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": 2.985259891388673,
+    "total_flos": 6.175913846901834e+18,
+    "train_loss": 0.0,
+    "train_runtime": 7.3353,
+    "train_samples_per_second": 16865.155,
+    "train_steps_per_second": 32.718
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/eguha/models_cache/Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb5c616d43d3edec9400b16a474b480ddc7159bc9cb492766d732828048c316
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fffc70a5b73267d3e5aaa7d1e971e2a4e1032a3579e144c2d1e16913a7a62de9
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f9798f58e2585345dfd5ee8bf97d74a0537da43f593d6328eb81649f426d37
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72046c53eb76364845d9a0e4f3b8f35c0b7800b5a86d58ee5c49fc2189a2ebb6
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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 +1,208 @@
+{
+  "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 Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.985259891388673,
+    "total_flos": 6.175913846901834e+18,
+    "train_loss": 0.0,
+    "train_runtime": 7.3353,
+    "train_samples_per_second": 16865.155,
+    "train_steps_per_second": 32.718
+}

trainer_log.jsonl

@@ -0,0 +1,246 @@
+{"current_steps": 1, "total_steps": 240, "loss": 0.8592, "lr": 3.3333333333333333e-06, "epoch": 0.012412723041117145, "percentage": 0.42, "elapsed_time": "0:04:04", "remaining_time": "16:13:27"}
+{"current_steps": 2, "total_steps": 240, "loss": 0.8708, "lr": 6.666666666666667e-06, "epoch": 0.02482544608223429, "percentage": 0.83, "elapsed_time": "0:07:28", "remaining_time": "14:50:13"}
+{"current_steps": 3, "total_steps": 240, "loss": 0.8418, "lr": 1e-05, "epoch": 0.037238169123351435, "percentage": 1.25, "elapsed_time": "0:10:53", "remaining_time": "14:20:04"}
+{"current_steps": 4, "total_steps": 240, "loss": 0.7757, "lr": 1.3333333333333333e-05, "epoch": 0.04965089216446858, "percentage": 1.67, "elapsed_time": "0:14:17", "remaining_time": "14:03:33"}
+{"current_steps": 5, "total_steps": 240, "loss": 0.802, "lr": 1.6666666666666667e-05, "epoch": 0.062063615205585725, "percentage": 2.08, "elapsed_time": "0:17:43", "remaining_time": "13:52:52"}
+{"current_steps": 6, "total_steps": 240, "loss": 0.7535, "lr": 2e-05, "epoch": 0.07447633824670287, "percentage": 2.5, "elapsed_time": "0:21:07", "remaining_time": "13:44:08"}
+{"current_steps": 7, "total_steps": 240, "loss": 0.7712, "lr": 2.3333333333333336e-05, "epoch": 0.08688906128782002, "percentage": 2.92, "elapsed_time": "0:24:31", "remaining_time": "13:36:27"}
+{"current_steps": 8, "total_steps": 240, "loss": 0.7177, "lr": 2.6666666666666667e-05, "epoch": 0.09930178432893716, "percentage": 3.33, "elapsed_time": "0:27:56", "remaining_time": "13:30:17"}
+{"current_steps": 9, "total_steps": 240, "loss": 0.6858, "lr": 3.0000000000000004e-05, "epoch": 0.11171450737005431, "percentage": 3.75, "elapsed_time": "0:31:20", "remaining_time": "13:24:37"}
+{"current_steps": 10, "total_steps": 240, "loss": 0.6676, "lr": 3.3333333333333335e-05, "epoch": 0.12412723041117145, "percentage": 4.17, "elapsed_time": "0:34:44", "remaining_time": "13:19:11"}
+{"current_steps": 11, "total_steps": 240, "loss": 0.6418, "lr": 3.6666666666666666e-05, "epoch": 0.1365399534522886, "percentage": 4.58, "elapsed_time": "0:38:09", "remaining_time": "13:14:22"}
+{"current_steps": 12, "total_steps": 240, "loss": 0.6335, "lr": 4e-05, "epoch": 0.14895267649340574, "percentage": 5.0, "elapsed_time": "0:41:33", "remaining_time": "13:09:36"}
+{"current_steps": 13, "total_steps": 240, "loss": 0.6212, "lr": 4.3333333333333334e-05, "epoch": 0.1613653995345229, "percentage": 5.42, "elapsed_time": "0:44:57", "remaining_time": "13:05:09"}
+{"current_steps": 14, "total_steps": 240, "loss": 0.6196, "lr": 4.666666666666667e-05, "epoch": 0.17377812257564004, "percentage": 5.83, "elapsed_time": "0:48:22", "remaining_time": "13:00:49"}
+{"current_steps": 15, "total_steps": 240, "loss": 0.6099, "lr": 5e-05, "epoch": 0.18619084561675717, "percentage": 6.25, "elapsed_time": "0:51:46", "remaining_time": "12:56:44"}
+{"current_steps": 16, "total_steps": 240, "loss": 0.5928, "lr": 5.333333333333333e-05, "epoch": 0.19860356865787432, "percentage": 6.67, "elapsed_time": "0:55:11", "remaining_time": "12:52:39"}
+{"current_steps": 17, "total_steps": 240, "loss": 0.5895, "lr": 5.666666666666668e-05, "epoch": 0.21101629169899147, "percentage": 7.08, "elapsed_time": "0:58:36", "remaining_time": "12:48:54"}
+{"current_steps": 18, "total_steps": 240, "loss": 0.5829, "lr": 6.000000000000001e-05, "epoch": 0.22342901474010862, "percentage": 7.5, "elapsed_time": "1:02:01", "remaining_time": "12:45:04"}
+{"current_steps": 19, "total_steps": 240, "loss": 0.5849, "lr": 6.333333333333333e-05, "epoch": 0.23584173778122575, "percentage": 7.92, "elapsed_time": "1:05:27", "remaining_time": "12:41:20"}
+{"current_steps": 20, "total_steps": 240, "loss": 0.5754, "lr": 6.666666666666667e-05, "epoch": 0.2482544608223429, "percentage": 8.33, "elapsed_time": "1:08:51", "remaining_time": "12:37:30"}
+{"current_steps": 21, "total_steps": 240, "loss": 0.5782, "lr": 7.000000000000001e-05, "epoch": 0.26066718386346005, "percentage": 8.75, "elapsed_time": "1:12:17", "remaining_time": "12:33:57"}
+{"current_steps": 22, "total_steps": 240, "loss": 0.572, "lr": 7.333333333333333e-05, "epoch": 0.2730799069045772, "percentage": 9.17, "elapsed_time": "1:15:42", "remaining_time": "12:30:15"}
+{"current_steps": 23, "total_steps": 240, "loss": 0.5689, "lr": 7.666666666666668e-05, "epoch": 0.28549262994569435, "percentage": 9.58, "elapsed_time": "1:19:06", "remaining_time": "12:26:18"}
+{"current_steps": 24, "total_steps": 240, "loss": 0.5669, "lr": 8e-05, "epoch": 0.2979053529868115, "percentage": 10.0, "elapsed_time": "1:22:29", "remaining_time": "12:22:24"}
+{"current_steps": 25, "total_steps": 240, "loss": 0.5587, "lr": 7.99957692770843e-05, "epoch": 0.3103180760279286, "percentage": 10.42, "elapsed_time": "1:25:52", "remaining_time": "12:18:30"}
+{"current_steps": 26, "total_steps": 240, "loss": 0.5598, "lr": 7.998307800328803e-05, "epoch": 0.3227307990690458, "percentage": 10.83, "elapsed_time": "1:29:15", "remaining_time": "12:14:40"}
+{"current_steps": 27, "total_steps": 240, "loss": 0.5573, "lr": 7.996192886327432e-05, "epoch": 0.3351435221101629, "percentage": 11.25, "elapsed_time": "1:32:39", "remaining_time": "12:10:59"}
+{"current_steps": 28, "total_steps": 240, "loss": 0.5454, "lr": 7.993232633085074e-05, "epoch": 0.3475562451512801, "percentage": 11.67, "elapsed_time": "1:36:01", "remaining_time": "12:07:05"}
+{"current_steps": 29, "total_steps": 240, "loss": 0.5484, "lr": 7.98942766680229e-05, "epoch": 0.3599689681923972, "percentage": 12.08, "elapsed_time": "1:39:24", "remaining_time": "12:03:19"}
+{"current_steps": 30, "total_steps": 240, "loss": 0.5672, "lr": 7.984778792366983e-05, "epoch": 0.37238169123351433, "percentage": 12.5, "elapsed_time": "1:42:48", "remaining_time": "11:59:40"}
+{"current_steps": 31, "total_steps": 240, "loss": 0.5554, "lr": 7.979286993184134e-05, "epoch": 0.3847944142746315, "percentage": 12.92, "elapsed_time": "1:46:11", "remaining_time": "11:55:58"}
+{"current_steps": 32, "total_steps": 240, "loss": 0.552, "lr": 7.972953430967773e-05, "epoch": 0.39720713731574864, "percentage": 13.33, "elapsed_time": "1:49:35", "remaining_time": "11:52:21"}
+{"current_steps": 33, "total_steps": 240, "loss": 0.5647, "lr": 7.965779445495243e-05, "epoch": 0.40961986035686576, "percentage": 13.75, "elapsed_time": "1:52:59", "remaining_time": "11:48:45"}
+{"current_steps": 34, "total_steps": 240, "loss": 0.538, "lr": 7.957766554323778e-05, "epoch": 0.42203258339798294, "percentage": 14.17, "elapsed_time": "1:56:23", "remaining_time": "11:45:11"}
+{"current_steps": 35, "total_steps": 240, "loss": 0.5462, "lr": 7.948916452469497e-05, "epoch": 0.43444530643910007, "percentage": 14.58, "elapsed_time": "1:59:47", "remaining_time": "11:41:40"}
+{"current_steps": 36, "total_steps": 240, "loss": 0.5416, "lr": 7.939231012048833e-05, "epoch": 0.44685802948021724, "percentage": 15.0, "elapsed_time": "2:03:10", "remaining_time": "11:38:01"}
+{"current_steps": 37, "total_steps": 240, "loss": 0.5261, "lr": 7.928712281882523e-05, "epoch": 0.45927075252133437, "percentage": 15.42, "elapsed_time": "2:06:34", "remaining_time": "11:34:25"}
+{"current_steps": 38, "total_steps": 240, "loss": 0.5327, "lr": 7.917362487062207e-05, "epoch": 0.4716834755624515, "percentage": 15.83, "elapsed_time": "2:09:57", "remaining_time": "11:30:47"}
+{"current_steps": 39, "total_steps": 240, "loss": 0.5203, "lr": 7.905184028479734e-05, "epoch": 0.4840961986035687, "percentage": 16.25, "elapsed_time": "2:13:20", "remaining_time": "11:27:15"}
+{"current_steps": 40, "total_steps": 240, "loss": 0.5276, "lr": 7.892179482319297e-05, "epoch": 0.4965089216446858, "percentage": 16.67, "elapsed_time": "2:16:44", "remaining_time": "11:23:41"}
+{"current_steps": 41, "total_steps": 240, "loss": 0.5186, "lr": 7.878351599512465e-05, "epoch": 0.5089216446858029, "percentage": 17.08, "elapsed_time": "2:20:06", "remaining_time": "11:20:03"}
+{"current_steps": 42, "total_steps": 240, "loss": 0.519, "lr": 7.863703305156273e-05, "epoch": 0.5213343677269201, "percentage": 17.5, "elapsed_time": "2:23:30", "remaining_time": "11:16:30"}
+{"current_steps": 43, "total_steps": 240, "loss": 0.5039, "lr": 7.848237697894453e-05, "epoch": 0.5337470907680373, "percentage": 17.92, "elapsed_time": "2:26:52", "remaining_time": "11:12:55"}
+{"current_steps": 44, "total_steps": 240, "loss": 0.5086, "lr": 7.831958049261956e-05, "epoch": 0.5461598138091543, "percentage": 18.33, "elapsed_time": "2:30:15", "remaining_time": "11:09:19"}
+{"current_steps": 45, "total_steps": 240, "loss": 0.5191, "lr": 7.814867802992907e-05, "epoch": 0.5585725368502715, "percentage": 18.75, "elapsed_time": "2:33:38", "remaining_time": "11:05:45"}
+{"current_steps": 46, "total_steps": 240, "loss": 0.5114, "lr": 7.796970574292136e-05, "epoch": 0.5709852598913887, "percentage": 19.17, "elapsed_time": "2:37:01", "remaining_time": "11:02:13"}
+{"current_steps": 47, "total_steps": 240, "loss": 0.5072, "lr": 7.77827014907042e-05, "epoch": 0.5833979829325058, "percentage": 19.58, "elapsed_time": "2:40:24", "remaining_time": "10:58:40"}
+{"current_steps": 48, "total_steps": 240, "loss": 0.5128, "lr": 7.758770483143634e-05, "epoch": 0.595810705973623, "percentage": 20.0, "elapsed_time": "2:43:47", "remaining_time": "10:55:08"}
+{"current_steps": 49, "total_steps": 240, "loss": 0.5202, "lr": 7.738475701395955e-05, "epoch": 0.6082234290147401, "percentage": 20.42, "elapsed_time": "2:47:09", "remaining_time": "10:51:33"}
+{"current_steps": 50, "total_steps": 240, "loss": 0.5018, "lr": 7.71739009690729e-05, "epoch": 0.6206361520558572, "percentage": 20.83, "elapsed_time": "2:50:32", "remaining_time": "10:48:04"}
+{"current_steps": 51, "total_steps": 240, "loss": 0.5131, "lr": 7.695518130045147e-05, "epoch": 0.6330488750969744, "percentage": 21.25, "elapsed_time": "2:53:55", "remaining_time": "10:44:33"}
+{"current_steps": 52, "total_steps": 240, "loss": 0.5053, "lr": 7.672864427521097e-05, "epoch": 0.6454615981380916, "percentage": 21.67, "elapsed_time": "2:57:18", "remaining_time": "10:41:03"}
+{"current_steps": 53, "total_steps": 240, "loss": 0.5064, "lr": 7.649433781412058e-05, "epoch": 0.6578743211792087, "percentage": 22.08, "elapsed_time": "3:00:42", "remaining_time": "10:37:35"}
