 7.932960893854748e-05,
+      "loss": 1.2391,
+      "step": 126
+    },
+    {
+      "epoch": 0.6864864864864865,
+      "grad_norm": 1.2738792896270752,
+      "learning_rate": 7.832402234636872e-05,
+      "loss": 1.2819,
+      "step": 127
+    },
+    {
+      "epoch": 0.6918918918918919,
+      "grad_norm": 1.2565838098526,
+      "learning_rate": 7.731843575418995e-05,
+      "loss": 1.3168,
+      "step": 128
+    },
+    {
+      "epoch": 0.6972972972972973,
+      "grad_norm": 1.1551238298416138,
+      "learning_rate": 7.631284916201119e-05,
+      "loss": 1.3582,
+      "step": 129
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 1.153626799583435,
+      "learning_rate": 7.53072625698324e-05,
+      "loss": 1.2153,
+      "step": 130
+    },
+    {
+      "epoch": 0.7081081081081081,
+      "grad_norm": 1.3645069599151611,
+      "learning_rate": 7.430167597765365e-05,
+      "loss": 1.2957,
+      "step": 131
+    },
+    {
+      "epoch": 0.7135135135135136,
+      "grad_norm": 1.1639150381088257,
+      "learning_rate": 7.329608938547488e-05,
+      "loss": 1.2426,
+      "step": 132
+    },
+    {
+      "epoch": 0.7189189189189189,
+      "grad_norm": 1.2247486114501953,
+      "learning_rate": 7.22905027932961e-05,
+      "loss": 1.2479,
+      "step": 133
+    },
+    {
+      "epoch": 0.7243243243243244,
+      "grad_norm": 1.3136733770370483,
+      "learning_rate": 7.128491620111732e-05,
+      "loss": 1.2577,
+      "step": 134
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "grad_norm": 1.129638910293579,
+      "learning_rate": 7.027932960893855e-05,
+      "loss": 1.2942,
+      "step": 135
+    },
+    {
+      "epoch": 0.7351351351351352,
+      "grad_norm": 1.5812125205993652,
+      "learning_rate": 6.927374301675977e-05,
+      "loss": 1.3149,
+      "step": 136
+    },
+    {
+      "epoch": 0.7405405405405405,
+      "grad_norm": 1.1031138896942139,
+      "learning_rate": 6.826815642458102e-05,
+      "loss": 1.2825,
+      "step": 137
+    },
+    {
+      "epoch": 0.745945945945946,
+      "grad_norm": 1.4569562673568726,
+      "learning_rate": 6.726256983240225e-05,
+      "loss": 1.3553,
+      "step": 138
+    },
+    {
+      "epoch": 0.7513513513513513,
+      "grad_norm": 1.351787805557251,
+      "learning_rate": 6.625698324022346e-05,
+      "loss": 1.3805,
+      "step": 139
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 1.4399067163467407,
+      "learning_rate": 6.52513966480447e-05,
+      "loss": 1.3488,
+      "step": 140
+    },
+    {
+      "epoch": 0.7621621621621621,
+      "grad_norm": 1.097604751586914,
+      "learning_rate": 6.424581005586592e-05,
+      "loss": 1.2444,
+      "step": 141
+    },
+    {
+      "epoch": 0.7675675675675676,
+      "grad_norm": 1.2245107889175415,
+      "learning_rate": 6.324022346368715e-05,
+      "loss": 1.2415,
+      "step": 142
+    },
+    {
+      "epoch": 0.772972972972973,
+      "grad_norm": 1.2633042335510254,
+      "learning_rate": 6.223463687150838e-05,
+      "loss": 1.1964,
+      "step": 143
+    },
+    {
+      "epoch": 0.7783783783783784,
+      "grad_norm": 1.1645766496658325,
+      "learning_rate": 6.122905027932962e-05,
+      "loss": 1.1874,
+      "step": 144
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "grad_norm": 1.013777494430542,
+      "learning_rate": 6.022346368715084e-05,
+      "loss": 1.2065,
+      "step": 145
+    },
+    {
+      "epoch": 0.7891891891891892,
+      "grad_norm": 1.1051980257034302,
+      "learning_rate": 5.921787709497206e-05,
