Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.9548387096774196,
+    "total_flos": 5.413829559357276e+17,
+    "train_loss": 0.04737277891541311,
+    "train_runtime": 1301.7465,
+    "train_samples_per_second": 15.216,
+    "train_steps_per_second": 0.237
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/cpfs04/user/liyizhi/models/Qwen2.5-Coder-3B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915c486c3f1aae1ae739427a5623b743a959afcdd29e2a3aa20fb6d809c02ba8
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e5270f16b894bbca1a3268a8172987b7d374b32ca3daf31f2acdfe4a7feb268
+size 1836696752

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 6794207232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.9548387096774196,
+    "total_flos": 5.413829559357276e+17,
+    "train_loss": 0.04737277891541311,
+    "train_runtime": 1301.7465,
+    "train_samples_per_second": 15.216,
+    "train_steps_per_second": 0.237
+}

trainer_log.jsonl

@@ -0,0 +1,309 @@
+{"current_steps": 1, "total_steps": 308, "loss": 0.2085, "lr": 1.6129032258064516e-06, "epoch": 0.012903225806451613, "percentage": 0.32, "elapsed_time": "0:00:03", "remaining_time": "0:17:01"}
+{"current_steps": 2, "total_steps": 308, "loss": 0.2026, "lr": 3.225806451612903e-06, "epoch": 0.025806451612903226, "percentage": 0.65, "elapsed_time": "0:00:07", "remaining_time": "0:20:12"}
+{"current_steps": 3, "total_steps": 308, "loss": 0.2162, "lr": 4.838709677419355e-06, "epoch": 0.03870967741935484, "percentage": 0.97, "elapsed_time": "0:00:13", "remaining_time": "0:23:33"}
+{"current_steps": 4, "total_steps": 308, "loss": 0.1839, "lr": 6.451612903225806e-06, "epoch": 0.05161290322580645, "percentage": 1.3, "elapsed_time": "0:00:18", "remaining_time": "0:23:39"}
+{"current_steps": 5, "total_steps": 308, "loss": 0.1952, "lr": 8.064516129032258e-06, "epoch": 0.06451612903225806, "percentage": 1.62, "elapsed_time": "0:00:21", "remaining_time": "0:22:09"}
+{"current_steps": 6, "total_steps": 308, "loss": 0.1879, "lr": 9.67741935483871e-06, "epoch": 0.07741935483870968, "percentage": 1.95, "elapsed_time": "0:00:25", "remaining_time": "0:21:27"}
+{"current_steps": 7, "total_steps": 308, "loss": 0.1501, "lr": 1.129032258064516e-05, "epoch": 0.09032258064516129, "percentage": 2.27, "elapsed_time": "0:00:30", "remaining_time": "0:21:53"}
+{"current_steps": 8, "total_steps": 308, "loss": 0.1489, "lr": 1.2903225806451613e-05, "epoch": 0.1032258064516129, "percentage": 2.6, "elapsed_time": "0:00:34", "remaining_time": "0:21:38"}
+{"current_steps": 9, "total_steps": 308, "loss": 0.1484, "lr": 1.4516129032258066e-05, "epoch": 0.11612903225806452, "percentage": 2.92, "elapsed_time": "0:00:37", "remaining_time": "0:21:02"}
+{"current_steps": 10, "total_steps": 308, "loss": 0.1388, "lr": 1.6129032258064517e-05, "epoch": 0.12903225806451613, "percentage": 3.25, "elapsed_time": "0:00:42", "remaining_time": "0:21:05"}
+{"current_steps": 11, "total_steps": 308, "loss": 0.1319, "lr": 1.774193548387097e-05, "epoch": 0.14193548387096774, "percentage": 3.57, "elapsed_time": "0:00:47", "remaining_time": "0:21:11"}
+{"current_steps": 12, "total_steps": 308, "loss": 0.1246, "lr": 1.935483870967742e-05, "epoch": 0.15483870967741936, "percentage": 3.9, "elapsed_time": "0:00:53", "remaining_time": "0:21:52"}
+{"current_steps": 13, "total_steps": 308, "loss": 0.1319, "lr": 2.0967741935483873e-05, "epoch": 0.16774193548387098, "percentage": 4.22, "elapsed_time": "0:00:56", "remaining_time": "0:21:30"}
+{"current_steps": 14, "total_steps": 308, "loss": 0.1191, "lr": 2.258064516129032e-05, "epoch": 0.18064516129032257, "percentage": 4.55, "elapsed_time": "0:01:00", "remaining_time": "0:21:01"}
+{"current_steps": 15, "total_steps": 308, "loss": 0.1248, "lr": 2.4193548387096777e-05, "epoch": 0.1935483870967742, "percentage": 4.87, "elapsed_time": "0:01:03", "remaining_time": "0:20:45"}
+{"current_steps": 16, "total_steps": 308, "loss": 0.124, "lr": 2.5806451612903226e-05, "epoch": 0.2064516129032258, "percentage": 5.19, "elapsed_time": "0:01:07", "remaining_time": "0:20:38"}
+{"current_steps": 17, "total_steps": 308, "loss": 0.1068, "lr": 2.7419354838709678e-05, "epoch": 0.21935483870967742, "percentage": 5.52, "elapsed_time": "0:01:10", "remaining_time": "0:20:10"}
+{"current_steps": 18, "total_steps": 308, "loss": 0.1245, "lr": 2.9032258064516133e-05, "epoch": 0.23225806451612904, "percentage": 5.84, "elapsed_time": "0:01:14", "remaining_time": "0:19:52"}
+{"current_steps": 19, "total_steps": 308, "loss": 0.1099, "lr": 3.0645161290322585e-05, "epoch": 0.24516129032258063, "percentage": 6.17, "elapsed_time": "0:01:19", "remaining_time": "0:20:06"}
+{"current_steps": 20, "total_steps": 308, "loss": 0.0959, "lr": 3.2258064516129034e-05, "epoch": 0.25806451612903225, "percentage": 6.49, "elapsed_time": "0:01:23", "remaining_time": "0:19:55"}
+{"current_steps": 21, "total_steps": 308, "loss": 0.0923, "lr": 3.387096774193548e-05, "epoch": 0.2709677419354839, "percentage": 6.82, "elapsed_time": "0:01:26", "remaining_time": "0:19:48"}
+{"current_steps": 22, "total_steps": 308, "loss": 0.1088, "lr": 3.548387096774194e-05, "epoch": 0.2838709677419355, "percentage": 7.14, "elapsed_time": "0:01:32", "remaining_time": "0:19:57"}
+{"current_steps": 23, "total_steps": 308, "loss": 0.0882, "lr": 3.7096774193548386e-05, "epoch": 0.2967741935483871, "percentage": 7.47, "elapsed_time": "0:01:35", "remaining_time": "0:19:46"}
+{"current_steps": 24, "total_steps": 308, "loss": 0.0992, "lr": 3.870967741935484e-05, "epoch": 0.3096774193548387, "percentage": 7.79, "elapsed_time": "0:01:39", "remaining_time": "0:19:33"}
+{"current_steps": 25, "total_steps": 308, "loss": 0.1224, "lr": 4.032258064516129e-05, "epoch": 0.3225806451612903, "percentage": 8.12, "elapsed_time": "0:01:43", "remaining_time": "0:19:28"}
+{"current_steps": 26, "total_steps": 308, "loss": 0.0846, "lr": 4.1935483870967746e-05, "epoch": 0.33548387096774196, "percentage": 8.44, "elapsed_time": "0:01:46", "remaining_time": "0:19:11"}
+{"current_steps": 27, "total_steps": 308, "loss": 0.0864, "lr": 4.3548387096774194e-05, "epoch": 0.34838709677419355, "percentage": 8.77, "elapsed_time": "0:01:51", "remaining_time": "0:19:22"}
+{"current_steps": 28, "total_steps": 308, "loss": 0.103, "lr": 4.516129032258064e-05, "epoch": 0.36129032258064514, "percentage": 9.09, "elapsed_time": "0:01:56", "remaining_time": "0:19:22"}
+{"current_steps": 29, "total_steps": 308, "loss": 0.1148, "lr": 4.67741935483871e-05, "epoch": 0.3741935483870968, "percentage": 9.42, "elapsed_time": "0:02:00", "remaining_time": "0:19:18"}
+{"current_steps": 30, "total_steps": 308, "loss": 0.0789, "lr": 4.8387096774193554e-05, "epoch": 0.3870967741935484, "percentage": 9.74, "elapsed_time": "0:02:03", "remaining_time": "0:19:06"}
+{"current_steps": 31, "total_steps": 308, "loss": 0.0844, "lr": 5e-05, "epoch": 0.4, "percentage": 10.06, "elapsed_time": "0:02:09", "remaining_time": "0:19:15"}
+{"current_steps": 32, "total_steps": 308, "loss": 0.0813, "lr": 4.999839214987031e-05, "epoch": 0.4129032258064516, "percentage": 10.39, "elapsed_time": "0:02:15", "remaining_time": "0:19:25"}
+{"current_steps": 33, "total_steps": 308, "loss": 0.0818, "lr": 4.9993568806295786e-05, "epoch": 0.4258064516129032, "percentage": 10.71, "elapsed_time": "0:02:18", "remaining_time": "0:19:11"}
+{"current_steps": 34, "total_steps": 308, "loss": 0.0844, "lr": 4.9985530589693516e-05, "epoch": 0.43870967741935485, "percentage": 11.04, "elapsed_time": "0:02:22", "remaining_time": "0:19:04"}
+{"current_steps": 35, "total_steps": 308, "loss": 0.0903, "lr": 4.997427853400333e-05, "epoch": 0.45161290322580644, "percentage": 11.36, "elapsed_time": "0:02:26", "remaining_time": "0:18:59"}
+{"current_steps": 36, "total_steps": 308, "loss": 0.0772, "lr": 4.995981408655473e-05, "epoch": 0.4645161290322581, "percentage": 11.69, "elapsed_time": "0:02:30", "remaining_time": "0:18:55"}
+{"current_steps": 37, "total_steps": 308, "loss": 0.0786, "lr": 4.9942139107880844e-05, "epoch": 0.4774193548387097, "percentage": 12.01, "elapsed_time": "0:02:33", "remaining_time": "0:18:42"}
+{"current_steps": 38, "total_steps": 308, "loss": 0.0948, "lr": 4.9921255871479e-05, "epoch": 0.49032258064516127, "percentage": 12.34, "elapsed_time": "0:02:36", "remaining_time": "0:18:30"}
+{"current_steps": 39, "total_steps": 308, "loss": 0.0805, "lr": 4.989716706351835e-05, "epoch": 0.5032258064516129, "percentage": 12.66, "elapsed_time": "0:02:42", "remaining_time": "0:18:40"}
+{"current_steps": 40, "total_steps": 308, "loss": 0.0899, "lr": 4.986987578249432e-05, "epoch": 0.5161290322580645, "percentage": 12.99, "elapsed_time": "0:02:47", "remaining_time": "0:18:38"}
+{"current_steps": 41, "total_steps": 308, "loss": 0.0849, "lr": 4.9839385538830104e-05, "epoch": 0.5290322580645161, "percentage": 13.31, "elapsed_time": "0:02:50", "remaining_time": "0:18:27"}
+{"current_steps": 42, "total_steps": 308, "loss": 0.0845, "lr": 4.980570025442507e-05, "epoch": 0.5419354838709678, "percentage": 13.64, "elapsed_time": "0:02:53", "remaining_time": "0:18:19"}
+{"current_steps": 43, "total_steps": 308, "loss": 0.0912, "lr": 4.9768824262150344e-05, "epoch": 0.5548387096774193, "percentage": 13.96, "elapsed_time": "0:02:57", "remaining_time": "0:18:13"}
+{"current_steps": 44, "total_steps": 308, "loss": 0.0907, "lr": 4.972876230529142e-05, "epoch": 0.567741935483871, "percentage": 14.29, "elapsed_time": "0:03:02", "remaining_time": "0:18:13"}
+{"current_steps": 45, "total_steps": 308, "loss": 0.063, "lr": 4.968551953693813e-05, "epoch": 0.5806451612903226, "percentage": 14.61, "elapsed_time": "0:03:05", "remaining_time": "0:18:07"}
+{"current_steps": 46, "total_steps": 308, "loss": 0.0816, "lr": 4.963910151932171e-05, "epoch": 0.5935483870967742, "percentage": 14.94, "elapsed_time": "0:03:09", "remaining_time": "0:18:01"}
+{"current_steps": 47, "total_steps": 308, "loss": 0.0815, "lr": 4.958951422309942e-05, "epoch": 0.6064516129032258, "percentage": 15.26, "elapsed_time": "0:03:13", "remaining_time": "0:17:54"}
+{"current_steps": 48, "total_steps": 308, "loss": 0.0834, "lr": 4.95367640265865e-05, "epoch": 0.6193548387096774, "percentage": 15.58, "elapsed_time": "0:03:16", "remaining_time": "0:17:46"}
+{"current_steps": 49, "total_steps": 308, "loss": 0.0818, "lr": 4.948085771493579e-05, "epoch": 0.632258064516129, "percentage": 15.91, "elapsed_time": "0:03:20", "remaining_time": "0:17:37"}
+{"current_steps": 50, "total_steps": 308, "loss": 0.077, "lr": 4.942180247926492e-05, "epoch": 0.6451612903225806, "percentage": 16.23, "elapsed_time": "0:03:24", "remaining_time": "0:17:36"}
+{"current_steps": 51, "total_steps": 308, "loss": 0.0869, "lr": 4.935960591573135e-05, "epoch": 0.6580645161290323, "percentage": 16.56, "elapsed_time": "0:03:29", "remaining_time": "0:17:37"}
+{"current_steps": 52, "total_steps": 308, "loss": 0.091, "lr": 4.929427602455532e-05, "epoch": 0.6709677419354839, "percentage": 16.88, "elapsed_time": "0:03:33", "remaining_time": "0:17:29"}
+{"current_steps": 53, "total_steps": 308, "loss": 0.0772, "lr": 4.922582120899072e-05, "epoch": 0.6838709677419355, "percentage": 17.21, "elapsed_time": "0:03:37", "remaining_time": "0:17:27"}
+{"current_steps": 54, "total_steps": 308, "loss": 0.0815, "lr": 4.91542502742443e-05, "epoch": 0.6967741935483871, "percentage": 17.53, "elapsed_time": "0:03:40", "remaining_time": "0:17:19"}
+{"current_steps": 55, "total_steps": 308, "loss": 0.0819, "lr": 4.907957242634299e-05, "epoch": 0.7096774193548387, "percentage": 17.86, "elapsed_time": "0:03:45", "remaining_time": "0:17:16"}
+{"current_steps": 56, "total_steps": 308, "loss": 0.0852, "lr": 4.900179727094978e-05, "epoch": 0.7225806451612903, "percentage": 18.18, "elapsed_time": "0:03:50", "remaining_time": "0:17:17"}
+{"current_steps": 57, "total_steps": 308, "loss": 0.0846, "lr": 4.8920934812128164e-05, "epoch": 0.7354838709677419, "percentage": 18.51, "elapsed_time": "0:03:53", "remaining_time": "0:17:10"}
+{"current_steps": 58, "total_steps": 308, "loss": 0.0918, "lr": 4.8836995451055344e-05, "epoch": 0.7483870967741936, "percentage": 18.83, "elapsed_time": "0:03:58", "remaining_time": "0:17:06"}
+{"current_steps": 59, "total_steps": 308, "loss": 0.0713, "lr": 4.874998998468433e-05, "epoch": 0.7612903225806451, "percentage": 19.16, "elapsed_time": "0:04:02", "remaining_time": "0:17:03"}
+{"current_steps": 60, "total_steps": 308, "loss": 0.0838, "lr": 4.865992960435514e-05, "epoch": 0.7741935483870968, "percentage": 19.48, "elapsed_time": "0:04:07", "remaining_time": "0:17:01"}
+{"current_steps": 61, "total_steps": 308, "loss": 0.0948, "lr": 4.856682589435531e-05, "epoch": 0.7870967741935484, "percentage": 19.81, "elapsed_time": "0:04:10", "remaining_time": "0:16:53"}
+{"current_steps": 62, "total_steps": 308, "loss": 0.076, "lr": 4.8470690830429823e-05, "epoch": 0.8, "percentage": 20.13, "elapsed_time": "0:04:13", "remaining_time": "0:16:46"}
+{"current_steps": 63, "total_steps": 308, "loss": 0.0887, "lr": 4.837153677824067e-05, "epoch": 0.8129032258064516, "percentage": 20.45, "elapsed_time": "0:04:17", "remaining_time": "0:16:40"}
+{"current_steps": 64, "total_steps": 308, "loss": 0.0752, "lr": 4.826937649177632e-05, "epoch": 0.8258064516129032, "percentage": 20.78, "elapsed_time": "0:04:23", "remaining_time": "0:16:43"}
+{"current_steps": 65, "total_steps": 308, "loss": 0.0701, "lr": 4.816422311171115e-05, "epoch": 0.8387096774193549, "percentage": 21.1, "elapsed_time": "0:04:27", "remaining_time": "0:16:38"}
+{"current_steps": 66, "total_steps": 308, "loss": 0.072, "lr": 4.805609016371522e-05, "epoch": 0.8516129032258064, "percentage": 21.43, "elapsed_time": "0:04:31", "remaining_time": "0:16:35"}
+{"current_steps": 67, "total_steps": 308, "loss": 0.0639, "lr": 4.7944991556714496e-05, "epoch": 0.864516129032258, "percentage": 21.75, "elapsed_time": "0:04:37", "remaining_time": "0:16:37"}
+{"current_steps": 68, "total_steps": 308, "loss": 0.0804, "lr": 4.783094158110174e-05, "epoch": 0.8774193548387097, "percentage": 22.08, "elapsed_time": "0:04:41", "remaining_time": "0:16:32"}
+{"current_steps": 69, "total_steps": 308, "loss": 0.0883, "lr": 4.7713954906898415e-05, "epoch": 0.8903225806451613, "percentage": 22.4, "elapsed_time": "0:04:45", "remaining_time": "0:16:27"}
+{"current_steps": 70, "total_steps": 308, "loss": 0.086, "lr": 4.759404658186765e-05, "epoch": 0.9032258064516129, "percentage": 22.73, "elapsed_time": "0:04:49", "remaining_time": "0:16:22"}
