Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Qwen/Qwen2-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "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_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

added_tokens.json

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

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Qwen/Qwen2-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "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_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.41.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe7157df403e3af3e0328886829a32f76957b8b56c99caedb1921f2356c63c5
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146796ccef716e4bde6ae0a28aa6018afee4c506905e99a2131b356a13741114
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee4e44c5766fb4e3e19837f05c4ecb8dd65b0e917d14ca246436388cc5c01a2
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c6d17fbc1de294bf0b2891b568870bdf8d6293db48d691b64be3e63427402c
+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 +1,20 @@
+{
+  "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 +1,43 @@
+{
+  "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.026314635323012148,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 8.771545107670716e-05,
+      "grad_norm": 28.291993022356824,
+      "learning_rate": 4.385964912280702e-08,
+      "loss": 0.9764,
+      "step": 1
+    },
+    {
+      "epoch": 0.00017543090215341433,
+      "grad_norm": 11.00431285069151,
+      "learning_rate": 8.771929824561404e-08,
+      "loss": 0.7373,
+      "step": 2
+    },
+    {
+      "epoch": 0.0002631463532301215,
+      "grad_norm": 19.575902791602918,
+      "learning_rate": 1.3157894736842107e-07,
+      "loss": 0.92,
+      "step": 3
+    },
+    {
+      "epoch": 0.00035086180430682866,
+      "grad_norm": 28.862884630243123,
+      "learning_rate": 1.7543859649122808e-07,
+      "loss": 0.9196,
+      "step": 4
+    },
+    {
+      "epoch": 0.0004385772553835358,
+      "grad_norm": 15.982248327528751,
+      "learning_rate": 2.192982456140351e-07,
+      "loss": 0.8366,
+      "step": 5
+    },
+    {
+      "epoch": 0.000526292706460243,
+      "grad_norm": 31.85723876161732,
+      "learning_rate": 2.6315789473684213e-07,
+      "loss": 0.9335,
+      "step": 6
+    },
+    {
+      "epoch": 0.0006140081575369502,
+      "grad_norm": 21.310207454796295,
+      "learning_rate": 3.070175438596491e-07,
+      "loss": 0.8362,
+      "step": 7
+    },
+    {
+      "epoch": 0.0007017236086136573,
+      "grad_norm": 20.052830776823505,
+      "learning_rate": 3.5087719298245616e-07,
+      "loss": 0.8015,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007894390596903645,
+      "grad_norm": 16.06788143210757,
+      "learning_rate": 3.9473684210526315e-07,
+      "loss": 0.8729,
+      "step": 9
+    },
+    {
+      "epoch": 0.0008771545107670716,
+      "grad_norm": 29.100726513914584,
+      "learning_rate": 4.385964912280702e-07,
+      "loss": 0.9058,
+      "step": 10
+    },
+    {
+      "epoch": 0.0009648699618437788,
+      "grad_norm": 13.993390572028792,
+      "learning_rate": 4.824561403508772e-07,
+      "loss": 0.7093,
+      "step": 11
+    },
+    {
+      "epoch": 0.001052585412920486,
+      "grad_norm": 21.107935511000072,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 0.8955,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011403008639971931,
+      "grad_norm": 13.66193898339087,
+      "learning_rate": 5.701754385964912e-07,
+      "loss": 0.7219,
+      "step": 13
+    },
+    {
+      "epoch": 0.0012280163150739003,
+      "grad_norm": 10.537203866107753,
+      "learning_rate": 6.140350877192982e-07,
+      "loss": 0.8429,
+      "step": 14
+    },
+    {
+      "epoch": 0.0013157317661506075,
+      "grad_norm": 12.393106853157317,
+      "learning_rate": 6.578947368421053e-07,
+      "loss": 0.6708,
+      "step": 15
+    },
+    {
+      "epoch": 0.0014034472172273146,
+      "grad_norm": 8.734604355126535,
+      "learning_rate": 7.017543859649123e-07,
+      "loss": 0.6507,
+      "step": 16
+    },
+    {
+      "epoch": 0.0014911626683040218,
+      "grad_norm": 9.124362491394539,
+      "learning_rate": 7.456140350877194e-07,
+      "loss": 0.838,
+      "step": 17
+    },
+    {
+      "epoch": 0.001578878119380729,
+      "grad_norm": 8.958389642999963,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 0.6849,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016665935704574361,
+      "grad_norm": 11.542677492312867,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.6926,
+      "step": 19
+    },
+    {
+      "epoch": 0.0017543090215341433,
+      "grad_norm": 8.045066225626593,
+      "learning_rate": 8.771929824561404e-07,
+      "loss": 0.7006,
+      "step": 20
+    },
+    {
+      "epoch": 0.0018420244726108505,
+      "grad_norm": 8.146906074379428,
+      "learning_rate": 9.210526315789474e-07,
+      "loss": 0.6737,
+      "step": 21
+    },
+    {
+      "epoch": 0.0019297399236875576,
+      "grad_norm": 6.502955757535831,
+      "learning_rate": 9.649122807017545e-07,
+      "loss": 0.7495,
+      "step": 22
+    },
+    {
+      "epoch": 0.002017455374764265,
+      "grad_norm": 8.736982858234592,
+      "learning_rate": 1.0087719298245615e-06,
+      "loss": 0.7324,
+      "step": 23
+    },
+    {
+      "epoch": 0.002105170825840972,
+      "grad_norm": 7.851959741269017,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 0.6686,
+      "step": 24
+    },
+    {
+      "epoch": 0.002192886276917679,
+      "grad_norm": 8.594840793358543,
+      "learning_rate": 1.0964912280701756e-06,
+      "loss": 0.8064,
+      "step": 25
+    },
+    {
+      "epoch": 0.0022806017279943863,
+      "grad_norm": 8.935665287337994,
+      "learning_rate": 1.1403508771929824e-06,
+      "loss": 0.6751,
+      "step": 26
+    },
+    {
+      "epoch": 0.0023683171790710934,
+      "grad_norm": 11.146850280588064,
+      "learning_rate": 1.1842105263157894e-06,
+      "loss": 0.7884,
+      "step": 27
+    },
+    {
+      "epoch": 0.0024560326301478006,
+      "grad_norm": 6.917869007862471,
+      "learning_rate": 1.2280701754385965e-06,
+      "loss": 0.8772,
+      "step": 28
+    },
+    {
+      "epoch": 0.0025437480812245078,
+      "grad_norm": 9.32145567192897,
+      "learning_rate": 1.2719298245614037e-06,
+      "loss": 0.6486,
+      "step": 29
+    },
+    {
+      "epoch": 0.002631463532301215,
+      "grad_norm": 7.83399807213587,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.7793,
+      "step": 30
+    },
+    {
+      "epoch": 0.002719178983377922,
+      "grad_norm": 5.701851482721999,
+      "learning_rate": 1.3596491228070178e-06,
+      "loss": 0.6418,
+      "step": 31
+    },
+    {
+      "epoch": 0.0028068944344546293,
+      "grad_norm": 6.357569510522249,
+      "learning_rate": 1.4035087719298246e-06,
