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

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: original
+  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. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the Sky-T1 dataset.
+
+## 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: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch 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 2.4.0a0+f70bd71a48.nv24.06
+- 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 +1,8 @@
+{
+    "epoch": 1.9990426041168023,
+    "total_flos": 358710641426432.0,
+    "train_loss": 0.5378552473139488,
+    "train_runtime": 32465.3196,
+    "train_samples_per_second": 1.029,
+    "train_steps_per_second": 0.011
+}

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
+}

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 sha256:0d2288d652d9c1adf00f244bf7c002c6f42dad1e0c8d07b311604807860e521e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f170791fd98a0e443b713e2e89d78df7b4f803471301a32d807c5070d45f232
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4395c284a71384a65559b9399674e85f997185dcf3364d3f8201aaa8a2eaa2
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7364b87d717dc8e8be8525e0da5fb7d08341f2ca418a76c228ab58326b4aa7c
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9990426041168023,
+    "total_flos": 358710641426432.0,
+    "train_loss": 0.5378552473139488,
+    "train_runtime": 32465.3196,
+    "train_samples_per_second": 1.029,
+    "train_steps_per_second": 0.011
+}

trainer_log.jsonl

@@ -0,0 +1,349 @@
+{"current_steps": 1, "total_steps": 348, "loss": 0.8587, "lr": 2.8571428571428575e-07, "epoch": 0.0057443752991862135, "percentage": 0.29, "elapsed_time": "0:01:30", "remaining_time": "8:44:25"}
+{"current_steps": 2, "total_steps": 348, "loss": 0.8936, "lr": 5.714285714285715e-07, "epoch": 0.011488750598372427, "percentage": 0.57, "elapsed_time": "0:03:14", "remaining_time": "9:21:10"}
+{"current_steps": 3, "total_steps": 348, "loss": 0.9174, "lr": 8.571428571428572e-07, "epoch": 0.01723312589755864, "percentage": 0.86, "elapsed_time": "0:04:39", "remaining_time": "8:56:28"}
+{"current_steps": 4, "total_steps": 348, "loss": 0.8825, "lr": 1.142857142857143e-06, "epoch": 0.022977501196744854, "percentage": 1.15, "elapsed_time": "0:06:09", "remaining_time": "8:50:06"}
+{"current_steps": 5, "total_steps": 348, "loss": 0.8794, "lr": 1.4285714285714286e-06, "epoch": 0.028721876495931067, "percentage": 1.44, "elapsed_time": "0:07:41", "remaining_time": "8:47:24"}
+{"current_steps": 6, "total_steps": 348, "loss": 0.8566, "lr": 1.7142857142857145e-06, "epoch": 0.03446625179511728, "percentage": 1.72, "elapsed_time": "0:08:49", "remaining_time": "8:22:37"}
+{"current_steps": 7, "total_steps": 348, "loss": 0.8527, "lr": 2.0000000000000003e-06, "epoch": 0.040210627094303494, "percentage": 2.01, "elapsed_time": "0:10:14", "remaining_time": "8:18:48"}
+{"current_steps": 8, "total_steps": 348, "loss": 0.8273, "lr": 2.285714285714286e-06, "epoch": 0.04595500239348971, "percentage": 2.3, "elapsed_time": "0:11:44", "remaining_time": "8:19:17"}
+{"current_steps": 9, "total_steps": 348, "loss": 0.7763, "lr": 2.571428571428571e-06, "epoch": 0.05169937769267592, "percentage": 2.59, "elapsed_time": "0:13:12", "remaining_time": "8:17:14"}
+{"current_steps": 10, "total_steps": 348, "loss": 0.832, "lr": 2.8571428571428573e-06, "epoch": 0.057443752991862135, "percentage": 2.87, "elapsed_time": "0:14:40", "remaining_time": "8:16:10"}
+{"current_steps": 11, "total_steps": 348, "loss": 0.8195, "lr": 3.142857142857143e-06, "epoch": 0.06318812829104835, "percentage": 3.16, "elapsed_time": "0:16:10", "remaining_time": "8:15:42"}
+{"current_steps": 12, "total_steps": 348, "loss": 0.7293, "lr": 3.428571428571429e-06, "epoch": 0.06893250359023456, "percentage": 3.45, "elapsed_time": "0:17:44", "remaining_time": "8:16:57"}
+{"current_steps": 13, "total_steps": 348, "loss": 0.7993, "lr": 3.7142857142857146e-06, "epoch": 0.07467687888942078, "percentage": 3.74, "elapsed_time": "0:19:20", "remaining_time": "8:18:18"}
+{"current_steps": 14, "total_steps": 348, "loss": 0.7821, "lr": 4.000000000000001e-06, "epoch": 0.08042125418860699, "percentage": 4.02, "elapsed_time": "0:20:33", "remaining_time": "8:10:18"}
+{"current_steps": 15, "total_steps": 348, "loss": 0.7953, "lr": 4.2857142857142855e-06, "epoch": 0.0861656294877932, "percentage": 4.31, "elapsed_time": "0:22:08", "remaining_time": "8:11:32"}
+{"current_steps": 16, "total_steps": 348, "loss": 0.7904, "lr": 4.571428571428572e-06, "epoch": 0.09191000478697942, "percentage": 4.6, "elapsed_time": "0:23:48", "remaining_time": "8:14:03"}
+{"current_steps": 17, "total_steps": 348, "loss": 0.7397, "lr": 4.857142857142858e-06, "epoch": 0.09765438008616563, "percentage": 4.89, "elapsed_time": "0:25:14", "remaining_time": "8:11:26"}
+{"current_steps": 18, "total_steps": 348, "loss": 0.7405, "lr": 5.142857142857142e-06, "epoch": 0.10339875538535184, "percentage": 5.17, "elapsed_time": "0:26:52", "remaining_time": "8:12:36"}
+{"current_steps": 19, "total_steps": 348, "loss": 0.6697, "lr": 5.428571428571429e-06, "epoch": 0.10914313068453806, "percentage": 5.46, "elapsed_time": "0:28:22", "remaining_time": "8:11:27"}
+{"current_steps": 20, "total_steps": 348, "loss": 0.6977, "lr": 5.7142857142857145e-06, "epoch": 0.11488750598372427, "percentage": 5.75, "elapsed_time": "0:30:02", "remaining_time": "8:12:38"}
+{"current_steps": 21, "total_steps": 348, "loss": 0.6796, "lr": 6e-06, "epoch": 0.12063188128291048, "percentage": 6.03, "elapsed_time": "0:31:35", "remaining_time": "8:11:50"}
+{"current_steps": 22, "total_steps": 348, "loss": 0.674, "lr": 6.285714285714286e-06, "epoch": 0.1263762565820967, "percentage": 6.32, "elapsed_time": "0:33:03", "remaining_time": "8:09:49"}
+{"current_steps": 23, "total_steps": 348, "loss": 0.6336, "lr": 6.571428571428572e-06, "epoch": 0.13212063188128292, "percentage": 6.61, "elapsed_time": "0:34:31", "remaining_time": "8:07:52"}
+{"current_steps": 24, "total_steps": 348, "loss": 0.6701, "lr": 6.857142857142858e-06, "epoch": 0.13786500718046912, "percentage": 6.9, "elapsed_time": "0:36:04", "remaining_time": "8:06:56"}
+{"current_steps": 25, "total_steps": 348, "loss": 0.6557, "lr": 7.1428571428571436e-06, "epoch": 0.14360938247965535, "percentage": 7.18, "elapsed_time": "0:37:42", "remaining_time": "8:07:15"}
+{"current_steps": 26, "total_steps": 348, "loss": 0.6453, "lr": 7.428571428571429e-06, "epoch": 0.14935375777884155, "percentage": 7.47, "elapsed_time": "0:38:59", "remaining_time": "8:02:56"}
+{"current_steps": 27, "total_steps": 348, "loss": 0.6813, "lr": 7.714285714285716e-06, "epoch": 0.15509813307802778, "percentage": 7.76, "elapsed_time": "0:40:40", "remaining_time": "8:03:33"}
+{"current_steps": 28, "total_steps": 348, "loss": 0.6415, "lr": 8.000000000000001e-06, "epoch": 0.16084250837721398, "percentage": 8.05, "elapsed_time": "0:42:07", "remaining_time": "8:01:28"}
+{"current_steps": 29, "total_steps": 348, "loss": 0.6287, "lr": 8.285714285714287e-06, "epoch": 0.1665868836764002, "percentage": 8.33, "elapsed_time": "0:43:37", "remaining_time": "7:59:47"}
+{"current_steps": 30, "total_steps": 348, "loss": 0.6347, "lr": 8.571428571428571e-06, "epoch": 0.1723312589755864, "percentage": 8.62, "elapsed_time": "0:45:16", "remaining_time": "7:59:57"}
+{"current_steps": 31, "total_steps": 348, "loss": 0.5939, "lr": 8.857142857142858e-06, "epoch": 0.17807563427477263, "percentage": 8.91, "elapsed_time": "0:46:57", "remaining_time": "8:00:11"}
+{"current_steps": 32, "total_steps": 348, "loss": 0.5704, "lr": 9.142857142857144e-06, "epoch": 0.18382000957395883, "percentage": 9.2, "elapsed_time": "0:48:08", "remaining_time": "7:55:27"}
+{"current_steps": 33, "total_steps": 348, "loss": 0.6125, "lr": 9.42857142857143e-06, "epoch": 0.18956438487314506, "percentage": 9.48, "elapsed_time": "0:49:45", "remaining_time": "7:54:58"}
+{"current_steps": 34, "total_steps": 348, "loss": 0.6332, "lr": 9.714285714285715e-06, "epoch": 0.19530876017233126, "percentage": 9.77, "elapsed_time": "0:51:10", "remaining_time": "7:52:33"}
+{"current_steps": 35, "total_steps": 348, "loss": 0.6196, "lr": 1e-05, "epoch": 0.20105313547151749, "percentage": 10.06, "elapsed_time": "0:52:43", "remaining_time": "7:51:28"}
+{"current_steps": 36, "total_steps": 348, "loss": 0.6135, "lr": 9.999748146823376e-06, "epoch": 0.20679751077070369, "percentage": 10.34, "elapsed_time": "0:54:31", "remaining_time": "7:52:34"}
+{"current_steps": 37, "total_steps": 348, "loss": 0.5972, "lr": 9.99899261266551e-06, "epoch": 0.2125418860698899, "percentage": 10.63, "elapsed_time": "0:56:01", "remaining_time": "7:50:56"}
+{"current_steps": 38, "total_steps": 348, "loss": 0.6111, "lr": 9.997733473639876e-06, "epoch": 0.2182862613690761, "percentage": 10.92, "elapsed_time": "0:57:46", "remaining_time": "7:51:15"}
+{"current_steps": 39, "total_steps": 348, "loss": 0.6117, "lr": 9.995970856593739e-06, "epoch": 0.22403063666826234, "percentage": 11.21, "elapsed_time": "0:59:34", "remaining_time": "7:51:58"}
+{"current_steps": 40, "total_steps": 348, "loss": 0.5887, "lr": 9.993704939095376e-06, "epoch": 0.22977501196744854, "percentage": 11.49, "elapsed_time": "1:01:05", "remaining_time": "7:50:24"}
+{"current_steps": 41, "total_steps": 348, "loss": 0.631, "lr": 9.9909359494162e-06, "epoch": 0.23551938726663477, "percentage": 11.78, "elapsed_time": "1:02:40", "remaining_time": "7:49:18"}
+{"current_steps": 42, "total_steps": 348, "loss": 0.5682, "lr": 9.987664166507749e-06, "epoch": 0.24126376256582097, "percentage": 12.07, "elapsed_time": "1:04:27", "remaining_time": "7:49:35"}
+{"current_steps": 43, "total_steps": 348, "loss": 0.6056, "lr": 9.983889919973586e-06, "epoch": 0.2470081378650072, "percentage": 12.36, "elapsed_time": "1:05:58", "remaining_time": "7:47:56"}
+{"current_steps": 44, "total_steps": 348, "loss": 0.6209, "lr": 9.979613590036108e-06, "epoch": 0.2527525131641934, "percentage": 12.64, "elapsed_time": "1:07:38", "remaining_time": "7:47:22"}
+{"current_steps": 45, "total_steps": 348, "loss": 0.605, "lr": 9.974835607498224e-06, "epoch": 0.2584968884633796, "percentage": 12.93, "elapsed_time": "1:09:17", "remaining_time": "7:46:32"}
+{"current_steps": 46, "total_steps": 348, "loss": 0.556, "lr": 9.969556453699966e-06, "epoch": 0.26424126376256585, "percentage": 13.22, "elapsed_time": "1:10:46", "remaining_time": "7:44:38"}
+{"current_steps": 47, "total_steps": 348, "loss": 0.5852, "lr": 9.963776660469996e-06, "epoch": 0.26998563906175205, "percentage": 13.51, "elapsed_time": "1:12:15", "remaining_time": "7:42:46"}
+{"current_steps": 48, "total_steps": 348, "loss": 0.5736, "lr": 9.957496810072027e-06, "epoch": 0.27573001436093825, "percentage": 13.79, "elapsed_time": "1:14:03", "remaining_time": "7:42:49"}
+{"current_steps": 49, "total_steps": 348, "loss": 0.6078, "lr": 9.95071753514617e-06, "epoch": 0.28147438966012445, "percentage": 14.08, "elapsed_time": "1:15:53", "remaining_time": "7:43:03"}
+{"current_steps": 50, "total_steps": 348, "loss": 0.5638, "lr": 9.943439518645193e-06, "epoch": 0.2872187649593107, "percentage": 14.37, "elapsed_time": "1:17:25", "remaining_time": "7:41:26"}
+{"current_steps": 51, "total_steps": 348, "loss": 0.5501, "lr": 9.935663493765726e-06, "epoch": 0.2929631402584969, "percentage": 14.66, "elapsed_time": "1:18:57", "remaining_time": "7:39:50"}
+{"current_steps": 52, "total_steps": 348, "loss": 0.596, "lr": 9.9273902438744e-06, "epoch": 0.2987075155576831, "percentage": 14.94, "elapsed_time": "1:20:34", "remaining_time": "7:38:41"}
+{"current_steps": 53, "total_steps": 348, "loss": 0.568, "lr": 9.918620602428916e-06, "epoch": 0.3044518908568693, "percentage": 15.23, "elapsed_time": "1:21:55", "remaining_time": "7:35:57"}
+{"current_steps": 54, "total_steps": 348, "loss": 0.5581, "lr": 9.909355452894098e-06, "epoch": 0.31019626615605556, "percentage": 15.52, "elapsed_time": "1:23:38", "remaining_time": "7:35:23"}
+{"current_steps": 55, "total_steps": 348, "loss": 0.5628, "lr": 9.899595728652883e-06, "epoch": 0.31594064145524176, "percentage": 15.8, "elapsed_time": "1:24:58", "remaining_time": "7:32:41"}
+{"current_steps": 56, "total_steps": 348, "loss": 0.5708, "lr": 9.889342412912296e-06, "epoch": 0.32168501675442795, "percentage": 16.09, "elapsed_time": "1:26:37", "remaining_time": "7:31:41"}
+{"current_steps": 57, "total_steps": 348, "loss": 0.5792, "lr": 9.878596538604388e-06, "epoch": 0.32742939205361415, "percentage": 16.38, "elapsed_time": "1:28:16", "remaining_time": "7:30:41"}
+{"current_steps": 58, "total_steps": 348, "loss": 0.5733, "lr": 9.867359188282193e-06, "epoch": 0.3331737673528004, "percentage": 16.67, "elapsed_time": "1:29:46", "remaining_time": "7:28:51"}
+{"current_steps": 59, "total_steps": 348, "loss": 0.5473, "lr": 9.855631494010661e-06, "epoch": 0.3389181426519866, "percentage": 16.95, "elapsed_time": "1:31:20", "remaining_time": "7:27:23"}
+{"current_steps": 60, "total_steps": 348, "loss": 0.5568, "lr": 9.843414637252615e-06, "epoch": 0.3446625179511728, "percentage": 17.24, "elapsed_time": "1:32:35", "remaining_time": "7:24:24"}
+{"current_steps": 61, "total_steps": 348, "loss": 0.5732, "lr": 9.830709848749727e-06, "epoch": 0.350406893250359, "percentage": 17.53, "elapsed_time": "1:34:11", "remaining_time": "7:23:10"}
+{"current_steps": 62, "total_steps": 348, "loss": 0.5825, "lr": 9.817518408398536e-06, "epoch": 0.35615126854954526, "percentage": 17.82, "elapsed_time": "1:35:48", "remaining_time": "7:21:58"}
+{"current_steps": 63, "total_steps": 348, "loss": 0.5664, "lr": 9.803841645121505e-06, "epoch": 0.36189564384873146, "percentage": 18.1, "elapsed_time": "1:37:21", "remaining_time": "7:20:24"}
+{"current_steps": 64, "total_steps": 348, "loss": 0.55, "lr": 9.78968093673314e-06, "epoch": 0.36764001914791766, "percentage": 18.39, "elapsed_time": "1:38:52", "remaining_time": "7:18:44"}
+{"current_steps": 65, "total_steps": 348, "loss": 0.572, "lr": 9.775037709801206e-06, "epoch": 0.37338439444710386, "percentage": 18.68, "elapsed_time": "1:40:18", "remaining_time": "7:16:44"}
+{"current_steps": 66, "total_steps": 348, "loss": 0.5657, "lr": 9.759913439502982e-06, "epoch": 0.3791287697462901, "percentage": 18.97, "elapsed_time": "1:41:46", "remaining_time": "7:14:50"}