+{"current_steps": 71, "total_steps": 308, "loss": 0.0627, "lr": 4.747123202957872e-05, "epoch": 0.9161290322580645, "percentage": 23.05, "elapsed_time": "0:04:51", "remaining_time": "0:16:14"}
+{"current_steps": 72, "total_steps": 308, "loss": 0.087, "lr": 4.7345527047423135e-05, "epoch": 0.9290322580645162, "percentage": 23.38, "elapsed_time": "0:04:56", "remaining_time": "0:16:10"}
+{"current_steps": 73, "total_steps": 308, "loss": 0.0817, "lr": 4.721694780458266e-05, "epoch": 0.9419354838709677, "percentage": 23.7, "elapsed_time": "0:05:00", "remaining_time": "0:16:06"}
+{"current_steps": 74, "total_steps": 308, "loss": 0.0824, "lr": 4.7085510839949444e-05, "epoch": 0.9548387096774194, "percentage": 24.03, "elapsed_time": "0:05:03", "remaining_time": "0:15:59"}
+{"current_steps": 75, "total_steps": 308, "loss": 0.0757, "lr": 4.695123305999877e-05, "epoch": 0.967741935483871, "percentage": 24.35, "elapsed_time": "0:05:06", "remaining_time": "0:15:52"}
+{"current_steps": 76, "total_steps": 308, "loss": 0.0793, "lr": 4.681413173661429e-05, "epoch": 0.9806451612903225, "percentage": 24.68, "elapsed_time": "0:05:10", "remaining_time": "0:15:47"}
+{"current_steps": 77, "total_steps": 308, "loss": 0.0919, "lr": 4.667422450486646e-05, "epoch": 0.9935483870967742, "percentage": 25.0, "elapsed_time": "0:05:15", "remaining_time": "0:15:46"}
+{"current_steps": 78, "total_steps": 308, "loss": 0.0812, "lr": 4.653152936074413e-05, "epoch": 1.0, "percentage": 25.32, "elapsed_time": "0:05:16", "remaining_time": "0:15:34"}
+{"current_steps": 79, "total_steps": 308, "loss": 0.0528, "lr": 4.638606465883979e-05, "epoch": 1.0129032258064516, "percentage": 25.65, "elapsed_time": "0:05:20", "remaining_time": "0:15:27"}
+{"current_steps": 80, "total_steps": 308, "loss": 0.0562, "lr": 4.623784910998862e-05, "epoch": 1.0258064516129033, "percentage": 25.97, "elapsed_time": "0:05:25", "remaining_time": "0:15:28"}
+{"current_steps": 81, "total_steps": 308, "loss": 0.052, "lr": 4.608690177886177e-05, "epoch": 1.038709677419355, "percentage": 26.3, "elapsed_time": "0:05:30", "remaining_time": "0:15:26"}
+{"current_steps": 82, "total_steps": 308, "loss": 0.0477, "lr": 4.593324208151412e-05, "epoch": 1.0516129032258064, "percentage": 26.62, "elapsed_time": "0:05:33", "remaining_time": "0:15:20"}
+{"current_steps": 83, "total_steps": 308, "loss": 0.0552, "lr": 4.577688978288681e-05, "epoch": 1.064516129032258, "percentage": 26.95, "elapsed_time": "0:05:37", "remaining_time": "0:15:13"}
+{"current_steps": 84, "total_steps": 308, "loss": 0.0623, "lr": 4.5617864994264936e-05, "epoch": 1.0774193548387097, "percentage": 27.27, "elapsed_time": "0:05:41", "remaining_time": "0:15:09"}
+{"current_steps": 85, "total_steps": 308, "loss": 0.055, "lr": 4.545618817069066e-05, "epoch": 1.0903225806451613, "percentage": 27.6, "elapsed_time": "0:05:43", "remaining_time": "0:15:02"}
+{"current_steps": 86, "total_steps": 308, "loss": 0.0652, "lr": 4.529188010833212e-05, "epoch": 1.103225806451613, "percentage": 27.92, "elapsed_time": "0:05:48", "remaining_time": "0:14:58"}
+{"current_steps": 87, "total_steps": 308, "loss": 0.0506, "lr": 4.512496194180846e-05, "epoch": 1.1161290322580646, "percentage": 28.25, "elapsed_time": "0:05:52", "remaining_time": "0:14:56"}
+{"current_steps": 88, "total_steps": 308, "loss": 0.0671, "lr": 4.495545514147134e-05, "epoch": 1.129032258064516, "percentage": 28.57, "elapsed_time": "0:05:57", "remaining_time": "0:14:53"}
+{"current_steps": 89, "total_steps": 308, "loss": 0.0537, "lr": 4.478338151064323e-05, "epoch": 1.1419354838709677, "percentage": 28.9, "elapsed_time": "0:06:01", "remaining_time": "0:14:50"}
+{"current_steps": 90, "total_steps": 308, "loss": 0.0531, "lr": 4.460876318281291e-05, "epoch": 1.1548387096774193, "percentage": 29.22, "elapsed_time": "0:06:05", "remaining_time": "0:14:44"}
+{"current_steps": 91, "total_steps": 308, "loss": 0.051, "lr": 4.443162261878846e-05, "epoch": 1.167741935483871, "percentage": 29.55, "elapsed_time": "0:06:09", "remaining_time": "0:14:41"}
+{"current_steps": 92, "total_steps": 308, "loss": 0.0509, "lr": 4.425198260380818e-05, "epoch": 1.1806451612903226, "percentage": 29.87, "elapsed_time": "0:06:13", "remaining_time": "0:14:35"}
+{"current_steps": 93, "total_steps": 308, "loss": 0.0493, "lr": 4.406986624460979e-05, "epoch": 1.1935483870967742, "percentage": 30.19, "elapsed_time": "0:06:17", "remaining_time": "0:14:33"}
+{"current_steps": 94, "total_steps": 308, "loss": 0.0575, "lr": 4.3885296966458224e-05, "epoch": 1.206451612903226, "percentage": 30.52, "elapsed_time": "0:06:21", "remaining_time": "0:14:28"}
+{"current_steps": 95, "total_steps": 308, "loss": 0.0518, "lr": 4.369829851013251e-05, "epoch": 1.2193548387096773, "percentage": 30.84, "elapsed_time": "0:06:25", "remaining_time": "0:14:23"}
+{"current_steps": 96, "total_steps": 308, "loss": 0.0509, "lr": 4.350889492887203e-05, "epoch": 1.232258064516129, "percentage": 31.17, "elapsed_time": "0:06:29", "remaining_time": "0:14:20"}
+{"current_steps": 97, "total_steps": 308, "loss": 0.0468, "lr": 4.3317110585282595e-05, "epoch": 1.2451612903225806, "percentage": 31.49, "elapsed_time": "0:06:33", "remaining_time": "0:14:16"}
+{"current_steps": 98, "total_steps": 308, "loss": 0.055, "lr": 4.3122970148202744e-05, "epoch": 1.2580645161290323, "percentage": 31.82, "elapsed_time": "0:06:37", "remaining_time": "0:14:12"}
+{"current_steps": 99, "total_steps": 308, "loss": 0.07, "lr": 4.292649858953063e-05, "epoch": 1.270967741935484, "percentage": 32.14, "elapsed_time": "0:06:41", "remaining_time": "0:14:07"}
+{"current_steps": 100, "total_steps": 308, "loss": 0.0564, "lr": 4.272772118101195e-05, "epoch": 1.2838709677419355, "percentage": 32.47, "elapsed_time": "0:06:45", "remaining_time": "0:14:02"}
+{"current_steps": 101, "total_steps": 308, "loss": 0.0536, "lr": 4.252666349098926e-05, "epoch": 1.2967741935483872, "percentage": 32.79, "elapsed_time": "0:06:48", "remaining_time": "0:13:56"}
+{"current_steps": 102, "total_steps": 308, "loss": 0.0472, "lr": 4.2323351381113206e-05, "epoch": 1.3096774193548386, "percentage": 33.12, "elapsed_time": "0:06:53", "remaining_time": "0:13:54"}
+{"current_steps": 103, "total_steps": 308, "loss": 0.0645, "lr": 4.211781100301596e-05, "epoch": 1.3225806451612903, "percentage": 33.44, "elapsed_time": "0:06:57", "remaining_time": "0:13:50"}
+{"current_steps": 104, "total_steps": 308, "loss": 0.056, "lr": 4.1910068794947404e-05, "epoch": 1.335483870967742, "percentage": 33.77, "elapsed_time": "0:07:00", "remaining_time": "0:13:45"}
+{"current_steps": 105, "total_steps": 308, "loss": 0.0518, "lr": 4.170015147837444e-05, "epoch": 1.3483870967741935, "percentage": 34.09, "elapsed_time": "0:07:03", "remaining_time": "0:13:39"}
+{"current_steps": 106, "total_steps": 308, "loss": 0.0487, "lr": 4.148808605454385e-05, "epoch": 1.3612903225806452, "percentage": 34.42, "elapsed_time": "0:07:07", "remaining_time": "0:13:34"}
+{"current_steps": 107, "total_steps": 308, "loss": 0.0528, "lr": 4.127389980100915e-05, "epoch": 1.3741935483870968, "percentage": 34.74, "elapsed_time": "0:07:12", "remaining_time": "0:13:31"}
+{"current_steps": 108, "total_steps": 308, "loss": 0.0485, "lr": 4.1057620268122004e-05, "epoch": 1.3870967741935485, "percentage": 35.06, "elapsed_time": "0:07:17", "remaining_time": "0:13:29"}
+{"current_steps": 109, "total_steps": 308, "loss": 0.0485, "lr": 4.08392752754884e-05, "epoch": 1.4, "percentage": 35.39, "elapsed_time": "0:07:21", "remaining_time": "0:13:25"}
+{"current_steps": 110, "total_steps": 308, "loss": 0.0514, "lr": 4.0618892908390316e-05, "epoch": 1.4129032258064516, "percentage": 35.71, "elapsed_time": "0:07:26", "remaining_time": "0:13:23"}
+{"current_steps": 111, "total_steps": 308, "loss": 0.0442, "lr": 4.039650151417316e-05, "epoch": 1.4258064516129032, "percentage": 36.04, "elapsed_time": "0:07:30", "remaining_time": "0:13:19"}
+{"current_steps": 112, "total_steps": 308, "loss": 0.052, "lr": 4.0172129698599484e-05, "epoch": 1.4387096774193548, "percentage": 36.36, "elapsed_time": "0:07:35", "remaining_time": "0:13:16"}
+{"current_steps": 113, "total_steps": 308, "loss": 0.057, "lr": 3.994580632216952e-05, "epoch": 1.4516129032258065, "percentage": 36.69, "elapsed_time": "0:07:41", "remaining_time": "0:13:15"}
+{"current_steps": 114, "total_steps": 308, "loss": 0.0515, "lr": 3.971756049640888e-05, "epoch": 1.4645161290322581, "percentage": 37.01, "elapsed_time": "0:07:46", "remaining_time": "0:13:13"}
+{"current_steps": 115, "total_steps": 308, "loss": 0.0524, "lr": 3.9487421580124e-05, "epoch": 1.4774193548387098, "percentage": 37.34, "elapsed_time": "0:07:49", "remaining_time": "0:13:07"}
+{"current_steps": 116, "total_steps": 308, "loss": 0.0544, "lr": 3.92554191756258e-05, "epoch": 1.4903225806451612, "percentage": 37.66, "elapsed_time": "0:07:52", "remaining_time": "0:13:01"}
+{"current_steps": 117, "total_steps": 308, "loss": 0.0468, "lr": 3.902158312492196e-05, "epoch": 1.5032258064516129, "percentage": 37.99, "elapsed_time": "0:07:55", "remaining_time": "0:12:56"}
+{"current_steps": 118, "total_steps": 308, "loss": 0.0451, "lr": 3.878594350587844e-05, "epoch": 1.5161290322580645, "percentage": 38.31, "elapsed_time": "0:08:01", "remaining_time": "0:12:54"}
+{"current_steps": 119, "total_steps": 308, "loss": 0.0509, "lr": 3.8548530628350623e-05, "epoch": 1.5290322580645161, "percentage": 38.64, "elapsed_time": "0:08:05", "remaining_time": "0:12:50"}
+{"current_steps": 120, "total_steps": 308, "loss": 0.0616, "lr": 3.8309375030284566e-05, "epoch": 1.5419354838709678, "percentage": 38.96, "elapsed_time": "0:08:10", "remaining_time": "0:12:48"}
+{"current_steps": 121, "total_steps": 308, "loss": 0.0514, "lr": 3.806850747378902e-05, "epoch": 1.5548387096774192, "percentage": 39.29, "elapsed_time": "0:08:15", "remaining_time": "0:12:45"}
+{"current_steps": 122, "total_steps": 308, "loss": 0.0478, "lr": 3.782595894117854e-05, "epoch": 1.567741935483871, "percentage": 39.61, "elapsed_time": "0:08:18", "remaining_time": "0:12:40"}
+{"current_steps": 123, "total_steps": 308, "loss": 0.0489, "lr": 3.758176063098829e-05, "epoch": 1.5806451612903225, "percentage": 39.94, "elapsed_time": "0:08:23", "remaining_time": "0:12:36"}
+{"current_steps": 124, "total_steps": 308, "loss": 0.0516, "lr": 3.733594395396106e-05, "epoch": 1.5935483870967742, "percentage": 40.26, "elapsed_time": "0:08:26", "remaining_time": "0:12:30"}
+{"current_steps": 125, "total_steps": 308, "loss": 0.0461, "lr": 3.7088540529006924e-05, "epoch": 1.6064516129032258, "percentage": 40.58, "elapsed_time": "0:08:32", "remaining_time": "0:12:29"}
+{"current_steps": 126, "total_steps": 308, "loss": 0.0414, "lr": 3.68395821791362e-05, "epoch": 1.6193548387096774, "percentage": 40.91, "elapsed_time": "0:08:36", "remaining_time": "0:12:26"}
+{"current_steps": 127, "total_steps": 308, "loss": 0.0556, "lr": 3.65891009273661e-05, "epoch": 1.632258064516129, "percentage": 41.23, "elapsed_time": "0:08:42", "remaining_time": "0:12:24"}
+{"current_steps": 128, "total_steps": 308, "loss": 0.0575, "lr": 3.633712899260166e-05, "epoch": 1.6451612903225805, "percentage": 41.56, "elapsed_time": "0:08:45", "remaining_time": "0:12:19"}
+{"current_steps": 129, "total_steps": 308, "loss": 0.0451, "lr": 3.608369878549154e-05, "epoch": 1.6580645161290324, "percentage": 41.88, "elapsed_time": "0:08:49", "remaining_time": "0:12:15"}
+{"current_steps": 130, "total_steps": 308, "loss": 0.0522, "lr": 3.582884290425903e-05, "epoch": 1.6709677419354838, "percentage": 42.21, "elapsed_time": "0:08:54", "remaining_time": "0:12:11"}
+{"current_steps": 131, "total_steps": 308, "loss": 0.049, "lr": 3.557259413050907e-05, "epoch": 1.6838709677419355, "percentage": 42.53, "elapsed_time": "0:08:57", "remaining_time": "0:12:06"}
+{"current_steps": 132, "total_steps": 308, "loss": 0.0495, "lr": 3.531498542501161e-05, "epoch": 1.696774193548387, "percentage": 42.86, "elapsed_time": "0:09:01", "remaining_time": "0:12:01"}
+{"current_steps": 133, "total_steps": 308, "loss": 0.0494, "lr": 3.505604992346187e-05, "epoch": 1.7096774193548387, "percentage": 43.18, "elapsed_time": "0:09:06", "remaining_time": "0:11:59"}
+{"current_steps": 134, "total_steps": 308, "loss": 0.0489, "lr": 3.4795820932218235e-05, "epoch": 1.7225806451612904, "percentage": 43.51, "elapsed_time": "0:09:10", "remaining_time": "0:11:55"}
+{"current_steps": 135, "total_steps": 308, "loss": 0.058, "lr": 3.4534331924018095e-05, "epoch": 1.7354838709677418, "percentage": 43.83, "elapsed_time": "0:09:14", "remaining_time": "0:11:50"}
+{"current_steps": 136, "total_steps": 308, "loss": 0.0505, "lr": 3.427161653367231e-05, "epoch": 1.7483870967741937, "percentage": 44.16, "elapsed_time": "0:09:17", "remaining_time": "0:11:44"}
+{"current_steps": 137, "total_steps": 308, "loss": 0.0454, "lr": 3.4007708553738836e-05, "epoch": 1.761290322580645, "percentage": 44.48, "elapsed_time": "0:09:20", "remaining_time": "0:11:40"}
+{"current_steps": 138, "total_steps": 308, "loss": 0.0462, "lr": 3.3742641930176045e-05, "epoch": 1.7741935483870968, "percentage": 44.81, "elapsed_time": "0:09:24", "remaining_time": "0:11:35"}
+{"current_steps": 139, "total_steps": 308, "loss": 0.0436, "lr": 3.347645075797635e-05, "epoch": 1.7870967741935484, "percentage": 45.13, "elapsed_time": "0:09:29", "remaining_time": "0:11:32"}
+{"current_steps": 140, "total_steps": 308, "loss": 0.0386, "lr": 3.320916927678061e-05, "epoch": 1.8, "percentage": 45.45, "elapsed_time": "0:09:33", "remaining_time": "0:11:28"}
+{"current_steps": 141, "total_steps": 308, "loss": 0.0462, "lr": 3.2940831866473966e-05, "epoch": 1.8129032258064517, "percentage": 45.78, "elapsed_time": "0:09:38", "remaining_time": "0:11:25"}
+{"current_steps": 142, "total_steps": 308, "loss": 0.0545, "lr": 3.2671473042763604e-05, "epoch": 1.8258064516129031, "percentage": 46.1, "elapsed_time": "0:09:42", "remaining_time": "0:11:20"}
+{"current_steps": 143, "total_steps": 308, "loss": 0.0434, "lr": 3.240112745273911e-05, "epoch": 1.838709677419355, "percentage": 46.43, "elapsed_time": "0:09:45", "remaining_time": "0:11:16"}
+{"current_steps": 144, "total_steps": 308, "loss": 0.0459, "lr": 3.212982987041582e-05, "epoch": 1.8516129032258064, "percentage": 46.75, "elapsed_time": "0:09:50", "remaining_time": "0:11:12"}
+{"current_steps": 145, "total_steps": 308, "loss": 0.0548, "lr": 3.1857615192261984e-05, "epoch": 1.864516129032258, "percentage": 47.08, "elapsed_time": "0:09:53", "remaining_time": "0:11:07"}
