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

README.md

@@ -1,3 +1,63 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the cot_normal and the cot_math datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.3227
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

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 +1,12 @@
+{
+    "epoch": 1.9986348122866895,
+    "eval_loss": 0.32274916768074036,
+    "eval_runtime": 6.6209,
+    "eval_samples_per_second": 35.796,
+    "eval_steps_per_second": 9.062,
+    "total_flos": 86796684656640.0,
+    "train_loss": 0.2950779539965541,
+    "train_runtime": 2999.324,
+    "train_samples_per_second": 15.628,
+    "train_steps_per_second": 0.122
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "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
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.9986348122866895,
+    "eval_loss": 0.32274916768074036,
+    "eval_runtime": 6.6209,
+    "eval_samples_per_second": 35.796,
+    "eval_steps_per_second": 9.062
+}

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:f825f8754c339f92cf8e5bfc6124f4100ed13a38b95b334a78662172b9e7c54e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bcd955e8750f06de4aef14c63cc5cae3ab54188812e40bf098ca4fde9d0b19
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213bd8bf3cd08aab07b6eb39483110af224dc07037c8fecb8d27f24dcb883b85
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37dcac6b2eadd6b6c1ce5705b5c54d1aaa0576037bd8fb692a8b6dc237f12f5f
+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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.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": "<|im_end|>",
+  "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": 1.9986348122866895,
+    "total_flos": 86796684656640.0,
+    "train_loss": 0.2950779539965541,
+    "train_runtime": 2999.324,
+    "train_samples_per_second": 15.628,
+    "train_steps_per_second": 0.122
+}

trainer_log.jsonl

@@ -0,0 +1,367 @@
+{"current_steps": 1, "total_steps": 366, "loss": 0.5016, "lr": 2.702702702702703e-07, "epoch": 0.005460750853242321, "percentage": 0.27, "elapsed_time": "0:00:20", "remaining_time": "2:05:51"}
+{"current_steps": 2, "total_steps": 366, "loss": 0.5208, "lr": 5.405405405405406e-07, "epoch": 0.010921501706484642, "percentage": 0.55, "elapsed_time": "0:00:28", "remaining_time": "1:25:28"}
+{"current_steps": 3, "total_steps": 366, "loss": 0.4379, "lr": 8.108108108108109e-07, "epoch": 0.016382252559726963, "percentage": 0.82, "elapsed_time": "0:00:37", "remaining_time": "1:15:14"}
+{"current_steps": 4, "total_steps": 366, "loss": 0.4602, "lr": 1.0810810810810812e-06, "epoch": 0.021843003412969283, "percentage": 1.09, "elapsed_time": "0:00:45", "remaining_time": "1:09:07"}
+{"current_steps": 5, "total_steps": 366, "loss": 0.4578, "lr": 1.3513513513513515e-06, "epoch": 0.027303754266211604, "percentage": 1.37, "elapsed_time": "0:00:53", "remaining_time": "1:03:52"}
+{"current_steps": 6, "total_steps": 366, "loss": 0.4416, "lr": 1.6216216216216219e-06, "epoch": 0.032764505119453925, "percentage": 1.64, "elapsed_time": "0:01:02", "remaining_time": "1:02:20"}
+{"current_steps": 7, "total_steps": 366, "loss": 0.4635, "lr": 1.8918918918918922e-06, "epoch": 0.03822525597269624, "percentage": 1.91, "elapsed_time": "0:01:10", "remaining_time": "0:59:58"}
+{"current_steps": 8, "total_steps": 366, "loss": 0.4471, "lr": 2.1621621621621623e-06, "epoch": 0.04368600682593857, "percentage": 2.19, "elapsed_time": "0:01:18", "remaining_time": "0:58:45"}
+{"current_steps": 9, "total_steps": 366, "loss": 0.3669, "lr": 2.432432432432433e-06, "epoch": 0.049146757679180884, "percentage": 2.46, "elapsed_time": "0:01:27", "remaining_time": "0:57:49"}
+{"current_steps": 10, "total_steps": 366, "loss": 0.4232, "lr": 2.702702702702703e-06, "epoch": 0.05460750853242321, "percentage": 2.73, "elapsed_time": "0:01:35", "remaining_time": "0:56:56"}
+{"current_steps": 11, "total_steps": 366, "loss": 0.4105, "lr": 2.9729729729729736e-06, "epoch": 0.060068259385665526, "percentage": 3.01, "elapsed_time": "0:01:43", "remaining_time": "0:55:55"}
+{"current_steps": 12, "total_steps": 366, "loss": 0.386, "lr": 3.2432432432432437e-06, "epoch": 0.06552901023890785, "percentage": 3.28, "elapsed_time": "0:01:51", "remaining_time": "0:54:48"}
+{"current_steps": 13, "total_steps": 366, "loss": 0.405, "lr": 3.513513513513514e-06, "epoch": 0.07098976109215017, "percentage": 3.55, "elapsed_time": "0:01:58", "remaining_time": "0:53:43"}
+{"current_steps": 14, "total_steps": 366, "loss": 0.3908, "lr": 3.7837837837837844e-06, "epoch": 0.07645051194539249, "percentage": 3.83, "elapsed_time": "0:02:08", "remaining_time": "0:53:57"}
+{"current_steps": 15, "total_steps": 366, "loss": 0.3972, "lr": 4.0540540540540545e-06, "epoch": 0.08191126279863481, "percentage": 4.1, "elapsed_time": "0:02:16", "remaining_time": "0:53:14"}
+{"current_steps": 16, "total_steps": 366, "loss": 0.3739, "lr": 4.324324324324325e-06, "epoch": 0.08737201365187713, "percentage": 4.37, "elapsed_time": "0:02:25", "remaining_time": "0:53:08"}
+{"current_steps": 17, "total_steps": 366, "loss": 0.3521, "lr": 4.594594594594596e-06, "epoch": 0.09283276450511946, "percentage": 4.64, "elapsed_time": "0:02:34", "remaining_time": "0:52:45"}
+{"current_steps": 18, "total_steps": 366, "loss": 0.4348, "lr": 4.864864864864866e-06, "epoch": 0.09829351535836177, "percentage": 4.92, "elapsed_time": "0:02:42", "remaining_time": "0:52:14"}
+{"current_steps": 19, "total_steps": 366, "loss": 0.3949, "lr": 5.135135135135135e-06, "epoch": 0.1037542662116041, "percentage": 5.19, "elapsed_time": "0:02:51", "remaining_time": "0:52:10"}
+{"current_steps": 20, "total_steps": 366, "loss": 0.3775, "lr": 5.405405405405406e-06, "epoch": 0.10921501706484642, "percentage": 5.46, "elapsed_time": "0:02:58", "remaining_time": "0:51:34"}
+{"current_steps": 21, "total_steps": 366, "loss": 0.3721, "lr": 5.675675675675676e-06, "epoch": 0.11467576791808874, "percentage": 5.74, "elapsed_time": "0:03:06", "remaining_time": "0:50:59"}
+{"current_steps": 22, "total_steps": 366, "loss": 0.3884, "lr": 5.945945945945947e-06, "epoch": 0.12013651877133105, "percentage": 6.01, "elapsed_time": "0:03:14", "remaining_time": "0:50:35"}
+{"current_steps": 23, "total_steps": 366, "loss": 0.394, "lr": 6.2162162162162164e-06, "epoch": 0.12559726962457338, "percentage": 6.28, "elapsed_time": "0:03:22", "remaining_time": "0:50:17"}
+{"current_steps": 24, "total_steps": 366, "loss": 0.3664, "lr": 6.486486486486487e-06, "epoch": 0.1310580204778157, "percentage": 6.56, "elapsed_time": "0:03:33", "remaining_time": "0:50:38"}
+{"current_steps": 25, "total_steps": 366, "loss": 0.3872, "lr": 6.7567567567567575e-06, "epoch": 0.13651877133105803, "percentage": 6.83, "elapsed_time": "0:03:41", "remaining_time": "0:50:24"}
+{"current_steps": 26, "total_steps": 366, "loss": 0.3926, "lr": 7.027027027027028e-06, "epoch": 0.14197952218430035, "percentage": 7.1, "elapsed_time": "0:03:49", "remaining_time": "0:49:59"}
+{"current_steps": 27, "total_steps": 366, "loss": 0.3395, "lr": 7.297297297297298e-06, "epoch": 0.14744027303754267, "percentage": 7.38, "elapsed_time": "0:03:58", "remaining_time": "0:49:51"}
+{"current_steps": 28, "total_steps": 366, "loss": 0.3692, "lr": 7.567567567567569e-06, "epoch": 0.15290102389078497, "percentage": 7.65, "elapsed_time": "0:04:05", "remaining_time": "0:49:24"}
+{"current_steps": 29, "total_steps": 366, "loss": 0.3562, "lr": 7.837837837837838e-06, "epoch": 0.1583617747440273, "percentage": 7.92, "elapsed_time": "0:04:13", "remaining_time": "0:49:11"}
+{"current_steps": 30, "total_steps": 366, "loss": 0.3291, "lr": 8.108108108108109e-06, "epoch": 0.16382252559726962, "percentage": 8.2, "elapsed_time": "0:04:24", "remaining_time": "0:49:18"}
+{"current_steps": 31, "total_steps": 366, "loss": 0.3761, "lr": 8.378378378378378e-06, "epoch": 0.16928327645051194, "percentage": 8.47, "elapsed_time": "0:04:31", "remaining_time": "0:48:58"}
+{"current_steps": 32, "total_steps": 366, "loss": 0.3634, "lr": 8.64864864864865e-06, "epoch": 0.17474402730375427, "percentage": 8.74, "elapsed_time": "0:04:40", "remaining_time": "0:48:49"}
+{"current_steps": 33, "total_steps": 366, "loss": 0.4073, "lr": 8.91891891891892e-06, "epoch": 0.1802047781569966, "percentage": 9.02, "elapsed_time": "0:04:48", "remaining_time": "0:48:28"}
+{"current_steps": 34, "total_steps": 366, "loss": 0.3832, "lr": 9.189189189189191e-06, "epoch": 0.18566552901023892, "percentage": 9.29, "elapsed_time": "0:04:55", "remaining_time": "0:48:02"}
+{"current_steps": 35, "total_steps": 366, "loss": 0.366, "lr": 9.45945945945946e-06, "epoch": 0.19112627986348124, "percentage": 9.56, "elapsed_time": "0:05:03", "remaining_time": "0:47:49"}
+{"current_steps": 36, "total_steps": 366, "loss": 0.3828, "lr": 9.729729729729732e-06, "epoch": 0.19658703071672354, "percentage": 9.84, "elapsed_time": "0:05:10", "remaining_time": "0:47:27"}
+{"current_steps": 37, "total_steps": 366, "loss": 0.4253, "lr": 1e-05, "epoch": 0.20204778156996586, "percentage": 10.11, "elapsed_time": "0:05:18", "remaining_time": "0:47:10"}
+{"current_steps": 38, "total_steps": 366, "loss": 0.3426, "lr": 9.999772047343259e-06, "epoch": 0.2075085324232082, "percentage": 10.38, "elapsed_time": "0:05:28", "remaining_time": "0:47:13"}
+{"current_steps": 39, "total_steps": 366, "loss": 0.343, "lr": 9.999088210158001e-06, "epoch": 0.2129692832764505, "percentage": 10.66, "elapsed_time": "0:05:36", "remaining_time": "0:46:59"}
+{"current_steps": 40, "total_steps": 366, "loss": 0.325, "lr": 9.997948550797227e-06, "epoch": 0.21843003412969283, "percentage": 10.93, "elapsed_time": "0:05:45", "remaining_time": "0:46:56"}
+{"current_steps": 41, "total_steps": 366, "loss": 0.385, "lr": 9.99635317317629e-06, "epoch": 0.22389078498293516, "percentage": 11.2, "elapsed_time": "0:05:52", "remaining_time": "0:46:36"}
+{"current_steps": 42, "total_steps": 366, "loss": 0.3462, "lr": 9.994302222763415e-06, "epoch": 0.22935153583617748, "percentage": 11.48, "elapsed_time": "0:06:01", "remaining_time": "0:46:25"}
+{"current_steps": 43, "total_steps": 366, "loss": 0.3401, "lr": 9.991795886566443e-06, "epoch": 0.2348122866894198, "percentage": 11.75, "elapsed_time": "0:06:09", "remaining_time": "0:46:13"}
+{"current_steps": 44, "total_steps": 366, "loss": 0.3424, "lr": 9.988834393115768e-06, "epoch": 0.2402730375426621, "percentage": 12.02, "elapsed_time": "0:06:16", "remaining_time": "0:45:58"}
+{"current_steps": 45, "total_steps": 366, "loss": 0.3742, "lr": 9.98541801244351e-06, "epoch": 0.24573378839590443, "percentage": 12.3, "elapsed_time": "0:06:25", "remaining_time": "0:45:49"}
+{"current_steps": 46, "total_steps": 366, "loss": 0.3435, "lr": 9.981547056058893e-06, "epoch": 0.25119453924914675, "percentage": 12.57, "elapsed_time": "0:06:32", "remaining_time": "0:45:32"}
+{"current_steps": 47, "total_steps": 366, "loss": 0.3442, "lr": 9.977221876919833e-06, "epoch": 0.2566552901023891, "percentage": 12.84, "elapsed_time": "0:06:40", "remaining_time": "0:45:16"}
+{"current_steps": 48, "total_steps": 366, "loss": 0.358, "lr": 9.97244286940076e-06, "epoch": 0.2621160409556314, "percentage": 13.11, "elapsed_time": "0:06:49", "remaining_time": "0:45:12"}
+{"current_steps": 49, "total_steps": 366, "loss": 0.3329, "lr": 9.967210469256657e-06, "epoch": 0.2675767918088737, "percentage": 13.39, "elapsed_time": "0:06:57", "remaining_time": "0:45:03"}
+{"current_steps": 50, "total_steps": 366, "loss": 0.3474, "lr": 9.961525153583327e-06, "epoch": 0.27303754266211605, "percentage": 13.66, "elapsed_time": "0:07:05", "remaining_time": "0:44:51"}
+{"current_steps": 51, "total_steps": 366, "loss": 0.3364, "lr": 9.955387440773902e-06, "epoch": 0.2784982935153584, "percentage": 13.93, "elapsed_time": "0:07:13", "remaining_time": "0:44:35"}
+{"current_steps": 52, "total_steps": 366, "loss": 0.3684, "lr": 9.948797890471552e-06, "epoch": 0.2839590443686007, "percentage": 14.21, "elapsed_time": "0:07:20", "remaining_time": "0:44:20"}
+{"current_steps": 53, "total_steps": 366, "loss": 0.3564, "lr": 9.94175710351848e-06, "epoch": 0.289419795221843, "percentage": 14.48, "elapsed_time": "0:07:27", "remaining_time": "0:44:05"}
+{"current_steps": 54, "total_steps": 366, "loss": 0.3526, "lr": 9.93426572190112e-06, "epoch": 0.29488054607508535, "percentage": 14.75, "elapsed_time": "0:07:35", "remaining_time": "0:43:52"}
+{"current_steps": 55, "total_steps": 366, "loss": 0.3825, "lr": 9.926324428691612e-06, "epoch": 0.3003412969283277, "percentage": 15.03, "elapsed_time": "0:07:42", "remaining_time": "0:43:36"}
+{"current_steps": 56, "total_steps": 366, "loss": 0.3492, "lr": 9.917933947985508e-06, "epoch": 0.30580204778156994, "percentage": 15.3, "elapsed_time": "0:07:50", "remaining_time": "0:43:22"}
+{"current_steps": 57, "total_steps": 366, "loss": 0.3147, "lr": 9.909095044835755e-06, "epoch": 0.31126279863481227, "percentage": 15.57, "elapsed_time": "0:07:59", "remaining_time": "0:43:19"}
+{"current_steps": 58, "total_steps": 366, "loss": 0.3351, "lr": 9.899808525182935e-06, "epoch": 0.3167235494880546, "percentage": 15.85, "elapsed_time": "0:08:07", "remaining_time": "0:43:10"}
+{"current_steps": 59, "total_steps": 366, "loss": 0.3452, "lr": 9.89007523578178e-06, "epoch": 0.3221843003412969, "percentage": 16.12, "elapsed_time": "0:08:17", "remaining_time": "0:43:06"}
+{"current_steps": 60, "total_steps": 366, "loss": 0.3601, "lr": 9.879896064123961e-06, "epoch": 0.32764505119453924, "percentage": 16.39, "elapsed_time": "0:08:25", "remaining_time": "0:42:59"}
+{"current_steps": 61, "total_steps": 366, "loss": 0.3565, "lr": 9.869271938357168e-06, "epoch": 0.33310580204778156, "percentage": 16.67, "elapsed_time": "0:08:34", "remaining_time": "0:42:51"}
+{"current_steps": 62, "total_steps": 366, "loss": 0.3592, "lr": 9.858203827200477e-06, "epoch": 0.3385665529010239, "percentage": 16.94, "elapsed_time": "0:08:41", "remaining_time": "0:42:39"}
+{"current_steps": 63, "total_steps": 366, "loss": 0.3935, "lr": 9.846692739856023e-06, "epoch": 0.3440273037542662, "percentage": 17.21, "elapsed_time": "0:08:49", "remaining_time": "0:42:25"}
+{"current_steps": 64, "total_steps": 366, "loss": 0.3089, "lr": 9.834739725916988e-06, "epoch": 0.34948805460750854, "percentage": 17.49, "elapsed_time": "0:08:58", "remaining_time": "0:42:22"}
+{"current_steps": 65, "total_steps": 366, "loss": 0.313, "lr": 9.822345875271884e-06, "epoch": 0.35494880546075086, "percentage": 17.76, "elapsed_time": "0:09:08", "remaining_time": "0:42:19"}
+{"current_steps": 66, "total_steps": 366, "loss": 0.3355, "lr": 9.80951231800518e-06, "epoch": 0.3604095563139932, "percentage": 18.03, "elapsed_time": "0:09:16", "remaining_time": "0:42:09"}
+{"current_steps": 67, "total_steps": 366, "loss": 0.3067, "lr": 9.79624022429427e-06, "epoch": 0.3658703071672355, "percentage": 18.31, "elapsed_time": "0:09:26", "remaining_time": "0:42:06"}
+{"current_steps": 68, "total_steps": 366, "loss": 0.3593, "lr": 9.782530804302763e-06, "epoch": 0.37133105802047783, "percentage": 18.58, "elapsed_time": "0:09:33", "remaining_time": "0:41:53"}
+{"current_steps": 69, "total_steps": 366, "loss": 0.3629, "lr": 9.768385308070139e-06, "epoch": 0.37679180887372016, "percentage": 18.85, "elapsed_time": "0:09:41", "remaining_time": "0:41:42"}
+{"current_steps": 70, "total_steps": 366, "loss": 0.3458, "lr": 9.75380502539778e-06, "epoch": 0.3822525597269625, "percentage": 19.13, "elapsed_time": "0:09:48", "remaining_time": "0:41:28"}
+{"current_steps": 71, "total_steps": 366, "loss": 0.348, "lr": 9.738791285731353e-06, "epoch": 0.38771331058020475, "percentage": 19.4, "elapsed_time": "0:09:55", "remaining_time": "0:41:15"}
+{"current_steps": 72, "total_steps": 366, "loss": 0.3701, "lr": 9.723345458039595e-06, "epoch": 0.3931740614334471, "percentage": 19.67, "elapsed_time": "0:10:04", "remaining_time": "0:41:09"}
+{"current_steps": 73, "total_steps": 366, "loss": 0.3453, "lr": 9.70746895068949e-06, "epoch": 0.3986348122866894, "percentage": 19.95, "elapsed_time": "0:10:12", "remaining_time": "0:40:58"}
+{"current_steps": 74, "total_steps": 366, "loss": 0.3393, "lr": 9.691163211317853e-06, "epoch": 0.4040955631399317, "percentage": 20.22, "elapsed_time": "0:10:21", "remaining_time": "0:40:50"}
+{"current_steps": 75, "total_steps": 366, "loss": 0.3121, "lr": 9.674429726699324e-06, "epoch": 0.40955631399317405, "percentage": 20.49, "elapsed_time": "0:10:29", "remaining_time": "0:40:44"}
+{"current_steps": 76, "total_steps": 366, "loss": 0.3507, "lr": 9.657270022610814e-06, "epoch": 0.4150170648464164, "percentage": 20.77, "elapsed_time": "0:10:37", "remaining_time": "0:40:33"}
+{"current_steps": 77, "total_steps": 366, "loss": 0.3641, "lr": 9.63968566369238e-06, "epoch": 0.4204778156996587, "percentage": 21.04, "elapsed_time": "0:10:45", "remaining_time": "0:40:22"}
+{"current_steps": 78, "total_steps": 366, "loss": 0.3739, "lr": 9.62167825330455e-06, "epoch": 0.425938566552901, "percentage": 21.31, "elapsed_time": "0:10:53", "remaining_time": "0:40:11"}
+{"current_steps": 79, "total_steps": 366, "loss": 0.3185, "lr": 9.603249433382145e-06, "epoch": 0.43139931740614335, "percentage": 21.58, "elapsed_time": "0:11:02", "remaining_time": "0:40:05"}
+{"current_steps": 80, "total_steps": 366, "loss": 0.3415, "lr": 9.584400884284546e-06, "epoch": 0.43686006825938567, "percentage": 21.86, "elapsed_time": "0:11:10", "remaining_time": "0:39:57"}