+      "loss": 0.7803,
+      "step": 32
+    },
+    {
+      "epoch": 0.0028946098855313364,
+      "grad_norm": 6.1458878660724,
+      "learning_rate": 1.4473684210526317e-06,
+      "loss": 0.6075,
+      "step": 33
+    },
+    {
+      "epoch": 0.0029823253366080436,
+      "grad_norm": 5.258525934759675,
+      "learning_rate": 1.4912280701754387e-06,
+      "loss": 0.7558,
+      "step": 34
+    },
+    {
+      "epoch": 0.0030700407876847508,
+      "grad_norm": 5.96497463401995,
+      "learning_rate": 1.5350877192982458e-06,
+      "loss": 0.5807,
+      "step": 35
+    },
+    {
+      "epoch": 0.003157756238761458,
+      "grad_norm": 9.97378904781871,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.6766,
+      "step": 36
+    },
+    {
+      "epoch": 0.003245471689838165,
+      "grad_norm": 10.558130153122322,
+      "learning_rate": 1.6228070175438598e-06,
+      "loss": 0.6318,
+      "step": 37
+    },
+    {
+      "epoch": 0.0033331871409148723,
+      "grad_norm": 7.730592682668347,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.5723,
+      "step": 38
+    },
+    {
+      "epoch": 0.0034209025919915794,
+      "grad_norm": 6.513997535111305,
+      "learning_rate": 1.710526315789474e-06,
+      "loss": 0.7381,
+      "step": 39
+    },
+    {
+      "epoch": 0.0035086180430682866,
+      "grad_norm": 6.4186997859745185,
+      "learning_rate": 1.7543859649122807e-06,
+      "loss": 0.676,
+      "step": 40
+    },
+    {
+      "epoch": 0.0035963334941449938,
+      "grad_norm": 4.789756704738587,
+      "learning_rate": 1.798245614035088e-06,
+      "loss": 0.8106,
+      "step": 41
+    },
+    {
+      "epoch": 0.003684048945221701,
+      "grad_norm": 8.552415866186008,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 0.7834,
+      "step": 42
+    },
+    {
+      "epoch": 0.003771764396298408,
+      "grad_norm": 5.104236885105078,
+      "learning_rate": 1.8859649122807019e-06,
+      "loss": 0.6694,
+      "step": 43
+    },
+    {
+      "epoch": 0.0038594798473751152,
+      "grad_norm": 6.998642641947579,
+      "learning_rate": 1.929824561403509e-06,
+      "loss": 0.7184,
+      "step": 44
+    },
+    {
+      "epoch": 0.003947195298451822,
+      "grad_norm": 6.754484565741454,
+      "learning_rate": 1.973684210526316e-06,
+      "loss": 0.7682,
+      "step": 45
+    },
+    {
+      "epoch": 0.00403491074952853,
+      "grad_norm": 5.702466747706841,
+      "learning_rate": 2.017543859649123e-06,
+      "loss": 0.7167,
+      "step": 46
+    },
+    {
+      "epoch": 0.004122626200605236,
+      "grad_norm": 7.038100758557257,
+      "learning_rate": 2.06140350877193e-06,
+      "loss": 0.6709,
+      "step": 47
+    },
+    {
+      "epoch": 0.004210341651681944,
+      "grad_norm": 8.659378609826204,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.6508,
+      "step": 48
+    },
+    {
+      "epoch": 0.004298057102758651,
+      "grad_norm": 9.315174303463822,
+      "learning_rate": 2.149122807017544e-06,
+      "loss": 0.6168,
+      "step": 49
+    },
+    {
+      "epoch": 0.004385772553835358,
+      "grad_norm": 7.447716885721135,
+      "learning_rate": 2.192982456140351e-06,
+      "loss": 0.6738,
+      "step": 50
+    },
+    {
+      "epoch": 0.004473488004912065,
+      "grad_norm": 5.600770404460154,
+      "learning_rate": 2.236842105263158e-06,
+      "loss": 0.6311,
+      "step": 51
+    },
+    {
+      "epoch": 0.004561203455988773,
+      "grad_norm": 7.059691201242354,
+      "learning_rate": 2.280701754385965e-06,
+      "loss": 0.7204,
+      "step": 52
+    },
+    {
+      "epoch": 0.004648918907065479,
+      "grad_norm": 5.589092290239263,
+      "learning_rate": 2.324561403508772e-06,
+      "loss": 0.7266,
+      "step": 53
+    },
+    {
+      "epoch": 0.004736634358142187,
+      "grad_norm": 5.801762781587569,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.5336,
+      "step": 54
+    },
+    {
+      "epoch": 0.004824349809218894,
+      "grad_norm": 5.599754768073974,
+      "learning_rate": 2.412280701754386e-06,
+      "loss": 0.6338,
+      "step": 55
+    },
+    {
+      "epoch": 0.004912065260295601,
+      "grad_norm": 5.66437398031977,
+      "learning_rate": 2.456140350877193e-06,
+      "loss": 0.7813,
+      "step": 56
+    },
+    {
+      "epoch": 0.004999780711372308,
+      "grad_norm": 6.32022790188225,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6613,
+      "step": 57
+    },
+    {
+      "epoch": 0.0050874961624490156,
+      "grad_norm": 8.01474270706056,
+      "learning_rate": 2.5438596491228075e-06,
+      "loss": 0.6451,
+      "step": 58
+    },
+    {
+      "epoch": 0.005175211613525722,
+      "grad_norm": 6.586182462850705,
+      "learning_rate": 2.5877192982456147e-06,
+      "loss": 0.6984,
+      "step": 59
+    },
+    {
+      "epoch": 0.00526292706460243,
+      "grad_norm": 5.61553252576188,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.5773,
+      "step": 60
+    },
+    {
+      "epoch": 0.005350642515679137,
+      "grad_norm": 5.5274818204706895,
+      "learning_rate": 2.6754385964912284e-06,
+      "loss": 0.6083,
+      "step": 61
+    },
+    {
+      "epoch": 0.005438357966755844,
+      "grad_norm": 3.8762804528384254,
+      "learning_rate": 2.7192982456140356e-06,
+      "loss": 0.7174,
+      "step": 62
+    },
+    {
+      "epoch": 0.005526073417832551,
+      "grad_norm": 5.248404081335598,
+      "learning_rate": 2.7631578947368424e-06,
+      "loss": 0.7066,
+      "step": 63
+    },
+    {
+      "epoch": 0.0056137888689092585,
+      "grad_norm": 7.214109517049078,
+      "learning_rate": 2.8070175438596493e-06,
+      "loss": 0.692,
+      "step": 64
+    },
+    {
+      "epoch": 0.005701504319985965,
+      "grad_norm": 5.429278596290352,
+      "learning_rate": 2.8508771929824565e-06,
+      "loss": 0.6145,
+      "step": 65
+    },
+    {
+      "epoch": 0.005789219771062673,
+      "grad_norm": 17.638205100824422,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 0.7677,
+      "step": 66
+    },
+    {
+      "epoch": 0.00587693522213938,
+      "grad_norm": 5.677374136021176,
+      "learning_rate": 2.9385964912280706e-06,
+      "loss": 0.6779,
+      "step": 67
+    },
+    {
+      "epoch": 0.005964650673216087,
+      "grad_norm": 5.453107411280262,
+      "learning_rate": 2.9824561403508774e-06,
+      "loss": 0.6428,
+      "step": 68
+    },
+    {
+      "epoch": 0.006052366124292794,
+      "grad_norm": 5.888626008478417,
+      "learning_rate": 3.0263157894736843e-06,
+      "loss": 0.6342,
+      "step": 69
+    },
+    {
+      "epoch": 0.0061400815753695015,
+      "grad_norm": 5.3185045733144225,
+      "learning_rate": 3.0701754385964915e-06,
+      "loss": 0.5644,
+      "step": 70
+    },
+    {
+      "epoch": 0.006227797026446208,
+      "grad_norm": 4.902919731780363,