+{"current_steps": 146, "total_steps": 308, "loss": 0.0593, "lr": 3.158451843271005e-05, "epoch": 1.8774193548387097, "percentage": 47.4, "elapsed_time": "0:09:58", "remaining_time": "0:11:03"}
+{"current_steps": 147, "total_steps": 308, "loss": 0.0508, "lr": 3.131057471965283e-05, "epoch": 1.8903225806451613, "percentage": 47.73, "elapsed_time": "0:10:01", "remaining_time": "0:10:59"}
+{"current_steps": 148, "total_steps": 308, "loss": 0.0423, "lr": 3.10358192899251e-05, "epoch": 1.903225806451613, "percentage": 48.05, "elapsed_time": "0:10:07", "remaining_time": "0:10:56"}
+{"current_steps": 149, "total_steps": 308, "loss": 0.0442, "lr": 3.076028748477112e-05, "epoch": 1.9161290322580644, "percentage": 48.38, "elapsed_time": "0:10:12", "remaining_time": "0:10:53"}
+{"current_steps": 150, "total_steps": 308, "loss": 0.0571, "lr": 3.0484014745298784e-05, "epoch": 1.9290322580645163, "percentage": 48.7, "elapsed_time": "0:10:17", "remaining_time": "0:10:50"}
+{"current_steps": 151, "total_steps": 308, "loss": 0.0498, "lr": 3.0207036607920892e-05, "epoch": 1.9419354838709677, "percentage": 49.03, "elapsed_time": "0:10:21", "remaining_time": "0:10:46"}
+{"current_steps": 152, "total_steps": 308, "loss": 0.0548, "lr": 2.9929388699784163e-05, "epoch": 1.9548387096774194, "percentage": 49.35, "elapsed_time": "0:10:25", "remaining_time": "0:10:42"}
+{"current_steps": 153, "total_steps": 308, "loss": 0.0473, "lr": 2.9651106734186618e-05, "epoch": 1.967741935483871, "percentage": 49.68, "elapsed_time": "0:10:29", "remaining_time": "0:10:38"}
+{"current_steps": 154, "total_steps": 308, "loss": 0.0515, "lr": 2.9372226505983802e-05, "epoch": 1.9806451612903224, "percentage": 50.0, "elapsed_time": "0:10:33", "remaining_time": "0:10:33"}
+{"current_steps": 155, "total_steps": 308, "loss": 0.049, "lr": 2.9092783886984615e-05, "epoch": 1.9935483870967743, "percentage": 50.32, "elapsed_time": "0:10:38", "remaining_time": "0:10:30"}
+{"current_steps": 156, "total_steps": 308, "loss": 0.0358, "lr": 2.8812814821337147e-05, "epoch": 2.0, "percentage": 50.65, "elapsed_time": "0:10:40", "remaining_time": "0:10:24"}
+{"current_steps": 157, "total_steps": 308, "loss": 0.0252, "lr": 2.8532355320905274e-05, "epoch": 2.0129032258064514, "percentage": 50.97, "elapsed_time": "0:10:45", "remaining_time": "0:10:20"}
+{"current_steps": 158, "total_steps": 308, "loss": 0.0242, "lr": 2.825144146063654e-05, "epoch": 2.0258064516129033, "percentage": 51.3, "elapsed_time": "0:10:48", "remaining_time": "0:10:16"}
+{"current_steps": 159, "total_steps": 308, "loss": 0.0278, "lr": 2.7970109373921878e-05, "epoch": 2.0387096774193547, "percentage": 51.62, "elapsed_time": "0:10:52", "remaining_time": "0:10:11"}
+{"current_steps": 160, "total_steps": 308, "loss": 0.0292, "lr": 2.7688395247947842e-05, "epoch": 2.0516129032258066, "percentage": 51.95, "elapsed_time": "0:10:57", "remaining_time": "0:10:08"}
+{"current_steps": 161, "total_steps": 308, "loss": 0.0257, "lr": 2.740633531904196e-05, "epoch": 2.064516129032258, "percentage": 52.27, "elapsed_time": "0:11:02", "remaining_time": "0:10:04"}
+{"current_steps": 162, "total_steps": 308, "loss": 0.0246, "lr": 2.712396586801169e-05, "epoch": 2.07741935483871, "percentage": 52.6, "elapsed_time": "0:11:06", "remaining_time": "0:10:00"}
+{"current_steps": 163, "total_steps": 308, "loss": 0.0313, "lr": 2.6841323215477714e-05, "epoch": 2.0903225806451613, "percentage": 52.92, "elapsed_time": "0:11:09", "remaining_time": "0:09:55"}
+{"current_steps": 164, "total_steps": 308, "loss": 0.0311, "lr": 2.6558443717202076e-05, "epoch": 2.1032258064516127, "percentage": 53.25, "elapsed_time": "0:11:12", "remaining_time": "0:09:50"}
+{"current_steps": 165, "total_steps": 308, "loss": 0.036, "lr": 2.6275363759411815e-05, "epoch": 2.1161290322580646, "percentage": 53.57, "elapsed_time": "0:11:16", "remaining_time": "0:09:45"}
+{"current_steps": 166, "total_steps": 308, "loss": 0.0194, "lr": 2.599211975411867e-05, "epoch": 2.129032258064516, "percentage": 53.9, "elapsed_time": "0:11:20", "remaining_time": "0:09:42"}
+{"current_steps": 167, "total_steps": 308, "loss": 0.0259, "lr": 2.57087481344355e-05, "epoch": 2.141935483870968, "percentage": 54.22, "elapsed_time": "0:11:26", "remaining_time": "0:09:39"}
+{"current_steps": 168, "total_steps": 308, "loss": 0.0239, "lr": 2.5425285349889938e-05, "epoch": 2.1548387096774193, "percentage": 54.55, "elapsed_time": "0:11:29", "remaining_time": "0:09:34"}
+{"current_steps": 169, "total_steps": 308, "loss": 0.0248, "lr": 2.5141767861735976e-05, "epoch": 2.167741935483871, "percentage": 54.87, "elapsed_time": "0:11:32", "remaining_time": "0:09:29"}
+{"current_steps": 170, "total_steps": 308, "loss": 0.0259, "lr": 2.485823213826403e-05, "epoch": 2.1806451612903226, "percentage": 55.19, "elapsed_time": "0:11:37", "remaining_time": "0:09:25"}
+{"current_steps": 171, "total_steps": 308, "loss": 0.026, "lr": 2.457471465011007e-05, "epoch": 2.193548387096774, "percentage": 55.52, "elapsed_time": "0:11:40", "remaining_time": "0:09:21"}
+{"current_steps": 172, "total_steps": 308, "loss": 0.0252, "lr": 2.4291251865564505e-05, "epoch": 2.206451612903226, "percentage": 55.84, "elapsed_time": "0:11:44", "remaining_time": "0:09:17"}
+{"current_steps": 173, "total_steps": 308, "loss": 0.0236, "lr": 2.400788024588134e-05, "epoch": 2.2193548387096773, "percentage": 56.17, "elapsed_time": "0:11:48", "remaining_time": "0:09:12"}
+{"current_steps": 174, "total_steps": 308, "loss": 0.0346, "lr": 2.3724636240588194e-05, "epoch": 2.232258064516129, "percentage": 56.49, "elapsed_time": "0:11:53", "remaining_time": "0:09:09"}
+{"current_steps": 175, "total_steps": 308, "loss": 0.0351, "lr": 2.3441556282797934e-05, "epoch": 2.2451612903225806, "percentage": 56.82, "elapsed_time": "0:11:56", "remaining_time": "0:09:04"}
+{"current_steps": 176, "total_steps": 308, "loss": 0.0257, "lr": 2.315867678452229e-05, "epoch": 2.258064516129032, "percentage": 57.14, "elapsed_time": "0:12:01", "remaining_time": "0:09:00"}
+{"current_steps": 177, "total_steps": 308, "loss": 0.0307, "lr": 2.287603413198831e-05, "epoch": 2.270967741935484, "percentage": 57.47, "elapsed_time": "0:12:04", "remaining_time": "0:08:56"}
+{"current_steps": 178, "total_steps": 308, "loss": 0.0325, "lr": 2.2593664680958045e-05, "epoch": 2.2838709677419353, "percentage": 57.79, "elapsed_time": "0:12:10", "remaining_time": "0:08:53"}
+{"current_steps": 179, "total_steps": 308, "loss": 0.0279, "lr": 2.231160475205216e-05, "epoch": 2.296774193548387, "percentage": 58.12, "elapsed_time": "0:12:14", "remaining_time": "0:08:49"}
+{"current_steps": 180, "total_steps": 308, "loss": 0.0242, "lr": 2.202989062607813e-05, "epoch": 2.3096774193548386, "percentage": 58.44, "elapsed_time": "0:12:17", "remaining_time": "0:08:44"}
+{"current_steps": 181, "total_steps": 308, "loss": 0.0213, "lr": 2.1748558539363458e-05, "epoch": 2.3225806451612905, "percentage": 58.77, "elapsed_time": "0:12:22", "remaining_time": "0:08:40"}
+{"current_steps": 182, "total_steps": 308, "loss": 0.0202, "lr": 2.1467644679094728e-05, "epoch": 2.335483870967742, "percentage": 59.09, "elapsed_time": "0:12:25", "remaining_time": "0:08:35"}
+{"current_steps": 183, "total_steps": 308, "loss": 0.0361, "lr": 2.118718517866286e-05, "epoch": 2.3483870967741938, "percentage": 59.42, "elapsed_time": "0:12:30", "remaining_time": "0:08:32"}
+{"current_steps": 184, "total_steps": 308, "loss": 0.0303, "lr": 2.0907216113015397e-05, "epoch": 2.361290322580645, "percentage": 59.74, "elapsed_time": "0:12:34", "remaining_time": "0:08:28"}
+{"current_steps": 185, "total_steps": 308, "loss": 0.0265, "lr": 2.0627773494016207e-05, "epoch": 2.3741935483870966, "percentage": 60.06, "elapsed_time": "0:12:38", "remaining_time": "0:08:24"}
+{"current_steps": 186, "total_steps": 308, "loss": 0.0233, "lr": 2.0348893265813394e-05, "epoch": 2.3870967741935485, "percentage": 60.39, "elapsed_time": "0:12:42", "remaining_time": "0:08:19"}
+{"current_steps": 187, "total_steps": 308, "loss": 0.0259, "lr": 2.0070611300215843e-05, "epoch": 2.4, "percentage": 60.71, "elapsed_time": "0:12:46", "remaining_time": "0:08:16"}
+{"current_steps": 188, "total_steps": 308, "loss": 0.0267, "lr": 1.979296339207912e-05, "epoch": 2.412903225806452, "percentage": 61.04, "elapsed_time": "0:12:49", "remaining_time": "0:08:11"}
+{"current_steps": 189, "total_steps": 308, "loss": 0.02, "lr": 1.951598525470122e-05, "epoch": 2.425806451612903, "percentage": 61.36, "elapsed_time": "0:12:53", "remaining_time": "0:08:06"}
+{"current_steps": 190, "total_steps": 308, "loss": 0.0235, "lr": 1.923971251522888e-05, "epoch": 2.4387096774193546, "percentage": 61.69, "elapsed_time": "0:12:56", "remaining_time": "0:08:02"}
+{"current_steps": 191, "total_steps": 308, "loss": 0.0242, "lr": 1.8964180710074905e-05, "epoch": 2.4516129032258065, "percentage": 62.01, "elapsed_time": "0:13:00", "remaining_time": "0:07:57"}
+{"current_steps": 192, "total_steps": 308, "loss": 0.0246, "lr": 1.8689425280347166e-05, "epoch": 2.464516129032258, "percentage": 62.34, "elapsed_time": "0:13:03", "remaining_time": "0:07:53"}
+{"current_steps": 193, "total_steps": 308, "loss": 0.0223, "lr": 1.8415481567289954e-05, "epoch": 2.47741935483871, "percentage": 62.66, "elapsed_time": "0:13:09", "remaining_time": "0:07:50"}
+{"current_steps": 194, "total_steps": 308, "loss": 0.027, "lr": 1.8142384807738022e-05, "epoch": 2.490322580645161, "percentage": 62.99, "elapsed_time": "0:13:12", "remaining_time": "0:07:45"}
+{"current_steps": 195, "total_steps": 308, "loss": 0.0241, "lr": 1.787017012958419e-05, "epoch": 2.5032258064516126, "percentage": 63.31, "elapsed_time": "0:13:17", "remaining_time": "0:07:42"}
+{"current_steps": 196, "total_steps": 308, "loss": 0.0241, "lr": 1.75988725472609e-05, "epoch": 2.5161290322580645, "percentage": 63.64, "elapsed_time": "0:13:22", "remaining_time": "0:07:38"}
+{"current_steps": 197, "total_steps": 308, "loss": 0.0302, "lr": 1.7328526957236406e-05, "epoch": 2.5290322580645164, "percentage": 63.96, "elapsed_time": "0:13:25", "remaining_time": "0:07:33"}
+{"current_steps": 198, "total_steps": 308, "loss": 0.0236, "lr": 1.7059168133526043e-05, "epoch": 2.541935483870968, "percentage": 64.29, "elapsed_time": "0:13:29", "remaining_time": "0:07:29"}
+{"current_steps": 199, "total_steps": 308, "loss": 0.0228, "lr": 1.6790830723219398e-05, "epoch": 2.554838709677419, "percentage": 64.61, "elapsed_time": "0:13:33", "remaining_time": "0:07:25"}
+{"current_steps": 200, "total_steps": 308, "loss": 0.027, "lr": 1.6523549242023655e-05, "epoch": 2.567741935483871, "percentage": 64.94, "elapsed_time": "0:13:37", "remaining_time": "0:07:21"}
+{"current_steps": 201, "total_steps": 308, "loss": 0.0304, "lr": 1.6257358069823965e-05, "epoch": 2.5806451612903225, "percentage": 65.26, "elapsed_time": "0:13:40", "remaining_time": "0:07:16"}
+{"current_steps": 202, "total_steps": 308, "loss": 0.0254, "lr": 1.5992291446261166e-05, "epoch": 2.5935483870967744, "percentage": 65.58, "elapsed_time": "0:13:45", "remaining_time": "0:07:13"}
+{"current_steps": 203, "total_steps": 308, "loss": 0.0222, "lr": 1.5728383466327684e-05, "epoch": 2.606451612903226, "percentage": 65.91, "elapsed_time": "0:13:48", "remaining_time": "0:07:08"}
+{"current_steps": 204, "total_steps": 308, "loss": 0.0219, "lr": 1.5465668075981904e-05, "epoch": 2.6193548387096772, "percentage": 66.23, "elapsed_time": "0:13:52", "remaining_time": "0:07:04"}
+{"current_steps": 205, "total_steps": 308, "loss": 0.0264, "lr": 1.520417906778176e-05, "epoch": 2.632258064516129, "percentage": 66.56, "elapsed_time": "0:13:55", "remaining_time": "0:07:00"}
+{"current_steps": 206, "total_steps": 308, "loss": 0.0237, "lr": 1.4943950076538135e-05, "epoch": 2.6451612903225805, "percentage": 66.88, "elapsed_time": "0:14:00", "remaining_time": "0:06:55"}
+{"current_steps": 207, "total_steps": 308, "loss": 0.0313, "lr": 1.4685014574988393e-05, "epoch": 2.6580645161290324, "percentage": 67.21, "elapsed_time": "0:14:03", "remaining_time": "0:06:51"}
+{"current_steps": 208, "total_steps": 308, "loss": 0.0236, "lr": 1.4427405869490923e-05, "epoch": 2.670967741935484, "percentage": 67.53, "elapsed_time": "0:14:06", "remaining_time": "0:06:46"}
+{"current_steps": 209, "total_steps": 308, "loss": 0.027, "lr": 1.4171157095740976e-05, "epoch": 2.6838709677419352, "percentage": 67.86, "elapsed_time": "0:14:10", "remaining_time": "0:06:42"}
+{"current_steps": 210, "total_steps": 308, "loss": 0.0257, "lr": 1.391630121450847e-05, "epoch": 2.696774193548387, "percentage": 68.18, "elapsed_time": "0:14:12", "remaining_time": "0:06:38"}
+{"current_steps": 211, "total_steps": 308, "loss": 0.0274, "lr": 1.3662871007398348e-05, "epoch": 2.709677419354839, "percentage": 68.51, "elapsed_time": "0:14:16", "remaining_time": "0:06:33"}
+{"current_steps": 212, "total_steps": 308, "loss": 0.0292, "lr": 1.3410899072633915e-05, "epoch": 2.7225806451612904, "percentage": 68.83, "elapsed_time": "0:14:20", "remaining_time": "0:06:29"}
+{"current_steps": 213, "total_steps": 308, "loss": 0.0249, "lr": 1.3160417820863807e-05, "epoch": 2.735483870967742, "percentage": 69.16, "elapsed_time": "0:14:25", "remaining_time": "0:06:26"}
+{"current_steps": 214, "total_steps": 308, "loss": 0.019, "lr": 1.2911459470993085e-05, "epoch": 2.7483870967741937, "percentage": 69.48, "elapsed_time": "0:14:29", "remaining_time": "0:06:21"}
+{"current_steps": 215, "total_steps": 308, "loss": 0.0248, "lr": 1.2664056046038942e-05, "epoch": 2.761290322580645, "percentage": 69.81, "elapsed_time": "0:14:35", "remaining_time": "0:06:18"}
+{"current_steps": 216, "total_steps": 308, "loss": 0.0206, "lr": 1.2418239369011712e-05, "epoch": 2.774193548387097, "percentage": 70.13, "elapsed_time": "0:14:38", "remaining_time": "0:06:14"}
+{"current_steps": 217, "total_steps": 308, "loss": 0.02, "lr": 1.217404105882147e-05, "epoch": 2.7870967741935484, "percentage": 70.45, "elapsed_time": "0:14:43", "remaining_time": "0:06:10"}
+{"current_steps": 218, "total_steps": 308, "loss": 0.0217, "lr": 1.1931492526210988e-05, "epoch": 2.8, "percentage": 70.78, "elapsed_time": "0:14:45", "remaining_time": "0:06:05"}
+{"current_steps": 219, "total_steps": 308, "loss": 0.0248, "lr": 1.1690624969715441e-05, "epoch": 2.8129032258064517, "percentage": 71.1, "elapsed_time": "0:14:48", "remaining_time": "0:06:01"}
+{"current_steps": 220, "total_steps": 308, "loss": 0.0226, "lr": 1.145146937164938e-05, "epoch": 2.825806451612903, "percentage": 71.43, "elapsed_time": "0:14:54", "remaining_time": "0:05:57"}