+{"current_steps": 54, "total_steps": 240, "loss": 0.5074, "lr": 7.625231148146601e-05, "epoch": 0.6702870442203258, "percentage": 22.5, "elapsed_time": "3:04:05", "remaining_time": "10:34:04"}
+{"current_steps": 55, "total_steps": 240, "loss": 0.4996, "lr": 7.600261647456485e-05, "epoch": 0.682699767261443, "percentage": 22.92, "elapsed_time": "3:07:28", "remaining_time": "10:30:37"}
+{"current_steps": 56, "total_steps": 240, "loss": 0.5026, "lr": 7.57453056129365e-05, "epoch": 0.6951124903025602, "percentage": 23.33, "elapsed_time": "3:10:52", "remaining_time": "10:27:10"}
+{"current_steps": 57, "total_steps": 240, "loss": 0.5007, "lr": 7.548043332712887e-05, "epoch": 0.7075252133436772, "percentage": 23.75, "elapsed_time": "3:14:15", "remaining_time": "10:23:41"}
+{"current_steps": 58, "total_steps": 240, "loss": 0.5065, "lr": 7.520805564720444e-05, "epoch": 0.7199379363847944, "percentage": 24.17, "elapsed_time": "3:17:38", "remaining_time": "10:20:12"}
+{"current_steps": 59, "total_steps": 240, "loss": 0.4885, "lr": 7.492823019088785e-05, "epoch": 0.7323506594259116, "percentage": 24.58, "elapsed_time": "3:21:02", "remaining_time": "10:16:44"}
+{"current_steps": 60, "total_steps": 240, "loss": 0.5019, "lr": 7.464101615137756e-05, "epoch": 0.7447633824670287, "percentage": 25.0, "elapsed_time": "3:24:25", "remaining_time": "10:13:17"}
+{"current_steps": 61, "total_steps": 240, "loss": 0.5014, "lr": 7.434647428482453e-05, "epoch": 0.7571761055081458, "percentage": 25.42, "elapsed_time": "3:27:49", "remaining_time": "10:09:50"}
+{"current_steps": 62, "total_steps": 240, "loss": 0.4908, "lr": 7.404466689747999e-05, "epoch": 0.769588828549263, "percentage": 25.83, "elapsed_time": "3:31:11", "remaining_time": "10:06:20"}
+{"current_steps": 63, "total_steps": 240, "loss": 0.507, "lr": 7.373565783251544e-05, "epoch": 0.7820015515903801, "percentage": 26.25, "elapsed_time": "3:34:34", "remaining_time": "10:02:52"}
+{"current_steps": 64, "total_steps": 240, "loss": 0.4977, "lr": 7.341951245651747e-05, "epoch": 0.7944142746314973, "percentage": 26.67, "elapsed_time": "3:37:57", "remaining_time": "9:59:21"}
+{"current_steps": 65, "total_steps": 240, "loss": 0.4961, "lr": 7.309629764566042e-05, "epoch": 0.8068269976726145, "percentage": 27.08, "elapsed_time": "3:41:20", "remaining_time": "9:55:54"}
+{"current_steps": 66, "total_steps": 240, "loss": 0.4892, "lr": 7.276608177155968e-05, "epoch": 0.8192397207137315, "percentage": 27.5, "elapsed_time": "3:44:42", "remaining_time": "9:52:25"}
+{"current_steps": 67, "total_steps": 240, "loss": 0.5048, "lr": 7.242893468680849e-05, "epoch": 0.8316524437548487, "percentage": 27.92, "elapsed_time": "3:48:04", "remaining_time": "9:48:55"}
+{"current_steps": 68, "total_steps": 240, "loss": 0.4901, "lr": 7.208492771020176e-05, "epoch": 0.8440651667959659, "percentage": 28.33, "elapsed_time": "3:51:26", "remaining_time": "9:45:25"}
+{"current_steps": 69, "total_steps": 240, "loss": 0.4885, "lr": 7.173413361164941e-05, "epoch": 0.8564778898370831, "percentage": 28.75, "elapsed_time": "3:54:48", "remaining_time": "9:41:54"}
+{"current_steps": 70, "total_steps": 240, "loss": 0.4929, "lr": 7.137662659678303e-05, "epoch": 0.8688906128782001, "percentage": 29.17, "elapsed_time": "3:58:10", "remaining_time": "9:38:26"}
+{"current_steps": 71, "total_steps": 240, "loss": 0.4925, "lr": 7.101248229125864e-05, "epoch": 0.8813033359193173, "percentage": 29.58, "elapsed_time": "4:01:34", "remaining_time": "9:35:01"}
+{"current_steps": 72, "total_steps": 240, "loss": 0.4787, "lr": 7.064177772475912e-05, "epoch": 0.8937160589604345, "percentage": 30.0, "elapsed_time": "4:04:58", "remaining_time": "9:31:37"}
+{"current_steps": 73, "total_steps": 240, "loss": 0.4858, "lr": 7.026459131469972e-05, "epoch": 0.9061287820015516, "percentage": 30.42, "elapsed_time": "4:08:23", "remaining_time": "9:28:13"}
+{"current_steps": 74, "total_steps": 240, "loss": 0.4928, "lr": 6.988100284963985e-05, "epoch": 0.9185415050426687, "percentage": 30.83, "elapsed_time": "4:11:46", "remaining_time": "9:24:48"}
+{"current_steps": 75, "total_steps": 240, "loss": 0.4859, "lr": 6.949109347240496e-05, "epoch": 0.9309542280837859, "percentage": 31.25, "elapsed_time": "4:15:10", "remaining_time": "9:21:23"}
+{"current_steps": 76, "total_steps": 240, "loss": 0.4901, "lr": 6.909494566292195e-05, "epoch": 0.943366951124903, "percentage": 31.67, "elapsed_time": "4:18:34", "remaining_time": "9:17:59"}
+{"current_steps": 77, "total_steps": 240, "loss": 0.4726, "lr": 6.869264322077158e-05, "epoch": 0.9557796741660202, "percentage": 32.08, "elapsed_time": "4:21:59", "remaining_time": "9:14:35"}
+{"current_steps": 78, "total_steps": 240, "loss": 0.4942, "lr": 6.828427124746191e-05, "epoch": 0.9681923972071373, "percentage": 32.5, "elapsed_time": "4:25:23", "remaining_time": "9:11:11"}
+{"current_steps": 79, "total_steps": 240, "loss": 0.4802, "lr": 6.786991612842621e-05, "epoch": 0.9806051202482544, "percentage": 32.92, "elapsed_time": "4:28:47", "remaining_time": "9:07:47"}
+{"current_steps": 80, "total_steps": 240, "loss": 0.4928, "lr": 6.744966551474936e-05, "epoch": 0.9930178432893716, "percentage": 33.33, "elapsed_time": "4:32:11", "remaining_time": "9:04:22"}
+{"current_steps": 81, "total_steps": 240, "loss": 0.4722, "lr": 6.702360830462642e-05, "epoch": 1.008533747090768, "percentage": 33.75, "elapsed_time": "4:36:36", "remaining_time": "9:02:58"}
+{"current_steps": 82, "total_steps": 240, "loss": 0.4648, "lr": 6.659183462455751e-05, "epoch": 1.020946470131885, "percentage": 34.17, "elapsed_time": "4:40:01", "remaining_time": "8:59:33"}
+{"current_steps": 83, "total_steps": 240, "loss": 0.4668, "lr": 6.615443581028279e-05, "epoch": 1.0333591931730024, "percentage": 34.58, "elapsed_time": "4:43:26", "remaining_time": "8:56:08"}
+{"current_steps": 84, "total_steps": 240, "loss": 0.457, "lr": 6.571150438746157e-05, "epoch": 1.0457719162141195, "percentage": 35.0, "elapsed_time": "4:46:50", "remaining_time": "8:52:41"}
+{"current_steps": 85, "total_steps": 240, "loss": 0.4669, "lr": 6.526313405209991e-05, "epoch": 1.0581846392552365, "percentage": 35.42, "elapsed_time": "4:50:14", "remaining_time": "8:49:15"}
+{"current_steps": 86, "total_steps": 240, "loss": 0.4537, "lr": 6.480941965073041e-05, "epoch": 1.0705973622963538, "percentage": 35.83, "elapsed_time": "4:53:38", "remaining_time": "8:45:49"}
+{"current_steps": 87, "total_steps": 240, "loss": 0.4544, "lr": 6.435045716034883e-05, "epoch": 1.083010085337471, "percentage": 36.25, "elapsed_time": "4:57:02", "remaining_time": "8:42:22"}
+{"current_steps": 88, "total_steps": 240, "loss": 0.455, "lr": 6.388634366811146e-05, "epoch": 1.095422808378588, "percentage": 36.67, "elapsed_time": "5:00:27", "remaining_time": "8:38:57"}
+{"current_steps": 89, "total_steps": 240, "loss": 0.4664, "lr": 6.341717735079763e-05, "epoch": 1.1078355314197053, "percentage": 37.08, "elapsed_time": "5:03:51", "remaining_time": "8:35:31"}
+{"current_steps": 90, "total_steps": 240, "loss": 0.4495, "lr": 6.294305745404185e-05, "epoch": 1.1202482544608223, "percentage": 37.5, "elapsed_time": "5:07:15", "remaining_time": "8:32:05"}
+{"current_steps": 91, "total_steps": 240, "loss": 0.4641, "lr": 6.246408427133972e-05, "epoch": 1.1326609775019394, "percentage": 37.92, "elapsed_time": "5:10:39", "remaining_time": "8:28:39"}
+{"current_steps": 92, "total_steps": 240, "loss": 0.4616, "lr": 6.198035912283225e-05, "epoch": 1.1450737005430567, "percentage": 38.33, "elapsed_time": "5:14:03", "remaining_time": "8:25:13"}
+{"current_steps": 93, "total_steps": 240, "loss": 0.4571, "lr": 6.149198433387297e-05, "epoch": 1.1574864235841738, "percentage": 38.75, "elapsed_time": "5:17:28", "remaining_time": "8:21:48"}
+{"current_steps": 94, "total_steps": 240, "loss": 0.4601, "lr": 6.099906321338241e-05, "epoch": 1.169899146625291, "percentage": 39.17, "elapsed_time": "5:20:52", "remaining_time": "8:18:22"}
+{"current_steps": 95, "total_steps": 240, "loss": 0.4469, "lr": 6.0501700031994613e-05, "epoch": 1.182311869666408, "percentage": 39.58, "elapsed_time": "5:24:15", "remaining_time": "8:14:55"}
+{"current_steps": 96, "total_steps": 240, "loss": 0.4474, "lr": 6.000000000000001e-05, "epoch": 1.1947245927075252, "percentage": 40.0, "elapsed_time": "5:27:40", "remaining_time": "8:11:30"}
+{"current_steps": 97, "total_steps": 240, "loss": 0.4513, "lr": 5.94940692450897e-05, "epoch": 1.2071373157486422, "percentage": 40.42, "elapsed_time": "5:31:04", "remaining_time": "8:08:04"}
+{"current_steps": 98, "total_steps": 240, "loss": 0.4516, "lr": 5.8984014789905625e-05, "epoch": 1.2195500387897595, "percentage": 40.83, "elapsed_time": "5:34:28", "remaining_time": "8:04:38"}
+{"current_steps": 99, "total_steps": 240, "loss": 0.4493, "lr": 5.846994452940137e-05, "epoch": 1.2319627618308766, "percentage": 41.25, "elapsed_time": "5:37:52", "remaining_time": "8:01:12"}
+{"current_steps": 100, "total_steps": 240, "loss": 0.451, "lr": 5.79519672080185e-05, "epoch": 1.244375484871994, "percentage": 41.67, "elapsed_time": "5:41:16", "remaining_time": "7:57:46"}
+{"current_steps": 101, "total_steps": 240, "loss": 0.4494, "lr": 5.743019239668318e-05, "epoch": 1.256788207913111, "percentage": 42.08, "elapsed_time": "5:44:41", "remaining_time": "7:54:22"}
+{"current_steps": 102, "total_steps": 240, "loss": 0.4541, "lr": 5.6904730469627985e-05, "epoch": 1.269200930954228, "percentage": 42.5, "elapsed_time": "5:48:06", "remaining_time": "7:50:58"}
+{"current_steps": 103, "total_steps": 240, "loss": 0.439, "lr": 5.6375692581043705e-05, "epoch": 1.281613653995345, "percentage": 42.92, "elapsed_time": "5:51:30", "remaining_time": "7:47:32"}
+{"current_steps": 104, "total_steps": 240, "loss": 0.4516, "lr": 5.584319064156628e-05, "epoch": 1.2940263770364624, "percentage": 43.33, "elapsed_time": "5:54:54", "remaining_time": "7:44:06"}
+{"current_steps": 105, "total_steps": 240, "loss": 0.4372, "lr": 5.5307337294603595e-05, "epoch": 1.3064391000775795, "percentage": 43.75, "elapsed_time": "5:58:18", "remaining_time": "7:40:40"}
+{"current_steps": 106, "total_steps": 240, "loss": 0.4428, "lr": 5.476824589250738e-05, "epoch": 1.3188518231186968, "percentage": 44.17, "elapsed_time": "6:01:42", "remaining_time": "7:37:15"}
+{"current_steps": 107, "total_steps": 240, "loss": 0.4479, "lr": 5.4226030472595075e-05, "epoch": 1.3312645461598138, "percentage": 44.58, "elapsed_time": "6:05:07", "remaining_time": "7:33:50"}
+{"current_steps": 108, "total_steps": 240, "loss": 0.4544, "lr": 5.368080573302676e-05, "epoch": 1.343677269200931, "percentage": 45.0, "elapsed_time": "6:08:31", "remaining_time": "7:30:25"}
+{"current_steps": 109, "total_steps": 240, "loss": 0.445, "lr": 5.3132687008542454e-05, "epoch": 1.3560899922420482, "percentage": 45.42, "elapsed_time": "6:11:56", "remaining_time": "7:27:00"}
+{"current_steps": 110, "total_steps": 240, "loss": 0.4482, "lr": 5.258179024606455e-05, "epoch": 1.3685027152831652, "percentage": 45.83, "elapsed_time": "6:15:20", "remaining_time": "7:23:34"}
+{"current_steps": 111, "total_steps": 240, "loss": 0.4417, "lr": 5.202823198017092e-05, "epoch": 1.3809154383242823, "percentage": 46.25, "elapsed_time": "6:18:44", "remaining_time": "7:20:09"}
+{"current_steps": 112, "total_steps": 240, "loss": 0.4381, "lr": 5.1472129308443616e-05, "epoch": 1.3933281613653996, "percentage": 46.67, "elapsed_time": "6:22:08", "remaining_time": "7:16:44"}