+      "loss": 1.2878,
+      "step": 146
+    },
+    {
+      "epoch": 0.7945945945945946,
+      "grad_norm": 1.0944007635116577,
+      "learning_rate": 5.82122905027933e-05,
+      "loss": 1.2634,
+      "step": 147
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1613037586212158,
+      "learning_rate": 5.720670391061454e-05,
+      "loss": 1.3074,
+      "step": 148
+    },
+    {
+      "epoch": 0.8054054054054054,
+      "grad_norm": 1.0192413330078125,
+      "learning_rate": 5.620111731843576e-05,
+      "loss": 1.1785,
+      "step": 149
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 1.0536669492721558,
+      "learning_rate": 5.5195530726256985e-05,
+      "loss": 1.2221,
+      "step": 150
+    },
+    {
+      "epoch": 0.8162162162162162,
+      "grad_norm": 1.260764241218567,
+      "learning_rate": 5.418994413407821e-05,
+      "loss": 1.1202,
+      "step": 151
+    },
+    {
+      "epoch": 0.8216216216216217,
+      "grad_norm": 1.1566349267959595,
+      "learning_rate": 5.3184357541899446e-05,
+      "loss": 1.2774,
+      "step": 152
+    },
+    {
+      "epoch": 0.827027027027027,
+      "grad_norm": 1.132250189781189,
+      "learning_rate": 5.2178770949720676e-05,
+      "loss": 1.2011,
+      "step": 153
+    },
+    {
+      "epoch": 0.8324324324324325,
+      "grad_norm": 1.0502394437789917,
+      "learning_rate": 5.11731843575419e-05,
+      "loss": 1.2538,
+      "step": 154
+    },
+    {
+      "epoch": 0.8378378378378378,
+      "grad_norm": 2.7037501335144043,
+      "learning_rate": 5.016759776536313e-05,
+      "loss": 1.4687,
+      "step": 155
+    },
+    {
+      "epoch": 0.8432432432432433,
+      "grad_norm": 1.1927903890609741,
+      "learning_rate": 4.916201117318436e-05,
+      "loss": 1.2044,
+      "step": 156
+    },
+    {
+      "epoch": 0.8486486486486486,
+      "grad_norm": 1.0077776908874512,
+      "learning_rate": 4.815642458100559e-05,
+      "loss": 1.1471,
+      "step": 157
+    },
+    {
+      "epoch": 0.8540540540540541,
+      "grad_norm": 0.9799959659576416,
+      "learning_rate": 4.715083798882682e-05,
+      "loss": 1.2181,
+      "step": 158
+    },
+    {
+      "epoch": 0.8594594594594595,
+      "grad_norm": 1.0267740488052368,
+      "learning_rate": 4.614525139664805e-05,
+      "loss": 1.244,
+      "step": 159
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 3.7082221508026123,
+      "learning_rate": 4.5139664804469276e-05,
+      "loss": 2.2304,
+      "step": 160
+    },
+    {
+      "epoch": 0.8702702702702703,
+      "grad_norm": 1.0884734392166138,
+      "learning_rate": 4.413407821229051e-05,
+      "loss": 1.1469,
+      "step": 161
+    },
+    {
+      "epoch": 0.8756756756756757,
+      "grad_norm": 1.1083415746688843,
+      "learning_rate": 4.312849162011173e-05,
+      "loss": 1.2713,
+      "step": 162
+    },
+    {
+      "epoch": 0.8810810810810811,
+      "grad_norm": 1.0334668159484863,
+      "learning_rate": 4.212290502793296e-05,
+      "loss": 1.0654,
+      "step": 163
+    },
+    {
+      "epoch": 0.8864864864864865,
+      "grad_norm": 0.9540927410125732,
+      "learning_rate": 4.111731843575419e-05,
+      "loss": 1.1151,
+      "step": 164
+    },
+    {
+      "epoch": 0.8918918918918919,
+      "grad_norm": 0.9412338137626648,
+      "learning_rate": 4.0111731843575415e-05,
+      "loss": 1.2111,
+      "step": 165
+    },
+    {
+      "epoch": 0.8972972972972973,
+      "grad_norm": 1.0096511840820312,
+      "learning_rate": 3.910614525139665e-05,