+{"current_steps": 221, "total_steps": 308, "loss": 0.0272, "lr": 1.121405649412156e-05, "epoch": 2.838709677419355, "percentage": 71.75, "elapsed_time": "0:14:59", "remaining_time": "0:05:53"}
+{"current_steps": 222, "total_steps": 308, "loss": 0.0195, "lr": 1.0978416875078042e-05, "epoch": 2.8516129032258064, "percentage": 72.08, "elapsed_time": "0:15:02", "remaining_time": "0:05:49"}
+{"current_steps": 223, "total_steps": 308, "loss": 0.0336, "lr": 1.0744580824374217e-05, "epoch": 2.864516129032258, "percentage": 72.4, "elapsed_time": "0:15:05", "remaining_time": "0:05:45"}
+{"current_steps": 224, "total_steps": 308, "loss": 0.0236, "lr": 1.0512578419876004e-05, "epoch": 2.8774193548387097, "percentage": 72.73, "elapsed_time": "0:15:09", "remaining_time": "0:05:40"}
+{"current_steps": 225, "total_steps": 308, "loss": 0.0272, "lr": 1.0282439503591135e-05, "epoch": 2.8903225806451616, "percentage": 73.05, "elapsed_time": "0:15:13", "remaining_time": "0:05:37"}
+{"current_steps": 226, "total_steps": 308, "loss": 0.0244, "lr": 1.0054193677830481e-05, "epoch": 2.903225806451613, "percentage": 73.38, "elapsed_time": "0:15:17", "remaining_time": "0:05:32"}
+{"current_steps": 227, "total_steps": 308, "loss": 0.0214, "lr": 9.827870301400527e-06, "epoch": 2.9161290322580644, "percentage": 73.7, "elapsed_time": "0:15:23", "remaining_time": "0:05:29"}
+{"current_steps": 228, "total_steps": 308, "loss": 0.0223, "lr": 9.603498485826848e-06, "epoch": 2.9290322580645163, "percentage": 74.03, "elapsed_time": "0:15:28", "remaining_time": "0:05:25"}
+{"current_steps": 229, "total_steps": 308, "loss": 0.0227, "lr": 9.38110709160969e-06, "epoch": 2.9419354838709677, "percentage": 74.35, "elapsed_time": "0:15:33", "remaining_time": "0:05:21"}
+{"current_steps": 230, "total_steps": 308, "loss": 0.0288, "lr": 9.160724724511608e-06, "epoch": 2.9548387096774196, "percentage": 74.68, "elapsed_time": "0:15:36", "remaining_time": "0:05:17"}
+{"current_steps": 231, "total_steps": 308, "loss": 0.023, "lr": 8.942379731877992e-06, "epoch": 2.967741935483871, "percentage": 75.0, "elapsed_time": "0:15:42", "remaining_time": "0:05:14"}
+{"current_steps": 232, "total_steps": 308, "loss": 0.0213, "lr": 8.726100198990853e-06, "epoch": 2.9806451612903224, "percentage": 75.32, "elapsed_time": "0:15:45", "remaining_time": "0:05:09"}
+{"current_steps": 233, "total_steps": 308, "loss": 0.0314, "lr": 8.51191394545615e-06, "epoch": 2.9935483870967743, "percentage": 75.65, "elapsed_time": "0:15:49", "remaining_time": "0:05:05"}
+{"current_steps": 234, "total_steps": 308, "loss": 0.0159, "lr": 8.299848521625563e-06, "epoch": 3.0, "percentage": 75.97, "elapsed_time": "0:15:51", "remaining_time": "0:05:01"}
+{"current_steps": 235, "total_steps": 308, "loss": 0.0106, "lr": 8.089931205052597e-06, "epoch": 3.0129032258064514, "percentage": 76.3, "elapsed_time": "0:15:56", "remaining_time": "0:04:57"}
+{"current_steps": 236, "total_steps": 308, "loss": 0.0122, "lr": 7.882188996984046e-06, "epoch": 3.0258064516129033, "percentage": 76.62, "elapsed_time": "0:15:59", "remaining_time": "0:04:52"}
+{"current_steps": 237, "total_steps": 308, "loss": 0.0129, "lr": 7.676648618886798e-06, "epoch": 3.0387096774193547, "percentage": 76.95, "elapsed_time": "0:16:04", "remaining_time": "0:04:48"}
+{"current_steps": 238, "total_steps": 308, "loss": 0.0099, "lr": 7.473336509010742e-06, "epoch": 3.0516129032258066, "percentage": 77.27, "elapsed_time": "0:16:08", "remaining_time": "0:04:44"}
+{"current_steps": 239, "total_steps": 308, "loss": 0.0123, "lr": 7.2722788189880545e-06, "epoch": 3.064516129032258, "percentage": 77.6, "elapsed_time": "0:16:12", "remaining_time": "0:04:40"}
+{"current_steps": 240, "total_steps": 308, "loss": 0.0114, "lr": 7.073501410469371e-06, "epoch": 3.07741935483871, "percentage": 77.92, "elapsed_time": "0:16:16", "remaining_time": "0:04:36"}
+{"current_steps": 241, "total_steps": 308, "loss": 0.0091, "lr": 6.877029851797265e-06, "epoch": 3.0903225806451613, "percentage": 78.25, "elapsed_time": "0:16:21", "remaining_time": "0:04:32"}
+{"current_steps": 242, "total_steps": 308, "loss": 0.0084, "lr": 6.6828894147174165e-06, "epoch": 3.1032258064516127, "percentage": 78.57, "elapsed_time": "0:16:25", "remaining_time": "0:04:28"}
+{"current_steps": 243, "total_steps": 308, "loss": 0.0118, "lr": 6.491105071127984e-06, "epoch": 3.1161290322580646, "percentage": 78.9, "elapsed_time": "0:16:28", "remaining_time": "0:04:24"}
+{"current_steps": 244, "total_steps": 308, "loss": 0.0079, "lr": 6.3017014898674955e-06, "epoch": 3.129032258064516, "percentage": 79.22, "elapsed_time": "0:16:32", "remaining_time": "0:04:20"}
+{"current_steps": 245, "total_steps": 308, "loss": 0.013, "lr": 6.114703033541783e-06, "epoch": 3.141935483870968, "percentage": 79.55, "elapsed_time": "0:16:37", "remaining_time": "0:04:16"}
+{"current_steps": 246, "total_steps": 308, "loss": 0.0068, "lr": 5.930133755390216e-06, "epoch": 3.1548387096774193, "percentage": 79.87, "elapsed_time": "0:16:42", "remaining_time": "0:04:12"}
+{"current_steps": 247, "total_steps": 308, "loss": 0.0077, "lr": 5.7480173961918266e-06, "epoch": 3.167741935483871, "percentage": 80.19, "elapsed_time": "0:16:47", "remaining_time": "0:04:08"}
+{"current_steps": 248, "total_steps": 308, "loss": 0.0095, "lr": 5.568377381211548e-06, "epoch": 3.1806451612903226, "percentage": 80.52, "elapsed_time": "0:16:52", "remaining_time": "0:04:04"}
+{"current_steps": 249, "total_steps": 308, "loss": 0.0095, "lr": 5.391236817187095e-06, "epoch": 3.193548387096774, "percentage": 80.84, "elapsed_time": "0:16:55", "remaining_time": "0:04:00"}
+{"current_steps": 250, "total_steps": 308, "loss": 0.0111, "lr": 5.216618489356773e-06, "epoch": 3.206451612903226, "percentage": 81.17, "elapsed_time": "0:17:00", "remaining_time": "0:03:56"}
+{"current_steps": 251, "total_steps": 308, "loss": 0.0072, "lr": 5.0445448585286684e-06, "epoch": 3.2193548387096773, "percentage": 81.49, "elapsed_time": "0:17:04", "remaining_time": "0:03:52"}
+{"current_steps": 252, "total_steps": 308, "loss": 0.0055, "lr": 4.87503805819155e-06, "epoch": 3.232258064516129, "percentage": 81.82, "elapsed_time": "0:17:08", "remaining_time": "0:03:48"}
+{"current_steps": 253, "total_steps": 308, "loss": 0.0088, "lr": 4.708119891667892e-06, "epoch": 3.2451612903225806, "percentage": 82.14, "elapsed_time": "0:17:12", "remaining_time": "0:03:44"}
+{"current_steps": 254, "total_steps": 308, "loss": 0.0071, "lr": 4.5438118293093416e-06, "epoch": 3.258064516129032, "percentage": 82.47, "elapsed_time": "0:17:16", "remaining_time": "0:03:40"}
+{"current_steps": 255, "total_steps": 308, "loss": 0.0173, "lr": 4.382135005735072e-06, "epoch": 3.270967741935484, "percentage": 82.79, "elapsed_time": "0:17:21", "remaining_time": "0:03:36"}
+{"current_steps": 256, "total_steps": 308, "loss": 0.0079, "lr": 4.223110217113191e-06, "epoch": 3.2838709677419353, "percentage": 83.12, "elapsed_time": "0:17:25", "remaining_time": "0:03:32"}
+{"current_steps": 257, "total_steps": 308, "loss": 0.0069, "lr": 4.066757918485886e-06, "epoch": 3.296774193548387, "percentage": 83.44, "elapsed_time": "0:17:30", "remaining_time": "0:03:28"}
+{"current_steps": 258, "total_steps": 308, "loss": 0.0088, "lr": 3.913098221138237e-06, "epoch": 3.3096774193548386, "percentage": 83.77, "elapsed_time": "0:17:34", "remaining_time": "0:03:24"}
+{"current_steps": 259, "total_steps": 308, "loss": 0.0104, "lr": 3.762150890011387e-06, "epoch": 3.3225806451612905, "percentage": 84.09, "elapsed_time": "0:17:38", "remaining_time": "0:03:20"}
+{"current_steps": 260, "total_steps": 308, "loss": 0.009, "lr": 3.6139353411602154e-06, "epoch": 3.335483870967742, "percentage": 84.42, "elapsed_time": "0:17:44", "remaining_time": "0:03:16"}
+{"current_steps": 261, "total_steps": 308, "loss": 0.0103, "lr": 3.468470639255872e-06, "epoch": 3.3483870967741938, "percentage": 84.74, "elapsed_time": "0:17:47", "remaining_time": "0:03:12"}
+{"current_steps": 262, "total_steps": 308, "loss": 0.0086, "lr": 3.325775495133546e-06, "epoch": 3.361290322580645, "percentage": 85.06, "elapsed_time": "0:17:51", "remaining_time": "0:03:08"}
+{"current_steps": 263, "total_steps": 308, "loss": 0.0118, "lr": 3.1858682633857105e-06, "epoch": 3.3741935483870966, "percentage": 85.39, "elapsed_time": "0:17:56", "remaining_time": "0:03:04"}
+{"current_steps": 264, "total_steps": 308, "loss": 0.0089, "lr": 3.0487669400012382e-06, "epoch": 3.3870967741935485, "percentage": 85.71, "elapsed_time": "0:17:59", "remaining_time": "0:02:59"}
+{"current_steps": 265, "total_steps": 308, "loss": 0.0101, "lr": 2.914489160050554e-06, "epoch": 3.4, "percentage": 86.04, "elapsed_time": "0:18:03", "remaining_time": "0:02:55"}
+{"current_steps": 266, "total_steps": 308, "loss": 0.0088, "lr": 2.7830521954173543e-06, "epoch": 3.412903225806452, "percentage": 86.36, "elapsed_time": "0:18:08", "remaining_time": "0:02:51"}
+{"current_steps": 267, "total_steps": 308, "loss": 0.0083, "lr": 2.654472952576864e-06, "epoch": 3.425806451612903, "percentage": 86.69, "elapsed_time": "0:18:10", "remaining_time": "0:02:47"}
+{"current_steps": 268, "total_steps": 308, "loss": 0.0091, "lr": 2.5287679704212836e-06, "epoch": 3.4387096774193546, "percentage": 87.01, "elapsed_time": "0:18:14", "remaining_time": "0:02:43"}
+{"current_steps": 269, "total_steps": 308, "loss": 0.0102, "lr": 2.4059534181323588e-06, "epoch": 3.4516129032258065, "percentage": 87.34, "elapsed_time": "0:18:17", "remaining_time": "0:02:39"}
+{"current_steps": 270, "total_steps": 308, "loss": 0.0095, "lr": 2.2860450931015853e-06, "epoch": 3.464516129032258, "percentage": 87.66, "elapsed_time": "0:18:21", "remaining_time": "0:02:35"}
+{"current_steps": 271, "total_steps": 308, "loss": 0.0087, "lr": 2.1690584188982592e-06, "epoch": 3.47741935483871, "percentage": 87.99, "elapsed_time": "0:18:25", "remaining_time": "0:02:30"}
+{"current_steps": 272, "total_steps": 308, "loss": 0.0074, "lr": 2.0550084432855056e-06, "epoch": 3.490322580645161, "percentage": 88.31, "elapsed_time": "0:18:30", "remaining_time": "0:02:26"}
+{"current_steps": 273, "total_steps": 308, "loss": 0.008, "lr": 1.9439098362847825e-06, "epoch": 3.5032258064516126, "percentage": 88.64, "elapsed_time": "0:18:35", "remaining_time": "0:02:22"}
+{"current_steps": 274, "total_steps": 308, "loss": 0.0104, "lr": 1.835776888288851e-06, "epoch": 3.5161290322580645, "percentage": 88.96, "elapsed_time": "0:18:38", "remaining_time": "0:02:18"}
+{"current_steps": 275, "total_steps": 308, "loss": 0.0114, "lr": 1.730623508223686e-06, "epoch": 3.5290322580645164, "percentage": 89.29, "elapsed_time": "0:18:43", "remaining_time": "0:02:14"}
+{"current_steps": 276, "total_steps": 308, "loss": 0.0106, "lr": 1.62846322175933e-06, "epoch": 3.541935483870968, "percentage": 89.61, "elapsed_time": "0:18:47", "remaining_time": "0:02:10"}
+{"current_steps": 277, "total_steps": 308, "loss": 0.0083, "lr": 1.5293091695701839e-06, "epoch": 3.554838709677419, "percentage": 89.94, "elapsed_time": "0:18:50", "remaining_time": "0:02:06"}
+{"current_steps": 278, "total_steps": 308, "loss": 0.0166, "lr": 1.4331741056446968e-06, "epoch": 3.567741935483871, "percentage": 90.26, "elapsed_time": "0:18:55", "remaining_time": "0:02:02"}
+{"current_steps": 279, "total_steps": 308, "loss": 0.0074, "lr": 1.3400703956448684e-06, "epoch": 3.5806451612903225, "percentage": 90.58, "elapsed_time": "0:19:00", "remaining_time": "0:01:58"}
+{"current_steps": 280, "total_steps": 308, "loss": 0.0091, "lr": 1.2500100153156779e-06, "epoch": 3.5935483870967744, "percentage": 90.91, "elapsed_time": "0:19:05", "remaining_time": "0:01:54"}
+{"current_steps": 281, "total_steps": 308, "loss": 0.0078, "lr": 1.1630045489446572e-06, "epoch": 3.606451612903226, "percentage": 91.23, "elapsed_time": "0:19:08", "remaining_time": "0:01:50"}
+{"current_steps": 282, "total_steps": 308, "loss": 0.009, "lr": 1.079065187871839e-06, "epoch": 3.6193548387096772, "percentage": 91.56, "elapsed_time": "0:19:12", "remaining_time": "0:01:46"}
+{"current_steps": 283, "total_steps": 308, "loss": 0.0122, "lr": 9.982027290502238e-07, "epoch": 3.632258064516129, "percentage": 91.88, "elapsed_time": "0:19:15", "remaining_time": "0:01:42"}
+{"current_steps": 284, "total_steps": 308, "loss": 0.0082, "lr": 9.204275736570151e-07, "epoch": 3.6451612903225805, "percentage": 92.21, "elapsed_time": "0:19:18", "remaining_time": "0:01:37"}
+{"current_steps": 285, "total_steps": 308, "loss": 0.0078, "lr": 8.45749725755704e-07, "epoch": 3.6580645161290324, "percentage": 92.53, "elapsed_time": "0:19:21", "remaining_time": "0:01:33"}
+{"current_steps": 286, "total_steps": 308, "loss": 0.0058, "lr": 7.741787910092807e-07, "epoch": 3.670967741935484, "percentage": 92.86, "elapsed_time": "0:19:26", "remaining_time": "0:01:29"}
+{"current_steps": 287, "total_steps": 308, "loss": 0.0072, "lr": 7.05723975444686e-07, "epoch": 3.6838709677419352, "percentage": 93.18, "elapsed_time": "0:19:29", "remaining_time": "0:01:25"}
+{"current_steps": 288, "total_steps": 308, "loss": 0.0086, "lr": 6.403940842686474e-07, "epoch": 3.696774193548387, "percentage": 93.51, "elapsed_time": "0:19:35", "remaining_time": "0:01:21"}
+{"current_steps": 289, "total_steps": 308, "loss": 0.0074, "lr": 5.781975207350826e-07, "epoch": 3.709677419354839, "percentage": 93.83, "elapsed_time": "0:19:40", "remaining_time": "0:01:17"}
+{"current_steps": 290, "total_steps": 308, "loss": 0.0111, "lr": 5.191422850642113e-07, "epoch": 3.7225806451612904, "percentage": 94.16, "elapsed_time": "0:19:43", "remaining_time": "0:01:13"}
+{"current_steps": 291, "total_steps": 308, "loss": 0.0093, "lr": 4.6323597341350054e-07, "epoch": 3.735483870967742, "percentage": 94.48, "elapsed_time": "0:19:47", "remaining_time": "0:01:09"}
+{"current_steps": 292, "total_steps": 308, "loss": 0.008, "lr": 4.1048577690058766e-07, "epoch": 3.7483870967741937, "percentage": 94.81, "elapsed_time": "0:19:53", "remaining_time": "0:01:05"}
+{"current_steps": 293, "total_steps": 308, "loss": 0.0089, "lr": 3.608984806782928e-07, "epoch": 3.761290322580645, "percentage": 95.13, "elapsed_time": "0:19:58", "remaining_time": "0:01:01"}
+{"current_steps": 294, "total_steps": 308, "loss": 0.0098, "lr": 3.144804630618725e-07, "epoch": 3.774193548387097, "percentage": 95.45, "elapsed_time": "0:20:01", "remaining_time": "0:00:57"}
+{"current_steps": 295, "total_steps": 308, "loss": 0.0091, "lr": 2.71237694708576e-07, "epoch": 3.7870967741935484, "percentage": 95.78, "elapsed_time": "0:20:05", "remaining_time": "0:00:53"}