+{"current_steps": 113, "total_steps": 240, "loss": 0.4522, "lr": 5.091359986669845e-05, "epoch": 1.4057408844065167, "percentage": 47.08, "elapsed_time": "6:25:35", "remaining_time": "7:13:21"}
+{"current_steps": 114, "total_steps": 240, "loss": 0.4473, "lr": 5.0352761804100835e-05, "epoch": 1.4181536074476337, "percentage": 47.5, "elapsed_time": "6:28:59", "remaining_time": "7:09:56"}
+{"current_steps": 115, "total_steps": 240, "loss": 0.441, "lr": 4.9789733758172956e-05, "epoch": 1.430566330488751, "percentage": 47.92, "elapsed_time": "6:32:23", "remaining_time": "7:06:30"}
+{"current_steps": 116, "total_steps": 240, "loss": 0.4426, "lr": 4.922463482969761e-05, "epoch": 1.442979053529868, "percentage": 48.33, "elapsed_time": "6:35:46", "remaining_time": "7:03:04"}
+{"current_steps": 117, "total_steps": 240, "loss": 0.4417, "lr": 4.8657584557524116e-05, "epoch": 1.4553917765709854, "percentage": 48.75, "elapsed_time": "6:39:10", "remaining_time": "6:59:38"}
+{"current_steps": 118, "total_steps": 240, "loss": 0.4404, "lr": 4.808870289328153e-05, "epoch": 1.4678044996121025, "percentage": 49.17, "elapsed_time": "6:42:35", "remaining_time": "6:56:14"}
+{"current_steps": 119, "total_steps": 240, "loss": 0.4445, "lr": 4.751811017600448e-05, "epoch": 1.4802172226532195, "percentage": 49.58, "elapsed_time": "6:46:08", "remaining_time": "6:52:57"}
+{"current_steps": 120, "total_steps": 240, "loss": 0.4398, "lr": 4.694592710667723e-05, "epoch": 1.4926299456943366, "percentage": 50.0, "elapsed_time": "6:49:32", "remaining_time": "6:49:32"}
+{"current_steps": 121, "total_steps": 240, "loss": 0.4403, "lr": 4.637227472270091e-05, "epoch": 1.505042668735454, "percentage": 50.42, "elapsed_time": "6:52:56", "remaining_time": "6:46:06"}
+{"current_steps": 122, "total_steps": 240, "loss": 0.4398, "lr": 4.579727437228987e-05, "epoch": 1.517455391776571, "percentage": 50.83, "elapsed_time": "6:56:20", "remaining_time": "6:42:41"}
+{"current_steps": 123, "total_steps": 240, "loss": 0.4416, "lr": 4.522104768880208e-05, "epoch": 1.5298681148176883, "percentage": 51.25, "elapsed_time": "6:59:44", "remaining_time": "6:39:16"}
+{"current_steps": 124, "total_steps": 240, "loss": 0.4385, "lr": 4.464371656500921e-05, "epoch": 1.5422808378588053, "percentage": 51.67, "elapsed_time": "7:03:09", "remaining_time": "6:35:51"}
+{"current_steps": 125, "total_steps": 240, "loss": 0.4372, "lr": 4.406540312731208e-05, "epoch": 1.5546935608999224, "percentage": 52.08, "elapsed_time": "7:06:33", "remaining_time": "6:32:25"}
+{"current_steps": 126, "total_steps": 240, "loss": 0.4428, "lr": 4.348622970990634e-05, "epoch": 1.5671062839410395, "percentage": 52.5, "elapsed_time": "7:09:57", "remaining_time": "6:29:00"}
+{"current_steps": 127, "total_steps": 240, "loss": 0.4482, "lr": 4.290631882890443e-05, "epoch": 1.5795190069821567, "percentage": 52.92, "elapsed_time": "7:13:21", "remaining_time": "6:25:35"}
+{"current_steps": 128, "total_steps": 240, "loss": 0.4404, "lr": 4.2325793156419035e-05, "epoch": 1.5919317300232738, "percentage": 53.33, "elapsed_time": "7:16:45", "remaining_time": "6:22:09"}
+{"current_steps": 129, "total_steps": 240, "loss": 0.4461, "lr": 4.174477549461345e-05, "epoch": 1.604344453064391, "percentage": 53.75, "elapsed_time": "7:20:10", "remaining_time": "6:18:45"}
+{"current_steps": 130, "total_steps": 240, "loss": 0.4362, "lr": 4.116338874972446e-05, "epoch": 1.6167571761055082, "percentage": 54.17, "elapsed_time": "7:23:34", "remaining_time": "6:15:20"}
+{"current_steps": 131, "total_steps": 240, "loss": 0.435, "lr": 4.058175590606332e-05, "epoch": 1.6291698991466252, "percentage": 54.58, "elapsed_time": "7:26:58", "remaining_time": "6:11:55"}
+{"current_steps": 132, "total_steps": 240, "loss": 0.4435, "lr": 4e-05, "epoch": 1.6415826221877423, "percentage": 55.0, "elapsed_time": "7:30:23", "remaining_time": "6:08:30"}
+{"current_steps": 133, "total_steps": 240, "loss": 0.4405, "lr": 3.9418244093936694e-05, "epoch": 1.6539953452288596, "percentage": 55.42, "elapsed_time": "7:33:48", "remaining_time": "6:05:05"}
+{"current_steps": 134, "total_steps": 240, "loss": 0.4342, "lr": 3.8836611250275546e-05, "epoch": 1.6664080682699767, "percentage": 55.83, "elapsed_time": "7:37:14", "remaining_time": "6:01:41"}
+{"current_steps": 135, "total_steps": 240, "loss": 0.4376, "lr": 3.825522450538657e-05, "epoch": 1.678820791311094, "percentage": 56.25, "elapsed_time": "7:40:39", "remaining_time": "5:58:17"}
+{"current_steps": 136, "total_steps": 240, "loss": 0.4415, "lr": 3.767420684358097e-05, "epoch": 1.691233514352211, "percentage": 56.67, "elapsed_time": "7:44:03", "remaining_time": "5:54:52"}
+{"current_steps": 137, "total_steps": 240, "loss": 0.4399, "lr": 3.709368117109558e-05, "epoch": 1.703646237393328, "percentage": 57.08, "elapsed_time": "7:47:28", "remaining_time": "5:51:27"}
+{"current_steps": 138, "total_steps": 240, "loss": 0.4441, "lr": 3.6513770290093674e-05, "epoch": 1.7160589604344452, "percentage": 57.5, "elapsed_time": "7:50:53", "remaining_time": "5:48:03"}
+{"current_steps": 139, "total_steps": 240, "loss": 0.4374, "lr": 3.5934596872687924e-05, "epoch": 1.7284716834755625, "percentage": 57.92, "elapsed_time": "7:54:18", "remaining_time": "5:44:38"}
+{"current_steps": 140, "total_steps": 240, "loss": 0.4415, "lr": 3.535628343499079e-05, "epoch": 1.7408844065166797, "percentage": 58.33, "elapsed_time": "7:57:43", "remaining_time": "5:41:14"}
+{"current_steps": 141, "total_steps": 240, "loss": 0.4379, "lr": 3.477895231119795e-05, "epoch": 1.7532971295577968, "percentage": 58.75, "elapsed_time": "8:01:08", "remaining_time": "5:37:49"}
+{"current_steps": 142, "total_steps": 240, "loss": 0.4443, "lr": 3.4202725627710136e-05, "epoch": 1.7657098525989139, "percentage": 59.17, "elapsed_time": "8:04:32", "remaining_time": "5:34:24"}
+{"current_steps": 143, "total_steps": 240, "loss": 0.4413, "lr": 3.3627725277299103e-05, "epoch": 1.778122575640031, "percentage": 59.58, "elapsed_time": "8:07:57", "remaining_time": "5:30:59"}
+{"current_steps": 144, "total_steps": 240, "loss": 0.4384, "lr": 3.305407289332279e-05, "epoch": 1.790535298681148, "percentage": 60.0, "elapsed_time": "8:11:21", "remaining_time": "5:27:34"}
+{"current_steps": 145, "total_steps": 240, "loss": 0.4377, "lr": 3.248188982399553e-05, "epoch": 1.8029480217222653, "percentage": 60.42, "elapsed_time": "8:14:45", "remaining_time": "5:24:09"}
+{"current_steps": 146, "total_steps": 240, "loss": 0.4377, "lr": 3.191129710671849e-05, "epoch": 1.8153607447633826, "percentage": 60.83, "elapsed_time": "8:18:10", "remaining_time": "5:20:44"}
+{"current_steps": 147, "total_steps": 240, "loss": 0.4439, "lr": 3.134241544247589e-05, "epoch": 1.8277734678044997, "percentage": 61.25, "elapsed_time": "8:21:35", "remaining_time": "5:17:19"}
+{"current_steps": 148, "total_steps": 240, "loss": 0.433, "lr": 3.07753651703024e-05, "epoch": 1.8401861908456167, "percentage": 61.67, "elapsed_time": "8:24:59", "remaining_time": "5:13:55"}
+{"current_steps": 149, "total_steps": 240, "loss": 0.4357, "lr": 3.0210266241827047e-05, "epoch": 1.8525989138867338, "percentage": 62.08, "elapsed_time": "8:28:24", "remaining_time": "5:10:30"}
+{"current_steps": 150, "total_steps": 240, "loss": 0.4393, "lr": 2.9647238195899168e-05, "epoch": 1.865011636927851, "percentage": 62.5, "elapsed_time": "8:31:49", "remaining_time": "5:07:05"}
+{"current_steps": 151, "total_steps": 240, "loss": 0.4438, "lr": 2.9086400133301573e-05, "epoch": 1.8774243599689682, "percentage": 62.92, "elapsed_time": "8:35:14", "remaining_time": "5:03:40"}
+{"current_steps": 152, "total_steps": 240, "loss": 0.4253, "lr": 2.8527870691556404e-05, "epoch": 1.8898370830100855, "percentage": 63.33, "elapsed_time": "8:38:39", "remaining_time": "5:00:16"}
+{"current_steps": 153, "total_steps": 240, "loss": 0.425, "lr": 2.7971768019829083e-05, "epoch": 1.9022498060512025, "percentage": 63.75, "elapsed_time": "8:42:04", "remaining_time": "4:56:51"}
+{"current_steps": 154, "total_steps": 240, "loss": 0.4318, "lr": 2.7418209753935464e-05, "epoch": 1.9146625290923196, "percentage": 64.17, "elapsed_time": "8:45:28", "remaining_time": "4:53:26"}
+{"current_steps": 155, "total_steps": 240, "loss": 0.4373, "lr": 2.6867312991457563e-05, "epoch": 1.9270752521334367, "percentage": 64.58, "elapsed_time": "8:48:53", "remaining_time": "4:50:02"}
+{"current_steps": 156, "total_steps": 240, "loss": 0.4377, "lr": 2.6319194266973256e-05, "epoch": 1.939487975174554, "percentage": 65.0, "elapsed_time": "8:52:18", "remaining_time": "4:46:37"}
+{"current_steps": 157, "total_steps": 240, "loss": 0.4411, "lr": 2.577396952740495e-05, "epoch": 1.951900698215671, "percentage": 65.42, "elapsed_time": "8:55:44", "remaining_time": "4:43:13"}
+{"current_steps": 158, "total_steps": 240, "loss": 0.4331, "lr": 2.523175410749263e-05, "epoch": 1.9643134212567883, "percentage": 65.83, "elapsed_time": "8:59:08", "remaining_time": "4:39:48"}
+{"current_steps": 159, "total_steps": 240, "loss": 0.4306, "lr": 2.4692662705396412e-05, "epoch": 1.9767261442979054, "percentage": 66.25, "elapsed_time": "9:02:33", "remaining_time": "4:36:23"}
+{"current_steps": 160, "total_steps": 240, "loss": 0.4423, "lr": 2.4156809358433728e-05, "epoch": 1.9891388673390225, "percentage": 66.67, "elapsed_time": "9:05:58", "remaining_time": "4:32:59"}
+{"current_steps": 161, "total_steps": 240, "loss": 0.4252, "lr": 2.3624307418956298e-05, "epoch": 2.004654771140419, "percentage": 67.08, "elapsed_time": "9:10:29", "remaining_time": "4:30:06"}
+{"current_steps": 162, "total_steps": 240, "loss": 0.41, "lr": 2.3095269530372032e-05, "epoch": 2.017067494181536, "percentage": 67.5, "elapsed_time": "9:13:54", "remaining_time": "4:26:41"}
+{"current_steps": 163, "total_steps": 240, "loss": 0.4174, "lr": 2.2569807603316836e-05, "epoch": 2.029480217222653, "percentage": 67.92, "elapsed_time": "9:17:18", "remaining_time": "4:23:15"}
+{"current_steps": 164, "total_steps": 240, "loss": 0.4128, "lr": 2.2048032791981515e-05, "epoch": 2.04189294026377, "percentage": 68.33, "elapsed_time": "9:20:42", "remaining_time": "4:19:50"}
+{"current_steps": 165, "total_steps": 240, "loss": 0.4074, "lr": 2.1530055470598654e-05, "epoch": 2.0543056633048877, "percentage": 68.75, "elapsed_time": "9:24:08", "remaining_time": "4:16:25"}
+{"current_steps": 166, "total_steps": 240, "loss": 0.4113, "lr": 2.1015985210094385e-05, "epoch": 2.066718386346005, "percentage": 69.17, "elapsed_time": "9:27:32", "remaining_time": "4:13:00"}
+{"current_steps": 167, "total_steps": 240, "loss": 0.4038, "lr": 2.050593075491031e-05, "epoch": 2.079131109387122, "percentage": 69.58, "elapsed_time": "9:30:57", "remaining_time": "4:09:34"}
+{"current_steps": 168, "total_steps": 240, "loss": 0.4096, "lr": 2.0000000000000012e-05, "epoch": 2.091543832428239, "percentage": 70.0, "elapsed_time": "9:34:24", "remaining_time": "4:06:10"}
+{"current_steps": 169, "total_steps": 240, "loss": 0.4033, "lr": 1.9498299968005393e-05, "epoch": 2.103956555469356, "percentage": 70.42, "elapsed_time": "9:37:50", "remaining_time": "4:02:45"}
+{"current_steps": 170, "total_steps": 240, "loss": 0.4141, "lr": 1.90009367866176e-05, "epoch": 2.116369278510473, "percentage": 70.83, "elapsed_time": "9:41:15", "remaining_time": "3:59:20"}
+{"current_steps": 171, "total_steps": 240, "loss": 0.3997, "lr": 1.8508015666127043e-05, "epoch": 2.1287820015515906, "percentage": 71.25, "elapsed_time": "9:44:40", "remaining_time": "3:55:55"}
