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": 2.9788972089857046,
+    "total_flos": 7.02510214541004e+18,
+    "train_loss": 0.464617241979082,
+    "train_runtime": 57723.5744,
+    "train_samples_per_second": 2.443,
+    "train_steps_per_second": 0.005
+}

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:be8d712c0b4d16f8ed1d18334f67ddf830d8c912bb07b856280cac529185ae3b
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af710f56f9d6fbf388d0df38b66fbfbd471f3f6b67c73d759c882130f7d63e0
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d070496b1cdfcc308d1bcac55a4afdbb170ceec1a9878db235ad7260a8beb5bb
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98706c8eed78ad144bb25d149f647c53364679d2939f70ce17255d696a0b7be
+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": 2.9788972089857046,
+    "total_flos": 7.02510214541004e+18,
+    "train_loss": 0.464617241979082,
+    "train_runtime": 57723.5744,
+    "train_samples_per_second": 2.443,
+    "train_steps_per_second": 0.005
+}

trainer_log.jsonl

@@ -0,0 +1,274 @@
+{"current_steps": 1, "total_steps": 273, "loss": 0.8738, "lr": 2.8571428571428573e-06, "epoch": 0.010891763104152484, "percentage": 0.37, "elapsed_time": "0:04:17", "remaining_time": "19:27:36"}
+{"current_steps": 2, "total_steps": 273, "loss": 0.8637, "lr": 5.7142857142857145e-06, "epoch": 0.021783526208304968, "percentage": 0.73, "elapsed_time": "0:08:01", "remaining_time": "18:07:30"}
+{"current_steps": 3, "total_steps": 273, "loss": 0.8524, "lr": 8.571428571428571e-06, "epoch": 0.03267528931245745, "percentage": 1.1, "elapsed_time": "0:11:34", "remaining_time": "17:21:14"}
+{"current_steps": 4, "total_steps": 273, "loss": 0.783, "lr": 1.1428571428571429e-05, "epoch": 0.043567052416609936, "percentage": 1.47, "elapsed_time": "0:15:05", "remaining_time": "16:54:46"}
+{"current_steps": 5, "total_steps": 273, "loss": 0.7805, "lr": 1.4285714285714287e-05, "epoch": 0.05445881552076242, "percentage": 1.83, "elapsed_time": "0:18:46", "remaining_time": "16:46:10"}
+{"current_steps": 6, "total_steps": 273, "loss": 0.7643, "lr": 1.7142857142857142e-05, "epoch": 0.0653505786249149, "percentage": 2.2, "elapsed_time": "0:22:26", "remaining_time": "16:38:31"}
+{"current_steps": 7, "total_steps": 273, "loss": 0.7512, "lr": 2e-05, "epoch": 0.0762423417290674, "percentage": 2.56, "elapsed_time": "0:26:06", "remaining_time": "16:31:54"}
+{"current_steps": 8, "total_steps": 273, "loss": 0.7182, "lr": 2.2857142857142858e-05, "epoch": 0.08713410483321987, "percentage": 2.93, "elapsed_time": "0:29:44", "remaining_time": "16:25:27"}
+{"current_steps": 9, "total_steps": 273, "loss": 0.6835, "lr": 2.5714285714285718e-05, "epoch": 0.09802586793737236, "percentage": 3.3, "elapsed_time": "0:33:20", "remaining_time": "16:18:15"}
+{"current_steps": 10, "total_steps": 273, "loss": 0.666, "lr": 2.8571428571428574e-05, "epoch": 0.10891763104152484, "percentage": 3.66, "elapsed_time": "0:36:58", "remaining_time": "16:12:15"}
+{"current_steps": 11, "total_steps": 273, "loss": 0.6551, "lr": 3.142857142857143e-05, "epoch": 0.11980939414567733, "percentage": 4.03, "elapsed_time": "0:40:35", "remaining_time": "16:06:48"}
+{"current_steps": 12, "total_steps": 273, "loss": 0.6374, "lr": 3.4285714285714284e-05, "epoch": 0.1307011572498298, "percentage": 4.4, "elapsed_time": "0:44:12", "remaining_time": "16:01:31"}
+{"current_steps": 13, "total_steps": 273, "loss": 0.6142, "lr": 3.714285714285715e-05, "epoch": 0.1415929203539823, "percentage": 4.76, "elapsed_time": "0:47:48", "remaining_time": "15:56:04"}
+{"current_steps": 14, "total_steps": 273, "loss": 0.6085, "lr": 4e-05, "epoch": 0.1524846834581348, "percentage": 5.13, "elapsed_time": "0:51:24", "remaining_time": "15:51:05"}
+{"current_steps": 15, "total_steps": 273, "loss": 0.6168, "lr": 4.2857142857142856e-05, "epoch": 0.16337644656228728, "percentage": 5.49, "elapsed_time": "0:55:03", "remaining_time": "15:46:56"}
+{"current_steps": 16, "total_steps": 273, "loss": 0.5904, "lr": 4.5714285714285716e-05, "epoch": 0.17426820966643974, "percentage": 5.86, "elapsed_time": "0:58:33", "remaining_time": "15:40:40"}
+{"current_steps": 17, "total_steps": 273, "loss": 0.5983, "lr": 4.857142857142857e-05, "epoch": 0.18515997277059223, "percentage": 6.23, "elapsed_time": "1:02:01", "remaining_time": "15:34:00"}
+{"current_steps": 18, "total_steps": 273, "loss": 0.5762, "lr": 5.1428571428571436e-05, "epoch": 0.19605173587474473, "percentage": 6.59, "elapsed_time": "1:05:39", "remaining_time": "15:30:08"}
+{"current_steps": 19, "total_steps": 273, "loss": 0.5794, "lr": 5.4285714285714295e-05, "epoch": 0.20694349897889722, "percentage": 6.96, "elapsed_time": "1:09:18", "remaining_time": "15:26:31"}
+{"current_steps": 20, "total_steps": 273, "loss": 0.5723, "lr": 5.714285714285715e-05, "epoch": 0.21783526208304968, "percentage": 7.33, "elapsed_time": "1:12:56", "remaining_time": "15:22:45"}
+{"current_steps": 21, "total_steps": 273, "loss": 0.576, "lr": 6.000000000000001e-05, "epoch": 0.22872702518720217, "percentage": 7.69, "elapsed_time": "1:16:36", "remaining_time": "15:19:13"}
+{"current_steps": 22, "total_steps": 273, "loss": 0.5657, "lr": 6.285714285714286e-05, "epoch": 0.23961878829135466, "percentage": 8.06, "elapsed_time": "1:20:12", "remaining_time": "15:15:05"}
+{"current_steps": 23, "total_steps": 273, "loss": 0.5751, "lr": 6.571428571428571e-05, "epoch": 0.25051055139550715, "percentage": 8.42, "elapsed_time": "1:23:53", "remaining_time": "15:11:49"}
+{"current_steps": 24, "total_steps": 273, "loss": 0.5622, "lr": 6.857142857142857e-05, "epoch": 0.2614023144996596, "percentage": 8.79, "elapsed_time": "1:27:32", "remaining_time": "15:08:15"}
+{"current_steps": 25, "total_steps": 273, "loss": 0.553, "lr": 7.142857142857143e-05, "epoch": 0.27229407760381213, "percentage": 9.16, "elapsed_time": "1:31:09", "remaining_time": "15:04:15"}
+{"current_steps": 26, "total_steps": 273, "loss": 0.5746, "lr": 7.42857142857143e-05, "epoch": 0.2831858407079646, "percentage": 9.52, "elapsed_time": "1:34:45", "remaining_time": "15:00:13"}
+{"current_steps": 27, "total_steps": 273, "loss": 0.5504, "lr": 7.714285714285715e-05, "epoch": 0.29407760381211706, "percentage": 9.89, "elapsed_time": "1:38:21", "remaining_time": "14:56:08"}
+{"current_steps": 28, "total_steps": 273, "loss": 0.5542, "lr": 8e-05, "epoch": 0.3049693669162696, "percentage": 10.26, "elapsed_time": "1:42:00", "remaining_time": "14:52:31"}
+{"current_steps": 29, "total_steps": 273, "loss": 0.5507, "lr": 7.999671154713278e-05, "epoch": 0.31586113002042204, "percentage": 10.62, "elapsed_time": "1:45:29", "remaining_time": "14:47:35"}
+{"current_steps": 30, "total_steps": 273, "loss": 0.5496, "lr": 7.99868467292272e-05, "epoch": 0.32675289312457456, "percentage": 10.99, "elapsed_time": "1:48:58", "remaining_time": "14:42:45"}
+{"current_steps": 31, "total_steps": 273, "loss": 0.5575, "lr": 7.997040716828271e-05, "epoch": 0.337644656228727, "percentage": 11.36, "elapsed_time": "1:52:34", "remaining_time": "14:38:48"}
+{"current_steps": 32, "total_steps": 273, "loss": 0.5596, "lr": 7.994739556733538e-05, "epoch": 0.3485364193328795, "percentage": 11.72, "elapsed_time": "1:56:10", "remaining_time": "14:34:54"}
+{"current_steps": 33, "total_steps": 273, "loss": 0.5337, "lr": 7.991781571001347e-05, "epoch": 0.359428182437032, "percentage": 12.09, "elapsed_time": "1:59:46", "remaining_time": "14:31:08"}
+{"current_steps": 34, "total_steps": 273, "loss": 0.5492, "lr": 7.988167245991528e-05, "epoch": 0.37031994554118447, "percentage": 12.45, "elapsed_time": "2:03:22", "remaining_time": "14:27:14"}
+{"current_steps": 35, "total_steps": 273, "loss": 0.5314, "lr": 7.983897175980957e-05, "epoch": 0.381211708645337, "percentage": 12.82, "elapsed_time": "2:06:58", "remaining_time": "14:23:27"}
+{"current_steps": 36, "total_steps": 273, "loss": 0.5307, "lr": 7.97897206306583e-05, "epoch": 0.39210347174948945, "percentage": 13.19, "elapsed_time": "2:10:34", "remaining_time": "14:19:35"}
+{"current_steps": 37, "total_steps": 273, "loss": 0.5408, "lr": 7.973392717046233e-05, "epoch": 0.4029952348536419, "percentage": 13.55, "elapsed_time": "2:14:07", "remaining_time": "14:15:27"}
+{"current_steps": 38, "total_steps": 273, "loss": 0.5147, "lr": 7.967160055292984e-05, "epoch": 0.41388699795779443, "percentage": 13.92, "elapsed_time": "2:17:40", "remaining_time": "14:11:24"}
+{"current_steps": 39, "total_steps": 273, "loss": 0.5216, "lr": 7.960275102596809e-05, "epoch": 0.4247787610619469, "percentage": 14.29, "elapsed_time": "2:21:13", "remaining_time": "14:07:21"}
+{"current_steps": 40, "total_steps": 273, "loss": 0.5187, "lr": 7.952738990999824e-05, "epoch": 0.43567052416609936, "percentage": 14.65, "elapsed_time": "2:24:50", "remaining_time": "14:03:44"}
+{"current_steps": 41, "total_steps": 273, "loss": 0.5123, "lr": 7.94455295960942e-05, "epoch": 0.4465622872702519, "percentage": 15.02, "elapsed_time": "2:28:26", "remaining_time": "13:59:55"}
+{"current_steps": 42, "total_steps": 273, "loss": 0.5255, "lr": 7.93571835439452e-05, "epoch": 0.45745405037440434, "percentage": 15.38, "elapsed_time": "2:31:51", "remaining_time": "13:55:15"}
+{"current_steps": 43, "total_steps": 273, "loss": 0.5224, "lr": 7.926236627964262e-05, "epoch": 0.46834581347855686, "percentage": 15.75, "elapsed_time": "2:35:26", "remaining_time": "13:51:25"}
+{"current_steps": 44, "total_steps": 273, "loss": 0.5104, "lr": 7.916109339329173e-05, "epoch": 0.4792375765827093, "percentage": 16.12, "elapsed_time": "2:39:00", "remaining_time": "13:47:34"}
+{"current_steps": 45, "total_steps": 273, "loss": 0.5036, "lr": 7.905338153644818e-05, "epoch": 0.4901293396868618, "percentage": 16.48, "elapsed_time": "2:42:34", "remaining_time": "13:43:44"}
+{"current_steps": 46, "total_steps": 273, "loss": 0.5169, "lr": 7.89392484193802e-05, "epoch": 0.5010211027910143, "percentage": 16.85, "elapsed_time": "2:46:11", "remaining_time": "13:40:08"}
+{"current_steps": 47, "total_steps": 273, "loss": 0.5071, "lr": 7.881871280815659e-05, "epoch": 0.5119128658951668, "percentage": 17.22, "elapsed_time": "2:49:45", "remaining_time": "13:36:17"}
+{"current_steps": 48, "total_steps": 273, "loss": 0.5093, "lr": 7.869179452156118e-05, "epoch": 0.5228046289993192, "percentage": 17.58, "elapsed_time": "2:53:20", "remaining_time": "13:32:31"}
+{"current_steps": 49, "total_steps": 273, "loss": 0.501, "lr": 7.855851442783414e-05, "epoch": 0.5336963921034718, "percentage": 17.95, "elapsed_time": "2:56:55", "remaining_time": "13:28:46"}
+{"current_steps": 50, "total_steps": 273, "loss": 0.4997, "lr": 7.841889444124078e-05, "epoch": 0.5445881552076243, "percentage": 18.32, "elapsed_time": "3:00:30", "remaining_time": "13:25:04"}
+{"current_steps": 51, "total_steps": 273, "loss": 0.5151, "lr": 7.827295751846836e-05, "epoch": 0.5554799183117767, "percentage": 18.68, "elapsed_time": "3:04:04", "remaining_time": "13:21:17"}
+{"current_steps": 52, "total_steps": 273, "loss": 0.512, "lr": 7.81207276548515e-05, "epoch": 0.5663716814159292, "percentage": 19.05, "elapsed_time": "3:07:40", "remaining_time": "13:17:36"}
+{"current_steps": 53, "total_steps": 273, "loss": 0.5247, "lr": 7.796222988042676e-05, "epoch": 0.5772634445200817, "percentage": 19.41, "elapsed_time": "3:11:18", "remaining_time": "13:14:05"}
+{"current_steps": 54, "total_steps": 273, "loss": 0.5161, "lr": 7.779749025581717e-05, "epoch": 0.5881552076242341, "percentage": 19.78, "elapsed_time": "3:14:43", "remaining_time": "13:09:44"}
+{"current_steps": 55, "total_steps": 273, "loss": 0.5113, "lr": 7.762653586794731e-05, "epoch": 0.5990469707283866, "percentage": 20.15, "elapsed_time": "3:18:18", "remaining_time": "13:06:02"}
+{"current_steps": 56, "total_steps": 273, "loss": 0.5104, "lr": 7.74493948255895e-05, "epoch": 0.6099387338325392, "percentage": 20.51, "elapsed_time": "3:21:51", "remaining_time": "13:02:11"}
+{"current_steps": 57, "total_steps": 273, "loss": 0.5149, "lr": 7.726609625474218e-05, "epoch": 0.6208304969366917, "percentage": 20.88, "elapsed_time": "3:25:26", "remaining_time": "12:58:30"}
+{"current_steps": 58, "total_steps": 273, "loss": 0.4985, "lr": 7.707667029384088e-05, "epoch": 0.6317222600408441, "percentage": 21.25, "elapsed_time": "3:29:00", "remaining_time": "12:54:45"}
+{"current_steps": 59, "total_steps": 273, "loss": 0.515, "lr": 7.688114808880283e-05, "epoch": 0.6426140231449966, "percentage": 21.61, "elapsed_time": "3:32:34", "remaining_time": "12:51:00"}
+{"current_steps": 60, "total_steps": 273, "loss": 0.5059, "lr": 7.667956178790582e-05, "epoch": 0.6535057862491491, "percentage": 21.98, "elapsed_time": "3:36:06", "remaining_time": "12:47:11"}
+{"current_steps": 61, "total_steps": 273, "loss": 0.4935, "lr": 7.647194453650228e-05, "epoch": 0.6643975493533015, "percentage": 22.34, "elapsed_time": "3:39:40", "remaining_time": "12:43:28"}
+{"current_steps": 62, "total_steps": 273, "loss": 0.5058, "lr": 7.625833047156953e-05, "epoch": 0.675289312457454, "percentage": 22.71, "elapsed_time": "3:43:14", "remaining_time": "12:39:44"}