+{"current_steps": 296, "total_steps": 308, "loss": 0.0096, "lr": 2.3117573784966206e-07, "epoch": 3.8, "percentage": 96.1, "elapsed_time": "0:20:09", "remaining_time": "0:00:49"}
+{"current_steps": 297, "total_steps": 308, "loss": 0.0075, "lr": 1.9429974557493014e-07, "epoch": 3.8129032258064517, "percentage": 96.43, "elapsed_time": "0:20:12", "remaining_time": "0:00:44"}
+{"current_steps": 298, "total_steps": 308, "loss": 0.0097, "lr": 1.6061446116990008e-07, "epoch": 3.825806451612903, "percentage": 96.75, "elapsed_time": "0:20:17", "remaining_time": "0:00:40"}
+{"current_steps": 299, "total_steps": 308, "loss": 0.0105, "lr": 1.3012421750568105e-07, "epoch": 3.838709677419355, "percentage": 97.08, "elapsed_time": "0:20:22", "remaining_time": "0:00:36"}
+{"current_steps": 300, "total_steps": 308, "loss": 0.0087, "lr": 1.0283293648165605e-07, "epoch": 3.8516129032258064, "percentage": 97.4, "elapsed_time": "0:20:26", "remaining_time": "0:00:32"}
+{"current_steps": 301, "total_steps": 308, "loss": 0.0081, "lr": 7.874412852099944e-08, "epoch": 3.864516129032258, "percentage": 97.73, "elapsed_time": "0:20:31", "remaining_time": "0:00:28"}
+{"current_steps": 302, "total_steps": 308, "loss": 0.0116, "lr": 5.786089211915202e-08, "epoch": 3.8774193548387097, "percentage": 98.05, "elapsed_time": "0:20:36", "remaining_time": "0:00:24"}
+{"current_steps": 303, "total_steps": 308, "loss": 0.0079, "lr": 4.018591344526479e-08, "epoch": 3.8903225806451616, "percentage": 98.38, "elapsed_time": "0:20:41", "remaining_time": "0:00:20"}
+{"current_steps": 304, "total_steps": 308, "loss": 0.0061, "lr": 2.5721465996675355e-08, "epoch": 3.903225806451613, "percentage": 98.7, "elapsed_time": "0:20:44", "remaining_time": "0:00:16"}
+{"current_steps": 305, "total_steps": 308, "loss": 0.0074, "lr": 1.4469410306480746e-08, "epoch": 3.9161290322580644, "percentage": 99.03, "elapsed_time": "0:20:48", "remaining_time": "0:00:12"}
+{"current_steps": 306, "total_steps": 308, "loss": 0.0084, "lr": 6.431193704217741e-09, "epoch": 3.9290322580645163, "percentage": 99.35, "elapsed_time": "0:20:53", "remaining_time": "0:00:08"}
+{"current_steps": 307, "total_steps": 308, "loss": 0.0118, "lr": 1.6078501296951099e-09, "epoch": 3.9419354838709677, "percentage": 99.68, "elapsed_time": "0:20:56", "remaining_time": "0:00:04"}
+{"current_steps": 308, "total_steps": 308, "loss": 0.0059, "lr": 0.0, "epoch": 3.9548387096774196, "percentage": 100.0, "elapsed_time": "0:21:00", "remaining_time": "0:00:00"}
+{"current_steps": 308, "total_steps": 308, "epoch": 3.9548387096774196, "percentage": 100.0, "elapsed_time": "0:21:29", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2198 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9548387096774196,
+  "eval_steps": 500,
+  "global_step": 308,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012903225806451613,
+      "grad_norm": 3.865084409713745,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 0.2085,
+      "step": 1
+    },
+    {
+      "epoch": 0.025806451612903226,
+      "grad_norm": 4.324934482574463,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 0.2026,
+      "step": 2
+    },
+    {
+      "epoch": 0.03870967741935484,
+      "grad_norm": 3.4087750911712646,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 0.2162,
+      "step": 3
+    },
+    {
+      "epoch": 0.05161290322580645,
+      "grad_norm": 1.6109209060668945,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.1839,
+      "step": 4
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 1.3727400302886963,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 0.1952,
+      "step": 5
+    },
+    {
+      "epoch": 0.07741935483870968,
+      "grad_norm": 1.283871054649353,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 0.1879,
+      "step": 6
+    },
+    {
+      "epoch": 0.09032258064516129,
+      "grad_norm": 1.0045589208602905,
+      "learning_rate": 1.129032258064516e-05,
+      "loss": 0.1501,
+      "step": 7
+    },
+    {
+      "epoch": 0.1032258064516129,
+      "grad_norm": 1.3846447467803955,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 0.1489,
+      "step": 8
+    },
+    {
+      "epoch": 0.11612903225806452,
+      "grad_norm": 1.364700198173523,
+      "learning_rate": 1.4516129032258066e-05,
+      "loss": 0.1484,
+      "step": 9
+    },
+    {
+      "epoch": 0.12903225806451613,
+      "grad_norm": 0.9269119501113892,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 0.1388,
+      "step": 10
+    },
+    {
+      "epoch": 0.14193548387096774,
+      "grad_norm": 2.6850790977478027,
+      "learning_rate": 1.774193548387097e-05,
+      "loss": 0.1319,
+      "step": 11
+    },
+    {
+      "epoch": 0.15483870967741936,
+      "grad_norm": 1.2811543941497803,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 0.1246,
+      "step": 12
+    },
+    {
+      "epoch": 0.16774193548387098,
+      "grad_norm": 1.0256060361862183,
+      "learning_rate": 2.0967741935483873e-05,
+      "loss": 0.1319,
+      "step": 13
+    },
+    {
+      "epoch": 0.18064516129032257,
+      "grad_norm": 0.9394522905349731,
+      "learning_rate": 2.258064516129032e-05,
+      "loss": 0.1191,
+      "step": 14
+    },
+    {
+      "epoch": 0.1935483870967742,
+      "grad_norm": 0.8834514021873474,
+      "learning_rate": 2.4193548387096777e-05,
+      "loss": 0.1248,
+      "step": 15
+    },
+    {
+      "epoch": 0.2064516129032258,
+      "grad_norm": 1.0034328699111938,
+      "learning_rate": 2.5806451612903226e-05,
+      "loss": 0.124,
+      "step": 16
+    },
+    {
+      "epoch": 0.21935483870967742,
+      "grad_norm": 0.8772470951080322,
+      "learning_rate": 2.7419354838709678e-05,
+      "loss": 0.1068,
+      "step": 17
+    },
+    {
+      "epoch": 0.23225806451612904,
+      "grad_norm": 0.9788472652435303,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.1245,
+      "step": 18
+    },
+    {
+      "epoch": 0.24516129032258063,
+      "grad_norm": 0.8098297715187073,
+      "learning_rate": 3.0645161290322585e-05,
+      "loss": 0.1099,
+      "step": 19
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.8270663619041443,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 0.0959,
+      "step": 20
+    },
+    {
+      "epoch": 0.2709677419354839,
+      "grad_norm": 0.6456682682037354,
+      "learning_rate": 3.387096774193548e-05,
+      "loss": 0.0923,
+      "step": 21
+    },
+    {
+      "epoch": 0.2838709677419355,
+      "grad_norm": 0.8719914555549622,
+      "learning_rate": 3.548387096774194e-05,
+      "loss": 0.1088,
+      "step": 22
+    },
+    {
+      "epoch": 0.2967741935483871,
+      "grad_norm": 0.6625027060508728,
+      "learning_rate": 3.7096774193548386e-05,
+      "loss": 0.0882,
+      "step": 23
+    },
+    {
+      "epoch": 0.3096774193548387,
+      "grad_norm": 0.6829620003700256,
+      "learning_rate": 3.870967741935484e-05,
+      "loss": 0.0992,
+      "step": 24
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.8227680921554565,
+      "learning_rate": 4.032258064516129e-05,
+      "loss": 0.1224,
+      "step": 25
+    },
+    {
+      "epoch": 0.33548387096774196,
+      "grad_norm": 0.5915015339851379,
+      "learning_rate": 4.1935483870967746e-05,
+      "loss": 0.0846,
+      "step": 26
+    },
+    {
+      "epoch": 0.34838709677419355,
+      "grad_norm": 0.6318536400794983,
+      "learning_rate": 4.3548387096774194e-05,
+      "loss": 0.0864,
+      "step": 27
+    },
+    {
+      "epoch": 0.36129032258064514,
+      "grad_norm": 0.6643650531768799,
+      "learning_rate": 4.516129032258064e-05,
+      "loss": 0.103,
+      "step": 28
+    },
+    {
+      "epoch": 0.3741935483870968,
+      "grad_norm": 0.6708557605743408,
+      "learning_rate": 4.67741935483871e-05,
+      "loss": 0.1148,
+      "step": 29
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 0.5628843307495117,
+      "learning_rate": 4.8387096774193554e-05,
+      "loss": 0.0789,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5701764225959778,
+      "learning_rate": 5e-05,
+      "loss": 0.0844,
+      "step": 31
+    },
+    {
+      "epoch": 0.4129032258064516,
+      "grad_norm": 0.565487265586853,
+      "learning_rate": 4.999839214987031e-05,
+      "loss": 0.0813,
+      "step": 32
+    },
+    {
+      "epoch": 0.4258064516129032,
+      "grad_norm": 0.5022628903388977,
+      "learning_rate": 4.9993568806295786e-05,
+      "loss": 0.0818,
+      "step": 33
+    },
+    {
+      "epoch": 0.43870967741935485,
+      "grad_norm": 0.5096875429153442,
+      "learning_rate": 4.9985530589693516e-05,
+      "loss": 0.0844,
+      "step": 34
+    },
+    {
+      "epoch": 0.45161290322580644,
+      "grad_norm": 0.6019471883773804,
+      "learning_rate": 4.997427853400333e-05,
+      "loss": 0.0903,
+      "step": 35
+    },
+    {
+      "epoch": 0.4645161290322581,
+      "grad_norm": 0.4620855152606964,
+      "learning_rate": 4.995981408655473e-05,
+      "loss": 0.0772,
+      "step": 36
+    },
+    {
+      "epoch": 0.4774193548387097,
+      "grad_norm": 0.46718630194664,
+      "learning_rate": 4.9942139107880844e-05,
+      "loss": 0.0786,
+      "step": 37
+    },
+    {
+      "epoch": 0.49032258064516127,
+      "grad_norm": 0.6058530211448669,
+      "learning_rate": 4.9921255871479e-05,
+      "loss": 0.0948,
+      "step": 38
+    },
+    {
+      "epoch": 0.5032258064516129,
+      "grad_norm": 0.5089570879936218,
+      "learning_rate": 4.989716706351835e-05,
+      "loss": 0.0805,
+      "step": 39
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.4403476417064667,
+      "learning_rate": 4.986987578249432e-05,
+      "loss": 0.0899,
+      "step": 40
+    },
+    {
+      "epoch": 0.5290322580645161,
+      "grad_norm": 0.640173077583313,
+      "learning_rate": 4.9839385538830104e-05,
+      "loss": 0.0849,
+      "step": 41
+    },
+    {
+      "epoch": 0.5419354838709678,
+      "grad_norm": 0.5224989056587219,
+      "learning_rate": 4.980570025442507e-05,
+      "loss": 0.0845,
+      "step": 42
+    },
+    {
+      "epoch": 0.5548387096774193,
+      "grad_norm": 0.5968887805938721,
+      "learning_rate": 4.9768824262150344e-05,
+      "loss": 0.0912,
+      "step": 43
+    },
+    {
+      "epoch": 0.567741935483871,
+      "grad_norm": 0.5556889772415161,
+      "learning_rate": 4.972876230529142e-05,
+      "loss": 0.0907,
+      "step": 44
+    },
+    {
+      "epoch": 0.5806451612903226,
+      "grad_norm": 0.4258240759372711,
+      "learning_rate": 4.968551953693813e-05,
+      "loss": 0.063,
+      "step": 45
+    },
+    {
+      "epoch": 0.5935483870967742,
+      "grad_norm": 0.5726487636566162,
+      "learning_rate": 4.963910151932171e-05,
+      "loss": 0.0816,
+      "step": 46
+    },
+    {
+      "epoch": 0.6064516129032258,
+      "grad_norm": 0.5164178609848022,
+      "learning_rate": 4.958951422309942e-05,
+      "loss": 0.0815,
+      "step": 47
+    },
+    {
+      "epoch": 0.6193548387096774,
+      "grad_norm": 0.5187662839889526,
+      "learning_rate": 4.95367640265865e-05,
+      "loss": 0.0834,
+      "step": 48
+    },
+    {
+      "epoch": 0.632258064516129,
+      "grad_norm": 0.4768002927303314,
+      "learning_rate": 4.948085771493579e-05,
+      "loss": 0.0818,
+      "step": 49
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 1.3129404783248901,
+      "learning_rate": 4.942180247926492e-05,
+      "loss": 0.077,
+      "step": 50
+    },
+    {
+      "epoch": 0.6580645161290323,
+      "grad_norm": 0.5702396631240845,
+      "learning_rate": 4.935960591573135e-05,
+      "loss": 0.0869,
+      "step": 51
+    },
+    {
+      "epoch": 0.6709677419354839,
+      "grad_norm": 0.5151292085647583,
+      "learning_rate": 4.929427602455532e-05,
+      "loss": 0.091,
+      "step": 52
+    },
+    {
+      "epoch": 0.6838709677419355,
+      "grad_norm": 0.4023990035057068,
+      "learning_rate": 4.922582120899072e-05,
+      "loss": 0.0772,
+      "step": 53
+    },
+    {
+      "epoch": 0.6967741935483871,
+      "grad_norm": 0.5167486667633057,
+      "learning_rate": 4.91542502742443e-05,
+      "loss": 0.0815,
+      "step": 54
+    },
+    {
+      "epoch": 0.7096774193548387,
+      "grad_norm": 0.4807862341403961,
+      "learning_rate": 4.907957242634299e-05,
+      "loss": 0.0819,
+      "step": 55
+    },
+    {
+      "epoch": 0.7225806451612903,
+      "grad_norm": 0.5813907384872437,
+      "learning_rate": 4.900179727094978e-05,
+      "loss": 0.0852,
+      "step": 56
+    },
+    {
+      "epoch": 0.7354838709677419,
+      "grad_norm": 0.44726839661598206,
+      "learning_rate": 4.8920934812128164e-05,
+      "loss": 0.0846,
+      "step": 57
+    },
+    {
+      "epoch": 0.7483870967741936,
+      "grad_norm": 0.4237375557422638,
+      "learning_rate": 4.8836995451055344e-05,
+      "loss": 0.0918,
+      "step": 58
+    },
+    {
+      "epoch": 0.7612903225806451,
+      "grad_norm": 0.3706034719944,
+      "learning_rate": 4.874998998468433e-05,
+      "loss": 0.0713,
+      "step": 59
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.5643853545188904,
+      "learning_rate": 4.865992960435514e-05,
+      "loss": 0.0838,
+      "step": 60
+    },
+    {
+      "epoch": 0.7870967741935484,
+      "grad_norm": 0.4395618140697479,
+      "learning_rate": 4.856682589435531e-05,
+      "loss": 0.0948,
+      "step": 61
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4633603096008301,
+      "learning_rate": 4.8470690830429823e-05,
+      "loss": 0.076,
+      "step": 62
+    },
+    {
+      "epoch": 0.8129032258064516,
+      "grad_norm": 0.44225528836250305,
+      "learning_rate": 4.837153677824067e-05,
+      "loss": 0.0887,
+      "step": 63
+    },
+    {
+      "epoch": 0.8258064516129032,
+      "grad_norm": 0.3647634983062744,
+      "learning_rate": 4.826937649177632e-05,
+      "loss": 0.0752,
+      "step": 64
+    },
+    {
+      "epoch": 0.8387096774193549,
+      "grad_norm": 0.4087846577167511,
+      "learning_rate": 4.816422311171115e-05,
+      "loss": 0.0701,
+      "step": 65
+    },
+    {
+      "epoch": 0.8516129032258064,
+      "grad_norm": 0.3962288796901703,
+      "learning_rate": 4.805609016371522e-05,
+      "loss": 0.072,
+      "step": 66
+    },
+    {
+      "epoch": 0.864516129032258,
+      "grad_norm": 0.35116565227508545,
+      "learning_rate": 4.7944991556714496e-05,