+{"current_steps": 172, "total_steps": 240, "loss": 0.4102, "lr": 1.8019640877167763e-05, "epoch": 2.1411947245927077, "percentage": 71.67, "elapsed_time": "9:48:04", "remaining_time": "3:52:29"}
+{"current_steps": 173, "total_steps": 240, "loss": 0.4045, "lr": 1.753591572866029e-05, "epoch": 2.1536074476338247, "percentage": 72.08, "elapsed_time": "9:51:29", "remaining_time": "3:49:04"}
+{"current_steps": 174, "total_steps": 240, "loss": 0.411, "lr": 1.7056942545958167e-05, "epoch": 2.166020170674942, "percentage": 72.5, "elapsed_time": "9:54:55", "remaining_time": "3:45:39"}
+{"current_steps": 175, "total_steps": 240, "loss": 0.4043, "lr": 1.6582822649202382e-05, "epoch": 2.178432893716059, "percentage": 72.92, "elapsed_time": "9:58:20", "remaining_time": "3:42:14"}
+{"current_steps": 176, "total_steps": 240, "loss": 0.4081, "lr": 1.6113656331888563e-05, "epoch": 2.190845616757176, "percentage": 73.33, "elapsed_time": "10:01:45", "remaining_time": "3:38:49"}
+{"current_steps": 177, "total_steps": 240, "loss": 0.4059, "lr": 1.5649542839651175e-05, "epoch": 2.2032583397982934, "percentage": 73.75, "elapsed_time": "10:05:11", "remaining_time": "3:35:24"}
+{"current_steps": 178, "total_steps": 240, "loss": 0.4118, "lr": 1.5190580349269604e-05, "epoch": 2.2156710628394105, "percentage": 74.17, "elapsed_time": "10:08:37", "remaining_time": "3:31:59"}
+{"current_steps": 179, "total_steps": 240, "loss": 0.4059, "lr": 1.4736865947900106e-05, "epoch": 2.2280837858805276, "percentage": 74.58, "elapsed_time": "10:12:02", "remaining_time": "3:28:34"}
+{"current_steps": 180, "total_steps": 240, "loss": 0.418, "lr": 1.4288495612538427e-05, "epoch": 2.2404965089216446, "percentage": 75.0, "elapsed_time": "10:15:28", "remaining_time": "3:25:09"}
+{"current_steps": 181, "total_steps": 240, "loss": 0.4014, "lr": 1.3845564189717218e-05, "epoch": 2.2529092319627617, "percentage": 75.42, "elapsed_time": "10:18:52", "remaining_time": "3:21:44"}
+{"current_steps": 182, "total_steps": 240, "loss": 0.4076, "lr": 1.3408165375442486e-05, "epoch": 2.265321955003879, "percentage": 75.83, "elapsed_time": "10:22:18", "remaining_time": "3:18:18"}
+{"current_steps": 183, "total_steps": 240, "loss": 0.4117, "lr": 1.297639169537359e-05, "epoch": 2.2777346780449963, "percentage": 76.25, "elapsed_time": "10:25:43", "remaining_time": "3:14:53"}
+{"current_steps": 184, "total_steps": 240, "loss": 0.4074, "lr": 1.2550334485250661e-05, "epoch": 2.2901474010861134, "percentage": 76.67, "elapsed_time": "10:29:09", "remaining_time": "3:11:28"}
+{"current_steps": 185, "total_steps": 240, "loss": 0.4106, "lr": 1.2130083871573812e-05, "epoch": 2.3025601241272304, "percentage": 77.08, "elapsed_time": "10:32:34", "remaining_time": "3:08:03"}
+{"current_steps": 186, "total_steps": 240, "loss": 0.4068, "lr": 1.1715728752538103e-05, "epoch": 2.3149728471683475, "percentage": 77.5, "elapsed_time": "10:35:58", "remaining_time": "3:04:38"}
+{"current_steps": 187, "total_steps": 240, "loss": 0.4082, "lr": 1.130735677922842e-05, "epoch": 2.3273855702094646, "percentage": 77.92, "elapsed_time": "10:39:24", "remaining_time": "3:01:13"}
+{"current_steps": 188, "total_steps": 240, "loss": 0.4151, "lr": 1.0905054337078051e-05, "epoch": 2.339798293250582, "percentage": 78.33, "elapsed_time": "10:42:49", "remaining_time": "2:57:48"}
+{"current_steps": 189, "total_steps": 240, "loss": 0.4043, "lr": 1.0508906527595042e-05, "epoch": 2.352211016291699, "percentage": 78.75, "elapsed_time": "10:46:14", "remaining_time": "2:54:23"}
+{"current_steps": 190, "total_steps": 240, "loss": 0.4057, "lr": 1.0118997150360169e-05, "epoch": 2.364623739332816, "percentage": 79.17, "elapsed_time": "10:49:39", "remaining_time": "2:50:57"}
+{"current_steps": 191, "total_steps": 240, "loss": 0.4022, "lr": 9.735408685300287e-06, "epoch": 2.3770364623739333, "percentage": 79.58, "elapsed_time": "10:53:04", "remaining_time": "2:47:32"}
+{"current_steps": 192, "total_steps": 240, "loss": 0.4047, "lr": 9.358222275240884e-06, "epoch": 2.3894491854150504, "percentage": 80.0, "elapsed_time": "10:56:29", "remaining_time": "2:44:07"}
+{"current_steps": 193, "total_steps": 240, "loss": 0.4069, "lr": 8.987517708741364e-06, "epoch": 2.4018619084561674, "percentage": 80.42, "elapsed_time": "10:59:55", "remaining_time": "2:40:42"}
+{"current_steps": 194, "total_steps": 240, "loss": 0.4036, "lr": 8.623373403216972e-06, "epoch": 2.4142746314972845, "percentage": 80.83, "elapsed_time": "11:03:20", "remaining_time": "2:37:17"}
+{"current_steps": 195, "total_steps": 240, "loss": 0.407, "lr": 8.265866388350598e-06, "epoch": 2.426687354538402, "percentage": 81.25, "elapsed_time": "11:06:44", "remaining_time": "2:33:51"}
+{"current_steps": 196, "total_steps": 240, "loss": 0.4025, "lr": 7.915072289798247e-06, "epoch": 2.439100077579519, "percentage": 81.67, "elapsed_time": "11:10:10", "remaining_time": "2:30:26"}
+{"current_steps": 197, "total_steps": 240, "loss": 0.4028, "lr": 7.5710653131915125e-06, "epoch": 2.451512800620636, "percentage": 82.08, "elapsed_time": "11:13:35", "remaining_time": "2:27:01"}
+{"current_steps": 198, "total_steps": 240, "loss": 0.4032, "lr": 7.233918228440324e-06, "epoch": 2.463925523661753, "percentage": 82.5, "elapsed_time": "11:17:02", "remaining_time": "2:23:36"}
+{"current_steps": 199, "total_steps": 240, "loss": 0.3962, "lr": 6.903702354339578e-06, "epoch": 2.4763382467028703, "percentage": 82.92, "elapsed_time": "11:20:26", "remaining_time": "2:20:11"}
+{"current_steps": 200, "total_steps": 240, "loss": 0.404, "lr": 6.58048754348255e-06, "epoch": 2.488750969743988, "percentage": 83.33, "elapsed_time": "11:23:52", "remaining_time": "2:16:46"}
+{"current_steps": 201, "total_steps": 240, "loss": 0.4063, "lr": 6.26434216748458e-06, "epoch": 2.501163692785105, "percentage": 83.75, "elapsed_time": "11:27:18", "remaining_time": "2:13:21"}
+{"current_steps": 202, "total_steps": 240, "loss": 0.4098, "lr": 5.955333102520011e-06, "epoch": 2.513576415826222, "percentage": 84.17, "elapsed_time": "11:30:43", "remaining_time": "2:09:56"}
+{"current_steps": 203, "total_steps": 240, "loss": 0.4034, "lr": 5.653525715175483e-06, "epoch": 2.525989138867339, "percentage": 84.58, "elapsed_time": "11:34:09", "remaining_time": "2:06:31"}
+{"current_steps": 204, "total_steps": 240, "loss": 0.4082, "lr": 5.358983848622452e-06, "epoch": 2.538401861908456, "percentage": 85.0, "elapsed_time": "11:37:34", "remaining_time": "2:03:06"}
+{"current_steps": 205, "total_steps": 240, "loss": 0.4032, "lr": 5.07176980911217e-06, "epoch": 2.550814584949573, "percentage": 85.42, "elapsed_time": "11:40:59", "remaining_time": "1:59:40"}
+{"current_steps": 206, "total_steps": 240, "loss": 0.4011, "lr": 4.791944352795561e-06, "epoch": 2.56322730799069, "percentage": 85.83, "elapsed_time": "11:44:25", "remaining_time": "1:56:15"}
+{"current_steps": 207, "total_steps": 240, "loss": 0.4102, "lr": 4.519566672871132e-06, "epoch": 2.5756400310318077, "percentage": 86.25, "elapsed_time": "11:47:51", "remaining_time": "1:52:50"}
+{"current_steps": 208, "total_steps": 240, "loss": 0.4103, "lr": 4.254694387063514e-06, "epoch": 2.588052754072925, "percentage": 86.67, "elapsed_time": "11:51:15", "remaining_time": "1:49:25"}
+{"current_steps": 209, "total_steps": 240, "loss": 0.4068, "lr": 3.997383525435154e-06, "epoch": 2.600465477114042, "percentage": 87.08, "elapsed_time": "11:54:39", "remaining_time": "1:46:00"}
+{"current_steps": 210, "total_steps": 240, "loss": 0.3964, "lr": 3.747688518534003e-06, "epoch": 2.612878200155159, "percentage": 87.5, "elapsed_time": "11:58:01", "remaining_time": "1:42:34"}
+{"current_steps": 211, "total_steps": 240, "loss": 0.4107, "lr": 3.5056621858794393e-06, "epoch": 2.6252909231962764, "percentage": 87.92, "elapsed_time": "12:01:24", "remaining_time": "1:39:09"}
+{"current_steps": 212, "total_steps": 240, "loss": 0.4004, "lr": 3.2713557247890447e-06, "epoch": 2.6377036462373935, "percentage": 88.33, "elapsed_time": "12:04:47", "remaining_time": "1:35:43"}
+{"current_steps": 213, "total_steps": 240, "loss": 0.4052, "lr": 3.0448186995485307e-06, "epoch": 2.6501163692785106, "percentage": 88.75, "elapsed_time": "12:08:09", "remaining_time": "1:32:18"}
+{"current_steps": 214, "total_steps": 240, "loss": 0.4095, "lr": 2.8260990309270987e-06, "epoch": 2.6625290923196276, "percentage": 89.17, "elapsed_time": "12:11:32", "remaining_time": "1:28:52"}
+{"current_steps": 215, "total_steps": 240, "loss": 0.4024, "lr": 2.6152429860404647e-06, "epoch": 2.6749418153607447, "percentage": 89.58, "elapsed_time": "12:14:55", "remaining_time": "1:25:27"}
+{"current_steps": 216, "total_steps": 240, "loss": 0.4053, "lr": 2.4122951685636674e-06, "epoch": 2.687354538401862, "percentage": 90.0, "elapsed_time": "12:18:18", "remaining_time": "1:22:02"}
+{"current_steps": 217, "total_steps": 240, "loss": 0.4058, "lr": 2.217298509295813e-06, "epoch": 2.699767261442979, "percentage": 90.42, "elapsed_time": "12:21:40", "remaining_time": "1:18:36"}
+{"current_steps": 218, "total_steps": 240, "loss": 0.4128, "lr": 2.0302942570786446e-06, "epoch": 2.7121799844840964, "percentage": 90.83, "elapsed_time": "12:25:02", "remaining_time": "1:15:11"}
+{"current_steps": 219, "total_steps": 240, "loss": 0.4025, "lr": 1.8513219700709272e-06, "epoch": 2.7245927075252134, "percentage": 91.25, "elapsed_time": "12:28:25", "remaining_time": "1:11:45"}
+{"current_steps": 220, "total_steps": 240, "loss": 0.4097, "lr": 1.6804195073804442e-06, "epoch": 2.7370054305663305, "percentage": 91.67, "elapsed_time": "12:31:48", "remaining_time": "1:08:20"}
+{"current_steps": 221, "total_steps": 240, "loss": 0.4084, "lr": 1.5176230210554744e-06, "epoch": 2.7494181536074476, "percentage": 92.08, "elapsed_time": "12:35:12", "remaining_time": "1:04:55"}
+{"current_steps": 222, "total_steps": 240, "loss": 0.4087, "lr": 1.3629669484372722e-06, "epoch": 2.7618308766485646, "percentage": 92.5, "elapsed_time": "12:38:34", "remaining_time": "1:01:30"}
+{"current_steps": 223, "total_steps": 240, "loss": 0.4045, "lr": 1.2164840048753602e-06, "epoch": 2.774243599689682, "percentage": 92.92, "elapsed_time": "12:41:57", "remaining_time": "0:58:05"}
+{"current_steps": 224, "total_steps": 240, "loss": 0.4092, "lr": 1.0782051768070477e-06, "epoch": 2.786656322730799, "percentage": 93.33, "elapsed_time": "12:45:19", "remaining_time": "0:54:39"}
+{"current_steps": 225, "total_steps": 240, "loss": 0.4007, "lr": 9.481597152026656e-07, "epoch": 2.7990690457719163, "percentage": 93.75, "elapsed_time": "12:48:43", "remaining_time": "0:51:14"}
+{"current_steps": 226, "total_steps": 240, "loss": 0.4058, "lr": 8.263751293779409e-07, "epoch": 2.8114817688130334, "percentage": 94.17, "elapsed_time": "12:52:04", "remaining_time": "0:47:49"}
+{"current_steps": 227, "total_steps": 240, "loss": 0.4076, "lr": 7.128771811747737e-07, "epoch": 2.8238944918541504, "percentage": 94.58, "elapsed_time": "12:55:27", "remaining_time": "0:44:24"}
+{"current_steps": 228, "total_steps": 240, "loss": 0.4037, "lr": 6.076898795116792e-07, "epoch": 2.8363072148952675, "percentage": 95.0, "elapsed_time": "12:58:50", "remaining_time": "0:40:59"}
+{"current_steps": 229, "total_steps": 240, "loss": 0.3925, "lr": 5.108354753050381e-07, "epoch": 2.8487199379363846, "percentage": 95.42, "elapsed_time": "13:02:12", "remaining_time": "0:37:34"}
+{"current_steps": 230, "total_steps": 240, "loss": 0.4093, "lr": 4.223344567622212e-07, "epoch": 2.861132660977502, "percentage": 95.83, "elapsed_time": "13:05:34", "remaining_time": "0:34:09"}