+      "learning_rate": 3.1140350877192988e-06,
+      "loss": 0.709,
+      "step": 71
+    },
+    {
+      "epoch": 0.006315512477522916,
+      "grad_norm": 8.773622618503456,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.6674,
+      "step": 72
+    },
+    {
+      "epoch": 0.006403227928599623,
+      "grad_norm": 6.7570883776978174,
+      "learning_rate": 3.2017543859649124e-06,
+      "loss": 0.6918,
+      "step": 73
+    },
+    {
+      "epoch": 0.00649094337967633,
+      "grad_norm": 5.597179964370573,
+      "learning_rate": 3.2456140350877197e-06,
+      "loss": 0.7119,
+      "step": 74
+    },
+    {
+      "epoch": 0.006578658830753037,
+      "grad_norm": 5.4824260737552795,
+      "learning_rate": 3.289473684210527e-06,
+      "loss": 0.5667,
+      "step": 75
+    },
+    {
+      "epoch": 0.0066663742818297445,
+      "grad_norm": 6.083422094529157,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.5972,
+      "step": 76
+    },
+    {
+      "epoch": 0.006754089732906451,
+      "grad_norm": 6.688559230122185,
+      "learning_rate": 3.3771929824561406e-06,
+      "loss": 0.6079,
+      "step": 77
+    },
+    {
+      "epoch": 0.006841805183983159,
+      "grad_norm": 4.675152512564395,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.6431,
+      "step": 78
+    },
+    {
+      "epoch": 0.006929520635059866,
+      "grad_norm": 6.61824094926871,
+      "learning_rate": 3.464912280701755e-06,
+      "loss": 0.7219,
+      "step": 79
+    },
+    {
+      "epoch": 0.007017236086136573,
+      "grad_norm": 4.3090639659166685,
+      "learning_rate": 3.5087719298245615e-06,
+      "loss": 0.6267,
+      "step": 80
+    },
+    {
+      "epoch": 0.00710495153721328,
+      "grad_norm": 5.908526205124108,
+      "learning_rate": 3.5526315789473687e-06,
+      "loss": 0.5598,
+      "step": 81
+    },
+    {
+      "epoch": 0.0071926669882899875,
+      "grad_norm": 4.954945711406169,
+      "learning_rate": 3.596491228070176e-06,
+      "loss": 0.6251,
+      "step": 82
+    },
+    {
+      "epoch": 0.007280382439366694,
+      "grad_norm": 6.403352381905709,
+      "learning_rate": 3.640350877192983e-06,
+      "loss": 0.6921,
+      "step": 83
+    },
+    {
+      "epoch": 0.007368097890443402,
+      "grad_norm": 5.8960340556018505,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.5803,
+      "step": 84
+    },
+    {
+      "epoch": 0.007455813341520109,
+      "grad_norm": 5.5832723717085795,
+      "learning_rate": 3.728070175438597e-06,
+      "loss": 0.7109,
+      "step": 85
+    },
+    {
+      "epoch": 0.007543528792596816,
+      "grad_norm": 6.9538610646678425,
+      "learning_rate": 3.7719298245614037e-06,
+      "loss": 0.57,
+      "step": 86
+    },
+    {
+      "epoch": 0.007631244243673523,
+      "grad_norm": 4.9040721673618615,
+      "learning_rate": 3.815789473684211e-06,
+      "loss": 0.6681,
+      "step": 87
+    },
+    {
+      "epoch": 0.0077189596947502305,
+      "grad_norm": 4.367227562952691,
+      "learning_rate": 3.859649122807018e-06,
+      "loss": 0.5881,
+      "step": 88
+    },
+    {
+      "epoch": 0.007806675145826937,
+      "grad_norm": 6.135869823936115,
+      "learning_rate": 3.903508771929825e-06,
+      "loss": 0.6333,
+      "step": 89
+    },
+    {
+      "epoch": 0.007894390596903644,
+      "grad_norm": 5.26232269598073,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.6228,
+      "step": 90
+    },
+    {
+      "epoch": 0.007982106047980352,
+      "grad_norm": 5.478510766614749,
+      "learning_rate": 3.991228070175439e-06,
+      "loss": 0.6889,
+      "step": 91
+    },
+    {
+      "epoch": 0.00806982149905706,
+      "grad_norm": 7.252221492478827,
+      "learning_rate": 4.035087719298246e-06,
+      "loss": 0.6726,
+      "step": 92
+    },
+    {
+      "epoch": 0.008157536950133767,
+      "grad_norm": 6.810323867433885,
+      "learning_rate": 4.078947368421053e-06,
+      "loss": 0.6186,
+      "step": 93
+    },
+    {
+      "epoch": 0.008245252401210473,
+      "grad_norm": 5.1477310672971965,
+      "learning_rate": 4.12280701754386e-06,
+      "loss": 0.6739,
+      "step": 94
+    },
+    {
+      "epoch": 0.00833296785228718,
+      "grad_norm": 4.455009313283226,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6676,
+      "step": 95
+    },
+    {
+      "epoch": 0.008420683303363888,
+      "grad_norm": 4.854476484535793,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.624,
+      "step": 96
+    },
+    {
+      "epoch": 0.008508398754440595,
+      "grad_norm": 8.775528791539337,
+      "learning_rate": 4.254385964912281e-06,
+      "loss": 0.7236,
+      "step": 97
+    },
+    {
+      "epoch": 0.008596114205517301,
+      "grad_norm": 4.656928105654083,
+      "learning_rate": 4.298245614035088e-06,
+      "loss": 0.4853,
+      "step": 98
+    },
+    {
+      "epoch": 0.008683829656594009,
+      "grad_norm": 6.1151229878888795,
+      "learning_rate": 4.342105263157895e-06,
+      "loss": 0.6611,
+      "step": 99
+    },
+    {
+      "epoch": 0.008771545107670716,
+      "grad_norm": 4.846266795088099,
+      "learning_rate": 4.385964912280702e-06,
+      "loss": 0.6899,
+      "step": 100
+    },
+    {
+      "epoch": 0.008859260558747424,
+      "grad_norm": 5.63076019856985,
+      "learning_rate": 4.429824561403509e-06,
+      "loss": 0.7394,
+      "step": 101
+    },
+    {
+      "epoch": 0.00894697600982413,
+      "grad_norm": 6.152211661702361,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.6366,
+      "step": 102
+    },
+    {
+      "epoch": 0.009034691460900838,
+      "grad_norm": 5.271237730819475,
+      "learning_rate": 4.517543859649123e-06,
+      "loss": 0.6776,
+      "step": 103
+    },
+    {
+      "epoch": 0.009122406911977545,
+      "grad_norm": 6.150704296921181,
+      "learning_rate": 4.56140350877193e-06,
+      "loss": 0.7287,
+      "step": 104
+    },
+    {
+      "epoch": 0.009210122363054253,
+      "grad_norm": 5.511353295743786,
+      "learning_rate": 4.605263157894737e-06,
+      "loss": 0.7156,
+      "step": 105
+    },
+    {
+      "epoch": 0.009297837814130959,
+      "grad_norm": 5.651321362023493,
+      "learning_rate": 4.649122807017544e-06,
+      "loss": 0.5971,
+      "step": 106
+    },
+    {
+      "epoch": 0.009385553265207666,
+      "grad_norm": 4.521052312786367,
+      "learning_rate": 4.692982456140351e-06,
+      "loss": 0.662,
+      "step": 107
+    },
+    {
+      "epoch": 0.009473268716284374,
+      "grad_norm": 6.5893774516601775,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.6838,
+      "step": 108
+    },
+    {
+      "epoch": 0.009560984167361081,
+      "grad_norm": 7.413604525506308,
+      "learning_rate": 4.780701754385965e-06,
+      "loss": 0.6798,
+      "step": 109
+    },
+    {
+      "epoch": 0.009648699618437787,