+{"current_steps": 67, "total_steps": 348, "loss": 0.5261, "lr": 9.74430964947668e-06, "epoch": 0.3848731450454763, "percentage": 19.25, "elapsed_time": "1:43:08", "remaining_time": "7:12:35"}
+{"current_steps": 68, "total_steps": 348, "loss": 0.5494, "lr": 9.728227911667934e-06, "epoch": 0.3906175203446625, "percentage": 19.54, "elapsed_time": "1:44:43", "remaining_time": "7:11:11"}
+{"current_steps": 69, "total_steps": 348, "loss": 0.5771, "lr": 9.711669846171443e-06, "epoch": 0.3963618956438487, "percentage": 19.83, "elapsed_time": "1:46:16", "remaining_time": "7:09:41"}
+{"current_steps": 70, "total_steps": 348, "loss": 0.501, "lr": 9.694637121067764e-06, "epoch": 0.40210627094303497, "percentage": 20.11, "elapsed_time": "1:47:44", "remaining_time": "7:07:54"}
+{"current_steps": 71, "total_steps": 348, "loss": 0.555, "lr": 9.677131452255272e-06, "epoch": 0.40785064624222117, "percentage": 20.4, "elapsed_time": "1:49:13", "remaining_time": "7:06:07"}
+{"current_steps": 72, "total_steps": 348, "loss": 0.5344, "lr": 9.659154603277283e-06, "epoch": 0.41359502154140737, "percentage": 20.69, "elapsed_time": "1:50:52", "remaining_time": "7:04:59"}
+{"current_steps": 73, "total_steps": 348, "loss": 0.5547, "lr": 9.640708385144403e-06, "epoch": 0.41933939684059357, "percentage": 20.98, "elapsed_time": "1:52:23", "remaining_time": "7:03:21"}
+{"current_steps": 74, "total_steps": 348, "loss": 0.5578, "lr": 9.62179465615209e-06, "epoch": 0.4250837721397798, "percentage": 21.26, "elapsed_time": "1:53:51", "remaining_time": "7:01:35"}
+{"current_steps": 75, "total_steps": 348, "loss": 0.5687, "lr": 9.602415321693434e-06, "epoch": 0.430828147438966, "percentage": 21.55, "elapsed_time": "1:55:23", "remaining_time": "7:00:02"}
+{"current_steps": 76, "total_steps": 348, "loss": 0.5447, "lr": 9.582572334067213e-06, "epoch": 0.4365725227381522, "percentage": 21.84, "elapsed_time": "1:56:56", "remaining_time": "6:58:30"}
+{"current_steps": 77, "total_steps": 348, "loss": 0.5713, "lr": 9.562267692281212e-06, "epoch": 0.4423168980373384, "percentage": 22.13, "elapsed_time": "1:58:38", "remaining_time": "6:57:35"}
+{"current_steps": 78, "total_steps": 348, "loss": 0.5486, "lr": 9.541503441850844e-06, "epoch": 0.4480612733365247, "percentage": 22.41, "elapsed_time": "2:00:17", "remaining_time": "6:56:23"}
+{"current_steps": 79, "total_steps": 348, "loss": 0.5577, "lr": 9.520281674593084e-06, "epoch": 0.4538056486357109, "percentage": 22.7, "elapsed_time": "2:02:00", "remaining_time": "6:55:28"}
+{"current_steps": 80, "total_steps": 348, "loss": 0.5397, "lr": 9.498604528415731e-06, "epoch": 0.4595500239348971, "percentage": 22.99, "elapsed_time": "2:03:41", "remaining_time": "6:54:21"}
+{"current_steps": 81, "total_steps": 348, "loss": 0.5438, "lr": 9.476474187102033e-06, "epoch": 0.4652943992340833, "percentage": 23.28, "elapsed_time": "2:04:59", "remaining_time": "6:51:59"}
+{"current_steps": 82, "total_steps": 348, "loss": 0.5624, "lr": 9.453892880090696e-06, "epoch": 0.47103877453326953, "percentage": 23.56, "elapsed_time": "2:06:38", "remaining_time": "6:50:48"}
+{"current_steps": 83, "total_steps": 348, "loss": 0.5473, "lr": 9.430862882251279e-06, "epoch": 0.47678314983245573, "percentage": 23.85, "elapsed_time": "2:08:18", "remaining_time": "6:49:38"}
+{"current_steps": 84, "total_steps": 348, "loss": 0.5757, "lr": 9.40738651365503e-06, "epoch": 0.48252752513164193, "percentage": 24.14, "elapsed_time": "2:09:48", "remaining_time": "6:47:59"}
+{"current_steps": 85, "total_steps": 348, "loss": 0.5335, "lr": 9.38346613934115e-06, "epoch": 0.48827190043082813, "percentage": 24.43, "elapsed_time": "2:11:33", "remaining_time": "6:47:02"}
+{"current_steps": 86, "total_steps": 348, "loss": 0.5509, "lr": 9.359104169078541e-06, "epoch": 0.4940162757300144, "percentage": 24.71, "elapsed_time": "2:13:04", "remaining_time": "6:45:26"}
+{"current_steps": 87, "total_steps": 348, "loss": 0.5676, "lr": 9.334303057123044e-06, "epoch": 0.4997606510292006, "percentage": 25.0, "elapsed_time": "2:14:51", "remaining_time": "6:44:35"}
+{"current_steps": 88, "total_steps": 348, "loss": 0.5515, "lr": 9.309065301970193e-06, "epoch": 0.5055050263283868, "percentage": 25.29, "elapsed_time": "2:16:34", "remaining_time": "6:43:32"}
+{"current_steps": 89, "total_steps": 348, "loss": 0.5474, "lr": 9.283393446103506e-06, "epoch": 0.511249401627573, "percentage": 25.57, "elapsed_time": "2:18:12", "remaining_time": "6:42:11"}
+{"current_steps": 90, "total_steps": 348, "loss": 0.5574, "lr": 9.257290075738365e-06, "epoch": 0.5169937769267592, "percentage": 25.86, "elapsed_time": "2:19:44", "remaining_time": "6:40:36"}
+{"current_steps": 91, "total_steps": 348, "loss": 0.535, "lr": 9.23075782056147e-06, "epoch": 0.5227381522259454, "percentage": 26.15, "elapsed_time": "2:21:03", "remaining_time": "6:38:22"}
+{"current_steps": 92, "total_steps": 348, "loss": 0.5409, "lr": 9.20379935346592e-06, "epoch": 0.5284825275251317, "percentage": 26.44, "elapsed_time": "2:22:45", "remaining_time": "6:37:13"}
+{"current_steps": 93, "total_steps": 348, "loss": 0.5293, "lr": 9.176417390281944e-06, "epoch": 0.5342269028243178, "percentage": 26.72, "elapsed_time": "2:24:22", "remaining_time": "6:35:52"}
+{"current_steps": 94, "total_steps": 348, "loss": 0.5585, "lr": 9.148614689503307e-06, "epoch": 0.5399712781235041, "percentage": 27.01, "elapsed_time": "2:25:45", "remaining_time": "6:33:51"}
+{"current_steps": 95, "total_steps": 348, "loss": 0.5464, "lr": 9.120394052009412e-06, "epoch": 0.5457156534226902, "percentage": 27.3, "elapsed_time": "2:27:30", "remaining_time": "6:32:49"}
+{"current_steps": 96, "total_steps": 348, "loss": 0.5603, "lr": 9.091758320783139e-06, "epoch": 0.5514600287218765, "percentage": 27.59, "elapsed_time": "2:29:04", "remaining_time": "6:31:19"}
+{"current_steps": 97, "total_steps": 348, "loss": 0.5307, "lr": 9.062710380624439e-06, "epoch": 0.5572044040210627, "percentage": 27.87, "elapsed_time": "2:30:39", "remaining_time": "6:29:50"}
+{"current_steps": 98, "total_steps": 348, "loss": 0.5733, "lr": 9.033253157859715e-06, "epoch": 0.5629487793202489, "percentage": 28.16, "elapsed_time": "2:32:22", "remaining_time": "6:28:42"}
+{"current_steps": 99, "total_steps": 348, "loss": 0.5288, "lr": 9.003389620047012e-06, "epoch": 0.5686931546194351, "percentage": 28.45, "elapsed_time": "2:33:48", "remaining_time": "6:26:52"}
+{"current_steps": 100, "total_steps": 348, "loss": 0.5322, "lr": 8.973122775677078e-06, "epoch": 0.5744375299186214, "percentage": 28.74, "elapsed_time": "2:35:00", "remaining_time": "6:24:25"}
+{"current_steps": 101, "total_steps": 348, "loss": 0.5638, "lr": 8.942455673870278e-06, "epoch": 0.5801819052178075, "percentage": 29.02, "elapsed_time": "2:37:38", "remaining_time": "6:25:31"}
+{"current_steps": 102, "total_steps": 348, "loss": 0.5603, "lr": 8.91139140406941e-06, "epoch": 0.5859262805169938, "percentage": 29.31, "elapsed_time": "2:39:13", "remaining_time": "6:24:00"}
+{"current_steps": 103, "total_steps": 348, "loss": 0.5454, "lr": 8.879933095728485e-06, "epoch": 0.59167065581618, "percentage": 29.6, "elapsed_time": "2:40:39", "remaining_time": "6:22:09"}
+{"current_steps": 104, "total_steps": 348, "loss": 0.5287, "lr": 8.848083917997463e-06, "epoch": 0.5974150311153662, "percentage": 29.89, "elapsed_time": "2:42:13", "remaining_time": "6:20:35"}
+{"current_steps": 105, "total_steps": 348, "loss": 0.5301, "lr": 8.815847079402972e-06, "epoch": 0.6031594064145525, "percentage": 30.17, "elapsed_time": "2:43:32", "remaining_time": "6:18:28"}
+{"current_steps": 106, "total_steps": 348, "loss": 0.5529, "lr": 8.783225827525098e-06, "epoch": 0.6089037817137386, "percentage": 30.46, "elapsed_time": "2:45:00", "remaining_time": "6:16:42"}
+{"current_steps": 107, "total_steps": 348, "loss": 0.5464, "lr": 8.750223448670204e-06, "epoch": 0.6146481570129249, "percentage": 30.75, "elapsed_time": "2:46:27", "remaining_time": "6:14:55"}
+{"current_steps": 108, "total_steps": 348, "loss": 0.5634, "lr": 8.716843267539868e-06, "epoch": 0.6203925323121111, "percentage": 31.03, "elapsed_time": "2:48:07", "remaining_time": "6:13:36"}
+{"current_steps": 109, "total_steps": 348, "loss": 0.5102, "lr": 8.683088646895955e-06, "epoch": 0.6261369076112973, "percentage": 31.32, "elapsed_time": "2:49:31", "remaining_time": "6:11:42"}
+{"current_steps": 110, "total_steps": 348, "loss": 0.5767, "lr": 8.648962987221837e-06, "epoch": 0.6318812829104835, "percentage": 31.61, "elapsed_time": "2:51:11", "remaining_time": "6:10:24"}
+{"current_steps": 111, "total_steps": 348, "loss": 0.5567, "lr": 8.614469726379833e-06, "epoch": 0.6376256582096697, "percentage": 31.9, "elapsed_time": "2:52:45", "remaining_time": "6:08:50"}
+{"current_steps": 112, "total_steps": 348, "loss": 0.566, "lr": 8.579612339264867e-06, "epoch": 0.6433700335088559, "percentage": 32.18, "elapsed_time": "2:54:12", "remaining_time": "6:07:04"}
+{"current_steps": 113, "total_steps": 348, "loss": 0.5308, "lr": 8.544394337454409e-06, "epoch": 0.6491144088080422, "percentage": 32.47, "elapsed_time": "2:55:31", "remaining_time": "6:05:01"}
+{"current_steps": 114, "total_steps": 348, "loss": 0.555, "lr": 8.508819268854713e-06, "epoch": 0.6548587841072283, "percentage": 32.76, "elapsed_time": "2:57:08", "remaining_time": "6:03:35"}
+{"current_steps": 115, "total_steps": 348, "loss": 0.5623, "lr": 8.472890717343391e-06, "epoch": 0.6606031594064146, "percentage": 33.05, "elapsed_time": "2:58:28", "remaining_time": "6:01:36"}
+{"current_steps": 116, "total_steps": 348, "loss": 0.526, "lr": 8.436612302408376e-06, "epoch": 0.6663475347056008, "percentage": 33.33, "elapsed_time": "2:59:53", "remaining_time": "5:59:47"}
+{"current_steps": 117, "total_steps": 348, "loss": 0.5446, "lr": 8.399987678783285e-06, "epoch": 0.672091910004787, "percentage": 33.62, "elapsed_time": "3:01:30", "remaining_time": "5:58:21"}
+{"current_steps": 118, "total_steps": 348, "loss": 0.5671, "lr": 8.36302053607924e-06, "epoch": 0.6778362853039732, "percentage": 33.91, "elapsed_time": "3:03:10", "remaining_time": "5:57:01"}
+{"current_steps": 119, "total_steps": 348, "loss": 0.5701, "lr": 8.325714598413169e-06, "epoch": 0.6835806606031594, "percentage": 34.2, "elapsed_time": "3:04:51", "remaining_time": "5:55:44"}
+{"current_steps": 120, "total_steps": 348, "loss": 0.5321, "lr": 8.288073624032634e-06, "epoch": 0.6893250359023456, "percentage": 34.48, "elapsed_time": "3:06:24", "remaining_time": "5:54:10"}
+{"current_steps": 121, "total_steps": 348, "loss": 0.5542, "lr": 8.250101404937223e-06, "epoch": 0.6950694112015319, "percentage": 34.77, "elapsed_time": "3:08:16", "remaining_time": "5:53:12"}
+{"current_steps": 122, "total_steps": 348, "loss": 0.5311, "lr": 8.211801766496537e-06, "epoch": 0.700813786500718, "percentage": 35.06, "elapsed_time": "3:09:37", "remaining_time": "5:51:15"}
+{"current_steps": 123, "total_steps": 348, "loss": 0.523, "lr": 8.17317856706482e-06, "epoch": 0.7065581617999043, "percentage": 35.34, "elapsed_time": "3:11:15", "remaining_time": "5:49:52"}
+{"current_steps": 124, "total_steps": 348, "loss": 0.5678, "lr": 8.13423569759226e-06, "epoch": 0.7123025370990905, "percentage": 35.63, "elapsed_time": "3:12:47", "remaining_time": "5:48:15"}
+{"current_steps": 125, "total_steps": 348, "loss": 0.5669, "lr": 8.094977081233006e-06, "epoch": 0.7180469123982767, "percentage": 35.92, "elapsed_time": "3:14:26", "remaining_time": "5:46:53"}
+{"current_steps": 126, "total_steps": 348, "loss": 0.5275, "lr": 8.055406672949957e-06, "epoch": 0.7237912876974629, "percentage": 36.21, "elapsed_time": "3:15:56", "remaining_time": "5:45:13"}
+{"current_steps": 127, "total_steps": 348, "loss": 0.5275, "lr": 8.015528459116321e-06, "epoch": 0.7295356629966491, "percentage": 36.49, "elapsed_time": "3:17:15", "remaining_time": "5:43:15"}
+{"current_steps": 128, "total_steps": 348, "loss": 0.5396, "lr": 7.975346457114034e-06, "epoch": 0.7352800382958353, "percentage": 36.78, "elapsed_time": "3:18:47", "remaining_time": "5:41:41"}
+{"current_steps": 129, "total_steps": 348, "loss": 0.5483, "lr": 7.934864714929036e-06, "epoch": 0.7410244135950216, "percentage": 37.07, "elapsed_time": "3:20:23", "remaining_time": "5:40:11"}
+{"current_steps": 130, "total_steps": 348, "loss": 0.5617, "lr": 7.894087310743468e-06, "epoch": 0.7467687888942077, "percentage": 37.36, "elapsed_time": "3:21:56", "remaining_time": "5:38:37"}
+{"current_steps": 131, "total_steps": 348, "loss": 0.5253, "lr": 7.853018352524845e-06, "epoch": 0.752513164193394, "percentage": 37.64, "elapsed_time": "3:23:17", "remaining_time": "5:36:44"}
+{"current_steps": 132, "total_steps": 348, "loss": 0.5303, "lr": 7.811661977612202e-06, "epoch": 0.7582575394925802, "percentage": 37.93, "elapsed_time": "3:24:50", "remaining_time": "5:35:12"}
+{"current_steps": 133, "total_steps": 348, "loss": 0.5235, "lr": 7.770022352299294e-06, "epoch": 0.7640019147917664, "percentage": 38.22, "elapsed_time": "3:26:12", "remaining_time": "5:33:21"}
+{"current_steps": 134, "total_steps": 348, "loss": 0.5148, "lr": 7.728103671414889e-06, "epoch": 0.7697462900909526, "percentage": 38.51, "elapsed_time": "3:27:39", "remaining_time": "5:31:38"}
+{"current_steps": 135, "total_steps": 348, "loss": 0.5345, "lr": 7.685910157900158e-06, "epoch": 0.7754906653901388, "percentage": 38.79, "elapsed_time": "3:29:03", "remaining_time": "5:29:50"}
+{"current_steps": 136, "total_steps": 348, "loss": 0.5451, "lr": 7.643446062383273e-06, "epoch": 0.781235040689325, "percentage": 39.08, "elapsed_time": "3:30:54", "remaining_time": "5:28:46"}
+{"current_steps": 137, "total_steps": 348, "loss": 0.5083, "lr": 7.600715662751166e-06, "epoch": 0.7869794159885113, "percentage": 39.37, "elapsed_time": "3:32:32", "remaining_time": "5:27:21"}
+{"current_steps": 138, "total_steps": 348, "loss": 0.5516, "lr": 7.557723263718596e-06, "epoch": 0.7927237912876974, "percentage": 39.66, "elapsed_time": "3:34:10", "remaining_time": "5:25:55"}
+{"current_steps": 139, "total_steps": 348, "loss": 0.5583, "lr": 7.514473196394467e-06, "epoch": 0.7984681665868837, "percentage": 39.94, "elapsed_time": "3:35:32", "remaining_time": "5:24:04"}