+      "loss": 1.3087,
+      "step": 166
+    },
+    {
+      "epoch": 0.9027027027027027,
+      "grad_norm": 1.0874724388122559,
+      "learning_rate": 3.8100558659217876e-05,
+      "loss": 1.1717,
+      "step": 167
+    },
+    {
+      "epoch": 0.9081081081081082,
+      "grad_norm": 0.9713255167007446,
+      "learning_rate": 3.709497206703911e-05,
+      "loss": 1.1705,
+      "step": 168
+    },
+    {
+      "epoch": 0.9135135135135135,
+      "grad_norm": 0.9664978981018066,
+      "learning_rate": 3.608938547486034e-05,
+      "loss": 1.2627,
+      "step": 169
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 0.966834306716919,
+      "learning_rate": 3.508379888268157e-05,
+      "loss": 1.1916,
+      "step": 170
+    },
+    {
+      "epoch": 0.9243243243243243,
+      "grad_norm": 1.0459810495376587,
+      "learning_rate": 3.40782122905028e-05,
+      "loss": 1.1613,
+      "step": 171
+    },
+    {
+      "epoch": 0.9297297297297298,
+      "grad_norm": 1.3951828479766846,
+      "learning_rate": 3.307262569832403e-05,
+      "loss": 1.1818,
+      "step": 172
+    },
+    {
+      "epoch": 0.9351351351351351,
+      "grad_norm": 1.0367494821548462,
+      "learning_rate": 3.206703910614525e-05,
+      "loss": 1.0986,
+      "step": 173
+    },
+    {
+      "epoch": 0.9405405405405406,
+      "grad_norm": 0.9425138831138611,
+      "learning_rate": 3.106145251396648e-05,
+      "loss": 1.1385,
+      "step": 174
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.9617014527320862,
+      "learning_rate": 3.0055865921787714e-05,
+      "loss": 1.1954,
+      "step": 175
+    },
+    {
+      "epoch": 0.9513513513513514,
+      "grad_norm": 0.9694061279296875,
+      "learning_rate": 2.9050279329608944e-05,
+      "loss": 1.2628,
+      "step": 176
+    },
+    {
+      "epoch": 0.9567567567567568,
+      "grad_norm": 0.9338908195495605,
+      "learning_rate": 2.8044692737430168e-05,
+      "loss": 1.1221,
+      "step": 177
+    },
+    {
+      "epoch": 0.9621621621621622,
+      "grad_norm": 0.8477990031242371,
+      "learning_rate": 2.70391061452514e-05,
+      "loss": 1.1914,
+      "step": 178
+    },
+    {
+      "epoch": 0.9675675675675676,
+      "grad_norm": 0.8513604998588562,
+      "learning_rate": 2.603351955307263e-05,
+      "loss": 1.1203,
+      "step": 179
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 1.0121779441833496,
+      "learning_rate": 2.5027932960893856e-05,
+      "loss": 1.1387,
+      "step": 180
+    },
+    {
+      "epoch": 0.9783783783783784,
+      "grad_norm": 0.8904174566268921,
+      "learning_rate": 2.4022346368715086e-05,
+      "loss": 1.1362,
+      "step": 181
+    },
+    {
+      "epoch": 0.9837837837837838,
+      "grad_norm": 0.9687130451202393,
+      "learning_rate": 2.3016759776536314e-05,
+      "loss": 1.1407,
+      "step": 182
+    },
+    {
+      "epoch": 0.9891891891891892,
+      "grad_norm": 0.936590850353241,
+      "learning_rate": 2.2011173184357544e-05,
+      "loss": 1.1859,
+      "step": 183
+    },
+    {
+      "epoch": 0.9945945945945946,
+      "grad_norm": 0.8786422610282898,
+      "learning_rate": 2.100558659217877e-05,
+      "loss": 1.184,
+      "step": 184
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.894349217414856,
+      "learning_rate": 2e-05,
+      "loss": 0.9644,
+      "step": 185
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 185,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.38021889121321e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}