+      "grad_norm": 5.258683042524991,
+      "learning_rate": 4.824561403508772e-06,
+      "loss": 0.7137,
+      "step": 110
+    },
+    {
+      "epoch": 0.009736415069514495,
+      "grad_norm": 3.56629655229689,
+      "learning_rate": 4.8684210526315795e-06,
+      "loss": 0.5524,
+      "step": 111
+    },
+    {
+      "epoch": 0.009824130520591202,
+      "grad_norm": 7.972594797604,
+      "learning_rate": 4.912280701754386e-06,
+      "loss": 0.7946,
+      "step": 112
+    },
+    {
+      "epoch": 0.00991184597166791,
+      "grad_norm": 5.9169587346561965,
+      "learning_rate": 4.956140350877193e-06,
+      "loss": 0.6985,
+      "step": 113
+    },
+    {
+      "epoch": 0.009999561422744616,
+      "grad_norm": 4.9028768240583895,
+      "learning_rate": 5e-06,
+      "loss": 0.7471,
+      "step": 114
+    },
+    {
+      "epoch": 0.010087276873821324,
+      "grad_norm": 4.952040118758915,
+      "learning_rate": 4.999999903143301e-06,
+      "loss": 0.6645,
+      "step": 115
+    },
+    {
+      "epoch": 0.010174992324898031,
+      "grad_norm": 5.307375041926707,
+      "learning_rate": 4.999999612573212e-06,
+      "loss": 0.6568,
+      "step": 116
+    },
+    {
+      "epoch": 0.010262707775974739,
+      "grad_norm": 4.417210142946582,
+      "learning_rate": 4.9999991282897545e-06,
+      "loss": 0.6633,
+      "step": 117
+    },
+    {
+      "epoch": 0.010350423227051445,
+      "grad_norm": 6.813103500844099,
+      "learning_rate": 4.999998450292966e-06,
+      "loss": 0.7479,
+      "step": 118
+    },
+    {
+      "epoch": 0.010438138678128152,
+      "grad_norm": 5.220452049535287,
+      "learning_rate": 4.9999975785829e-06,
+      "loss": 0.5982,
+      "step": 119
+    },
+    {
+      "epoch": 0.01052585412920486,
+      "grad_norm": 6.470241976711781,
+      "learning_rate": 4.999996513159624e-06,
+      "loss": 0.5915,
+      "step": 120
+    },
+    {
+      "epoch": 0.010613569580281567,
+      "grad_norm": 5.236784827517624,
+      "learning_rate": 4.99999525402322e-06,
+      "loss": 0.665,
+      "step": 121
+    },
+    {
+      "epoch": 0.010701285031358273,
+      "grad_norm": 5.5322906674158565,
+      "learning_rate": 4.999993801173785e-06,
+      "loss": 0.473,
+      "step": 122
+    },
+    {
+      "epoch": 0.01078900048243498,
+      "grad_norm": 5.643434680672429,
+      "learning_rate": 4.999992154611433e-06,
+      "loss": 0.5802,
+      "step": 123
+    },
+    {
+      "epoch": 0.010876715933511688,
+      "grad_norm": 4.909123022379139,
+      "learning_rate": 4.9999903143362905e-06,
+      "loss": 0.6103,
+      "step": 124
+    },
+    {
+      "epoch": 0.010964431384588396,
+      "grad_norm": 7.046173121098522,
+      "learning_rate": 4.999988280348501e-06,
+      "loss": 0.6601,
+      "step": 125
+    },
+    {
+      "epoch": 0.011052146835665102,
+      "grad_norm": 5.567754476589664,
+      "learning_rate": 4.99998605264822e-06,
+      "loss": 0.7144,
+      "step": 126
+    },
+    {
+      "epoch": 0.01113986228674181,
+      "grad_norm": 6.670512866037107,
+      "learning_rate": 4.999983631235623e-06,
+      "loss": 0.5034,
+      "step": 127
+    },
+    {
+      "epoch": 0.011227577737818517,
+      "grad_norm": 5.068760146843144,
+      "learning_rate": 4.999981016110896e-06,
+      "loss": 0.5965,
+      "step": 128
+    },
+    {
+      "epoch": 0.011315293188895225,
+      "grad_norm": 5.493410339028754,
+      "learning_rate": 4.999978207274243e-06,
+      "loss": 0.6697,
+      "step": 129
+    },
+    {
+      "epoch": 0.01140300863997193,
+      "grad_norm": 5.662089015796081,
+      "learning_rate": 4.999975204725879e-06,
+      "loss": 0.7182,
+      "step": 130
+    },
+    {
+      "epoch": 0.011490724091048638,
+      "grad_norm": 3.734356064938746,
+      "learning_rate": 4.999972008466039e-06,
+      "loss": 0.632,
+      "step": 131
+    },
+    {
+      "epoch": 0.011578439542125346,
+      "grad_norm": 4.29907687663725,
+      "learning_rate": 4.99996861849497e-06,
+      "loss": 0.6321,
+      "step": 132
+    },
+    {
+      "epoch": 0.011666154993202053,
+      "grad_norm": 5.292963722155827,
+      "learning_rate": 4.999965034812934e-06,
+      "loss": 0.5768,
+      "step": 133
+    },
+    {
+      "epoch": 0.01175387044427876,
+      "grad_norm": 4.564589196086129,
+      "learning_rate": 4.99996125742021e-06,
+      "loss": 0.5991,
+      "step": 134
+    },
+    {
+      "epoch": 0.011841585895355467,
+      "grad_norm": 5.889974426321806,
+      "learning_rate": 4.99995728631709e-06,
+      "loss": 0.568,
+      "step": 135
+    },
+    {
+      "epoch": 0.011929301346432174,
+      "grad_norm": 4.903556688362067,
+      "learning_rate": 4.999953121503881e-06,
+      "loss": 0.6221,
+      "step": 136
+    },
+    {
+      "epoch": 0.012017016797508882,
+      "grad_norm": 4.652137494582458,
+      "learning_rate": 4.999948762980906e-06,
+      "loss": 0.6499,
+      "step": 137
+    },
+    {
+      "epoch": 0.012104732248585588,
+      "grad_norm": 7.2681565015460965,
+      "learning_rate": 4.999944210748504e-06,
+      "loss": 0.7997,
+      "step": 138
+    },
+    {
+      "epoch": 0.012192447699662295,
+      "grad_norm": 4.498966830496647,
+      "learning_rate": 4.999939464807027e-06,
+      "loss": 0.7033,
+      "step": 139
+    },
+    {
+      "epoch": 0.012280163150739003,
+      "grad_norm": 5.658829625864849,
+      "learning_rate": 4.999934525156842e-06,
+      "loss": 0.6234,
+      "step": 140
+    },
+    {
+      "epoch": 0.01236787860181571,
+      "grad_norm": 6.170987539440289,
+      "learning_rate": 4.9999293917983325e-06,
+      "loss": 0.7359,
+      "step": 141
+    },
+    {
+      "epoch": 0.012455594052892417,
+      "grad_norm": 4.889450035742974,
+      "learning_rate": 4.999924064731896e-06,
+      "loss": 0.6418,
+      "step": 142
+    },
+    {
+      "epoch": 0.012543309503969124,
+      "grad_norm": 5.565665252735285,
+      "learning_rate": 4.9999185439579445e-06,
+      "loss": 0.8114,
+      "step": 143
+    },
+    {
+      "epoch": 0.012631024955045832,
+      "grad_norm": 5.009655972578068,
+      "learning_rate": 4.9999128294769075e-06,
+      "loss": 0.7307,
+      "step": 144
+    },
+    {
+      "epoch": 0.01271874040612254,
+      "grad_norm": 5.011444448419762,
+      "learning_rate": 4.999906921289227e-06,
+      "loss": 0.6434,
+      "step": 145
+    },
+    {
+      "epoch": 0.012806455857199245,
+      "grad_norm": 5.91290249112379,
+      "learning_rate": 4.999900819395361e-06,
+      "loss": 0.7576,
+      "step": 146
+    },
+    {
+      "epoch": 0.012894171308275953,
+      "grad_norm": 5.291827066915767,
+      "learning_rate": 4.9998945237957814e-06,
+      "loss": 0.717,
+      "step": 147
+    },
+    {
+      "epoch": 0.01298188675935266,
+      "grad_norm": 6.889695918810895,
+      "learning_rate": 4.9998880344909765e-06,