+{"current_steps": 231, "total_steps": 240, "loss": 0.4058, "lr": 3.4220554504758475e-07, "epoch": 2.873545384018619, "percentage": 96.25, "elapsed_time": "13:08:56", "remaining_time": "0:30:44"}
+{"current_steps": 232, "total_steps": 240, "loss": 0.4028, "lr": 2.704656903222791e-07, "epoch": 2.885958107059736, "percentage": 96.67, "elapsed_time": "13:12:19", "remaining_time": "0:27:19"}
+{"current_steps": 233, "total_steps": 240, "loss": 0.4095, "lr": 2.0713006815868075e-07, "epoch": 2.8983708301008533, "percentage": 97.08, "elapsed_time": "13:15:42", "remaining_time": "0:23:54"}
+{"current_steps": 234, "total_steps": 240, "loss": 0.4037, "lr": 1.522120763301782e-07, "epoch": 2.910783553141971, "percentage": 97.5, "elapsed_time": "13:19:04", "remaining_time": "0:20:29"}
+{"current_steps": 235, "total_steps": 240, "loss": 0.4121, "lr": 1.0572333197711005e-07, "epoch": 2.923196276183088, "percentage": 97.92, "elapsed_time": "13:22:25", "remaining_time": "0:17:04"}
+{"current_steps": 236, "total_steps": 240, "loss": 0.4071, "lr": 6.767366914927298e-08, "epoch": 2.935608999224205, "percentage": 98.33, "elapsed_time": "13:25:49", "remaining_time": "0:13:39"}
+{"current_steps": 237, "total_steps": 240, "loss": 0.4016, "lr": 3.8071136725688074e-08, "epoch": 2.948021722265322, "percentage": 98.75, "elapsed_time": "13:29:11", "remaining_time": "0:10:14"}
+{"current_steps": 238, "total_steps": 240, "loss": 0.4033, "lr": 1.6921996711976028e-08, "epoch": 2.960434445306439, "percentage": 99.17, "elapsed_time": "13:32:34", "remaining_time": "0:06:49"}
+{"current_steps": 239, "total_steps": 240, "loss": 0.402, "lr": 4.230722915701257e-09, "epoch": 2.972847168347556, "percentage": 99.58, "elapsed_time": "13:35:56", "remaining_time": "0:03:24"}
+{"current_steps": 240, "total_steps": 240, "loss": 0.4036, "lr": 0.0, "epoch": 2.985259891388673, "percentage": 100.0, "elapsed_time": "13:39:18", "remaining_time": "0:00:00"}
+{"current_steps": 240, "total_steps": 240, "epoch": 2.985259891388673, "percentage": 100.0, "elapsed_time": "13:40:47", "remaining_time": "0:00:00"}
+{"current_steps": 240, "total_steps": 240, "epoch": 2.985259891388673, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 240, "total_steps": 240, "epoch": 2.985259891388673, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 240, "total_steps": 240, "epoch": 2.985259891388673, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 240, "total_steps": 240, "epoch": 2.985259891388673, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 240, "total_steps": 240, "epoch": 2.985259891388673, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1722 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.985259891388673,
+  "eval_steps": 500,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012412723041117145,
+      "grad_norm": 5.811139292413218,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8592,
+      "step": 1
+    },
+    {
+      "epoch": 0.02482544608223429,
+      "grad_norm": 5.912652754864286,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8708,
+      "step": 2
+    },
+    {
+      "epoch": 0.037238169123351435,
+      "grad_norm": 5.351962025116072,
+      "learning_rate": 1e-05,
+      "loss": 0.8418,
+      "step": 3
+    },
+    {
+      "epoch": 0.04965089216446858,
+      "grad_norm": 2.40376437239712,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7757,
+      "step": 4
+    },
+    {
+      "epoch": 0.062063615205585725,
+      "grad_norm": 4.572842895731978,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.802,
+      "step": 5
+    },
+    {
+      "epoch": 0.07447633824670287,
+      "grad_norm": 4.959247881565937,
+      "learning_rate": 2e-05,
+      "loss": 0.7535,
+      "step": 6
+    },
+    {
+      "epoch": 0.08688906128782002,
+      "grad_norm": 5.570890629167377,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.7712,
+      "step": 7
+    },
+    {
+      "epoch": 0.09930178432893716,
+      "grad_norm": 2.6844265825742717,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.7177,
+      "step": 8
+    },
+    {
+      "epoch": 0.11171450737005431,
+      "grad_norm": 2.41540133517055,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 0.6858,
+      "step": 9
+    },
+    {
+      "epoch": 0.12412723041117145,
+      "grad_norm": 1.7271085563985984,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6676,
+      "step": 10
+    },
+    {
+      "epoch": 0.1365399534522886,
+      "grad_norm": 1.4650115000680082,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.6418,
+      "step": 11
+    },
+    {
+      "epoch": 0.14895267649340574,
+      "grad_norm": 1.7202560044367992,
+      "learning_rate": 4e-05,
+      "loss": 0.6335,
+      "step": 12
+    },
+    {
+      "epoch": 0.1613653995345229,
+      "grad_norm": 1.7338123529243046,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.6212,
+      "step": 13
+    },
+    {
+      "epoch": 0.17377812257564004,
+      "grad_norm": 1.5458292130799125,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.6196,
+      "step": 14
+    },
+    {
+      "epoch": 0.18619084561675717,
+      "grad_norm": 1.6210213430259865,
+      "learning_rate": 5e-05,
+      "loss": 0.6099,
+      "step": 15
+    },
+    {
+      "epoch": 0.19860356865787432,
+      "grad_norm": 1.213400346916168,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.5928,
+      "step": 16
+    },
+    {
+      "epoch": 0.21101629169899147,
+      "grad_norm": 1.8118904252488883,
+      "learning_rate": 5.666666666666668e-05,
+      "loss": 0.5895,
+      "step": 17
+    },
+    {
+      "epoch": 0.22342901474010862,
+      "grad_norm": 1.2072813211462619,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.5829,
+      "step": 18
+    },
+    {
+      "epoch": 0.23584173778122575,
+      "grad_norm": 2.253552284596588,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 0.5849,
+      "step": 19
+    },
+    {
+      "epoch": 0.2482544608223429,
+      "grad_norm": 1.3951737001684923,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.5754,
+      "step": 20
+    },
+    {
+      "epoch": 0.26066718386346005,
+      "grad_norm": 1.8728926995550705,
+      "learning_rate": 7.000000000000001e-05,
+      "loss": 0.5782,
+      "step": 21
+    },
+    {
+      "epoch": 0.2730799069045772,
+      "grad_norm": 1.4025617403660748,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.572,
+      "step": 22
+    },
+    {
+      "epoch": 0.28549262994569435,
+      "grad_norm": 1.7280551511975304,
+      "learning_rate": 7.666666666666668e-05,
+      "loss": 0.5689,
+      "step": 23
+    },
+    {
+      "epoch": 0.2979053529868115,
+      "grad_norm": 1.2210172362751521,
+      "learning_rate": 8e-05,
+      "loss": 0.5669,
+      "step": 24
+    },
+    {
+      "epoch": 0.3103180760279286,
+      "grad_norm": 2.038907152211388,
+      "learning_rate": 7.99957692770843e-05,
+      "loss": 0.5587,
+      "step": 25
+    },
+    {
+      "epoch": 0.3227307990690458,
+      "grad_norm": 1.4012862098032781,
+      "learning_rate": 7.998307800328803e-05,
+      "loss": 0.5598,
+      "step": 26
+    },
+    {
+      "epoch": 0.3351435221101629,
+      "grad_norm": 2.306205673521179,
+      "learning_rate": 7.996192886327432e-05,
+      "loss": 0.5573,
+      "step": 27
+    },
+    {
+      "epoch": 0.3475562451512801,
+      "grad_norm": 1.7083136409254012,
+      "learning_rate": 7.993232633085074e-05,
+      "loss": 0.5454,
+      "step": 28
+    },
+    {
+      "epoch": 0.3599689681923972,
+      "grad_norm": 1.096606614399358,
+      "learning_rate": 7.98942766680229e-05,
+      "loss": 0.5484,
+      "step": 29
+    },
+    {
+      "epoch": 0.37238169123351433,
+      "grad_norm": 2.489709057654376,
+      "learning_rate": 7.984778792366983e-05,
+      "loss": 0.5672,
+      "step": 30
+    },
+    {
+      "epoch": 0.3847944142746315,
+      "grad_norm": 1.4105856894628461,
+      "learning_rate": 7.979286993184134e-05,
+      "loss": 0.5554,
+      "step": 31
+    },
+    {
+      "epoch": 0.39720713731574864,
+      "grad_norm": 2.6673332762599387,
+      "learning_rate": 7.972953430967773e-05,
+      "loss": 0.552,
+      "step": 32
+    },
+    {
+      "epoch": 0.40961986035686576,
+      "grad_norm": 1.8448184671441439,
+      "learning_rate": 7.965779445495243e-05,
+      "loss": 0.5647,
+      "step": 33
+    },
+    {
+      "epoch": 0.42203258339798294,
+      "grad_norm": 1.9222419634800547,
+      "learning_rate": 7.957766554323778e-05,
+      "loss": 0.538,
+      "step": 34
+    },
+    {
+      "epoch": 0.43444530643910007,
+      "grad_norm": 1.8012414185492107,
+      "learning_rate": 7.948916452469497e-05,
+      "loss": 0.5462,
+      "step": 35
+    },
+    {
+      "epoch": 0.44685802948021724,
+      "grad_norm": 1.4627932591704245,
+      "learning_rate": 7.939231012048833e-05,
+      "loss": 0.5416,
+      "step": 36
+    },
+    {
+      "epoch": 0.45927075252133437,
+      "grad_norm": 1.2663111206857713,
+      "learning_rate": 7.928712281882523e-05,
+      "loss": 0.5261,
+      "step": 37
+    },
+    {
+      "epoch": 0.4716834755624515,
+      "grad_norm": 1.3479368409888506,
+      "learning_rate": 7.917362487062207e-05,
+      "loss": 0.5327,
+      "step": 38
+    },
+    {
+      "epoch": 0.4840961986035687,
+      "grad_norm": 1.3651153144107784,
+      "learning_rate": 7.905184028479734e-05,
+      "loss": 0.5203,
+      "step": 39
+    },
+    {
+      "epoch": 0.4965089216446858,
+      "grad_norm": 1.8147701791804869,
+      "learning_rate": 7.892179482319297e-05,
+      "loss": 0.5276,
+      "step": 40
+    },
+    {
+      "epoch": 0.5089216446858029,
+      "grad_norm": 1.0906112288541403,
+      "learning_rate": 7.878351599512465e-05,
+      "loss": 0.5186,
+      "step": 41
+    },
+    {
+      "epoch": 0.5213343677269201,
+      "grad_norm": 0.9766482263848564,
+      "learning_rate": 7.863703305156273e-05,
+      "loss": 0.519,
+      "step": 42
+    },
+    {
+      "epoch": 0.5337470907680373,
+      "grad_norm": 0.7623912143188495,
+      "learning_rate": 7.848237697894453e-05,
+      "loss": 0.5039,
+      "step": 43
+    },
+    {
+      "epoch": 0.5461598138091543,
+      "grad_norm": 1.3088313038494377,
+      "learning_rate": 7.831958049261956e-05,
+      "loss": 0.5086,
+      "step": 44
+    },
+    {
+      "epoch": 0.5585725368502715,
+      "grad_norm": 1.7656141946058659,
+      "learning_rate": 7.814867802992907e-05,
+      "loss": 0.5191,
+      "step": 45
+    },
+    {
+      "epoch": 0.5709852598913887,
+      "grad_norm": 1.0700866892638767,
+      "learning_rate": 7.796970574292136e-05,
+      "loss": 0.5114,
+      "step": 46
+    },
+    {
+      "epoch": 0.5833979829325058,
+      "grad_norm": 1.78305462655261,
+      "learning_rate": 7.77827014907042e-05,
+      "loss": 0.5072,
+      "step": 47
+    },
+    {
+      "epoch": 0.595810705973623,
+      "grad_norm": 1.02406879721298,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.5128,
+      "step": 48
+    },
+    {
+      "epoch": 0.6082234290147401,
+      "grad_norm": 1.95990042435999,
+      "learning_rate": 7.738475701395955e-05,
+      "loss": 0.5202,
+      "step": 49
+    },
+    {
+      "epoch": 0.6206361520558572,
+      "grad_norm": 1.0960181908669033,
+      "learning_rate": 7.71739009690729e-05,
+      "loss": 0.5018,
+      "step": 50
+    },
+    {
+      "epoch": 0.6330488750969744,