+{"current_steps": 140, "total_steps": 348, "loss": 0.5675, "lr": 7.470969817845518e-06, "epoch": 0.8042125418860699, "percentage": 40.23, "elapsed_time": "3:37:17", "remaining_time": "5:22:49"}
+{"current_steps": 141, "total_steps": 348, "loss": 0.5242, "lr": 7.427217510657383e-06, "epoch": 0.8099569171852561, "percentage": 40.52, "elapsed_time": "3:38:41", "remaining_time": "5:21:03"}
+{"current_steps": 142, "total_steps": 348, "loss": 0.56, "lr": 7.383220682493081e-06, "epoch": 0.8157012924844423, "percentage": 40.8, "elapsed_time": "3:40:12", "remaining_time": "5:19:28"}
+{"current_steps": 143, "total_steps": 348, "loss": 0.517, "lr": 7.338983765648985e-06, "epoch": 0.8214456677836285, "percentage": 41.09, "elapsed_time": "3:41:33", "remaining_time": "5:17:37"}
+{"current_steps": 144, "total_steps": 348, "loss": 0.5568, "lr": 7.294511216608308e-06, "epoch": 0.8271900430828147, "percentage": 41.38, "elapsed_time": "3:42:58", "remaining_time": "5:15:53"}
+{"current_steps": 145, "total_steps": 348, "loss": 0.5391, "lr": 7.249807515592149e-06, "epoch": 0.832934418382001, "percentage": 41.67, "elapsed_time": "3:44:50", "remaining_time": "5:14:47"}
+{"current_steps": 146, "total_steps": 348, "loss": 0.5393, "lr": 7.2048771661081515e-06, "epoch": 0.8386787936811871, "percentage": 41.95, "elapsed_time": "3:46:47", "remaining_time": "5:13:47"}
+{"current_steps": 147, "total_steps": 348, "loss": 0.5104, "lr": 7.159724694496815e-06, "epoch": 0.8444231689803734, "percentage": 42.24, "elapsed_time": "3:48:07", "remaining_time": "5:11:56"}
+{"current_steps": 148, "total_steps": 348, "loss": 0.5373, "lr": 7.114354649475499e-06, "epoch": 0.8501675442795597, "percentage": 42.53, "elapsed_time": "3:49:47", "remaining_time": "5:10:32"}
+{"current_steps": 149, "total_steps": 348, "loss": 0.516, "lr": 7.068771601680191e-06, "epoch": 0.8559119195787458, "percentage": 42.82, "elapsed_time": "3:51:07", "remaining_time": "5:08:40"}
+{"current_steps": 150, "total_steps": 348, "loss": 0.5421, "lr": 7.022980143205046e-06, "epoch": 0.861656294877932, "percentage": 43.1, "elapsed_time": "3:52:28", "remaining_time": "5:06:52"}
+{"current_steps": 151, "total_steps": 348, "loss": 0.5576, "lr": 6.976984887139775e-06, "epoch": 0.8674006701771182, "percentage": 43.39, "elapsed_time": "3:54:05", "remaining_time": "5:05:24"}
+{"current_steps": 152, "total_steps": 348, "loss": 0.4881, "lr": 6.930790467104916e-06, "epoch": 0.8731450454763044, "percentage": 43.68, "elapsed_time": "3:55:31", "remaining_time": "5:03:42"}
+{"current_steps": 153, "total_steps": 348, "loss": 0.5521, "lr": 6.884401536785045e-06, "epoch": 0.8788894207754907, "percentage": 43.97, "elapsed_time": "3:57:05", "remaining_time": "5:02:10"}
+{"current_steps": 154, "total_steps": 348, "loss": 0.5143, "lr": 6.837822769459942e-06, "epoch": 0.8846337960746768, "percentage": 44.25, "elapsed_time": "3:58:21", "remaining_time": "5:00:15"}
+{"current_steps": 155, "total_steps": 348, "loss": 0.5248, "lr": 6.791058857533814e-06, "epoch": 0.8903781713738631, "percentage": 44.54, "elapsed_time": "3:59:53", "remaining_time": "4:58:41"}
+{"current_steps": 156, "total_steps": 348, "loss": 0.543, "lr": 6.744114512062571e-06, "epoch": 0.8961225466730494, "percentage": 44.83, "elapsed_time": "4:01:20", "remaining_time": "4:57:02"}
+{"current_steps": 157, "total_steps": 348, "loss": 0.5272, "lr": 6.696994462279223e-06, "epoch": 0.9018669219722355, "percentage": 45.11, "elapsed_time": "4:02:45", "remaining_time": "4:55:19"}
+{"current_steps": 158, "total_steps": 348, "loss": 0.5572, "lr": 6.6497034551174585e-06, "epoch": 0.9076112972714218, "percentage": 45.4, "elapsed_time": "4:04:33", "remaining_time": "4:54:05"}
+{"current_steps": 159, "total_steps": 348, "loss": 0.5216, "lr": 6.602246254733431e-06, "epoch": 0.9133556725706079, "percentage": 45.69, "elapsed_time": "4:06:04", "remaining_time": "4:52:29"}
+{"current_steps": 160, "total_steps": 348, "loss": 0.5278, "lr": 6.554627642025807e-06, "epoch": 0.9191000478697942, "percentage": 45.98, "elapsed_time": "4:07:25", "remaining_time": "4:50:43"}
+{"current_steps": 161, "total_steps": 348, "loss": 0.5479, "lr": 6.506852414154138e-06, "epoch": 0.9248444231689804, "percentage": 46.26, "elapsed_time": "4:09:06", "remaining_time": "4:49:20"}
+{"current_steps": 162, "total_steps": 348, "loss": 0.4813, "lr": 6.4589253840555856e-06, "epoch": 0.9305887984681666, "percentage": 46.55, "elapsed_time": "4:10:33", "remaining_time": "4:47:40"}
+{"current_steps": 163, "total_steps": 348, "loss": 0.5391, "lr": 6.41085137996006e-06, "epoch": 0.9363331737673528, "percentage": 46.84, "elapsed_time": "4:12:10", "remaining_time": "4:46:12"}
+{"current_steps": 164, "total_steps": 348, "loss": 0.556, "lr": 6.362635244903818e-06, "epoch": 0.9420775490665391, "percentage": 47.13, "elapsed_time": "4:13:46", "remaining_time": "4:44:43"}
+{"current_steps": 165, "total_steps": 348, "loss": 0.552, "lr": 6.314281836241573e-06, "epoch": 0.9478219243657252, "percentage": 47.41, "elapsed_time": "4:15:15", "remaining_time": "4:43:05"}
+{"current_steps": 166, "total_steps": 348, "loss": 0.5028, "lr": 6.265796025157154e-06, "epoch": 0.9535662996649115, "percentage": 47.7, "elapsed_time": "4:16:52", "remaining_time": "4:41:37"}
+{"current_steps": 167, "total_steps": 348, "loss": 0.5229, "lr": 6.217182696172776e-06, "epoch": 0.9593106749640976, "percentage": 47.99, "elapsed_time": "4:18:23", "remaining_time": "4:40:03"}
+{"current_steps": 168, "total_steps": 348, "loss": 0.5166, "lr": 6.168446746656973e-06, "epoch": 0.9650550502632839, "percentage": 48.28, "elapsed_time": "4:20:03", "remaining_time": "4:38:38"}
+{"current_steps": 169, "total_steps": 348, "loss": 0.5342, "lr": 6.119593086331225e-06, "epoch": 0.9707994255624701, "percentage": 48.56, "elapsed_time": "4:21:29", "remaining_time": "4:36:57"}
+{"current_steps": 170, "total_steps": 348, "loss": 0.526, "lr": 6.070626636775349e-06, "epoch": 0.9765438008616563, "percentage": 48.85, "elapsed_time": "4:22:52", "remaining_time": "4:35:14"}
+{"current_steps": 171, "total_steps": 348, "loss": 0.5599, "lr": 6.021552330931693e-06, "epoch": 0.9822881761608425, "percentage": 49.14, "elapsed_time": "4:24:42", "remaining_time": "4:33:59"}
+{"current_steps": 172, "total_steps": 348, "loss": 0.5265, "lr": 5.972375112608182e-06, "epoch": 0.9880325514600288, "percentage": 49.43, "elapsed_time": "4:26:04", "remaining_time": "4:32:15"}
+{"current_steps": 173, "total_steps": 348, "loss": 0.5652, "lr": 5.923099935980278e-06, "epoch": 0.9937769267592149, "percentage": 49.71, "elapsed_time": "4:27:42", "remaining_time": "4:30:48"}
+{"current_steps": 174, "total_steps": 348, "loss": 0.5462, "lr": 5.8737317650918905e-06, "epoch": 0.9995213020584012, "percentage": 50.0, "elapsed_time": "4:29:20", "remaining_time": "4:29:20"}
+{"current_steps": 175, "total_steps": 348, "loss": 0.9082, "lr": 5.824275573355278e-06, "epoch": 1.0052656773575874, "percentage": 50.29, "elapsed_time": "4:30:44", "remaining_time": "4:27:39"}
+{"current_steps": 176, "total_steps": 348, "loss": 0.4953, "lr": 5.7747363430500395e-06, "epoch": 1.0110100526567736, "percentage": 50.57, "elapsed_time": "4:32:07", "remaining_time": "4:25:56"}
+{"current_steps": 177, "total_steps": 348, "loss": 0.5229, "lr": 5.725119064821185e-06, "epoch": 1.0167544279559597, "percentage": 50.86, "elapsed_time": "4:33:56", "remaining_time": "4:24:39"}
+{"current_steps": 178, "total_steps": 348, "loss": 0.461, "lr": 5.675428737176367e-06, "epoch": 1.022498803255146, "percentage": 51.15, "elapsed_time": "4:35:14", "remaining_time": "4:22:52"}
+{"current_steps": 179, "total_steps": 348, "loss": 0.4442, "lr": 5.625670365982332e-06, "epoch": 1.0282431785543322, "percentage": 51.44, "elapsed_time": "4:36:35", "remaining_time": "4:21:08"}
+{"current_steps": 180, "total_steps": 348, "loss": 0.5286, "lr": 5.575848963960621e-06, "epoch": 1.0339875538535184, "percentage": 51.72, "elapsed_time": "4:38:09", "remaining_time": "4:19:36"}
+{"current_steps": 181, "total_steps": 348, "loss": 0.4789, "lr": 5.525969550182577e-06, "epoch": 1.0397319291527047, "percentage": 52.01, "elapsed_time": "4:39:47", "remaining_time": "4:18:08"}
+{"current_steps": 182, "total_steps": 348, "loss": 0.4753, "lr": 5.4760371495637256e-06, "epoch": 1.0454763044518909, "percentage": 52.3, "elapsed_time": "4:41:08", "remaining_time": "4:16:25"}
+{"current_steps": 183, "total_steps": 348, "loss": 0.4895, "lr": 5.426056792357552e-06, "epoch": 1.051220679751077, "percentage": 52.59, "elapsed_time": "4:42:45", "remaining_time": "4:14:56"}
+{"current_steps": 184, "total_steps": 348, "loss": 0.4794, "lr": 5.376033513648743e-06, "epoch": 1.0569650550502634, "percentage": 52.87, "elapsed_time": "4:44:20", "remaining_time": "4:13:26"}
+{"current_steps": 185, "total_steps": 348, "loss": 0.4957, "lr": 5.325972352845965e-06, "epoch": 1.0627094303494495, "percentage": 53.16, "elapsed_time": "4:45:51", "remaining_time": "4:11:51"}
+{"current_steps": 186, "total_steps": 348, "loss": 0.5047, "lr": 5.2758783531741655e-06, "epoch": 1.0684538056486357, "percentage": 53.45, "elapsed_time": "4:47:31", "remaining_time": "4:10:25"}
+{"current_steps": 187, "total_steps": 348, "loss": 0.5066, "lr": 5.225756561166521e-06, "epoch": 1.0741981809478218, "percentage": 53.74, "elapsed_time": "4:49:18", "remaining_time": "4:09:05"}
+{"current_steps": 188, "total_steps": 348, "loss": 0.5012, "lr": 5.175612026156045e-06, "epoch": 1.0799425562470082, "percentage": 54.02, "elapsed_time": "4:50:56", "remaining_time": "4:07:36"}
+{"current_steps": 189, "total_steps": 348, "loss": 0.4638, "lr": 5.125449799766916e-06, "epoch": 1.0856869315461943, "percentage": 54.31, "elapsed_time": "4:52:23", "remaining_time": "4:05:59"}
+{"current_steps": 190, "total_steps": 348, "loss": 0.4915, "lr": 5.075274935405554e-06, "epoch": 1.0914313068453805, "percentage": 54.6, "elapsed_time": "4:53:51", "remaining_time": "4:04:22"}
+{"current_steps": 191, "total_steps": 348, "loss": 0.494, "lr": 5.025092487751552e-06, "epoch": 1.0971756821445668, "percentage": 54.89, "elapsed_time": "4:55:15", "remaining_time": "4:02:42"}
+{"current_steps": 192, "total_steps": 348, "loss": 0.4549, "lr": 4.974907512248451e-06, "epoch": 1.102920057443753, "percentage": 55.17, "elapsed_time": "4:56:36", "remaining_time": "4:00:59"}
+{"current_steps": 193, "total_steps": 348, "loss": 0.489, "lr": 4.924725064594448e-06, "epoch": 1.1086644327429391, "percentage": 55.46, "elapsed_time": "4:57:55", "remaining_time": "3:59:15"}
+{"current_steps": 194, "total_steps": 348, "loss": 0.4907, "lr": 4.874550200233085e-06, "epoch": 1.1144088080421255, "percentage": 55.75, "elapsed_time": "4:59:31", "remaining_time": "3:57:45"}
+{"current_steps": 195, "total_steps": 348, "loss": 0.5129, "lr": 4.824387973843957e-06, "epoch": 1.1201531833413116, "percentage": 56.03, "elapsed_time": "5:00:56", "remaining_time": "3:56:07"}
+{"current_steps": 196, "total_steps": 348, "loss": 0.4418, "lr": 4.7742434388334815e-06, "epoch": 1.1258975586404978, "percentage": 56.32, "elapsed_time": "5:02:13", "remaining_time": "3:54:22"}
+{"current_steps": 197, "total_steps": 348, "loss": 0.5022, "lr": 4.724121646825838e-06, "epoch": 1.1316419339396842, "percentage": 56.61, "elapsed_time": "5:03:47", "remaining_time": "3:52:51"}
+{"current_steps": 198, "total_steps": 348, "loss": 0.4711, "lr": 4.674027647154037e-06, "epoch": 1.1373863092388703, "percentage": 56.9, "elapsed_time": "5:05:28", "remaining_time": "3:51:24"}
+{"current_steps": 199, "total_steps": 348, "loss": 0.4465, "lr": 4.623966486351257e-06, "epoch": 1.1431306845380564, "percentage": 57.18, "elapsed_time": "5:06:43", "remaining_time": "3:49:39"}
+{"current_steps": 200, "total_steps": 348, "loss": 0.4659, "lr": 4.573943207642452e-06, "epoch": 1.1488750598372426, "percentage": 57.47, "elapsed_time": "5:07:54", "remaining_time": "3:47:51"}
+{"current_steps": 201, "total_steps": 348, "loss": 0.4974, "lr": 4.523962850436276e-06, "epoch": 1.154619435136429, "percentage": 57.76, "elapsed_time": "5:10:33", "remaining_time": "3:47:07"}
+{"current_steps": 202, "total_steps": 348, "loss": 0.5099, "lr": 4.474030449817423e-06, "epoch": 1.160363810435615, "percentage": 58.05, "elapsed_time": "5:11:49", "remaining_time": "3:45:22"}
+{"current_steps": 203, "total_steps": 348, "loss": 0.4687, "lr": 4.424151036039381e-06, "epoch": 1.1661081857348012, "percentage": 58.33, "elapsed_time": "5:13:20", "remaining_time": "3:43:48"}
+{"current_steps": 204, "total_steps": 348, "loss": 0.505, "lr": 4.3743296340176694e-06, "epoch": 1.1718525610339876, "percentage": 58.62, "elapsed_time": "5:14:52", "remaining_time": "3:42:15"}
+{"current_steps": 205, "total_steps": 348, "loss": 0.5201, "lr": 4.3245712628236356e-06, "epoch": 1.1775969363331737, "percentage": 58.91, "elapsed_time": "5:16:35", "remaining_time": "3:40:50"}
+{"current_steps": 206, "total_steps": 348, "loss": 0.4652, "lr": 4.274880935178817e-06, "epoch": 1.18334131163236, "percentage": 59.2, "elapsed_time": "5:18:01", "remaining_time": "3:39:13"}
+{"current_steps": 207, "total_steps": 348, "loss": 0.4692, "lr": 4.225263656949961e-06, "epoch": 1.1890856869315463, "percentage": 59.48, "elapsed_time": "5:19:32", "remaining_time": "3:37:39"}
+{"current_steps": 208, "total_steps": 348, "loss": 0.4842, "lr": 4.175724426644724e-06, "epoch": 1.1948300622307324, "percentage": 59.77, "elapsed_time": "5:21:00", "remaining_time": "3:36:03"}
+{"current_steps": 209, "total_steps": 348, "loss": 0.4535, "lr": 4.12626823490811e-06, "epoch": 1.2005744375299185, "percentage": 60.06, "elapsed_time": "5:22:31", "remaining_time": "3:34:30"}
+{"current_steps": 210, "total_steps": 348, "loss": 0.5134, "lr": 4.076900064019721e-06, "epoch": 1.206318812829105, "percentage": 60.34, "elapsed_time": "5:24:09", "remaining_time": "3:33:01"}
+{"current_steps": 211, "total_steps": 348, "loss": 0.4933, "lr": 4.02762488739182e-06, "epoch": 1.212063188128291, "percentage": 60.63, "elapsed_time": "5:25:43", "remaining_time": "3:31:29"}
+{"current_steps": 212, "total_steps": 348, "loss": 0.4924, "lr": 3.978447669068309e-06, "epoch": 1.2178075634274772, "percentage": 60.92, "elapsed_time": "5:27:04", "remaining_time": "3:29:49"}