+      "loss": 0.6566,
+      "step": 148
+    },
+    {
+      "epoch": 0.013069602210429368,
+      "grad_norm": 4.139725258131711,
+      "learning_rate": 4.999881351481449e-06,
+      "loss": 0.6139,
+      "step": 149
+    },
+    {
+      "epoch": 0.013157317661506074,
+      "grad_norm": 5.041147601092224,
+      "learning_rate": 4.999874474767718e-06,
+      "loss": 0.7046,
+      "step": 150
+    },
+    {
+      "epoch": 0.013245033112582781,
+      "grad_norm": 4.850191233243735,
+      "learning_rate": 4.999867404350315e-06,
+      "loss": 0.6494,
+      "step": 151
+    },
+    {
+      "epoch": 0.013332748563659489,
+      "grad_norm": 5.608814210289025,
+      "learning_rate": 4.999860140229788e-06,
+      "loss": 0.8654,
+      "step": 152
+    },
+    {
+      "epoch": 0.013420464014736197,
+      "grad_norm": 4.097824317856954,
+      "learning_rate": 4.9998526824067e-06,
+      "loss": 0.6889,
+      "step": 153
+    },
+    {
+      "epoch": 0.013508179465812903,
+      "grad_norm": 6.425927321695068,
+      "learning_rate": 4.999845030881629e-06,
+      "loss": 0.5837,
+      "step": 154
+    },
+    {
+      "epoch": 0.01359589491688961,
+      "grad_norm": 7.686652681051417,
+      "learning_rate": 4.999837185655168e-06,
+      "loss": 0.6869,
+      "step": 155
+    },
+    {
+      "epoch": 0.013683610367966318,
+      "grad_norm": 6.199666417167642,
+      "learning_rate": 4.9998291467279245e-06,
+      "loss": 0.7371,
+      "step": 156
+    },
+    {
+      "epoch": 0.013771325819043024,
+      "grad_norm": 6.797879751043678,
+      "learning_rate": 4.999820914100522e-06,
+      "loss": 0.6912,
+      "step": 157
+    },
+    {
+      "epoch": 0.013859041270119731,
+      "grad_norm": 9.837640179642968,
+      "learning_rate": 4.999812487773597e-06,
+      "loss": 0.8045,
+      "step": 158
+    },
+    {
+      "epoch": 0.013946756721196439,
+      "grad_norm": 6.620454193744729,
+      "learning_rate": 4.9998038677478044e-06,
+      "loss": 0.6018,
+      "step": 159
+    },
+    {
+      "epoch": 0.014034472172273146,
+      "grad_norm": 4.952380418390811,
+      "learning_rate": 4.99979505402381e-06,
+      "loss": 0.5851,
+      "step": 160
+    },
+    {
+      "epoch": 0.014122187623349852,
+      "grad_norm": 4.571346505498035,
+      "learning_rate": 4.999786046602299e-06,
+      "loss": 0.6633,
+      "step": 161
+    },
+    {
+      "epoch": 0.01420990307442656,
+      "grad_norm": 6.745466717777739,
+      "learning_rate": 4.999776845483968e-06,
+      "loss": 0.714,
+      "step": 162
+    },
+    {
+      "epoch": 0.014297618525503267,
+      "grad_norm": 4.888639355192875,
+      "learning_rate": 4.999767450669531e-06,
+      "loss": 0.5328,
+      "step": 163
+    },
+    {
+      "epoch": 0.014385333976579975,
+      "grad_norm": 5.263414218540685,
+      "learning_rate": 4.999757862159713e-06,
+      "loss": 0.6746,
+      "step": 164
+    },
+    {
+      "epoch": 0.014473049427656681,
+      "grad_norm": 5.8723140369149895,
+      "learning_rate": 4.99974807995526e-06,
+      "loss": 0.7101,
+      "step": 165
+    },
+    {
+      "epoch": 0.014560764878733388,
+      "grad_norm": 4.125348885535371,
+      "learning_rate": 4.999738104056931e-06,
+      "loss": 0.6418,
+      "step": 166
+    },
+    {
+      "epoch": 0.014648480329810096,
+      "grad_norm": 5.079939786355144,
+      "learning_rate": 4.999727934465495e-06,
+      "loss": 0.6757,
+      "step": 167
+    },
+    {
+      "epoch": 0.014736195780886804,
+      "grad_norm": 4.436648943550616,
+      "learning_rate": 4.999717571181742e-06,
+      "loss": 0.6878,
+      "step": 168
+    },
+    {
+      "epoch": 0.01482391123196351,
+      "grad_norm": 4.6070293178483706,
+      "learning_rate": 4.999707014206475e-06,
+      "loss": 0.6882,
+      "step": 169
+    },
+    {
+      "epoch": 0.014911626683040217,
+      "grad_norm": 4.337658765605819,
+      "learning_rate": 4.999696263540513e-06,
+      "loss": 0.6418,
+      "step": 170
+    },
+    {
+      "epoch": 0.014999342134116925,
+      "grad_norm": 5.834498841218243,
+      "learning_rate": 4.999685319184688e-06,
+      "loss": 0.6367,
+      "step": 171
+    },
+    {
+      "epoch": 0.015087057585193632,
+      "grad_norm": 6.027148776110112,
+      "learning_rate": 4.999674181139848e-06,
+      "loss": 0.7505,
+      "step": 172
+    },
+    {
+      "epoch": 0.015174773036270338,
+      "grad_norm": 4.712652033599274,
+      "learning_rate": 4.999662849406855e-06,
+      "loss": 0.7515,
+      "step": 173
+    },
+    {
+      "epoch": 0.015262488487347046,
+      "grad_norm": 5.325275991673836,
+      "learning_rate": 4.99965132398659e-06,
+      "loss": 0.7871,
+      "step": 174
+    },
+    {
+      "epoch": 0.015350203938423753,
+      "grad_norm": 5.006048437293231,
+      "learning_rate": 4.999639604879943e-06,
+      "loss": 0.6038,
+      "step": 175
+    },
+    {
+      "epoch": 0.015437919389500461,
+      "grad_norm": 4.692976251794895,
+      "learning_rate": 4.999627692087824e-06,
+      "loss": 0.7106,
+      "step": 176
+    },
+    {
+      "epoch": 0.015525634840577167,
+      "grad_norm": 6.484912012474024,
+      "learning_rate": 4.999615585611156e-06,
+      "loss": 0.6456,
+      "step": 177
+    },
+    {
+      "epoch": 0.015613350291653874,
+      "grad_norm": 7.072312221146792,
+      "learning_rate": 4.999603285450875e-06,
+      "loss": 0.6986,
+      "step": 178
+    },
+    {
+      "epoch": 0.015701065742730582,
+      "grad_norm": 5.072158684292459,
+      "learning_rate": 4.999590791607936e-06,
+      "loss": 0.6386,
+      "step": 179
+    },
+    {
+      "epoch": 0.015788781193807288,
+      "grad_norm": 5.674801641765509,
+      "learning_rate": 4.999578104083307e-06,
+      "loss": 0.6512,
+      "step": 180
+    },
+    {
+      "epoch": 0.015876496644883997,
+      "grad_norm": 6.011232915930249,
+      "learning_rate": 4.9995652228779715e-06,
+      "loss": 0.6166,
+      "step": 181
+    },
+    {
+      "epoch": 0.015964212095960703,
+      "grad_norm": 7.067996556252431,
+      "learning_rate": 4.999552147992926e-06,
+      "loss": 0.8316,
+      "step": 182
+    },
+    {
+      "epoch": 0.01605192754703741,
+      "grad_norm": 6.191586224655665,
+      "learning_rate": 4.999538879429183e-06,
+      "loss": 0.7167,
+      "step": 183
+    },
+    {
+      "epoch": 0.01613964299811412,
+      "grad_norm": 5.40861794404673,
+      "learning_rate": 4.999525417187774e-06,
+      "loss": 0.6604,
+      "step": 184
+    },
+    {
+      "epoch": 0.016227358449190824,
+      "grad_norm": 5.619694849325643,
+      "learning_rate": 4.999511761269739e-06,
+      "loss": 0.7141,
+      "step": 185
+    },
+    {
+      "epoch": 0.016315073900267534,
+      "grad_norm": 7.467663008400906,
+      "learning_rate": 4.999497911676138e-06,
+      "loss": 0.6086,
+      "step": 186
+    },