+      "loss": 0.0639,
+      "step": 67
+    },
+    {
+      "epoch": 0.8774193548387097,
+      "grad_norm": 0.37532997131347656,
+      "learning_rate": 4.783094158110174e-05,
+      "loss": 0.0804,
+      "step": 68
+    },
+    {
+      "epoch": 0.8903225806451613,
+      "grad_norm": 0.4580182433128357,
+      "learning_rate": 4.7713954906898415e-05,
+      "loss": 0.0883,
+      "step": 69
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 0.46939095854759216,
+      "learning_rate": 4.759404658186765e-05,
+      "loss": 0.086,
+      "step": 70
+    },
+    {
+      "epoch": 0.9161290322580645,
+      "grad_norm": 0.38567599654197693,
+      "learning_rate": 4.747123202957872e-05,
+      "loss": 0.0627,
+      "step": 71
+    },
+    {
+      "epoch": 0.9290322580645162,
+      "grad_norm": 0.5291863083839417,
+      "learning_rate": 4.7345527047423135e-05,
+      "loss": 0.087,
+      "step": 72
+    },
+    {
+      "epoch": 0.9419354838709677,
+      "grad_norm": 0.5343989133834839,
+      "learning_rate": 4.721694780458266e-05,
+      "loss": 0.0817,
+      "step": 73
+    },
+    {
+      "epoch": 0.9548387096774194,
+      "grad_norm": 0.5286762118339539,
+      "learning_rate": 4.7085510839949444e-05,
+      "loss": 0.0824,
+      "step": 74
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.6843681931495667,
+      "learning_rate": 4.695123305999877e-05,
+      "loss": 0.0757,
+      "step": 75
+    },
+    {
+      "epoch": 0.9806451612903225,
+      "grad_norm": 0.48566552996635437,
+      "learning_rate": 4.681413173661429e-05,
+      "loss": 0.0793,
+      "step": 76
+    },
+    {
+      "epoch": 0.9935483870967742,
+      "grad_norm": 0.5594713091850281,
+      "learning_rate": 4.667422450486646e-05,
+      "loss": 0.0919,
+      "step": 77
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5594713091850281,
+      "learning_rate": 4.653152936074413e-05,
+      "loss": 0.0812,
+      "step": 78
+    },
+    {
+      "epoch": 1.0129032258064516,
+      "grad_norm": 0.6600771546363831,
+      "learning_rate": 4.638606465883979e-05,
+      "loss": 0.0528,
+      "step": 79
+    },
+    {
+      "epoch": 1.0258064516129033,
+      "grad_norm": 0.4466298520565033,
+      "learning_rate": 4.623784910998862e-05,
+      "loss": 0.0562,
+      "step": 80
+    },
+    {
+      "epoch": 1.038709677419355,
+      "grad_norm": 0.46932584047317505,
+      "learning_rate": 4.608690177886177e-05,
+      "loss": 0.052,
+      "step": 81
+    },
+    {
+      "epoch": 1.0516129032258064,
+      "grad_norm": 0.3475061357021332,
+      "learning_rate": 4.593324208151412e-05,
+      "loss": 0.0477,
+      "step": 82
+    },
+    {
+      "epoch": 1.064516129032258,
+      "grad_norm": 0.3392031788825989,
+      "learning_rate": 4.577688978288681e-05,
+      "loss": 0.0552,
+      "step": 83
+    },
+    {
+      "epoch": 1.0774193548387097,
+      "grad_norm": 0.36944520473480225,
+      "learning_rate": 4.5617864994264936e-05,
+      "loss": 0.0623,
+      "step": 84
+    },
+    {
+      "epoch": 1.0903225806451613,
+      "grad_norm": 0.3976334035396576,
+      "learning_rate": 4.545618817069066e-05,
+      "loss": 0.055,
+      "step": 85
+    },
+    {
+      "epoch": 1.103225806451613,
+      "grad_norm": 0.3573772609233856,
+      "learning_rate": 4.529188010833212e-05,
+      "loss": 0.0652,
+      "step": 86
+    },
+    {
+      "epoch": 1.1161290322580646,
+      "grad_norm": 0.37986183166503906,
+      "learning_rate": 4.512496194180846e-05,
+      "loss": 0.0506,
+      "step": 87
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.45936280488967896,
+      "learning_rate": 4.495545514147134e-05,
+      "loss": 0.0671,
+      "step": 88
+    },
+    {
+      "epoch": 1.1419354838709677,
+      "grad_norm": 0.3391832113265991,
+      "learning_rate": 4.478338151064323e-05,
+      "loss": 0.0537,
+      "step": 89
+    },
+    {
+      "epoch": 1.1548387096774193,
+      "grad_norm": 0.30911317467689514,
+      "learning_rate": 4.460876318281291e-05,
+      "loss": 0.0531,
+      "step": 90
+    },
+    {
+      "epoch": 1.167741935483871,
+      "grad_norm": 0.4350668489933014,
+      "learning_rate": 4.443162261878846e-05,
+      "loss": 0.051,
+      "step": 91
+    },
+    {
+      "epoch": 1.1806451612903226,
+      "grad_norm": 0.34030795097351074,
+      "learning_rate": 4.425198260380818e-05,
+      "loss": 0.0509,
+      "step": 92
+    },
+    {
+      "epoch": 1.1935483870967742,
+      "grad_norm": 0.31266239285469055,
+      "learning_rate": 4.406986624460979e-05,
+      "loss": 0.0493,
+      "step": 93
+    },
+    {
+      "epoch": 1.206451612903226,
+      "grad_norm": 0.3814278244972229,
+      "learning_rate": 4.3885296966458224e-05,
+      "loss": 0.0575,
+      "step": 94
+    },
+    {
+      "epoch": 1.2193548387096773,
+      "grad_norm": 0.2861946225166321,
+      "learning_rate": 4.369829851013251e-05,
+      "loss": 0.0518,
+      "step": 95
+    },
+    {
+      "epoch": 1.232258064516129,
+      "grad_norm": 0.35761791467666626,
+      "learning_rate": 4.350889492887203e-05,
+      "loss": 0.0509,
+      "step": 96
+    },
+    {
+      "epoch": 1.2451612903225806,
+      "grad_norm": 0.321609765291214,
+      "learning_rate": 4.3317110585282595e-05,
+      "loss": 0.0468,
+      "step": 97
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 0.33591514825820923,
+      "learning_rate": 4.3122970148202744e-05,
+      "loss": 0.055,
+      "step": 98
+    },
+    {
+      "epoch": 1.270967741935484,
+      "grad_norm": 0.38554760813713074,
+      "learning_rate": 4.292649858953063e-05,
+      "loss": 0.07,
+      "step": 99
+    },
+    {
+      "epoch": 1.2838709677419355,
+      "grad_norm": 0.5272489786148071,
+      "learning_rate": 4.272772118101195e-05,
+      "loss": 0.0564,
+      "step": 100
+    },
+    {
+      "epoch": 1.2967741935483872,
+      "grad_norm": 0.4388972818851471,
+      "learning_rate": 4.252666349098926e-05,
+      "loss": 0.0536,
+      "step": 101
+    },
+    {
+      "epoch": 1.3096774193548386,
+      "grad_norm": 0.33931440114974976,
+      "learning_rate": 4.2323351381113206e-05,
+      "loss": 0.0472,
+      "step": 102
+    },
+    {
+      "epoch": 1.3225806451612903,
+      "grad_norm": 0.2954395115375519,
+      "learning_rate": 4.211781100301596e-05,
+      "loss": 0.0645,
+      "step": 103
+    },
+    {
+      "epoch": 1.335483870967742,
+      "grad_norm": 0.5045889019966125,
+      "learning_rate": 4.1910068794947404e-05,
+      "loss": 0.056,
+      "step": 104
+    },
+    {
+      "epoch": 1.3483870967741935,
+      "grad_norm": 0.3853508532047272,
+      "learning_rate": 4.170015147837444e-05,
+      "loss": 0.0518,
+      "step": 105
+    },
+    {
+      "epoch": 1.3612903225806452,
+      "grad_norm": 0.27302005887031555,
+      "learning_rate": 4.148808605454385e-05,
+      "loss": 0.0487,
+      "step": 106
+    },
+    {
+      "epoch": 1.3741935483870968,
+      "grad_norm": 0.41000276803970337,
+      "learning_rate": 4.127389980100915e-05,
+      "loss": 0.0528,
+      "step": 107
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "grad_norm": 0.3967251479625702,
+      "learning_rate": 4.1057620268122004e-05,
+      "loss": 0.0485,
+      "step": 108
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.30169478058815,
+      "learning_rate": 4.08392752754884e-05,
+      "loss": 0.0485,
+      "step": 109
+    },
+    {
+      "epoch": 1.4129032258064516,
+      "grad_norm": 0.3874256908893585,
+      "learning_rate": 4.0618892908390316e-05,
+      "loss": 0.0514,
+      "step": 110
+    },
+    {
+      "epoch": 1.4258064516129032,
+      "grad_norm": 0.29030513763427734,
+      "learning_rate": 4.039650151417316e-05,
+      "loss": 0.0442,
+      "step": 111
+    },
+    {
+      "epoch": 1.4387096774193548,
+      "grad_norm": 0.3206923007965088,
+      "learning_rate": 4.0172129698599484e-05,
+      "loss": 0.052,
+      "step": 112
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.3883202075958252,
+      "learning_rate": 3.994580632216952e-05,
+      "loss": 0.057,
+      "step": 113
+    },
+    {
+      "epoch": 1.4645161290322581,
+      "grad_norm": 0.38505852222442627,
+      "learning_rate": 3.971756049640888e-05,
+      "loss": 0.0515,
+      "step": 114
+    },
+    {
+      "epoch": 1.4774193548387098,
+      "grad_norm": 0.27141115069389343,
+      "learning_rate": 3.9487421580124e-05,
+      "loss": 0.0524,
+      "step": 115
+    },
+    {
+      "epoch": 1.4903225806451612,
+      "grad_norm": 0.4098750054836273,
+      "learning_rate": 3.92554191756258e-05,
+      "loss": 0.0544,
+      "step": 116
+    },
+    {
+      "epoch": 1.5032258064516129,
+      "grad_norm": 0.3381025791168213,
+      "learning_rate": 3.902158312492196e-05,
+      "loss": 0.0468,
+      "step": 117
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 0.3622021973133087,
+      "learning_rate": 3.878594350587844e-05,
+      "loss": 0.0451,
+      "step": 118
+    },
+    {
+      "epoch": 1.5290322580645161,
+      "grad_norm": 0.31938228011131287,
+      "learning_rate": 3.8548530628350623e-05,
+      "loss": 0.0509,
+      "step": 119
+    },
+    {
+      "epoch": 1.5419354838709678,
+      "grad_norm": 0.3087027370929718,
+      "learning_rate": 3.8309375030284566e-05,
+      "loss": 0.0616,
+      "step": 120
+    },
+    {
+      "epoch": 1.5548387096774192,
+      "grad_norm": 0.36196205019950867,
+      "learning_rate": 3.806850747378902e-05,
+      "loss": 0.0514,
+      "step": 121
+    },
+    {
+      "epoch": 1.567741935483871,
+      "grad_norm": 0.31175723671913147,
+      "learning_rate": 3.782595894117854e-05,
+      "loss": 0.0478,
+      "step": 122
+    },
+    {
+      "epoch": 1.5806451612903225,
+      "grad_norm": 0.3437715768814087,
+      "learning_rate": 3.758176063098829e-05,
+      "loss": 0.0489,
+      "step": 123
+    },
+    {
+      "epoch": 1.5935483870967742,
+      "grad_norm": 0.3346206247806549,
+      "learning_rate": 3.733594395396106e-05,
+      "loss": 0.0516,
+      "step": 124
+    },
+    {
+      "epoch": 1.6064516129032258,
+      "grad_norm": 0.38583481311798096,
+      "learning_rate": 3.7088540529006924e-05,
+      "loss": 0.0461,
+      "step": 125
+    },
+    {
+      "epoch": 1.6193548387096774,
+      "grad_norm": 0.25379714369773865,
+      "learning_rate": 3.68395821791362e-05,
+      "loss": 0.0414,
+      "step": 126
+    },
+    {
+      "epoch": 1.632258064516129,
+      "grad_norm": 0.42217546701431274,
+      "learning_rate": 3.65891009273661e-05,
+      "loss": 0.0556,
+      "step": 127
+    },
+    {
+      "epoch": 1.6451612903225805,
+      "grad_norm": 0.36978331208229065,
+      "learning_rate": 3.633712899260166e-05,
+      "loss": 0.0575,
+      "step": 128
+    },
+    {
+      "epoch": 1.6580645161290324,
+      "grad_norm": 0.3139955401420593,
+      "learning_rate": 3.608369878549154e-05,
+      "loss": 0.0451,
+      "step": 129
+    },
+    {
+      "epoch": 1.6709677419354838,
+      "grad_norm": 0.3436100482940674,
+      "learning_rate": 3.582884290425903e-05,
+      "loss": 0.0522,
+      "step": 130
+    },
+    {
+      "epoch": 1.6838709677419355,
+      "grad_norm": 0.2942555248737335,
+      "learning_rate": 3.557259413050907e-05,
+      "loss": 0.049,
+      "step": 131
+    },
+    {
+      "epoch": 1.696774193548387,
+      "grad_norm": 0.32971078157424927,
+      "learning_rate": 3.531498542501161e-05,
+      "loss": 0.0495,
+      "step": 132
+    },
+    {
+      "epoch": 1.7096774193548387,
+      "grad_norm": 0.2842581272125244,
+      "learning_rate": 3.505604992346187e-05,
+      "loss": 0.0494,
+      "step": 133
+    },
+    {
+      "epoch": 1.7225806451612904,
+      "grad_norm": 0.37220752239227295,
+      "learning_rate": 3.4795820932218235e-05,
+      "loss": 0.0489,
+      "step": 134
+    },
+    {
+      "epoch": 1.7354838709677418,
+      "grad_norm": 0.3396855592727661,
+      "learning_rate": 3.4534331924018095e-05,
+      "loss": 0.058,
+      "step": 135
+    },
+    {
+      "epoch": 1.7483870967741937,
+      "grad_norm": 0.30913567543029785,
+      "learning_rate": 3.427161653367231e-05,
+      "loss": 0.0505,
+      "step": 136
+    },
+    {
+      "epoch": 1.761290322580645,
+      "grad_norm": 0.3557908535003662,
+      "learning_rate": 3.4007708553738836e-05,
+      "loss": 0.0454,
+      "step": 137
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.32114386558532715,
+      "learning_rate": 3.3742641930176045e-05,
+      "loss": 0.0462,
+      "step": 138
+    },
+    {
+      "epoch": 1.7870967741935484,
+      "grad_norm": 0.264426589012146,
+      "learning_rate": 3.347645075797635e-05,
+      "loss": 0.0436,
+      "step": 139
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.3021955192089081,
+      "learning_rate": 3.320916927678061e-05,
+      "loss": 0.0386,
+      "step": 140
+    },
+    {
+      "epoch": 1.8129032258064517,
+      "grad_norm": 0.35488826036453247,
+      "learning_rate": 3.2940831866473966e-05,
+      "loss": 0.0462,
+      "step": 141
+    },
+    {
+      "epoch": 1.8258064516129031,
+      "grad_norm": 0.2876163125038147,
+      "learning_rate": 3.2671473042763604e-05,
+      "loss": 0.0545,
+      "step": 142
+    },
+    {
+      "epoch": 1.838709677419355,
+      "grad_norm": 0.3992978036403656,
+      "learning_rate": 3.240112745273911e-05,
+      "loss": 0.0434,
+      "step": 143
+    },
+    {
+      "epoch": 1.8516129032258064,
+      "grad_norm": 0.3140002489089966,
+      "learning_rate": 3.212982987041582e-05,
+      "loss": 0.0459,
+      "step": 144
+    },
+    {
+      "epoch": 1.864516129032258,
+      "grad_norm": 0.357721209526062,
+      "learning_rate": 3.1857615192261984e-05,
+      "loss": 0.0548,
+      "step": 145
+    },
+    {
+      "epoch": 1.8774193548387097,
+      "grad_norm": 0.32279306650161743,
+      "learning_rate": 3.158451843271005e-05,
+      "loss": 0.0593,
+      "step": 146
+    },
+    {
+      "epoch": 1.8903225806451613,
+      "grad_norm": 0.3754781484603882,
+      "learning_rate": 3.131057471965283e-05,
+      "loss": 0.0508,
+      "step": 147
+    },
+    {
+      "epoch": 1.903225806451613,
+      "grad_norm": 0.42713454365730286,
+      "learning_rate": 3.10358192899251e-05,
+      "loss": 0.0423,
+      "step": 148
+    },
+    {
+      "epoch": 1.9161290322580644,
+      "grad_norm": 0.28894898295402527,