+{"current_steps": 213, "total_steps": 348, "loss": 0.4602, "lr": 3.929373363224654e-06, "epoch": 1.2235519387266636, "percentage": 61.21, "elapsed_time": "5:28:28", "remaining_time": "3:28:11"}
+{"current_steps": 214, "total_steps": 348, "loss": 0.4469, "lr": 3.8804069136687775e-06, "epoch": 1.2292963140258497, "percentage": 61.49, "elapsed_time": "5:29:47", "remaining_time": "3:26:30"}
+{"current_steps": 215, "total_steps": 348, "loss": 0.4937, "lr": 3.8315532533430285e-06, "epoch": 1.2350406893250359, "percentage": 61.78, "elapsed_time": "5:31:35", "remaining_time": "3:25:07"}
+{"current_steps": 216, "total_steps": 348, "loss": 0.5012, "lr": 3.7828173038272266e-06, "epoch": 1.2407850646242222, "percentage": 62.07, "elapsed_time": "5:33:03", "remaining_time": "3:23:32"}
+{"current_steps": 217, "total_steps": 348, "loss": 0.448, "lr": 3.7342039748428473e-06, "epoch": 1.2465294399234084, "percentage": 62.36, "elapsed_time": "5:34:41", "remaining_time": "3:22:03"}
+{"current_steps": 218, "total_steps": 348, "loss": 0.4803, "lr": 3.685718163758427e-06, "epoch": 1.2522738152225945, "percentage": 62.64, "elapsed_time": "5:36:03", "remaining_time": "3:20:24"}
+{"current_steps": 219, "total_steps": 348, "loss": 0.4844, "lr": 3.6373647550961834e-06, "epoch": 1.2580181905217809, "percentage": 62.93, "elapsed_time": "5:37:31", "remaining_time": "3:18:48"}
+{"current_steps": 220, "total_steps": 348, "loss": 0.5254, "lr": 3.5891486200399413e-06, "epoch": 1.263762565820967, "percentage": 63.22, "elapsed_time": "5:39:16", "remaining_time": "3:17:24"}
+{"current_steps": 221, "total_steps": 348, "loss": 0.503, "lr": 3.5410746159444165e-06, "epoch": 1.2695069411201532, "percentage": 63.51, "elapsed_time": "5:40:47", "remaining_time": "3:15:50"}
+{"current_steps": 222, "total_steps": 348, "loss": 0.474, "lr": 3.4931475858458634e-06, "epoch": 1.2752513164193395, "percentage": 63.79, "elapsed_time": "5:42:12", "remaining_time": "3:14:13"}
+{"current_steps": 223, "total_steps": 348, "loss": 0.5197, "lr": 3.445372357974194e-06, "epoch": 1.2809956917185257, "percentage": 64.08, "elapsed_time": "5:43:55", "remaining_time": "3:12:46"}
+{"current_steps": 224, "total_steps": 348, "loss": 0.4698, "lr": 3.397753745266571e-06, "epoch": 1.2867400670177118, "percentage": 64.37, "elapsed_time": "5:45:16", "remaining_time": "3:11:07"}
+{"current_steps": 225, "total_steps": 348, "loss": 0.4573, "lr": 3.350296544882543e-06, "epoch": 1.292484442316898, "percentage": 64.66, "elapsed_time": "5:46:48", "remaining_time": "3:09:35"}
+{"current_steps": 226, "total_steps": 348, "loss": 0.4654, "lr": 3.303005537720778e-06, "epoch": 1.2982288176160843, "percentage": 64.94, "elapsed_time": "5:48:12", "remaining_time": "3:07:58"}
+{"current_steps": 227, "total_steps": 348, "loss": 0.5075, "lr": 3.255885487937431e-06, "epoch": 1.3039731929152705, "percentage": 65.23, "elapsed_time": "5:49:47", "remaining_time": "3:06:27"}
+{"current_steps": 228, "total_steps": 348, "loss": 0.5467, "lr": 3.2089411424661864e-06, "epoch": 1.3097175682144566, "percentage": 65.52, "elapsed_time": "5:51:20", "remaining_time": "3:04:55"}
+{"current_steps": 229, "total_steps": 348, "loss": 0.4965, "lr": 3.1621772305400603e-06, "epoch": 1.3154619435136428, "percentage": 65.8, "elapsed_time": "5:52:51", "remaining_time": "3:03:22"}
+{"current_steps": 230, "total_steps": 348, "loss": 0.4826, "lr": 3.1155984632149565e-06, "epoch": 1.3212063188128291, "percentage": 66.09, "elapsed_time": "5:54:23", "remaining_time": "3:01:48"}
+{"current_steps": 231, "total_steps": 348, "loss": 0.4355, "lr": 3.0692095328950843e-06, "epoch": 1.3269506941120153, "percentage": 66.38, "elapsed_time": "5:55:42", "remaining_time": "3:00:09"}
+{"current_steps": 232, "total_steps": 348, "loss": 0.5378, "lr": 3.023015112860228e-06, "epoch": 1.3326950694112014, "percentage": 66.67, "elapsed_time": "5:57:27", "remaining_time": "2:58:43"}
+{"current_steps": 233, "total_steps": 348, "loss": 0.4811, "lr": 2.977019856794955e-06, "epoch": 1.3384394447103878, "percentage": 66.95, "elapsed_time": "5:59:00", "remaining_time": "2:57:11"}
+{"current_steps": 234, "total_steps": 348, "loss": 0.4956, "lr": 2.93122839831981e-06, "epoch": 1.344183820009574, "percentage": 67.24, "elapsed_time": "6:00:49", "remaining_time": "2:55:47"}
+{"current_steps": 235, "total_steps": 348, "loss": 0.4729, "lr": 2.8856453505245018e-06, "epoch": 1.34992819530876, "percentage": 67.53, "elapsed_time": "6:02:30", "remaining_time": "2:54:18"}
+{"current_steps": 236, "total_steps": 348, "loss": 0.5352, "lr": 2.840275305503186e-06, "epoch": 1.3556725706079464, "percentage": 67.82, "elapsed_time": "6:04:12", "remaining_time": "2:52:50"}
+{"current_steps": 237, "total_steps": 348, "loss": 0.4523, "lr": 2.7951228338918506e-06, "epoch": 1.3614169459071326, "percentage": 68.1, "elapsed_time": "6:05:42", "remaining_time": "2:51:16"}
+{"current_steps": 238, "total_steps": 348, "loss": 0.4824, "lr": 2.7501924844078538e-06, "epoch": 1.3671613212063187, "percentage": 68.39, "elapsed_time": "6:07:20", "remaining_time": "2:49:46"}
+{"current_steps": 239, "total_steps": 348, "loss": 0.5059, "lr": 2.7054887833916933e-06, "epoch": 1.372905696505505, "percentage": 68.68, "elapsed_time": "6:08:52", "remaining_time": "2:48:14"}
+{"current_steps": 240, "total_steps": 348, "loss": 0.5039, "lr": 2.6610162343510183e-06, "epoch": 1.3786500718046912, "percentage": 68.97, "elapsed_time": "6:10:36", "remaining_time": "2:46:46"}
+{"current_steps": 241, "total_steps": 348, "loss": 0.4668, "lr": 2.616779317506921e-06, "epoch": 1.3843944471038774, "percentage": 69.25, "elapsed_time": "6:12:13", "remaining_time": "2:45:15"}
+{"current_steps": 242, "total_steps": 348, "loss": 0.4365, "lr": 2.572782489342617e-06, "epoch": 1.3901388224030637, "percentage": 69.54, "elapsed_time": "6:13:41", "remaining_time": "2:43:41"}
+{"current_steps": 243, "total_steps": 348, "loss": 0.5055, "lr": 2.5290301821544826e-06, "epoch": 1.39588319770225, "percentage": 69.83, "elapsed_time": "6:15:17", "remaining_time": "2:42:09"}
+{"current_steps": 244, "total_steps": 348, "loss": 0.5001, "lr": 2.4855268036055346e-06, "epoch": 1.401627573001436, "percentage": 70.11, "elapsed_time": "6:17:02", "remaining_time": "2:40:42"}
+{"current_steps": 245, "total_steps": 348, "loss": 0.5056, "lr": 2.4422767362814045e-06, "epoch": 1.4073719483006224, "percentage": 70.4, "elapsed_time": "6:18:42", "remaining_time": "2:39:12"}
+{"current_steps": 246, "total_steps": 348, "loss": 0.477, "lr": 2.3992843372488357e-06, "epoch": 1.4131163235998085, "percentage": 70.69, "elapsed_time": "6:19:59", "remaining_time": "2:37:33"}
+{"current_steps": 247, "total_steps": 348, "loss": 0.5074, "lr": 2.3565539376167295e-06, "epoch": 1.4188606988989947, "percentage": 70.98, "elapsed_time": "6:21:25", "remaining_time": "2:35:58"}
+{"current_steps": 248, "total_steps": 348, "loss": 0.4686, "lr": 2.3140898420998425e-06, "epoch": 1.424605074198181, "percentage": 71.26, "elapsed_time": "6:23:05", "remaining_time": "2:34:28"}
+{"current_steps": 249, "total_steps": 348, "loss": 0.4852, "lr": 2.271896328585114e-06, "epoch": 1.4303494494973672, "percentage": 71.55, "elapsed_time": "6:24:37", "remaining_time": "2:32:55"}
+{"current_steps": 250, "total_steps": 348, "loss": 0.4729, "lr": 2.2299776477007073e-06, "epoch": 1.4360938247965533, "percentage": 71.84, "elapsed_time": "6:26:11", "remaining_time": "2:31:23"}
+{"current_steps": 251, "total_steps": 348, "loss": 0.5039, "lr": 2.1883380223878004e-06, "epoch": 1.4418382000957397, "percentage": 72.13, "elapsed_time": "6:27:48", "remaining_time": "2:29:52"}
+{"current_steps": 252, "total_steps": 348, "loss": 0.5264, "lr": 2.1469816474751566e-06, "epoch": 1.4475825753949259, "percentage": 72.41, "elapsed_time": "6:29:22", "remaining_time": "2:28:20"}
+{"current_steps": 253, "total_steps": 348, "loss": 0.4575, "lr": 2.105912689256533e-06, "epoch": 1.453326950694112, "percentage": 72.7, "elapsed_time": "6:30:47", "remaining_time": "2:26:44"}
+{"current_steps": 254, "total_steps": 348, "loss": 0.4846, "lr": 2.0651352850709656e-06, "epoch": 1.4590713259932984, "percentage": 72.99, "elapsed_time": "6:32:13", "remaining_time": "2:25:09"}
+{"current_steps": 255, "total_steps": 348, "loss": 0.4968, "lr": 2.0246535428859652e-06, "epoch": 1.4648157012924845, "percentage": 73.28, "elapsed_time": "6:33:53", "remaining_time": "2:23:39"}
+{"current_steps": 256, "total_steps": 348, "loss": 0.4874, "lr": 1.984471540883679e-06, "epoch": 1.4705600765916707, "percentage": 73.56, "elapsed_time": "6:35:40", "remaining_time": "2:22:11"}
+{"current_steps": 257, "total_steps": 348, "loss": 0.5144, "lr": 1.9445933270500444e-06, "epoch": 1.4763044518908568, "percentage": 73.85, "elapsed_time": "6:37:28", "remaining_time": "2:20:44"}
+{"current_steps": 258, "total_steps": 348, "loss": 0.4621, "lr": 1.905022918766995e-06, "epoch": 1.4820488271900432, "percentage": 74.14, "elapsed_time": "6:39:02", "remaining_time": "2:19:12"}
+{"current_steps": 259, "total_steps": 348, "loss": 0.5212, "lr": 1.8657643024077431e-06, "epoch": 1.4877932024892293, "percentage": 74.43, "elapsed_time": "6:40:46", "remaining_time": "2:17:43"}
+{"current_steps": 260, "total_steps": 348, "loss": 0.4859, "lr": 1.8268214329351797e-06, "epoch": 1.4935375777884154, "percentage": 74.71, "elapsed_time": "6:42:19", "remaining_time": "2:16:10"}
+{"current_steps": 261, "total_steps": 348, "loss": 0.4308, "lr": 1.7881982335034625e-06, "epoch": 1.4992819530876016, "percentage": 75.0, "elapsed_time": "6:43:49", "remaining_time": "2:14:36"}
+{"current_steps": 262, "total_steps": 348, "loss": 0.4565, "lr": 1.7498985950627794e-06, "epoch": 1.505026328386788, "percentage": 75.29, "elapsed_time": "6:45:12", "remaining_time": "2:13:00"}
+{"current_steps": 263, "total_steps": 348, "loss": 0.4704, "lr": 1.7119263759673677e-06, "epoch": 1.510770703685974, "percentage": 75.57, "elapsed_time": "6:46:41", "remaining_time": "2:11:26"}
+{"current_steps": 264, "total_steps": 348, "loss": 0.5137, "lr": 1.6742854015868349e-06, "epoch": 1.5165150789851602, "percentage": 75.86, "elapsed_time": "6:48:23", "remaining_time": "2:09:56"}
+{"current_steps": 265, "total_steps": 348, "loss": 0.4582, "lr": 1.6369794639207626e-06, "epoch": 1.5222594542843466, "percentage": 76.15, "elapsed_time": "6:49:51", "remaining_time": "2:08:22"}
+{"current_steps": 266, "total_steps": 348, "loss": 0.471, "lr": 1.6000123212167158e-06, "epoch": 1.5280038295835328, "percentage": 76.44, "elapsed_time": "6:51:19", "remaining_time": "2:06:47"}
+{"current_steps": 267, "total_steps": 348, "loss": 0.479, "lr": 1.5633876975916261e-06, "epoch": 1.533748204882719, "percentage": 76.72, "elapsed_time": "6:52:56", "remaining_time": "2:05:16"}
+{"current_steps": 268, "total_steps": 348, "loss": 0.4918, "lr": 1.5271092826566108e-06, "epoch": 1.5394925801819053, "percentage": 77.01, "elapsed_time": "6:54:33", "remaining_time": "2:03:44"}
+{"current_steps": 269, "total_steps": 348, "loss": 0.4862, "lr": 1.4911807311452874e-06, "epoch": 1.5452369554810914, "percentage": 77.3, "elapsed_time": "6:56:10", "remaining_time": "2:02:13"}
+{"current_steps": 270, "total_steps": 348, "loss": 0.472, "lr": 1.4556056625455922e-06, "epoch": 1.5509813307802776, "percentage": 77.59, "elapsed_time": "6:57:42", "remaining_time": "2:00:40"}
+{"current_steps": 271, "total_steps": 348, "loss": 0.5468, "lr": 1.4203876607351347e-06, "epoch": 1.556725706079464, "percentage": 77.87, "elapsed_time": "6:59:26", "remaining_time": "1:59:10"}
+{"current_steps": 272, "total_steps": 348, "loss": 0.4695, "lr": 1.3855302736201686e-06, "epoch": 1.56247008137865, "percentage": 78.16, "elapsed_time": "7:01:10", "remaining_time": "1:57:40"}
+{"current_steps": 273, "total_steps": 348, "loss": 0.5009, "lr": 1.3510370127781635e-06, "epoch": 1.5682144566778362, "percentage": 78.45, "elapsed_time": "7:02:37", "remaining_time": "1:56:06"}
+{"current_steps": 274, "total_steps": 348, "loss": 0.509, "lr": 1.3169113531040462e-06, "epoch": 1.5739588319770226, "percentage": 78.74, "elapsed_time": "7:04:04", "remaining_time": "1:54:31"}
+{"current_steps": 275, "total_steps": 348, "loss": 0.4961, "lr": 1.2831567324601325e-06, "epoch": 1.5797032072762087, "percentage": 79.02, "elapsed_time": "7:05:58", "remaining_time": "1:53:04"}
+{"current_steps": 276, "total_steps": 348, "loss": 0.4923, "lr": 1.2497765513297976e-06, "epoch": 1.5854475825753949, "percentage": 79.31, "elapsed_time": "7:07:54", "remaining_time": "1:51:37"}
+{"current_steps": 277, "total_steps": 348, "loss": 0.4894, "lr": 1.2167741724749026e-06, "epoch": 1.5911919578745812, "percentage": 79.6, "elapsed_time": "7:09:50", "remaining_time": "1:50:10"}
+{"current_steps": 278, "total_steps": 348, "loss": 0.4224, "lr": 1.1841529205970281e-06, "epoch": 1.5969363331737674, "percentage": 79.89, "elapsed_time": "7:11:37", "remaining_time": "1:48:41"}
+{"current_steps": 279, "total_steps": 348, "loss": 0.4937, "lr": 1.1519160820025382e-06, "epoch": 1.6026807084729535, "percentage": 80.17, "elapsed_time": "7:13:14", "remaining_time": "1:47:08"}
+{"current_steps": 280, "total_steps": 348, "loss": 0.4921, "lr": 1.1200669042715163e-06, "epoch": 1.6084250837721399, "percentage": 80.46, "elapsed_time": "7:14:46", "remaining_time": "1:45:35"}
+{"current_steps": 281, "total_steps": 348, "loss": 0.5068, "lr": 1.0886085959305915e-06, "epoch": 1.614169459071326, "percentage": 80.75, "elapsed_time": "7:16:27", "remaining_time": "1:44:04"}
+{"current_steps": 282, "total_steps": 348, "loss": 0.4888, "lr": 1.057544326129723e-06, "epoch": 1.6199138343705122, "percentage": 81.03, "elapsed_time": "7:18:06", "remaining_time": "1:42:32"}
+{"current_steps": 283, "total_steps": 348, "loss": 0.5025, "lr": 1.026877224322923e-06, "epoch": 1.6256582096696985, "percentage": 81.32, "elapsed_time": "7:19:51", "remaining_time": "1:41:01"}
+{"current_steps": 284, "total_steps": 348, "loss": 0.5262, "lr": 9.966103799529891e-07, "epoch": 1.6314025849688847, "percentage": 81.61, "elapsed_time": "7:21:40", "remaining_time": "1:39:31"}
+{"current_steps": 285, "total_steps": 348, "loss": 0.4623, "lr": 9.66746842140287e-07, "epoch": 1.6371469602680708, "percentage": 81.9, "elapsed_time": "7:23:20", "remaining_time": "1:38:00"}