+    {
+      "epoch": 0.01640278935134424,
+      "grad_norm": 4.645589903763359,
+      "learning_rate": 4.999483868408043e-06,
+      "loss": 0.6932,
+      "step": 187
+    },
+    {
+      "epoch": 0.016490504802420945,
+      "grad_norm": 4.819294533224638,
+      "learning_rate": 4.999469631466544e-06,
+      "loss": 0.6256,
+      "step": 188
+    },
+    {
+      "epoch": 0.016578220253497655,
+      "grad_norm": 4.711171445741636,
+      "learning_rate": 4.999455200852741e-06,
+      "loss": 0.7445,
+      "step": 189
+    },
+    {
+      "epoch": 0.01666593570457436,
+      "grad_norm": 4.371758877075776,
+      "learning_rate": 4.999440576567755e-06,
+      "loss": 0.6801,
+      "step": 190
+    },
+    {
+      "epoch": 0.016753651155651066,
+      "grad_norm": 5.761171404408883,
+      "learning_rate": 4.999425758612718e-06,
+      "loss": 0.6701,
+      "step": 191
+    },
+    {
+      "epoch": 0.016841366606727776,
+      "grad_norm": 4.340375314807721,
+      "learning_rate": 4.999410746988778e-06,
+      "loss": 0.5556,
+      "step": 192
+    },
+    {
+      "epoch": 0.01692908205780448,
+      "grad_norm": 4.775058922031801,
+      "learning_rate": 4.9993955416970986e-06,
+      "loss": 0.6915,
+      "step": 193
+    },
+    {
+      "epoch": 0.01701679750888119,
+      "grad_norm": 4.301940379009061,
+      "learning_rate": 4.999380142738857e-06,
+      "loss": 0.6982,
+      "step": 194
+    },
+    {
+      "epoch": 0.017104512959957897,
+      "grad_norm": 4.746670538298819,
+      "learning_rate": 4.9993645501152485e-06,
+      "loss": 0.5392,
+      "step": 195
+    },
+    {
+      "epoch": 0.017192228411034603,
+      "grad_norm": 5.312812102176541,
+      "learning_rate": 4.999348763827479e-06,
+      "loss": 0.6254,
+      "step": 196
+    },
+    {
+      "epoch": 0.017279943862111312,
+      "grad_norm": 6.073252701324542,
+      "learning_rate": 4.999332783876774e-06,
+      "loss": 0.7221,
+      "step": 197
+    },
+    {
+      "epoch": 0.017367659313188018,
+      "grad_norm": 6.783014797465277,
+      "learning_rate": 4.999316610264369e-06,
+      "loss": 0.5914,
+      "step": 198
+    },
+    {
+      "epoch": 0.017455374764264724,
+      "grad_norm": 5.105373260000072,
+      "learning_rate": 4.999300242991519e-06,
+      "loss": 0.4895,
+      "step": 199
+    },
+    {
+      "epoch": 0.017543090215341433,
+      "grad_norm": 5.3256898167081825,
+      "learning_rate": 4.999283682059493e-06,
+      "loss": 0.714,
+      "step": 200
+    },
+    {
+      "epoch": 0.01763080566641814,
+      "grad_norm": 7.815945435660424,
+      "learning_rate": 4.999266927469572e-06,
+      "loss": 0.7691,
+      "step": 201
+    },
+    {
+      "epoch": 0.017718521117494848,
+      "grad_norm": 4.350216346007481,
+      "learning_rate": 4.999249979223056e-06,
+      "loss": 0.7205,
+      "step": 202
+    },
+    {
+      "epoch": 0.017806236568571554,
+      "grad_norm": 4.167534183562087,
+      "learning_rate": 4.999232837321257e-06,
+      "loss": 0.6716,
+      "step": 203
+    },
+    {
+      "epoch": 0.01789395201964826,
+      "grad_norm": 6.564156035042191,
+      "learning_rate": 4.999215501765504e-06,
+      "loss": 0.6139,
+      "step": 204
+    },
+    {
+      "epoch": 0.01798166747072497,
+      "grad_norm": 4.58988335300785,
+      "learning_rate": 4.9991979725571395e-06,
+      "loss": 0.6241,
+      "step": 205
+    },
+    {
+      "epoch": 0.018069382921801675,
+      "grad_norm": 7.14774553510386,
+      "learning_rate": 4.999180249697524e-06,
+      "loss": 0.7338,
+      "step": 206
+    },
+    {
+      "epoch": 0.01815709837287838,
+      "grad_norm": 4.3154768710391656,
+      "learning_rate": 4.999162333188028e-06,
+      "loss": 0.646,
+      "step": 207
+    },
+    {
+      "epoch": 0.01824481382395509,
+      "grad_norm": 3.930924147546703,
+      "learning_rate": 4.999144223030041e-06,
+      "loss": 0.7162,
+      "step": 208
+    },
+    {
+      "epoch": 0.018332529275031796,
+      "grad_norm": 3.75066761929553,
+      "learning_rate": 4.999125919224966e-06,
+      "loss": 0.6283,
+      "step": 209
+    },
+    {
+      "epoch": 0.018420244726108505,
+      "grad_norm": 4.916459254987505,
+      "learning_rate": 4.999107421774222e-06,
+      "loss": 0.6716,
+      "step": 210
+    },
+    {
+      "epoch": 0.01850796017718521,
+      "grad_norm": 4.570226928027306,
+      "learning_rate": 4.999088730679241e-06,
+      "loss": 0.6527,
+      "step": 211
+    },
+    {
+      "epoch": 0.018595675628261917,
+      "grad_norm": 3.6658012035372605,
+      "learning_rate": 4.999069845941472e-06,
+      "loss": 0.5452,
+      "step": 212
+    },
+    {
+      "epoch": 0.018683391079338627,
+      "grad_norm": 4.697816375671605,
+      "learning_rate": 4.999050767562379e-06,
+      "loss": 0.7316,
+      "step": 213
+    },
+    {
+      "epoch": 0.018771106530415332,
+      "grad_norm": 5.639876519194002,
+      "learning_rate": 4.99903149554344e-06,
+      "loss": 0.5152,
+      "step": 214
+    },
+    {
+      "epoch": 0.018858821981492038,
+      "grad_norm": 5.527702869650481,
+      "learning_rate": 4.999012029886147e-06,
+      "loss": 0.6119,
+      "step": 215
+    },
+    {
+      "epoch": 0.018946537432568748,
+      "grad_norm": 6.019639388484205,
+      "learning_rate": 4.998992370592008e-06,
+      "loss": 0.7366,
+      "step": 216
+    },
+    {
+      "epoch": 0.019034252883645453,
+      "grad_norm": 4.014799337285965,
+      "learning_rate": 4.998972517662549e-06,
+      "loss": 0.7088,
+      "step": 217
+    },
+    {
+      "epoch": 0.019121968334722163,
+      "grad_norm": 7.876499612097003,
+      "learning_rate": 4.998952471099307e-06,
+      "loss": 0.5565,
+      "step": 218
+    },
+    {
+      "epoch": 0.01920968378579887,
+      "grad_norm": 7.386792956892447,
+      "learning_rate": 4.998932230903835e-06,
+      "loss": 0.6387,
+      "step": 219
+    },
+    {
+      "epoch": 0.019297399236875575,
+      "grad_norm": 5.346097163630257,
+      "learning_rate": 4.998911797077701e-06,
+      "loss": 0.6237,
+      "step": 220
+    },
+    {
+      "epoch": 0.019385114687952284,
+      "grad_norm": 6.133310652425816,
+      "learning_rate": 4.998891169622488e-06,
+      "loss": 0.7428,
+      "step": 221
+    },
+    {
+      "epoch": 0.01947283013902899,
+      "grad_norm": 4.224801633855712,
+      "learning_rate": 4.998870348539797e-06,
+      "loss": 0.7206,
+      "step": 222
+    },
+    {
+      "epoch": 0.019560545590105696,
+      "grad_norm": 5.648869005800134,
+      "learning_rate": 4.998849333831238e-06,
+      "loss": 0.6249,
+      "step": 223
+    },
+    {
+      "epoch": 0.019648261041182405,
+      "grad_norm": 4.634920959306503,
+      "learning_rate": 4.998828125498441e-06,
+      "loss": 0.6764,
+      "step": 224
+    },
+    {
+      "epoch": 0.01973597649225911,