+{"current_steps": 63, "total_steps": 273, "loss": 0.4903, "lr": 7.603875471609677e-05, "epoch": 0.6861810755616066, "percentage": 23.08, "elapsed_time": "3:46:49", "remaining_time": "12:36:03"}
+{"current_steps": 64, "total_steps": 273, "loss": 0.497, "lr": 7.581325337331013e-05, "epoch": 0.697072838665759, "percentage": 23.44, "elapsed_time": "3:50:23", "remaining_time": "12:32:23"}
+{"current_steps": 65, "total_steps": 273, "loss": 0.4874, "lr": 7.558186352073648e-05, "epoch": 0.7079646017699115, "percentage": 23.81, "elapsed_time": "3:53:53", "remaining_time": "12:28:27"}
+{"current_steps": 66, "total_steps": 273, "loss": 0.4957, "lr": 7.534462320410702e-05, "epoch": 0.718856364874064, "percentage": 24.18, "elapsed_time": "3:57:23", "remaining_time": "12:24:33"}
+{"current_steps": 67, "total_steps": 273, "loss": 0.4976, "lr": 7.510157143110172e-05, "epoch": 0.7297481279782164, "percentage": 24.54, "elapsed_time": "4:00:56", "remaining_time": "12:20:49"}
+{"current_steps": 68, "total_steps": 273, "loss": 0.4959, "lr": 7.485274816493558e-05, "epoch": 0.7406398910823689, "percentage": 24.91, "elapsed_time": "4:04:29", "remaining_time": "12:17:04"}
+{"current_steps": 69, "total_steps": 273, "loss": 0.4796, "lr": 7.459819431778775e-05, "epoch": 0.7515316541865215, "percentage": 25.27, "elapsed_time": "4:08:04", "remaining_time": "12:13:27"}
+{"current_steps": 70, "total_steps": 273, "loss": 0.4762, "lr": 7.433795174407465e-05, "epoch": 0.762423417290674, "percentage": 25.64, "elapsed_time": "4:11:37", "remaining_time": "12:09:41"}
+{"current_steps": 71, "total_steps": 273, "loss": 0.4955, "lr": 7.407206323356818e-05, "epoch": 0.7733151803948264, "percentage": 26.01, "elapsed_time": "4:15:11", "remaining_time": "12:06:02"}
+{"current_steps": 72, "total_steps": 273, "loss": 0.4945, "lr": 7.380057250436006e-05, "epoch": 0.7842069434989789, "percentage": 26.37, "elapsed_time": "4:18:44", "remaining_time": "12:02:17"}
+{"current_steps": 73, "total_steps": 273, "loss": 0.4883, "lr": 7.352352419567362e-05, "epoch": 0.7950987066031314, "percentage": 26.74, "elapsed_time": "4:22:17", "remaining_time": "11:58:35"}
+{"current_steps": 74, "total_steps": 273, "loss": 0.4906, "lr": 7.324096386052416e-05, "epoch": 0.8059904697072838, "percentage": 27.11, "elapsed_time": "4:25:52", "remaining_time": "11:54:59"}
+{"current_steps": 75, "total_steps": 273, "loss": 0.4838, "lr": 7.295293795822887e-05, "epoch": 0.8168822328114363, "percentage": 27.47, "elapsed_time": "4:29:26", "remaining_time": "11:51:18"}
+{"current_steps": 76, "total_steps": 273, "loss": 0.4815, "lr": 7.265949384676795e-05, "epoch": 0.8277739959155889, "percentage": 27.84, "elapsed_time": "4:32:54", "remaining_time": "11:47:25"}
+{"current_steps": 77, "total_steps": 273, "loss": 0.4855, "lr": 7.236067977499791e-05, "epoch": 0.8386657590197413, "percentage": 28.21, "elapsed_time": "4:36:29", "remaining_time": "11:43:46"}
+{"current_steps": 78, "total_steps": 273, "loss": 0.4811, "lr": 7.205654487471826e-05, "epoch": 0.8495575221238938, "percentage": 28.57, "elapsed_time": "4:40:03", "remaining_time": "11:40:08"}
+{"current_steps": 79, "total_steps": 273, "loss": 0.4889, "lr": 7.174713915259331e-05, "epoch": 0.8604492852280463, "percentage": 28.94, "elapsed_time": "4:43:36", "remaining_time": "11:36:26"}
+{"current_steps": 80, "total_steps": 273, "loss": 0.488, "lr": 7.143251348192971e-05, "epoch": 0.8713410483321987, "percentage": 29.3, "elapsed_time": "4:47:10", "remaining_time": "11:32:49"}
+{"current_steps": 81, "total_steps": 273, "loss": 0.4859, "lr": 7.111271959431189e-05, "epoch": 0.8822328114363512, "percentage": 29.67, "elapsed_time": "4:50:44", "remaining_time": "11:29:10"}
+{"current_steps": 82, "total_steps": 273, "loss": 0.4803, "lr": 7.078781007109625e-05, "epoch": 0.8931245745405038, "percentage": 30.04, "elapsed_time": "4:54:18", "remaining_time": "11:25:30"}
+{"current_steps": 83, "total_steps": 273, "loss": 0.4733, "lr": 7.045783833476538e-05, "epoch": 0.9040163376446563, "percentage": 30.4, "elapsed_time": "4:57:52", "remaining_time": "11:21:51"}
+{"current_steps": 84, "total_steps": 273, "loss": 0.4726, "lr": 7.012285864014445e-05, "epoch": 0.9149081007488087, "percentage": 30.77, "elapsed_time": "5:01:25", "remaining_time": "11:18:12"}
+{"current_steps": 85, "total_steps": 273, "loss": 0.4817, "lr": 6.978292606548029e-05, "epoch": 0.9257998638529612, "percentage": 31.14, "elapsed_time": "5:04:58", "remaining_time": "11:14:31"}
+{"current_steps": 86, "total_steps": 273, "loss": 0.4856, "lr": 6.943809650338541e-05, "epoch": 0.9366916269571137, "percentage": 31.5, "elapsed_time": "5:08:31", "remaining_time": "11:10:51"}
+{"current_steps": 87, "total_steps": 273, "loss": 0.4893, "lr": 6.908842665164789e-05, "epoch": 0.9475833900612661, "percentage": 31.87, "elapsed_time": "5:11:58", "remaining_time": "11:06:59"}
+{"current_steps": 88, "total_steps": 273, "loss": 0.4749, "lr": 6.873397400390911e-05, "epoch": 0.9584751531654186, "percentage": 32.23, "elapsed_time": "5:15:29", "remaining_time": "11:03:14"}
+{"current_steps": 89, "total_steps": 273, "loss": 0.4642, "lr": 6.837479684021032e-05, "epoch": 0.9693669162695712, "percentage": 32.6, "elapsed_time": "5:19:02", "remaining_time": "10:59:35"}
+{"current_steps": 90, "total_steps": 273, "loss": 0.4721, "lr": 6.80109542174102e-05, "epoch": 0.9802586793737236, "percentage": 32.97, "elapsed_time": "5:22:34", "remaining_time": "10:55:54"}
+{"current_steps": 91, "total_steps": 273, "loss": 0.471, "lr": 6.76425059594746e-05, "epoch": 0.9911504424778761, "percentage": 33.33, "elapsed_time": "5:26:08", "remaining_time": "10:52:16"}
+{"current_steps": 92, "total_steps": 273, "loss": 0.4723, "lr": 6.726951264763998e-05, "epoch": 1.0047651463580667, "percentage": 33.7, "elapsed_time": "5:31:00", "remaining_time": "10:51:12"}
+{"current_steps": 93, "total_steps": 273, "loss": 0.4562, "lr": 6.689203561045268e-05, "epoch": 1.0156569094622192, "percentage": 34.07, "elapsed_time": "5:34:33", "remaining_time": "10:47:32"}
+{"current_steps": 94, "total_steps": 273, "loss": 0.4599, "lr": 6.651013691368492e-05, "epoch": 1.0265486725663717, "percentage": 34.43, "elapsed_time": "5:38:06", "remaining_time": "10:43:51"}
+{"current_steps": 95, "total_steps": 273, "loss": 0.4586, "lr": 6.612387935012995e-05, "epoch": 1.0374404356705242, "percentage": 34.8, "elapsed_time": "5:41:38", "remaining_time": "10:40:07"}
+{"current_steps": 96, "total_steps": 273, "loss": 0.4564, "lr": 6.573332642927737e-05, "epoch": 1.0483321987746765, "percentage": 35.16, "elapsed_time": "5:45:09", "remaining_time": "10:36:24"}
+{"current_steps": 97, "total_steps": 273, "loss": 0.4532, "lr": 6.53385423668708e-05, "epoch": 1.059223961878829, "percentage": 35.53, "elapsed_time": "5:48:43", "remaining_time": "10:32:44"}
+{"current_steps": 98, "total_steps": 273, "loss": 0.4518, "lr": 6.493959207434934e-05, "epoch": 1.0701157249829816, "percentage": 35.9, "elapsed_time": "5:52:11", "remaining_time": "10:28:54"}
+{"current_steps": 99, "total_steps": 273, "loss": 0.4602, "lr": 6.453654114817467e-05, "epoch": 1.081007488087134, "percentage": 36.26, "elapsed_time": "5:55:43", "remaining_time": "10:25:13"}
+{"current_steps": 100, "total_steps": 273, "loss": 0.4706, "lr": 6.412945585904545e-05, "epoch": 1.0918992511912866, "percentage": 36.63, "elapsed_time": "5:59:19", "remaining_time": "10:21:37"}
+{"current_steps": 101, "total_steps": 273, "loss": 0.4746, "lr": 6.371840314100104e-05, "epoch": 1.1027910142954391, "percentage": 37.0, "elapsed_time": "6:02:52", "remaining_time": "10:17:57"}
+{"current_steps": 102, "total_steps": 273, "loss": 0.4645, "lr": 6.330345058041585e-05, "epoch": 1.1136827773995917, "percentage": 37.36, "elapsed_time": "6:06:25", "remaining_time": "10:14:18"}
+{"current_steps": 103, "total_steps": 273, "loss": 0.4574, "lr": 6.288466640488679e-05, "epoch": 1.124574540503744, "percentage": 37.73, "elapsed_time": "6:09:58", "remaining_time": "10:10:39"}
+{"current_steps": 104, "total_steps": 273, "loss": 0.453, "lr": 6.2462119472015e-05, "epoch": 1.1354663036078965, "percentage": 38.1, "elapsed_time": "6:13:31", "remaining_time": "10:06:59"}
+{"current_steps": 105, "total_steps": 273, "loss": 0.4562, "lr": 6.20358792580841e-05, "epoch": 1.146358066712049, "percentage": 38.46, "elapsed_time": "6:17:05", "remaining_time": "10:03:20"}
+{"current_steps": 106, "total_steps": 273, "loss": 0.4544, "lr": 6.160601584663681e-05, "epoch": 1.1572498298162015, "percentage": 38.83, "elapsed_time": "6:20:40", "remaining_time": "9:59:43"}
+{"current_steps": 107, "total_steps": 273, "loss": 0.4567, "lr": 6.11725999169515e-05, "epoch": 1.168141592920354, "percentage": 39.19, "elapsed_time": "6:24:12", "remaining_time": "9:56:04"}
+{"current_steps": 108, "total_steps": 273, "loss": 0.4537, "lr": 6.0735702732421015e-05, "epoch": 1.1790333560245065, "percentage": 39.56, "elapsed_time": "6:27:45", "remaining_time": "9:52:24"}
+{"current_steps": 109, "total_steps": 273, "loss": 0.4514, "lr": 6.029539612883529e-05, "epoch": 1.189925119128659, "percentage": 39.93, "elapsed_time": "6:31:10", "remaining_time": "9:48:33"}
+{"current_steps": 110, "total_steps": 273, "loss": 0.4462, "lr": 5.9851752502570015e-05, "epoch": 1.2008168822328114, "percentage": 40.29, "elapsed_time": "6:34:42", "remaining_time": "9:44:53"}
+{"current_steps": 111, "total_steps": 273, "loss": 0.4456, "lr": 5.940484479868288e-05, "epoch": 1.2117086453369639, "percentage": 40.66, "elapsed_time": "6:38:16", "remaining_time": "9:41:15"}
+{"current_steps": 112, "total_steps": 273, "loss": 0.4441, "lr": 5.895474649891995e-05, "epoch": 1.2226004084411164, "percentage": 41.03, "elapsed_time": "6:41:50", "remaining_time": "9:37:38"}
+{"current_steps": 113, "total_steps": 273, "loss": 0.4463, "lr": 5.8501531609633424e-05, "epoch": 1.233492171545269, "percentage": 41.39, "elapsed_time": "6:45:24", "remaining_time": "9:34:01"}
+{"current_steps": 114, "total_steps": 273, "loss": 0.4424, "lr": 5.8045274649613386e-05, "epoch": 1.2443839346494214, "percentage": 41.76, "elapsed_time": "6:48:58", "remaining_time": "9:30:24"}
+{"current_steps": 115, "total_steps": 273, "loss": 0.4459, "lr": 5.7586050637835295e-05, "epoch": 1.2552756977535737, "percentage": 42.12, "elapsed_time": "6:52:31", "remaining_time": "9:26:46"}
+{"current_steps": 116, "total_steps": 273, "loss": 0.4408, "lr": 5.7123935081125034e-05, "epoch": 1.2661674608577265, "percentage": 42.49, "elapsed_time": "6:56:04", "remaining_time": "9:23:08"}
+{"current_steps": 117, "total_steps": 273, "loss": 0.4455, "lr": 5.6659003961743965e-05, "epoch": 1.2770592239618788, "percentage": 42.86, "elapsed_time": "6:59:37", "remaining_time": "9:19:29"}
+{"current_steps": 118, "total_steps": 273, "loss": 0.4362, "lr": 5.619133372489575e-05, "epoch": 1.2879509870660313, "percentage": 43.22, "elapsed_time": "7:03:03", "remaining_time": "9:15:43"}
+{"current_steps": 119, "total_steps": 273, "loss": 0.4483, "lr": 5.572100126615695e-05, "epoch": 1.2988427501701838, "percentage": 43.59, "elapsed_time": "7:06:32", "remaining_time": "9:12:00"}
+{"current_steps": 120, "total_steps": 273, "loss": 0.4488, "lr": 5.524808391883367e-05, "epoch": 1.3097345132743363, "percentage": 43.96, "elapsed_time": "7:10:00", "remaining_time": "9:08:15"}
+{"current_steps": 121, "total_steps": 273, "loss": 0.4466, "lr": 5.477265944124626e-05, "epoch": 1.3206262763784888, "percentage": 44.32, "elapsed_time": "7:13:23", "remaining_time": "9:04:26"}
+{"current_steps": 122, "total_steps": 273, "loss": 0.4455, "lr": 5.429480600394405e-05, "epoch": 1.3315180394826411, "percentage": 44.69, "elapsed_time": "7:16:45", "remaining_time": "9:00:35"}
+{"current_steps": 123, "total_steps": 273, "loss": 0.4409, "lr": 5.381460217685231e-05, "epoch": 1.3424098025867937, "percentage": 45.05, "elapsed_time": "7:20:07", "remaining_time": "8:56:44"}
+{"current_steps": 124, "total_steps": 273, "loss": 0.4368, "lr": 5.333212691635368e-05, "epoch": 1.3533015656909462, "percentage": 45.42, "elapsed_time": "7:23:29", "remaining_time": "8:52:54"}
+{"current_steps": 125, "total_steps": 273, "loss": 0.4414, "lr": 5.2847459552305834e-05, "epoch": 1.3641933287950987, "percentage": 45.79, "elapsed_time": "7:26:52", "remaining_time": "8:49:05"}
+{"current_steps": 126, "total_steps": 273, "loss": 0.4342, "lr": 5.23606797749979e-05, "epoch": 1.3750850918992512, "percentage": 46.15, "elapsed_time": "7:30:17", "remaining_time": "8:45:20"}
+{"current_steps": 127, "total_steps": 273, "loss": 0.4349, "lr": 5.1871867622047624e-05, "epoch": 1.3859768550034037, "percentage": 46.52, "elapsed_time": "7:33:39", "remaining_time": "8:41:32"}
+{"current_steps": 128, "total_steps": 273, "loss": 0.4359, "lr": 5.13811034652413e-05, "epoch": 1.3968686181075562, "percentage": 46.89, "elapsed_time": "7:37:04", "remaining_time": "8:37:46"}