+{"current_steps": 286, "total_steps": 348, "loss": 0.4814, "lr": 9.372896193755621e-07, "epoch": 1.6428913355672572, "percentage": 82.18, "elapsed_time": "7:24:56", "remaining_time": "1:36:27"}
+{"current_steps": 287, "total_steps": 348, "loss": 0.5195, "lr": 9.082416792168608e-07, "epoch": 1.6486357108664431, "percentage": 82.47, "elapsed_time": "7:26:31", "remaining_time": "1:34:54"}
+{"current_steps": 288, "total_steps": 348, "loss": 0.4491, "lr": 8.7960594799059e-07, "epoch": 1.6543800861656295, "percentage": 82.76, "elapsed_time": "7:27:59", "remaining_time": "1:33:19"}
+{"current_steps": 289, "total_steps": 348, "loss": 0.5042, "lr": 8.513853104966951e-07, "epoch": 1.6601244614648158, "percentage": 83.05, "elapsed_time": "7:29:30", "remaining_time": "1:31:46"}
+{"current_steps": 290, "total_steps": 348, "loss": 0.4904, "lr": 8.235826097180566e-07, "epoch": 1.6658688367640018, "percentage": 83.33, "elapsed_time": "7:31:16", "remaining_time": "1:30:15"}
+{"current_steps": 291, "total_steps": 348, "loss": 0.4554, "lr": 7.962006465340821e-07, "epoch": 1.6716132120631881, "percentage": 83.62, "elapsed_time": "7:32:37", "remaining_time": "1:28:39"}
+{"current_steps": 292, "total_steps": 348, "loss": 0.473, "lr": 7.692421794385313e-07, "epoch": 1.6773575873623745, "percentage": 83.91, "elapsed_time": "7:34:02", "remaining_time": "1:27:04"}
+{"current_steps": 293, "total_steps": 348, "loss": 0.5168, "lr": 7.427099242616348e-07, "epoch": 1.6831019626615604, "percentage": 84.2, "elapsed_time": "7:35:43", "remaining_time": "1:25:32"}
+{"current_steps": 294, "total_steps": 348, "loss": 0.5405, "lr": 7.166065538964955e-07, "epoch": 1.6888463379607468, "percentage": 84.48, "elapsed_time": "7:37:18", "remaining_time": "1:23:59"}
+{"current_steps": 295, "total_steps": 348, "loss": 0.4794, "lr": 6.909346980298093e-07, "epoch": 1.694590713259933, "percentage": 84.77, "elapsed_time": "7:38:43", "remaining_time": "1:22:24"}
+{"current_steps": 296, "total_steps": 348, "loss": 0.4514, "lr": 6.656969428769567e-07, "epoch": 1.700335088559119, "percentage": 85.06, "elapsed_time": "7:40:25", "remaining_time": "1:20:53"}
+{"current_steps": 297, "total_steps": 348, "loss": 0.4801, "lr": 6.408958309214597e-07, "epoch": 1.7060794638583054, "percentage": 85.34, "elapsed_time": "7:42:08", "remaining_time": "1:19:21"}
+{"current_steps": 298, "total_steps": 348, "loss": 0.5115, "lr": 6.165338606588517e-07, "epoch": 1.7118238391574916, "percentage": 85.63, "elapsed_time": "7:43:54", "remaining_time": "1:17:50"}
+{"current_steps": 299, "total_steps": 348, "loss": 0.4826, "lr": 5.926134863449712e-07, "epoch": 1.7175682144566777, "percentage": 85.92, "elapsed_time": "7:45:32", "remaining_time": "1:16:17"}
+{"current_steps": 300, "total_steps": 348, "loss": 0.4491, "lr": 5.691371177487215e-07, "epoch": 1.723312589755864, "percentage": 86.21, "elapsed_time": "7:47:09", "remaining_time": "1:14:44"}
+{"current_steps": 301, "total_steps": 348, "loss": 0.5254, "lr": 5.461071199093048e-07, "epoch": 1.7290569650550502, "percentage": 86.49, "elapsed_time": "7:49:38", "remaining_time": "1:13:19"}
+{"current_steps": 302, "total_steps": 348, "loss": 0.4591, "lr": 5.235258128979676e-07, "epoch": 1.7348013403542364, "percentage": 86.78, "elapsed_time": "7:51:11", "remaining_time": "1:11:46"}
+{"current_steps": 303, "total_steps": 348, "loss": 0.4621, "lr": 5.0139547158427e-07, "epoch": 1.7405457156534228, "percentage": 87.07, "elapsed_time": "7:52:37", "remaining_time": "1:10:11"}
+{"current_steps": 304, "total_steps": 348, "loss": 0.499, "lr": 4.797183254069176e-07, "epoch": 1.746290090952609, "percentage": 87.36, "elapsed_time": "7:53:55", "remaining_time": "1:08:35"}
+{"current_steps": 305, "total_steps": 348, "loss": 0.5162, "lr": 4.5849655814915683e-07, "epoch": 1.752034466251795, "percentage": 87.64, "elapsed_time": "7:55:36", "remaining_time": "1:07:03"}
+{"current_steps": 306, "total_steps": 348, "loss": 0.4925, "lr": 4.3773230771879004e-07, "epoch": 1.7577788415509814, "percentage": 87.93, "elapsed_time": "7:57:04", "remaining_time": "1:05:28"}
+{"current_steps": 307, "total_steps": 348, "loss": 0.4587, "lr": 4.1742766593278974e-07, "epoch": 1.7635232168501676, "percentage": 88.22, "elapsed_time": "7:58:32", "remaining_time": "1:03:54"}
+{"current_steps": 308, "total_steps": 348, "loss": 0.5026, "lr": 3.9758467830656623e-07, "epoch": 1.7692675921493537, "percentage": 88.51, "elapsed_time": "8:00:20", "remaining_time": "1:02:22"}
+{"current_steps": 309, "total_steps": 348, "loss": 0.4692, "lr": 3.782053438479094e-07, "epoch": 1.77501196744854, "percentage": 88.79, "elapsed_time": "8:01:49", "remaining_time": "1:00:48"}
+{"current_steps": 310, "total_steps": 348, "loss": 0.4576, "lr": 3.5929161485559694e-07, "epoch": 1.7807563427477262, "percentage": 89.08, "elapsed_time": "8:03:31", "remaining_time": "0:59:16"}
+{"current_steps": 311, "total_steps": 348, "loss": 0.5168, "lr": 3.4084539672271764e-07, "epoch": 1.7865007180469124, "percentage": 89.37, "elapsed_time": "8:04:48", "remaining_time": "0:57:40"}
+{"current_steps": 312, "total_steps": 348, "loss": 0.4769, "lr": 3.228685477447291e-07, "epoch": 1.7922450933460987, "percentage": 89.66, "elapsed_time": "8:06:18", "remaining_time": "0:56:06"}
+{"current_steps": 313, "total_steps": 348, "loss": 0.4646, "lr": 3.0536287893223603e-07, "epoch": 1.7979894686452849, "percentage": 89.94, "elapsed_time": "8:07:22", "remaining_time": "0:54:29"}
+{"current_steps": 314, "total_steps": 348, "loss": 0.4506, "lr": 2.883301538285582e-07, "epoch": 1.803733843944471, "percentage": 90.23, "elapsed_time": "8:08:43", "remaining_time": "0:52:55"}
+{"current_steps": 315, "total_steps": 348, "loss": 0.4858, "lr": 2.717720883320685e-07, "epoch": 1.8094782192436574, "percentage": 90.52, "elapsed_time": "8:10:14", "remaining_time": "0:51:21"}
+{"current_steps": 316, "total_steps": 348, "loss": 0.5302, "lr": 2.556903505233216e-07, "epoch": 1.8152225945428435, "percentage": 90.8, "elapsed_time": "8:11:43", "remaining_time": "0:49:47"}
+{"current_steps": 317, "total_steps": 348, "loss": 0.4868, "lr": 2.4008656049701875e-07, "epoch": 1.8209669698420297, "percentage": 91.09, "elapsed_time": "8:13:23", "remaining_time": "0:48:14"}
+{"current_steps": 318, "total_steps": 348, "loss": 0.4698, "lr": 2.2496229019879635e-07, "epoch": 1.826711345141216, "percentage": 91.38, "elapsed_time": "8:14:46", "remaining_time": "0:46:40"}
+{"current_steps": 319, "total_steps": 348, "loss": 0.4716, "lr": 2.1031906326685946e-07, "epoch": 1.832455720440402, "percentage": 91.67, "elapsed_time": "8:16:17", "remaining_time": "0:45:07"}
+{"current_steps": 320, "total_steps": 348, "loss": 0.4804, "lr": 1.9615835487849677e-07, "epoch": 1.8382000957395883, "percentage": 91.95, "elapsed_time": "8:17:33", "remaining_time": "0:43:32"}
+{"current_steps": 321, "total_steps": 348, "loss": 0.5048, "lr": 1.824815916014644e-07, "epoch": 1.8439444710387747, "percentage": 92.24, "elapsed_time": "8:19:02", "remaining_time": "0:41:58"}
+{"current_steps": 322, "total_steps": 348, "loss": 0.4454, "lr": 1.6929015125027314e-07, "epoch": 1.8496888463379606, "percentage": 92.53, "elapsed_time": "8:20:30", "remaining_time": "0:40:24"}
+{"current_steps": 323, "total_steps": 348, "loss": 0.5037, "lr": 1.5658536274738623e-07, "epoch": 1.855433221637147, "percentage": 92.82, "elapsed_time": "8:22:08", "remaining_time": "0:38:51"}
+{"current_steps": 324, "total_steps": 348, "loss": 0.5074, "lr": 1.443685059893396e-07, "epoch": 1.8611775969363333, "percentage": 93.1, "elapsed_time": "8:23:47", "remaining_time": "0:37:19"}
+{"current_steps": 325, "total_steps": 348, "loss": 0.4878, "lr": 1.3264081171780797e-07, "epoch": 1.8669219722355193, "percentage": 93.39, "elapsed_time": "8:25:06", "remaining_time": "0:35:44"}
+{"current_steps": 326, "total_steps": 348, "loss": 0.4694, "lr": 1.2140346139561277e-07, "epoch": 1.8726663475347056, "percentage": 93.68, "elapsed_time": "8:26:46", "remaining_time": "0:34:11"}
+{"current_steps": 327, "total_steps": 348, "loss": 0.4856, "lr": 1.1065758708770468e-07, "epoch": 1.8784107228338918, "percentage": 93.97, "elapsed_time": "8:28:11", "remaining_time": "0:32:38"}
+{"current_steps": 328, "total_steps": 348, "loss": 0.5022, "lr": 1.004042713471165e-07, "epoch": 1.884155098133078, "percentage": 94.25, "elapsed_time": "8:29:52", "remaining_time": "0:31:05"}
+{"current_steps": 329, "total_steps": 348, "loss": 0.4619, "lr": 9.064454710590253e-08, "epoch": 1.8898994734322643, "percentage": 94.54, "elapsed_time": "8:31:24", "remaining_time": "0:29:32"}
+{"current_steps": 330, "total_steps": 348, "loss": 0.4584, "lr": 8.137939757108526e-08, "epoch": 1.8956438487314504, "percentage": 94.83, "elapsed_time": "8:32:55", "remaining_time": "0:27:58"}
+{"current_steps": 331, "total_steps": 348, "loss": 0.4813, "lr": 7.260975612560173e-08, "epoch": 1.9013882240306366, "percentage": 95.11, "elapsed_time": "8:34:26", "remaining_time": "0:26:25"}
+{"current_steps": 332, "total_steps": 348, "loss": 0.4304, "lr": 6.433650623427379e-08, "epoch": 1.907132599329823, "percentage": 95.4, "elapsed_time": "8:35:43", "remaining_time": "0:24:51"}
+{"current_steps": 333, "total_steps": 348, "loss": 0.4624, "lr": 5.6560481354807625e-08, "epoch": 1.912876974629009, "percentage": 95.69, "elapsed_time": "8:37:03", "remaining_time": "0:23:17"}
+{"current_steps": 334, "total_steps": 348, "loss": 0.5049, "lr": 4.928246485383148e-08, "epoch": 1.9186213499281952, "percentage": 95.98, "elapsed_time": "8:38:45", "remaining_time": "0:21:44"}
+{"current_steps": 335, "total_steps": 348, "loss": 0.5062, "lr": 4.250318992797375e-08, "epoch": 1.9243657252273816, "percentage": 96.26, "elapsed_time": "8:40:16", "remaining_time": "0:20:11"}
+{"current_steps": 336, "total_steps": 348, "loss": 0.4485, "lr": 3.622333953000601e-08, "epoch": 1.9301101005265677, "percentage": 96.55, "elapsed_time": "8:41:30", "remaining_time": "0:18:37"}
+{"current_steps": 337, "total_steps": 348, "loss": 0.4358, "lr": 3.0443546300035764e-08, "epoch": 1.9358544758257539, "percentage": 96.84, "elapsed_time": "8:42:56", "remaining_time": "0:17:04"}
+{"current_steps": 338, "total_steps": 348, "loss": 0.46, "lr": 2.516439250177749e-08, "epoch": 1.9415988511249402, "percentage": 97.13, "elapsed_time": "8:44:31", "remaining_time": "0:15:31"}
+{"current_steps": 339, "total_steps": 348, "loss": 0.5263, "lr": 2.038640996389285e-08, "epoch": 1.9473432264241264, "percentage": 97.41, "elapsed_time": "8:46:09", "remaining_time": "0:13:58"}
+{"current_steps": 340, "total_steps": 348, "loss": 0.4882, "lr": 1.6110080026414123e-08, "epoch": 1.9530876017233125, "percentage": 97.7, "elapsed_time": "8:47:34", "remaining_time": "0:12:24"}
+{"current_steps": 341, "total_steps": 348, "loss": 0.4988, "lr": 1.2335833492252425e-08, "epoch": 1.958831977022499, "percentage": 97.99, "elapsed_time": "8:49:09", "remaining_time": "0:10:51"}
+{"current_steps": 342, "total_steps": 348, "loss": 0.5049, "lr": 9.06405058380022e-09, "epoch": 1.964576352321685, "percentage": 98.28, "elapsed_time": "8:51:06", "remaining_time": "0:09:19"}
+{"current_steps": 343, "total_steps": 348, "loss": 0.4578, "lr": 6.295060904623618e-09, "epoch": 1.9703207276208712, "percentage": 98.56, "elapsed_time": "8:52:18", "remaining_time": "0:07:45"}
+{"current_steps": 344, "total_steps": 348, "loss": 0.4775, "lr": 4.02914340626226e-09, "epoch": 1.9760651029200575, "percentage": 98.85, "elapsed_time": "8:53:45", "remaining_time": "0:06:12"}
+{"current_steps": 345, "total_steps": 348, "loss": 0.491, "lr": 2.2665263601240328e-09, "epoch": 1.9818094782192437, "percentage": 99.14, "elapsed_time": "8:55:24", "remaining_time": "0:04:39"}
+{"current_steps": 346, "total_steps": 348, "loss": 0.5071, "lr": 1.0073873344895735e-09, "epoch": 1.9875538535184298, "percentage": 99.43, "elapsed_time": "8:57:07", "remaining_time": "0:03:06"}
+{"current_steps": 347, "total_steps": 348, "loss": 0.5096, "lr": 2.5185317662490547e-10, "epoch": 1.9932982288176162, "percentage": 99.71, "elapsed_time": "8:58:31", "remaining_time": "0:01:33"}
+{"current_steps": 348, "total_steps": 348, "loss": 0.436, "lr": 0.0, "epoch": 1.9990426041168023, "percentage": 100.0, "elapsed_time": "8:59:57", "remaining_time": "0:00:00"}
+{"current_steps": 348, "total_steps": 348, "epoch": 1.9990426041168023, "percentage": 100.0, "elapsed_time": "9:01:04", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2478 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9990426041168023,
+  "eval_steps": 500,
+  "global_step": 348,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0057443752991862135,
+      "grad_norm": 5.363491058349609,
+      "learning_rate": 2.8571428571428575e-07,
+      "loss": 0.8587,
+      "step": 1
+    },
+    {
+      "epoch": 0.011488750598372427,
+      "grad_norm": 5.751570701599121,
+      "learning_rate": 5.714285714285715e-07,
+      "loss": 0.8936,
+      "step": 2
+    },
+    {
+      "epoch": 0.01723312589755864,
+      "grad_norm": 5.681423187255859,
+      "learning_rate": 8.571428571428572e-07,
+      "loss": 0.9174,
+      "step": 3
+    },
+    {
+      "epoch": 0.022977501196744854,
+      "grad_norm": 5.466259956359863,
+      "learning_rate": 1.142857142857143e-06,
+      "loss": 0.8825,
+      "step": 4
+    },
+    {
+      "epoch": 0.028721876495931067,
+      "grad_norm": 5.4661688804626465,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.8794,
+      "step": 5
+    },
+    {
+      "epoch": 0.03446625179511728,
+      "grad_norm": 5.406000137329102,
+      "learning_rate": 1.7142857142857145e-06,
+      "loss": 0.8566,
+      "step": 6
+    },
+    {
+      "epoch": 0.040210627094303494,
+      "grad_norm": 4.255201816558838,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.8527,
+      "step": 7
+    },
+    {
+      "epoch": 0.04595500239348971,
+      "grad_norm": 3.8569490909576416,
+      "learning_rate": 2.285714285714286e-06,
+      "loss": 0.8273,
+      "step": 8
+    },
+    {
+      "epoch": 0.05169937769267592,
+      "grad_norm": 2.5158278942108154,
+      "learning_rate": 2.571428571428571e-06,
+      "loss": 0.7763,
+      "step": 9
+    },
+    {
+      "epoch": 0.057443752991862135,