+      "grad_norm": 4.882651557085375,
+      "learning_rate": 4.998806723543049e-06,
+      "loss": 0.6682,
+      "step": 225
+    },
+    {
+      "epoch": 0.01982369194333582,
+      "grad_norm": 4.5073631852916645,
+      "learning_rate": 4.998785127966721e-06,
+      "loss": 0.7658,
+      "step": 226
+    },
+    {
+      "epoch": 0.019911407394412526,
+      "grad_norm": 6.444404326993186,
+      "learning_rate": 4.99876333877113e-06,
+      "loss": 0.7161,
+      "step": 227
+    },
+    {
+      "epoch": 0.019999122845489232,
+      "grad_norm": 5.926254683053582,
+      "learning_rate": 4.998741355957963e-06,
+      "loss": 0.6083,
+      "step": 228
+    },
+    {
+      "epoch": 0.02008683829656594,
+      "grad_norm": 4.715935033600424,
+      "learning_rate": 4.998719179528925e-06,
+      "loss": 0.5764,
+      "step": 229
+    },
+    {
+      "epoch": 0.020174553747642647,
+      "grad_norm": 4.06642116262848,
+      "learning_rate": 4.998696809485734e-06,
+      "loss": 0.6436,
+      "step": 230
+    },
+    {
+      "epoch": 0.020262269198719353,
+      "grad_norm": 4.060536926809771,
+      "learning_rate": 4.998674245830123e-06,
+      "loss": 0.6455,
+      "step": 231
+    },
+    {
+      "epoch": 0.020349984649796062,
+      "grad_norm": 5.769596888340199,
+      "learning_rate": 4.9986514885638405e-06,
+      "loss": 0.6422,
+      "step": 232
+    },
+    {
+      "epoch": 0.020437700100872768,
+      "grad_norm": 5.619149975421577,
+      "learning_rate": 4.99862853768865e-06,
+      "loss": 0.5151,
+      "step": 233
+    },
+    {
+      "epoch": 0.020525415551949477,
+      "grad_norm": 5.738973149236573,
+      "learning_rate": 4.998605393206329e-06,
+      "loss": 0.5698,
+      "step": 234
+    },
+    {
+      "epoch": 0.020613131003026183,
+      "grad_norm": 3.9117936997485443,
+      "learning_rate": 4.998582055118672e-06,
+      "loss": 0.6139,
+      "step": 235
+    },
+    {
+      "epoch": 0.02070084645410289,
+      "grad_norm": 5.594946157519774,
+      "learning_rate": 4.998558523427488e-06,
+      "loss": 0.6305,
+      "step": 236
+    },
+    {
+      "epoch": 0.0207885619051796,
+      "grad_norm": 3.7796595114227816,
+      "learning_rate": 4.998534798134598e-06,
+      "loss": 0.6064,
+      "step": 237
+    },
+    {
+      "epoch": 0.020876277356256304,
+      "grad_norm": 5.530110712124758,
+      "learning_rate": 4.998510879241842e-06,
+      "loss": 0.7404,
+      "step": 238
+    },
+    {
+      "epoch": 0.02096399280733301,
+      "grad_norm": 5.795681054870311,
+      "learning_rate": 4.998486766751073e-06,
+      "loss": 0.6637,
+      "step": 239
+    },
+    {
+      "epoch": 0.02105170825840972,
+      "grad_norm": 5.250443330736557,
+      "learning_rate": 4.99846246066416e-06,
+      "loss": 0.7229,
+      "step": 240
+    },
+    {
+      "epoch": 0.021139423709486425,
+      "grad_norm": 5.307033877732376,
+      "learning_rate": 4.998437960982985e-06,
+      "loss": 0.729,
+      "step": 241
+    },
+    {
+      "epoch": 0.021227139160563135,
+      "grad_norm": 4.264326950314863,
+      "learning_rate": 4.998413267709446e-06,
+      "loss": 0.6363,
+      "step": 242
+    },
+    {
+      "epoch": 0.02131485461163984,
+      "grad_norm": 4.56674428695937,
+      "learning_rate": 4.99838838084546e-06,
+      "loss": 0.573,
+      "step": 243
+    },
+    {
+      "epoch": 0.021402570062716546,
+      "grad_norm": 5.367393577306364,
+      "learning_rate": 4.998363300392951e-06,
+      "loss": 0.6187,
+      "step": 244
+    },
+    {
+      "epoch": 0.021490285513793256,
+      "grad_norm": 5.58627031411974,
+      "learning_rate": 4.998338026353865e-06,
+      "loss": 0.635,
+      "step": 245
+    },
+    {
+      "epoch": 0.02157800096486996,
+      "grad_norm": 4.1536241104050005,
+      "learning_rate": 4.9983125587301594e-06,
+      "loss": 0.7296,
+      "step": 246
+    },
+    {
+      "epoch": 0.021665716415946668,
+      "grad_norm": 5.369955138376355,
+      "learning_rate": 4.998286897523808e-06,
+      "loss": 0.5939,
+      "step": 247
+    },
+    {
+      "epoch": 0.021753431867023377,
+      "grad_norm": 4.749169550030242,
+      "learning_rate": 4.998261042736799e-06,
+      "loss": 0.7125,
+      "step": 248
+    },
+    {
+      "epoch": 0.021841147318100083,
+      "grad_norm": 3.847851803716185,
+      "learning_rate": 4.998234994371135e-06,
+      "loss": 0.6874,
+      "step": 249
+    },
+    {
+      "epoch": 0.021928862769176792,
+      "grad_norm": 6.3610718821634755,
+      "learning_rate": 4.998208752428836e-06,
+      "loss": 0.6839,
+      "step": 250
+    },
+    {
+      "epoch": 0.022016578220253498,
+      "grad_norm": 6.90892255007994,
+      "learning_rate": 4.998182316911934e-06,
+      "loss": 0.6706,
+      "step": 251
+    },
+    {
+      "epoch": 0.022104293671330204,
+      "grad_norm": 4.842858396629252,
+      "learning_rate": 4.998155687822478e-06,
+      "loss": 0.7887,
+      "step": 252
+    },
+    {
+      "epoch": 0.022192009122406913,
+      "grad_norm": 6.80960196083629,
+      "learning_rate": 4.99812886516253e-06,
+      "loss": 0.6891,
+      "step": 253
+    },
+    {
+      "epoch": 0.02227972457348362,
+      "grad_norm": 6.897100992823047,
+      "learning_rate": 4.998101848934171e-06,
+      "loss": 0.7213,
+      "step": 254
+    },
+    {
+      "epoch": 0.022367440024560325,
+      "grad_norm": 4.383904436150581,
+      "learning_rate": 4.9980746391394916e-06,
+      "loss": 0.5472,
+      "step": 255
+    },
+    {
+      "epoch": 0.022455155475637034,
+      "grad_norm": 6.136102422729719,
+      "learning_rate": 4.998047235780603e-06,
+      "loss": 0.7462,
+      "step": 256
+    },
+    {
+      "epoch": 0.02254287092671374,
+      "grad_norm": 5.873462354540876,
+      "learning_rate": 4.9980196388596255e-06,
+      "loss": 0.6893,
+      "step": 257
+    },
+    {
+      "epoch": 0.02263058637779045,
+      "grad_norm": 5.36389164609212,
+      "learning_rate": 4.9979918483787e-06,
+      "loss": 0.725,
+      "step": 258
+    },
+    {
+      "epoch": 0.022718301828867155,
+      "grad_norm": 6.634852411669424,
+      "learning_rate": 4.997963864339978e-06,
+      "loss": 0.7619,
+      "step": 259
+    },
+    {
+      "epoch": 0.02280601727994386,
+      "grad_norm": 4.201015694891079,
+      "learning_rate": 4.99793568674563e-06,
+      "loss": 0.653,
+      "step": 260
+    },
+    {
+      "epoch": 0.02289373273102057,
+      "grad_norm": 4.951129353141893,
+      "learning_rate": 4.997907315597836e-06,
+      "loss": 0.7543,
+      "step": 261
+    },
+    {
+      "epoch": 0.022981448182097276,
+      "grad_norm": 4.331792323630216,
+      "learning_rate": 4.997878750898798e-06,
+      "loss": 0.6553,
+      "step": 262
+    },
+    {
+      "epoch": 0.023069163633173982,
+      "grad_norm": 4.764837636647203,
+      "learning_rate": 4.997849992650727e-06,