+{"current_steps": 129, "total_steps": 273, "loss": 0.4449, "lr": 5.088846799731885e-05, "epoch": 1.4077603812117085, "percentage": 47.25, "elapsed_time": "7:40:25", "remaining_time": "8:33:58"}
+{"current_steps": 130, "total_steps": 273, "loss": 0.4384, "lr": 5.039404221870612e-05, "epoch": 1.418652144315861, "percentage": 47.62, "elapsed_time": "7:43:48", "remaining_time": "8:30:10"}
+{"current_steps": 131, "total_steps": 273, "loss": 0.4391, "lr": 4.989790742419658e-05, "epoch": 1.4295439074200136, "percentage": 47.99, "elapsed_time": "7:47:10", "remaining_time": "8:26:23"}
+{"current_steps": 132, "total_steps": 273, "loss": 0.435, "lr": 4.940014518958461e-05, "epoch": 1.440435670524166, "percentage": 48.35, "elapsed_time": "7:50:34", "remaining_time": "8:22:39"}
+{"current_steps": 133, "total_steps": 273, "loss": 0.4423, "lr": 4.890083735825258e-05, "epoch": 1.4513274336283186, "percentage": 48.72, "elapsed_time": "7:53:59", "remaining_time": "8:18:56"}
+{"current_steps": 134, "total_steps": 273, "loss": 0.4373, "lr": 4.8400066027713974e-05, "epoch": 1.4622191967324711, "percentage": 49.08, "elapsed_time": "7:57:22", "remaining_time": "8:15:11"}
+{"current_steps": 135, "total_steps": 273, "loss": 0.441, "lr": 4.789791353611469e-05, "epoch": 1.4731109598366237, "percentage": 49.45, "elapsed_time": "8:00:44", "remaining_time": "8:11:25"}
+{"current_steps": 136, "total_steps": 273, "loss": 0.4392, "lr": 4.7394462448694756e-05, "epoch": 1.484002722940776, "percentage": 49.82, "elapsed_time": "8:04:07", "remaining_time": "8:07:40"}
+{"current_steps": 137, "total_steps": 273, "loss": 0.4437, "lr": 4.688979554421276e-05, "epoch": 1.4948944860449285, "percentage": 50.18, "elapsed_time": "8:07:31", "remaining_time": "8:03:57"}
+{"current_steps": 138, "total_steps": 273, "loss": 0.4448, "lr": 4.6383995801335176e-05, "epoch": 1.505786249149081, "percentage": 50.55, "elapsed_time": "8:10:54", "remaining_time": "8:00:13"}
+{"current_steps": 139, "total_steps": 273, "loss": 0.4431, "lr": 4.5877146384992725e-05, "epoch": 1.5166780122532335, "percentage": 50.92, "elapsed_time": "8:14:21", "remaining_time": "7:56:34"}
+{"current_steps": 140, "total_steps": 273, "loss": 0.4331, "lr": 4.5369330632706223e-05, "epoch": 1.527569775357386, "percentage": 51.28, "elapsed_time": "8:17:45", "remaining_time": "7:52:52"}
+{"current_steps": 141, "total_steps": 273, "loss": 0.4433, "lr": 4.486063204088402e-05, "epoch": 1.5384615384615383, "percentage": 51.65, "elapsed_time": "8:21:08", "remaining_time": "7:49:08"}
+{"current_steps": 142, "total_steps": 273, "loss": 0.4337, "lr": 4.435113425109324e-05, "epoch": 1.549353301565691, "percentage": 52.01, "elapsed_time": "8:24:31", "remaining_time": "7:45:26"}
+{"current_steps": 143, "total_steps": 273, "loss": 0.4387, "lr": 4.3840921036307274e-05, "epoch": 1.5602450646698434, "percentage": 52.38, "elapsed_time": "8:27:53", "remaining_time": "7:41:43"}
+{"current_steps": 144, "total_steps": 273, "loss": 0.4333, "lr": 4.333007628713158e-05, "epoch": 1.5711368277739959, "percentage": 52.75, "elapsed_time": "8:31:15", "remaining_time": "7:37:59"}
+{"current_steps": 145, "total_steps": 273, "loss": 0.4375, "lr": 4.281868399801016e-05, "epoch": 1.5820285908781484, "percentage": 53.11, "elapsed_time": "8:34:37", "remaining_time": "7:34:16"}
+{"current_steps": 146, "total_steps": 273, "loss": 0.4331, "lr": 4.230682825341498e-05, "epoch": 1.592920353982301, "percentage": 53.48, "elapsed_time": "8:38:02", "remaining_time": "7:30:37"}
+{"current_steps": 147, "total_steps": 273, "loss": 0.4432, "lr": 4.17945932140206e-05, "epoch": 1.6038121170864534, "percentage": 53.85, "elapsed_time": "8:41:27", "remaining_time": "7:26:57"}
+{"current_steps": 148, "total_steps": 273, "loss": 0.433, "lr": 4.128206310286622e-05, "epoch": 1.6147038801906057, "percentage": 54.21, "elapsed_time": "8:44:52", "remaining_time": "7:23:18"}
+{"current_steps": 149, "total_steps": 273, "loss": 0.4291, "lr": 4.0769322191507485e-05, "epoch": 1.6255956432947585, "percentage": 54.58, "elapsed_time": "8:48:15", "remaining_time": "7:19:37"}
+{"current_steps": 150, "total_steps": 273, "loss": 0.4479, "lr": 4.025645478616045e-05, "epoch": 1.6364874063989108, "percentage": 54.95, "elapsed_time": "8:51:36", "remaining_time": "7:15:55"}
+{"current_steps": 151, "total_steps": 273, "loss": 0.4305, "lr": 3.974354521383956e-05, "epoch": 1.6473791695030633, "percentage": 55.31, "elapsed_time": "8:55:00", "remaining_time": "7:12:15"}
+{"current_steps": 152, "total_steps": 273, "loss": 0.4341, "lr": 3.923067780849252e-05, "epoch": 1.6582709326072158, "percentage": 55.68, "elapsed_time": "8:58:21", "remaining_time": "7:08:34"}
+{"current_steps": 153, "total_steps": 273, "loss": 0.4332, "lr": 3.87179368971338e-05, "epoch": 1.6691626957113683, "percentage": 56.04, "elapsed_time": "9:01:47", "remaining_time": "7:04:55"}
+{"current_steps": 154, "total_steps": 273, "loss": 0.4324, "lr": 3.820540678597942e-05, "epoch": 1.6800544588155208, "percentage": 56.41, "elapsed_time": "9:05:09", "remaining_time": "7:01:15"}
+{"current_steps": 155, "total_steps": 273, "loss": 0.4289, "lr": 3.769317174658503e-05, "epoch": 1.6909462219196731, "percentage": 56.78, "elapsed_time": "9:08:31", "remaining_time": "6:57:35"}
+{"current_steps": 156, "total_steps": 273, "loss": 0.4414, "lr": 3.718131600198984e-05, "epoch": 1.7018379850238259, "percentage": 57.14, "elapsed_time": "9:11:54", "remaining_time": "6:53:55"}
+{"current_steps": 157, "total_steps": 273, "loss": 0.4341, "lr": 3.666992371286843e-05, "epoch": 1.7127297481279782, "percentage": 57.51, "elapsed_time": "9:15:17", "remaining_time": "6:50:16"}
+{"current_steps": 158, "total_steps": 273, "loss": 0.4391, "lr": 3.615907896369273e-05, "epoch": 1.7236215112321307, "percentage": 57.88, "elapsed_time": "9:18:40", "remaining_time": "6:46:37"}
+{"current_steps": 159, "total_steps": 273, "loss": 0.4368, "lr": 3.564886574890677e-05, "epoch": 1.7345132743362832, "percentage": 58.24, "elapsed_time": "9:22:02", "remaining_time": "6:42:58"}
+{"current_steps": 160, "total_steps": 273, "loss": 0.4362, "lr": 3.5139367959115986e-05, "epoch": 1.7454050374404355, "percentage": 58.61, "elapsed_time": "9:25:24", "remaining_time": "6:39:19"}
+{"current_steps": 161, "total_steps": 273, "loss": 0.4321, "lr": 3.4630669367293797e-05, "epoch": 1.7562968005445883, "percentage": 58.97, "elapsed_time": "9:28:46", "remaining_time": "6:35:40"}
+{"current_steps": 162, "total_steps": 273, "loss": 0.4327, "lr": 3.412285361500729e-05, "epoch": 1.7671885636487406, "percentage": 59.34, "elapsed_time": "9:32:10", "remaining_time": "6:32:02"}
+{"current_steps": 163, "total_steps": 273, "loss": 0.4324, "lr": 3.3616004198664845e-05, "epoch": 1.778080326752893, "percentage": 59.71, "elapsed_time": "9:35:33", "remaining_time": "6:28:24"}
+{"current_steps": 164, "total_steps": 273, "loss": 0.4377, "lr": 3.311020445578725e-05, "epoch": 1.7889720898570456, "percentage": 60.07, "elapsed_time": "9:38:56", "remaining_time": "6:24:47"}
+{"current_steps": 165, "total_steps": 273, "loss": 0.4299, "lr": 3.260553755130525e-05, "epoch": 1.799863852961198, "percentage": 60.44, "elapsed_time": "9:42:19", "remaining_time": "6:21:09"}
+{"current_steps": 166, "total_steps": 273, "loss": 0.43, "lr": 3.210208646388532e-05, "epoch": 1.8107556160653506, "percentage": 60.81, "elapsed_time": "9:45:41", "remaining_time": "6:17:31"}
+{"current_steps": 167, "total_steps": 273, "loss": 0.4346, "lr": 3.1599933972286026e-05, "epoch": 1.821647379169503, "percentage": 61.17, "elapsed_time": "9:49:05", "remaining_time": "6:13:55"}
+{"current_steps": 168, "total_steps": 273, "loss": 0.4288, "lr": 3.109916264174743e-05, "epoch": 1.8325391422736557, "percentage": 61.54, "elapsed_time": "9:52:28", "remaining_time": "6:10:17"}
+{"current_steps": 169, "total_steps": 273, "loss": 0.428, "lr": 3.0599854810415393e-05, "epoch": 1.843430905377808, "percentage": 61.9, "elapsed_time": "9:55:50", "remaining_time": "6:06:40"}
+{"current_steps": 170, "total_steps": 273, "loss": 0.4333, "lr": 3.0102092575803435e-05, "epoch": 1.8543226684819605, "percentage": 62.27, "elapsed_time": "9:59:13", "remaining_time": "6:03:03"}
+{"current_steps": 171, "total_steps": 273, "loss": 0.4346, "lr": 2.9605957781293893e-05, "epoch": 1.865214431586113, "percentage": 62.64, "elapsed_time": "10:02:36", "remaining_time": "5:59:26"}
+{"current_steps": 172, "total_steps": 273, "loss": 0.4251, "lr": 2.911153200268116e-05, "epoch": 1.8761061946902655, "percentage": 63.0, "elapsed_time": "10:05:58", "remaining_time": "5:55:50"}
+{"current_steps": 173, "total_steps": 273, "loss": 0.4377, "lr": 2.8618896534758707e-05, "epoch": 1.886997957794418, "percentage": 63.37, "elapsed_time": "10:09:21", "remaining_time": "5:52:13"}
+{"current_steps": 174, "total_steps": 273, "loss": 0.4227, "lr": 2.8128132377952376e-05, "epoch": 1.8978897208985703, "percentage": 63.74, "elapsed_time": "10:12:43", "remaining_time": "5:48:37"}
+{"current_steps": 175, "total_steps": 273, "loss": 0.4325, "lr": 2.7639320225002108e-05, "epoch": 1.908781484002723, "percentage": 64.1, "elapsed_time": "10:16:06", "remaining_time": "5:45:01"}
+{"current_steps": 176, "total_steps": 273, "loss": 0.4308, "lr": 2.715254044769418e-05, "epoch": 1.9196732471068754, "percentage": 64.47, "elapsed_time": "10:19:30", "remaining_time": "5:41:25"}
+{"current_steps": 177, "total_steps": 273, "loss": 0.4322, "lr": 2.666787308364634e-05, "epoch": 1.9305650102110279, "percentage": 64.84, "elapsed_time": "10:22:52", "remaining_time": "5:37:49"}
+{"current_steps": 178, "total_steps": 273, "loss": 0.4263, "lr": 2.6185397823147703e-05, "epoch": 1.9414567733151804, "percentage": 65.2, "elapsed_time": "10:26:13", "remaining_time": "5:34:13"}
+{"current_steps": 179, "total_steps": 273, "loss": 0.4231, "lr": 2.5705193996055977e-05, "epoch": 1.952348536419333, "percentage": 65.57, "elapsed_time": "10:29:36", "remaining_time": "5:30:37"}
+{"current_steps": 180, "total_steps": 273, "loss": 0.4323, "lr": 2.5227340558753755e-05, "epoch": 1.9632402995234854, "percentage": 65.93, "elapsed_time": "10:33:00", "remaining_time": "5:27:03"}
+{"current_steps": 181, "total_steps": 273, "loss": 0.4318, "lr": 2.4751916081166336e-05, "epoch": 1.9741320626276377, "percentage": 66.3, "elapsed_time": "10:36:22", "remaining_time": "5:23:27"}
+{"current_steps": 182, "total_steps": 273, "loss": 0.4284, "lr": 2.427899873384306e-05, "epoch": 1.9850238257317905, "percentage": 66.67, "elapsed_time": "10:39:49", "remaining_time": "5:19:54"}
+{"current_steps": 183, "total_steps": 273, "loss": 0.4303, "lr": 2.3808666275104248e-05, "epoch": 1.9959155888359428, "percentage": 67.03, "elapsed_time": "10:43:03", "remaining_time": "5:16:15"}
+{"current_steps": 184, "total_steps": 273, "loss": 0.4195, "lr": 2.334099603825605e-05, "epoch": 2.0095302927161334, "percentage": 67.4, "elapsed_time": "10:47:31", "remaining_time": "5:13:12"}
+{"current_steps": 185, "total_steps": 273, "loss": 0.4056, "lr": 2.2876064918874993e-05, "epoch": 2.020422055820286, "percentage": 67.77, "elapsed_time": "10:50:56", "remaining_time": "5:09:38"}
+{"current_steps": 186, "total_steps": 273, "loss": 0.4033, "lr": 2.241394936216472e-05, "epoch": 2.0313138189244384, "percentage": 68.13, "elapsed_time": "10:54:18", "remaining_time": "5:06:02"}
+{"current_steps": 187, "total_steps": 273, "loss": 0.405, "lr": 2.1954725350386614e-05, "epoch": 2.0422055820285907, "percentage": 68.5, "elapsed_time": "10:57:41", "remaining_time": "5:02:28"}
+{"current_steps": 188, "total_steps": 273, "loss": 0.4094, "lr": 2.14984683903666e-05, "epoch": 2.0530973451327434, "percentage": 68.86, "elapsed_time": "11:01:07", "remaining_time": "4:58:54"}
+{"current_steps": 189, "total_steps": 273, "loss": 0.3988, "lr": 2.1045253501080058e-05, "epoch": 2.0639891082368957, "percentage": 69.23, "elapsed_time": "11:04:30", "remaining_time": "4:55:20"}
+{"current_steps": 190, "total_steps": 273, "loss": 0.4009, "lr": 2.0595155201317115e-05, "epoch": 2.0748808713410485, "percentage": 69.6, "elapsed_time": "11:07:55", "remaining_time": "4:51:46"}
+{"current_steps": 191, "total_steps": 273, "loss": 0.4016, "lr": 2.0148247497430012e-05, "epoch": 2.085772634445201, "percentage": 69.96, "elapsed_time": "11:11:18", "remaining_time": "4:48:12"}
+{"current_steps": 192, "total_steps": 273, "loss": 0.3948, "lr": 1.970460387116472e-05, "epoch": 2.096664397549353, "percentage": 70.33, "elapsed_time": "11:14:40", "remaining_time": "4:44:37"}
+{"current_steps": 193, "total_steps": 273, "loss": 0.3995, "lr": 1.9264297267579e-05, "epoch": 2.107556160653506, "percentage": 70.7, "elapsed_time": "11:18:05", "remaining_time": "4:41:04"}
+{"current_steps": 194, "total_steps": 273, "loss": 0.404, "lr": 1.8827400083048503e-05, "epoch": 2.118447923757658, "percentage": 71.06, "elapsed_time": "11:21:30", "remaining_time": "4:37:31"}
+{"current_steps": 195, "total_steps": 273, "loss": 0.3886, "lr": 1.8393984153363203e-05, "epoch": 2.129339686861811, "percentage": 71.43, "elapsed_time": "11:24:52", "remaining_time": "4:33:56"}