+      "grad_norm": 2.4135913848876953,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.832,
+      "step": 10
+    },
+    {
+      "epoch": 0.06318812829104835,
+      "grad_norm": 2.236311674118042,
+      "learning_rate": 3.142857142857143e-06,
+      "loss": 0.8195,
+      "step": 11
+    },
+    {
+      "epoch": 0.06893250359023456,
+      "grad_norm": 2.0858547687530518,
+      "learning_rate": 3.428571428571429e-06,
+      "loss": 0.7293,
+      "step": 12
+    },
+    {
+      "epoch": 0.07467687888942078,
+      "grad_norm": 3.858452320098877,
+      "learning_rate": 3.7142857142857146e-06,
+      "loss": 0.7993,
+      "step": 13
+    },
+    {
+      "epoch": 0.08042125418860699,
+      "grad_norm": 3.8865373134613037,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.7821,
+      "step": 14
+    },
+    {
+      "epoch": 0.0861656294877932,
+      "grad_norm": 3.8490350246429443,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.7953,
+      "step": 15
+    },
+    {
+      "epoch": 0.09191000478697942,
+      "grad_norm": 3.2923967838287354,
+      "learning_rate": 4.571428571428572e-06,
+      "loss": 0.7904,
+      "step": 16
+    },
+    {
+      "epoch": 0.09765438008616563,
+      "grad_norm": 2.2245757579803467,
+      "learning_rate": 4.857142857142858e-06,
+      "loss": 0.7397,
+      "step": 17
+    },
+    {
+      "epoch": 0.10339875538535184,
+      "grad_norm": 1.9646612405776978,
+      "learning_rate": 5.142857142857142e-06,
+      "loss": 0.7405,
+      "step": 18
+    },
+    {
+      "epoch": 0.10914313068453806,
+      "grad_norm": 1.5325367450714111,
+      "learning_rate": 5.428571428571429e-06,
+      "loss": 0.6697,
+      "step": 19
+    },
+    {
+      "epoch": 0.11488750598372427,
+      "grad_norm": 1.4567933082580566,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.6977,
+      "step": 20
+    },
+    {
+      "epoch": 0.12063188128291048,
+      "grad_norm": 1.4041451215744019,
+      "learning_rate": 6e-06,
+      "loss": 0.6796,
+      "step": 21
+    },
+    {
+      "epoch": 0.1263762565820967,
+      "grad_norm": 1.1699495315551758,
+      "learning_rate": 6.285714285714286e-06,
+      "loss": 0.674,
+      "step": 22
+    },
+    {
+      "epoch": 0.13212063188128292,
+      "grad_norm": 1.0591332912445068,
+      "learning_rate": 6.571428571428572e-06,
+      "loss": 0.6336,
+      "step": 23
+    },
+    {
+      "epoch": 0.13786500718046912,
+      "grad_norm": 1.2895734310150146,
+      "learning_rate": 6.857142857142858e-06,
+      "loss": 0.6701,
+      "step": 24
+    },
+    {
+      "epoch": 0.14360938247965535,
+      "grad_norm": 1.0462803840637207,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.6557,
+      "step": 25
+    },
+    {
+      "epoch": 0.14935375777884155,
+      "grad_norm": 1.1943080425262451,
+      "learning_rate": 7.428571428571429e-06,
+      "loss": 0.6453,
+      "step": 26
+    },
+    {
+      "epoch": 0.15509813307802778,
+      "grad_norm": 1.0741592645645142,
+      "learning_rate": 7.714285714285716e-06,
+      "loss": 0.6813,
+      "step": 27
+    },
+    {
+      "epoch": 0.16084250837721398,
+      "grad_norm": 0.9222673773765564,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.6415,
+      "step": 28
+    },
+    {
+      "epoch": 0.1665868836764002,
+      "grad_norm": 0.8281923532485962,
+      "learning_rate": 8.285714285714287e-06,
+      "loss": 0.6287,
+      "step": 29
+    },
+    {
+      "epoch": 0.1723312589755864,
+      "grad_norm": 1.0101515054702759,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.6347,
+      "step": 30
+    },
+    {
+      "epoch": 0.17807563427477263,
+      "grad_norm": 0.9029678702354431,
+      "learning_rate": 8.857142857142858e-06,
+      "loss": 0.5939,
+      "step": 31
+    },
+    {
+      "epoch": 0.18382000957395883,
+      "grad_norm": 0.6645869016647339,
+      "learning_rate": 9.142857142857144e-06,
+      "loss": 0.5704,
+      "step": 32
+    },
+    {
+      "epoch": 0.18956438487314506,
+      "grad_norm": 0.7702145576477051,
+      "learning_rate": 9.42857142857143e-06,
+      "loss": 0.6125,
+      "step": 33
+    },
+    {
+      "epoch": 0.19530876017233126,
+      "grad_norm": 0.8352411985397339,
+      "learning_rate": 9.714285714285715e-06,
+      "loss": 0.6332,
+      "step": 34
+    },
+    {
+      "epoch": 0.20105313547151749,
+      "grad_norm": 0.6543819308280945,
+      "learning_rate": 1e-05,
+      "loss": 0.6196,
+      "step": 35
+    },
+    {
+      "epoch": 0.20679751077070369,
+      "grad_norm": 0.6806799173355103,
+      "learning_rate": 9.999748146823376e-06,
+      "loss": 0.6135,
+      "step": 36
+    },
+    {
+      "epoch": 0.2125418860698899,
+      "grad_norm": 0.7468794584274292,
+      "learning_rate": 9.99899261266551e-06,
+      "loss": 0.5972,
+      "step": 37
+    },
+    {
+      "epoch": 0.2182862613690761,
+      "grad_norm": 0.6796684861183167,
+      "learning_rate": 9.997733473639876e-06,
+      "loss": 0.6111,
+      "step": 38
+    },
+    {
+      "epoch": 0.22403063666826234,
+      "grad_norm": 0.6619651913642883,
+      "learning_rate": 9.995970856593739e-06,
+      "loss": 0.6117,
+      "step": 39
+    },
+    {
+      "epoch": 0.22977501196744854,
+      "grad_norm": 0.6917636394500732,
+      "learning_rate": 9.993704939095376e-06,
+      "loss": 0.5887,
+      "step": 40
+    },
+    {
+      "epoch": 0.23551938726663477,
+      "grad_norm": 0.6591335535049438,
+      "learning_rate": 9.9909359494162e-06,
+      "loss": 0.631,
+      "step": 41
+    },
+    {
+      "epoch": 0.24126376256582097,
+      "grad_norm": 0.7333484888076782,
+      "learning_rate": 9.987664166507749e-06,
+      "loss": 0.5682,
+      "step": 42
+    },
+    {
+      "epoch": 0.2470081378650072,
+      "grad_norm": 0.7811906933784485,
+      "learning_rate": 9.983889919973586e-06,
+      "loss": 0.6056,
+      "step": 43
+    },
+    {
+      "epoch": 0.2527525131641934,
+      "grad_norm": 0.691569447517395,
+      "learning_rate": 9.979613590036108e-06,
+      "loss": 0.6209,
+      "step": 44
+    },
+    {
+      "epoch": 0.2584968884633796,
+      "grad_norm": 0.684109091758728,
+      "learning_rate": 9.974835607498224e-06,
+      "loss": 0.605,
+      "step": 45
+    },
+    {
+      "epoch": 0.26424126376256585,
+      "grad_norm": 0.7513927817344666,
+      "learning_rate": 9.969556453699966e-06,
+      "loss": 0.556,
+      "step": 46
+    },
+    {
+      "epoch": 0.26998563906175205,
+      "grad_norm": 0.7860096096992493,
+      "learning_rate": 9.963776660469996e-06,
+      "loss": 0.5852,
+      "step": 47
+    },
+    {
+      "epoch": 0.27573001436093825,
+      "grad_norm": 0.555550754070282,
+      "learning_rate": 9.957496810072027e-06,
+      "loss": 0.5736,
+      "step": 48
+    },
+    {
+      "epoch": 0.28147438966012445,
+      "grad_norm": 0.8144235014915466,
+      "learning_rate": 9.95071753514617e-06,
+      "loss": 0.6078,
+      "step": 49
+    },
+    {
+      "epoch": 0.2872187649593107,
+      "grad_norm": 0.6273301839828491,
+      "learning_rate": 9.943439518645193e-06,
+      "loss": 0.5638,
+      "step": 50
+    },
+    {
+      "epoch": 0.2929631402584969,
+      "grad_norm": 0.5855135321617126,
+      "learning_rate": 9.935663493765726e-06,
+      "loss": 0.5501,
+      "step": 51
+    },
+    {
+      "epoch": 0.2987075155576831,
+      "grad_norm": 0.7060447931289673,
+      "learning_rate": 9.9273902438744e-06,
+      "loss": 0.596,
+      "step": 52
+    },
+    {
+      "epoch": 0.3044518908568693,
+      "grad_norm": 0.6160895228385925,
+      "learning_rate": 9.918620602428916e-06,
+      "loss": 0.568,
+      "step": 53
+    },
+    {
+      "epoch": 0.31019626615605556,
+      "grad_norm": 0.6151447296142578,
+      "learning_rate": 9.909355452894098e-06,
+      "loss": 0.5581,
+      "step": 54
+    },
+    {
+      "epoch": 0.31594064145524176,
+      "grad_norm": 0.5906559824943542,
+      "learning_rate": 9.899595728652883e-06,
+      "loss": 0.5628,
+      "step": 55
+    },
+    {
+      "epoch": 0.32168501675442795,
+      "grad_norm": 0.6064203977584839,
+      "learning_rate": 9.889342412912296e-06,
+      "loss": 0.5708,
+      "step": 56
+    },
+    {
+      "epoch": 0.32742939205361415,
+      "grad_norm": 0.645464301109314,
+      "learning_rate": 9.878596538604388e-06,
+      "loss": 0.5792,
+      "step": 57
+    },
+    {
+      "epoch": 0.3331737673528004,
+      "grad_norm": 0.6362553238868713,
+      "learning_rate": 9.867359188282193e-06,
+      "loss": 0.5733,
+      "step": 58
+    },
+    {
+      "epoch": 0.3389181426519866,
+      "grad_norm": 0.680167019367218,
+      "learning_rate": 9.855631494010661e-06,
+      "loss": 0.5473,
+      "step": 59
+    },
+    {
+      "epoch": 0.3446625179511728,
+      "grad_norm": 0.6046214699745178,
+      "learning_rate": 9.843414637252615e-06,
+      "loss": 0.5568,
+      "step": 60
+    },
+    {
+      "epoch": 0.350406893250359,
+      "grad_norm": 0.6066192388534546,
+      "learning_rate": 9.830709848749727e-06,
+      "loss": 0.5732,
+      "step": 61
+    },
+    {
+      "epoch": 0.35615126854954526,
+      "grad_norm": 0.5794113278388977,
+      "learning_rate": 9.817518408398536e-06,
+      "loss": 0.5825,
+      "step": 62
+    },
+    {
+      "epoch": 0.36189564384873146,
+      "grad_norm": 0.5537358522415161,
+      "learning_rate": 9.803841645121505e-06,
+      "loss": 0.5664,
+      "step": 63
+    },
+    {
+      "epoch": 0.36764001914791766,
+      "grad_norm": 0.6195133328437805,
+      "learning_rate": 9.78968093673314e-06,
+      "loss": 0.55,
+      "step": 64
+    },
+    {
+      "epoch": 0.37338439444710386,
+      "grad_norm": 0.5777291655540466,
+      "learning_rate": 9.775037709801206e-06,
+      "loss": 0.572,
+      "step": 65
+    },
+    {
+      "epoch": 0.3791287697462901,
+      "grad_norm": 0.6024558544158936,
+      "learning_rate": 9.759913439502982e-06,
+      "loss": 0.5657,
+      "step": 66
+    },
+    {
+      "epoch": 0.3848731450454763,
+      "grad_norm": 0.5568858981132507,
+      "learning_rate": 9.74430964947668e-06,
+      "loss": 0.5261,
+      "step": 67
+    },
+    {
+      "epoch": 0.3906175203446625,
+      "grad_norm": 0.5718939304351807,
+      "learning_rate": 9.728227911667934e-06,
+      "loss": 0.5494,
+      "step": 68
+    },
+    {
+      "epoch": 0.3963618956438487,
+      "grad_norm": 0.5540202856063843,
+      "learning_rate": 9.711669846171443e-06,
+      "loss": 0.5771,
+      "step": 69
+    },
+    {
+      "epoch": 0.40210627094303497,
+      "grad_norm": 0.5410825610160828,
+      "learning_rate": 9.694637121067764e-06,
+      "loss": 0.501,
+      "step": 70
+    },
+    {
+      "epoch": 0.40785064624222117,
+      "grad_norm": 0.6998445987701416,
+      "learning_rate": 9.677131452255272e-06,
+      "loss": 0.555,
+      "step": 71
+    },
+    {
+      "epoch": 0.41359502154140737,
+      "grad_norm": 0.5608072876930237,
+      "learning_rate": 9.659154603277283e-06,
+      "loss": 0.5344,
+      "step": 72
+    },
+    {
+      "epoch": 0.41933939684059357,
+      "grad_norm": 0.5644481182098389,
+      "learning_rate": 9.640708385144403e-06,
+      "loss": 0.5547,
+      "step": 73
+    },
+    {
+      "epoch": 0.4250837721397798,
+      "grad_norm": 0.643834114074707,
+      "learning_rate": 9.62179465615209e-06,
+      "loss": 0.5578,
+      "step": 74
+    },
+    {
+      "epoch": 0.430828147438966,
+      "grad_norm": 0.6082519888877869,
+      "learning_rate": 9.602415321693434e-06,
+      "loss": 0.5687,
+      "step": 75
+    },
+    {
+      "epoch": 0.4365725227381522,
+      "grad_norm": 0.4994487762451172,
+      "learning_rate": 9.582572334067213e-06,
+      "loss": 0.5447,
+      "step": 76
+    },
+    {
+      "epoch": 0.4423168980373384,
+      "grad_norm": 0.52949458360672,
+      "learning_rate": 9.562267692281212e-06,
+      "loss": 0.5713,
+      "step": 77
+    },
+    {
+      "epoch": 0.4480612733365247,
+      "grad_norm": 0.5970189571380615,
+      "learning_rate": 9.541503441850844e-06,
+      "loss": 0.5486,
+      "step": 78
+    },
+    {
+      "epoch": 0.4538056486357109,
+      "grad_norm": 0.5419505834579468,
+      "learning_rate": 9.520281674593084e-06,
+      "loss": 0.5577,
+      "step": 79
+    },
+    {
+      "epoch": 0.4595500239348971,
+      "grad_norm": 0.5340558886528015,
+      "learning_rate": 9.498604528415731e-06,
+      "loss": 0.5397,
+      "step": 80
+    },
+    {
+      "epoch": 0.4652943992340833,
+      "grad_norm": 0.5403291583061218,
+      "learning_rate": 9.476474187102033e-06,
+      "loss": 0.5438,
+      "step": 81
+    },
+    {
+      "epoch": 0.47103877453326953,
+      "grad_norm": 0.6180256605148315,
+      "learning_rate": 9.453892880090696e-06,
+      "loss": 0.5624,
+      "step": 82
+    },
+    {
+      "epoch": 0.47678314983245573,
+      "grad_norm": 0.5336986780166626,
+      "learning_rate": 9.430862882251279e-06,
+      "loss": 0.5473,
+      "step": 83
+    },
+    {
+      "epoch": 0.48252752513164193,
+      "grad_norm": 0.6668586134910583,
+      "learning_rate": 9.40738651365503e-06,
+      "loss": 0.5757,
+      "step": 84
+    },
+    {
+      "epoch": 0.48827190043082813,
+      "grad_norm": 0.6107608675956726,
+      "learning_rate": 9.38346613934115e-06,
+      "loss": 0.5335,
+      "step": 85
+    },
+    {
+      "epoch": 0.4940162757300144,
+      "grad_norm": 0.5242419838905334,
+      "learning_rate": 9.359104169078541e-06,
+      "loss": 0.5509,
+      "step": 86
+    },
+    {
+      "epoch": 0.4997606510292006,
+      "grad_norm": 0.6356630921363831,
+      "learning_rate": 9.334303057123044e-06,
+      "loss": 0.5676,
+      "step": 87
+    },
+    {
+      "epoch": 0.5055050263283868,
+      "grad_norm": 0.533847987651825,
+      "learning_rate": 9.309065301970193e-06,
+      "loss": 0.5515,
+      "step": 88
+    },
+    {
+      "epoch": 0.511249401627573,
+      "grad_norm": 0.5083225965499878,
+      "learning_rate": 9.283393446103506e-06,
+      "loss": 0.5474,
+      "step": 89
+    },
+    {
+      "epoch": 0.5169937769267592,
+      "grad_norm": 0.5779216885566711,