+      "learning_rate": 3.076028748477112e-05,
+      "loss": 0.0442,
+      "step": 149
+    },
+    {
+      "epoch": 1.9290322580645163,
+      "grad_norm": 0.32115331292152405,
+      "learning_rate": 3.0484014745298784e-05,
+      "loss": 0.0571,
+      "step": 150
+    },
+    {
+      "epoch": 1.9419354838709677,
+      "grad_norm": 0.36180686950683594,
+      "learning_rate": 3.0207036607920892e-05,
+      "loss": 0.0498,
+      "step": 151
+    },
+    {
+      "epoch": 1.9548387096774194,
+      "grad_norm": 0.36315590143203735,
+      "learning_rate": 2.9929388699784163e-05,
+      "loss": 0.0548,
+      "step": 152
+    },
+    {
+      "epoch": 1.967741935483871,
+      "grad_norm": 0.24509944021701813,
+      "learning_rate": 2.9651106734186618e-05,
+      "loss": 0.0473,
+      "step": 153
+    },
+    {
+      "epoch": 1.9806451612903224,
+      "grad_norm": 0.30309274792671204,
+      "learning_rate": 2.9372226505983802e-05,
+      "loss": 0.0515,
+      "step": 154
+    },
+    {
+      "epoch": 1.9935483870967743,
+      "grad_norm": 0.31110507249832153,
+      "learning_rate": 2.9092783886984615e-05,
+      "loss": 0.049,
+      "step": 155
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5940459966659546,
+      "learning_rate": 2.8812814821337147e-05,
+      "loss": 0.0358,
+      "step": 156
+    },
+    {
+      "epoch": 2.0129032258064514,
+      "grad_norm": 0.23582255840301514,
+      "learning_rate": 2.8532355320905274e-05,
+      "loss": 0.0252,
+      "step": 157
+    },
+    {
+      "epoch": 2.0258064516129033,
+      "grad_norm": 0.2490931898355484,
+      "learning_rate": 2.825144146063654e-05,
+      "loss": 0.0242,
+      "step": 158
+    },
+    {
+      "epoch": 2.0387096774193547,
+      "grad_norm": 0.300824373960495,
+      "learning_rate": 2.7970109373921878e-05,
+      "loss": 0.0278,
+      "step": 159
+    },
+    {
+      "epoch": 2.0516129032258066,
+      "grad_norm": 0.2460525780916214,
+      "learning_rate": 2.7688395247947842e-05,
+      "loss": 0.0292,
+      "step": 160
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 0.2941141724586487,
+      "learning_rate": 2.740633531904196e-05,
+      "loss": 0.0257,
+      "step": 161
+    },
+    {
+      "epoch": 2.07741935483871,
+      "grad_norm": 0.27139392495155334,
+      "learning_rate": 2.712396586801169e-05,
+      "loss": 0.0246,
+      "step": 162
+    },
+    {
+      "epoch": 2.0903225806451613,
+      "grad_norm": 0.3047543168067932,
+      "learning_rate": 2.6841323215477714e-05,
+      "loss": 0.0313,
+      "step": 163
+    },
+    {
+      "epoch": 2.1032258064516127,
+      "grad_norm": 0.3697696924209595,
+      "learning_rate": 2.6558443717202076e-05,
+      "loss": 0.0311,
+      "step": 164
+    },
+    {
+      "epoch": 2.1161290322580646,
+      "grad_norm": 0.4939499497413635,
+      "learning_rate": 2.6275363759411815e-05,
+      "loss": 0.036,
+      "step": 165
+    },
+    {
+      "epoch": 2.129032258064516,
+      "grad_norm": 0.2502232789993286,
+      "learning_rate": 2.599211975411867e-05,
+      "loss": 0.0194,
+      "step": 166
+    },
+    {
+      "epoch": 2.141935483870968,
+      "grad_norm": 0.2647090554237366,
+      "learning_rate": 2.57087481344355e-05,
+      "loss": 0.0259,
+      "step": 167
+    },
+    {
+      "epoch": 2.1548387096774193,
+      "grad_norm": 0.2818278968334198,
+      "learning_rate": 2.5425285349889938e-05,
+      "loss": 0.0239,
+      "step": 168
+    },
+    {
+      "epoch": 2.167741935483871,
+      "grad_norm": 0.28670820593833923,
+      "learning_rate": 2.5141767861735976e-05,
+      "loss": 0.0248,
+      "step": 169
+    },
+    {
+      "epoch": 2.1806451612903226,
+      "grad_norm": 0.2521524727344513,
+      "learning_rate": 2.485823213826403e-05,
+      "loss": 0.0259,
+      "step": 170
+    },
+    {
+      "epoch": 2.193548387096774,
+      "grad_norm": 0.2689652740955353,
+      "learning_rate": 2.457471465011007e-05,
+      "loss": 0.026,
+      "step": 171
+    },
+    {
+      "epoch": 2.206451612903226,
+      "grad_norm": 0.24064841866493225,
+      "learning_rate": 2.4291251865564505e-05,
+      "loss": 0.0252,
+      "step": 172
+    },
+    {
+      "epoch": 2.2193548387096773,
+      "grad_norm": 0.26753664016723633,
+      "learning_rate": 2.400788024588134e-05,
+      "loss": 0.0236,
+      "step": 173
+    },
+    {
+      "epoch": 2.232258064516129,
+      "grad_norm": 0.30342286825180054,
+      "learning_rate": 2.3724636240588194e-05,
+      "loss": 0.0346,
+      "step": 174
+    },
+    {
+      "epoch": 2.2451612903225806,
+      "grad_norm": 0.36332225799560547,
+      "learning_rate": 2.3441556282797934e-05,
+      "loss": 0.0351,
+      "step": 175
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 0.2872660458087921,
+      "learning_rate": 2.315867678452229e-05,
+      "loss": 0.0257,
+      "step": 176
+    },
+    {
+      "epoch": 2.270967741935484,
+      "grad_norm": 0.33576029539108276,
+      "learning_rate": 2.287603413198831e-05,
+      "loss": 0.0307,
+      "step": 177
+    },
+    {
+      "epoch": 2.2838709677419353,
+      "grad_norm": 0.42973652482032776,
+      "learning_rate": 2.2593664680958045e-05,
+      "loss": 0.0325,
+      "step": 178
+    },
+    {
+      "epoch": 2.296774193548387,
+      "grad_norm": 0.28366559743881226,
+      "learning_rate": 2.231160475205216e-05,
+      "loss": 0.0279,
+      "step": 179
+    },
+    {
+      "epoch": 2.3096774193548386,
+      "grad_norm": 0.23520596325397491,
+      "learning_rate": 2.202989062607813e-05,
+      "loss": 0.0242,
+      "step": 180
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 0.23934811353683472,
+      "learning_rate": 2.1748558539363458e-05,
+      "loss": 0.0213,
+      "step": 181
+    },
+    {
+      "epoch": 2.335483870967742,
+      "grad_norm": 0.2189173400402069,
+      "learning_rate": 2.1467644679094728e-05,
+      "loss": 0.0202,
+      "step": 182
+    },
+    {
+      "epoch": 2.3483870967741938,
+      "grad_norm": 0.42822569608688354,
+      "learning_rate": 2.118718517866286e-05,
+      "loss": 0.0361,
+      "step": 183
+    },
+    {
+      "epoch": 2.361290322580645,
+      "grad_norm": 0.2864365875720978,
+      "learning_rate": 2.0907216113015397e-05,
+      "loss": 0.0303,
+      "step": 184
+    },
+    {
+      "epoch": 2.3741935483870966,
+      "grad_norm": 0.24325411021709442,
+      "learning_rate": 2.0627773494016207e-05,
+      "loss": 0.0265,
+      "step": 185
+    },
+    {
+      "epoch": 2.3870967741935485,
+      "grad_norm": 0.23324590921401978,
+      "learning_rate": 2.0348893265813394e-05,
+      "loss": 0.0233,
+      "step": 186
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.2864069640636444,
+      "learning_rate": 2.0070611300215843e-05,
+      "loss": 0.0259,
+      "step": 187
+    },
+    {
+      "epoch": 2.412903225806452,
+      "grad_norm": 0.2672640085220337,
+      "learning_rate": 1.979296339207912e-05,
+      "loss": 0.0267,
+      "step": 188
+    },
+    {
+      "epoch": 2.425806451612903,
+      "grad_norm": 0.22086627781391144,
+      "learning_rate": 1.951598525470122e-05,
+      "loss": 0.02,
+      "step": 189
+    },
+    {
+      "epoch": 2.4387096774193546,
+      "grad_norm": 0.24434693157672882,
+      "learning_rate": 1.923971251522888e-05,
+      "loss": 0.0235,
+      "step": 190
+    },
+    {
+      "epoch": 2.4516129032258065,
+      "grad_norm": 0.2901481091976166,
+      "learning_rate": 1.8964180710074905e-05,
+      "loss": 0.0242,
+      "step": 191
+    },
+    {
+      "epoch": 2.464516129032258,
+      "grad_norm": 0.2797795236110687,
+      "learning_rate": 1.8689425280347166e-05,
+      "loss": 0.0246,
+      "step": 192
+    },
+    {
+      "epoch": 2.47741935483871,
+      "grad_norm": 0.22296951711177826,
+      "learning_rate": 1.8415481567289954e-05,
+      "loss": 0.0223,
+      "step": 193
+    },
+    {
+      "epoch": 2.490322580645161,
+      "grad_norm": 0.2699308395385742,
+      "learning_rate": 1.8142384807738022e-05,
+      "loss": 0.027,
+      "step": 194
+    },
+    {
+      "epoch": 2.5032258064516126,
+      "grad_norm": 0.23768910765647888,
+      "learning_rate": 1.787017012958419e-05,
+      "loss": 0.0241,
+      "step": 195
+    },
+    {
+      "epoch": 2.5161290322580645,
+      "grad_norm": 0.2236274927854538,
+      "learning_rate": 1.75988725472609e-05,
+      "loss": 0.0241,
+      "step": 196
+    },
+    {
+      "epoch": 2.5290322580645164,
+      "grad_norm": 0.31210729479789734,
+      "learning_rate": 1.7328526957236406e-05,
+      "loss": 0.0302,
+      "step": 197
+    },
+    {
+      "epoch": 2.541935483870968,
+      "grad_norm": 0.22504620254039764,
+      "learning_rate": 1.7059168133526043e-05,
+      "loss": 0.0236,
+      "step": 198
+    },
+    {
+      "epoch": 2.554838709677419,
+      "grad_norm": 0.24498535692691803,
+      "learning_rate": 1.6790830723219398e-05,
+      "loss": 0.0228,
+      "step": 199
+    },
+    {
+      "epoch": 2.567741935483871,
+      "grad_norm": 0.2544174790382385,
+      "learning_rate": 1.6523549242023655e-05,
+      "loss": 0.027,
+      "step": 200
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.2597277760505676,
+      "learning_rate": 1.6257358069823965e-05,
+      "loss": 0.0304,
+      "step": 201
+    },
+    {
+      "epoch": 2.5935483870967744,
+      "grad_norm": 0.2677987515926361,
+      "learning_rate": 1.5992291446261166e-05,
+      "loss": 0.0254,
+      "step": 202
+    },
+    {
+      "epoch": 2.606451612903226,
+      "grad_norm": 0.27171266078948975,
+      "learning_rate": 1.5728383466327684e-05,
+      "loss": 0.0222,
+      "step": 203
+    },
+    {
+      "epoch": 2.6193548387096772,
+      "grad_norm": 0.2346351146697998,
+      "learning_rate": 1.5465668075981904e-05,
+      "loss": 0.0219,
+      "step": 204
+    },
+    {
+      "epoch": 2.632258064516129,
+      "grad_norm": 0.25438180565834045,
+      "learning_rate": 1.520417906778176e-05,
+      "loss": 0.0264,
+      "step": 205
+    },
+    {
+      "epoch": 2.6451612903225805,
+      "grad_norm": 0.2690618336200714,
+      "learning_rate": 1.4943950076538135e-05,
+      "loss": 0.0237,
+      "step": 206
+    },
+    {
+      "epoch": 2.6580645161290324,
+      "grad_norm": 0.29505690932273865,
+      "learning_rate": 1.4685014574988393e-05,
+      "loss": 0.0313,
+      "step": 207
+    },
+    {
+      "epoch": 2.670967741935484,
+      "grad_norm": 0.26153627038002014,
+      "learning_rate": 1.4427405869490923e-05,
+      "loss": 0.0236,
+      "step": 208
+    },
+    {
+      "epoch": 2.6838709677419352,
+      "grad_norm": 0.2462136447429657,
+      "learning_rate": 1.4171157095740976e-05,
+      "loss": 0.027,
+      "step": 209
+    },
+    {
+      "epoch": 2.696774193548387,
+      "grad_norm": 0.33909931778907776,
+      "learning_rate": 1.391630121450847e-05,
+      "loss": 0.0257,
+      "step": 210
+    },
+    {
+      "epoch": 2.709677419354839,
+      "grad_norm": 0.2736709415912628,
+      "learning_rate": 1.3662871007398348e-05,
+      "loss": 0.0274,
+      "step": 211
+    },
+    {
+      "epoch": 2.7225806451612904,
+      "grad_norm": 0.3460533022880554,
+      "learning_rate": 1.3410899072633915e-05,
+      "loss": 0.0292,
+      "step": 212
+    },
+    {
+      "epoch": 2.735483870967742,
+      "grad_norm": 0.28637826442718506,
+      "learning_rate": 1.3160417820863807e-05,
+      "loss": 0.0249,
+      "step": 213
+    },
+    {
+      "epoch": 2.7483870967741937,
+      "grad_norm": 0.21176108717918396,
+      "learning_rate": 1.2911459470993085e-05,
+      "loss": 0.019,
+      "step": 214
+    },
+    {
+      "epoch": 2.761290322580645,
+      "grad_norm": 0.22695419192314148,
+      "learning_rate": 1.2664056046038942e-05,
+      "loss": 0.0248,
+      "step": 215
+    },
+    {
+      "epoch": 2.774193548387097,
+      "grad_norm": 0.3826678693294525,
+      "learning_rate": 1.2418239369011712e-05,
+      "loss": 0.0206,
+      "step": 216
+    },
+    {
+      "epoch": 2.7870967741935484,
+      "grad_norm": 0.21120679378509521,
+      "learning_rate": 1.217404105882147e-05,
+      "loss": 0.02,
+      "step": 217
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.266303151845932,
+      "learning_rate": 1.1931492526210988e-05,
+      "loss": 0.0217,
+      "step": 218
+    },
+    {
+      "epoch": 2.8129032258064517,
+      "grad_norm": 0.2666541635990143,
+      "learning_rate": 1.1690624969715441e-05,
+      "loss": 0.0248,
+      "step": 219
+    },
+    {
+      "epoch": 2.825806451612903,
+      "grad_norm": 0.2325655072927475,
+      "learning_rate": 1.145146937164938e-05,
+      "loss": 0.0226,
+      "step": 220
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 0.277413934469223,
+      "learning_rate": 1.121405649412156e-05,
+      "loss": 0.0272,
+      "step": 221
+    },
+    {
+      "epoch": 2.8516129032258064,
+      "grad_norm": 0.23814360797405243,
+      "learning_rate": 1.0978416875078042e-05,
+      "loss": 0.0195,
+      "step": 222
+    },
+    {
+      "epoch": 2.864516129032258,
+      "grad_norm": 0.3257719576358795,
+      "learning_rate": 1.0744580824374217e-05,
+      "loss": 0.0336,
+      "step": 223
+    },
+    {
+      "epoch": 2.8774193548387097,
+      "grad_norm": 0.24910488724708557,
+      "learning_rate": 1.0512578419876004e-05,
+      "loss": 0.0236,
+      "step": 224
+    },
+    {
+      "epoch": 2.8903225806451616,
+      "grad_norm": 0.27725309133529663,
+      "learning_rate": 1.0282439503591135e-05,
+      "loss": 0.0272,
+      "step": 225
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 0.23216702044010162,
+      "learning_rate": 1.0054193677830481e-05,
+      "loss": 0.0244,
+      "step": 226
+    },
+    {
+      "epoch": 2.9161290322580644,
+      "grad_norm": 0.27499204874038696,
+      "learning_rate": 9.827870301400527e-06,
+      "loss": 0.0214,
+      "step": 227
+    },
+    {
+      "epoch": 2.9290322580645163,
+      "grad_norm": 0.2503328323364258,
+      "learning_rate": 9.603498485826848e-06,
+      "loss": 0.0223,
+      "step": 228
+    },
+    {
+      "epoch": 2.9419354838709677,
+      "grad_norm": 0.23868584632873535,
+      "learning_rate": 9.38110709160969e-06,
+      "loss": 0.0227,
+      "step": 229
+    },
+    {
+      "epoch": 2.9548387096774196,
+      "grad_norm": 0.3298948407173157,
+      "learning_rate": 9.160724724511608e-06,
+      "loss": 0.0288,
+      "step": 230