+{"current_steps": 196, "total_steps": 273, "loss": 0.4082, "lr": 1.7964120741915905e-05, "epoch": 2.140231449965963, "percentage": 71.79, "elapsed_time": "11:28:16", "remaining_time": "4:30:23"}
+{"current_steps": 197, "total_steps": 273, "loss": 0.3994, "lr": 1.753788052798501e-05, "epoch": 2.151123213070116, "percentage": 72.16, "elapsed_time": "11:31:38", "remaining_time": "4:26:49"}
+{"current_steps": 198, "total_steps": 273, "loss": 0.403, "lr": 1.7115333595113225e-05, "epoch": 2.162014976174268, "percentage": 72.53, "elapsed_time": "11:35:00", "remaining_time": "4:23:15"}
+{"current_steps": 199, "total_steps": 273, "loss": 0.4032, "lr": 1.669654941958416e-05, "epoch": 2.172906739278421, "percentage": 72.89, "elapsed_time": "11:38:22", "remaining_time": "4:19:41"}
+{"current_steps": 200, "total_steps": 273, "loss": 0.405, "lr": 1.628159685899897e-05, "epoch": 2.1837985023825732, "percentage": 73.26, "elapsed_time": "11:41:44", "remaining_time": "4:16:08"}
+{"current_steps": 201, "total_steps": 273, "loss": 0.4077, "lr": 1.5870544140954543e-05, "epoch": 2.1946902654867255, "percentage": 73.63, "elapsed_time": "11:45:05", "remaining_time": "4:12:34"}
+{"current_steps": 202, "total_steps": 273, "loss": 0.4053, "lr": 1.5463458851825345e-05, "epoch": 2.2055820285908783, "percentage": 73.99, "elapsed_time": "11:48:28", "remaining_time": "4:09:01"}
+{"current_steps": 203, "total_steps": 273, "loss": 0.4036, "lr": 1.5060407925650662e-05, "epoch": 2.2164737916950306, "percentage": 74.36, "elapsed_time": "11:51:53", "remaining_time": "4:05:28"}
+{"current_steps": 204, "total_steps": 273, "loss": 0.4021, "lr": 1.466145763312922e-05, "epoch": 2.2273655547991833, "percentage": 74.73, "elapsed_time": "11:55:18", "remaining_time": "4:01:56"}
+{"current_steps": 205, "total_steps": 273, "loss": 0.403, "lr": 1.426667357072265e-05, "epoch": 2.2382573179033356, "percentage": 75.09, "elapsed_time": "11:58:39", "remaining_time": "3:58:23"}
+{"current_steps": 206, "total_steps": 273, "loss": 0.4068, "lr": 1.3876120649870051e-05, "epoch": 2.249149081007488, "percentage": 75.46, "elapsed_time": "12:02:01", "remaining_time": "3:54:49"}
+{"current_steps": 207, "total_steps": 273, "loss": 0.3954, "lr": 1.3489863086315085e-05, "epoch": 2.2600408441116406, "percentage": 75.82, "elapsed_time": "12:05:22", "remaining_time": "3:51:16"}
+{"current_steps": 208, "total_steps": 273, "loss": 0.4056, "lr": 1.3107964389547326e-05, "epoch": 2.270932607215793, "percentage": 76.19, "elapsed_time": "12:08:44", "remaining_time": "3:47:43"}
+{"current_steps": 209, "total_steps": 273, "loss": 0.4028, "lr": 1.2730487352360026e-05, "epoch": 2.2818243703199457, "percentage": 76.56, "elapsed_time": "12:12:06", "remaining_time": "3:44:11"}
+{"current_steps": 210, "total_steps": 273, "loss": 0.4125, "lr": 1.2357494040525416e-05, "epoch": 2.292716133424098, "percentage": 76.92, "elapsed_time": "12:15:29", "remaining_time": "3:40:38"}
+{"current_steps": 211, "total_steps": 273, "loss": 0.404, "lr": 1.1989045782589815e-05, "epoch": 2.3036078965282503, "percentage": 77.29, "elapsed_time": "12:18:50", "remaining_time": "3:37:06"}
+{"current_steps": 212, "total_steps": 273, "loss": 0.398, "lr": 1.1625203159789686e-05, "epoch": 2.314499659632403, "percentage": 77.66, "elapsed_time": "12:22:13", "remaining_time": "3:33:33"}
+{"current_steps": 213, "total_steps": 273, "loss": 0.4103, "lr": 1.1266025996090902e-05, "epoch": 2.3253914227365553, "percentage": 78.02, "elapsed_time": "12:25:37", "remaining_time": "3:30:02"}
+{"current_steps": 214, "total_steps": 273, "loss": 0.4054, "lr": 1.0911573348352107e-05, "epoch": 2.336283185840708, "percentage": 78.39, "elapsed_time": "12:29:01", "remaining_time": "3:26:30"}
+{"current_steps": 215, "total_steps": 273, "loss": 0.4036, "lr": 1.0561903496614603e-05, "epoch": 2.3471749489448603, "percentage": 78.75, "elapsed_time": "12:32:23", "remaining_time": "3:22:58"}
+{"current_steps": 216, "total_steps": 273, "loss": 0.4012, "lr": 1.0217073934519726e-05, "epoch": 2.358066712049013, "percentage": 79.12, "elapsed_time": "12:35:44", "remaining_time": "3:19:25"}
+{"current_steps": 217, "total_steps": 273, "loss": 0.4109, "lr": 9.877141359855567e-06, "epoch": 2.3689584751531654, "percentage": 79.49, "elapsed_time": "12:39:08", "remaining_time": "3:15:54"}
+{"current_steps": 218, "total_steps": 273, "loss": 0.3991, "lr": 9.542161665234623e-06, "epoch": 2.379850238257318, "percentage": 79.85, "elapsed_time": "12:42:31", "remaining_time": "3:12:22"}
+{"current_steps": 219, "total_steps": 273, "loss": 0.4008, "lr": 9.212189928903758e-06, "epoch": 2.3907420013614704, "percentage": 80.22, "elapsed_time": "12:45:52", "remaining_time": "3:08:50"}
+{"current_steps": 220, "total_steps": 273, "loss": 0.4044, "lr": 8.887280405688106e-06, "epoch": 2.4016337644656227, "percentage": 80.59, "elapsed_time": "12:49:13", "remaining_time": "3:05:18"}
+{"current_steps": 221, "total_steps": 273, "loss": 0.3992, "lr": 8.567486518070306e-06, "epoch": 2.4125255275697755, "percentage": 80.95, "elapsed_time": "12:52:34", "remaining_time": "3:01:46"}
+{"current_steps": 222, "total_steps": 273, "loss": 0.3948, "lr": 8.252860847406712e-06, "epoch": 2.4234172906739277, "percentage": 81.32, "elapsed_time": "12:55:58", "remaining_time": "2:58:15"}
+{"current_steps": 223, "total_steps": 273, "loss": 0.3995, "lr": 7.943455125281741e-06, "epoch": 2.4343090537780805, "percentage": 81.68, "elapsed_time": "12:59:23", "remaining_time": "2:54:45"}
+{"current_steps": 224, "total_steps": 273, "loss": 0.407, "lr": 7.639320225002106e-06, "epoch": 2.445200816882233, "percentage": 82.05, "elapsed_time": "13:02:45", "remaining_time": "2:51:13"}
+{"current_steps": 225, "total_steps": 273, "loss": 0.4, "lr": 7.340506153232052e-06, "epoch": 2.456092579986385, "percentage": 82.42, "elapsed_time": "13:06:06", "remaining_time": "2:47:42"}
+{"current_steps": 226, "total_steps": 273, "loss": 0.4045, "lr": 7.047062041771133e-06, "epoch": 2.466984343090538, "percentage": 82.78, "elapsed_time": "13:09:27", "remaining_time": "2:44:10"}
+{"current_steps": 227, "total_steps": 273, "loss": 0.3964, "lr": 6.759036139475843e-06, "epoch": 2.47787610619469, "percentage": 83.15, "elapsed_time": "13:12:48", "remaining_time": "2:40:39"}
+{"current_steps": 228, "total_steps": 273, "loss": 0.4025, "lr": 6.476475804326377e-06, "epoch": 2.488767869298843, "percentage": 83.52, "elapsed_time": "13:16:12", "remaining_time": "2:37:08"}
+{"current_steps": 229, "total_steps": 273, "loss": 0.3994, "lr": 6.199427495639963e-06, "epoch": 2.499659632402995, "percentage": 83.88, "elapsed_time": "13:19:36", "remaining_time": "2:33:38"}
+{"current_steps": 230, "total_steps": 273, "loss": 0.4022, "lr": 5.927936766431836e-06, "epoch": 2.5105513955071475, "percentage": 84.25, "elapsed_time": "13:22:57", "remaining_time": "2:30:07"}
+{"current_steps": 231, "total_steps": 273, "loss": 0.3988, "lr": 5.662048255925357e-06, "epoch": 2.5214431586113, "percentage": 84.62, "elapsed_time": "13:26:19", "remaining_time": "2:26:36"}
+{"current_steps": 232, "total_steps": 273, "loss": 0.4047, "lr": 5.40180568221226e-06, "epoch": 2.532334921715453, "percentage": 84.98, "elapsed_time": "13:29:41", "remaining_time": "2:23:05"}
+{"current_steps": 233, "total_steps": 273, "loss": 0.4057, "lr": 5.147251835064424e-06, "epoch": 2.5432266848196052, "percentage": 85.35, "elapsed_time": "13:33:03", "remaining_time": "2:19:34"}
+{"current_steps": 234, "total_steps": 273, "loss": 0.3971, "lr": 4.898428568898288e-06, "epoch": 2.5541184479237575, "percentage": 85.71, "elapsed_time": "13:36:25", "remaining_time": "2:16:04"}
+{"current_steps": 235, "total_steps": 273, "loss": 0.4045, "lr": 4.65537679589299e-06, "epoch": 2.5650102110279103, "percentage": 86.08, "elapsed_time": "13:39:47", "remaining_time": "2:12:33"}
+{"current_steps": 236, "total_steps": 273, "loss": 0.4004, "lr": 4.418136479263533e-06, "epoch": 2.5759019741320626, "percentage": 86.45, "elapsed_time": "13:43:08", "remaining_time": "2:09:03"}
+{"current_steps": 237, "total_steps": 273, "loss": 0.4006, "lr": 4.186746626689879e-06, "epoch": 2.5867937372362153, "percentage": 86.81, "elapsed_time": "13:46:29", "remaining_time": "2:05:32"}
+{"current_steps": 238, "total_steps": 273, "loss": 0.4025, "lr": 3.961245283903239e-06, "epoch": 2.5976855003403676, "percentage": 87.18, "elapsed_time": "13:52:45", "remaining_time": "2:02:27"}
+{"current_steps": 239, "total_steps": 273, "loss": 0.4051, "lr": 3.7416695284304737e-06, "epoch": 2.60857726344452, "percentage": 87.55, "elapsed_time": "13:56:11", "remaining_time": "1:58:57"}
+{"current_steps": 240, "total_steps": 273, "loss": 0.4013, "lr": 3.5280554634977217e-06, "epoch": 2.6194690265486726, "percentage": 87.91, "elapsed_time": "13:59:54", "remaining_time": "1:55:29"}
+{"current_steps": 241, "total_steps": 273, "loss": 0.4059, "lr": 3.320438212094197e-06, "epoch": 2.630360789652825, "percentage": 88.28, "elapsed_time": "14:03:38", "remaining_time": "1:52:01"}
+{"current_steps": 242, "total_steps": 273, "loss": 0.4039, "lr": 3.1188519111971804e-06, "epoch": 2.6412525527569777, "percentage": 88.64, "elapsed_time": "14:07:12", "remaining_time": "1:48:31"}
+{"current_steps": 243, "total_steps": 273, "loss": 0.3973, "lr": 2.9233297061591346e-06, "epoch": 2.65214431586113, "percentage": 89.01, "elapsed_time": "14:10:59", "remaining_time": "1:45:03"}
+{"current_steps": 244, "total_steps": 273, "loss": 0.4049, "lr": 2.733903745257838e-06, "epoch": 2.6630360789652823, "percentage": 89.38, "elapsed_time": "14:15:25", "remaining_time": "1:41:40"}
+{"current_steps": 245, "total_steps": 273, "loss": 0.4017, "lr": 2.550605174410512e-06, "epoch": 2.673927842069435, "percentage": 89.74, "elapsed_time": "14:25:57", "remaining_time": "1:38:57"}
+{"current_steps": 246, "total_steps": 273, "loss": 0.4115, "lr": 2.373464132052701e-06, "epoch": 2.6848196051735873, "percentage": 90.11, "elapsed_time": "14:29:19", "remaining_time": "1:35:24"}
+{"current_steps": 247, "total_steps": 273, "loss": 0.3982, "lr": 2.202509744182835e-06, "epoch": 2.69571136827774, "percentage": 90.48, "elapsed_time": "14:32:40", "remaining_time": "1:31:51"}
+{"current_steps": 248, "total_steps": 273, "loss": 0.4071, "lr": 2.0377701195732545e-06, "epoch": 2.7066031313818923, "percentage": 90.84, "elapsed_time": "14:36:02", "remaining_time": "1:28:18"}
+{"current_steps": 249, "total_steps": 273, "loss": 0.4101, "lr": 1.879272345148513e-06, "epoch": 2.717494894486045, "percentage": 91.21, "elapsed_time": "14:39:24", "remaining_time": "1:24:45"}
+{"current_steps": 250, "total_steps": 273, "loss": 0.4035, "lr": 1.727042481531651e-06, "epoch": 2.7283866575901974, "percentage": 91.58, "elapsed_time": "14:42:45", "remaining_time": "1:21:12"}
+{"current_steps": 251, "total_steps": 273, "loss": 0.4009, "lr": 1.5811055587592283e-06, "epoch": 2.73927842069435, "percentage": 91.94, "elapsed_time": "14:46:07", "remaining_time": "1:17:40"}
+{"current_steps": 252, "total_steps": 273, "loss": 0.4041, "lr": 1.4414855721658705e-06, "epoch": 2.7501701837985024, "percentage": 92.31, "elapsed_time": "14:49:31", "remaining_time": "1:14:07"}
+{"current_steps": 253, "total_steps": 273, "loss": 0.4055, "lr": 1.3082054784388221e-06, "epoch": 2.7610619469026547, "percentage": 92.67, "elapsed_time": "14:52:52", "remaining_time": "1:10:35"}
+{"current_steps": 254, "total_steps": 273, "loss": 0.4027, "lr": 1.1812871918434143e-06, "epoch": 2.7719537100068075, "percentage": 93.04, "elapsed_time": "14:56:15", "remaining_time": "1:07:02"}
+{"current_steps": 255, "total_steps": 273, "loss": 0.4079, "lr": 1.0607515806198142e-06, "epoch": 2.7828454731109598, "percentage": 93.41, "elapsed_time": "14:59:37", "remaining_time": "1:03:30"}
+{"current_steps": 256, "total_steps": 273, "loss": 0.4017, "lr": 9.466184635518361e-07, "epoch": 2.7937372362151125, "percentage": 93.77, "elapsed_time": "15:03:00", "remaining_time": "0:59:57"}
+{"current_steps": 257, "total_steps": 273, "loss": 0.3967, "lr": 8.389066067082852e-07, "epoch": 2.804628999319265, "percentage": 94.14, "elapsed_time": "15:06:21", "remaining_time": "0:56:25"}
+{"current_steps": 258, "total_steps": 273, "loss": 0.406, "lr": 7.376337203573824e-07, "epoch": 2.815520762423417, "percentage": 94.51, "elapsed_time": "15:09:44", "remaining_time": "0:52:53"}
+{"current_steps": 259, "total_steps": 273, "loss": 0.4076, "lr": 6.428164560548134e-07, "epoch": 2.82641252552757, "percentage": 94.87, "elapsed_time": "15:13:06", "remaining_time": "0:49:21"}
+{"current_steps": 260, "total_steps": 273, "loss": 0.3983, "lr": 5.544704039058025e-07, "epoch": 2.837304288631722, "percentage": 95.24, "elapsed_time": "15:16:28", "remaining_time": "0:45:49"}
+{"current_steps": 261, "total_steps": 273, "loss": 0.3918, "lr": 4.7261009000177274e-07, "epoch": 2.848196051735875, "percentage": 95.6, "elapsed_time": "15:19:50", "remaining_time": "0:42:17"}