+{"current_steps": 81, "total_steps": 366, "loss": 0.3331, "lr": 9.565134324642491e-06, "epoch": 0.442320819112628, "percentage": 22.13, "elapsed_time": "0:11:18", "remaining_time": "0:39:48"}
+{"current_steps": 82, "total_steps": 366, "loss": 0.322, "lr": 9.545451511201365e-06, "epoch": 0.4477815699658703, "percentage": 22.4, "elapsed_time": "0:11:27", "remaining_time": "0:39:40"}
+{"current_steps": 83, "total_steps": 366, "loss": 0.3476, "lr": 9.52535423866101e-06, "epoch": 0.45324232081911264, "percentage": 22.68, "elapsed_time": "0:11:35", "remaining_time": "0:39:32"}
+{"current_steps": 84, "total_steps": 366, "loss": 0.3671, "lr": 9.504844339512096e-06, "epoch": 0.45870307167235497, "percentage": 22.95, "elapsed_time": "0:11:42", "remaining_time": "0:39:19"}
+{"current_steps": 85, "total_steps": 366, "loss": 0.352, "lr": 9.483923683869025e-06, "epoch": 0.4641638225255973, "percentage": 23.22, "elapsed_time": "0:11:50", "remaining_time": "0:39:07"}
+{"current_steps": 86, "total_steps": 366, "loss": 0.3533, "lr": 9.462594179299408e-06, "epoch": 0.4696245733788396, "percentage": 23.5, "elapsed_time": "0:11:58", "remaining_time": "0:38:58"}
+{"current_steps": 87, "total_steps": 366, "loss": 0.3501, "lr": 9.440857770650139e-06, "epoch": 0.4750853242320819, "percentage": 23.77, "elapsed_time": "0:12:06", "remaining_time": "0:38:49"}
+{"current_steps": 88, "total_steps": 366, "loss": 0.3092, "lr": 9.418716439870056e-06, "epoch": 0.4805460750853242, "percentage": 24.04, "elapsed_time": "0:12:16", "remaining_time": "0:38:45"}
+{"current_steps": 89, "total_steps": 366, "loss": 0.3514, "lr": 9.396172205829235e-06, "epoch": 0.48600682593856653, "percentage": 24.32, "elapsed_time": "0:12:23", "remaining_time": "0:38:35"}
+{"current_steps": 90, "total_steps": 366, "loss": 0.3489, "lr": 9.373227124134888e-06, "epoch": 0.49146757679180886, "percentage": 24.59, "elapsed_time": "0:12:31", "remaining_time": "0:38:25"}
+{"current_steps": 91, "total_steps": 366, "loss": 0.3632, "lr": 9.349883286943951e-06, "epoch": 0.4969283276450512, "percentage": 24.86, "elapsed_time": "0:12:38", "remaining_time": "0:38:13"}
+{"current_steps": 92, "total_steps": 366, "loss": 0.3584, "lr": 9.326142822772301e-06, "epoch": 0.5023890784982935, "percentage": 25.14, "elapsed_time": "0:12:47", "remaining_time": "0:38:06"}
+{"current_steps": 93, "total_steps": 366, "loss": 0.3591, "lr": 9.302007896300697e-06, "epoch": 0.5078498293515359, "percentage": 25.41, "elapsed_time": "0:12:55", "remaining_time": "0:37:57"}
+{"current_steps": 94, "total_steps": 366, "loss": 0.3143, "lr": 9.27748070817738e-06, "epoch": 0.5133105802047782, "percentage": 25.68, "elapsed_time": "0:13:04", "remaining_time": "0:37:50"}
+{"current_steps": 95, "total_steps": 366, "loss": 0.3772, "lr": 9.252563494817426e-06, "epoch": 0.5187713310580204, "percentage": 25.96, "elapsed_time": "0:13:12", "remaining_time": "0:37:39"}
+{"current_steps": 96, "total_steps": 366, "loss": 0.3131, "lr": 9.227258528198832e-06, "epoch": 0.5242320819112628, "percentage": 26.23, "elapsed_time": "0:13:19", "remaining_time": "0:37:29"}
+{"current_steps": 97, "total_steps": 366, "loss": 0.329, "lr": 9.201568115655343e-06, "epoch": 0.5296928327645051, "percentage": 26.5, "elapsed_time": "0:13:27", "remaining_time": "0:37:19"}
+{"current_steps": 98, "total_steps": 366, "loss": 0.3278, "lr": 9.175494599666078e-06, "epoch": 0.5351535836177475, "percentage": 26.78, "elapsed_time": "0:13:36", "remaining_time": "0:37:11"}
+{"current_steps": 99, "total_steps": 366, "loss": 0.3225, "lr": 9.14904035764193e-06, "epoch": 0.5406143344709897, "percentage": 27.05, "elapsed_time": "0:13:44", "remaining_time": "0:37:03"}
+{"current_steps": 100, "total_steps": 366, "loss": 0.3524, "lr": 9.122207801708802e-06, "epoch": 0.5460750853242321, "percentage": 27.32, "elapsed_time": "0:13:52", "remaining_time": "0:36:54"}
+{"current_steps": 101, "total_steps": 366, "loss": 0.3546, "lr": 9.094999378487659e-06, "epoch": 0.5515358361774744, "percentage": 27.6, "elapsed_time": "0:14:00", "remaining_time": "0:36:44"}
+{"current_steps": 102, "total_steps": 366, "loss": 0.3548, "lr": 9.067417568871444e-06, "epoch": 0.5569965870307167, "percentage": 27.87, "elapsed_time": "0:14:07", "remaining_time": "0:36:34"}
+{"current_steps": 103, "total_steps": 366, "loss": 0.3439, "lr": 9.03946488779887e-06, "epoch": 0.562457337883959, "percentage": 28.14, "elapsed_time": "0:14:15", "remaining_time": "0:36:24"}
+{"current_steps": 104, "total_steps": 366, "loss": 0.3242, "lr": 9.0111438840251e-06, "epoch": 0.5679180887372014, "percentage": 28.42, "elapsed_time": "0:14:24", "remaining_time": "0:36:16"}
+{"current_steps": 105, "total_steps": 366, "loss": 0.3598, "lr": 8.982457139889358e-06, "epoch": 0.5733788395904437, "percentage": 28.69, "elapsed_time": "0:14:31", "remaining_time": "0:36:06"}
+{"current_steps": 106, "total_steps": 366, "loss": 0.3425, "lr": 8.953407271079456e-06, "epoch": 0.578839590443686, "percentage": 28.96, "elapsed_time": "0:14:38", "remaining_time": "0:35:55"}
+{"current_steps": 107, "total_steps": 366, "loss": 0.3795, "lr": 8.923996926393306e-06, "epoch": 0.5843003412969283, "percentage": 29.23, "elapsed_time": "0:14:46", "remaining_time": "0:35:45"}
+{"current_steps": 108, "total_steps": 366, "loss": 0.3555, "lr": 8.894228787497389e-06, "epoch": 0.5897610921501707, "percentage": 29.51, "elapsed_time": "0:14:54", "remaining_time": "0:35:37"}
+{"current_steps": 109, "total_steps": 366, "loss": 0.3425, "lr": 8.864105568682245e-06, "epoch": 0.595221843003413, "percentage": 29.78, "elapsed_time": "0:15:04", "remaining_time": "0:35:32"}
+{"current_steps": 110, "total_steps": 366, "loss": 0.3214, "lr": 8.833630016614976e-06, "epoch": 0.6006825938566553, "percentage": 30.05, "elapsed_time": "0:15:11", "remaining_time": "0:35:21"}
+{"current_steps": 111, "total_steps": 366, "loss": 0.3477, "lr": 8.80280491008881e-06, "epoch": 0.6061433447098976, "percentage": 30.33, "elapsed_time": "0:15:19", "remaining_time": "0:35:11"}
+{"current_steps": 112, "total_steps": 366, "loss": 0.3836, "lr": 8.771633059769712e-06, "epoch": 0.6116040955631399, "percentage": 30.6, "elapsed_time": "0:15:27", "remaining_time": "0:35:02"}
+{"current_steps": 113, "total_steps": 366, "loss": 0.3397, "lr": 8.740117307940123e-06, "epoch": 0.6170648464163823, "percentage": 30.87, "elapsed_time": "0:15:34", "remaining_time": "0:34:51"}
+{"current_steps": 114, "total_steps": 366, "loss": 0.3389, "lr": 8.708260528239788e-06, "epoch": 0.6225255972696245, "percentage": 31.15, "elapsed_time": "0:15:42", "remaining_time": "0:34:42"}
+{"current_steps": 115, "total_steps": 366, "loss": 0.3788, "lr": 8.676065625403733e-06, "epoch": 0.6279863481228669, "percentage": 31.42, "elapsed_time": "0:15:49", "remaining_time": "0:34:32"}
+{"current_steps": 116, "total_steps": 366, "loss": 0.3274, "lr": 8.64353553499741e-06, "epoch": 0.6334470989761092, "percentage": 31.69, "elapsed_time": "0:15:57", "remaining_time": "0:34:22"}
+{"current_steps": 117, "total_steps": 366, "loss": 0.3598, "lr": 8.610673223149036e-06, "epoch": 0.6389078498293516, "percentage": 31.97, "elapsed_time": "0:16:05", "remaining_time": "0:34:14"}
+{"current_steps": 118, "total_steps": 366, "loss": 0.3522, "lr": 8.577481686279123e-06, "epoch": 0.6443686006825938, "percentage": 32.24, "elapsed_time": "0:16:13", "remaining_time": "0:34:05"}
+{"current_steps": 119, "total_steps": 366, "loss": 0.3416, "lr": 8.543963950827279e-06, "epoch": 0.6498293515358362, "percentage": 32.51, "elapsed_time": "0:16:21", "remaining_time": "0:33:57"}
+{"current_steps": 120, "total_steps": 366, "loss": 0.341, "lr": 8.51012307297624e-06, "epoch": 0.6552901023890785, "percentage": 32.79, "elapsed_time": "0:16:29", "remaining_time": "0:33:47"}
+{"current_steps": 121, "total_steps": 366, "loss": 0.3268, "lr": 8.475962138373212e-06, "epoch": 0.6607508532423209, "percentage": 33.06, "elapsed_time": "0:16:38", "remaining_time": "0:33:40"}
+{"current_steps": 122, "total_steps": 366, "loss": 0.3744, "lr": 8.441484261848514e-06, "epoch": 0.6662116040955631, "percentage": 33.33, "elapsed_time": "0:16:45", "remaining_time": "0:33:30"}
+{"current_steps": 123, "total_steps": 366, "loss": 0.341, "lr": 8.406692587131569e-06, "epoch": 0.6716723549488055, "percentage": 33.61, "elapsed_time": "0:16:53", "remaining_time": "0:33:22"}
+{"current_steps": 124, "total_steps": 366, "loss": 0.3239, "lr": 8.371590286564247e-06, "epoch": 0.6771331058020478, "percentage": 33.88, "elapsed_time": "0:17:01", "remaining_time": "0:33:12"}
+{"current_steps": 125, "total_steps": 366, "loss": 0.3588, "lr": 8.336180560811619e-06, "epoch": 0.6825938566552902, "percentage": 34.15, "elapsed_time": "0:17:08", "remaining_time": "0:33:03"}
+{"current_steps": 126, "total_steps": 366, "loss": 0.3431, "lr": 8.30046663857011e-06, "epoch": 0.6880546075085324, "percentage": 34.43, "elapsed_time": "0:17:17", "remaining_time": "0:32:56"}
+{"current_steps": 127, "total_steps": 366, "loss": 0.3489, "lr": 8.264451776273104e-06, "epoch": 0.6935153583617747, "percentage": 34.7, "elapsed_time": "0:17:24", "remaining_time": "0:32:46"}
+{"current_steps": 128, "total_steps": 366, "loss": 0.3595, "lr": 8.228139257794012e-06, "epoch": 0.6989761092150171, "percentage": 34.97, "elapsed_time": "0:17:33", "remaining_time": "0:32:37"}
+{"current_steps": 129, "total_steps": 366, "loss": 0.328, "lr": 8.191532394146865e-06, "epoch": 0.7044368600682593, "percentage": 35.25, "elapsed_time": "0:17:40", "remaining_time": "0:32:29"}
+{"current_steps": 130, "total_steps": 366, "loss": 0.3392, "lr": 8.154634523184389e-06, "epoch": 0.7098976109215017, "percentage": 35.52, "elapsed_time": "0:17:48", "remaining_time": "0:32:20"}
+{"current_steps": 131, "total_steps": 366, "loss": 0.3482, "lr": 8.117449009293668e-06, "epoch": 0.715358361774744, "percentage": 35.79, "elapsed_time": "0:17:56", "remaining_time": "0:32:11"}
+{"current_steps": 132, "total_steps": 366, "loss": 0.3258, "lr": 8.07997924308938e-06, "epoch": 0.7208191126279864, "percentage": 36.07, "elapsed_time": "0:18:05", "remaining_time": "0:32:04"}
+{"current_steps": 133, "total_steps": 366, "loss": 0.3164, "lr": 8.042228641104622e-06, "epoch": 0.7262798634812286, "percentage": 36.34, "elapsed_time": "0:18:14", "remaining_time": "0:31:57"}
+{"current_steps": 134, "total_steps": 366, "loss": 0.3267, "lr": 8.004200645479403e-06, "epoch": 0.731740614334471, "percentage": 36.61, "elapsed_time": "0:18:24", "remaining_time": "0:31:51"}
+{"current_steps": 135, "total_steps": 366, "loss": 0.3556, "lr": 7.965898723646777e-06, "epoch": 0.7372013651877133, "percentage": 36.89, "elapsed_time": "0:18:31", "remaining_time": "0:31:41"}
+{"current_steps": 136, "total_steps": 366, "loss": 0.349, "lr": 7.927326368016677e-06, "epoch": 0.7426621160409557, "percentage": 37.16, "elapsed_time": "0:18:38", "remaining_time": "0:31:32"}
+{"current_steps": 137, "total_steps": 366, "loss": 0.3301, "lr": 7.888487095657484e-06, "epoch": 0.7481228668941979, "percentage": 37.43, "elapsed_time": "0:18:46", "remaining_time": "0:31:23"}
+{"current_steps": 138, "total_steps": 366, "loss": 0.3534, "lr": 7.849384447975322e-06, "epoch": 0.7535836177474403, "percentage": 37.7, "elapsed_time": "0:18:54", "remaining_time": "0:31:14"}
+{"current_steps": 139, "total_steps": 366, "loss": 0.3405, "lr": 7.810021990391163e-06, "epoch": 0.7590443686006826, "percentage": 37.98, "elapsed_time": "0:19:02", "remaining_time": "0:31:06"}
+{"current_steps": 140, "total_steps": 366, "loss": 0.3678, "lr": 7.77040331201572e-06, "epoch": 0.764505119453925, "percentage": 38.25, "elapsed_time": "0:19:11", "remaining_time": "0:30:58"}
+{"current_steps": 141, "total_steps": 366, "loss": 0.3469, "lr": 7.73053202532219e-06, "epoch": 0.7699658703071672, "percentage": 38.52, "elapsed_time": "0:19:18", "remaining_time": "0:30:48"}
+{"current_steps": 142, "total_steps": 366, "loss": 0.3395, "lr": 7.690411765816864e-06, "epoch": 0.7754266211604095, "percentage": 38.8, "elapsed_time": "0:19:25", "remaining_time": "0:30:39"}
+{"current_steps": 143, "total_steps": 366, "loss": 0.3352, "lr": 7.650046191707641e-06, "epoch": 0.7808873720136519, "percentage": 39.07, "elapsed_time": "0:19:33", "remaining_time": "0:30:29"}
+{"current_steps": 144, "total_steps": 366, "loss": 0.34, "lr": 7.609438983570461e-06, "epoch": 0.7863481228668942, "percentage": 39.34, "elapsed_time": "0:19:41", "remaining_time": "0:30:20"}
+{"current_steps": 145, "total_steps": 366, "loss": 0.3434, "lr": 7.5685938440137185e-06, "epoch": 0.7918088737201365, "percentage": 39.62, "elapsed_time": "0:19:49", "remaining_time": "0:30:13"}
+{"current_steps": 146, "total_steps": 366, "loss": 0.3536, "lr": 7.527514497340642e-06, "epoch": 0.7972696245733788, "percentage": 39.89, "elapsed_time": "0:19:57", "remaining_time": "0:30:04"}
+{"current_steps": 147, "total_steps": 366, "loss": 0.3071, "lr": 7.486204689209719e-06, "epoch": 0.8027303754266212, "percentage": 40.16, "elapsed_time": "0:20:06", "remaining_time": "0:29:57"}
+{"current_steps": 148, "total_steps": 366, "loss": 0.3318, "lr": 7.444668186293153e-06, "epoch": 0.8081911262798634, "percentage": 40.44, "elapsed_time": "0:20:15", "remaining_time": "0:29:49"}
+{"current_steps": 149, "total_steps": 366, "loss": 0.3282, "lr": 7.402908775933419e-06, "epoch": 0.8136518771331058, "percentage": 40.71, "elapsed_time": "0:20:22", "remaining_time": "0:29:41"}
+{"current_steps": 150, "total_steps": 366, "loss": 0.3592, "lr": 7.360930265797934e-06, "epoch": 0.8191126279863481, "percentage": 40.98, "elapsed_time": "0:20:30", "remaining_time": "0:29:31"}
+{"current_steps": 151, "total_steps": 366, "loss": 0.3455, "lr": 7.318736483531861e-06, "epoch": 0.8245733788395905, "percentage": 41.26, "elapsed_time": "0:20:37", "remaining_time": "0:29:22"}
+{"current_steps": 152, "total_steps": 366, "loss": 0.307, "lr": 7.2763312764091055e-06, "epoch": 0.8300341296928327, "percentage": 41.53, "elapsed_time": "0:20:45", "remaining_time": "0:29:13"}
+{"current_steps": 153, "total_steps": 366, "loss": 0.3104, "lr": 7.23371851098152e-06, "epoch": 0.8354948805460751, "percentage": 41.8, "elapsed_time": "0:20:53", "remaining_time": "0:29:05"}
+{"current_steps": 154, "total_steps": 366, "loss": 0.3601, "lr": 7.190902072726336e-06, "epoch": 0.8409556313993174, "percentage": 42.08, "elapsed_time": "0:21:01", "remaining_time": "0:28:57"}
+{"current_steps": 155, "total_steps": 366, "loss": 0.3592, "lr": 7.147885865691899e-06, "epoch": 0.8464163822525598, "percentage": 42.35, "elapsed_time": "0:21:09", "remaining_time": "0:28:48"}
+{"current_steps": 156, "total_steps": 366, "loss": 0.2919, "lr": 7.104673812141676e-06, "epoch": 0.851877133105802, "percentage": 42.62, "elapsed_time": "0:21:19", "remaining_time": "0:28:42"}
+{"current_steps": 157, "total_steps": 366, "loss": 0.345, "lr": 7.061269852196633e-06, "epoch": 0.8573378839590444, "percentage": 42.9, "elapsed_time": "0:21:27", "remaining_time": "0:28:34"}
+{"current_steps": 158, "total_steps": 366, "loss": 0.321, "lr": 7.017677943475962e-06, "epoch": 0.8627986348122867, "percentage": 43.17, "elapsed_time": "0:21:35", "remaining_time": "0:28:24"}
+{"current_steps": 159, "total_steps": 366, "loss": 0.3435, "lr": 6.973902060736226e-06, "epoch": 0.868259385665529, "percentage": 43.44, "elapsed_time": "0:21:43", "remaining_time": "0:28:17"}
+{"current_steps": 160, "total_steps": 366, "loss": 0.3163, "lr": 6.929946195508933e-06, "epoch": 0.8737201365187713, "percentage": 43.72, "elapsed_time": "0:21:51", "remaining_time": "0:28:08"}
+{"current_steps": 161, "total_steps": 366, "loss": 0.328, "lr": 6.8858143557365865e-06, "epoch": 0.8791808873720136, "percentage": 43.99, "elapsed_time": "0:22:00", "remaining_time": "0:28:01"}
+{"current_steps": 162, "total_steps": 366, "loss": 0.3341, "lr": 6.841510565407235e-06, "epoch": 0.884641638225256, "percentage": 44.26, "elapsed_time": "0:22:07", "remaining_time": "0:27:51"}
+{"current_steps": 163, "total_steps": 366, "loss": 0.3059, "lr": 6.797038864187564e-06, "epoch": 0.8901023890784983, "percentage": 44.54, "elapsed_time": "0:22:15", "remaining_time": "0:27:43"}
+{"current_steps": 164, "total_steps": 366, "loss": 0.3283, "lr": 6.752403307054549e-06, "epoch": 0.8955631399317406, "percentage": 44.81, "elapsed_time": "0:22:23", "remaining_time": "0:27:34"}
+{"current_steps": 165, "total_steps": 366, "loss": 0.3592, "lr": 6.707607963925725e-06, "epoch": 0.9010238907849829, "percentage": 45.08, "elapsed_time": "0:22:30", "remaining_time": "0:27:25"}
+{"current_steps": 166, "total_steps": 366, "loss": 0.3605, "lr": 6.66265691928808e-06, "epoch": 0.9064846416382253, "percentage": 45.36, "elapsed_time": "0:22:37", "remaining_time": "0:27:16"}
+{"current_steps": 167, "total_steps": 366, "loss": 0.3051, "lr": 6.617554271825636e-06, "epoch": 0.9119453924914676, "percentage": 45.63, "elapsed_time": "0:22:46", "remaining_time": "0:27:08"}
+{"current_steps": 168, "total_steps": 366, "loss": 0.3542, "lr": 6.5723041340457175e-06, "epoch": 0.9174061433447099, "percentage": 45.9, "elapsed_time": "0:22:54", "remaining_time": "0:27:00"}
+{"current_steps": 169, "total_steps": 366, "loss": 0.3254, "lr": 6.526910631903973e-06, "epoch": 0.9228668941979522, "percentage": 46.17, "elapsed_time": "0:23:02", "remaining_time": "0:26:51"}
+{"current_steps": 170, "total_steps": 366, "loss": 0.3297, "lr": 6.481377904428171e-06, "epoch": 0.9283276450511946, "percentage": 46.45, "elapsed_time": "0:23:10", "remaining_time": "0:26:43"}