+      "grad_norm": 1.5036795888520276,
+      "learning_rate": 7.695518130045147e-05,
+      "loss": 0.5131,
+      "step": 51
+    },
+    {
+      "epoch": 0.6454615981380916,
+      "grad_norm": 1.319616365412143,
+      "learning_rate": 7.672864427521097e-05,
+      "loss": 0.5053,
+      "step": 52
+    },
+    {
+      "epoch": 0.6578743211792087,
+      "grad_norm": 0.9926898320186054,
+      "learning_rate": 7.649433781412058e-05,
+      "loss": 0.5064,
+      "step": 53
+    },
+    {
+      "epoch": 0.6702870442203258,
+      "grad_norm": 1.3273860712062824,
+      "learning_rate": 7.625231148146601e-05,
+      "loss": 0.5074,
+      "step": 54
+    },
+    {
+      "epoch": 0.682699767261443,
+      "grad_norm": 1.050117023627409,
+      "learning_rate": 7.600261647456485e-05,
+      "loss": 0.4996,
+      "step": 55
+    },
+    {
+      "epoch": 0.6951124903025602,
+      "grad_norm": 1.4843888072932643,
+      "learning_rate": 7.57453056129365e-05,
+      "loss": 0.5026,
+      "step": 56
+    },
+    {
+      "epoch": 0.7075252133436772,
+      "grad_norm": 1.2011318743015846,
+      "learning_rate": 7.548043332712887e-05,
+      "loss": 0.5007,
+      "step": 57
+    },
+    {
+      "epoch": 0.7199379363847944,
+      "grad_norm": 0.9430820882760581,
+      "learning_rate": 7.520805564720444e-05,
+      "loss": 0.5065,
+      "step": 58
+    },
+    {
+      "epoch": 0.7323506594259116,
+      "grad_norm": 0.8622207395547754,
+      "learning_rate": 7.492823019088785e-05,
+      "loss": 0.4885,
+      "step": 59
+    },
+    {
+      "epoch": 0.7447633824670287,
+      "grad_norm": 1.4984422541100448,
+      "learning_rate": 7.464101615137756e-05,
+      "loss": 0.5019,
+      "step": 60
+    },
+    {
+      "epoch": 0.7571761055081458,
+      "grad_norm": 1.8968172780942756,
+      "learning_rate": 7.434647428482453e-05,
+      "loss": 0.5014,
+      "step": 61
+    },
+    {
+      "epoch": 0.769588828549263,
+      "grad_norm": 0.8995696049500695,
+      "learning_rate": 7.404466689747999e-05,
+      "loss": 0.4908,
+      "step": 62
+    },
+    {
+      "epoch": 0.7820015515903801,
+      "grad_norm": 2.0680311795084334,
+      "learning_rate": 7.373565783251544e-05,
+      "loss": 0.507,
+      "step": 63
+    },
+    {
+      "epoch": 0.7944142746314973,
+      "grad_norm": 1.2792641311231951,
+      "learning_rate": 7.341951245651747e-05,
+      "loss": 0.4977,
+      "step": 64
+    },
+    {
+      "epoch": 0.8068269976726145,
+      "grad_norm": 1.628671131933847,
+      "learning_rate": 7.309629764566042e-05,
+      "loss": 0.4961,
+      "step": 65
+    },
+    {
+      "epoch": 0.8192397207137315,
+      "grad_norm": 1.282895413004134,
+      "learning_rate": 7.276608177155968e-05,
+      "loss": 0.4892,
+      "step": 66
+    },
+    {
+      "epoch": 0.8316524437548487,
+      "grad_norm": 1.3336324116999307,
+      "learning_rate": 7.242893468680849e-05,
+      "loss": 0.5048,
+      "step": 67
+    },
+    {
+      "epoch": 0.8440651667959659,
+      "grad_norm": 1.4064833583401357,
+      "learning_rate": 7.208492771020176e-05,
+      "loss": 0.4901,
+      "step": 68
+    },
+    {
+      "epoch": 0.8564778898370831,
+      "grad_norm": 1.0047322181335383,
+      "learning_rate": 7.173413361164941e-05,
+      "loss": 0.4885,
+      "step": 69
+    },
+    {
+      "epoch": 0.8688906128782001,
+      "grad_norm": 1.348170854739073,
+      "learning_rate": 7.137662659678303e-05,
+      "loss": 0.4929,
+      "step": 70
+    },
+    {
+      "epoch": 0.8813033359193173,
+      "grad_norm": 0.7514869415644483,
+      "learning_rate": 7.101248229125864e-05,
+      "loss": 0.4925,
+      "step": 71
+    },
+    {
+      "epoch": 0.8937160589604345,
+      "grad_norm": 0.9684633356516557,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.4787,
+      "step": 72
+    },
+    {
+      "epoch": 0.9061287820015516,
+      "grad_norm": 1.105735924264768,
+      "learning_rate": 7.026459131469972e-05,
+      "loss": 0.4858,
+      "step": 73
+    },
+    {
+      "epoch": 0.9185415050426687,
+      "grad_norm": 1.2840631567872773,
+      "learning_rate": 6.988100284963985e-05,
+      "loss": 0.4928,
+      "step": 74
+    },
+    {
+      "epoch": 0.9309542280837859,
+      "grad_norm": 1.124500179559376,
+      "learning_rate": 6.949109347240496e-05,
+      "loss": 0.4859,
+      "step": 75
+    },
+    {
+      "epoch": 0.943366951124903,
+      "grad_norm": 0.8700397395412913,
+      "learning_rate": 6.909494566292195e-05,
+      "loss": 0.4901,
+      "step": 76
+    },
+    {
+      "epoch": 0.9557796741660202,
+      "grad_norm": 1.0066989400671469,
+      "learning_rate": 6.869264322077158e-05,
+      "loss": 0.4726,
+      "step": 77
+    },
+    {
+      "epoch": 0.9681923972071373,
+      "grad_norm": 1.1397544809910465,
+      "learning_rate": 6.828427124746191e-05,
+      "loss": 0.4942,
+      "step": 78
+    },
+    {
+      "epoch": 0.9806051202482544,
+      "grad_norm": 0.993511131353873,
+      "learning_rate": 6.786991612842621e-05,
+      "loss": 0.4802,
+      "step": 79
+    },
+    {
+      "epoch": 0.9930178432893716,
+      "grad_norm": 1.231281291343096,
+      "learning_rate": 6.744966551474936e-05,
+      "loss": 0.4928,
+      "step": 80
+    },
+    {
+      "epoch": 1.008533747090768,
+      "grad_norm": 1.0563462152913707,
+      "learning_rate": 6.702360830462642e-05,
+      "loss": 0.4722,
+      "step": 81
+    },
+    {
+      "epoch": 1.020946470131885,
+      "grad_norm": 1.0365813092466865,
+      "learning_rate": 6.659183462455751e-05,
+      "loss": 0.4648,
+      "step": 82
+    },
+    {
+      "epoch": 1.0333591931730024,
+      "grad_norm": 1.3854826043823374,
+      "learning_rate": 6.615443581028279e-05,
+      "loss": 0.4668,
+      "step": 83
+    },
+    {
+      "epoch": 1.0457719162141195,
+      "grad_norm": 0.8902743615666566,
+      "learning_rate": 6.571150438746157e-05,
+      "loss": 0.457,
+      "step": 84
+    },
+    {
+      "epoch": 1.0581846392552365,
+      "grad_norm": 1.5634765476427963,
+      "learning_rate": 6.526313405209991e-05,
+      "loss": 0.4669,
+      "step": 85
+    },
+    {
+      "epoch": 1.0705973622963538,
+      "grad_norm": 0.8758561461959842,
+      "learning_rate": 6.480941965073041e-05,
+      "loss": 0.4537,
+      "step": 86
+    },
+    {
+      "epoch": 1.083010085337471,
+      "grad_norm": 1.4060919651373076,
+      "learning_rate": 6.435045716034883e-05,
+      "loss": 0.4544,
+      "step": 87
+    },
+    {
+      "epoch": 1.095422808378588,
+      "grad_norm": 0.8531148774155226,
+      "learning_rate": 6.388634366811146e-05,
+      "loss": 0.455,
+      "step": 88
+    },
+    {
+      "epoch": 1.1078355314197053,
+      "grad_norm": 1.3748253684101237,
+      "learning_rate": 6.341717735079763e-05,
+      "loss": 0.4664,
+      "step": 89
+    },
+    {
+      "epoch": 1.1202482544608223,
+      "grad_norm": 0.8496487999863389,
+      "learning_rate": 6.294305745404185e-05,
+      "loss": 0.4495,
+      "step": 90
+    },
+    {
+      "epoch": 1.1326609775019394,
+      "grad_norm": 1.3064967904807294,
+      "learning_rate": 6.246408427133972e-05,
+      "loss": 0.4641,
+      "step": 91
+    },
+    {
+      "epoch": 1.1450737005430567,
+      "grad_norm": 1.0138641652256504,
+      "learning_rate": 6.198035912283225e-05,
+      "loss": 0.4616,
+      "step": 92
+    },
+    {
+      "epoch": 1.1574864235841738,
+      "grad_norm": 1.320386044205821,
+      "learning_rate": 6.149198433387297e-05,
+      "loss": 0.4571,
+      "step": 93
+    },
+    {
+      "epoch": 1.169899146625291,
+      "grad_norm": 0.9923566120667087,
+      "learning_rate": 6.099906321338241e-05,
+      "loss": 0.4601,
+      "step": 94
+    },
+    {
+      "epoch": 1.182311869666408,
+      "grad_norm": 1.0486458199181818,
+      "learning_rate": 6.0501700031994613e-05,
+      "loss": 0.4469,
+      "step": 95
+    },
+    {
+      "epoch": 1.1947245927075252,
+      "grad_norm": 0.8777950190842737,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.4474,
+      "step": 96
+    },
+    {
+      "epoch": 1.2071373157486422,
+      "grad_norm": 0.7139436573975456,
+      "learning_rate": 5.94940692450897e-05,
+      "loss": 0.4513,
+      "step": 97
+    },
+    {
+      "epoch": 1.2195500387897595,
+      "grad_norm": 0.9010940242607579,
+      "learning_rate": 5.8984014789905625e-05,
+      "loss": 0.4516,
+      "step": 98
+    },
+    {
+      "epoch": 1.2319627618308766,
+      "grad_norm": 0.7712158124572633,
+      "learning_rate": 5.846994452940137e-05,
+      "loss": 0.4493,
+      "step": 99
+    },
+    {
+      "epoch": 1.244375484871994,
+      "grad_norm": 0.7178059141809746,
+      "learning_rate": 5.79519672080185e-05,
+      "loss": 0.451,
+      "step": 100
+    },
+    {
+      "epoch": 1.256788207913111,
+      "grad_norm": 0.6811767000700364,
+      "learning_rate": 5.743019239668318e-05,
+      "loss": 0.4494,
+      "step": 101
+    },
+    {
+      "epoch": 1.269200930954228,
+      "grad_norm": 0.683423884337864,
+      "learning_rate": 5.6904730469627985e-05,
+      "loss": 0.4541,
+      "step": 102
+    },
+    {
+      "epoch": 1.281613653995345,
+      "grad_norm": 0.5714550331585366,
+      "learning_rate": 5.6375692581043705e-05,
+      "loss": 0.439,
+      "step": 103
+    },
+    {
+      "epoch": 1.2940263770364624,
+      "grad_norm": 0.5956249252941349,
+      "learning_rate": 5.584319064156628e-05,
+      "loss": 0.4516,
+      "step": 104
+    },
+    {
+      "epoch": 1.3064391000775795,
+      "grad_norm": 0.5070491288854403,
+      "learning_rate": 5.5307337294603595e-05,
+      "loss": 0.4372,
+      "step": 105
+    },
+    {
+      "epoch": 1.3188518231186968,
+      "grad_norm": 0.5353342216666782,
+      "learning_rate": 5.476824589250738e-05,
+      "loss": 0.4428,
+      "step": 106
+    },
+    {
+      "epoch": 1.3312645461598138,
+      "grad_norm": 0.44994731231873464,
+      "learning_rate": 5.4226030472595075e-05,
+      "loss": 0.4479,
+      "step": 107
+    },
+    {
+      "epoch": 1.343677269200931,
+      "grad_norm": 0.47601680997429713,
+      "learning_rate": 5.368080573302676e-05,
+      "loss": 0.4544,
+      "step": 108
+    },
+    {
+      "epoch": 1.3560899922420482,
+      "grad_norm": 0.390901139311722,
+      "learning_rate": 5.3132687008542454e-05,
+      "loss": 0.445,
+      "step": 109
+    },
+    {
+      "epoch": 1.3685027152831652,
+      "grad_norm": 0.37879369550367104,
+      "learning_rate": 5.258179024606455e-05,
+      "loss": 0.4482,
+      "step": 110
+    },
+    {
+      "epoch": 1.3809154383242823,
+      "grad_norm": 0.3316114914269788,
+      "learning_rate": 5.202823198017092e-05,
+      "loss": 0.4417,
+      "step": 111
+    },
+    {
+      "epoch": 1.3933281613653996,
+      "grad_norm": 0.31615771252775365,
+      "learning_rate": 5.1472129308443616e-05,
+      "loss": 0.4381,
+      "step": 112
+    },
+    {
+      "epoch": 1.4057408844065167,
+      "grad_norm": 0.38657010088667876,
+      "learning_rate": 5.091359986669845e-05,
+      "loss": 0.4522,
+      "step": 113
+    },
+    {
+      "epoch": 1.4181536074476337,
+      "grad_norm": 0.3298153645734073,
+      "learning_rate": 5.0352761804100835e-05,
+      "loss": 0.4473,
+      "step": 114
+    },
+    {
+      "epoch": 1.430566330488751,
+      "grad_norm": 0.3670344833587799,
+      "learning_rate": 4.9789733758172956e-05,