+{"current_steps": 262, "total_steps": 273, "loss": 0.3924, "lr": 3.972489740319274e-07, "epoch": 2.859087814840027, "percentage": 95.97, "elapsed_time": "15:23:12", "remaining_time": "0:38:45"}
+{"current_steps": 263, "total_steps": 273, "loss": 0.4057, "lr": 3.283994470701579e-07, "epoch": 2.8699795779441795, "percentage": 96.34, "elapsed_time": "15:26:35", "remaining_time": "0:35:13"}
+{"current_steps": 264, "total_steps": 273, "loss": 0.4099, "lr": 2.66072829537678e-07, "epoch": 2.880871341048332, "percentage": 96.7, "elapsed_time": "15:30:05", "remaining_time": "0:31:42"}
+{"current_steps": 265, "total_steps": 273, "loss": 0.4073, "lr": 2.102793693417038e-07, "epoch": 2.891763104152485, "percentage": 97.07, "elapsed_time": "15:33:29", "remaining_time": "0:28:10"}
+{"current_steps": 266, "total_steps": 273, "loss": 0.4002, "lr": 1.6102824019043728e-07, "epoch": 2.9026548672566372, "percentage": 97.44, "elapsed_time": "15:36:52", "remaining_time": "0:24:39"}
+{"current_steps": 267, "total_steps": 273, "loss": 0.389, "lr": 1.1832754008472614e-07, "epoch": 2.9135466303607895, "percentage": 97.8, "elapsed_time": "15:40:15", "remaining_time": "0:21:07"}
+{"current_steps": 268, "total_steps": 273, "loss": 0.3955, "lr": 8.21842899865466e-08, "epoch": 2.9244383934649423, "percentage": 98.17, "elapsed_time": "15:43:39", "remaining_time": "0:17:36"}
+{"current_steps": 269, "total_steps": 273, "loss": 0.3949, "lr": 5.260443266462467e-08, "epoch": 2.9353301565690946, "percentage": 98.53, "elapsed_time": "15:47:02", "remaining_time": "0:14:04"}
+{"current_steps": 270, "total_steps": 273, "loss": 0.4072, "lr": 2.9592831717293326e-08, "epoch": 2.9462219196732473, "percentage": 98.9, "elapsed_time": "15:50:24", "remaining_time": "0:10:33"}
+{"current_steps": 271, "total_steps": 273, "loss": 0.3967, "lr": 1.3153270772807702e-08, "epoch": 2.9571136827773996, "percentage": 99.27, "elapsed_time": "15:53:47", "remaining_time": "0:07:02"}
+{"current_steps": 272, "total_steps": 273, "loss": 0.395, "lr": 3.2884528672294523e-09, "epoch": 2.968005445881552, "percentage": 99.63, "elapsed_time": "15:57:10", "remaining_time": "0:03:31"}
+{"current_steps": 273, "total_steps": 273, "loss": 0.4097, "lr": 0.0, "epoch": 2.9788972089857046, "percentage": 100.0, "elapsed_time": "16:00:37", "remaining_time": "0:00:00"}
+{"current_steps": 273, "total_steps": 273, "epoch": 2.9788972089857046, "percentage": 100.0, "elapsed_time": "16:01:43", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1953 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9788972089857046,
+  "eval_steps": 500,
+  "global_step": 273,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010891763104152484,
+      "grad_norm": 5.917168704218648,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.8738,
+      "step": 1
+    },
+    {
+      "epoch": 0.021783526208304968,
+      "grad_norm": 5.848189651981173,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.8637,
+      "step": 2
+    },
+    {
+      "epoch": 0.03267528931245745,
+      "grad_norm": 5.4410485869996865,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.8524,
+      "step": 3
+    },
+    {
+      "epoch": 0.043567052416609936,
+      "grad_norm": 2.423684029964203,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.783,
+      "step": 4
+    },
+    {
+      "epoch": 0.05445881552076242,
+      "grad_norm": 4.0235503087845155,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.7805,
+      "step": 5
+    },
+    {
+      "epoch": 0.0653505786249149,
+      "grad_norm": 4.14511666016107,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.7643,
+      "step": 6
+    },
+    {
+      "epoch": 0.0762423417290674,
+      "grad_norm": 4.42039479030743,
+      "learning_rate": 2e-05,
+      "loss": 0.7512,
+      "step": 7
+    },
+    {
+      "epoch": 0.08713410483321987,
+      "grad_norm": 2.857807259160155,
+      "learning_rate": 2.2857142857142858e-05,
+      "loss": 0.7182,
+      "step": 8
+    },
+    {
+      "epoch": 0.09802586793737236,
+      "grad_norm": 2.690272592093101,
+      "learning_rate": 2.5714285714285718e-05,
+      "loss": 0.6835,
+      "step": 9
+    },
+    {
+      "epoch": 0.10891763104152484,
+      "grad_norm": 2.0185553871545165,
+      "learning_rate": 2.8571428571428574e-05,
+      "loss": 0.666,
+      "step": 10
+    },
+    {
+      "epoch": 0.11980939414567733,
+      "grad_norm": 1.6526659811622688,
+      "learning_rate": 3.142857142857143e-05,
+      "loss": 0.6551,
+      "step": 11
+    },
+    {
+      "epoch": 0.1307011572498298,
+      "grad_norm": 1.3684051055691528,
+      "learning_rate": 3.4285714285714284e-05,
+      "loss": 0.6374,
+      "step": 12
+    },
+    {
+      "epoch": 0.1415929203539823,
+      "grad_norm": 1.3936888061646935,
+      "learning_rate": 3.714285714285715e-05,
+      "loss": 0.6142,
+      "step": 13
+    },
+    {
+      "epoch": 0.1524846834581348,
+      "grad_norm": 1.3347032728939032,
+      "learning_rate": 4e-05,
+      "loss": 0.6085,
+      "step": 14
+    },
+    {
+      "epoch": 0.16337644656228728,
+      "grad_norm": 1.6041646981350726,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.6168,
+      "step": 15
+    },
+    {
+      "epoch": 0.17426820966643974,
+      "grad_norm": 1.250156217488812,
+      "learning_rate": 4.5714285714285716e-05,
+      "loss": 0.5904,
+      "step": 16
+    },
+    {
+      "epoch": 0.18515997277059223,
+      "grad_norm": 1.363684815879282,
+      "learning_rate": 4.857142857142857e-05,
+      "loss": 0.5983,
+      "step": 17
+    },
+    {
+      "epoch": 0.19605173587474473,
+      "grad_norm": 1.160866980807094,
+      "learning_rate": 5.1428571428571436e-05,
+      "loss": 0.5762,
+      "step": 18
+    },
+    {
+      "epoch": 0.20694349897889722,
+      "grad_norm": 1.8320088500371636,
+      "learning_rate": 5.4285714285714295e-05,
+      "loss": 0.5794,
+      "step": 19
+    },
+    {
+      "epoch": 0.21783526208304968,
+      "grad_norm": 1.310331415981151,
+      "learning_rate": 5.714285714285715e-05,
+      "loss": 0.5723,
+      "step": 20
+    },
+    {
+      "epoch": 0.22872702518720217,
+      "grad_norm": 2.0403045692700275,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.576,
+      "step": 21
+    },
+    {
+      "epoch": 0.23961878829135466,
+      "grad_norm": 1.0753217952290004,
+      "learning_rate": 6.285714285714286e-05,
+      "loss": 0.5657,
+      "step": 22
+    },
+    {
+      "epoch": 0.25051055139550715,
+      "grad_norm": 2.0101370583197076,
+      "learning_rate": 6.571428571428571e-05,
+      "loss": 0.5751,
+      "step": 23
+    },
+    {
+      "epoch": 0.2614023144996596,
+      "grad_norm": 1.8269660980505025,
+      "learning_rate": 6.857142857142857e-05,
+      "loss": 0.5622,
+      "step": 24
+    },
+    {
+      "epoch": 0.27229407760381213,
+      "grad_norm": 1.333190530233097,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.553,
+      "step": 25
+    },
+    {
+      "epoch": 0.2831858407079646,
+      "grad_norm": 1.5278657539191043,
+      "learning_rate": 7.42857142857143e-05,
+      "loss": 0.5746,
+      "step": 26
+    },
+    {
+      "epoch": 0.29407760381211706,
+      "grad_norm": 1.4753801604023495,
+      "learning_rate": 7.714285714285715e-05,
+      "loss": 0.5504,
+      "step": 27
+    },
+    {
+      "epoch": 0.3049693669162696,
+      "grad_norm": 1.4736990838732313,
+      "learning_rate": 8e-05,
+      "loss": 0.5542,
+      "step": 28
+    },
+    {
+      "epoch": 0.31586113002042204,
+      "grad_norm": 2.3486277040401893,
+      "learning_rate": 7.999671154713278e-05,
+      "loss": 0.5507,
+      "step": 29
+    },
+    {
+      "epoch": 0.32675289312457456,
+      "grad_norm": 1.1844138236301467,
+      "learning_rate": 7.99868467292272e-05,
+      "loss": 0.5496,
+      "step": 30
+    },
+    {
+      "epoch": 0.337644656228727,
+      "grad_norm": 2.4920955827056748,
+      "learning_rate": 7.997040716828271e-05,
+      "loss": 0.5575,
+      "step": 31
+    },
+    {
+      "epoch": 0.3485364193328795,
+      "grad_norm": 1.7099423006847476,
+      "learning_rate": 7.994739556733538e-05,
+      "loss": 0.5596,
+      "step": 32
+    },
+    {
+      "epoch": 0.359428182437032,
+      "grad_norm": 2.1342906902090504,
+      "learning_rate": 7.991781571001347e-05,
+      "loss": 0.5337,
+      "step": 33
+    },
+    {
+      "epoch": 0.37031994554118447,
+      "grad_norm": 1.7483277996825424,
+      "learning_rate": 7.988167245991528e-05,
+      "loss": 0.5492,
+      "step": 34
+    },
+    {
+      "epoch": 0.381211708645337,
+      "grad_norm": 1.7968259576328387,
+      "learning_rate": 7.983897175980957e-05,
+      "loss": 0.5314,
+      "step": 35
+    },
+    {
+      "epoch": 0.39210347174948945,
+      "grad_norm": 1.559300515616932,
+      "learning_rate": 7.97897206306583e-05,
+      "loss": 0.5307,
+      "step": 36
+    },
+    {
+      "epoch": 0.4029952348536419,
+      "grad_norm": 1.0889578452931736,
+      "learning_rate": 7.973392717046233e-05,
+      "loss": 0.5408,
+      "step": 37
+    },
+    {
+      "epoch": 0.41388699795779443,
+      "grad_norm": 1.313871076023579,
+      "learning_rate": 7.967160055292984e-05,
+      "loss": 0.5147,
+      "step": 38
+    },
+    {
+      "epoch": 0.4247787610619469,
+      "grad_norm": 1.583430729115433,
+      "learning_rate": 7.960275102596809e-05,
+      "loss": 0.5216,
+      "step": 39
+    },
+    {
+      "epoch": 0.43567052416609936,
+      "grad_norm": 1.3933127292778362,
+      "learning_rate": 7.952738990999824e-05,
+      "loss": 0.5187,
+      "step": 40
+    },
+    {
+      "epoch": 0.4465622872702519,
+      "grad_norm": 1.4991075926399846,
+      "learning_rate": 7.94455295960942e-05,
+      "loss": 0.5123,
+      "step": 41
+    },
+    {
+      "epoch": 0.45745405037440434,
+      "grad_norm": 1.2790673350427315,
+      "learning_rate": 7.93571835439452e-05,
+      "loss": 0.5255,
+      "step": 42
+    },
+    {
+      "epoch": 0.46834581347855686,
+      "grad_norm": 1.656174041977428,
+      "learning_rate": 7.926236627964262e-05,
+      "loss": 0.5224,
+      "step": 43
+    },
+    {
+      "epoch": 0.4792375765827093,
+      "grad_norm": 1.3680863968048569,
+      "learning_rate": 7.916109339329173e-05,
+      "loss": 0.5104,
+      "step": 44
+    },
+    {
+      "epoch": 0.4901293396868618,
+      "grad_norm": 1.1248700116366424,
+      "learning_rate": 7.905338153644818e-05,
+      "loss": 0.5036,
+      "step": 45
+    },
+    {
+      "epoch": 0.5010211027910143,
+      "grad_norm": 1.4820737812996578,
+      "learning_rate": 7.89392484193802e-05,
+      "loss": 0.5169,
+      "step": 46
+    },
+    {
+      "epoch": 0.5119128658951668,
+      "grad_norm": 1.1533791684607533,
+      "learning_rate": 7.881871280815659e-05,
+      "loss": 0.5071,
+      "step": 47
+    },
+    {
+      "epoch": 0.5228046289993192,
+      "grad_norm": 1.9492363638377506,
+      "learning_rate": 7.869179452156118e-05,
+      "loss": 0.5093,
+      "step": 48
+    },
+    {
+      "epoch": 0.5336963921034718,
+      "grad_norm": 0.9617512636578286,
+      "learning_rate": 7.855851442783414e-05,
+      "loss": 0.501,
+      "step": 49
+    },
+    {
+      "epoch": 0.5445881552076243,
+      "grad_norm": 1.0817397757606,
+      "learning_rate": 7.841889444124078e-05,
+      "loss": 0.4997,
+      "step": 50
+    },
+    {
+      "epoch": 0.5554799183117767,
+      "grad_norm": 2.1099922597533074,
+      "learning_rate": 7.827295751846836e-05,
+      "loss": 0.5151,
+      "step": 51
+    },
+    {
+      "epoch": 0.5663716814159292,
+      "grad_norm": 1.0752679988230807,
+      "learning_rate": 7.81207276548515e-05,
+      "loss": 0.512,
+      "step": 52
+    },
+    {
+      "epoch": 0.5772634445200817,
+      "grad_norm": 2.033228507248604,
+      "learning_rate": 7.796222988042676e-05,
+      "loss": 0.5247,
+      "step": 53
+    },
+    {
+      "epoch": 0.5881552076242341,
+      "grad_norm": 1.4290947325043002,
+      "learning_rate": 7.779749025581717e-05,
+      "loss": 0.5161,
+      "step": 54
+    },
+    {
+      "epoch": 0.5990469707283866,
+      "grad_norm": 1.6107474254316703,
+      "learning_rate": 7.762653586794731e-05,
+      "loss": 0.5113,
+      "step": 55
+    },
+    {
+      "epoch": 0.6099387338325392,
+      "grad_norm": 1.7403793303180215,
+      "learning_rate": 7.74493948255895e-05,
+      "loss": 0.5104,
+      "step": 56
+    },
+    {
+      "epoch": 0.6208304969366917,
+      "grad_norm": 1.3273260664695445,
+      "learning_rate": 7.726609625474218e-05,
+      "loss": 0.5149,
+      "step": 57
+    },
+    {
+      "epoch": 0.6317222600408441,
+      "grad_norm": 1.2835468728323596,
+      "learning_rate": 7.707667029384088e-05,
+      "loss": 0.4985,
+      "step": 58
+    },
+    {
+      "epoch": 0.6426140231449966,
+      "grad_norm": 1.3493586560972042,
+      "learning_rate": 7.688114808880283e-05,
+      "loss": 0.515,
+      "step": 59
+    },
+    {