+{"current_steps": 171, "total_steps": 366, "loss": 0.3531, "lr": 6.435710103340787e-06, "epoch": 0.9337883959044369, "percentage": 46.72, "elapsed_time": "0:23:18", "remaining_time": "0:26:34"}
+{"current_steps": 172, "total_steps": 366, "loss": 0.3279, "lr": 6.3899113926804565e-06, "epoch": 0.9392491467576792, "percentage": 46.99, "elapsed_time": "0:23:26", "remaining_time": "0:26:25"}
+{"current_steps": 173, "total_steps": 366, "loss": 0.3206, "lr": 6.3439859484222874e-06, "epoch": 0.9447098976109215, "percentage": 47.27, "elapsed_time": "0:23:34", "remaining_time": "0:26:17"}
+{"current_steps": 174, "total_steps": 366, "loss": 0.3185, "lr": 6.297937958097094e-06, "epoch": 0.9501706484641638, "percentage": 47.54, "elapsed_time": "0:23:41", "remaining_time": "0:26:08"}
+{"current_steps": 175, "total_steps": 366, "loss": 0.3408, "lr": 6.251771620409563e-06, "epoch": 0.9556313993174061, "percentage": 47.81, "elapsed_time": "0:23:49", "remaining_time": "0:25:59"}
+{"current_steps": 176, "total_steps": 366, "loss": 0.3388, "lr": 6.205491144855432e-06, "epoch": 0.9610921501706484, "percentage": 48.09, "elapsed_time": "0:23:57", "remaining_time": "0:25:51"}
+{"current_steps": 177, "total_steps": 366, "loss": 0.348, "lr": 6.1591007513376425e-06, "epoch": 0.9665529010238908, "percentage": 48.36, "elapsed_time": "0:24:06", "remaining_time": "0:25:44"}
+{"current_steps": 178, "total_steps": 366, "loss": 0.3187, "lr": 6.112604669781572e-06, "epoch": 0.9720136518771331, "percentage": 48.63, "elapsed_time": "0:24:14", "remaining_time": "0:25:36"}
+{"current_steps": 179, "total_steps": 366, "loss": 0.3112, "lr": 6.066007139749351e-06, "epoch": 0.9774744027303754, "percentage": 48.91, "elapsed_time": "0:24:21", "remaining_time": "0:25:27"}
+{"current_steps": 180, "total_steps": 366, "loss": 0.3115, "lr": 6.019312410053286e-06, "epoch": 0.9829351535836177, "percentage": 49.18, "elapsed_time": "0:24:29", "remaining_time": "0:25:18"}
+{"current_steps": 181, "total_steps": 366, "loss": 0.3015, "lr": 5.972524738368452e-06, "epoch": 0.9883959044368601, "percentage": 49.45, "elapsed_time": "0:24:37", "remaining_time": "0:25:09"}
+{"current_steps": 182, "total_steps": 366, "loss": 0.3405, "lr": 5.925648390844476e-06, "epoch": 0.9938566552901024, "percentage": 49.73, "elapsed_time": "0:24:45", "remaining_time": "0:25:01"}
+{"current_steps": 183, "total_steps": 366, "loss": 0.3241, "lr": 5.878687641716539e-06, "epoch": 0.9993174061433447, "percentage": 50.0, "elapsed_time": "0:24:54", "remaining_time": "0:24:54"}
+{"current_steps": 184, "total_steps": 366, "loss": 0.5887, "lr": 5.831646772915651e-06, "epoch": 1.004778156996587, "percentage": 50.27, "elapsed_time": "0:25:02", "remaining_time": "0:24:45"}
+{"current_steps": 185, "total_steps": 366, "loss": 0.2696, "lr": 5.7845300736782205e-06, "epoch": 1.0102389078498293, "percentage": 50.55, "elapsed_time": "0:25:10", "remaining_time": "0:24:37"}
+{"current_steps": 186, "total_steps": 366, "loss": 0.2179, "lr": 5.7373418401549565e-06, "epoch": 1.0156996587030718, "percentage": 50.82, "elapsed_time": "0:25:21", "remaining_time": "0:24:32"}
+{"current_steps": 187, "total_steps": 366, "loss": 0.2063, "lr": 5.690086375019135e-06, "epoch": 1.021160409556314, "percentage": 51.09, "elapsed_time": "0:25:29", "remaining_time": "0:24:23"}
+{"current_steps": 188, "total_steps": 366, "loss": 0.2395, "lr": 5.642767987074288e-06, "epoch": 1.0266211604095563, "percentage": 51.37, "elapsed_time": "0:25:38", "remaining_time": "0:24:16"}
+{"current_steps": 189, "total_steps": 366, "loss": 0.2593, "lr": 5.595390990861311e-06, "epoch": 1.0320819112627986, "percentage": 51.64, "elapsed_time": "0:25:47", "remaining_time": "0:24:08"}
+{"current_steps": 190, "total_steps": 366, "loss": 0.25, "lr": 5.547959706265068e-06, "epoch": 1.0375426621160408, "percentage": 51.91, "elapsed_time": "0:25:54", "remaining_time": "0:24:00"}
+{"current_steps": 191, "total_steps": 366, "loss": 0.2656, "lr": 5.500478458120493e-06, "epoch": 1.0430034129692833, "percentage": 52.19, "elapsed_time": "0:26:02", "remaining_time": "0:23:51"}
+{"current_steps": 192, "total_steps": 366, "loss": 0.2643, "lr": 5.45295157581825e-06, "epoch": 1.0484641638225256, "percentage": 52.46, "elapsed_time": "0:26:09", "remaining_time": "0:23:42"}
+{"current_steps": 193, "total_steps": 366, "loss": 0.2521, "lr": 5.405383392909973e-06, "epoch": 1.0539249146757679, "percentage": 52.73, "elapsed_time": "0:26:18", "remaining_time": "0:23:34"}
+{"current_steps": 194, "total_steps": 366, "loss": 0.254, "lr": 5.357778246713131e-06, "epoch": 1.0593856655290101, "percentage": 53.01, "elapsed_time": "0:26:25", "remaining_time": "0:23:25"}
+{"current_steps": 195, "total_steps": 366, "loss": 0.2303, "lr": 5.310140477915544e-06, "epoch": 1.0648464163822526, "percentage": 53.28, "elapsed_time": "0:26:32", "remaining_time": "0:23:16"}
+{"current_steps": 196, "total_steps": 366, "loss": 0.2587, "lr": 5.262474430179597e-06, "epoch": 1.070307167235495, "percentage": 53.55, "elapsed_time": "0:26:39", "remaining_time": "0:23:07"}
+{"current_steps": 197, "total_steps": 366, "loss": 0.2201, "lr": 5.2147844497461745e-06, "epoch": 1.0757679180887372, "percentage": 53.83, "elapsed_time": "0:26:48", "remaining_time": "0:22:59"}
+{"current_steps": 198, "total_steps": 366, "loss": 0.2131, "lr": 5.1670748850383734e-06, "epoch": 1.0812286689419794, "percentage": 54.1, "elapsed_time": "0:26:56", "remaining_time": "0:22:51"}
+{"current_steps": 199, "total_steps": 366, "loss": 0.2272, "lr": 5.1193500862650045e-06, "epoch": 1.086689419795222, "percentage": 54.37, "elapsed_time": "0:27:04", "remaining_time": "0:22:42"}
+{"current_steps": 200, "total_steps": 366, "loss": 0.2239, "lr": 5.071614405023938e-06, "epoch": 1.0921501706484642, "percentage": 54.64, "elapsed_time": "0:27:11", "remaining_time": "0:22:34"}
+{"current_steps": 201, "total_steps": 366, "loss": 0.2564, "lr": 5.023872193905316e-06, "epoch": 1.0976109215017065, "percentage": 54.92, "elapsed_time": "0:27:20", "remaining_time": "0:22:26"}
+{"current_steps": 202, "total_steps": 366, "loss": 0.2598, "lr": 4.976127806094685e-06, "epoch": 1.1030716723549487, "percentage": 55.19, "elapsed_time": "0:27:28", "remaining_time": "0:22:18"}
+{"current_steps": 203, "total_steps": 366, "loss": 0.2391, "lr": 4.928385594976063e-06, "epoch": 1.108532423208191, "percentage": 55.46, "elapsed_time": "0:27:36", "remaining_time": "0:22:09"}
+{"current_steps": 204, "total_steps": 366, "loss": 0.2111, "lr": 4.880649913734996e-06, "epoch": 1.1139931740614335, "percentage": 55.74, "elapsed_time": "0:27:44", "remaining_time": "0:22:02"}
+{"current_steps": 205, "total_steps": 366, "loss": 0.2291, "lr": 4.832925114961629e-06, "epoch": 1.1194539249146758, "percentage": 56.01, "elapsed_time": "0:27:52", "remaining_time": "0:21:53"}
+{"current_steps": 206, "total_steps": 366, "loss": 0.2237, "lr": 4.785215550253826e-06, "epoch": 1.124914675767918, "percentage": 56.28, "elapsed_time": "0:28:00", "remaining_time": "0:21:45"}
+{"current_steps": 207, "total_steps": 366, "loss": 0.2415, "lr": 4.737525569820405e-06, "epoch": 1.1303754266211605, "percentage": 56.56, "elapsed_time": "0:28:08", "remaining_time": "0:21:36"}
+{"current_steps": 208, "total_steps": 366, "loss": 0.2573, "lr": 4.689859522084457e-06, "epoch": 1.1358361774744028, "percentage": 56.83, "elapsed_time": "0:28:16", "remaining_time": "0:21:28"}
+{"current_steps": 209, "total_steps": 366, "loss": 0.2535, "lr": 4.64222175328687e-06, "epoch": 1.141296928327645, "percentage": 57.1, "elapsed_time": "0:28:24", "remaining_time": "0:21:20"}
+{"current_steps": 210, "total_steps": 366, "loss": 0.2284, "lr": 4.594616607090028e-06, "epoch": 1.1467576791808873, "percentage": 57.38, "elapsed_time": "0:28:34", "remaining_time": "0:21:13"}
+{"current_steps": 211, "total_steps": 366, "loss": 0.2294, "lr": 4.547048424181751e-06, "epoch": 1.1522184300341296, "percentage": 57.65, "elapsed_time": "0:28:42", "remaining_time": "0:21:05"}
+{"current_steps": 212, "total_steps": 366, "loss": 0.2226, "lr": 4.499521541879508e-06, "epoch": 1.157679180887372, "percentage": 57.92, "elapsed_time": "0:28:52", "remaining_time": "0:20:58"}
+{"current_steps": 213, "total_steps": 366, "loss": 0.2108, "lr": 4.452040293734934e-06, "epoch": 1.1631399317406144, "percentage": 58.2, "elapsed_time": "0:29:02", "remaining_time": "0:20:51"}
+{"current_steps": 214, "total_steps": 366, "loss": 0.2224, "lr": 4.40460900913869e-06, "epoch": 1.1686006825938566, "percentage": 58.47, "elapsed_time": "0:29:10", "remaining_time": "0:20:43"}
+{"current_steps": 215, "total_steps": 366, "loss": 0.2384, "lr": 4.357232012925714e-06, "epoch": 1.174061433447099, "percentage": 58.74, "elapsed_time": "0:29:18", "remaining_time": "0:20:35"}
+{"current_steps": 216, "total_steps": 366, "loss": 0.2347, "lr": 4.309913624980866e-06, "epoch": 1.1795221843003414, "percentage": 59.02, "elapsed_time": "0:29:26", "remaining_time": "0:20:26"}
+{"current_steps": 217, "total_steps": 366, "loss": 0.229, "lr": 4.262658159845046e-06, "epoch": 1.1849829351535837, "percentage": 59.29, "elapsed_time": "0:29:34", "remaining_time": "0:20:18"}
+{"current_steps": 218, "total_steps": 366, "loss": 0.2286, "lr": 4.2154699263217794e-06, "epoch": 1.190443686006826, "percentage": 59.56, "elapsed_time": "0:29:43", "remaining_time": "0:20:10"}
+{"current_steps": 219, "total_steps": 366, "loss": 0.2574, "lr": 4.1683532270843505e-06, "epoch": 1.1959044368600682, "percentage": 59.84, "elapsed_time": "0:29:51", "remaining_time": "0:20:02"}
+{"current_steps": 220, "total_steps": 366, "loss": 0.2149, "lr": 4.121312358283464e-06, "epoch": 1.2013651877133107, "percentage": 60.11, "elapsed_time": "0:30:00", "remaining_time": "0:19:54"}
+{"current_steps": 221, "total_steps": 366, "loss": 0.2381, "lr": 4.074351609155527e-06, "epoch": 1.206825938566553, "percentage": 60.38, "elapsed_time": "0:30:08", "remaining_time": "0:19:46"}
+{"current_steps": 222, "total_steps": 366, "loss": 0.2344, "lr": 4.0274752616315485e-06, "epoch": 1.2122866894197952, "percentage": 60.66, "elapsed_time": "0:30:16", "remaining_time": "0:19:38"}
+{"current_steps": 223, "total_steps": 366, "loss": 0.2319, "lr": 3.980687589946715e-06, "epoch": 1.2177474402730375, "percentage": 60.93, "elapsed_time": "0:30:24", "remaining_time": "0:19:30"}
+{"current_steps": 224, "total_steps": 366, "loss": 0.2497, "lr": 3.9339928602506505e-06, "epoch": 1.2232081911262798, "percentage": 61.2, "elapsed_time": "0:30:32", "remaining_time": "0:19:21"}
+{"current_steps": 225, "total_steps": 366, "loss": 0.2336, "lr": 3.887395330218429e-06, "epoch": 1.2286689419795223, "percentage": 61.48, "elapsed_time": "0:30:40", "remaining_time": "0:19:13"}
+{"current_steps": 226, "total_steps": 366, "loss": 0.2552, "lr": 3.840899248662358e-06, "epoch": 1.2341296928327645, "percentage": 61.75, "elapsed_time": "0:30:48", "remaining_time": "0:19:05"}
+{"current_steps": 227, "total_steps": 366, "loss": 0.2563, "lr": 3.7945088551445698e-06, "epoch": 1.2395904436860068, "percentage": 62.02, "elapsed_time": "0:30:57", "remaining_time": "0:18:57"}
+{"current_steps": 228, "total_steps": 366, "loss": 0.2291, "lr": 3.748228379590438e-06, "epoch": 1.245051194539249, "percentage": 62.3, "elapsed_time": "0:31:04", "remaining_time": "0:18:48"}
+{"current_steps": 229, "total_steps": 366, "loss": 0.2141, "lr": 3.7020620419029095e-06, "epoch": 1.2505119453924913, "percentage": 62.57, "elapsed_time": "0:31:12", "remaining_time": "0:18:40"}
+{"current_steps": 230, "total_steps": 366, "loss": 0.2122, "lr": 3.656014051577713e-06, "epoch": 1.2559726962457338, "percentage": 62.84, "elapsed_time": "0:31:22", "remaining_time": "0:18:33"}
+{"current_steps": 231, "total_steps": 366, "loss": 0.2367, "lr": 3.610088607319544e-06, "epoch": 1.261433447098976, "percentage": 63.11, "elapsed_time": "0:31:30", "remaining_time": "0:18:24"}
+{"current_steps": 232, "total_steps": 366, "loss": 0.235, "lr": 3.5642898966592145e-06, "epoch": 1.2668941979522184, "percentage": 63.39, "elapsed_time": "0:31:39", "remaining_time": "0:18:17"}
+{"current_steps": 233, "total_steps": 366, "loss": 0.2208, "lr": 3.518622095571831e-06, "epoch": 1.2723549488054609, "percentage": 63.66, "elapsed_time": "0:31:48", "remaining_time": "0:18:09"}
+{"current_steps": 234, "total_steps": 366, "loss": 0.2406, "lr": 3.4730893680960267e-06, "epoch": 1.2778156996587031, "percentage": 63.93, "elapsed_time": "0:31:56", "remaining_time": "0:18:01"}
+{"current_steps": 235, "total_steps": 366, "loss": 0.243, "lr": 3.4276958659542838e-06, "epoch": 1.2832764505119454, "percentage": 64.21, "elapsed_time": "0:32:03", "remaining_time": "0:17:52"}
+{"current_steps": 236, "total_steps": 366, "loss": 0.2586, "lr": 3.382445728174365e-06, "epoch": 1.2887372013651877, "percentage": 64.48, "elapsed_time": "0:32:11", "remaining_time": "0:17:43"}
+{"current_steps": 237, "total_steps": 366, "loss": 0.2251, "lr": 3.3373430807119212e-06, "epoch": 1.29419795221843, "percentage": 64.75, "elapsed_time": "0:32:21", "remaining_time": "0:17:36"}
+{"current_steps": 238, "total_steps": 366, "loss": 0.2316, "lr": 3.292392036074277e-06, "epoch": 1.2996587030716724, "percentage": 65.03, "elapsed_time": "0:32:28", "remaining_time": "0:17:28"}
+{"current_steps": 239, "total_steps": 366, "loss": 0.2384, "lr": 3.2475966929454505e-06, "epoch": 1.3051194539249147, "percentage": 65.3, "elapsed_time": "0:32:36", "remaining_time": "0:17:19"}
+{"current_steps": 240, "total_steps": 366, "loss": 0.248, "lr": 3.202961135812437e-06, "epoch": 1.310580204778157, "percentage": 65.57, "elapsed_time": "0:32:43", "remaining_time": "0:17:10"}
+{"current_steps": 241, "total_steps": 366, "loss": 0.2212, "lr": 3.1584894345927663e-06, "epoch": 1.3160409556313994, "percentage": 65.85, "elapsed_time": "0:32:52", "remaining_time": "0:17:02"}
+{"current_steps": 242, "total_steps": 366, "loss": 0.222, "lr": 3.114185644263415e-06, "epoch": 1.3215017064846417, "percentage": 66.12, "elapsed_time": "0:32:59", "remaining_time": "0:16:54"}
+{"current_steps": 243, "total_steps": 366, "loss": 0.2246, "lr": 3.0700538044910684e-06, "epoch": 1.326962457337884, "percentage": 66.39, "elapsed_time": "0:33:06", "remaining_time": "0:16:45"}
+{"current_steps": 244, "total_steps": 366, "loss": 0.2518, "lr": 3.0260979392637753e-06, "epoch": 1.3324232081911263, "percentage": 66.67, "elapsed_time": "0:33:14", "remaining_time": "0:16:37"}
+{"current_steps": 245, "total_steps": 366, "loss": 0.2224, "lr": 2.9823220565240396e-06, "epoch": 1.3378839590443685, "percentage": 66.94, "elapsed_time": "0:33:22", "remaining_time": "0:16:28"}
+{"current_steps": 246, "total_steps": 366, "loss": 0.2521, "lr": 2.9387301478033694e-06, "epoch": 1.343344709897611, "percentage": 67.21, "elapsed_time": "0:33:30", "remaining_time": "0:16:20"}
+{"current_steps": 247, "total_steps": 366, "loss": 0.2164, "lr": 2.8953261878583263e-06, "epoch": 1.3488054607508533, "percentage": 67.49, "elapsed_time": "0:33:39", "remaining_time": "0:16:13"}
+{"current_steps": 248, "total_steps": 366, "loss": 0.2532, "lr": 2.852114134308104e-06, "epoch": 1.3542662116040955, "percentage": 67.76, "elapsed_time": "0:33:46", "remaining_time": "0:16:04"}
+{"current_steps": 249, "total_steps": 366, "loss": 0.2401, "lr": 2.8090979272736663e-06, "epoch": 1.3597269624573378, "percentage": 68.03, "elapsed_time": "0:33:54", "remaining_time": "0:15:55"}
+{"current_steps": 250, "total_steps": 366, "loss": 0.2293, "lr": 2.766281489018482e-06, "epoch": 1.36518771331058, "percentage": 68.31, "elapsed_time": "0:34:02", "remaining_time": "0:15:47"}
+{"current_steps": 251, "total_steps": 366, "loss": 0.2188, "lr": 2.7236687235908953e-06, "epoch": 1.3706484641638226, "percentage": 68.58, "elapsed_time": "0:34:09", "remaining_time": "0:15:39"}
+{"current_steps": 252, "total_steps": 366, "loss": 0.2475, "lr": 2.681263516468139e-06, "epoch": 1.3761092150170648, "percentage": 68.85, "elapsed_time": "0:34:17", "remaining_time": "0:15:30"}
+{"current_steps": 253, "total_steps": 366, "loss": 0.2343, "lr": 2.6390697342020665e-06, "epoch": 1.3815699658703071, "percentage": 69.13, "elapsed_time": "0:34:24", "remaining_time": "0:15:22"}
+{"current_steps": 254, "total_steps": 366, "loss": 0.2353, "lr": 2.5970912240665815e-06, "epoch": 1.3870307167235496, "percentage": 69.4, "elapsed_time": "0:34:32", "remaining_time": "0:15:13"}
+{"current_steps": 255, "total_steps": 366, "loss": 0.2474, "lr": 2.5553318137068473e-06, "epoch": 1.3924914675767919, "percentage": 69.67, "elapsed_time": "0:34:40", "remaining_time": "0:15:05"}
+{"current_steps": 256, "total_steps": 366, "loss": 0.2322, "lr": 2.5137953107902814e-06, "epoch": 1.3979522184300341, "percentage": 69.95, "elapsed_time": "0:34:48", "remaining_time": "0:14:57"}
+{"current_steps": 257, "total_steps": 366, "loss": 0.2468, "lr": 2.472485502659358e-06, "epoch": 1.4034129692832764, "percentage": 70.22, "elapsed_time": "0:34:56", "remaining_time": "0:14:49"}
+{"current_steps": 258, "total_steps": 366, "loss": 0.2398, "lr": 2.4314061559862836e-06, "epoch": 1.4088737201365187, "percentage": 70.49, "elapsed_time": "0:35:05", "remaining_time": "0:14:41"}
+{"current_steps": 259, "total_steps": 366, "loss": 0.2329, "lr": 2.3905610164295394e-06, "epoch": 1.4143344709897612, "percentage": 70.77, "elapsed_time": "0:35:13", "remaining_time": "0:14:33"}