+      "loss": 0.441,
+      "step": 115
+    },
+    {
+      "epoch": 1.442979053529868,
+      "grad_norm": 0.4178206319271822,
+      "learning_rate": 4.922463482969761e-05,
+      "loss": 0.4426,
+      "step": 116
+    },
+    {
+      "epoch": 1.4553917765709854,
+      "grad_norm": 0.39336715579991594,
+      "learning_rate": 4.8657584557524116e-05,
+      "loss": 0.4417,
+      "step": 117
+    },
+    {
+      "epoch": 1.4678044996121025,
+      "grad_norm": 0.3576802123788652,
+      "learning_rate": 4.808870289328153e-05,
+      "loss": 0.4404,
+      "step": 118
+    },
+    {
+      "epoch": 1.4802172226532195,
+      "grad_norm": 0.40571896021906834,
+      "learning_rate": 4.751811017600448e-05,
+      "loss": 0.4445,
+      "step": 119
+    },
+    {
+      "epoch": 1.4926299456943366,
+      "grad_norm": 0.42873696967833597,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.4398,
+      "step": 120
+    },
+    {
+      "epoch": 1.505042668735454,
+      "grad_norm": 0.4463431186356652,
+      "learning_rate": 4.637227472270091e-05,
+      "loss": 0.4403,
+      "step": 121
+    },
+    {
+      "epoch": 1.517455391776571,
+      "grad_norm": 0.5019352129475477,
+      "learning_rate": 4.579727437228987e-05,
+      "loss": 0.4398,
+      "step": 122
+    },
+    {
+      "epoch": 1.5298681148176883,
+      "grad_norm": 0.5280217709941869,
+      "learning_rate": 4.522104768880208e-05,
+      "loss": 0.4416,
+      "step": 123
+    },
+    {
+      "epoch": 1.5422808378588053,
+      "grad_norm": 0.4267811043008705,
+      "learning_rate": 4.464371656500921e-05,
+      "loss": 0.4385,
+      "step": 124
+    },
+    {
+      "epoch": 1.5546935608999224,
+      "grad_norm": 0.37075894007460064,
+      "learning_rate": 4.406540312731208e-05,
+      "loss": 0.4372,
+      "step": 125
+    },
+    {
+      "epoch": 1.5671062839410395,
+      "grad_norm": 0.3118971735686549,
+      "learning_rate": 4.348622970990634e-05,
+      "loss": 0.4428,
+      "step": 126
+    },
+    {
+      "epoch": 1.5795190069821567,
+      "grad_norm": 0.2544870362464729,
+      "learning_rate": 4.290631882890443e-05,
+      "loss": 0.4482,
+      "step": 127
+    },
+    {
+      "epoch": 1.5919317300232738,
+      "grad_norm": 0.31533516890590463,
+      "learning_rate": 4.2325793156419035e-05,
+      "loss": 0.4404,
+      "step": 128
+    },
+    {
+      "epoch": 1.604344453064391,
+      "grad_norm": 0.39480642124339466,
+      "learning_rate": 4.174477549461345e-05,
+      "loss": 0.4461,
+      "step": 129
+    },
+    {
+      "epoch": 1.6167571761055082,
+      "grad_norm": 0.3295488629367603,
+      "learning_rate": 4.116338874972446e-05,
+      "loss": 0.4362,
+      "step": 130
+    },
+    {
+      "epoch": 1.6291698991466252,
+      "grad_norm": 0.2890321036820898,
+      "learning_rate": 4.058175590606332e-05,
+      "loss": 0.435,
+      "step": 131
+    },
+    {
+      "epoch": 1.6415826221877423,
+      "grad_norm": 0.2589627079960217,
+      "learning_rate": 4e-05,
+      "loss": 0.4435,
+      "step": 132
+    },
+    {
+      "epoch": 1.6539953452288596,
+      "grad_norm": 0.27164517893607737,
+      "learning_rate": 3.9418244093936694e-05,
+      "loss": 0.4405,
+      "step": 133
+    },
+    {
+      "epoch": 1.6664080682699767,
+      "grad_norm": 0.3564254929444707,
+      "learning_rate": 3.8836611250275546e-05,
+      "loss": 0.4342,
+      "step": 134
+    },
+    {
+      "epoch": 1.678820791311094,
+      "grad_norm": 0.297830456089688,
+      "learning_rate": 3.825522450538657e-05,
+      "loss": 0.4376,
+      "step": 135
+    },
+    {
+      "epoch": 1.691233514352211,
+      "grad_norm": 0.2817649680936038,
+      "learning_rate": 3.767420684358097e-05,
+      "loss": 0.4415,
+      "step": 136
+    },
+    {
+      "epoch": 1.703646237393328,
+      "grad_norm": 0.24878667700916582,
+      "learning_rate": 3.709368117109558e-05,
+      "loss": 0.4399,
+      "step": 137
+    },
+    {
+      "epoch": 1.7160589604344452,
+      "grad_norm": 0.2468282410833734,
+      "learning_rate": 3.6513770290093674e-05,
+      "loss": 0.4441,
+      "step": 138
+    },
+    {
+      "epoch": 1.7284716834755625,
+      "grad_norm": 0.30172206694247933,
+      "learning_rate": 3.5934596872687924e-05,
+      "loss": 0.4374,
+      "step": 139
+    },
+    {
+      "epoch": 1.7408844065166797,
+      "grad_norm": 0.22655838970060208,
+      "learning_rate": 3.535628343499079e-05,
+      "loss": 0.4415,
+      "step": 140
+    },
+    {
+      "epoch": 1.7532971295577968,
+      "grad_norm": 0.18993025201910843,
+      "learning_rate": 3.477895231119795e-05,
+      "loss": 0.4379,
+      "step": 141
+    },
+    {
+      "epoch": 1.7657098525989139,
+      "grad_norm": 0.21995137974510678,
+      "learning_rate": 3.4202725627710136e-05,
+      "loss": 0.4443,
+      "step": 142
+    },
+    {
+      "epoch": 1.778122575640031,
+      "grad_norm": 0.2215613725954931,
+      "learning_rate": 3.3627725277299103e-05,
+      "loss": 0.4413,
+      "step": 143
+    },
+    {
+      "epoch": 1.790535298681148,
+      "grad_norm": 0.1851165152734122,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.4384,
+      "step": 144
+    },
+    {
+      "epoch": 1.8029480217222653,
+      "grad_norm": 0.18121721969215485,
+      "learning_rate": 3.248188982399553e-05,
+      "loss": 0.4377,
+      "step": 145
+    },
+    {
+      "epoch": 1.8153607447633826,
+      "grad_norm": 0.2146367296889632,
+      "learning_rate": 3.191129710671849e-05,
+      "loss": 0.4377,
+      "step": 146
+    },
+    {
+      "epoch": 1.8277734678044997,
+      "grad_norm": 0.17494812302183207,
+      "learning_rate": 3.134241544247589e-05,
+      "loss": 0.4439,
+      "step": 147
+    },
+    {
+      "epoch": 1.8401861908456167,
+      "grad_norm": 0.2259462851671031,
+      "learning_rate": 3.07753651703024e-05,
+      "loss": 0.433,
+      "step": 148
+    },
+    {
+      "epoch": 1.8525989138867338,
+      "grad_norm": 0.2054803927426192,
+      "learning_rate": 3.0210266241827047e-05,
+      "loss": 0.4357,
+      "step": 149
+    },
+    {
+      "epoch": 1.865011636927851,
+      "grad_norm": 0.18543152534412152,
+      "learning_rate": 2.9647238195899168e-05,
+      "loss": 0.4393,
+      "step": 150
+    },
+    {
+      "epoch": 1.8774243599689682,
+      "grad_norm": 0.22920574719661485,
+      "learning_rate": 2.9086400133301573e-05,
+      "loss": 0.4438,
+      "step": 151
+    },
+    {
+      "epoch": 1.8898370830100855,
+      "grad_norm": 0.19796411017675886,
+      "learning_rate": 2.8527870691556404e-05,
+      "loss": 0.4253,
+      "step": 152
+    },
+    {
+      "epoch": 1.9022498060512025,
+      "grad_norm": 0.17583210693353807,
+      "learning_rate": 2.7971768019829083e-05,
+      "loss": 0.425,
+      "step": 153
+    },
+    {
+      "epoch": 1.9146625290923196,
+      "grad_norm": 0.23539781610525687,
+      "learning_rate": 2.7418209753935464e-05,
+      "loss": 0.4318,
+      "step": 154
+    },
+    {
+      "epoch": 1.9270752521334367,
+      "grad_norm": 0.17062981201530733,
+      "learning_rate": 2.6867312991457563e-05,
+      "loss": 0.4373,
+      "step": 155
+    },
+    {
+      "epoch": 1.939487975174554,
+      "grad_norm": 0.18896979901750025,
+      "learning_rate": 2.6319194266973256e-05,
+      "loss": 0.4377,
+      "step": 156
+    },
+    {
+      "epoch": 1.951900698215671,
+      "grad_norm": 0.21444056877429374,
+      "learning_rate": 2.577396952740495e-05,
+      "loss": 0.4411,
+      "step": 157
+    },
+    {
+      "epoch": 1.9643134212567883,
+      "grad_norm": 0.15711359620880003,
+      "learning_rate": 2.523175410749263e-05,
+      "loss": 0.4331,
+      "step": 158
+    },
+    {
+      "epoch": 1.9767261442979054,
+      "grad_norm": 0.2386397978639225,
+      "learning_rate": 2.4692662705396412e-05,
+      "loss": 0.4306,
+      "step": 159
+    },
+    {
+      "epoch": 1.9891388673390225,
+      "grad_norm": 0.16774705478586877,
+      "learning_rate": 2.4156809358433728e-05,
+      "loss": 0.4423,
+      "step": 160
+    },
+    {
+      "epoch": 2.004654771140419,
+      "grad_norm": 0.2115138678012771,
+      "learning_rate": 2.3624307418956298e-05,
+      "loss": 0.4252,
+      "step": 161
+    },
+    {
+      "epoch": 2.017067494181536,
+      "grad_norm": 0.20421331493417683,
+      "learning_rate": 2.3095269530372032e-05,
+      "loss": 0.41,
+      "step": 162
+    },
+    {
+      "epoch": 2.029480217222653,
+      "grad_norm": 0.17274856512168255,
+      "learning_rate": 2.2569807603316836e-05,
+      "loss": 0.4174,
+      "step": 163
+    },
+    {
+      "epoch": 2.04189294026377,
+      "grad_norm": 0.18787081207924167,
+      "learning_rate": 2.2048032791981515e-05,
+      "loss": 0.4128,
+      "step": 164
+    },
+    {
+      "epoch": 2.0543056633048877,
+      "grad_norm": 0.2005445880914298,
+      "learning_rate": 2.1530055470598654e-05,
+      "loss": 0.4074,
+      "step": 165
+    },
+    {
+      "epoch": 2.066718386346005,
+      "grad_norm": 0.19825273354259515,
+      "learning_rate": 2.1015985210094385e-05,
+      "loss": 0.4113,
+      "step": 166
+    },
+    {
+      "epoch": 2.079131109387122,
+      "grad_norm": 0.2026060497902466,
+      "learning_rate": 2.050593075491031e-05,
+      "loss": 0.4038,
+      "step": 167
+    },
+    {
+      "epoch": 2.091543832428239,
+      "grad_norm": 0.21452873361155297,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.4096,
+      "step": 168
+    },
+    {
+      "epoch": 2.103956555469356,
+      "grad_norm": 0.16506703246465879,
+      "learning_rate": 1.9498299968005393e-05,
+      "loss": 0.4033,
+      "step": 169
+    },
+    {
+      "epoch": 2.116369278510473,
+      "grad_norm": 0.18330461503628598,
+      "learning_rate": 1.90009367866176e-05,
+      "loss": 0.4141,
+      "step": 170
+    },
+    {
+      "epoch": 2.1287820015515906,
+      "grad_norm": 0.17036098721476692,
+      "learning_rate": 1.8508015666127043e-05,
+      "loss": 0.3997,
+      "step": 171
+    },
+    {
+      "epoch": 2.1411947245927077,
+      "grad_norm": 0.1565848493763908,
+      "learning_rate": 1.8019640877167763e-05,
+      "loss": 0.4102,
+      "step": 172
+    },
+    {
+      "epoch": 2.1536074476338247,
+      "grad_norm": 0.15113321296774232,
+      "learning_rate": 1.753591572866029e-05,
+      "loss": 0.4045,
+      "step": 173
+    },
+    {
+      "epoch": 2.166020170674942,
+      "grad_norm": 0.17567587774912344,
+      "learning_rate": 1.7056942545958167e-05,
+      "loss": 0.411,
+      "step": 174
+    },
+    {
+      "epoch": 2.178432893716059,
+      "grad_norm": 0.1514916669173168,
+      "learning_rate": 1.6582822649202382e-05,
+      "loss": 0.4043,
+      "step": 175
+    },
+    {
+      "epoch": 2.190845616757176,
+      "grad_norm": 0.13692215774283953,
+      "learning_rate": 1.6113656331888563e-05,
+      "loss": 0.4081,
+      "step": 176
+    },
+    {
+      "epoch": 2.2032583397982934,
+      "grad_norm": 0.1547902305379429,
+      "learning_rate": 1.5649542839651175e-05,
+      "loss": 0.4059,
+      "step": 177
+    },
+    {
+      "epoch": 2.2156710628394105,
+      "grad_norm": 0.15478961230484406,
+      "learning_rate": 1.5190580349269604e-05,
+      "loss": 0.4118,
+      "step": 178
+    },
+    {
+      "epoch": 2.2280837858805276,
+      "grad_norm": 0.1563215287329166,
+      "learning_rate": 1.4736865947900106e-05,