+      "learning_rate": 9.257290075738365e-06,
+      "loss": 0.5574,
+      "step": 90
+    },
+    {
+      "epoch": 0.5227381522259454,
+      "grad_norm": 0.6124880313873291,
+      "learning_rate": 9.23075782056147e-06,
+      "loss": 0.535,
+      "step": 91
+    },
+    {
+      "epoch": 0.5284825275251317,
+      "grad_norm": 0.598517119884491,
+      "learning_rate": 9.20379935346592e-06,
+      "loss": 0.5409,
+      "step": 92
+    },
+    {
+      "epoch": 0.5342269028243178,
+      "grad_norm": 0.492055207490921,
+      "learning_rate": 9.176417390281944e-06,
+      "loss": 0.5293,
+      "step": 93
+    },
+    {
+      "epoch": 0.5399712781235041,
+      "grad_norm": 0.4873235523700714,
+      "learning_rate": 9.148614689503307e-06,
+      "loss": 0.5585,
+      "step": 94
+    },
+    {
+      "epoch": 0.5457156534226902,
+      "grad_norm": 0.5771122574806213,
+      "learning_rate": 9.120394052009412e-06,
+      "loss": 0.5464,
+      "step": 95
+    },
+    {
+      "epoch": 0.5514600287218765,
+      "grad_norm": 0.5583028793334961,
+      "learning_rate": 9.091758320783139e-06,
+      "loss": 0.5603,
+      "step": 96
+    },
+    {
+      "epoch": 0.5572044040210627,
+      "grad_norm": 0.5799354910850525,
+      "learning_rate": 9.062710380624439e-06,
+      "loss": 0.5307,
+      "step": 97
+    },
+    {
+      "epoch": 0.5629487793202489,
+      "grad_norm": 0.5598204731941223,
+      "learning_rate": 9.033253157859715e-06,
+      "loss": 0.5733,
+      "step": 98
+    },
+    {
+      "epoch": 0.5686931546194351,
+      "grad_norm": 0.5341041684150696,
+      "learning_rate": 9.003389620047012e-06,
+      "loss": 0.5288,
+      "step": 99
+    },
+    {
+      "epoch": 0.5744375299186214,
+      "grad_norm": 0.5493537187576294,
+      "learning_rate": 8.973122775677078e-06,
+      "loss": 0.5322,
+      "step": 100
+    },
+    {
+      "epoch": 0.5801819052178075,
+      "grad_norm": 0.7178077101707458,
+      "learning_rate": 8.942455673870278e-06,
+      "loss": 0.5638,
+      "step": 101
+    },
+    {
+      "epoch": 0.5859262805169938,
+      "grad_norm": 0.5725718140602112,
+      "learning_rate": 8.91139140406941e-06,
+      "loss": 0.5603,
+      "step": 102
+    },
+    {
+      "epoch": 0.59167065581618,
+      "grad_norm": 0.5904880166053772,
+      "learning_rate": 8.879933095728485e-06,
+      "loss": 0.5454,
+      "step": 103
+    },
+    {
+      "epoch": 0.5974150311153662,
+      "grad_norm": 0.5282031893730164,
+      "learning_rate": 8.848083917997463e-06,
+      "loss": 0.5287,
+      "step": 104
+    },
+    {
+      "epoch": 0.6031594064145525,
+      "grad_norm": 0.5110641121864319,
+      "learning_rate": 8.815847079402972e-06,
+      "loss": 0.5301,
+      "step": 105
+    },
+    {
+      "epoch": 0.6089037817137386,
+      "grad_norm": 0.7060251235961914,
+      "learning_rate": 8.783225827525098e-06,
+      "loss": 0.5529,
+      "step": 106
+    },
+    {
+      "epoch": 0.6146481570129249,
+      "grad_norm": 0.5038994550704956,
+      "learning_rate": 8.750223448670204e-06,
+      "loss": 0.5464,
+      "step": 107
+    },
+    {
+      "epoch": 0.6203925323121111,
+      "grad_norm": 0.6462810039520264,
+      "learning_rate": 8.716843267539868e-06,
+      "loss": 0.5634,
+      "step": 108
+    },
+    {
+      "epoch": 0.6261369076112973,
+      "grad_norm": 0.5832483768463135,
+      "learning_rate": 8.683088646895955e-06,
+      "loss": 0.5102,
+      "step": 109
+    },
+    {
+      "epoch": 0.6318812829104835,
+      "grad_norm": 0.5752907991409302,
+      "learning_rate": 8.648962987221837e-06,
+      "loss": 0.5767,
+      "step": 110
+    },
+    {
+      "epoch": 0.6376256582096697,
+      "grad_norm": 0.714330792427063,
+      "learning_rate": 8.614469726379833e-06,
+      "loss": 0.5567,
+      "step": 111
+    },
+    {
+      "epoch": 0.6433700335088559,
+      "grad_norm": 0.5703815817832947,
+      "learning_rate": 8.579612339264867e-06,
+      "loss": 0.566,
+      "step": 112
+    },
+    {
+      "epoch": 0.6491144088080422,
+      "grad_norm": 0.7698194980621338,
+      "learning_rate": 8.544394337454409e-06,
+      "loss": 0.5308,
+      "step": 113
+    },
+    {
+      "epoch": 0.6548587841072283,
+      "grad_norm": 0.5629884600639343,
+      "learning_rate": 8.508819268854713e-06,
+      "loss": 0.555,
+      "step": 114
+    },
+    {
+      "epoch": 0.6606031594064146,
+      "grad_norm": 0.6958817839622498,
+      "learning_rate": 8.472890717343391e-06,
+      "loss": 0.5623,
+      "step": 115
+    },
+    {
+      "epoch": 0.6663475347056008,
+      "grad_norm": 0.6036946773529053,
+      "learning_rate": 8.436612302408376e-06,
+      "loss": 0.526,
+      "step": 116
+    },
+    {
+      "epoch": 0.672091910004787,
+      "grad_norm": 0.511654794216156,
+      "learning_rate": 8.399987678783285e-06,
+      "loss": 0.5446,
+      "step": 117
+    },
+    {
+      "epoch": 0.6778362853039732,
+      "grad_norm": 0.7489587068557739,
+      "learning_rate": 8.36302053607924e-06,
+      "loss": 0.5671,
+      "step": 118
+    },
+    {
+      "epoch": 0.6835806606031594,
+      "grad_norm": 0.6197418570518494,
+      "learning_rate": 8.325714598413169e-06,
+      "loss": 0.5701,
+      "step": 119
+    },
+    {
+      "epoch": 0.6893250359023456,
+      "grad_norm": 0.6502342820167542,
+      "learning_rate": 8.288073624032634e-06,
+      "loss": 0.5321,
+      "step": 120
+    },
+    {
+      "epoch": 0.6950694112015319,
+      "grad_norm": 0.49902498722076416,
+      "learning_rate": 8.250101404937223e-06,
+      "loss": 0.5542,
+      "step": 121
+    },
+    {
+      "epoch": 0.700813786500718,
+      "grad_norm": 0.5273813009262085,
+      "learning_rate": 8.211801766496537e-06,
+      "loss": 0.5311,
+      "step": 122
+    },
+    {
+      "epoch": 0.7065581617999043,
+      "grad_norm": 0.5683380365371704,
+      "learning_rate": 8.17317856706482e-06,
+      "loss": 0.523,
+      "step": 123
+    },
+    {
+      "epoch": 0.7123025370990905,
+      "grad_norm": 0.5648055076599121,
+      "learning_rate": 8.13423569759226e-06,
+      "loss": 0.5678,
+      "step": 124
+    },
+    {
+      "epoch": 0.7180469123982767,
+      "grad_norm": 0.5629974007606506,
+      "learning_rate": 8.094977081233006e-06,
+      "loss": 0.5669,
+      "step": 125
+    },
+    {
+      "epoch": 0.7237912876974629,
+      "grad_norm": 0.602506160736084,
+      "learning_rate": 8.055406672949957e-06,
+      "loss": 0.5275,
+      "step": 126
+    },
+    {
+      "epoch": 0.7295356629966491,
+      "grad_norm": 0.572467029094696,
+      "learning_rate": 8.015528459116321e-06,
+      "loss": 0.5275,
+      "step": 127
+    },
+    {
+      "epoch": 0.7352800382958353,
+      "grad_norm": 0.5794216394424438,
+      "learning_rate": 7.975346457114034e-06,
+      "loss": 0.5396,
+      "step": 128
+    },
+    {
+      "epoch": 0.7410244135950216,
+      "grad_norm": 0.560357391834259,
+      "learning_rate": 7.934864714929036e-06,
+      "loss": 0.5483,
+      "step": 129
+    },
+    {
+      "epoch": 0.7467687888942077,
+      "grad_norm": 0.5050742626190186,
+      "learning_rate": 7.894087310743468e-06,
+      "loss": 0.5617,
+      "step": 130
+    },
+    {
+      "epoch": 0.752513164193394,
+      "grad_norm": 0.4990502595901489,
+      "learning_rate": 7.853018352524845e-06,
+      "loss": 0.5253,
+      "step": 131
+    },
+    {
+      "epoch": 0.7582575394925802,
+      "grad_norm": 0.4985724985599518,
+      "learning_rate": 7.811661977612202e-06,
+      "loss": 0.5303,
+      "step": 132
+    },
+    {
+      "epoch": 0.7640019147917664,
+      "grad_norm": 0.5744158029556274,
+      "learning_rate": 7.770022352299294e-06,
+      "loss": 0.5235,
+      "step": 133
+    },
+    {
+      "epoch": 0.7697462900909526,
+      "grad_norm": 0.5937462449073792,
+      "learning_rate": 7.728103671414889e-06,
+      "loss": 0.5148,
+      "step": 134
+    },
+    {
+      "epoch": 0.7754906653901388,
+      "grad_norm": 0.5738289952278137,
+      "learning_rate": 7.685910157900158e-06,
+      "loss": 0.5345,
+      "step": 135
+    },
+    {
+      "epoch": 0.781235040689325,
+      "grad_norm": 0.5279061794281006,
+      "learning_rate": 7.643446062383273e-06,
+      "loss": 0.5451,
+      "step": 136
+    },
+    {
+      "epoch": 0.7869794159885113,
+      "grad_norm": 0.5690545439720154,
+      "learning_rate": 7.600715662751166e-06,
+      "loss": 0.5083,
+      "step": 137
+    },
+    {
+      "epoch": 0.7927237912876974,
+      "grad_norm": 0.5676944255828857,
+      "learning_rate": 7.557723263718596e-06,
+      "loss": 0.5516,
+      "step": 138
+    },
+    {
+      "epoch": 0.7984681665868837,
+      "grad_norm": 0.6335099339485168,
+      "learning_rate": 7.514473196394467e-06,
+      "loss": 0.5583,
+      "step": 139
+    },
+    {
+      "epoch": 0.8042125418860699,
+      "grad_norm": 0.6167879104614258,
+      "learning_rate": 7.470969817845518e-06,
+      "loss": 0.5675,
+      "step": 140
+    },
+    {
+      "epoch": 0.8099569171852561,
+      "grad_norm": 0.6238246560096741,
+      "learning_rate": 7.427217510657383e-06,
+      "loss": 0.5242,
+      "step": 141
+    },
+    {
+      "epoch": 0.8157012924844423,
+      "grad_norm": 0.6096833944320679,
+      "learning_rate": 7.383220682493081e-06,
+      "loss": 0.56,
+      "step": 142
+    },
+    {
+      "epoch": 0.8214456677836285,
+      "grad_norm": 0.6408026814460754,
+      "learning_rate": 7.338983765648985e-06,
+      "loss": 0.517,
+      "step": 143
+    },
+    {
+      "epoch": 0.8271900430828147,
+      "grad_norm": 0.6161112785339355,
+      "learning_rate": 7.294511216608308e-06,
+      "loss": 0.5568,
+      "step": 144
+    },
+    {
+      "epoch": 0.832934418382001,
+      "grad_norm": 0.6821258664131165,
+      "learning_rate": 7.249807515592149e-06,
+      "loss": 0.5391,
+      "step": 145
+    },
+    {
+      "epoch": 0.8386787936811871,
+      "grad_norm": 0.5701781511306763,
+      "learning_rate": 7.2048771661081515e-06,
+      "loss": 0.5393,
+      "step": 146
+    },
+    {
+      "epoch": 0.8444231689803734,
+      "grad_norm": 0.573361873626709,
+      "learning_rate": 7.159724694496815e-06,
+      "loss": 0.5104,
+      "step": 147
+    },
+    {
+      "epoch": 0.8501675442795597,
+      "grad_norm": 0.6415104269981384,
+      "learning_rate": 7.114354649475499e-06,
+      "loss": 0.5373,
+      "step": 148
+    },
+    {
+      "epoch": 0.8559119195787458,
+      "grad_norm": 0.5799002647399902,
+      "learning_rate": 7.068771601680191e-06,
+      "loss": 0.516,
+      "step": 149
+    },
+    {
+      "epoch": 0.861656294877932,
+      "grad_norm": 0.6010524034500122,
+      "learning_rate": 7.022980143205046e-06,
+      "loss": 0.5421,
+      "step": 150
+    },
+    {
+      "epoch": 0.8674006701771182,
+      "grad_norm": 0.5849425196647644,
+      "learning_rate": 6.976984887139775e-06,
+      "loss": 0.5576,
+      "step": 151
+    },
+    {
+      "epoch": 0.8731450454763044,
+      "grad_norm": 0.49850520491600037,
+      "learning_rate": 6.930790467104916e-06,
+      "loss": 0.4881,
+      "step": 152
+    },
+    {
+      "epoch": 0.8788894207754907,
+      "grad_norm": 0.6236470937728882,
+      "learning_rate": 6.884401536785045e-06,
+      "loss": 0.5521,
+      "step": 153
+    },
+    {
+      "epoch": 0.8846337960746768,
+      "grad_norm": 0.5845939517021179,
+      "learning_rate": 6.837822769459942e-06,
+      "loss": 0.5143,
+      "step": 154
+    },
+    {
+      "epoch": 0.8903781713738631,
+      "grad_norm": 0.48170965909957886,
+      "learning_rate": 6.791058857533814e-06,
+      "loss": 0.5248,
+      "step": 155
+    },
+    {
+      "epoch": 0.8961225466730494,
+      "grad_norm": 0.5586768984794617,
+      "learning_rate": 6.744114512062571e-06,
+      "loss": 0.543,
+      "step": 156
+    },
+    {
+      "epoch": 0.9018669219722355,
+      "grad_norm": 0.5925922393798828,
+      "learning_rate": 6.696994462279223e-06,
+      "loss": 0.5272,
+      "step": 157
+    },
+    {
+      "epoch": 0.9076112972714218,
+      "grad_norm": 0.5067867636680603,
+      "learning_rate": 6.6497034551174585e-06,
+      "loss": 0.5572,
+      "step": 158
+    },
+    {
+      "epoch": 0.9133556725706079,
+      "grad_norm": 0.5289098024368286,
+      "learning_rate": 6.602246254733431e-06,
+      "loss": 0.5216,
+      "step": 159
+    },
+    {
+      "epoch": 0.9191000478697942,
+      "grad_norm": 0.5776088833808899,
+      "learning_rate": 6.554627642025807e-06,
+      "loss": 0.5278,
+      "step": 160
+    },
+    {
+      "epoch": 0.9248444231689804,
+      "grad_norm": 0.4834924340248108,
+      "learning_rate": 6.506852414154138e-06,
+      "loss": 0.5479,
+      "step": 161
+    },
+    {
+      "epoch": 0.9305887984681666,
+      "grad_norm": 0.5455948114395142,
+      "learning_rate": 6.4589253840555856e-06,
+      "loss": 0.4813,
+      "step": 162
+    },
+    {
+      "epoch": 0.9363331737673528,
+      "grad_norm": 0.5379589200019836,
+      "learning_rate": 6.41085137996006e-06,
+      "loss": 0.5391,
+      "step": 163
+    },
+    {
+      "epoch": 0.9420775490665391,
+      "grad_norm": 0.5952578783035278,
+      "learning_rate": 6.362635244903818e-06,
+      "loss": 0.556,
+      "step": 164
+    },
+    {
+      "epoch": 0.9478219243657252,
+      "grad_norm": 0.5639842748641968,
+      "learning_rate": 6.314281836241573e-06,
+      "loss": 0.552,
+      "step": 165
+    },
+    {
+      "epoch": 0.9535662996649115,
+      "grad_norm": 0.5705066323280334,
+      "learning_rate": 6.265796025157154e-06,
+      "loss": 0.5028,
+      "step": 166
+    },
+    {
+      "epoch": 0.9593106749640976,
+      "grad_norm": 0.5012354850769043,
+      "learning_rate": 6.217182696172776e-06,
+      "loss": 0.5229,
+      "step": 167
+    },
+    {
+      "epoch": 0.9650550502632839,
+      "grad_norm": 0.5164003968238831,
+      "learning_rate": 6.168446746656973e-06,
+      "loss": 0.5166,
+      "step": 168
+    },
+    {
+      "epoch": 0.9707994255624701,
+      "grad_norm": 0.5868187546730042,
+      "learning_rate": 6.119593086331225e-06,
+      "loss": 0.5342,