+      "epoch": 0.6535057862491491,
+      "grad_norm": 0.8317273919287447,
+      "learning_rate": 7.667956178790582e-05,
+      "loss": 0.5059,
+      "step": 60
+    },
+    {
+      "epoch": 0.6643975493533015,
+      "grad_norm": 1.1983241891992835,
+      "learning_rate": 7.647194453650228e-05,
+      "loss": 0.4935,
+      "step": 61
+    },
+    {
+      "epoch": 0.675289312457454,
+      "grad_norm": 1.1964694002526848,
+      "learning_rate": 7.625833047156953e-05,
+      "loss": 0.5058,
+      "step": 62
+    },
+    {
+      "epoch": 0.6861810755616066,
+      "grad_norm": 1.1878899519661879,
+      "learning_rate": 7.603875471609677e-05,
+      "loss": 0.4903,
+      "step": 63
+    },
+    {
+      "epoch": 0.697072838665759,
+      "grad_norm": 1.2583807783190593,
+      "learning_rate": 7.581325337331013e-05,
+      "loss": 0.497,
+      "step": 64
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.9383067837973975,
+      "learning_rate": 7.558186352073648e-05,
+      "loss": 0.4874,
+      "step": 65
+    },
+    {
+      "epoch": 0.718856364874064,
+      "grad_norm": 1.114271813149658,
+      "learning_rate": 7.534462320410702e-05,
+      "loss": 0.4957,
+      "step": 66
+    },
+    {
+      "epoch": 0.7297481279782164,
+      "grad_norm": 0.9889746448795311,
+      "learning_rate": 7.510157143110172e-05,
+      "loss": 0.4976,
+      "step": 67
+    },
+    {
+      "epoch": 0.7406398910823689,
+      "grad_norm": 1.5156805885931242,
+      "learning_rate": 7.485274816493558e-05,
+      "loss": 0.4959,
+      "step": 68
+    },
+    {
+      "epoch": 0.7515316541865215,
+      "grad_norm": 0.9749471928652824,
+      "learning_rate": 7.459819431778775e-05,
+      "loss": 0.4796,
+      "step": 69
+    },
+    {
+      "epoch": 0.762423417290674,
+      "grad_norm": 0.8404206560752534,
+      "learning_rate": 7.433795174407465e-05,
+      "loss": 0.4762,
+      "step": 70
+    },
+    {
+      "epoch": 0.7733151803948264,
+      "grad_norm": 1.2857273953478379,
+      "learning_rate": 7.407206323356818e-05,
+      "loss": 0.4955,
+      "step": 71
+    },
+    {
+      "epoch": 0.7842069434989789,
+      "grad_norm": 1.5254696719564749,
+      "learning_rate": 7.380057250436006e-05,
+      "loss": 0.4945,
+      "step": 72
+    },
+    {
+      "epoch": 0.7950987066031314,
+      "grad_norm": 1.0225507119621404,
+      "learning_rate": 7.352352419567362e-05,
+      "loss": 0.4883,
+      "step": 73
+    },
+    {
+      "epoch": 0.8059904697072838,
+      "grad_norm": 1.3824406570348136,
+      "learning_rate": 7.324096386052416e-05,
+      "loss": 0.4906,
+      "step": 74
+    },
+    {
+      "epoch": 0.8168822328114363,
+      "grad_norm": 0.9568602258759329,
+      "learning_rate": 7.295293795822887e-05,
+      "loss": 0.4838,
+      "step": 75
+    },
+    {
+      "epoch": 0.8277739959155889,
+      "grad_norm": 1.2765315330970022,
+      "learning_rate": 7.265949384676795e-05,
+      "loss": 0.4815,
+      "step": 76
+    },
+    {
+      "epoch": 0.8386657590197413,
+      "grad_norm": 1.2279324061842216,
+      "learning_rate": 7.236067977499791e-05,
+      "loss": 0.4855,
+      "step": 77
+    },
+    {
+      "epoch": 0.8495575221238938,
+      "grad_norm": 0.9629770077059606,
+      "learning_rate": 7.205654487471826e-05,
+      "loss": 0.4811,
+      "step": 78
+    },
+    {
+      "epoch": 0.8604492852280463,
+      "grad_norm": 1.295116932433786,
+      "learning_rate": 7.174713915259331e-05,
+      "loss": 0.4889,
+      "step": 79
+    },
+    {
+      "epoch": 0.8713410483321987,
+      "grad_norm": 0.9924719057218118,
+      "learning_rate": 7.143251348192971e-05,
+      "loss": 0.488,
+      "step": 80
+    },
+    {
+      "epoch": 0.8822328114363512,
+      "grad_norm": 1.3773423039136135,
+      "learning_rate": 7.111271959431189e-05,
+      "loss": 0.4859,
+      "step": 81
+    },
+    {
+      "epoch": 0.8931245745405038,
+      "grad_norm": 0.9416135398394887,
+      "learning_rate": 7.078781007109625e-05,
+      "loss": 0.4803,
+      "step": 82
+    },
+    {
+      "epoch": 0.9040163376446563,
+      "grad_norm": 1.0674313281470116,
+      "learning_rate": 7.045783833476538e-05,
+      "loss": 0.4733,
+      "step": 83
+    },
+    {
+      "epoch": 0.9149081007488087,
+      "grad_norm": 1.000464101793752,
+      "learning_rate": 7.012285864014445e-05,
+      "loss": 0.4726,
+      "step": 84
+    },
+    {
+      "epoch": 0.9257998638529612,
+      "grad_norm": 1.3944228987734595,
+      "learning_rate": 6.978292606548029e-05,
+      "loss": 0.4817,
+      "step": 85
+    },
+    {
+      "epoch": 0.9366916269571137,
+      "grad_norm": 0.9210477820477416,
+      "learning_rate": 6.943809650338541e-05,
+      "loss": 0.4856,
+      "step": 86
+    },
+    {
+      "epoch": 0.9475833900612661,
+      "grad_norm": 1.4702724614133884,
+      "learning_rate": 6.908842665164789e-05,
+      "loss": 0.4893,
+      "step": 87
+    },
+    {
+      "epoch": 0.9584751531654186,
+      "grad_norm": 0.9392028605617796,
+      "learning_rate": 6.873397400390911e-05,
+      "loss": 0.4749,
+      "step": 88
+    },
+    {
+      "epoch": 0.9693669162695712,
+      "grad_norm": 1.33752177947439,
+      "learning_rate": 6.837479684021032e-05,
+      "loss": 0.4642,
+      "step": 89
+    },
+    {
+      "epoch": 0.9802586793737236,
+      "grad_norm": 1.0674472905397991,
+      "learning_rate": 6.80109542174102e-05,
+      "loss": 0.4721,
+      "step": 90
+    },
+    {
+      "epoch": 0.9911504424778761,
+      "grad_norm": 0.8855006430820443,
+      "learning_rate": 6.76425059594746e-05,
+      "loss": 0.471,
+      "step": 91
+    },
+    {
+      "epoch": 1.0047651463580667,
+      "grad_norm": 0.7477549645216865,
+      "learning_rate": 6.726951264763998e-05,
+      "loss": 0.4723,
+      "step": 92
+    },
+    {
+      "epoch": 1.0156569094622192,
+      "grad_norm": 0.8956363744921413,
+      "learning_rate": 6.689203561045268e-05,
+      "loss": 0.4562,
+      "step": 93
+    },
+    {
+      "epoch": 1.0265486725663717,
+      "grad_norm": 1.060602408653099,
+      "learning_rate": 6.651013691368492e-05,
+      "loss": 0.4599,
+      "step": 94
+    },
+    {
+      "epoch": 1.0374404356705242,
+      "grad_norm": 1.2755687426821307,
+      "learning_rate": 6.612387935012995e-05,
+      "loss": 0.4586,
+      "step": 95
+    },
+    {
+      "epoch": 1.0483321987746765,
+      "grad_norm": 0.7866789226297869,
+      "learning_rate": 6.573332642927737e-05,
+      "loss": 0.4564,
+      "step": 96
+    },
+    {
+      "epoch": 1.059223961878829,
+      "grad_norm": 1.0671580779917749,
+      "learning_rate": 6.53385423668708e-05,
+      "loss": 0.4532,
+      "step": 97
+    },
+    {
+      "epoch": 1.0701157249829816,
+      "grad_norm": 1.8705582630594135,
+      "learning_rate": 6.493959207434934e-05,
+      "loss": 0.4518,
+      "step": 98
+    },
+    {
+      "epoch": 1.081007488087134,
+      "grad_norm": 0.8747747648963227,
+      "learning_rate": 6.453654114817467e-05,
+      "loss": 0.4602,
+      "step": 99
+    },
+    {
+      "epoch": 1.0918992511912866,
+      "grad_norm": 2.6708530213907915,
+      "learning_rate": 6.412945585904545e-05,
+      "loss": 0.4706,
+      "step": 100
+    },
+    {
+      "epoch": 1.1027910142954391,
+      "grad_norm": 2.059630403847963,
+      "learning_rate": 6.371840314100104e-05,
+      "loss": 0.4746,
+      "step": 101
+    },
+    {
+      "epoch": 1.1136827773995917,
+      "grad_norm": 2.100904334906369,
+      "learning_rate": 6.330345058041585e-05,
+      "loss": 0.4645,
+      "step": 102
+    },
+    {
+      "epoch": 1.124574540503744,
+      "grad_norm": 1.9589727338791063,
+      "learning_rate": 6.288466640488679e-05,
+      "loss": 0.4574,
+      "step": 103
+    },
+    {
+      "epoch": 1.1354663036078965,
+      "grad_norm": 1.250427733328813,
+      "learning_rate": 6.2462119472015e-05,
+      "loss": 0.453,
+      "step": 104
+    },
+    {
+      "epoch": 1.146358066712049,
+      "grad_norm": 1.244933711184395,
+      "learning_rate": 6.20358792580841e-05,
+      "loss": 0.4562,
+      "step": 105
+    },
+    {
+      "epoch": 1.1572498298162015,
+      "grad_norm": 0.978598635089721,
+      "learning_rate": 6.160601584663681e-05,
+      "loss": 0.4544,
+      "step": 106
+    },
+    {
+      "epoch": 1.168141592920354,
+      "grad_norm": 1.0133074820438104,
+      "learning_rate": 6.11725999169515e-05,
+      "loss": 0.4567,
+      "step": 107
+    },
+    {
+      "epoch": 1.1790333560245065,
+      "grad_norm": 0.9079803477398684,
+      "learning_rate": 6.0735702732421015e-05,
+      "loss": 0.4537,
+      "step": 108
+    },
+    {
+      "epoch": 1.189925119128659,
+      "grad_norm": 0.47916750157430577,
+      "learning_rate": 6.029539612883529e-05,
+      "loss": 0.4514,
+      "step": 109
+    },
+    {
+      "epoch": 1.2008168822328114,
+      "grad_norm": 0.737478359754882,
+      "learning_rate": 5.9851752502570015e-05,
+      "loss": 0.4462,
+      "step": 110
+    },
+    {
+      "epoch": 1.2117086453369639,
+      "grad_norm": 0.5899481616784151,
+      "learning_rate": 5.940484479868288e-05,
+      "loss": 0.4456,
+      "step": 111
+    },
+    {
+      "epoch": 1.2226004084411164,
+      "grad_norm": 0.766606804098348,
+      "learning_rate": 5.895474649891995e-05,
+      "loss": 0.4441,
+      "step": 112
+    },
+    {
+      "epoch": 1.233492171545269,
+      "grad_norm": 0.6645207203467242,
+      "learning_rate": 5.8501531609633424e-05,
+      "loss": 0.4463,
+      "step": 113
+    },
+    {
+      "epoch": 1.2443839346494214,
+      "grad_norm": 0.681340548554224,
+      "learning_rate": 5.8045274649613386e-05,
+      "loss": 0.4424,
+      "step": 114
+    },
+    {
+      "epoch": 1.2552756977535737,
+      "grad_norm": 0.7119900691253739,
+      "learning_rate": 5.7586050637835295e-05,
+      "loss": 0.4459,
+      "step": 115
+    },
+    {
+      "epoch": 1.2661674608577265,
+      "grad_norm": 0.49479084006465096,
+      "learning_rate": 5.7123935081125034e-05,
+      "loss": 0.4408,
+      "step": 116
+    },
+    {
+      "epoch": 1.2770592239618788,
+      "grad_norm": 0.7116517379970301,
+      "learning_rate": 5.6659003961743965e-05,
+      "loss": 0.4455,
+      "step": 117
+    },
+    {
+      "epoch": 1.2879509870660313,
+      "grad_norm": 0.6527860650845239,
+      "learning_rate": 5.619133372489575e-05,
+      "loss": 0.4362,
+      "step": 118
+    },
+    {
+      "epoch": 1.2988427501701838,
+      "grad_norm": 0.5221316831765591,
+      "learning_rate": 5.572100126615695e-05,
+      "loss": 0.4483,
+      "step": 119
+    },
+    {
+      "epoch": 1.3097345132743363,
+      "grad_norm": 0.36665207601249333,
+      "learning_rate": 5.524808391883367e-05,
+      "loss": 0.4488,
+      "step": 120
+    },
+    {
+      "epoch": 1.3206262763784888,
+      "grad_norm": 0.41335991497113145,
+      "learning_rate": 5.477265944124626e-05,
+      "loss": 0.4466,
+      "step": 121
+    },
+    {
+      "epoch": 1.3315180394826411,
+      "grad_norm": 0.4288901779920896,
+      "learning_rate": 5.429480600394405e-05,
+      "loss": 0.4455,
+      "step": 122
+    },
+    {
+      "epoch": 1.3424098025867937,
+      "grad_norm": 0.4476404528186165,
+      "learning_rate": 5.381460217685231e-05,
+      "loss": 0.4409,
+      "step": 123
+    },
+    {
+      "epoch": 1.3533015656909462,
+      "grad_norm": 0.3975466345144197,
+      "learning_rate": 5.333212691635368e-05,
+      "loss": 0.4368,
+      "step": 124
+    },
+    {
+      "epoch": 1.3641933287950987,
+      "grad_norm": 0.3833210592542072,
+      "learning_rate": 5.2847459552305834e-05,
+      "loss": 0.4414,
+      "step": 125
+    },
+    {
+      "epoch": 1.3750850918992512,
+      "grad_norm": 0.38028400797503575,
+      "learning_rate": 5.23606797749979e-05,
+      "loss": 0.4342,
+      "step": 126
+    },
+    {
+      "epoch": 1.3859768550034037,
+      "grad_norm": 0.29336709544411704,
+      "learning_rate": 5.1871867622047624e-05,
+      "loss": 0.4349,
+      "step": 127
+    },
+    {
+      "epoch": 1.3968686181075562,
+      "grad_norm": 0.4021055378411946,
+      "learning_rate": 5.13811034652413e-05,
+      "loss": 0.4359,
+      "step": 128
+    },
+    {
+      "epoch": 1.4077603812117085,
+      "grad_norm": 0.36564910628203584,
+      "learning_rate": 5.088846799731885e-05,
+      "loss": 0.4449,
+      "step": 129
+    },
+    {
+      "epoch": 1.418652144315861,
+      "grad_norm": 0.3687189406492797,
+      "learning_rate": 5.039404221870612e-05,
+      "loss": 0.4384,
+      "step": 130
+    },
+    {
+      "epoch": 1.4295439074200136,
+      "grad_norm": 0.29150702350417407,
+      "learning_rate": 4.989790742419658e-05,
+      "loss": 0.4391,
+      "step": 131
+    },
+    {
+      "epoch": 1.440435670524166,
+      "grad_norm": 0.28941702462294044,
+      "learning_rate": 4.940014518958461e-05,