+      "loss": 0.4059,
+      "step": 179
+    },
+    {
+      "epoch": 2.2404965089216446,
+      "grad_norm": 0.1348428361773952,
+      "learning_rate": 1.4288495612538427e-05,
+      "loss": 0.418,
+      "step": 180
+    },
+    {
+      "epoch": 2.2529092319627617,
+      "grad_norm": 0.15420965802945238,
+      "learning_rate": 1.3845564189717218e-05,
+      "loss": 0.4014,
+      "step": 181
+    },
+    {
+      "epoch": 2.265321955003879,
+      "grad_norm": 0.1370864776868977,
+      "learning_rate": 1.3408165375442486e-05,
+      "loss": 0.4076,
+      "step": 182
+    },
+    {
+      "epoch": 2.2777346780449963,
+      "grad_norm": 0.1382956405855855,
+      "learning_rate": 1.297639169537359e-05,
+      "loss": 0.4117,
+      "step": 183
+    },
+    {
+      "epoch": 2.2901474010861134,
+      "grad_norm": 0.14618626946439975,
+      "learning_rate": 1.2550334485250661e-05,
+      "loss": 0.4074,
+      "step": 184
+    },
+    {
+      "epoch": 2.3025601241272304,
+      "grad_norm": 0.15203645240178526,
+      "learning_rate": 1.2130083871573812e-05,
+      "loss": 0.4106,
+      "step": 185
+    },
+    {
+      "epoch": 2.3149728471683475,
+      "grad_norm": 0.13590418910786364,
+      "learning_rate": 1.1715728752538103e-05,
+      "loss": 0.4068,
+      "step": 186
+    },
+    {
+      "epoch": 2.3273855702094646,
+      "grad_norm": 0.13230060891826068,
+      "learning_rate": 1.130735677922842e-05,
+      "loss": 0.4082,
+      "step": 187
+    },
+    {
+      "epoch": 2.339798293250582,
+      "grad_norm": 0.14626290513171095,
+      "learning_rate": 1.0905054337078051e-05,
+      "loss": 0.4151,
+      "step": 188
+    },
+    {
+      "epoch": 2.352211016291699,
+      "grad_norm": 0.13167282445865477,
+      "learning_rate": 1.0508906527595042e-05,
+      "loss": 0.4043,
+      "step": 189
+    },
+    {
+      "epoch": 2.364623739332816,
+      "grad_norm": 0.13115893719779556,
+      "learning_rate": 1.0118997150360169e-05,
+      "loss": 0.4057,
+      "step": 190
+    },
+    {
+      "epoch": 2.3770364623739333,
+      "grad_norm": 0.1167912265598181,
+      "learning_rate": 9.735408685300287e-06,
+      "loss": 0.4022,
+      "step": 191
+    },
+    {
+      "epoch": 2.3894491854150504,
+      "grad_norm": 0.13650510298957205,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.4047,
+      "step": 192
+    },
+    {
+      "epoch": 2.4018619084561674,
+      "grad_norm": 0.14005131555099598,
+      "learning_rate": 8.987517708741364e-06,
+      "loss": 0.4069,
+      "step": 193
+    },
+    {
+      "epoch": 2.4142746314972845,
+      "grad_norm": 0.13370431951600578,
+      "learning_rate": 8.623373403216972e-06,
+      "loss": 0.4036,
+      "step": 194
+    },
+    {
+      "epoch": 2.426687354538402,
+      "grad_norm": 0.10932322182068067,
+      "learning_rate": 8.265866388350598e-06,
+      "loss": 0.407,
+      "step": 195
+    },
+    {
+      "epoch": 2.439100077579519,
+      "grad_norm": 0.11891911902408805,
+      "learning_rate": 7.915072289798247e-06,
+      "loss": 0.4025,
+      "step": 196
+    },
+    {
+      "epoch": 2.451512800620636,
+      "grad_norm": 0.12169155119506193,
+      "learning_rate": 7.5710653131915125e-06,
+      "loss": 0.4028,
+      "step": 197
+    },
+    {
+      "epoch": 2.463925523661753,
+      "grad_norm": 0.12121517946822892,
+      "learning_rate": 7.233918228440324e-06,
+      "loss": 0.4032,
+      "step": 198
+    },
+    {
+      "epoch": 2.4763382467028703,
+      "grad_norm": 0.11176519152290101,
+      "learning_rate": 6.903702354339578e-06,
+      "loss": 0.3962,
+      "step": 199
+    },
+    {
+      "epoch": 2.488750969743988,
+      "grad_norm": 0.10525267300520544,
+      "learning_rate": 6.58048754348255e-06,
+      "loss": 0.404,
+      "step": 200
+    },
+    {
+      "epoch": 2.501163692785105,
+      "grad_norm": 0.11282045999859883,
+      "learning_rate": 6.26434216748458e-06,
+      "loss": 0.4063,
+      "step": 201
+    },
+    {
+      "epoch": 2.513576415826222,
+      "grad_norm": 0.1059927760955221,
+      "learning_rate": 5.955333102520011e-06,
+      "loss": 0.4098,
+      "step": 202
+    },
+    {
+      "epoch": 2.525989138867339,
+      "grad_norm": 0.11542081949984047,
+      "learning_rate": 5.653525715175483e-06,
+      "loss": 0.4034,
+      "step": 203
+    },
+    {
+      "epoch": 2.538401861908456,
+      "grad_norm": 0.1068575175680495,
+      "learning_rate": 5.358983848622452e-06,
+      "loss": 0.4082,
+      "step": 204
+    },
+    {
+      "epoch": 2.550814584949573,
+      "grad_norm": 0.0998447600600978,
+      "learning_rate": 5.07176980911217e-06,
+      "loss": 0.4032,
+      "step": 205
+    },
+    {
+      "epoch": 2.56322730799069,
+      "grad_norm": 0.10645141895653579,
+      "learning_rate": 4.791944352795561e-06,
+      "loss": 0.4011,
+      "step": 206
+    },
+    {
+      "epoch": 2.5756400310318077,
+      "grad_norm": 0.10626200569289866,
+      "learning_rate": 4.519566672871132e-06,
+      "loss": 0.4102,
+      "step": 207
+    },
+    {
+      "epoch": 2.588052754072925,
+      "grad_norm": 0.11636570353568788,
+      "learning_rate": 4.254694387063514e-06,
+      "loss": 0.4103,
+      "step": 208
+    },
+    {
+      "epoch": 2.600465477114042,
+      "grad_norm": 0.107141998632238,
+      "learning_rate": 3.997383525435154e-06,
+      "loss": 0.4068,
+      "step": 209
+    },
+    {
+      "epoch": 2.612878200155159,
+      "grad_norm": 0.10093732057922751,
+      "learning_rate": 3.747688518534003e-06,
+      "loss": 0.3964,
+      "step": 210
+    },
+    {
+      "epoch": 2.6252909231962764,
+      "grad_norm": 0.10840061896237646,
+      "learning_rate": 3.5056621858794393e-06,
+      "loss": 0.4107,
+      "step": 211
+    },
+    {
+      "epoch": 2.6377036462373935,
+      "grad_norm": 0.10482808960146338,
+      "learning_rate": 3.2713557247890447e-06,
+      "loss": 0.4004,
+      "step": 212
+    },
+    {
+      "epoch": 2.6501163692785106,
+      "grad_norm": 0.09796857797838394,
+      "learning_rate": 3.0448186995485307e-06,
+      "loss": 0.4052,
+      "step": 213
+    },
+    {
+      "epoch": 2.6625290923196276,
+      "grad_norm": 0.09645691066767442,
+      "learning_rate": 2.8260990309270987e-06,
+      "loss": 0.4095,
+      "step": 214
+    },
+    {
+      "epoch": 2.6749418153607447,
+      "grad_norm": 0.08818830792986776,
+      "learning_rate": 2.6152429860404647e-06,
+      "loss": 0.4024,
+      "step": 215
+    },
+    {
+      "epoch": 2.687354538401862,
+      "grad_norm": 0.10461452357891382,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.4053,
+      "step": 216
+    },
+    {
+      "epoch": 2.699767261442979,
+      "grad_norm": 0.0958591909381086,
+      "learning_rate": 2.217298509295813e-06,
+      "loss": 0.4058,
+      "step": 217
+    },
+    {
+      "epoch": 2.7121799844840964,
+      "grad_norm": 0.09454426601563226,
+      "learning_rate": 2.0302942570786446e-06,
+      "loss": 0.4128,
+      "step": 218
+    },
+    {
+      "epoch": 2.7245927075252134,
+      "grad_norm": 0.09870742468169597,
+      "learning_rate": 1.8513219700709272e-06,
+      "loss": 0.4025,
+      "step": 219
+    },
+    {
+      "epoch": 2.7370054305663305,
+      "grad_norm": 0.09548815281206169,
+      "learning_rate": 1.6804195073804442e-06,
+      "loss": 0.4097,
+      "step": 220
+    },
+    {
+      "epoch": 2.7494181536074476,
+      "grad_norm": 0.08898176383898977,
+      "learning_rate": 1.5176230210554744e-06,
+      "loss": 0.4084,
+      "step": 221
+    },
+    {
+      "epoch": 2.7618308766485646,
+      "grad_norm": 0.08380703116347994,
+      "learning_rate": 1.3629669484372722e-06,
+      "loss": 0.4087,
+      "step": 222
+    },
+    {
+      "epoch": 2.774243599689682,
+      "grad_norm": 0.08735931792493482,
+      "learning_rate": 1.2164840048753602e-06,
+      "loss": 0.4045,
+      "step": 223
+    },
+    {
+      "epoch": 2.786656322730799,
+      "grad_norm": 0.08917261448613861,
+      "learning_rate": 1.0782051768070477e-06,
+      "loss": 0.4092,
+      "step": 224
+    },
+    {
+      "epoch": 2.7990690457719163,
+      "grad_norm": 0.09021739845221655,
+      "learning_rate": 9.481597152026656e-07,
+      "loss": 0.4007,
+      "step": 225
+    },
+    {
+      "epoch": 2.8114817688130334,
+      "grad_norm": 0.09225448100194185,
+      "learning_rate": 8.263751293779409e-07,
+      "loss": 0.4058,
+      "step": 226
+    },
+    {
+      "epoch": 2.8238944918541504,
+      "grad_norm": 0.09137600151436115,
+      "learning_rate": 7.128771811747737e-07,
+      "loss": 0.4076,
+      "step": 227
+    },
+    {
+      "epoch": 2.8363072148952675,
+      "grad_norm": 0.08445926239287047,
+      "learning_rate": 6.076898795116792e-07,
+      "loss": 0.4037,
+      "step": 228
+    },
+    {
+      "epoch": 2.8487199379363846,
+      "grad_norm": 0.0855276769278236,
+      "learning_rate": 5.108354753050381e-07,
+      "loss": 0.3925,
+      "step": 229
+    },
+    {
+      "epoch": 2.861132660977502,
+      "grad_norm": 0.09024662389492867,
+      "learning_rate": 4.223344567622212e-07,
+      "loss": 0.4093,
+      "step": 230
+    },
+    {
+      "epoch": 2.873545384018619,
+      "grad_norm": 0.08328959518934888,
+      "learning_rate": 3.4220554504758475e-07,
+      "loss": 0.4058,
+      "step": 231
+    },
+    {
+      "epoch": 2.885958107059736,
+      "grad_norm": 0.07995172675909383,
+      "learning_rate": 2.704656903222791e-07,
+      "loss": 0.4028,
+      "step": 232
+    },
+    {
+      "epoch": 2.8983708301008533,
+      "grad_norm": 0.08216437041993355,
+      "learning_rate": 2.0713006815868075e-07,
+      "loss": 0.4095,
+      "step": 233
+    },
+    {
+      "epoch": 2.910783553141971,
+      "grad_norm": 0.08619940468667671,
+      "learning_rate": 1.522120763301782e-07,
+      "loss": 0.4037,
+      "step": 234
+    },
+    {
+      "epoch": 2.923196276183088,
+      "grad_norm": 0.08312117746203736,
+      "learning_rate": 1.0572333197711005e-07,
+      "loss": 0.4121,
+      "step": 235
+    },
+    {
+      "epoch": 2.935608999224205,
+      "grad_norm": 0.08306970164689674,
+      "learning_rate": 6.767366914927298e-08,
+      "loss": 0.4071,
+      "step": 236
+    },
+    {
+      "epoch": 2.948021722265322,
+      "grad_norm": 0.08356505815113774,
+      "learning_rate": 3.8071136725688074e-08,
+      "loss": 0.4016,
+      "step": 237
+    },
+    {
+      "epoch": 2.960434445306439,
+      "grad_norm": 0.0827393164081486,
+      "learning_rate": 1.6921996711976028e-08,
+      "loss": 0.4033,
+      "step": 238
+    },
+    {
+      "epoch": 2.972847168347556,
+      "grad_norm": 0.08270985499858342,
+      "learning_rate": 4.230722915701257e-09,
+      "loss": 0.402,
+      "step": 239
+    },
+    {
+      "epoch": 2.985259891388673,
+      "grad_norm": 0.08199262003406134,
+      "learning_rate": 0.0,
+      "loss": 0.4036,
+      "step": 240
+    },
+    {
+      "epoch": 2.985259891388673,
+      "step": 240,
+      "total_flos": 6.175913846901834e+18,
+      "train_loss": 0.0,
+      "train_runtime": 7.3353,
+      "train_samples_per_second": 16865.155,
+      "train_steps_per_second": 32.718
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 6.175913846901834e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98cf03fc68bcd6b8339567499d73b9745215e506217086206bd3f3bab7ddb03e
+size 7480