+{"current_steps": 260, "total_steps": 366, "loss": 0.2446, "lr": 2.3499538082923607e-06, "epoch": 1.4197952218430034, "percentage": 71.04, "elapsed_time": "0:35:21", "remaining_time": "0:14:24"}
+{"current_steps": 261, "total_steps": 366, "loss": 0.215, "lr": 2.309588234183137e-06, "epoch": 1.4252559726962457, "percentage": 71.31, "elapsed_time": "0:35:31", "remaining_time": "0:14:17"}
+{"current_steps": 262, "total_steps": 366, "loss": 0.2235, "lr": 2.2694679746778116e-06, "epoch": 1.430716723549488, "percentage": 71.58, "elapsed_time": "0:35:39", "remaining_time": "0:14:09"}
+{"current_steps": 263, "total_steps": 366, "loss": 0.21, "lr": 2.22959668798428e-06, "epoch": 1.4361774744027302, "percentage": 71.86, "elapsed_time": "0:35:48", "remaining_time": "0:14:01"}
+{"current_steps": 264, "total_steps": 366, "loss": 0.2609, "lr": 2.1899780096088375e-06, "epoch": 1.4416382252559727, "percentage": 72.13, "elapsed_time": "0:35:55", "remaining_time": "0:13:52"}
+{"current_steps": 265, "total_steps": 366, "loss": 0.2275, "lr": 2.1506155520246795e-06, "epoch": 1.447098976109215, "percentage": 72.4, "elapsed_time": "0:36:03", "remaining_time": "0:13:44"}
+{"current_steps": 266, "total_steps": 366, "loss": 0.2577, "lr": 2.1115129043425188e-06, "epoch": 1.4525597269624573, "percentage": 72.68, "elapsed_time": "0:36:11", "remaining_time": "0:13:36"}
+{"current_steps": 267, "total_steps": 366, "loss": 0.2583, "lr": 2.072673631983323e-06, "epoch": 1.4580204778156998, "percentage": 72.95, "elapsed_time": "0:36:19", "remaining_time": "0:13:28"}
+{"current_steps": 268, "total_steps": 366, "loss": 0.2252, "lr": 2.0341012763532243e-06, "epoch": 1.463481228668942, "percentage": 73.22, "elapsed_time": "0:36:27", "remaining_time": "0:13:19"}
+{"current_steps": 269, "total_steps": 366, "loss": 0.2282, "lr": 1.995799354520598e-06, "epoch": 1.4689419795221843, "percentage": 73.5, "elapsed_time": "0:36:34", "remaining_time": "0:13:11"}
+{"current_steps": 270, "total_steps": 366, "loss": 0.2204, "lr": 1.9577713588953797e-06, "epoch": 1.4744027303754266, "percentage": 73.77, "elapsed_time": "0:36:43", "remaining_time": "0:13:03"}
+{"current_steps": 271, "total_steps": 366, "loss": 0.2363, "lr": 1.9200207569106216e-06, "epoch": 1.4798634812286688, "percentage": 74.04, "elapsed_time": "0:36:50", "remaining_time": "0:12:54"}
+{"current_steps": 272, "total_steps": 366, "loss": 0.2312, "lr": 1.8825509907063328e-06, "epoch": 1.4853242320819113, "percentage": 74.32, "elapsed_time": "0:36:59", "remaining_time": "0:12:47"}
+{"current_steps": 273, "total_steps": 366, "loss": 0.2512, "lr": 1.8453654768156138e-06, "epoch": 1.4907849829351536, "percentage": 74.59, "elapsed_time": "0:37:07", "remaining_time": "0:12:38"}
+{"current_steps": 274, "total_steps": 366, "loss": 0.2285, "lr": 1.8084676058531376e-06, "epoch": 1.4962457337883959, "percentage": 74.86, "elapsed_time": "0:37:16", "remaining_time": "0:12:30"}
+{"current_steps": 275, "total_steps": 366, "loss": 0.2512, "lr": 1.771860742205988e-06, "epoch": 1.5017064846416384, "percentage": 75.14, "elapsed_time": "0:37:23", "remaining_time": "0:12:22"}
+{"current_steps": 276, "total_steps": 366, "loss": 0.2382, "lr": 1.7355482237268983e-06, "epoch": 1.5071672354948804, "percentage": 75.41, "elapsed_time": "0:37:31", "remaining_time": "0:12:14"}
+{"current_steps": 277, "total_steps": 366, "loss": 0.2097, "lr": 1.6995333614298908e-06, "epoch": 1.512627986348123, "percentage": 75.68, "elapsed_time": "0:37:39", "remaining_time": "0:12:06"}
+{"current_steps": 278, "total_steps": 366, "loss": 0.2352, "lr": 1.6638194391883822e-06, "epoch": 1.5180887372013652, "percentage": 75.96, "elapsed_time": "0:37:48", "remaining_time": "0:11:57"}
+{"current_steps": 279, "total_steps": 366, "loss": 0.2241, "lr": 1.6284097134357535e-06, "epoch": 1.5235494880546074, "percentage": 76.23, "elapsed_time": "0:37:55", "remaining_time": "0:11:49"}
+{"current_steps": 280, "total_steps": 366, "loss": 0.2149, "lr": 1.5933074128684333e-06, "epoch": 1.52901023890785, "percentage": 76.5, "elapsed_time": "0:38:03", "remaining_time": "0:11:41"}
+{"current_steps": 281, "total_steps": 366, "loss": 0.2629, "lr": 1.5585157381514875e-06, "epoch": 1.5344709897610922, "percentage": 76.78, "elapsed_time": "0:38:11", "remaining_time": "0:11:33"}
+{"current_steps": 282, "total_steps": 366, "loss": 0.2213, "lr": 1.5240378616267887e-06, "epoch": 1.5399317406143345, "percentage": 77.05, "elapsed_time": "0:38:18", "remaining_time": "0:11:24"}
+{"current_steps": 283, "total_steps": 366, "loss": 0.2469, "lr": 1.4898769270237611e-06, "epoch": 1.545392491467577, "percentage": 77.32, "elapsed_time": "0:38:26", "remaining_time": "0:11:16"}
+{"current_steps": 284, "total_steps": 366, "loss": 0.2369, "lr": 1.4560360491727233e-06, "epoch": 1.550853242320819, "percentage": 77.6, "elapsed_time": "0:38:35", "remaining_time": "0:11:08"}
+{"current_steps": 285, "total_steps": 366, "loss": 0.2464, "lr": 1.4225183137208775e-06, "epoch": 1.5563139931740615, "percentage": 77.87, "elapsed_time": "0:38:42", "remaining_time": "0:11:00"}
+{"current_steps": 286, "total_steps": 366, "loss": 0.2378, "lr": 1.389326776850966e-06, "epoch": 1.5617747440273038, "percentage": 78.14, "elapsed_time": "0:38:51", "remaining_time": "0:10:52"}
+{"current_steps": 287, "total_steps": 366, "loss": 0.2501, "lr": 1.3564644650025894e-06, "epoch": 1.567235494880546, "percentage": 78.42, "elapsed_time": "0:39:00", "remaining_time": "0:10:44"}
+{"current_steps": 288, "total_steps": 366, "loss": 0.2642, "lr": 1.323934374596268e-06, "epoch": 1.5726962457337885, "percentage": 78.69, "elapsed_time": "0:39:07", "remaining_time": "0:10:35"}
+{"current_steps": 289, "total_steps": 366, "loss": 0.2391, "lr": 1.2917394717602123e-06, "epoch": 1.5781569965870306, "percentage": 78.96, "elapsed_time": "0:39:14", "remaining_time": "0:10:27"}
+{"current_steps": 290, "total_steps": 366, "loss": 0.2471, "lr": 1.2598826920598773e-06, "epoch": 1.583617747440273, "percentage": 79.23, "elapsed_time": "0:39:22", "remaining_time": "0:10:19"}
+{"current_steps": 291, "total_steps": 366, "loss": 0.2441, "lr": 1.2283669402302878e-06, "epoch": 1.5890784982935153, "percentage": 79.51, "elapsed_time": "0:39:29", "remaining_time": "0:10:10"}
+{"current_steps": 292, "total_steps": 366, "loss": 0.2359, "lr": 1.197195089911191e-06, "epoch": 1.5945392491467576, "percentage": 79.78, "elapsed_time": "0:39:39", "remaining_time": "0:10:03"}
+{"current_steps": 293, "total_steps": 366, "loss": 0.2302, "lr": 1.166369983385024e-06, "epoch": 1.6, "percentage": 80.05, "elapsed_time": "0:39:47", "remaining_time": "0:09:54"}
+{"current_steps": 294, "total_steps": 366, "loss": 0.2312, "lr": 1.1358944313177566e-06, "epoch": 1.6054607508532424, "percentage": 80.33, "elapsed_time": "0:39:57", "remaining_time": "0:09:47"}
+{"current_steps": 295, "total_steps": 366, "loss": 0.2442, "lr": 1.1057712125026116e-06, "epoch": 1.6109215017064846, "percentage": 80.6, "elapsed_time": "0:40:04", "remaining_time": "0:09:38"}
+{"current_steps": 296, "total_steps": 366, "loss": 0.2297, "lr": 1.0760030736066952e-06, "epoch": 1.6163822525597271, "percentage": 80.87, "elapsed_time": "0:40:12", "remaining_time": "0:09:30"}
+{"current_steps": 297, "total_steps": 366, "loss": 0.2346, "lr": 1.0465927289205452e-06, "epoch": 1.6218430034129692, "percentage": 81.15, "elapsed_time": "0:40:20", "remaining_time": "0:09:22"}
+{"current_steps": 298, "total_steps": 366, "loss": 0.2119, "lr": 1.0175428601106441e-06, "epoch": 1.6273037542662117, "percentage": 81.42, "elapsed_time": "0:40:28", "remaining_time": "0:09:14"}
+{"current_steps": 299, "total_steps": 366, "loss": 0.2432, "lr": 9.888561159748995e-07, "epoch": 1.632764505119454, "percentage": 81.69, "elapsed_time": "0:40:37", "remaining_time": "0:09:06"}
+{"current_steps": 300, "total_steps": 366, "loss": 0.2392, "lr": 9.605351122011308e-07, "epoch": 1.6382252559726962, "percentage": 81.97, "elapsed_time": "0:40:45", "remaining_time": "0:08:57"}
+{"current_steps": 301, "total_steps": 366, "loss": 0.2173, "lr": 9.325824311285564e-07, "epoch": 1.6436860068259387, "percentage": 82.24, "elapsed_time": "0:40:53", "remaining_time": "0:08:49"}
+{"current_steps": 302, "total_steps": 366, "loss": 0.2606, "lr": 9.050006215123419e-07, "epoch": 1.6491467576791807, "percentage": 82.51, "elapsed_time": "0:41:00", "remaining_time": "0:08:41"}
+{"current_steps": 303, "total_steps": 366, "loss": 0.2214, "lr": 8.777921982911996e-07, "epoch": 1.6546075085324232, "percentage": 82.79, "elapsed_time": "0:41:09", "remaining_time": "0:08:33"}
+{"current_steps": 304, "total_steps": 366, "loss": 0.2464, "lr": 8.509596423580712e-07, "epoch": 1.6600682593856655, "percentage": 83.06, "elapsed_time": "0:41:17", "remaining_time": "0:08:25"}
+{"current_steps": 305, "total_steps": 366, "loss": 0.226, "lr": 8.245054003339247e-07, "epoch": 1.6655290102389078, "percentage": 83.33, "elapsed_time": "0:41:25", "remaining_time": "0:08:17"}
+{"current_steps": 306, "total_steps": 366, "loss": 0.2221, "lr": 7.984318843446593e-07, "epoch": 1.6709897610921502, "percentage": 83.61, "elapsed_time": "0:41:32", "remaining_time": "0:08:08"}
+{"current_steps": 307, "total_steps": 366, "loss": 0.2117, "lr": 7.727414718011706e-07, "epoch": 1.6764505119453925, "percentage": 83.88, "elapsed_time": "0:41:41", "remaining_time": "0:08:00"}
+{"current_steps": 308, "total_steps": 366, "loss": 0.257, "lr": 7.474365051825749e-07, "epoch": 1.6819112627986348, "percentage": 84.15, "elapsed_time": "0:41:49", "remaining_time": "0:07:52"}
+{"current_steps": 309, "total_steps": 366, "loss": 0.2395, "lr": 7.225192918226215e-07, "epoch": 1.6873720136518773, "percentage": 84.43, "elapsed_time": "0:41:57", "remaining_time": "0:07:44"}
+{"current_steps": 310, "total_steps": 366, "loss": 0.2233, "lr": 6.979921036993042e-07, "epoch": 1.6928327645051193, "percentage": 84.7, "elapsed_time": "0:42:05", "remaining_time": "0:07:36"}
+{"current_steps": 311, "total_steps": 366, "loss": 0.2416, "lr": 6.738571772276997e-07, "epoch": 1.6982935153583618, "percentage": 84.97, "elapsed_time": "0:42:13", "remaining_time": "0:07:28"}
+{"current_steps": 312, "total_steps": 366, "loss": 0.2283, "lr": 6.501167130560515e-07, "epoch": 1.703754266211604, "percentage": 85.25, "elapsed_time": "0:42:21", "remaining_time": "0:07:19"}
+{"current_steps": 313, "total_steps": 366, "loss": 0.2302, "lr": 6.267728758651131e-07, "epoch": 1.7092150170648464, "percentage": 85.52, "elapsed_time": "0:42:28", "remaining_time": "0:07:11"}
+{"current_steps": 314, "total_steps": 366, "loss": 0.2039, "lr": 6.038277941707671e-07, "epoch": 1.7146757679180888, "percentage": 85.79, "elapsed_time": "0:42:37", "remaining_time": "0:07:03"}
+{"current_steps": 315, "total_steps": 366, "loss": 0.254, "lr": 5.812835601299438e-07, "epoch": 1.7201365187713311, "percentage": 86.07, "elapsed_time": "0:42:44", "remaining_time": "0:06:55"}
+{"current_steps": 316, "total_steps": 366, "loss": 0.2074, "lr": 5.591422293498633e-07, "epoch": 1.7255972696245734, "percentage": 86.34, "elapsed_time": "0:42:54", "remaining_time": "0:06:47"}
+{"current_steps": 317, "total_steps": 366, "loss": 0.242, "lr": 5.374058207005945e-07, "epoch": 1.7310580204778157, "percentage": 86.61, "elapsed_time": "0:43:02", "remaining_time": "0:06:39"}
+{"current_steps": 318, "total_steps": 366, "loss": 0.2208, "lr": 5.160763161309768e-07, "epoch": 1.736518771331058, "percentage": 86.89, "elapsed_time": "0:43:10", "remaining_time": "0:06:31"}
+{"current_steps": 319, "total_steps": 366, "loss": 0.2167, "lr": 4.951556604879049e-07, "epoch": 1.7419795221843004, "percentage": 87.16, "elapsed_time": "0:43:19", "remaining_time": "0:06:22"}
+{"current_steps": 320, "total_steps": 366, "loss": 0.2208, "lr": 4.7464576133899043e-07, "epoch": 1.7474402730375427, "percentage": 87.43, "elapsed_time": "0:43:26", "remaining_time": "0:06:14"}
+{"current_steps": 321, "total_steps": 366, "loss": 0.2558, "lr": 4.545484887986368e-07, "epoch": 1.752901023890785, "percentage": 87.7, "elapsed_time": "0:43:33", "remaining_time": "0:06:06"}
+{"current_steps": 322, "total_steps": 366, "loss": 0.2412, "lr": 4.348656753575092e-07, "epoch": 1.7583617747440274, "percentage": 87.98, "elapsed_time": "0:43:41", "remaining_time": "0:05:58"}
+{"current_steps": 323, "total_steps": 366, "loss": 0.2302, "lr": 4.1559911571545544e-07, "epoch": 1.7638225255972695, "percentage": 88.25, "elapsed_time": "0:43:50", "remaining_time": "0:05:50"}
+{"current_steps": 324, "total_steps": 366, "loss": 0.2184, "lr": 3.9675056661785563e-07, "epoch": 1.769283276450512, "percentage": 88.52, "elapsed_time": "0:43:58", "remaining_time": "0:05:41"}
+{"current_steps": 325, "total_steps": 366, "loss": 0.2302, "lr": 3.783217466954503e-07, "epoch": 1.7747440273037542, "percentage": 88.8, "elapsed_time": "0:44:05", "remaining_time": "0:05:33"}
+{"current_steps": 326, "total_steps": 366, "loss": 0.2155, "lr": 3.603143363076217e-07, "epoch": 1.7802047781569965, "percentage": 89.07, "elapsed_time": "0:44:13", "remaining_time": "0:05:25"}
+{"current_steps": 327, "total_steps": 366, "loss": 0.2661, "lr": 3.427299773891868e-07, "epoch": 1.785665529010239, "percentage": 89.34, "elapsed_time": "0:44:20", "remaining_time": "0:05:17"}
+{"current_steps": 328, "total_steps": 366, "loss": 0.2338, "lr": 3.255702733006766e-07, "epoch": 1.7911262798634813, "percentage": 89.62, "elapsed_time": "0:44:28", "remaining_time": "0:05:09"}
+{"current_steps": 329, "total_steps": 366, "loss": 0.2514, "lr": 3.088367886821481e-07, "epoch": 1.7965870307167235, "percentage": 89.89, "elapsed_time": "0:44:36", "remaining_time": "0:05:00"}
+{"current_steps": 330, "total_steps": 366, "loss": 0.208, "lr": 2.925310493105099e-07, "epoch": 1.802047781569966, "percentage": 90.16, "elapsed_time": "0:44:44", "remaining_time": "0:04:52"}
+{"current_steps": 331, "total_steps": 366, "loss": 0.2568, "lr": 2.7665454196040665e-07, "epoch": 1.807508532423208, "percentage": 90.44, "elapsed_time": "0:44:51", "remaining_time": "0:04:44"}
+{"current_steps": 332, "total_steps": 366, "loss": 0.2445, "lr": 2.6120871426864866e-07, "epoch": 1.8129692832764506, "percentage": 90.71, "elapsed_time": "0:44:59", "remaining_time": "0:04:36"}
+{"current_steps": 333, "total_steps": 366, "loss": 0.2408, "lr": 2.4619497460222184e-07, "epoch": 1.8184300341296928, "percentage": 90.98, "elapsed_time": "0:45:06", "remaining_time": "0:04:28"}
+{"current_steps": 334, "total_steps": 366, "loss": 0.221, "lr": 2.316146919298623e-07, "epoch": 1.823890784982935, "percentage": 91.26, "elapsed_time": "0:45:13", "remaining_time": "0:04:20"}
+{"current_steps": 335, "total_steps": 366, "loss": 0.2137, "lr": 2.1746919569723858e-07, "epoch": 1.8293515358361776, "percentage": 91.53, "elapsed_time": "0:45:23", "remaining_time": "0:04:12"}
+{"current_steps": 336, "total_steps": 366, "loss": 0.2178, "lr": 2.037597757057297e-07, "epoch": 1.8348122866894196, "percentage": 91.8, "elapsed_time": "0:45:32", "remaining_time": "0:04:04"}
+{"current_steps": 337, "total_steps": 366, "loss": 0.2417, "lr": 1.9048768199481983e-07, "epoch": 1.8402730375426621, "percentage": 92.08, "elapsed_time": "0:45:40", "remaining_time": "0:03:55"}
+{"current_steps": 338, "total_steps": 366, "loss": 0.229, "lr": 1.776541247281177e-07, "epoch": 1.8457337883959044, "percentage": 92.35, "elapsed_time": "0:45:48", "remaining_time": "0:03:47"}
+{"current_steps": 339, "total_steps": 366, "loss": 0.2212, "lr": 1.6526027408301227e-07, "epoch": 1.8511945392491467, "percentage": 92.62, "elapsed_time": "0:45:56", "remaining_time": "0:03:39"}
+{"current_steps": 340, "total_steps": 366, "loss": 0.2301, "lr": 1.5330726014397668e-07, "epoch": 1.8566552901023892, "percentage": 92.9, "elapsed_time": "0:46:04", "remaining_time": "0:03:31"}
+{"current_steps": 341, "total_steps": 366, "loss": 0.2239, "lr": 1.417961727995254e-07, "epoch": 1.8621160409556314, "percentage": 93.17, "elapsed_time": "0:46:12", "remaining_time": "0:03:23"}
+{"current_steps": 342, "total_steps": 366, "loss": 0.2093, "lr": 1.307280616428336e-07, "epoch": 1.8675767918088737, "percentage": 93.44, "elapsed_time": "0:46:20", "remaining_time": "0:03:15"}
+{"current_steps": 343, "total_steps": 366, "loss": 0.2558, "lr": 1.2010393587603975e-07, "epoch": 1.8730375426621162, "percentage": 93.72, "elapsed_time": "0:46:28", "remaining_time": "0:03:07"}
+{"current_steps": 344, "total_steps": 366, "loss": 0.2217, "lr": 1.0992476421822052e-07, "epoch": 1.8784982935153582, "percentage": 93.99, "elapsed_time": "0:46:38", "remaining_time": "0:02:58"}
+{"current_steps": 345, "total_steps": 366, "loss": 0.2, "lr": 1.0019147481706626e-07, "epoch": 1.8839590443686007, "percentage": 94.26, "elapsed_time": "0:46:45", "remaining_time": "0:02:50"}
+{"current_steps": 346, "total_steps": 366, "loss": 0.2219, "lr": 9.090495516424713e-08, "epoch": 1.889419795221843, "percentage": 94.54, "elapsed_time": "0:46:53", "remaining_time": "0:02:42"}
+{"current_steps": 347, "total_steps": 366, "loss": 0.2029, "lr": 8.206605201449447e-08, "epoch": 1.8948805460750853, "percentage": 94.81, "elapsed_time": "0:47:01", "remaining_time": "0:02:34"}
+{"current_steps": 348, "total_steps": 366, "loss": 0.2256, "lr": 7.367557130838921e-08, "epoch": 1.9003412969283278, "percentage": 95.08, "elapsed_time": "0:47:09", "remaining_time": "0:02:26"}
+{"current_steps": 349, "total_steps": 366, "loss": 0.2003, "lr": 6.573427809888067e-08, "epoch": 1.9058020477815698, "percentage": 95.36, "elapsed_time": "0:47:17", "remaining_time": "0:02:18"}