+      "loss": 0.435,
+      "step": 132
+    },
+    {
+      "epoch": 1.4513274336283186,
+      "grad_norm": 0.3046809035055879,
+      "learning_rate": 4.890083735825258e-05,
+      "loss": 0.4423,
+      "step": 133
+    },
+    {
+      "epoch": 1.4622191967324711,
+      "grad_norm": 0.3901636771063769,
+      "learning_rate": 4.8400066027713974e-05,
+      "loss": 0.4373,
+      "step": 134
+    },
+    {
+      "epoch": 1.4731109598366237,
+      "grad_norm": 0.2975253048975319,
+      "learning_rate": 4.789791353611469e-05,
+      "loss": 0.441,
+      "step": 135
+    },
+    {
+      "epoch": 1.484002722940776,
+      "grad_norm": 0.2861058200191958,
+      "learning_rate": 4.7394462448694756e-05,
+      "loss": 0.4392,
+      "step": 136
+    },
+    {
+      "epoch": 1.4948944860449285,
+      "grad_norm": 0.30291271659415053,
+      "learning_rate": 4.688979554421276e-05,
+      "loss": 0.4437,
+      "step": 137
+    },
+    {
+      "epoch": 1.505786249149081,
+      "grad_norm": 0.27992103529188517,
+      "learning_rate": 4.6383995801335176e-05,
+      "loss": 0.4448,
+      "step": 138
+    },
+    {
+      "epoch": 1.5166780122532335,
+      "grad_norm": 0.25747738933655456,
+      "learning_rate": 4.5877146384992725e-05,
+      "loss": 0.4431,
+      "step": 139
+    },
+    {
+      "epoch": 1.527569775357386,
+      "grad_norm": 0.341071325514537,
+      "learning_rate": 4.5369330632706223e-05,
+      "loss": 0.4331,
+      "step": 140
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.2602954860252923,
+      "learning_rate": 4.486063204088402e-05,
+      "loss": 0.4433,
+      "step": 141
+    },
+    {
+      "epoch": 1.549353301565691,
+      "grad_norm": 0.23767705409963544,
+      "learning_rate": 4.435113425109324e-05,
+      "loss": 0.4337,
+      "step": 142
+    },
+    {
+      "epoch": 1.5602450646698434,
+      "grad_norm": 0.29322114556856593,
+      "learning_rate": 4.3840921036307274e-05,
+      "loss": 0.4387,
+      "step": 143
+    },
+    {
+      "epoch": 1.5711368277739959,
+      "grad_norm": 0.2171415398561475,
+      "learning_rate": 4.333007628713158e-05,
+      "loss": 0.4333,
+      "step": 144
+    },
+    {
+      "epoch": 1.5820285908781484,
+      "grad_norm": 0.26753092128368694,
+      "learning_rate": 4.281868399801016e-05,
+      "loss": 0.4375,
+      "step": 145
+    },
+    {
+      "epoch": 1.592920353982301,
+      "grad_norm": 0.2577848543389177,
+      "learning_rate": 4.230682825341498e-05,
+      "loss": 0.4331,
+      "step": 146
+    },
+    {
+      "epoch": 1.6038121170864534,
+      "grad_norm": 0.23037795102518452,
+      "learning_rate": 4.17945932140206e-05,
+      "loss": 0.4432,
+      "step": 147
+    },
+    {
+      "epoch": 1.6147038801906057,
+      "grad_norm": 0.22432493774064247,
+      "learning_rate": 4.128206310286622e-05,
+      "loss": 0.433,
+      "step": 148
+    },
+    {
+      "epoch": 1.6255956432947585,
+      "grad_norm": 0.27660950965609943,
+      "learning_rate": 4.0769322191507485e-05,
+      "loss": 0.4291,
+      "step": 149
+    },
+    {
+      "epoch": 1.6364874063989108,
+      "grad_norm": 0.29639803872823944,
+      "learning_rate": 4.025645478616045e-05,
+      "loss": 0.4479,
+      "step": 150
+    },
+    {
+      "epoch": 1.6473791695030633,
+      "grad_norm": 0.22551842554518517,
+      "learning_rate": 3.974354521383956e-05,
+      "loss": 0.4305,
+      "step": 151
+    },
+    {
+      "epoch": 1.6582709326072158,
+      "grad_norm": 0.21855552569143427,
+      "learning_rate": 3.923067780849252e-05,
+      "loss": 0.4341,
+      "step": 152
+    },
+    {
+      "epoch": 1.6691626957113683,
+      "grad_norm": 0.25345471682479176,
+      "learning_rate": 3.87179368971338e-05,
+      "loss": 0.4332,
+      "step": 153
+    },
+    {
+      "epoch": 1.6800544588155208,
+      "grad_norm": 0.3294043510791402,
+      "learning_rate": 3.820540678597942e-05,
+      "loss": 0.4324,
+      "step": 154
+    },
+    {
+      "epoch": 1.6909462219196731,
+      "grad_norm": 0.2915052857817396,
+      "learning_rate": 3.769317174658503e-05,
+      "loss": 0.4289,
+      "step": 155
+    },
+    {
+      "epoch": 1.7018379850238259,
+      "grad_norm": 0.20123186425930717,
+      "learning_rate": 3.718131600198984e-05,
+      "loss": 0.4414,
+      "step": 156
+    },
+    {
+      "epoch": 1.7127297481279782,
+      "grad_norm": 0.23019840765145663,
+      "learning_rate": 3.666992371286843e-05,
+      "loss": 0.4341,
+      "step": 157
+    },
+    {
+      "epoch": 1.7236215112321307,
+      "grad_norm": 0.2075296642104422,
+      "learning_rate": 3.615907896369273e-05,
+      "loss": 0.4391,
+      "step": 158
+    },
+    {
+      "epoch": 1.7345132743362832,
+      "grad_norm": 0.20499145565748494,
+      "learning_rate": 3.564886574890677e-05,
+      "loss": 0.4368,
+      "step": 159
+    },
+    {
+      "epoch": 1.7454050374404355,
+      "grad_norm": 0.2270936672913207,
+      "learning_rate": 3.5139367959115986e-05,
+      "loss": 0.4362,
+      "step": 160
+    },
+    {
+      "epoch": 1.7562968005445883,
+      "grad_norm": 0.20695924414455472,
+      "learning_rate": 3.4630669367293797e-05,
+      "loss": 0.4321,
+      "step": 161
+    },
+    {
+      "epoch": 1.7671885636487406,
+      "grad_norm": 0.20145634393976244,
+      "learning_rate": 3.412285361500729e-05,
+      "loss": 0.4327,
+      "step": 162
+    },
+    {
+      "epoch": 1.778080326752893,
+      "grad_norm": 0.1954369301373391,
+      "learning_rate": 3.3616004198664845e-05,
+      "loss": 0.4324,
+      "step": 163
+    },
+    {
+      "epoch": 1.7889720898570456,
+      "grad_norm": 0.20481400956545093,
+      "learning_rate": 3.311020445578725e-05,
+      "loss": 0.4377,
+      "step": 164
+    },
+    {
+      "epoch": 1.799863852961198,
+      "grad_norm": 0.2162909320824147,
+      "learning_rate": 3.260553755130525e-05,
+      "loss": 0.4299,
+      "step": 165
+    },
+    {
+      "epoch": 1.8107556160653506,
+      "grad_norm": 0.1811829339048361,
+      "learning_rate": 3.210208646388532e-05,
+      "loss": 0.43,
+      "step": 166
+    },
+    {
+      "epoch": 1.821647379169503,
+      "grad_norm": 0.2086574503584923,
+      "learning_rate": 3.1599933972286026e-05,
+      "loss": 0.4346,
+      "step": 167
+    },
+    {
+      "epoch": 1.8325391422736557,
+      "grad_norm": 0.22526815431719788,
+      "learning_rate": 3.109916264174743e-05,
+      "loss": 0.4288,
+      "step": 168
+    },
+    {
+      "epoch": 1.843430905377808,
+      "grad_norm": 0.18015782113002662,
+      "learning_rate": 3.0599854810415393e-05,
+      "loss": 0.428,
+      "step": 169
+    },
+    {
+      "epoch": 1.8543226684819605,
+      "grad_norm": 0.20990114701229817,
+      "learning_rate": 3.0102092575803435e-05,
+      "loss": 0.4333,
+      "step": 170
+    },
+    {
+      "epoch": 1.865214431586113,
+      "grad_norm": 0.1988483391924283,
+      "learning_rate": 2.9605957781293893e-05,
+      "loss": 0.4346,
+      "step": 171
+    },
+    {
+      "epoch": 1.8761061946902655,
+      "grad_norm": 0.19078378305907726,
+      "learning_rate": 2.911153200268116e-05,
+      "loss": 0.4251,
+      "step": 172
+    },
+    {
+      "epoch": 1.886997957794418,
+      "grad_norm": 0.23446180498320415,
+      "learning_rate": 2.8618896534758707e-05,
+      "loss": 0.4377,
+      "step": 173
+    },
+    {
+      "epoch": 1.8978897208985703,
+      "grad_norm": 0.1761870449513099,
+      "learning_rate": 2.8128132377952376e-05,
+      "loss": 0.4227,
+      "step": 174
+    },
+    {
+      "epoch": 1.908781484002723,
+      "grad_norm": 0.2332557884998122,
+      "learning_rate": 2.7639320225002108e-05,
+      "loss": 0.4325,
+      "step": 175
+    },
+    {
+      "epoch": 1.9196732471068754,
+      "grad_norm": 0.2211426717672741,
+      "learning_rate": 2.715254044769418e-05,
+      "loss": 0.4308,
+      "step": 176
+    },
+    {
+      "epoch": 1.9305650102110279,
+      "grad_norm": 0.18328106510038045,
+      "learning_rate": 2.666787308364634e-05,
+      "loss": 0.4322,
+      "step": 177
+    },
+    {
+      "epoch": 1.9414567733151804,
+      "grad_norm": 0.2288520554831422,
+      "learning_rate": 2.6185397823147703e-05,
+      "loss": 0.4263,
+      "step": 178
+    },
+    {
+      "epoch": 1.952348536419333,
+      "grad_norm": 0.17271019835077814,
+      "learning_rate": 2.5705193996055977e-05,
+      "loss": 0.4231,
+      "step": 179
+    },
+    {
+      "epoch": 1.9632402995234854,
+      "grad_norm": 0.21114296576465388,
+      "learning_rate": 2.5227340558753755e-05,
+      "loss": 0.4323,
+      "step": 180
+    },
+    {
+      "epoch": 1.9741320626276377,
+      "grad_norm": 0.1708320475165614,
+      "learning_rate": 2.4751916081166336e-05,
+      "loss": 0.4318,
+      "step": 181
+    },
+    {
+      "epoch": 1.9850238257317905,
+      "grad_norm": 0.20243633225986957,
+      "learning_rate": 2.427899873384306e-05,
+      "loss": 0.4284,
+      "step": 182
+    },
+    {
+      "epoch": 1.9959155888359428,
+      "grad_norm": 0.17214298347005028,
+      "learning_rate": 2.3808666275104248e-05,
+      "loss": 0.4303,
+      "step": 183
+    },
+    {
+      "epoch": 2.0095302927161334,
+      "grad_norm": 0.2371948537766053,
+      "learning_rate": 2.334099603825605e-05,
+      "loss": 0.4195,
+      "step": 184
+    },
+    {
+      "epoch": 2.020422055820286,
+      "grad_norm": 0.20683435017217672,
+      "learning_rate": 2.2876064918874993e-05,
+      "loss": 0.4056,
+      "step": 185
+    },
+    {
+      "epoch": 2.0313138189244384,
+      "grad_norm": 0.2132114122172093,
+      "learning_rate": 2.241394936216472e-05,
+      "loss": 0.4033,
+      "step": 186
+    },
+    {
+      "epoch": 2.0422055820285907,
+      "grad_norm": 0.19087121395561507,
+      "learning_rate": 2.1954725350386614e-05,
+      "loss": 0.405,
+      "step": 187
+    },
+    {
+      "epoch": 2.0530973451327434,
+      "grad_norm": 0.21040243392909405,
+      "learning_rate": 2.14984683903666e-05,
+      "loss": 0.4094,
+      "step": 188
+    },
+    {
+      "epoch": 2.0639891082368957,
+      "grad_norm": 0.16468816702883052,
+      "learning_rate": 2.1045253501080058e-05,
+      "loss": 0.3988,
+      "step": 189
+    },
+    {
+      "epoch": 2.0748808713410485,
+      "grad_norm": 0.17523456140653074,
+      "learning_rate": 2.0595155201317115e-05,
+      "loss": 0.4009,
+      "step": 190
+    },
+    {
+      "epoch": 2.085772634445201,
+      "grad_norm": 0.19773800473297834,
+      "learning_rate": 2.0148247497430012e-05,
+      "loss": 0.4016,
+      "step": 191
+    },
+    {
+      "epoch": 2.096664397549353,
+      "grad_norm": 0.1647636735264003,
+      "learning_rate": 1.970460387116472e-05,
+      "loss": 0.3948,
+      "step": 192
+    },
+    {
+      "epoch": 2.107556160653506,
+      "grad_norm": 0.18353188744441096,
+      "learning_rate": 1.9264297267579e-05,
+      "loss": 0.3995,
+      "step": 193
+    },
+    {
+      "epoch": 2.118447923757658,
+      "grad_norm": 0.1804931450578559,
+      "learning_rate": 1.8827400083048503e-05,
+      "loss": 0.404,
+      "step": 194
+    },
+    {
+      "epoch": 2.129339686861811,
+      "grad_norm": 0.16921208996470288,
+      "learning_rate": 1.8393984153363203e-05,
+      "loss": 0.3886,
+      "step": 195
+    },
+    {
+      "epoch": 2.140231449965963,
+      "grad_norm": 0.15129405097453685,
+      "learning_rate": 1.7964120741915905e-05,
+      "loss": 0.4082,
+      "step": 196
+    },
+    {
+      "epoch": 2.151123213070116,
+      "grad_norm": 0.17224554916641183,
+      "learning_rate": 1.753788052798501e-05,
+      "loss": 0.3994,
+      "step": 197
+    },
+    {
+      "epoch": 2.162014976174268,
+      "grad_norm": 0.15770956818834928,
+      "learning_rate": 1.7115333595113225e-05,
+      "loss": 0.403,
+      "step": 198
+    },
+    {
+      "epoch": 2.172906739278421,
+      "grad_norm": 0.1716039599905281,
+      "learning_rate": 1.669654941958416e-05,
+      "loss": 0.4032,
+      "step": 199
+    },
+    {
+      "epoch": 2.1837985023825732,
+      "grad_norm": 0.16454710212660165,
+      "learning_rate": 1.628159685899897e-05,
+      "loss": 0.405,
+      "step": 200
+    },
+    {
+      "epoch": 2.1946902654867255,
+      "grad_norm": 0.13993922901377312,
+      "learning_rate": 1.5870544140954543e-05,
+      "loss": 0.4077,
+      "step": 201
+    },
+    {
+      "epoch": 2.2055820285908783,
+      "grad_norm": 0.16301323668704157,
+      "learning_rate": 1.5463458851825345e-05,
+      "loss": 0.4053,
+      "step": 202
+    },
+    {
+      "epoch": 2.2164737916950306,
+      "grad_norm": 0.15989174020128882,
+      "learning_rate": 1.5060407925650662e-05,
+      "loss": 0.4036,
+      "step": 203
+    },
+    {
+      "epoch": 2.2273655547991833,
+      "grad_norm": 0.14155165998806302,
+      "learning_rate": 1.466145763312922e-05,
+      "loss": 0.4021,