+    },
+    {
+      "epoch": 2.967741935483871,
+      "grad_norm": 0.23431891202926636,
+      "learning_rate": 8.942379731877992e-06,
+      "loss": 0.023,
+      "step": 231
+    },
+    {
+      "epoch": 2.9806451612903224,
+      "grad_norm": 0.2671021819114685,
+      "learning_rate": 8.726100198990853e-06,
+      "loss": 0.0213,
+      "step": 232
+    },
+    {
+      "epoch": 2.9935483870967743,
+      "grad_norm": 0.29010385274887085,
+      "learning_rate": 8.51191394545615e-06,
+      "loss": 0.0314,
+      "step": 233
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.29010385274887085,
+      "learning_rate": 8.299848521625563e-06,
+      "loss": 0.0159,
+      "step": 234
+    },
+    {
+      "epoch": 3.0129032258064514,
+      "grad_norm": 0.28189539909362793,
+      "learning_rate": 8.089931205052597e-06,
+      "loss": 0.0106,
+      "step": 235
+    },
+    {
+      "epoch": 3.0258064516129033,
+      "grad_norm": 0.1651533842086792,
+      "learning_rate": 7.882188996984046e-06,
+      "loss": 0.0122,
+      "step": 236
+    },
+    {
+      "epoch": 3.0387096774193547,
+      "grad_norm": 0.1792869120836258,
+      "learning_rate": 7.676648618886798e-06,
+      "loss": 0.0129,
+      "step": 237
+    },
+    {
+      "epoch": 3.0516129032258066,
+      "grad_norm": 0.16915558278560638,
+      "learning_rate": 7.473336509010742e-06,
+      "loss": 0.0099,
+      "step": 238
+    },
+    {
+      "epoch": 3.064516129032258,
+      "grad_norm": 0.15584175288677216,
+      "learning_rate": 7.2722788189880545e-06,
+      "loss": 0.0123,
+      "step": 239
+    },
+    {
+      "epoch": 3.07741935483871,
+      "grad_norm": 0.1726021021604538,
+      "learning_rate": 7.073501410469371e-06,
+      "loss": 0.0114,
+      "step": 240
+    },
+    {
+      "epoch": 3.0903225806451613,
+      "grad_norm": 0.15609051287174225,
+      "learning_rate": 6.877029851797265e-06,
+      "loss": 0.0091,
+      "step": 241
+    },
+    {
+      "epoch": 3.1032258064516127,
+      "grad_norm": 0.14097200334072113,
+      "learning_rate": 6.6828894147174165e-06,
+      "loss": 0.0084,
+      "step": 242
+    },
+    {
+      "epoch": 3.1161290322580646,
+      "grad_norm": 0.17083188891410828,
+      "learning_rate": 6.491105071127984e-06,
+      "loss": 0.0118,
+      "step": 243
+    },
+    {
+      "epoch": 3.129032258064516,
+      "grad_norm": 0.18476150929927826,
+      "learning_rate": 6.3017014898674955e-06,
+      "loss": 0.0079,
+      "step": 244
+    },
+    {
+      "epoch": 3.141935483870968,
+      "grad_norm": 0.22733564674854279,
+      "learning_rate": 6.114703033541783e-06,
+      "loss": 0.013,
+      "step": 245
+    },
+    {
+      "epoch": 3.1548387096774193,
+      "grad_norm": 0.15913838148117065,
+      "learning_rate": 5.930133755390216e-06,
+      "loss": 0.0068,
+      "step": 246
+    },
+    {
+      "epoch": 3.167741935483871,
+      "grad_norm": 0.1369076371192932,
+      "learning_rate": 5.7480173961918266e-06,
+      "loss": 0.0077,
+      "step": 247
+    },
+    {
+      "epoch": 3.1806451612903226,
+      "grad_norm": 0.2318694293498993,
+      "learning_rate": 5.568377381211548e-06,
+      "loss": 0.0095,
+      "step": 248
+    },
+    {
+      "epoch": 3.193548387096774,
+      "grad_norm": 0.21019090712070465,
+      "learning_rate": 5.391236817187095e-06,
+      "loss": 0.0095,
+      "step": 249
+    },
+    {
+      "epoch": 3.206451612903226,
+      "grad_norm": 0.1967868059873581,
+      "learning_rate": 5.216618489356773e-06,
+      "loss": 0.0111,
+      "step": 250
+    },
+    {
+      "epoch": 3.2193548387096773,
+      "grad_norm": 0.24731586873531342,
+      "learning_rate": 5.0445448585286684e-06,
+      "loss": 0.0072,
+      "step": 251
+    },
+    {
+      "epoch": 3.232258064516129,
+      "grad_norm": 0.19581767916679382,
+      "learning_rate": 4.87503805819155e-06,
+      "loss": 0.0055,
+      "step": 252
+    },
+    {
+      "epoch": 3.2451612903225806,
+      "grad_norm": 0.1791073977947235,
+      "learning_rate": 4.708119891667892e-06,
+      "loss": 0.0088,
+      "step": 253
+    },
+    {
+      "epoch": 3.258064516129032,
+      "grad_norm": 0.25945040583610535,
+      "learning_rate": 4.5438118293093416e-06,
+      "loss": 0.0071,
+      "step": 254
+    },
+    {
+      "epoch": 3.270967741935484,
+      "grad_norm": 0.21385855972766876,
+      "learning_rate": 4.382135005735072e-06,
+      "loss": 0.0173,
+      "step": 255
+    },
+    {
+      "epoch": 3.2838709677419353,
+      "grad_norm": 0.5789936780929565,
+      "learning_rate": 4.223110217113191e-06,
+      "loss": 0.0079,
+      "step": 256
+    },
+    {
+      "epoch": 3.296774193548387,
+      "grad_norm": 0.23074735701084137,
+      "learning_rate": 4.066757918485886e-06,
+      "loss": 0.0069,
+      "step": 257
+    },
+    {
+      "epoch": 3.3096774193548386,
+      "grad_norm": 0.20934291183948517,
+      "learning_rate": 3.913098221138237e-06,
+      "loss": 0.0088,
+      "step": 258
+    },
+    {
+      "epoch": 3.3225806451612905,
+      "grad_norm": 0.2551226019859314,
+      "learning_rate": 3.762150890011387e-06,
+      "loss": 0.0104,
+      "step": 259
+    },
+    {
+      "epoch": 3.335483870967742,
+      "grad_norm": 0.22543351352214813,
+      "learning_rate": 3.6139353411602154e-06,
+      "loss": 0.009,
+      "step": 260
+    },
+    {
+      "epoch": 3.3483870967741938,
+      "grad_norm": 0.22513934969902039,
+      "learning_rate": 3.468470639255872e-06,
+      "loss": 0.0103,
+      "step": 261
+    },
+    {
+      "epoch": 3.361290322580645,
+      "grad_norm": 0.23426640033721924,
+      "learning_rate": 3.325775495133546e-06,
+      "loss": 0.0086,
+      "step": 262
+    },
+    {
+      "epoch": 3.3741935483870966,
+      "grad_norm": 0.17604398727416992,
+      "learning_rate": 3.1858682633857105e-06,
+      "loss": 0.0118,
+      "step": 263
+    },
+    {
+      "epoch": 3.3870967741935485,
+      "grad_norm": 0.22662527859210968,
+      "learning_rate": 3.0487669400012382e-06,
+      "loss": 0.0089,
+      "step": 264
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.1959221363067627,
+      "learning_rate": 2.914489160050554e-06,
+      "loss": 0.0101,
+      "step": 265
+    },
+    {
+      "epoch": 3.412903225806452,
+      "grad_norm": 0.20400796830654144,
+      "learning_rate": 2.7830521954173543e-06,
+      "loss": 0.0088,
+      "step": 266
+    },
+    {
+      "epoch": 3.425806451612903,
+      "grad_norm": 0.21109241247177124,
+      "learning_rate": 2.654472952576864e-06,
+      "loss": 0.0083,
+      "step": 267
+    },
+    {
+      "epoch": 3.4387096774193546,
+      "grad_norm": 0.20984111726284027,
+      "learning_rate": 2.5287679704212836e-06,
+      "loss": 0.0091,
+      "step": 268
+    },
+    {
+      "epoch": 3.4516129032258065,
+      "grad_norm": 0.22513136267662048,
+      "learning_rate": 2.4059534181323588e-06,
+      "loss": 0.0102,
+      "step": 269
+    },
+    {
+      "epoch": 3.464516129032258,
+      "grad_norm": 0.23501525819301605,
+      "learning_rate": 2.2860450931015853e-06,
+      "loss": 0.0095,
+      "step": 270
+    },
+    {
+      "epoch": 3.47741935483871,
+      "grad_norm": 0.19732145965099335,
+      "learning_rate": 2.1690584188982592e-06,
+      "loss": 0.0087,
+      "step": 271
+    },
+    {
+      "epoch": 3.490322580645161,
+      "grad_norm": 0.19582946598529816,
+      "learning_rate": 2.0550084432855056e-06,
+      "loss": 0.0074,
+      "step": 272
+    },
+    {
+      "epoch": 3.5032258064516126,
+      "grad_norm": 0.19379809498786926,
+      "learning_rate": 1.9439098362847825e-06,
+      "loss": 0.008,
+      "step": 273
+    },
+    {
+      "epoch": 3.5161290322580645,
+      "grad_norm": 0.20334380865097046,
+      "learning_rate": 1.835776888288851e-06,
+      "loss": 0.0104,
+      "step": 274
+    },
+    {
+      "epoch": 3.5290322580645164,
+      "grad_norm": 0.1963813155889511,
+      "learning_rate": 1.730623508223686e-06,
+      "loss": 0.0114,
+      "step": 275
+    },
+    {
+      "epoch": 3.541935483870968,
+      "grad_norm": 0.2684271037578583,
+      "learning_rate": 1.62846322175933e-06,
+      "loss": 0.0106,
+      "step": 276
+    },
+    {
+      "epoch": 3.554838709677419,
+      "grad_norm": 0.19259046018123627,
+      "learning_rate": 1.5293091695701839e-06,
+      "loss": 0.0083,
+      "step": 277
+    },
+    {
+      "epoch": 3.567741935483871,
+      "grad_norm": 0.19738364219665527,
+      "learning_rate": 1.4331741056446968e-06,
+      "loss": 0.0166,
+      "step": 278
+    },
+    {
+      "epoch": 3.5806451612903225,
+      "grad_norm": 0.22224943339824677,
+      "learning_rate": 1.3400703956448684e-06,
+      "loss": 0.0074,
+      "step": 279
+    },
+    {
+      "epoch": 3.5935483870967744,
+      "grad_norm": 0.23735593259334564,
+      "learning_rate": 1.2500100153156779e-06,
+      "loss": 0.0091,
+      "step": 280
+    },
+    {
+      "epoch": 3.606451612903226,
+      "grad_norm": 0.1716444343328476,
+      "learning_rate": 1.1630045489446572e-06,
+      "loss": 0.0078,
+      "step": 281
+    },
+    {
+      "epoch": 3.6193548387096772,
+      "grad_norm": 0.1820307821035385,
+      "learning_rate": 1.079065187871839e-06,
+      "loss": 0.009,
+      "step": 282
+    },
+    {
+      "epoch": 3.632258064516129,
+      "grad_norm": 0.1972561627626419,
+      "learning_rate": 9.982027290502238e-07,
+      "loss": 0.0122,
+      "step": 283
+    },
+    {
+      "epoch": 3.6451612903225805,
+      "grad_norm": 0.21676687896251678,
+      "learning_rate": 9.204275736570151e-07,
+      "loss": 0.0082,
+      "step": 284
+    },
+    {
+      "epoch": 3.6580645161290324,
+      "grad_norm": 0.1852135956287384,
+      "learning_rate": 8.45749725755704e-07,
+      "loss": 0.0078,
+      "step": 285
+    },
+    {
+      "epoch": 3.670967741935484,
+      "grad_norm": 0.15526923537254333,
+      "learning_rate": 7.741787910092807e-07,
+      "loss": 0.0058,
+      "step": 286
+    },
+    {
+      "epoch": 3.6838709677419352,
+      "grad_norm": 0.25308313965797424,
+      "learning_rate": 7.05723975444686e-07,
+      "loss": 0.0072,
+      "step": 287
+    },
+    {
+      "epoch": 3.696774193548387,
+      "grad_norm": 0.16028578579425812,
+      "learning_rate": 6.403940842686474e-07,
+      "loss": 0.0086,
+      "step": 288
+    },
+    {
+      "epoch": 3.709677419354839,
+      "grad_norm": 0.164954274892807,
+      "learning_rate": 5.781975207350826e-07,
+      "loss": 0.0074,
+      "step": 289
+    },
+    {
+      "epoch": 3.7225806451612904,
+      "grad_norm": 0.21616578102111816,
+      "learning_rate": 5.191422850642113e-07,
+      "loss": 0.0111,
+      "step": 290
+    },
+    {
+      "epoch": 3.735483870967742,
+      "grad_norm": 0.23164188861846924,
+      "learning_rate": 4.6323597341350054e-07,
+      "loss": 0.0093,
+      "step": 291
+    },
+    {
+      "epoch": 3.7483870967741937,
+      "grad_norm": 0.2091163843870163,
+      "learning_rate": 4.1048577690058766e-07,
+      "loss": 0.008,
+      "step": 292
+    },
+    {
+      "epoch": 3.761290322580645,
+      "grad_norm": 0.17184507846832275,
+      "learning_rate": 3.608984806782928e-07,
+      "loss": 0.0089,
+      "step": 293
+    },
+    {
+      "epoch": 3.774193548387097,
+      "grad_norm": 0.2208150029182434,
+      "learning_rate": 3.144804630618725e-07,
+      "loss": 0.0098,
+      "step": 294
+    },
+    {
+      "epoch": 3.7870967741935484,
+      "grad_norm": 0.18591627478599548,
+      "learning_rate": 2.71237694708576e-07,
+      "loss": 0.0091,
+      "step": 295
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.22179189324378967,
+      "learning_rate": 2.3117573784966206e-07,
+      "loss": 0.0096,
+      "step": 296
+    },
+    {
+      "epoch": 3.8129032258064517,
+      "grad_norm": 0.247935950756073,
+      "learning_rate": 1.9429974557493014e-07,
+      "loss": 0.0075,
+      "step": 297
+    },
+    {
+      "epoch": 3.825806451612903,
+      "grad_norm": 0.19308875501155853,
+      "learning_rate": 1.6061446116990008e-07,
+      "loss": 0.0097,
+      "step": 298
+    },
+    {
+      "epoch": 3.838709677419355,
+      "grad_norm": 0.28245624899864197,
+      "learning_rate": 1.3012421750568105e-07,
+      "loss": 0.0105,
+      "step": 299
+    },
+    {
+      "epoch": 3.8516129032258064,
+      "grad_norm": 0.15781083703041077,
+      "learning_rate": 1.0283293648165605e-07,
+      "loss": 0.0087,
+      "step": 300
+    },
+    {
+      "epoch": 3.864516129032258,
+      "grad_norm": 0.20132358372211456,
+      "learning_rate": 7.874412852099944e-08,
+      "loss": 0.0081,
+      "step": 301
+    },
+    {
+      "epoch": 3.8774193548387097,
+      "grad_norm": 0.19697970151901245,
+      "learning_rate": 5.786089211915202e-08,
+      "loss": 0.0116,
+      "step": 302
+    },
+    {
+      "epoch": 3.8903225806451616,
+      "grad_norm": 0.189448282122612,
+      "learning_rate": 4.018591344526479e-08,
+      "loss": 0.0079,
+      "step": 303
+    },
+    {
+      "epoch": 3.903225806451613,
+      "grad_norm": 0.1814439296722412,
+      "learning_rate": 2.5721465996675355e-08,
+      "loss": 0.0061,
+      "step": 304
+    },
+    {
+      "epoch": 3.9161290322580644,
+      "grad_norm": 0.17018909752368927,
+      "learning_rate": 1.4469410306480746e-08,
+      "loss": 0.0074,
+      "step": 305
+    },
+    {
+      "epoch": 3.9290322580645163,
+      "grad_norm": 0.2005801647901535,
+      "learning_rate": 6.431193704217741e-09,
+      "loss": 0.0084,
+      "step": 306
+    },
+    {
+      "epoch": 3.9419354838709677,
+      "grad_norm": 0.2100239396095276,
+      "learning_rate": 1.6078501296951099e-09,
+      "loss": 0.0118,
+      "step": 307
+    },
+    {
+      "epoch": 3.9548387096774196,
+      "grad_norm": 0.17311210930347443,
+      "learning_rate": 0.0,
+      "loss": 0.0059,
+      "step": 308
+    },
+    {
+      "epoch": 3.9548387096774196,
+      "step": 308,
+      "total_flos": 5.413829559357276e+17,
+      "train_loss": 0.04737277891541311,
+      "train_runtime": 1301.7465,
+      "train_samples_per_second": 15.216,
+      "train_steps_per_second": 0.237
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 308,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.413829559357276e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0147f65520966842111e240eb7cb47fc0b022edde5bf3438859211cda77392
+size 7352