+{"current_steps": 350, "total_steps": 366, "loss": 0.2395, "lr": 5.824289648152126e-08, "epoch": 1.9112627986348123, "percentage": 95.63, "elapsed_time": "0:47:25", "remaining_time": "0:02:10"}
+{"current_steps": 351, "total_steps": 366, "loss": 0.271, "lr": 5.120210952844873e-08, "epoch": 1.9167235494880546, "percentage": 95.9, "elapsed_time": "0:47:34", "remaining_time": "0:02:01"}
+{"current_steps": 352, "total_steps": 366, "loss": 0.2172, "lr": 4.461255922609986e-08, "epoch": 1.9221843003412968, "percentage": 96.17, "elapsed_time": "0:47:42", "remaining_time": "0:01:53"}
+{"current_steps": 353, "total_steps": 366, "loss": 0.2399, "lr": 3.8474846416672874e-08, "epoch": 1.9276450511945393, "percentage": 96.45, "elapsed_time": "0:47:51", "remaining_time": "0:01:45"}
+{"current_steps": 354, "total_steps": 366, "loss": 0.2212, "lr": 3.278953074334512e-08, "epoch": 1.9331058020477816, "percentage": 96.72, "elapsed_time": "0:47:58", "remaining_time": "0:01:37"}
+{"current_steps": 355, "total_steps": 366, "loss": 0.2374, "lr": 2.75571305992417e-08, "epoch": 1.9385665529010239, "percentage": 96.99, "elapsed_time": "0:48:06", "remaining_time": "0:01:29"}
+{"current_steps": 356, "total_steps": 366, "loss": 0.2317, "lr": 2.2778123080167136e-08, "epoch": 1.9440273037542664, "percentage": 97.27, "elapsed_time": "0:48:13", "remaining_time": "0:01:21"}
+{"current_steps": 357, "total_steps": 366, "loss": 0.2161, "lr": 1.845294394110686e-08, "epoch": 1.9494880546075084, "percentage": 97.54, "elapsed_time": "0:48:21", "remaining_time": "0:01:13"}
+{"current_steps": 358, "total_steps": 366, "loss": 0.2273, "lr": 1.4581987556490095e-08, "epoch": 1.954948805460751, "percentage": 97.81, "elapsed_time": "0:48:29", "remaining_time": "0:01:05"}
+{"current_steps": 359, "total_steps": 366, "loss": 0.2514, "lr": 1.1165606884234182e-08, "epoch": 1.9604095563139932, "percentage": 98.09, "elapsed_time": "0:48:38", "remaining_time": "0:00:56"}
+{"current_steps": 360, "total_steps": 366, "loss": 0.2248, "lr": 8.204113433559202e-09, "epoch": 1.9658703071672354, "percentage": 98.36, "elapsed_time": "0:48:45", "remaining_time": "0:00:48"}
+{"current_steps": 361, "total_steps": 366, "loss": 0.2415, "lr": 5.6977772365857105e-09, "epoch": 1.971331058020478, "percentage": 98.63, "elapsed_time": "0:48:52", "remaining_time": "0:00:40"}
+{"current_steps": 362, "total_steps": 366, "loss": 0.2319, "lr": 3.6468268237105364e-09, "epoch": 1.9767918088737202, "percentage": 98.91, "elapsed_time": "0:49:00", "remaining_time": "0:00:32"}
+{"current_steps": 363, "total_steps": 366, "loss": 0.2457, "lr": 2.0514492027728928e-09, "epoch": 1.9822525597269625, "percentage": 99.18, "elapsed_time": "0:49:08", "remaining_time": "0:00:24"}
+{"current_steps": 364, "total_steps": 366, "loss": 0.2574, "lr": 9.117898419991333e-10, "epoch": 1.9877133105802047, "percentage": 99.45, "elapsed_time": "0:49:15", "remaining_time": "0:00:16"}
+{"current_steps": 365, "total_steps": 366, "loss": 0.2499, "lr": 2.2795265674113721e-10, "epoch": 1.993174061433447, "percentage": 99.73, "elapsed_time": "0:49:23", "remaining_time": "0:00:08"}
+{"current_steps": 366, "total_steps": 366, "loss": 0.2179, "lr": 0.0, "epoch": 1.9986348122866895, "percentage": 100.0, "elapsed_time": "0:49:32", "remaining_time": "0:00:00"}
+{"current_steps": 366, "total_steps": 366, "epoch": 1.9986348122866895, "percentage": 100.0, "elapsed_time": "0:49:58", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2604 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9986348122866895,
+  "eval_steps": 500,
+  "global_step": 366,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005460750853242321,
+      "grad_norm": 3.971062381322324,
+      "learning_rate": 2.702702702702703e-07,
+      "loss": 0.5016,
+      "step": 1
+    },
+    {
+      "epoch": 0.010921501706484642,
+      "grad_norm": 4.14826323264813,
+      "learning_rate": 5.405405405405406e-07,
+      "loss": 0.5208,
+      "step": 2
+    },
+    {
+      "epoch": 0.016382252559726963,
+      "grad_norm": 3.745507693250097,
+      "learning_rate": 8.108108108108109e-07,
+      "loss": 0.4379,
+      "step": 3
+    },
+    {
+      "epoch": 0.021843003412969283,
+      "grad_norm": 3.8553920899968372,
+      "learning_rate": 1.0810810810810812e-06,
+      "loss": 0.4602,
+      "step": 4
+    },
+    {
+      "epoch": 0.027303754266211604,
+      "grad_norm": 4.006658163193665,
+      "learning_rate": 1.3513513513513515e-06,
+      "loss": 0.4578,
+      "step": 5
+    },
+    {
+      "epoch": 0.032764505119453925,
+      "grad_norm": 3.0693234037079433,
+      "learning_rate": 1.6216216216216219e-06,
+      "loss": 0.4416,
+      "step": 6
+    },
+    {
+      "epoch": 0.03822525597269624,
+      "grad_norm": 2.3221220798320386,
+      "learning_rate": 1.8918918918918922e-06,
+      "loss": 0.4635,
+      "step": 7
+    },
+    {
+      "epoch": 0.04368600682593857,
+      "grad_norm": 1.9622941289180669,
+      "learning_rate": 2.1621621621621623e-06,
+      "loss": 0.4471,
+      "step": 8
+    },
+    {
+      "epoch": 0.049146757679180884,
+      "grad_norm": 1.5785046223376498,
+      "learning_rate": 2.432432432432433e-06,
+      "loss": 0.3669,
+      "step": 9
+    },
+    {
+      "epoch": 0.05460750853242321,
+      "grad_norm": 1.592167130140165,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 0.4232,
+      "step": 10
+    },
+    {
+      "epoch": 0.060068259385665526,
+      "grad_norm": 1.4756853657479083,
+      "learning_rate": 2.9729729729729736e-06,
+      "loss": 0.4105,
+      "step": 11
+    },
+    {
+      "epoch": 0.06552901023890785,
+      "grad_norm": 1.327708040902143,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 0.386,
+      "step": 12
+    },
+    {
+      "epoch": 0.07098976109215017,
+      "grad_norm": 1.5458703208762807,
+      "learning_rate": 3.513513513513514e-06,
+      "loss": 0.405,
+      "step": 13
+    },
+    {
+      "epoch": 0.07645051194539249,
+      "grad_norm": 1.6200361209703527,
+      "learning_rate": 3.7837837837837844e-06,
+      "loss": 0.3908,
+      "step": 14
+    },
+    {
+      "epoch": 0.08191126279863481,
+      "grad_norm": 1.5715327605819764,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 0.3972,
+      "step": 15
+    },
+    {
+      "epoch": 0.08737201365187713,
+      "grad_norm": 1.2301811554389595,
+      "learning_rate": 4.324324324324325e-06,
+      "loss": 0.3739,
+      "step": 16
+    },
+    {
+      "epoch": 0.09283276450511946,
+      "grad_norm": 1.0413606131616007,
+      "learning_rate": 4.594594594594596e-06,
+      "loss": 0.3521,
+      "step": 17
+    },
+    {
+      "epoch": 0.09829351535836177,
+      "grad_norm": 1.1239884207253636,
+      "learning_rate": 4.864864864864866e-06,
+      "loss": 0.4348,
+      "step": 18
+    },
+    {
+      "epoch": 0.1037542662116041,
+      "grad_norm": 1.1123432515923368,
+      "learning_rate": 5.135135135135135e-06,
+      "loss": 0.3949,
+      "step": 19
+    },
+    {
+      "epoch": 0.10921501706484642,
+      "grad_norm": 1.0996938196641266,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 0.3775,
+      "step": 20
+    },
+    {
+      "epoch": 0.11467576791808874,
+      "grad_norm": 1.0868866085505373,
+      "learning_rate": 5.675675675675676e-06,
+      "loss": 0.3721,
+      "step": 21
+    },
+    {
+      "epoch": 0.12013651877133105,
+      "grad_norm": 1.10559810934531,
+      "learning_rate": 5.945945945945947e-06,
+      "loss": 0.3884,
+      "step": 22
+    },
+    {
+      "epoch": 0.12559726962457338,
+      "grad_norm": 1.0187684787484814,
+      "learning_rate": 6.2162162162162164e-06,
+      "loss": 0.394,
+      "step": 23
+    },
+    {
+      "epoch": 0.1310580204778157,
+      "grad_norm": 0.9515401547070604,
+      "learning_rate": 6.486486486486487e-06,
+      "loss": 0.3664,
+      "step": 24
+    },
+    {
+      "epoch": 0.13651877133105803,
+      "grad_norm": 0.9873275768348283,
+      "learning_rate": 6.7567567567567575e-06,
+      "loss": 0.3872,
+      "step": 25
+    },
+    {
+      "epoch": 0.14197952218430035,
+      "grad_norm": 0.9420302821261468,
+      "learning_rate": 7.027027027027028e-06,
+      "loss": 0.3926,
+      "step": 26
+    },
+    {
+      "epoch": 0.14744027303754267,
+      "grad_norm": 0.8628951646680264,
+      "learning_rate": 7.297297297297298e-06,
+      "loss": 0.3395,
+      "step": 27
+    },
+    {
+      "epoch": 0.15290102389078497,
+      "grad_norm": 0.8883050014456254,
+      "learning_rate": 7.567567567567569e-06,
+      "loss": 0.3692,
+      "step": 28
+    },
+    {
+      "epoch": 0.1583617747440273,
+      "grad_norm": 0.9314104245334247,
+      "learning_rate": 7.837837837837838e-06,
+      "loss": 0.3562,
+      "step": 29
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.8388999546883599,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 0.3291,
+      "step": 30
+    },
+    {
+      "epoch": 0.16928327645051194,
+      "grad_norm": 0.9110394289660935,
+      "learning_rate": 8.378378378378378e-06,
+      "loss": 0.3761,
+      "step": 31
+    },
+    {
+      "epoch": 0.17474402730375427,
+      "grad_norm": 0.8529619793059433,
+      "learning_rate": 8.64864864864865e-06,
+      "loss": 0.3634,
+      "step": 32
+    },
+    {
+      "epoch": 0.1802047781569966,
+      "grad_norm": 1.034615680095172,
+      "learning_rate": 8.91891891891892e-06,
+      "loss": 0.4073,
+      "step": 33
+    },
+    {
+      "epoch": 0.18566552901023892,
+      "grad_norm": 0.9654399340446536,
+      "learning_rate": 9.189189189189191e-06,
+      "loss": 0.3832,
+      "step": 34
+    },
+    {
+      "epoch": 0.19112627986348124,
+      "grad_norm": 0.8266008406999349,
+      "learning_rate": 9.45945945945946e-06,
+      "loss": 0.366,
+      "step": 35
+    },
+    {
+      "epoch": 0.19658703071672354,
+      "grad_norm": 1.0298041047732736,
+      "learning_rate": 9.729729729729732e-06,
+      "loss": 0.3828,
+      "step": 36
+    },
+    {
+      "epoch": 0.20204778156996586,
+      "grad_norm": 1.0253984164765952,
+      "learning_rate": 1e-05,
+      "loss": 0.4253,
+      "step": 37
+    },
+    {
+      "epoch": 0.2075085324232082,
+      "grad_norm": 0.845565254392157,
+      "learning_rate": 9.999772047343259e-06,
+      "loss": 0.3426,
+      "step": 38
+    },
+    {
+      "epoch": 0.2129692832764505,
+      "grad_norm": 0.9194984294487474,
+      "learning_rate": 9.999088210158001e-06,
+      "loss": 0.343,
+      "step": 39
+    },
+    {
+      "epoch": 0.21843003412969283,
+      "grad_norm": 0.8148322661922577,
+      "learning_rate": 9.997948550797227e-06,
+      "loss": 0.325,
+      "step": 40
+    },
+    {
+      "epoch": 0.22389078498293516,
+      "grad_norm": 0.9623977105015672,
+      "learning_rate": 9.99635317317629e-06,
+      "loss": 0.385,
+      "step": 41
+    },
+    {
+      "epoch": 0.22935153583617748,
+      "grad_norm": 0.814300333357098,
+      "learning_rate": 9.994302222763415e-06,
+      "loss": 0.3462,
+      "step": 42
+    },
+    {
+      "epoch": 0.2348122866894198,
+      "grad_norm": 0.8725030955526336,
+      "learning_rate": 9.991795886566443e-06,
+      "loss": 0.3401,
+      "step": 43
+    },
+    {
+      "epoch": 0.2402730375426621,
+      "grad_norm": 0.9974480242764955,
+      "learning_rate": 9.988834393115768e-06,
+      "loss": 0.3424,
+      "step": 44
+    },
+    {
+      "epoch": 0.24573378839590443,
+      "grad_norm": 0.8805730275929089,
+      "learning_rate": 9.98541801244351e-06,
+      "loss": 0.3742,
+      "step": 45
+    },
+    {
+      "epoch": 0.25119453924914675,
+      "grad_norm": 0.8332420506302001,
+      "learning_rate": 9.981547056058893e-06,
+      "loss": 0.3435,
+      "step": 46
+    },
+    {
+      "epoch": 0.2566552901023891,
+      "grad_norm": 0.9445729244701234,
+      "learning_rate": 9.977221876919833e-06,
+      "loss": 0.3442,
+      "step": 47
+    },
+    {
+      "epoch": 0.2621160409556314,
+      "grad_norm": 0.859922027597315,
+      "learning_rate": 9.97244286940076e-06,
+      "loss": 0.358,
+      "step": 48
+    },
+    {
+      "epoch": 0.2675767918088737,
+      "grad_norm": 0.8022442917536148,
+      "learning_rate": 9.967210469256657e-06,
+      "loss": 0.3329,
+      "step": 49
+    },
+    {
+      "epoch": 0.27303754266211605,
+      "grad_norm": 0.8369993999252197,
+      "learning_rate": 9.961525153583327e-06,
+      "loss": 0.3474,
+      "step": 50
+    },
+    {
+      "epoch": 0.2784982935153584,
+      "grad_norm": 0.8719055464818419,
+      "learning_rate": 9.955387440773902e-06,
+      "loss": 0.3364,
+      "step": 51
+    },
+    {
+      "epoch": 0.2839590443686007,
+      "grad_norm": 0.9269845480680101,
+      "learning_rate": 9.948797890471552e-06,
+      "loss": 0.3684,
+      "step": 52
+    },
+    {
+      "epoch": 0.289419795221843,
+      "grad_norm": 0.8246571303849338,
+      "learning_rate": 9.94175710351848e-06,
+      "loss": 0.3564,
+      "step": 53
+    },
+    {
+      "epoch": 0.29488054607508535,
+      "grad_norm": 0.9162125135698432,
+      "learning_rate": 9.93426572190112e-06,
+      "loss": 0.3526,
+      "step": 54
+    },
+    {
+      "epoch": 0.3003412969283277,
+      "grad_norm": 0.9689985766932336,
+      "learning_rate": 9.926324428691612e-06,
+      "loss": 0.3825,
+      "step": 55
+    },
+    {
+      "epoch": 0.30580204778156994,
+      "grad_norm": 0.9203465649703365,
+      "learning_rate": 9.917933947985508e-06,
+      "loss": 0.3492,
+      "step": 56
+    },
+    {
+      "epoch": 0.31126279863481227,
+      "grad_norm": 0.810691112658576,
+      "learning_rate": 9.909095044835755e-06,
+      "loss": 0.3147,
+      "step": 57
+    },
+    {
+      "epoch": 0.3167235494880546,
+      "grad_norm": 0.8980168883992854,
+      "learning_rate": 9.899808525182935e-06,
+      "loss": 0.3351,
+      "step": 58
+    },
+    {
+      "epoch": 0.3221843003412969,
+      "grad_norm": 0.8843165617295874,
+      "learning_rate": 9.89007523578178e-06,
+      "loss": 0.3452,
+      "step": 59
+    },
+    {
+      "epoch": 0.32764505119453924,
+      "grad_norm": 0.8660715276442186,
+      "learning_rate": 9.879896064123961e-06,
+      "loss": 0.3601,
+      "step": 60
+    },
+    {
+      "epoch": 0.33310580204778156,
+      "grad_norm": 0.8638898824914902,
+      "learning_rate": 9.869271938357168e-06,
+      "loss": 0.3565,
+      "step": 61
+    },
+    {
+      "epoch": 0.3385665529010239,
+      "grad_norm": 0.8349466672789928,
+      "learning_rate": 9.858203827200477e-06,
+      "loss": 0.3592,
+      "step": 62
+    },
+    {
+      "epoch": 0.3440273037542662,
+      "grad_norm": 0.9346433422616252,
+      "learning_rate": 9.846692739856023e-06,
+      "loss": 0.3935,
+      "step": 63
+    },
+    {
+      "epoch": 0.34948805460750854,
+      "grad_norm": 0.8287634034991234,
+      "learning_rate": 9.834739725916988e-06,
+      "loss": 0.3089,
+      "step": 64
+    },
+    {
+      "epoch": 0.35494880546075086,
+      "grad_norm": 0.8040217244181859,
+      "learning_rate": 9.822345875271884e-06,
+      "loss": 0.313,
+      "step": 65
+    },
+    {
+      "epoch": 0.3604095563139932,
+      "grad_norm": 0.8053513263090958,
+      "learning_rate": 9.80951231800518e-06,
+      "loss": 0.3355,
+      "step": 66
+    },
+    {
+      "epoch": 0.3658703071672355,
+      "grad_norm": 0.7533298814162714,
+      "learning_rate": 9.79624022429427e-06,
+      "loss": 0.3067,
+      "step": 67
+    },
+    {
+      "epoch": 0.37133105802047783,
+      "grad_norm": 0.9386782501271983,
+      "learning_rate": 9.782530804302763e-06,
+      "loss": 0.3593,
+      "step": 68
+    },
+    {
+      "epoch": 0.37679180887372016,
+      "grad_norm": 0.8507056335702303,
+      "learning_rate": 9.768385308070139e-06,
+      "loss": 0.3629,
+      "step": 69
+    },
+    {
+      "epoch": 0.3822525597269625,
+      "grad_norm": 0.782049564136347,
+      "learning_rate": 9.75380502539778e-06,
+      "loss": 0.3458,
+      "step": 70
+    },
+    {
+      "epoch": 0.38771331058020475,
+      "grad_norm": 0.9109652113851044,
+      "learning_rate": 9.738791285731353e-06,
+      "loss": 0.348,
+      "step": 71
+    },
+    {
+      "epoch": 0.3931740614334471,
+      "grad_norm": 0.8457379953081087,
+      "learning_rate": 9.723345458039595e-06,
+      "loss": 0.3701,
+      "step": 72
+    },
+    {
+      "epoch": 0.3986348122866894,
+      "grad_norm": 0.8354411100444213,
+      "learning_rate": 9.70746895068949e-06,
+      "loss": 0.3453,
+      "step": 73
+    },
+    {
+      "epoch": 0.4040955631399317,
+      "grad_norm": 0.7824544054631952,
+      "learning_rate": 9.691163211317853e-06,
+      "loss": 0.3393,
+      "step": 74
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 0.7752036290890001,
+      "learning_rate": 9.674429726699324e-06,
+      "loss": 0.3121,
+      "step": 75
+    },
+    {
+      "epoch": 0.4150170648464164,
+      "grad_norm": 0.9047037383020493,
+      "learning_rate": 9.657270022610814e-06,
+      "loss": 0.3507,
+      "step": 76
+    },
+    {
+      "epoch": 0.4204778156996587,
+      "grad_norm": 0.8453635648693023,
+      "learning_rate": 9.63968566369238e-06,
+      "loss": 0.3641,
+      "step": 77
+    },
+    {
+      "epoch": 0.425938566552901,