+      "step": 204
+    },
+    {
+      "epoch": 2.2382573179033356,
+      "grad_norm": 0.13197910914100647,
+      "learning_rate": 1.426667357072265e-05,
+      "loss": 0.403,
+      "step": 205
+    },
+    {
+      "epoch": 2.249149081007488,
+      "grad_norm": 0.1502501179431283,
+      "learning_rate": 1.3876120649870051e-05,
+      "loss": 0.4068,
+      "step": 206
+    },
+    {
+      "epoch": 2.2600408441116406,
+      "grad_norm": 0.12632548576221497,
+      "learning_rate": 1.3489863086315085e-05,
+      "loss": 0.3954,
+      "step": 207
+    },
+    {
+      "epoch": 2.270932607215793,
+      "grad_norm": 0.12310652443499624,
+      "learning_rate": 1.3107964389547326e-05,
+      "loss": 0.4056,
+      "step": 208
+    },
+    {
+      "epoch": 2.2818243703199457,
+      "grad_norm": 0.13232393309386553,
+      "learning_rate": 1.2730487352360026e-05,
+      "loss": 0.4028,
+      "step": 209
+    },
+    {
+      "epoch": 2.292716133424098,
+      "grad_norm": 0.12337150415039137,
+      "learning_rate": 1.2357494040525416e-05,
+      "loss": 0.4125,
+      "step": 210
+    },
+    {
+      "epoch": 2.3036078965282503,
+      "grad_norm": 0.11483009808175632,
+      "learning_rate": 1.1989045782589815e-05,
+      "loss": 0.404,
+      "step": 211
+    },
+    {
+      "epoch": 2.314499659632403,
+      "grad_norm": 0.1213039797258653,
+      "learning_rate": 1.1625203159789686e-05,
+      "loss": 0.398,
+      "step": 212
+    },
+    {
+      "epoch": 2.3253914227365553,
+      "grad_norm": 0.1296712824505999,
+      "learning_rate": 1.1266025996090902e-05,
+      "loss": 0.4103,
+      "step": 213
+    },
+    {
+      "epoch": 2.336283185840708,
+      "grad_norm": 0.12739388021409695,
+      "learning_rate": 1.0911573348352107e-05,
+      "loss": 0.4054,
+      "step": 214
+    },
+    {
+      "epoch": 2.3471749489448603,
+      "grad_norm": 0.11766621480801555,
+      "learning_rate": 1.0561903496614603e-05,
+      "loss": 0.4036,
+      "step": 215
+    },
+    {
+      "epoch": 2.358066712049013,
+      "grad_norm": 0.12339813858079209,
+      "learning_rate": 1.0217073934519726e-05,
+      "loss": 0.4012,
+      "step": 216
+    },
+    {
+      "epoch": 2.3689584751531654,
+      "grad_norm": 0.11647805921713034,
+      "learning_rate": 9.877141359855567e-06,
+      "loss": 0.4109,
+      "step": 217
+    },
+    {
+      "epoch": 2.379850238257318,
+      "grad_norm": 0.109735463051235,
+      "learning_rate": 9.542161665234623e-06,
+      "loss": 0.3991,
+      "step": 218
+    },
+    {
+      "epoch": 2.3907420013614704,
+      "grad_norm": 0.1181837766256319,
+      "learning_rate": 9.212189928903758e-06,
+      "loss": 0.4008,
+      "step": 219
+    },
+    {
+      "epoch": 2.4016337644656227,
+      "grad_norm": 0.12247494016760661,
+      "learning_rate": 8.887280405688106e-06,
+      "loss": 0.4044,
+      "step": 220
+    },
+    {
+      "epoch": 2.4125255275697755,
+      "grad_norm": 0.11192215755173132,
+      "learning_rate": 8.567486518070306e-06,
+      "loss": 0.3992,
+      "step": 221
+    },
+    {
+      "epoch": 2.4234172906739277,
+      "grad_norm": 0.109297303198497,
+      "learning_rate": 8.252860847406712e-06,
+      "loss": 0.3948,
+      "step": 222
+    },
+    {
+      "epoch": 2.4343090537780805,
+      "grad_norm": 0.11284991227332902,
+      "learning_rate": 7.943455125281741e-06,
+      "loss": 0.3995,
+      "step": 223
+    },
+    {
+      "epoch": 2.445200816882233,
+      "grad_norm": 0.11548250618562617,
+      "learning_rate": 7.639320225002106e-06,
+      "loss": 0.407,
+      "step": 224
+    },
+    {
+      "epoch": 2.456092579986385,
+      "grad_norm": 0.116001123064691,
+      "learning_rate": 7.340506153232052e-06,
+      "loss": 0.4,
+      "step": 225
+    },
+    {
+      "epoch": 2.466984343090538,
+      "grad_norm": 0.10992561869419722,
+      "learning_rate": 7.047062041771133e-06,
+      "loss": 0.4045,
+      "step": 226
+    },
+    {
+      "epoch": 2.47787610619469,
+      "grad_norm": 0.10955112339301888,
+      "learning_rate": 6.759036139475843e-06,
+      "loss": 0.3964,
+      "step": 227
+    },
+    {
+      "epoch": 2.488767869298843,
+      "grad_norm": 0.11910747258190017,
+      "learning_rate": 6.476475804326377e-06,
+      "loss": 0.4025,
+      "step": 228
+    },
+    {
+      "epoch": 2.499659632402995,
+      "grad_norm": 0.116651055560925,
+      "learning_rate": 6.199427495639963e-06,
+      "loss": 0.3994,
+      "step": 229
+    },
+    {
+      "epoch": 2.5105513955071475,
+      "grad_norm": 0.1138861345434715,
+      "learning_rate": 5.927936766431836e-06,
+      "loss": 0.4022,
+      "step": 230
+    },
+    {
+      "epoch": 2.5214431586113,
+      "grad_norm": 0.09848824385777599,
+      "learning_rate": 5.662048255925357e-06,
+      "loss": 0.3988,
+      "step": 231
+    },
+    {
+      "epoch": 2.532334921715453,
+      "grad_norm": 0.10150492531984864,
+      "learning_rate": 5.40180568221226e-06,
+      "loss": 0.4047,
+      "step": 232
+    },
+    {
+      "epoch": 2.5432266848196052,
+      "grad_norm": 0.11056977593577616,
+      "learning_rate": 5.147251835064424e-06,
+      "loss": 0.4057,
+      "step": 233
+    },
+    {
+      "epoch": 2.5541184479237575,
+      "grad_norm": 0.10655441819972683,
+      "learning_rate": 4.898428568898288e-06,
+      "loss": 0.3971,
+      "step": 234
+    },
+    {
+      "epoch": 2.5650102110279103,
+      "grad_norm": 0.10580636847333873,
+      "learning_rate": 4.65537679589299e-06,
+      "loss": 0.4045,
+      "step": 235
+    },
+    {
+      "epoch": 2.5759019741320626,
+      "grad_norm": 0.09908356652521799,
+      "learning_rate": 4.418136479263533e-06,
+      "loss": 0.4004,
+      "step": 236
+    },
+    {
+      "epoch": 2.5867937372362153,
+      "grad_norm": 0.09287282151185479,
+      "learning_rate": 4.186746626689879e-06,
+      "loss": 0.4006,
+      "step": 237
+    },
+    {
+      "epoch": 2.5976855003403676,
+      "grad_norm": 0.11618401418689138,
+      "learning_rate": 3.961245283903239e-06,
+      "loss": 0.4025,
+      "step": 238
+    },
+    {
+      "epoch": 2.60857726344452,
+      "grad_norm": 0.09813772046749265,
+      "learning_rate": 3.7416695284304737e-06,
+      "loss": 0.4051,
+      "step": 239
+    },
+    {
+      "epoch": 2.6194690265486726,
+      "grad_norm": 0.08852232603950476,
+      "learning_rate": 3.5280554634977217e-06,
+      "loss": 0.4013,
+      "step": 240
+    },
+    {
+      "epoch": 2.630360789652825,
+      "grad_norm": 0.09394838490800748,
+      "learning_rate": 3.320438212094197e-06,
+      "loss": 0.4059,
+      "step": 241
+    },
+    {
+      "epoch": 2.6412525527569777,
+      "grad_norm": 0.09059231002024923,
+      "learning_rate": 3.1188519111971804e-06,
+      "loss": 0.4039,
+      "step": 242
+    },
+    {
+      "epoch": 2.65214431586113,
+      "grad_norm": 0.09411366384619929,
+      "learning_rate": 2.9233297061591346e-06,
+      "loss": 0.3973,
+      "step": 243
+    },
+    {
+      "epoch": 2.6630360789652823,
+      "grad_norm": 0.09939434350976686,
+      "learning_rate": 2.733903745257838e-06,
+      "loss": 0.4049,
+      "step": 244
+    },
+    {
+      "epoch": 2.673927842069435,
+      "grad_norm": 0.09359826061681908,
+      "learning_rate": 2.550605174410512e-06,
+      "loss": 0.4017,
+      "step": 245
+    },
+    {
+      "epoch": 2.6848196051735873,
+      "grad_norm": 0.09354919223068338,
+      "learning_rate": 2.373464132052701e-06,
+      "loss": 0.4115,
+      "step": 246
+    },
+    {
+      "epoch": 2.69571136827774,
+      "grad_norm": 0.09746026612098238,
+      "learning_rate": 2.202509744182835e-06,
+      "loss": 0.3982,
+      "step": 247
+    },
+    {
+      "epoch": 2.7066031313818923,
+      "grad_norm": 0.09168148902821703,
+      "learning_rate": 2.0377701195732545e-06,
+      "loss": 0.4071,
+      "step": 248
+    },
+    {
+      "epoch": 2.717494894486045,
+      "grad_norm": 0.09074247743593482,
+      "learning_rate": 1.879272345148513e-06,
+      "loss": 0.4101,
+      "step": 249
+    },
+    {
+      "epoch": 2.7283866575901974,
+      "grad_norm": 0.09117996023348725,
+      "learning_rate": 1.727042481531651e-06,
+      "loss": 0.4035,
+      "step": 250
+    },
+    {
+      "epoch": 2.73927842069435,
+      "grad_norm": 0.09180074130441847,
+      "learning_rate": 1.5811055587592283e-06,
+      "loss": 0.4009,
+      "step": 251
+    },
+    {
+      "epoch": 2.7501701837985024,
+      "grad_norm": 0.08657516729277243,
+      "learning_rate": 1.4414855721658705e-06,
+      "loss": 0.4041,
+      "step": 252
+    },
+    {
+      "epoch": 2.7610619469026547,
+      "grad_norm": 0.09146051585946402,
+      "learning_rate": 1.3082054784388221e-06,
+      "loss": 0.4055,
+      "step": 253
+    },
+    {
+      "epoch": 2.7719537100068075,
+      "grad_norm": 0.09305195530663764,
+      "learning_rate": 1.1812871918434143e-06,
+      "loss": 0.4027,
+      "step": 254
+    },
+    {
+      "epoch": 2.7828454731109598,
+      "grad_norm": 0.09703421946821408,
+      "learning_rate": 1.0607515806198142e-06,
+      "loss": 0.4079,
+      "step": 255
+    },
+    {
+      "epoch": 2.7937372362151125,
+      "grad_norm": 0.08906174726324725,
+      "learning_rate": 9.466184635518361e-07,
+      "loss": 0.4017,
+      "step": 256
+    },
+    {
+      "epoch": 2.804628999319265,
+      "grad_norm": 0.08574571986172967,
+      "learning_rate": 8.389066067082852e-07,
+      "loss": 0.3967,
+      "step": 257
+    },
+    {
+      "epoch": 2.815520762423417,
+      "grad_norm": 0.0880676756279348,
+      "learning_rate": 7.376337203573824e-07,
+      "loss": 0.406,
+      "step": 258
+    },
+    {
+      "epoch": 2.82641252552757,
+      "grad_norm": 0.08789941779545143,
+      "learning_rate": 6.428164560548134e-07,
+      "loss": 0.4076,
+      "step": 259
+    },
+    {
+      "epoch": 2.837304288631722,
+      "grad_norm": 0.08553769033856681,
+      "learning_rate": 5.544704039058025e-07,
+      "loss": 0.3983,
+      "step": 260
+    },
+    {
+      "epoch": 2.848196051735875,
+      "grad_norm": 0.08010149417951533,
+      "learning_rate": 4.7261009000177274e-07,
+      "loss": 0.3918,
+      "step": 261
+    },
+    {
+      "epoch": 2.859087814840027,
+      "grad_norm": 0.07962434672916259,
+      "learning_rate": 3.972489740319274e-07,
+      "loss": 0.3924,
+      "step": 262
+    },
+    {
+      "epoch": 2.8699795779441795,
+      "grad_norm": 0.08482433839475353,
+      "learning_rate": 3.283994470701579e-07,
+      "loss": 0.4057,
+      "step": 263
+    },
+    {
+      "epoch": 2.880871341048332,
+      "grad_norm": 0.08350491927147591,
+      "learning_rate": 2.66072829537678e-07,
+      "loss": 0.4099,
+      "step": 264
+    },
+    {
+      "epoch": 2.891763104152485,
+      "grad_norm": 0.0880658902471283,
+      "learning_rate": 2.102793693417038e-07,
+      "loss": 0.4073,
+      "step": 265
+    },
+    {
+      "epoch": 2.9026548672566372,
+      "grad_norm": 0.08328293731348216,
+      "learning_rate": 1.6102824019043728e-07,
+      "loss": 0.4002,
+      "step": 266
+    },
+    {
+      "epoch": 2.9135466303607895,
+      "grad_norm": 0.07841175895615185,
+      "learning_rate": 1.1832754008472614e-07,
+      "loss": 0.389,
+      "step": 267
+    },
+    {
+      "epoch": 2.9244383934649423,
+      "grad_norm": 0.08287793053425582,
+      "learning_rate": 8.21842899865466e-08,
+      "loss": 0.3955,
+      "step": 268
+    },
+    {
+      "epoch": 2.9353301565690946,
+      "grad_norm": 0.08049459789709469,
+      "learning_rate": 5.260443266462467e-08,
+      "loss": 0.3949,
+      "step": 269
+    },
+    {
+      "epoch": 2.9462219196732473,
+      "grad_norm": 0.086710676105483,
+      "learning_rate": 2.9592831717293326e-08,
+      "loss": 0.4072,
+      "step": 270
+    },
+    {
+      "epoch": 2.9571136827773996,
+      "grad_norm": 0.08154316295610879,
+      "learning_rate": 1.3153270772807702e-08,
+      "loss": 0.3967,
+      "step": 271
+    },
+    {
+      "epoch": 2.968005445881552,
+      "grad_norm": 0.08705352570078856,
+      "learning_rate": 3.2884528672294523e-09,
+      "loss": 0.395,
+      "step": 272
+    },
+    {
+      "epoch": 2.9788972089857046,
+      "grad_norm": 0.08297445165644558,
+      "learning_rate": 0.0,
+      "loss": 0.4097,
+      "step": 273
+    },
+    {
+      "epoch": 2.9788972089857046,
+      "step": 273,
+      "total_flos": 7.02510214541004e+18,
+      "train_loss": 0.464617241979082,
+      "train_runtime": 57723.5744,
+      "train_samples_per_second": 2.443,
+      "train_steps_per_second": 0.005
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 273,
+  "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": 7.02510214541004e+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 sha256:1af47f5342cbd8773365d38926c74cf71e5e6d70f24170c6f8fa8315553a1cb0
+size 7416