+      "loss": 0.719,
+      "step": 263
+    },
+    {
+      "epoch": 0.02315687908425069,
+      "grad_norm": 7.315146297212186,
+      "learning_rate": 4.997821040855852e-06,
+      "loss": 0.8217,
+      "step": 264
+    },
+    {
+      "epoch": 0.023244594535327397,
+      "grad_norm": 4.5164891139288015,
+      "learning_rate": 4.997791895516417e-06,
+      "loss": 0.5553,
+      "step": 265
+    },
+    {
+      "epoch": 0.023332309986404107,
+      "grad_norm": 4.651549875308793,
+      "learning_rate": 4.99776255663468e-06,
+      "loss": 0.6981,
+      "step": 266
+    },
+    {
+      "epoch": 0.023420025437480813,
+      "grad_norm": 4.941120481014187,
+      "learning_rate": 4.997733024212913e-06,
+      "loss": 0.604,
+      "step": 267
+    },
+    {
+      "epoch": 0.02350774088855752,
+      "grad_norm": 6.3616778757465315,
+      "learning_rate": 4.997703298253406e-06,
+      "loss": 0.7253,
+      "step": 268
+    },
+    {
+      "epoch": 0.023595456339634228,
+      "grad_norm": 4.723855693485358,
+      "learning_rate": 4.997673378758462e-06,
+      "loss": 0.7335,
+      "step": 269
+    },
+    {
+      "epoch": 0.023683171790710934,
+      "grad_norm": 4.336523073382538,
+      "learning_rate": 4.997643265730399e-06,
+      "loss": 0.5665,
+      "step": 270
+    },
+    {
+      "epoch": 0.02377088724178764,
+      "grad_norm": 6.547875149524498,
+      "learning_rate": 4.997612959171549e-06,
+      "loss": 0.6542,
+      "step": 271
+    },
+    {
+      "epoch": 0.02385860269286435,
+      "grad_norm": 5.285021138793967,
+      "learning_rate": 4.997582459084264e-06,
+      "loss": 0.7824,
+      "step": 272
+    },
+    {
+      "epoch": 0.023946318143941055,
+      "grad_norm": 4.447718203152539,
+      "learning_rate": 4.9975517654709025e-06,
+      "loss": 0.6728,
+      "step": 273
+    },
+    {
+      "epoch": 0.024034033595017764,
+      "grad_norm": 4.323105158596241,
+      "learning_rate": 4.997520878333847e-06,
+      "loss": 0.6516,
+      "step": 274
+    },
+    {
+      "epoch": 0.02412174904609447,
+      "grad_norm": 4.091596093860627,
+      "learning_rate": 4.997489797675489e-06,
+      "loss": 0.5786,
+      "step": 275
+    },
+    {
+      "epoch": 0.024209464497171176,
+      "grad_norm": 4.50262054947591,
+      "learning_rate": 4.997458523498236e-06,
+      "loss": 0.6632,
+      "step": 276
+    },
+    {
+      "epoch": 0.024297179948247885,
+      "grad_norm": 5.394966563241667,
+      "learning_rate": 4.997427055804513e-06,
+      "loss": 0.7415,
+      "step": 277
+    },
+    {
+      "epoch": 0.02438489539932459,
+      "grad_norm": 5.134838704391961,
+      "learning_rate": 4.9973953945967565e-06,
+      "loss": 0.6225,
+      "step": 278
+    },
+    {
+      "epoch": 0.024472610850401297,
+      "grad_norm": 4.555937935551801,
+      "learning_rate": 4.9973635398774226e-06,
+      "loss": 0.7451,
+      "step": 279
+    },
+    {
+      "epoch": 0.024560326301478006,
+      "grad_norm": 4.014041307501394,
+      "learning_rate": 4.997331491648976e-06,
+      "loss": 0.607,
+      "step": 280
+    },
+    {
+      "epoch": 0.024648041752554712,
+      "grad_norm": 5.398424400960683,
+      "learning_rate": 4.9972992499139025e-06,
+      "loss": 0.665,
+      "step": 281
+    },
+    {
+      "epoch": 0.02473575720363142,
+      "grad_norm": 6.959554022697295,
+      "learning_rate": 4.9972668146746995e-06,
+      "loss": 0.8175,
+      "step": 282
+    },
+    {
+      "epoch": 0.024823472654708127,
+      "grad_norm": 5.048396931572014,
+      "learning_rate": 4.997234185933879e-06,
+      "loss": 0.6961,
+      "step": 283
+    },
+    {
+      "epoch": 0.024911188105784833,
+      "grad_norm": 4.737474855724115,
+      "learning_rate": 4.997201363693972e-06,
+      "loss": 0.5337,
+      "step": 284
+    },
+    {
+      "epoch": 0.024998903556861542,
+      "grad_norm": 7.374843310231967,
+      "learning_rate": 4.997168347957521e-06,
+      "loss": 0.6791,
+      "step": 285
+    },
+    {
+      "epoch": 0.025086619007938248,
+      "grad_norm": 4.306967488515473,
+      "learning_rate": 4.997135138727081e-06,
+      "loss": 0.8791,
+      "step": 286
+    },
+    {
+      "epoch": 0.025174334459014954,
+      "grad_norm": 3.7949900410813737,
+      "learning_rate": 4.99710173600523e-06,
+      "loss": 0.7743,
+      "step": 287
+    },
+    {
+      "epoch": 0.025262049910091663,
+      "grad_norm": 4.842604758031469,
+      "learning_rate": 4.997068139794554e-06,
+      "loss": 0.6602,
+      "step": 288
+    },
+    {
+      "epoch": 0.02534976536116837,
+      "grad_norm": 3.531764677671023,
+      "learning_rate": 4.9970343500976545e-06,
+      "loss": 0.6317,
+      "step": 289
+    },
+    {
+      "epoch": 0.02543748081224508,
+      "grad_norm": 5.68234167540357,
+      "learning_rate": 4.997000366917153e-06,
+      "loss": 0.7404,
+      "step": 290
+    },
+    {
+      "epoch": 0.025525196263321785,
+      "grad_norm": 4.623883782994243,
+      "learning_rate": 4.9969661902556804e-06,
+      "loss": 0.6093,
+      "step": 291
+    },
+    {
+      "epoch": 0.02561291171439849,
+      "grad_norm": 5.9956405593570175,
+      "learning_rate": 4.996931820115885e-06,
+      "loss": 0.6773,
+      "step": 292
+    },
+    {
+      "epoch": 0.0257006271654752,
+      "grad_norm": 5.06274620174889,
+      "learning_rate": 4.996897256500433e-06,
+      "loss": 0.7249,
+      "step": 293
+    },
+    {
+      "epoch": 0.025788342616551906,
+      "grad_norm": 5.989915075597491,
+      "learning_rate": 4.996862499411998e-06,
+      "loss": 0.7526,
+      "step": 294
+    },
+    {
+      "epoch": 0.02587605806762861,
+      "grad_norm": 4.58567195302804,
+      "learning_rate": 4.996827548853276e-06,
+      "loss": 0.6762,
+      "step": 295
+    },
+    {
+      "epoch": 0.02596377351870532,
+      "grad_norm": 4.097368677404026,
+      "learning_rate": 4.996792404826974e-06,
+      "loss": 0.6238,
+      "step": 296
+    },
+    {
+      "epoch": 0.026051488969782027,
+      "grad_norm": 4.021749832913485,
+      "learning_rate": 4.996757067335816e-06,
+      "loss": 0.7958,
+      "step": 297
+    },
+    {
+      "epoch": 0.026139204420858736,
+      "grad_norm": 4.679522912267575,
+      "learning_rate": 4.99672153638254e-06,
+      "loss": 0.6583,
+      "step": 298
+    },
+    {
+      "epoch": 0.026226919871935442,
+      "grad_norm": 4.256974035317045,
+      "learning_rate": 4.996685811969898e-06,
+      "loss": 0.6464,
+      "step": 299
+    },
+    {
+      "epoch": 0.026314635323012148,
+      "grad_norm": 4.4862335847168096,
+      "learning_rate": 4.996649894100659e-06,
+      "loss": 0.6116,
+      "step": 300
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 11400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7802380615680.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}