+      "grad_norm": 0.8290743120901927,
+      "learning_rate": 9.62167825330455e-06,
+      "loss": 0.3739,
+      "step": 78
+    },
+    {
+      "epoch": 0.43139931740614335,
+      "grad_norm": 0.8977215293449932,
+      "learning_rate": 9.603249433382145e-06,
+      "loss": 0.3185,
+      "step": 79
+    },
+    {
+      "epoch": 0.43686006825938567,
+      "grad_norm": 0.9078617748361664,
+      "learning_rate": 9.584400884284546e-06,
+      "loss": 0.3415,
+      "step": 80
+    },
+    {
+      "epoch": 0.442320819112628,
+      "grad_norm": 0.8589830385419883,
+      "learning_rate": 9.565134324642491e-06,
+      "loss": 0.3331,
+      "step": 81
+    },
+    {
+      "epoch": 0.4477815699658703,
+      "grad_norm": 0.804380018393787,
+      "learning_rate": 9.545451511201365e-06,
+      "loss": 0.322,
+      "step": 82
+    },
+    {
+      "epoch": 0.45324232081911264,
+      "grad_norm": 0.8685230840996425,
+      "learning_rate": 9.52535423866101e-06,
+      "loss": 0.3476,
+      "step": 83
+    },
+    {
+      "epoch": 0.45870307167235497,
+      "grad_norm": 0.9643956240091752,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.3671,
+      "step": 84
+    },
+    {
+      "epoch": 0.4641638225255973,
+      "grad_norm": 0.8997894029115073,
+      "learning_rate": 9.483923683869025e-06,
+      "loss": 0.352,
+      "step": 85
+    },
+    {
+      "epoch": 0.4696245733788396,
+      "grad_norm": 0.9409163478885427,
+      "learning_rate": 9.462594179299408e-06,
+      "loss": 0.3533,
+      "step": 86
+    },
+    {
+      "epoch": 0.4750853242320819,
+      "grad_norm": 1.0349789755076704,
+      "learning_rate": 9.440857770650139e-06,
+      "loss": 0.3501,
+      "step": 87
+    },
+    {
+      "epoch": 0.4805460750853242,
+      "grad_norm": 0.7719492270463393,
+      "learning_rate": 9.418716439870056e-06,
+      "loss": 0.3092,
+      "step": 88
+    },
+    {
+      "epoch": 0.48600682593856653,
+      "grad_norm": 0.9082886643398166,
+      "learning_rate": 9.396172205829235e-06,
+      "loss": 0.3514,
+      "step": 89
+    },
+    {
+      "epoch": 0.49146757679180886,
+      "grad_norm": 0.8358389654564478,
+      "learning_rate": 9.373227124134888e-06,
+      "loss": 0.3489,
+      "step": 90
+    },
+    {
+      "epoch": 0.4969283276450512,
+      "grad_norm": 0.8974753686960236,
+      "learning_rate": 9.349883286943951e-06,
+      "loss": 0.3632,
+      "step": 91
+    },
+    {
+      "epoch": 0.5023890784982935,
+      "grad_norm": 0.8827201059716774,
+      "learning_rate": 9.326142822772301e-06,
+      "loss": 0.3584,
+      "step": 92
+    },
+    {
+      "epoch": 0.5078498293515359,
+      "grad_norm": 0.813182991570662,
+      "learning_rate": 9.302007896300697e-06,
+      "loss": 0.3591,
+      "step": 93
+    },
+    {
+      "epoch": 0.5133105802047782,
+      "grad_norm": 0.7442842781039997,
+      "learning_rate": 9.27748070817738e-06,
+      "loss": 0.3143,
+      "step": 94
+    },
+    {
+      "epoch": 0.5187713310580204,
+      "grad_norm": 0.906866423901588,
+      "learning_rate": 9.252563494817426e-06,
+      "loss": 0.3772,
+      "step": 95
+    },
+    {
+      "epoch": 0.5242320819112628,
+      "grad_norm": 0.7894206448318375,
+      "learning_rate": 9.227258528198832e-06,
+      "loss": 0.3131,
+      "step": 96
+    },
+    {
+      "epoch": 0.5296928327645051,
+      "grad_norm": 0.8009536933279702,
+      "learning_rate": 9.201568115655343e-06,
+      "loss": 0.329,
+      "step": 97
+    },
+    {
+      "epoch": 0.5351535836177475,
+      "grad_norm": 0.8048929927509286,
+      "learning_rate": 9.175494599666078e-06,
+      "loss": 0.3278,
+      "step": 98
+    },
+    {
+      "epoch": 0.5406143344709897,
+      "grad_norm": 0.814222453793431,
+      "learning_rate": 9.14904035764193e-06,
+      "loss": 0.3225,
+      "step": 99
+    },
+    {
+      "epoch": 0.5460750853242321,
+      "grad_norm": 0.8732367458543802,
+      "learning_rate": 9.122207801708802e-06,
+      "loss": 0.3524,
+      "step": 100
+    },
+    {
+      "epoch": 0.5515358361774744,
+      "grad_norm": 0.8134905761183274,
+      "learning_rate": 9.094999378487659e-06,
+      "loss": 0.3546,
+      "step": 101
+    },
+    {
+      "epoch": 0.5569965870307167,
+      "grad_norm": 0.8567463415353727,
+      "learning_rate": 9.067417568871444e-06,
+      "loss": 0.3548,
+      "step": 102
+    },
+    {
+      "epoch": 0.562457337883959,
+      "grad_norm": 0.8151562254810784,
+      "learning_rate": 9.03946488779887e-06,
+      "loss": 0.3439,
+      "step": 103
+    },
+    {
+      "epoch": 0.5679180887372014,
+      "grad_norm": 0.8746438505757359,
+      "learning_rate": 9.0111438840251e-06,
+      "loss": 0.3242,
+      "step": 104
+    },
+    {
+      "epoch": 0.5733788395904437,
+      "grad_norm": 0.8085121266810896,
+      "learning_rate": 8.982457139889358e-06,
+      "loss": 0.3598,
+      "step": 105
+    },
+    {
+      "epoch": 0.578839590443686,
+      "grad_norm": 0.8191769217039168,
+      "learning_rate": 8.953407271079456e-06,
+      "loss": 0.3425,
+      "step": 106
+    },
+    {
+      "epoch": 0.5843003412969283,
+      "grad_norm": 0.874872463262842,
+      "learning_rate": 8.923996926393306e-06,
+      "loss": 0.3795,
+      "step": 107
+    },
+    {
+      "epoch": 0.5897610921501707,
+      "grad_norm": 0.8469769243731713,
+      "learning_rate": 8.894228787497389e-06,
+      "loss": 0.3555,
+      "step": 108
+    },
+    {
+      "epoch": 0.595221843003413,
+      "grad_norm": 0.7907533312057188,
+      "learning_rate": 8.864105568682245e-06,
+      "loss": 0.3425,
+      "step": 109
+    },
+    {
+      "epoch": 0.6006825938566553,
+      "grad_norm": 0.9105392675920642,
+      "learning_rate": 8.833630016614976e-06,
+      "loss": 0.3214,
+      "step": 110
+    },
+    {
+      "epoch": 0.6061433447098976,
+      "grad_norm": 0.7743632593675985,
+      "learning_rate": 8.80280491008881e-06,
+      "loss": 0.3477,
+      "step": 111
+    },
+    {
+      "epoch": 0.6116040955631399,
+      "grad_norm": 0.9007334854740756,
+      "learning_rate": 8.771633059769712e-06,
+      "loss": 0.3836,
+      "step": 112
+    },
+    {
+      "epoch": 0.6170648464163823,
+      "grad_norm": 0.810760704066922,
+      "learning_rate": 8.740117307940123e-06,
+      "loss": 0.3397,
+      "step": 113
+    },
+    {
+      "epoch": 0.6225255972696245,
+      "grad_norm": 0.9072711750424595,
+      "learning_rate": 8.708260528239788e-06,
+      "loss": 0.3389,
+      "step": 114
+    },
+    {
+      "epoch": 0.6279863481228669,
+      "grad_norm": 0.8621760047744049,
+      "learning_rate": 8.676065625403733e-06,
+      "loss": 0.3788,
+      "step": 115
+    },
+    {
+      "epoch": 0.6334470989761092,
+      "grad_norm": 0.8388020553913726,
+      "learning_rate": 8.64353553499741e-06,
+      "loss": 0.3274,
+      "step": 116
+    },
+    {
+      "epoch": 0.6389078498293516,
+      "grad_norm": 0.8591445453801212,
+      "learning_rate": 8.610673223149036e-06,
+      "loss": 0.3598,
+      "step": 117
+    },
+    {
+      "epoch": 0.6443686006825938,
+      "grad_norm": 0.8057297251815362,
+      "learning_rate": 8.577481686279123e-06,
+      "loss": 0.3522,
+      "step": 118
+    },
+    {
+      "epoch": 0.6498293515358362,
+      "grad_norm": 0.779914515334107,
+      "learning_rate": 8.543963950827279e-06,
+      "loss": 0.3416,
+      "step": 119
+    },
+    {
+      "epoch": 0.6552901023890785,
+      "grad_norm": 0.8241347234199242,
+      "learning_rate": 8.51012307297624e-06,
+      "loss": 0.341,
+      "step": 120
+    },
+    {
+      "epoch": 0.6607508532423209,
+      "grad_norm": 0.7674873201219691,
+      "learning_rate": 8.475962138373212e-06,
+      "loss": 0.3268,
+      "step": 121
+    },
+    {
+      "epoch": 0.6662116040955631,
+      "grad_norm": 0.7983877124268901,
+      "learning_rate": 8.441484261848514e-06,
+      "loss": 0.3744,
+      "step": 122
+    },
+    {
+      "epoch": 0.6716723549488055,
+      "grad_norm": 0.924444516956386,
+      "learning_rate": 8.406692587131569e-06,
+      "loss": 0.341,
+      "step": 123
+    },
+    {
+      "epoch": 0.6771331058020478,
+      "grad_norm": 0.7648013324474998,
+      "learning_rate": 8.371590286564247e-06,
+      "loss": 0.3239,
+      "step": 124
+    },
+    {
+      "epoch": 0.6825938566552902,
+      "grad_norm": 0.8275858574184091,
+      "learning_rate": 8.336180560811619e-06,
+      "loss": 0.3588,
+      "step": 125
+    },
+    {
+      "epoch": 0.6880546075085324,
+      "grad_norm": 0.7874924257335151,
+      "learning_rate": 8.30046663857011e-06,
+      "loss": 0.3431,
+      "step": 126
+    },
+    {
+      "epoch": 0.6935153583617747,
+      "grad_norm": 0.8745641415217126,
+      "learning_rate": 8.264451776273104e-06,
+      "loss": 0.3489,
+      "step": 127
+    },
+    {
+      "epoch": 0.6989761092150171,
+      "grad_norm": 0.8858812955767805,
+      "learning_rate": 8.228139257794012e-06,
+      "loss": 0.3595,
+      "step": 128
+    },
+    {
+      "epoch": 0.7044368600682593,
+      "grad_norm": 0.812177330348684,
+      "learning_rate": 8.191532394146865e-06,
+      "loss": 0.328,
+      "step": 129
+    },
+    {
+      "epoch": 0.7098976109215017,
+      "grad_norm": 0.7755088132854933,
+      "learning_rate": 8.154634523184389e-06,
+      "loss": 0.3392,
+      "step": 130
+    },
+    {
+      "epoch": 0.715358361774744,
+      "grad_norm": 0.8715295143660003,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.3482,
+      "step": 131
+    },
+    {
+      "epoch": 0.7208191126279864,
+      "grad_norm": 0.7737148258150855,
+      "learning_rate": 8.07997924308938e-06,
+      "loss": 0.3258,
+      "step": 132
+    },
+    {
+      "epoch": 0.7262798634812286,
+      "grad_norm": 0.7616464397737633,
+      "learning_rate": 8.042228641104622e-06,
+      "loss": 0.3164,
+      "step": 133
+    },
+    {
+      "epoch": 0.731740614334471,
+      "grad_norm": 0.7706843428925245,
+      "learning_rate": 8.004200645479403e-06,
+      "loss": 0.3267,
+      "step": 134
+    },
+    {
+      "epoch": 0.7372013651877133,
+      "grad_norm": 0.807087784184599,
+      "learning_rate": 7.965898723646777e-06,
+      "loss": 0.3556,
+      "step": 135
+    },
+    {
+      "epoch": 0.7426621160409557,
+      "grad_norm": 0.8571787444948499,
+      "learning_rate": 7.927326368016677e-06,
+      "loss": 0.349,
+      "step": 136
+    },
+    {
+      "epoch": 0.7481228668941979,
+      "grad_norm": 0.758611440956407,
+      "learning_rate": 7.888487095657484e-06,
+      "loss": 0.3301,
+      "step": 137
+    },
+    {
+      "epoch": 0.7535836177474403,
+      "grad_norm": 0.7924167608304931,
+      "learning_rate": 7.849384447975322e-06,
+      "loss": 0.3534,
+      "step": 138
+    },
+    {
+      "epoch": 0.7590443686006826,
+      "grad_norm": 0.8750460208633537,
+      "learning_rate": 7.810021990391163e-06,
+      "loss": 0.3405,
+      "step": 139
+    },
+    {
+      "epoch": 0.764505119453925,
+      "grad_norm": 0.7895037781717571,
+      "learning_rate": 7.77040331201572e-06,
+      "loss": 0.3678,
+      "step": 140
+    },
+    {
+      "epoch": 0.7699658703071672,
+      "grad_norm": 0.8223142510608592,
+      "learning_rate": 7.73053202532219e-06,
+      "loss": 0.3469,
+      "step": 141
+    },
+    {
+      "epoch": 0.7754266211604095,
+      "grad_norm": 0.8172036706667312,
+      "learning_rate": 7.690411765816864e-06,
+      "loss": 0.3395,
+      "step": 142
+    },
+    {
+      "epoch": 0.7808873720136519,
+      "grad_norm": 0.7717521340469524,
+      "learning_rate": 7.650046191707641e-06,
+      "loss": 0.3352,
+      "step": 143
+    },
+    {
+      "epoch": 0.7863481228668942,
+      "grad_norm": 0.8745843729938327,
+      "learning_rate": 7.609438983570461e-06,
+      "loss": 0.34,
+      "step": 144
+    },
+    {
+      "epoch": 0.7918088737201365,
+      "grad_norm": 0.8462879664073518,
+      "learning_rate": 7.5685938440137185e-06,
+      "loss": 0.3434,
+      "step": 145
+    },
+    {
+      "epoch": 0.7972696245733788,
+      "grad_norm": 0.8887194246240154,
+      "learning_rate": 7.527514497340642e-06,
+      "loss": 0.3536,
+      "step": 146
+    },
+    {
+      "epoch": 0.8027303754266212,
+      "grad_norm": 0.720734982965855,
+      "learning_rate": 7.486204689209719e-06,
+      "loss": 0.3071,
+      "step": 147
+    },
+    {
+      "epoch": 0.8081911262798634,
+      "grad_norm": 0.7852180915891143,
+      "learning_rate": 7.444668186293153e-06,
+      "loss": 0.3318,
+      "step": 148
+    },
+    {
+      "epoch": 0.8136518771331058,
+      "grad_norm": 0.8169236397844766,
+      "learning_rate": 7.402908775933419e-06,
+      "loss": 0.3282,
+      "step": 149
+    },
+    {
+      "epoch": 0.8191126279863481,
+      "grad_norm": 0.8409146266167947,
+      "learning_rate": 7.360930265797934e-06,
+      "loss": 0.3592,
+      "step": 150
+    },
+    {
+      "epoch": 0.8245733788395905,
+      "grad_norm": 0.7893736430445095,
+      "learning_rate": 7.318736483531861e-06,
+      "loss": 0.3455,
+      "step": 151
+    },
+    {
+      "epoch": 0.8300341296928327,
+      "grad_norm": 0.7092487578490618,
+      "learning_rate": 7.2763312764091055e-06,
+      "loss": 0.307,
+      "step": 152
+    },
+    {
+      "epoch": 0.8354948805460751,
+      "grad_norm": 0.7643841671055314,
+      "learning_rate": 7.23371851098152e-06,
+      "loss": 0.3104,
+      "step": 153
+    },
+    {
+      "epoch": 0.8409556313993174,
+      "grad_norm": 0.8743703462981528,
+      "learning_rate": 7.190902072726336e-06,
+      "loss": 0.3601,
+      "step": 154
+    },
+    {
+      "epoch": 0.8464163822525598,
+      "grad_norm": 0.8748161240027253,
+      "learning_rate": 7.147885865691899e-06,
+      "loss": 0.3592,
+      "step": 155
+    },
+    {
+      "epoch": 0.851877133105802,
+      "grad_norm": 0.6528952892311825,
+      "learning_rate": 7.104673812141676e-06,
+      "loss": 0.2919,
+      "step": 156
+    },
+    {
+      "epoch": 0.8573378839590444,
+      "grad_norm": 0.8161745547126792,
+      "learning_rate": 7.061269852196633e-06,
+      "loss": 0.345,
+      "step": 157
+    },
+    {
+      "epoch": 0.8627986348122867,
+      "grad_norm": 0.8321903783865391,
+      "learning_rate": 7.017677943475962e-06,
+      "loss": 0.321,
+      "step": 158
+    },
+    {
+      "epoch": 0.868259385665529,
+      "grad_norm": 0.83313681444351,
+      "learning_rate": 6.973902060736226e-06,
+      "loss": 0.3435,
+      "step": 159
+    },
+    {
+      "epoch": 0.8737201365187713,
+      "grad_norm": 0.7505151585539925,
+      "learning_rate": 6.929946195508933e-06,
+      "loss": 0.3163,
+      "step": 160
+    },
+    {
+      "epoch": 0.8791808873720136,
+      "grad_norm": 0.7304802524364322,
+      "learning_rate": 6.8858143557365865e-06,
+      "loss": 0.328,
+      "step": 161
+    },
+    {
+      "epoch": 0.884641638225256,
+      "grad_norm": 0.8143420713928606,
+      "learning_rate": 6.841510565407235e-06,
+      "loss": 0.3341,
+      "step": 162
+    },
+    {
+      "epoch": 0.8901023890784983,
+      "grad_norm": 0.7567204344075086,
+      "learning_rate": 6.797038864187564e-06,
+      "loss": 0.3059,
+      "step": 163
+    },
+    {
+      "epoch": 0.8955631399317406,
+      "grad_norm": 0.7826567782778101,
+      "learning_rate": 6.752403307054549e-06,
+      "loss": 0.3283,
+      "step": 164
+    },
+    {
+      "epoch": 0.9010238907849829,
+      "grad_norm": 0.7886900433942758,
+      "learning_rate": 6.707607963925725e-06,
+      "loss": 0.3592,
+      "step": 165
+    },
+    {
+      "epoch": 0.9064846416382253,
+      "grad_norm": 0.820709571232716,
+      "learning_rate": 6.66265691928808e-06,
+      "loss": 0.3605,
+      "step": 166
+    },
+    {
+      "epoch": 0.9119453924914676,
+      "grad_norm": 0.7681789982648866,
+      "learning_rate": 6.617554271825636e-06,
+      "loss": 0.3051,
+      "step": 167
+    },
+    {
+      "epoch": 0.9174061433447099,
+      "grad_norm": 0.8006459558215293,
+      "learning_rate": 6.5723041340457175e-06,
+      "loss": 0.3542,
+      "step": 168
+    },
+    {
+      "epoch": 0.9228668941979522,
+      "grad_norm": 0.7333102829214887,
+      "learning_rate": 6.526910631903973e-06,
+      "loss": 0.3254,
+      "step": 169
+    },
+    {
+      "epoch": 0.9283276450511946,
+      "grad_norm": 0.7766899671870917,
+      "learning_rate": 6.481377904428171e-06,
+      "loss": 0.3297,
+      "step": 170
+    },
+    {
+      "epoch": 0.9337883959044369,
+      "grad_norm": 0.8887532080533157,
+      "learning_rate": 6.435710103340787e-06,
+      "loss": 0.3531,
+      "step": 171
+    },
+    {
+      "epoch": 0.9392491467576792,
+      "grad_norm": 0.7606421967689092,
+      "learning_rate": 6.3899113926804565e-06,
+      "loss": 0.3279,
+      "step": 172
+    },
+    {
+      "epoch": 0.9447098976109215,
+      "grad_norm": 0.7894203946388427,
+      "learning_rate": 6.3439859484222874e-06,
+      "loss": 0.3206,
+      "step": 173
+    },
+    {
+      "epoch": 0.9501706484641638,
+      "grad_norm": 0.8106143896629081,
+      "learning_rate": 6.297937958097094e-06,
+      "loss": 0.3185,
+      "step": 174
+    },
+    {
+      "epoch": 0.9556313993174061,
+      "grad_norm": 0.7673331407317434,
+      "learning_rate": 6.251771620409563e-06,
+      "loss": 0.3408,
+      "step": 175
+    },
+    {
+      "epoch": 0.9610921501706484,
+      "grad_norm": 0.7678720102410665,
+      "learning_rate": 6.205491144855432e-06,
+      "loss": 0.3388,
+      "step": 176
+    },
+    {
+      "epoch": 0.9665529010238908,
+      "grad_norm": 0.8058357314804626,
+      "learning_rate": 6.1591007513376425e-06,
+      "loss": 0.348,
+      "step": 177
+    },
+    {
+      "epoch": 0.9720136518771331,
+      "grad_norm": 0.7150290944167804,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.3187,
+      "step": 178
+    },
+    {
+      "epoch": 0.9774744027303754,
+      "grad_norm": 0.7724885943742522,
+      "learning_rate": 6.066007139749351e-06,
+      "loss": 0.3112,
+      "step": 179
+    },
+    {
+      "epoch": 0.9829351535836177,
+      "grad_norm": 0.7079636144073458,
+      "learning_rate": 6.019312410053286e-06,
+      "loss": 0.3115,
+      "step": 180
+    },
+    {
+      "epoch": 0.9883959044368601,
+      "grad_norm": 0.7145124027416198,
+      "learning_rate": 5.972524738368452e-06,
+      "loss": 0.3015,
+      "step": 181
+    },
+    {
+      "epoch": 0.9938566552901024,
+      "grad_norm": 0.7747190577463166,
+      "learning_rate": 5.925648390844476e-06,
+      "loss": 0.3405,
+      "step": 182
+    },
+    {
+      "epoch": 0.9993174061433447,
+      "grad_norm": 0.7411495697672651,
+      "learning_rate": 5.878687641716539e-06,
+      "loss": 0.3241,
+      "step": 183
+    },
+    {
+      "epoch": 1.004778156996587,
+      "grad_norm": 2.2845026949908367,
+      "learning_rate": 5.831646772915651e-06,
+      "loss": 0.5887,
+      "step": 184
+    },
+    {
+      "epoch": 1.0102389078498293,
+      "grad_norm": 0.767067987662548,
+      "learning_rate": 5.7845300736782205e-06,
+      "loss": 0.2696,
+      "step": 185
+    },
+    {
+      "epoch": 1.0156996587030718,
+      "grad_norm": 0.6444558204539116,
+      "learning_rate": 5.7373418401549565e-06,
+      "loss": 0.2179,
+      "step": 186
+    },
+    {
+      "epoch": 1.021160409556314,
+      "grad_norm": 0.6326875020427418,
+      "learning_rate": 5.690086375019135e-06,
+      "loss": 0.2063,
+      "step": 187
+    },
+    {
+      "epoch": 1.0266211604095563,
+      "grad_norm": 0.6386737207560813,
+      "learning_rate": 5.642767987074288e-06,
+      "loss": 0.2395,
+      "step": 188
+    },
+    {
+      "epoch": 1.0320819112627986,
+      "grad_norm": 0.7191360204333792,
+      "learning_rate": 5.595390990861311e-06,
+      "loss": 0.2593,
+      "step": 189
+    },
+    {
+      "epoch": 1.0375426621160408,
+      "grad_norm": 0.7139153218951271,
+      "learning_rate": 5.547959706265068e-06,
+      "loss": 0.25,
+      "step": 190
+    },
+    {
+      "epoch": 1.0430034129692833,
+      "grad_norm": 0.7132174285440807,
+      "learning_rate": 5.500478458120493e-06,
+      "loss": 0.2656,
+      "step": 191
+    },
+    {
+      "epoch": 1.0484641638225256,
+      "grad_norm": 0.7373698973683902,
+      "learning_rate": 5.45295157581825e-06,
+      "loss": 0.2643,
+      "step": 192
+    },
+    {
+      "epoch": 1.0539249146757679,
+      "grad_norm": 0.6806301830473086,
+      "learning_rate": 5.405383392909973e-06,
+      "loss": 0.2521,
+      "step": 193
+    },
+    {
+      "epoch": 1.0593856655290101,
+      "grad_norm": 0.6785558579468979,
+      "learning_rate": 5.357778246713131e-06,
+      "loss": 0.254,
+      "step": 194
+    },
+    {
+      "epoch": 1.0648464163822526,
+      "grad_norm": 0.6701400051635917,
+      "learning_rate": 5.310140477915544e-06,
+      "loss": 0.2303,
+      "step": 195
+    },
+    {
+      "epoch": 1.070307167235495,
+      "grad_norm": 0.7408218245910705,
+      "learning_rate": 5.262474430179597e-06,
+      "loss": 0.2587,
+      "step": 196
+    },
+    {
+      "epoch": 1.0757679180887372,
+      "grad_norm": 0.652029496994987,
+      "learning_rate": 5.2147844497461745e-06,
+      "loss": 0.2201,
+      "step": 197
+    },
+    {
+      "epoch": 1.0812286689419794,
+      "grad_norm": 0.6145756306559864,
+      "learning_rate": 5.1670748850383734e-06,
+      "loss": 0.2131,
+      "step": 198
+    },
+    {
+      "epoch": 1.086689419795222,
+      "grad_norm": 0.6166424191446999,
+      "learning_rate": 5.1193500862650045e-06,
+      "loss": 0.2272,
+      "step": 199
+    },
+    {
+      "epoch": 1.0921501706484642,
+      "grad_norm": 0.6183167944122974,
+      "learning_rate": 5.071614405023938e-06,
+      "loss": 0.2239,
+      "step": 200
+    },
+    {
+      "epoch": 1.0976109215017065,
+      "grad_norm": 0.7073017446193981,
+      "learning_rate": 5.023872193905316e-06,
+      "loss": 0.2564,
+      "step": 201
+    },
+    {
+      "epoch": 1.1030716723549487,
+      "grad_norm": 0.6785368103283103,
+      "learning_rate": 4.976127806094685e-06,
+      "loss": 0.2598,
+      "step": 202
+    },
+    {
+      "epoch": 1.108532423208191,
+      "grad_norm": 0.6686099383276679,
+      "learning_rate": 4.928385594976063e-06,
+      "loss": 0.2391,
+      "step": 203
+    },
+    {
+      "epoch": 1.1139931740614335,
+      "grad_norm": 0.6046536649329635,
+      "learning_rate": 4.880649913734996e-06,
+      "loss": 0.2111,
+      "step": 204
+    },
+    {
+      "epoch": 1.1194539249146758,
+      "grad_norm": 0.6455972829075776,
+      "learning_rate": 4.832925114961629e-06,
+      "loss": 0.2291,
+      "step": 205
+    },
+    {
+      "epoch": 1.124914675767918,
+      "grad_norm": 0.6294601922178525,
+      "learning_rate": 4.785215550253826e-06,
+      "loss": 0.2237,
+      "step": 206
+    },
+    {
+      "epoch": 1.1303754266211605,
+      "grad_norm": 0.6539972986726327,
+      "learning_rate": 4.737525569820405e-06,
+      "loss": 0.2415,
+      "step": 207
+    },
+    {
+      "epoch": 1.1358361774744028,
+      "grad_norm": 0.6841776523547041,
+      "learning_rate": 4.689859522084457e-06,
+      "loss": 0.2573,
+      "step": 208
+    },
+    {
+      "epoch": 1.141296928327645,
+      "grad_norm": 0.708275852733329,
+      "learning_rate": 4.64222175328687e-06,
+      "loss": 0.2535,
+      "step": 209
+    },
+    {
+      "epoch": 1.1467576791808873,
+      "grad_norm": 0.6327858698732379,
+      "learning_rate": 4.594616607090028e-06,
+      "loss": 0.2284,
+      "step": 210
+    },
+    {
+      "epoch": 1.1522184300341296,
+      "grad_norm": 0.6408257648532151,
+      "learning_rate": 4.547048424181751e-06,
+      "loss": 0.2294,
+      "step": 211
+    },
+    {
+      "epoch": 1.157679180887372,
+      "grad_norm": 0.6159123552870842,
+      "learning_rate": 4.499521541879508e-06,
+      "loss": 0.2226,
+      "step": 212
+    },
+    {
+      "epoch": 1.1631399317406144,
+      "grad_norm": 0.5823300781202381,
+      "learning_rate": 4.452040293734934e-06,
+      "loss": 0.2108,
+      "step": 213
+    },
+    {
+      "epoch": 1.1686006825938566,
+      "grad_norm": 0.6041391928150867,
+      "learning_rate": 4.40460900913869e-06,
+      "loss": 0.2224,
+      "step": 214
+    },
+    {
+      "epoch": 1.174061433447099,
+      "grad_norm": 0.6641306892375002,
+      "learning_rate": 4.357232012925714e-06,
+      "loss": 0.2384,
+      "step": 215
+    },
+    {
+      "epoch": 1.1795221843003414,
+      "grad_norm": 0.6503207204016519,
+      "learning_rate": 4.309913624980866e-06,
+      "loss": 0.2347,
+      "step": 216
+    },
+    {
+      "epoch": 1.1849829351535837,
+      "grad_norm": 0.62805580635999,
+      "learning_rate": 4.262658159845046e-06,
+      "loss": 0.229,
+      "step": 217
+    },
+    {
+      "epoch": 1.190443686006826,
+      "grad_norm": 0.6275617918722145,
+      "learning_rate": 4.2154699263217794e-06,
+      "loss": 0.2286,
+      "step": 218
+    },
+    {
+      "epoch": 1.1959044368600682,
+      "grad_norm": 0.7617460871871701,
+      "learning_rate": 4.1683532270843505e-06,
+      "loss": 0.2574,
+      "step": 219
+    },
+    {
+      "epoch": 1.2013651877133107,
+      "grad_norm": 0.6140110702778818,
+      "learning_rate": 4.121312358283464e-06,
+      "loss": 0.2149,
+      "step": 220
+    },
+    {
+      "epoch": 1.206825938566553,
+      "grad_norm": 0.6247259244040378,
+      "learning_rate": 4.074351609155527e-06,
+      "loss": 0.2381,
+      "step": 221
+    },
+    {
+      "epoch": 1.2122866894197952,
+      "grad_norm": 0.6591171660703798,
+      "learning_rate": 4.0274752616315485e-06,
+      "loss": 0.2344,
+      "step": 222
+    },
+    {
+      "epoch": 1.2177474402730375,
+      "grad_norm": 0.6436293629709356,
+      "learning_rate": 3.980687589946715e-06,
+      "loss": 0.2319,
+      "step": 223
+    },
+    {
+      "epoch": 1.2232081911262798,
+      "grad_norm": 0.7670288305294722,
+      "learning_rate": 3.9339928602506505e-06,
+      "loss": 0.2497,
+      "step": 224
+    },
+    {
+      "epoch": 1.2286689419795223,
+      "grad_norm": 0.6962942427446093,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.2336,
+      "step": 225
+    },
+    {
+      "epoch": 1.2341296928327645,
+      "grad_norm": 0.6965676226191562,
+      "learning_rate": 3.840899248662358e-06,
+      "loss": 0.2552,
+      "step": 226
+    },
+    {
+      "epoch": 1.2395904436860068,
+      "grad_norm": 0.6641042493963545,
+      "learning_rate": 3.7945088551445698e-06,
+      "loss": 0.2563,
+      "step": 227
+    },
+    {
+      "epoch": 1.245051194539249,
+      "grad_norm": 0.6196955536234605,
+      "learning_rate": 3.748228379590438e-06,
+      "loss": 0.2291,
+      "step": 228
+    },
+    {
+      "epoch": 1.2505119453924913,
+      "grad_norm": 0.6278753799486634,
+      "learning_rate": 3.7020620419029095e-06,
+      "loss": 0.2141,
+      "step": 229
+    },
+    {
+      "epoch": 1.2559726962457338,
+      "grad_norm": 0.6082644009007588,
+      "learning_rate": 3.656014051577713e-06,
+      "loss": 0.2122,
+      "step": 230
+    },
+    {
+      "epoch": 1.261433447098976,
+      "grad_norm": 0.6736359984841271,
+      "learning_rate": 3.610088607319544e-06,
+      "loss": 0.2367,
+      "step": 231
+    },
+    {
+      "epoch": 1.2668941979522184,
+      "grad_norm": 0.6329301932656438,
+      "learning_rate": 3.5642898966592145e-06,
+      "loss": 0.235,
+      "step": 232
+    },
+    {
+      "epoch": 1.2723549488054609,
+      "grad_norm": 0.619963960271499,
+      "learning_rate": 3.518622095571831e-06,
+      "loss": 0.2208,
+      "step": 233
+    },
+    {
+      "epoch": 1.2778156996587031,
+      "grad_norm": 0.6693990598652739,
+      "learning_rate": 3.4730893680960267e-06,
+      "loss": 0.2406,
+      "step": 234
+    },
+    {
+      "epoch": 1.2832764505119454,
+      "grad_norm": 0.6864592317171182,
+      "learning_rate": 3.4276958659542838e-06,
+      "loss": 0.243,
+      "step": 235
+    },
+    {
+      "epoch": 1.2887372013651877,
+      "grad_norm": 0.7236681291816511,
+      "learning_rate": 3.382445728174365e-06,
+      "loss": 0.2586,
+      "step": 236
+    },
+    {
+      "epoch": 1.29419795221843,
+      "grad_norm": 0.6176752667693888,
+      "learning_rate": 3.3373430807119212e-06,
+      "loss": 0.2251,
+      "step": 237
+    },
+    {
+      "epoch": 1.2996587030716724,
+      "grad_norm": 0.7022262485772638,
+      "learning_rate": 3.292392036074277e-06,
+      "loss": 0.2316,
+      "step": 238
+    },
+    {
+      "epoch": 1.3051194539249147,
+      "grad_norm": 0.6404240889042992,
+      "learning_rate": 3.2475966929454505e-06,
+      "loss": 0.2384,
+      "step": 239
+    },
+    {
+      "epoch": 1.310580204778157,
+      "grad_norm": 0.7080127357360425,
+      "learning_rate": 3.202961135812437e-06,
+      "loss": 0.248,
+      "step": 240
+    },
+    {
+      "epoch": 1.3160409556313994,
+      "grad_norm": 0.668638034601711,
+      "learning_rate": 3.1584894345927663e-06,
+      "loss": 0.2212,
+      "step": 241
+    },
+    {
+      "epoch": 1.3215017064846417,
+      "grad_norm": 0.6729621818012642,
+      "learning_rate": 3.114185644263415e-06,
+      "loss": 0.222,
+      "step": 242
+    },
+    {
+      "epoch": 1.326962457337884,
+      "grad_norm": 0.6723316181938683,
+      "learning_rate": 3.0700538044910684e-06,
+      "loss": 0.2246,
+      "step": 243
+    },
+    {
+      "epoch": 1.3324232081911263,
+      "grad_norm": 0.6671061425745013,
+      "learning_rate": 3.0260979392637753e-06,
+      "loss": 0.2518,
+      "step": 244
+    },
+    {
+      "epoch": 1.3378839590443685,
+      "grad_norm": 0.5962051816320753,
+      "learning_rate": 2.9823220565240396e-06,
+      "loss": 0.2224,
+      "step": 245
+    },
+    {
+      "epoch": 1.343344709897611,
+      "grad_norm": 0.6511243444073086,
+      "learning_rate": 2.9387301478033694e-06,
+      "loss": 0.2521,
+      "step": 246
+    },
+    {
+      "epoch": 1.3488054607508533,
+      "grad_norm": 0.6112346949791394,
+      "learning_rate": 2.8953261878583263e-06,
+      "loss": 0.2164,
+      "step": 247
+    },
+    {
+      "epoch": 1.3542662116040955,
+      "grad_norm": 0.6844064518509092,
+      "learning_rate": 2.852114134308104e-06,
+      "loss": 0.2532,
+      "step": 248
+    },
+    {
+      "epoch": 1.3597269624573378,
+      "grad_norm": 0.6383549765315465,
+      "learning_rate": 2.8090979272736663e-06,
+      "loss": 0.2401,
+      "step": 249
+    },
+    {
+      "epoch": 1.36518771331058,
+      "grad_norm": 0.5944587646093914,
+      "learning_rate": 2.766281489018482e-06,
+      "loss": 0.2293,
+      "step": 250
+    },
+    {
+      "epoch": 1.3706484641638226,
+      "grad_norm": 0.6307687611402706,
+      "learning_rate": 2.7236687235908953e-06,
+      "loss": 0.2188,
+      "step": 251
+    },
+    {
+      "epoch": 1.3761092150170648,
+      "grad_norm": 0.6238745929037437,
+      "learning_rate": 2.681263516468139e-06,
+      "loss": 0.2475,
+      "step": 252
+    },
+    {
+      "epoch": 1.3815699658703071,
+      "grad_norm": 0.6373763499985442,
+      "learning_rate": 2.6390697342020665e-06,
+      "loss": 0.2343,
+      "step": 253
+    },
+    {
+      "epoch": 1.3870307167235496,
+      "grad_norm": 0.6734367954708225,
+      "learning_rate": 2.5970912240665815e-06,
+      "loss": 0.2353,
+      "step": 254
+    },
+    {
+      "epoch": 1.3924914675767919,
+      "grad_norm": 0.6582720475674197,
+      "learning_rate": 2.5553318137068473e-06,
+      "loss": 0.2474,
+      "step": 255
+    },
+    {
+      "epoch": 1.3979522184300341,
+      "grad_norm": 0.6052116695135601,
+      "learning_rate": 2.5137953107902814e-06,
+      "loss": 0.2322,
+      "step": 256
+    },
+    {
+      "epoch": 1.4034129692832764,
+      "grad_norm": 0.6552372504854818,
+      "learning_rate": 2.472485502659358e-06,
+      "loss": 0.2468,
+      "step": 257
+    },
+    {
+      "epoch": 1.4088737201365187,
+      "grad_norm": 0.6302233591025854,
+      "learning_rate": 2.4314061559862836e-06,
+      "loss": 0.2398,
+      "step": 258
+    },
+    {
+      "epoch": 1.4143344709897612,
+      "grad_norm": 0.654084080401935,
+      "learning_rate": 2.3905610164295394e-06,
+      "loss": 0.2329,
+      "step": 259
+    },
+    {
+      "epoch": 1.4197952218430034,
+      "grad_norm": 0.6485524489438387,
+      "learning_rate": 2.3499538082923607e-06,
+      "loss": 0.2446,
+      "step": 260
+    },
+    {
+      "epoch": 1.4252559726962457,
+      "grad_norm": 0.6260148485778105,
+      "learning_rate": 2.309588234183137e-06,
+      "loss": 0.215,
+      "step": 261
+    },
+    {
+      "epoch": 1.430716723549488,
+      "grad_norm": 0.6165139801898837,
+      "learning_rate": 2.2694679746778116e-06,
+      "loss": 0.2235,
+      "step": 262
+    },
+    {
+      "epoch": 1.4361774744027302,
+      "grad_norm": 0.6073663452431178,
+      "learning_rate": 2.22959668798428e-06,
+      "loss": 0.21,
+      "step": 263
+    },
+    {
+      "epoch": 1.4416382252559727,
+      "grad_norm": 0.6687068934985456,
+      "learning_rate": 2.1899780096088375e-06,
+      "loss": 0.2609,
+      "step": 264
+    },
+    {
+      "epoch": 1.447098976109215,
+      "grad_norm": 0.5999286753849784,
+      "learning_rate": 2.1506155520246795e-06,
+      "loss": 0.2275,
+      "step": 265
+    },
+    {
+      "epoch": 1.4525597269624573,
+      "grad_norm": 0.6562378405208374,
+      "learning_rate": 2.1115129043425188e-06,
+      "loss": 0.2577,
+      "step": 266
+    },
+    {
+      "epoch": 1.4580204778156998,
+      "grad_norm": 0.6564390690276799,
+      "learning_rate": 2.072673631983323e-06,
+      "loss": 0.2583,
+      "step": 267
+    },
+    {
+      "epoch": 1.463481228668942,
+      "grad_norm": 0.6175405413313049,
+      "learning_rate": 2.0341012763532243e-06,
+      "loss": 0.2252,
+      "step": 268
+    },
+    {
+      "epoch": 1.4689419795221843,
+      "grad_norm": 0.6294576454771881,
+      "learning_rate": 1.995799354520598e-06,
+      "loss": 0.2282,
+      "step": 269
+    },
+    {
+      "epoch": 1.4744027303754266,
+      "grad_norm": 0.6491408881404807,
+      "learning_rate": 1.9577713588953797e-06,
+      "loss": 0.2204,
+      "step": 270
+    },
+    {
+      "epoch": 1.4798634812286688,
+      "grad_norm": 0.626492440911862,
+      "learning_rate": 1.9200207569106216e-06,
+      "loss": 0.2363,
+      "step": 271
+    },
+    {
+      "epoch": 1.4853242320819113,
+      "grad_norm": 0.6328542452711655,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.2312,
+      "step": 272
+    },
+    {
+      "epoch": 1.4907849829351536,
+      "grad_norm": 0.6502462448470019,
+      "learning_rate": 1.8453654768156138e-06,
+      "loss": 0.2512,
+      "step": 273
+    },
+    {
+      "epoch": 1.4962457337883959,
+      "grad_norm": 0.6012861830171234,
+      "learning_rate": 1.8084676058531376e-06,
+      "loss": 0.2285,
+      "step": 274
+    },
+    {
+      "epoch": 1.5017064846416384,
+      "grad_norm": 0.6834276368175269,
+      "learning_rate": 1.771860742205988e-06,
+      "loss": 0.2512,
+      "step": 275
+    },
+    {
+      "epoch": 1.5071672354948804,
+      "grad_norm": 0.6528553917231606,
+      "learning_rate": 1.7355482237268983e-06,
+      "loss": 0.2382,
+      "step": 276
+    },
+    {
+      "epoch": 1.512627986348123,
+      "grad_norm": 0.5819350883243867,
+      "learning_rate": 1.6995333614298908e-06,
+      "loss": 0.2097,
+      "step": 277
+    },
+    {
+      "epoch": 1.5180887372013652,
+      "grad_norm": 0.6231114790212122,
+      "learning_rate": 1.6638194391883822e-06,
+      "loss": 0.2352,
+      "step": 278
+    },
+    {
+      "epoch": 1.5235494880546074,
+      "grad_norm": 0.6082248229800555,
+      "learning_rate": 1.6284097134357535e-06,
+      "loss": 0.2241,
+      "step": 279
+    },
+    {
+      "epoch": 1.52901023890785,
+      "grad_norm": 0.5824479788396233,
+      "learning_rate": 1.5933074128684333e-06,
+      "loss": 0.2149,
+      "step": 280
+    },
+    {
+      "epoch": 1.5344709897610922,
+      "grad_norm": 0.6414988574509947,
+      "learning_rate": 1.5585157381514875e-06,
+      "loss": 0.2629,
+      "step": 281
+    },
+    {
+      "epoch": 1.5399317406143345,
+      "grad_norm": 0.6281763626708758,
+      "learning_rate": 1.5240378616267887e-06,
+      "loss": 0.2213,
+      "step": 282
+    },
+    {
+      "epoch": 1.545392491467577,
+      "grad_norm": 0.6342381052621304,
+      "learning_rate": 1.4898769270237611e-06,
+      "loss": 0.2469,
+      "step": 283
+    },
+    {
+      "epoch": 1.550853242320819,
+      "grad_norm": 0.63348306460088,
+      "learning_rate": 1.4560360491727233e-06,
+      "loss": 0.2369,
+      "step": 284
+    },
+    {
+      "epoch": 1.5563139931740615,
+      "grad_norm": 0.6211597914243564,
+      "learning_rate": 1.4225183137208775e-06,
+      "loss": 0.2464,
+      "step": 285
+    },
+    {
+      "epoch": 1.5617747440273038,
+      "grad_norm": 0.6287566376737247,
+      "learning_rate": 1.389326776850966e-06,
+      "loss": 0.2378,
+      "step": 286
+    },
+    {
+      "epoch": 1.567235494880546,
+      "grad_norm": 0.6155227503256832,
+      "learning_rate": 1.3564644650025894e-06,
+      "loss": 0.2501,
+      "step": 287
+    },
+    {
+      "epoch": 1.5726962457337885,
+      "grad_norm": 0.6705552802557545,
+      "learning_rate": 1.323934374596268e-06,
+      "loss": 0.2642,
+      "step": 288
+    },
+    {
+      "epoch": 1.5781569965870306,
+      "grad_norm": 0.6468155028186762,
+      "learning_rate": 1.2917394717602123e-06,
+      "loss": 0.2391,
+      "step": 289
+    },
+    {
+      "epoch": 1.583617747440273,
+      "grad_norm": 0.6059123207863814,
+      "learning_rate": 1.2598826920598773e-06,
+      "loss": 0.2471,
+      "step": 290
+    },
+    {
+      "epoch": 1.5890784982935153,
+      "grad_norm": 0.622906276078447,
+      "learning_rate": 1.2283669402302878e-06,
+      "loss": 0.2441,
+      "step": 291
+    },
+    {
+      "epoch": 1.5945392491467576,
+      "grad_norm": 0.6123734431964898,
+      "learning_rate": 1.197195089911191e-06,
+      "loss": 0.2359,
+      "step": 292
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6173696097759185,
+      "learning_rate": 1.166369983385024e-06,
+      "loss": 0.2302,
+      "step": 293
+    },
+    {
+      "epoch": 1.6054607508532424,
+      "grad_norm": 0.6309581460125253,
+      "learning_rate": 1.1358944313177566e-06,
+      "loss": 0.2312,
+      "step": 294
+    },
+    {
+      "epoch": 1.6109215017064846,
+      "grad_norm": 0.6390016010862638,
+      "learning_rate": 1.1057712125026116e-06,
+      "loss": 0.2442,
+      "step": 295
+    },
+    {
+      "epoch": 1.6163822525597271,
+      "grad_norm": 0.6276135127186313,
+      "learning_rate": 1.0760030736066952e-06,
+      "loss": 0.2297,
+      "step": 296
+    },
+    {
+      "epoch": 1.6218430034129692,
+      "grad_norm": 0.612896281499447,
+      "learning_rate": 1.0465927289205452e-06,
+      "loss": 0.2346,
+      "step": 297
+    },
+    {
+      "epoch": 1.6273037542662117,
+      "grad_norm": 0.5859909784104106,
+      "learning_rate": 1.0175428601106441e-06,
+      "loss": 0.2119,
+      "step": 298
+    },
+    {
+      "epoch": 1.632764505119454,
+      "grad_norm": 0.6209786013367464,
+      "learning_rate": 9.888561159748995e-07,
+      "loss": 0.2432,
+      "step": 299
+    },
+    {
+      "epoch": 1.6382252559726962,
+      "grad_norm": 0.6352233419147338,
+      "learning_rate": 9.605351122011308e-07,
+      "loss": 0.2392,
+      "step": 300
+    },
+    {
+      "epoch": 1.6436860068259387,
+      "grad_norm": 0.5719749997080835,
+      "learning_rate": 9.325824311285564e-07,
+      "loss": 0.2173,
+      "step": 301
+    },
+    {
+      "epoch": 1.6491467576791807,
+      "grad_norm": 0.6657684609315078,
+      "learning_rate": 9.050006215123419e-07,
+      "loss": 0.2606,
+      "step": 302
+    },
+    {
+      "epoch": 1.6546075085324232,
+      "grad_norm": 0.5728781873883457,
+      "learning_rate": 8.777921982911996e-07,
+      "loss": 0.2214,
+      "step": 303
+    },
+    {
+      "epoch": 1.6600682593856655,
+      "grad_norm": 0.6162844560531199,
+      "learning_rate": 8.509596423580712e-07,
+      "loss": 0.2464,
+      "step": 304
+    },
+    {
+      "epoch": 1.6655290102389078,
+      "grad_norm": 0.5952374213138941,
+      "learning_rate": 8.245054003339247e-07,
+      "loss": 0.226,
+      "step": 305
+    },
+    {
+      "epoch": 1.6709897610921502,
+      "grad_norm": 0.5961891699890017,
+      "learning_rate": 7.984318843446593e-07,
+      "loss": 0.2221,
+      "step": 306
+    },
+    {
+      "epoch": 1.6764505119453925,
+      "grad_norm": 0.5937715818201527,
+      "learning_rate": 7.727414718011706e-07,
+      "loss": 0.2117,
+      "step": 307
+    },
+    {
+      "epoch": 1.6819112627986348,
+      "grad_norm": 0.6853681886295775,
+      "learning_rate": 7.474365051825749e-07,
+      "loss": 0.257,
+      "step": 308
+    },
+    {
+      "epoch": 1.6873720136518773,
+      "grad_norm": 0.6359287265633253,
+      "learning_rate": 7.225192918226215e-07,
+      "loss": 0.2395,
+      "step": 309
+    },
+    {
+      "epoch": 1.6928327645051193,
+      "grad_norm": 0.5963026735275871,
+      "learning_rate": 6.979921036993042e-07,
+      "loss": 0.2233,
+      "step": 310
+    },
+    {
+      "epoch": 1.6982935153583618,
+      "grad_norm": 0.6319949149208983,
+      "learning_rate": 6.738571772276997e-07,
+      "loss": 0.2416,
+      "step": 311
+    },
+    {
+      "epoch": 1.703754266211604,
+      "grad_norm": 0.6203658184125409,
+      "learning_rate": 6.501167130560515e-07,
+      "loss": 0.2283,
+      "step": 312
+    },
+    {
+      "epoch": 1.7092150170648464,
+      "grad_norm": 0.5938364868062161,
+      "learning_rate": 6.267728758651131e-07,
+      "loss": 0.2302,
+      "step": 313
+    },
+    {
+      "epoch": 1.7146757679180888,
+      "grad_norm": 0.6087142064405593,
+      "learning_rate": 6.038277941707671e-07,
+      "loss": 0.2039,
+      "step": 314
+    },
+    {
+      "epoch": 1.7201365187713311,
+      "grad_norm": 0.6401443657158584,
+      "learning_rate": 5.812835601299438e-07,
+      "loss": 0.254,
+      "step": 315
+    },
+    {
+      "epoch": 1.7255972696245734,
+      "grad_norm": 0.5597403672115617,
+      "learning_rate": 5.591422293498633e-07,
+      "loss": 0.2074,
+      "step": 316
+    },
+    {
+      "epoch": 1.7310580204778157,
+      "grad_norm": 0.6510913944426799,
+      "learning_rate": 5.374058207005945e-07,
+      "loss": 0.242,
+      "step": 317
+    },
+    {
+      "epoch": 1.736518771331058,
+      "grad_norm": 0.5851164556251767,
+      "learning_rate": 5.160763161309768e-07,
+      "loss": 0.2208,
+      "step": 318
+    },
+    {
+      "epoch": 1.7419795221843004,
+      "grad_norm": 0.5863228147924701,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.2167,
+      "step": 319
+    },
+    {
+      "epoch": 1.7474402730375427,
+      "grad_norm": 0.6434185214532853,
+      "learning_rate": 4.7464576133899043e-07,
+      "loss": 0.2208,
+      "step": 320
+    },
+    {
+      "epoch": 1.752901023890785,
+      "grad_norm": 0.6536708886817881,
+      "learning_rate": 4.545484887986368e-07,
+      "loss": 0.2558,
+      "step": 321
+    },
+    {
+      "epoch": 1.7583617747440274,
+      "grad_norm": 0.5913503349988765,
+      "learning_rate": 4.348656753575092e-07,
+      "loss": 0.2412,
+      "step": 322
+    },
+    {
+      "epoch": 1.7638225255972695,
+      "grad_norm": 0.6056503972371652,
+      "learning_rate": 4.1559911571545544e-07,
+      "loss": 0.2302,
+      "step": 323
+    },
+    {
+      "epoch": 1.769283276450512,
+      "grad_norm": 0.6287557474105558,
+      "learning_rate": 3.9675056661785563e-07,
+      "loss": 0.2184,
+      "step": 324
+    },
+    {
+      "epoch": 1.7747440273037542,
+      "grad_norm": 0.6387002743522794,
+      "learning_rate": 3.783217466954503e-07,
+      "loss": 0.2302,
+      "step": 325
+    },
+    {
+      "epoch": 1.7802047781569965,
+      "grad_norm": 0.5919282825342829,
+      "learning_rate": 3.603143363076217e-07,
+      "loss": 0.2155,
+      "step": 326
+    },
+    {
+      "epoch": 1.785665529010239,
+      "grad_norm": 0.6473381627525607,
+      "learning_rate": 3.427299773891868e-07,
+      "loss": 0.2661,
+      "step": 327
+    },
+    {
+      "epoch": 1.7911262798634813,
+      "grad_norm": 0.5931604711623788,
+      "learning_rate": 3.255702733006766e-07,
+      "loss": 0.2338,
+      "step": 328
+    },
+    {
+      "epoch": 1.7965870307167235,
+      "grad_norm": 0.6129008231127687,
+      "learning_rate": 3.088367886821481e-07,
+      "loss": 0.2514,
+      "step": 329
+    },
+    {
+      "epoch": 1.802047781569966,
+      "grad_norm": 0.6062339345391793,
+      "learning_rate": 2.925310493105099e-07,
+      "loss": 0.208,
+      "step": 330
+    },
+    {
+      "epoch": 1.807508532423208,
+      "grad_norm": 0.640691825777882,
+      "learning_rate": 2.7665454196040665e-07,
+      "loss": 0.2568,
+      "step": 331
+    },
+    {
+      "epoch": 1.8129692832764506,
+      "grad_norm": 0.6228877907424235,
+      "learning_rate": 2.6120871426864866e-07,
+      "loss": 0.2445,
+      "step": 332
+    },
+    {
+      "epoch": 1.8184300341296928,
+      "grad_norm": 0.6109720444847905,
+      "learning_rate": 2.4619497460222184e-07,
+      "loss": 0.2408,
+      "step": 333
+    },
+    {
+      "epoch": 1.823890784982935,
+      "grad_norm": 0.6345094654832795,
+      "learning_rate": 2.316146919298623e-07,
+      "loss": 0.221,
+      "step": 334
+    },
+    {
+      "epoch": 1.8293515358361776,
+      "grad_norm": 0.5612296424074616,
+      "learning_rate": 2.1746919569723858e-07,
+      "loss": 0.2137,
+      "step": 335
+    },
+    {
+      "epoch": 1.8348122866894196,
+      "grad_norm": 0.5831279872950338,
+      "learning_rate": 2.037597757057297e-07,
+      "loss": 0.2178,
+      "step": 336
+    },
+    {
+      "epoch": 1.8402730375426621,
+      "grad_norm": 0.639477342500686,
+      "learning_rate": 1.9048768199481983e-07,
+      "loss": 0.2417,
+      "step": 337
+    },
+    {
+      "epoch": 1.8457337883959044,
+      "grad_norm": 0.5861730216308635,
+      "learning_rate": 1.776541247281177e-07,
+      "loss": 0.229,
+      "step": 338
+    },
+    {
+      "epoch": 1.8511945392491467,
+      "grad_norm": 0.6019956045442054,
+      "learning_rate": 1.6526027408301227e-07,
+      "loss": 0.2212,
+      "step": 339
+    },
+    {
+      "epoch": 1.8566552901023892,
+      "grad_norm": 0.59132952240458,
+      "learning_rate": 1.5330726014397668e-07,
+      "loss": 0.2301,
+      "step": 340
+    },
+    {
+      "epoch": 1.8621160409556314,
+      "grad_norm": 0.6078005334703832,
+      "learning_rate": 1.417961727995254e-07,
+      "loss": 0.2239,
+      "step": 341
+    },
+    {
+      "epoch": 1.8675767918088737,
+      "grad_norm": 0.585630251596369,
+      "learning_rate": 1.307280616428336e-07,
+      "loss": 0.2093,
+      "step": 342
+    },
+    {
+      "epoch": 1.8730375426621162,
+      "grad_norm": 0.6003005675220531,
+      "learning_rate": 1.2010393587603975e-07,
+      "loss": 0.2558,
+      "step": 343
+    },
+    {
+      "epoch": 1.8784982935153582,
+      "grad_norm": 0.6007862550074166,
+      "learning_rate": 1.0992476421822052e-07,
+      "loss": 0.2217,
+      "step": 344
+    },
+    {
+      "epoch": 1.8839590443686007,
+      "grad_norm": 0.5798264754441842,
+      "learning_rate": 1.0019147481706626e-07,
+      "loss": 0.2,
+      "step": 345
+    },
+    {
+      "epoch": 1.889419795221843,
+      "grad_norm": 0.5801152259959127,
+      "learning_rate": 9.090495516424713e-08,
+      "loss": 0.2219,
+      "step": 346
+    },
+    {
+      "epoch": 1.8948805460750853,
+      "grad_norm": 0.5923845690395708,
+      "learning_rate": 8.206605201449447e-08,
+      "loss": 0.2029,
+      "step": 347
+    },
+    {
+      "epoch": 1.9003412969283278,
+      "grad_norm": 0.5987478859251119,
+      "learning_rate": 7.367557130838921e-08,
+      "loss": 0.2256,
+      "step": 348
+    },
+    {
+      "epoch": 1.9058020477815698,
+      "grad_norm": 0.5842539453063824,
+      "learning_rate": 6.573427809888067e-08,
+      "loss": 0.2003,
+      "step": 349
+    },
+    {
+      "epoch": 1.9112627986348123,
+      "grad_norm": 0.6351293922330473,
+      "learning_rate": 5.824289648152126e-08,
+      "loss": 0.2395,
+      "step": 350
+    },
+    {
+      "epoch": 1.9167235494880546,
+      "grad_norm": 0.6674020151826169,
+      "learning_rate": 5.120210952844873e-08,
+      "loss": 0.271,
+      "step": 351
+    },
+    {
+      "epoch": 1.9221843003412968,
+      "grad_norm": 0.5675294646121625,
+      "learning_rate": 4.461255922609986e-08,
+      "loss": 0.2172,
+      "step": 352
+    },
+    {
+      "epoch": 1.9276450511945393,
+      "grad_norm": 0.6285436049388992,
+      "learning_rate": 3.8474846416672874e-08,
+      "loss": 0.2399,
+      "step": 353
+    },
+    {
+      "epoch": 1.9331058020477816,
+      "grad_norm": 0.6175868696026672,
+      "learning_rate": 3.278953074334512e-08,
+      "loss": 0.2212,
+      "step": 354
+    },
+    {
+      "epoch": 1.9385665529010239,
+      "grad_norm": 0.6190764065365002,
+      "learning_rate": 2.75571305992417e-08,
+      "loss": 0.2374,
+      "step": 355
+    },
+    {
+      "epoch": 1.9440273037542664,
+      "grad_norm": 0.6366754795576353,
+      "learning_rate": 2.2778123080167136e-08,
+      "loss": 0.2317,
+      "step": 356
+    },
+    {
+      "epoch": 1.9494880546075084,
+      "grad_norm": 0.6088811286257059,
+      "learning_rate": 1.845294394110686e-08,
+      "loss": 0.2161,
+      "step": 357
+    },
+    {
+      "epoch": 1.954948805460751,
+      "grad_norm": 0.5983150959140915,
+      "learning_rate": 1.4581987556490095e-08,
+      "loss": 0.2273,
+      "step": 358
+    },
+    {
+      "epoch": 1.9604095563139932,
+      "grad_norm": 0.6172951456789394,
+      "learning_rate": 1.1165606884234182e-08,
+      "loss": 0.2514,
+      "step": 359
+    },
+    {
+      "epoch": 1.9658703071672354,
+      "grad_norm": 0.6110206348502005,
+      "learning_rate": 8.204113433559202e-09,
+      "loss": 0.2248,
+      "step": 360
+    },
+    {
+      "epoch": 1.971331058020478,
+      "grad_norm": 0.5973553403473014,
+      "learning_rate": 5.6977772365857105e-09,
+      "loss": 0.2415,
+      "step": 361
+    },
+    {
+      "epoch": 1.9767918088737202,
+      "grad_norm": 0.6109000206055947,
+      "learning_rate": 3.6468268237105364e-09,
+      "loss": 0.2319,
+      "step": 362
+    },
+    {
+      "epoch": 1.9822525597269625,
+      "grad_norm": 0.6357125881065677,
+      "learning_rate": 2.0514492027728928e-09,
+      "loss": 0.2457,
+      "step": 363
+    },
+    {
+      "epoch": 1.9877133105802047,
+      "grad_norm": 0.669166818877388,
+      "learning_rate": 9.117898419991333e-10,
+      "loss": 0.2574,
+      "step": 364
+    },
+    {
+      "epoch": 1.993174061433447,
+      "grad_norm": 0.6418127603308712,
+      "learning_rate": 2.2795265674113721e-10,
+      "loss": 0.2499,
+      "step": 365
+    },
+    {
+      "epoch": 1.9986348122866895,
+      "grad_norm": 0.6075592770961785,
+      "learning_rate": 0.0,
+      "loss": 0.2179,
+      "step": 366
+    },
+    {
+      "epoch": 1.9986348122866895,
+      "step": 366,
+      "total_flos": 86796684656640.0,
+      "train_loss": 0.2950779539965541,
+      "train_runtime": 2999.324,
+      "train_samples_per_second": 15.628,
+      "train_steps_per_second": 0.122
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 366,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 86796684656640.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29b3038da8136ba73edce7f5e6c8ae50ccd51452534007edec5320d988ff0a5
+size 7160