+      "step": 169
+    },
+    {
+      "epoch": 0.9765438008616563,
+      "grad_norm": 0.5106255412101746,
+      "learning_rate": 6.070626636775349e-06,
+      "loss": 0.526,
+      "step": 170
+    },
+    {
+      "epoch": 0.9822881761608425,
+      "grad_norm": 0.44993191957473755,
+      "learning_rate": 6.021552330931693e-06,
+      "loss": 0.5599,
+      "step": 171
+    },
+    {
+      "epoch": 0.9880325514600288,
+      "grad_norm": 0.5432422161102295,
+      "learning_rate": 5.972375112608182e-06,
+      "loss": 0.5265,
+      "step": 172
+    },
+    {
+      "epoch": 0.9937769267592149,
+      "grad_norm": 0.5361687541007996,
+      "learning_rate": 5.923099935980278e-06,
+      "loss": 0.5652,
+      "step": 173
+    },
+    {
+      "epoch": 0.9995213020584012,
+      "grad_norm": 0.43177682161331177,
+      "learning_rate": 5.8737317650918905e-06,
+      "loss": 0.5462,
+      "step": 174
+    },
+    {
+      "epoch": 1.0052656773575874,
+      "grad_norm": 1.580591082572937,
+      "learning_rate": 5.824275573355278e-06,
+      "loss": 0.9082,
+      "step": 175
+    },
+    {
+      "epoch": 1.0110100526567736,
+      "grad_norm": 0.5395136475563049,
+      "learning_rate": 5.7747363430500395e-06,
+      "loss": 0.4953,
+      "step": 176
+    },
+    {
+      "epoch": 1.0167544279559597,
+      "grad_norm": 0.5305489301681519,
+      "learning_rate": 5.725119064821185e-06,
+      "loss": 0.5229,
+      "step": 177
+    },
+    {
+      "epoch": 1.022498803255146,
+      "grad_norm": 0.5417148470878601,
+      "learning_rate": 5.675428737176367e-06,
+      "loss": 0.461,
+      "step": 178
+    },
+    {
+      "epoch": 1.0282431785543322,
+      "grad_norm": 0.5382701754570007,
+      "learning_rate": 5.625670365982332e-06,
+      "loss": 0.4442,
+      "step": 179
+    },
+    {
+      "epoch": 1.0339875538535184,
+      "grad_norm": 0.5847955346107483,
+      "learning_rate": 5.575848963960621e-06,
+      "loss": 0.5286,
+      "step": 180
+    },
+    {
+      "epoch": 1.0397319291527047,
+      "grad_norm": 0.4929944574832916,
+      "learning_rate": 5.525969550182577e-06,
+      "loss": 0.4789,
+      "step": 181
+    },
+    {
+      "epoch": 1.0454763044518909,
+      "grad_norm": 0.5635377764701843,
+      "learning_rate": 5.4760371495637256e-06,
+      "loss": 0.4753,
+      "step": 182
+    },
+    {
+      "epoch": 1.051220679751077,
+      "grad_norm": 0.4980822801589966,
+      "learning_rate": 5.426056792357552e-06,
+      "loss": 0.4895,
+      "step": 183
+    },
+    {
+      "epoch": 1.0569650550502634,
+      "grad_norm": 0.5097235441207886,
+      "learning_rate": 5.376033513648743e-06,
+      "loss": 0.4794,
+      "step": 184
+    },
+    {
+      "epoch": 1.0627094303494495,
+      "grad_norm": 0.5179345607757568,
+      "learning_rate": 5.325972352845965e-06,
+      "loss": 0.4957,
+      "step": 185
+    },
+    {
+      "epoch": 1.0684538056486357,
+      "grad_norm": 0.4883691072463989,
+      "learning_rate": 5.2758783531741655e-06,
+      "loss": 0.5047,
+      "step": 186
+    },
+    {
+      "epoch": 1.0741981809478218,
+      "grad_norm": 0.46270909905433655,
+      "learning_rate": 5.225756561166521e-06,
+      "loss": 0.5066,
+      "step": 187
+    },
+    {
+      "epoch": 1.0799425562470082,
+      "grad_norm": 0.5014520883560181,
+      "learning_rate": 5.175612026156045e-06,
+      "loss": 0.5012,
+      "step": 188
+    },
+    {
+      "epoch": 1.0856869315461943,
+      "grad_norm": 0.4673246443271637,
+      "learning_rate": 5.125449799766916e-06,
+      "loss": 0.4638,
+      "step": 189
+    },
+    {
+      "epoch": 1.0914313068453805,
+      "grad_norm": 0.4951716363430023,
+      "learning_rate": 5.075274935405554e-06,
+      "loss": 0.4915,
+      "step": 190
+    },
+    {
+      "epoch": 1.0971756821445668,
+      "grad_norm": 0.4571003317832947,
+      "learning_rate": 5.025092487751552e-06,
+      "loss": 0.494,
+      "step": 191
+    },
+    {
+      "epoch": 1.102920057443753,
+      "grad_norm": 0.4891183078289032,
+      "learning_rate": 4.974907512248451e-06,
+      "loss": 0.4549,
+      "step": 192
+    },
+    {
+      "epoch": 1.1086644327429391,
+      "grad_norm": 0.4218912422657013,
+      "learning_rate": 4.924725064594448e-06,
+      "loss": 0.489,
+      "step": 193
+    },
+    {
+      "epoch": 1.1144088080421255,
+      "grad_norm": 0.45297980308532715,
+      "learning_rate": 4.874550200233085e-06,
+      "loss": 0.4907,
+      "step": 194
+    },
+    {
+      "epoch": 1.1201531833413116,
+      "grad_norm": 0.5533784031867981,
+      "learning_rate": 4.824387973843957e-06,
+      "loss": 0.5129,
+      "step": 195
+    },
+    {
+      "epoch": 1.1258975586404978,
+      "grad_norm": 0.45622408390045166,
+      "learning_rate": 4.7742434388334815e-06,
+      "loss": 0.4418,
+      "step": 196
+    },
+    {
+      "epoch": 1.1316419339396842,
+      "grad_norm": 0.4435925781726837,
+      "learning_rate": 4.724121646825838e-06,
+      "loss": 0.5022,
+      "step": 197
+    },
+    {
+      "epoch": 1.1373863092388703,
+      "grad_norm": 0.4371262490749359,
+      "learning_rate": 4.674027647154037e-06,
+      "loss": 0.4711,
+      "step": 198
+    },
+    {
+      "epoch": 1.1431306845380564,
+      "grad_norm": 0.473237544298172,
+      "learning_rate": 4.623966486351257e-06,
+      "loss": 0.4465,
+      "step": 199
+    },
+    {
+      "epoch": 1.1488750598372426,
+      "grad_norm": 0.4501272439956665,
+      "learning_rate": 4.573943207642452e-06,
+      "loss": 0.4659,
+      "step": 200
+    },
+    {
+      "epoch": 1.154619435136429,
+      "grad_norm": 0.5544123649597168,
+      "learning_rate": 4.523962850436276e-06,
+      "loss": 0.4974,
+      "step": 201
+    },
+    {
+      "epoch": 1.160363810435615,
+      "grad_norm": 0.519002377986908,
+      "learning_rate": 4.474030449817423e-06,
+      "loss": 0.5099,
+      "step": 202
+    },
+    {
+      "epoch": 1.1661081857348012,
+      "grad_norm": 0.48358842730522156,
+      "learning_rate": 4.424151036039381e-06,
+      "loss": 0.4687,
+      "step": 203
+    },
+    {
+      "epoch": 1.1718525610339876,
+      "grad_norm": 0.5397114753723145,
+      "learning_rate": 4.3743296340176694e-06,
+      "loss": 0.505,
+      "step": 204
+    },
+    {
+      "epoch": 1.1775969363331737,
+      "grad_norm": 0.47014209628105164,
+      "learning_rate": 4.3245712628236356e-06,
+      "loss": 0.5201,
+      "step": 205
+    },
+    {
+      "epoch": 1.18334131163236,
+      "grad_norm": 0.4648483395576477,
+      "learning_rate": 4.274880935178817e-06,
+      "loss": 0.4652,
+      "step": 206
+    },
+    {
+      "epoch": 1.1890856869315463,
+      "grad_norm": 0.45514115691185,
+      "learning_rate": 4.225263656949961e-06,
+      "loss": 0.4692,
+      "step": 207
+    },
+    {
+      "epoch": 1.1948300622307324,
+      "grad_norm": 0.48053470253944397,
+      "learning_rate": 4.175724426644724e-06,
+      "loss": 0.4842,
+      "step": 208
+    },
+    {
+      "epoch": 1.2005744375299185,
+      "grad_norm": 0.45836907625198364,
+      "learning_rate": 4.12626823490811e-06,
+      "loss": 0.4535,
+      "step": 209
+    },
+    {
+      "epoch": 1.206318812829105,
+      "grad_norm": 0.43734660744667053,
+      "learning_rate": 4.076900064019721e-06,
+      "loss": 0.5134,
+      "step": 210
+    },
+    {
+      "epoch": 1.212063188128291,
+      "grad_norm": 0.4292330741882324,
+      "learning_rate": 4.02762488739182e-06,
+      "loss": 0.4933,
+      "step": 211
+    },
+    {
+      "epoch": 1.2178075634274772,
+      "grad_norm": 0.48980435729026794,
+      "learning_rate": 3.978447669068309e-06,
+      "loss": 0.4924,
+      "step": 212
+    },
+    {
+      "epoch": 1.2235519387266636,
+      "grad_norm": 0.415892630815506,
+      "learning_rate": 3.929373363224654e-06,
+      "loss": 0.4602,
+      "step": 213
+    },
+    {
+      "epoch": 1.2292963140258497,
+      "grad_norm": 0.5073506236076355,
+      "learning_rate": 3.8804069136687775e-06,
+      "loss": 0.4469,
+      "step": 214
+    },
+    {
+      "epoch": 1.2350406893250359,
+      "grad_norm": 0.4534899592399597,
+      "learning_rate": 3.8315532533430285e-06,
+      "loss": 0.4937,
+      "step": 215
+    },
+    {
+      "epoch": 1.2407850646242222,
+      "grad_norm": 0.43552905321121216,
+      "learning_rate": 3.7828173038272266e-06,
+      "loss": 0.5012,
+      "step": 216
+    },
+    {
+      "epoch": 1.2465294399234084,
+      "grad_norm": 0.45762044191360474,
+      "learning_rate": 3.7342039748428473e-06,
+      "loss": 0.448,
+      "step": 217
+    },
+    {
+      "epoch": 1.2522738152225945,
+      "grad_norm": 0.4884515702724457,
+      "learning_rate": 3.685718163758427e-06,
+      "loss": 0.4803,
+      "step": 218
+    },
+    {
+      "epoch": 1.2580181905217809,
+      "grad_norm": 0.414726585149765,
+      "learning_rate": 3.6373647550961834e-06,
+      "loss": 0.4844,
+      "step": 219
+    },
+    {
+      "epoch": 1.263762565820967,
+      "grad_norm": 0.44502031803131104,
+      "learning_rate": 3.5891486200399413e-06,
+      "loss": 0.5254,
+      "step": 220
+    },
+    {
+      "epoch": 1.2695069411201532,
+      "grad_norm": 0.46549510955810547,
+      "learning_rate": 3.5410746159444165e-06,
+      "loss": 0.503,
+      "step": 221
+    },
+    {
+      "epoch": 1.2752513164193395,
+      "grad_norm": 0.480082631111145,
+      "learning_rate": 3.4931475858458634e-06,
+      "loss": 0.474,
+      "step": 222
+    },
+    {
+      "epoch": 1.2809956917185257,
+      "grad_norm": 0.5088851451873779,
+      "learning_rate": 3.445372357974194e-06,
+      "loss": 0.5197,
+      "step": 223
+    },
+    {
+      "epoch": 1.2867400670177118,
+      "grad_norm": 0.4297751486301422,
+      "learning_rate": 3.397753745266571e-06,
+      "loss": 0.4698,
+      "step": 224
+    },
+    {
+      "epoch": 1.292484442316898,
+      "grad_norm": 0.436560720205307,
+      "learning_rate": 3.350296544882543e-06,
+      "loss": 0.4573,
+      "step": 225
+    },
+    {
+      "epoch": 1.2982288176160843,
+      "grad_norm": 0.451806902885437,
+      "learning_rate": 3.303005537720778e-06,
+      "loss": 0.4654,
+      "step": 226
+    },
+    {
+      "epoch": 1.3039731929152705,
+      "grad_norm": 0.4921393394470215,
+      "learning_rate": 3.255885487937431e-06,
+      "loss": 0.5075,
+      "step": 227
+    },
+    {
+      "epoch": 1.3097175682144566,
+      "grad_norm": 0.4880327880382538,
+      "learning_rate": 3.2089411424661864e-06,
+      "loss": 0.5467,
+      "step": 228
+    },
+    {
+      "epoch": 1.3154619435136428,
+      "grad_norm": 0.40174514055252075,
+      "learning_rate": 3.1621772305400603e-06,
+      "loss": 0.4965,
+      "step": 229
+    },
+    {
+      "epoch": 1.3212063188128291,
+      "grad_norm": 0.41413503885269165,
+      "learning_rate": 3.1155984632149565e-06,
+      "loss": 0.4826,
+      "step": 230
+    },
+    {
+      "epoch": 1.3269506941120153,
+      "grad_norm": 0.43642458319664,
+      "learning_rate": 3.0692095328950843e-06,
+      "loss": 0.4355,
+      "step": 231
+    },
+    {
+      "epoch": 1.3326950694112014,
+      "grad_norm": 0.4538045823574066,
+      "learning_rate": 3.023015112860228e-06,
+      "loss": 0.5378,
+      "step": 232
+    },
+    {
+      "epoch": 1.3384394447103878,
+      "grad_norm": 0.42121201753616333,
+      "learning_rate": 2.977019856794955e-06,
+      "loss": 0.4811,
+      "step": 233
+    },
+    {
+      "epoch": 1.344183820009574,
+      "grad_norm": 0.3827037513256073,
+      "learning_rate": 2.93122839831981e-06,
+      "loss": 0.4956,
+      "step": 234
+    },
+    {
+      "epoch": 1.34992819530876,
+      "grad_norm": 0.3937554359436035,
+      "learning_rate": 2.8856453505245018e-06,
+      "loss": 0.4729,
+      "step": 235
+    },
+    {
+      "epoch": 1.3556725706079464,
+      "grad_norm": 0.4603598415851593,
+      "learning_rate": 2.840275305503186e-06,
+      "loss": 0.5352,
+      "step": 236
+    },
+    {
+      "epoch": 1.3614169459071326,
+      "grad_norm": 0.4124448001384735,
+      "learning_rate": 2.7951228338918506e-06,
+      "loss": 0.4523,
+      "step": 237
+    },
+    {
+      "epoch": 1.3671613212063187,
+      "grad_norm": 0.41025596857070923,
+      "learning_rate": 2.7501924844078538e-06,
+      "loss": 0.4824,
+      "step": 238
+    },
+    {
+      "epoch": 1.372905696505505,
+      "grad_norm": 0.3917722702026367,
+      "learning_rate": 2.7054887833916933e-06,
+      "loss": 0.5059,
+      "step": 239
+    },
+    {
+      "epoch": 1.3786500718046912,
+      "grad_norm": 0.4388699531555176,
+      "learning_rate": 2.6610162343510183e-06,
+      "loss": 0.5039,
+      "step": 240
+    },
+    {
+      "epoch": 1.3843944471038774,
+      "grad_norm": 0.4307573139667511,
+      "learning_rate": 2.616779317506921e-06,
+      "loss": 0.4668,
+      "step": 241
+    },
+    {
+      "epoch": 1.3901388224030637,
+      "grad_norm": 0.40513068437576294,
+      "learning_rate": 2.572782489342617e-06,
+      "loss": 0.4365,
+      "step": 242
+    },
+    {
+      "epoch": 1.39588319770225,
+      "grad_norm": 0.43141913414001465,
+      "learning_rate": 2.5290301821544826e-06,
+      "loss": 0.5055,
+      "step": 243
+    },
+    {
+      "epoch": 1.401627573001436,
+      "grad_norm": 0.4245367646217346,
+      "learning_rate": 2.4855268036055346e-06,
+      "loss": 0.5001,
+      "step": 244
+    },
+    {
+      "epoch": 1.4073719483006224,
+      "grad_norm": 0.41667869687080383,
+      "learning_rate": 2.4422767362814045e-06,
+      "loss": 0.5056,
+      "step": 245
+    },
+    {
+      "epoch": 1.4131163235998085,
+      "grad_norm": 0.41470879316329956,
+      "learning_rate": 2.3992843372488357e-06,
+      "loss": 0.477,
+      "step": 246
+    },
+    {
+      "epoch": 1.4188606988989947,
+      "grad_norm": 0.43821245431900024,
+      "learning_rate": 2.3565539376167295e-06,
+      "loss": 0.5074,
+      "step": 247
+    },
+    {
+      "epoch": 1.424605074198181,
+      "grad_norm": 0.38262587785720825,
+      "learning_rate": 2.3140898420998425e-06,
+      "loss": 0.4686,
+      "step": 248
+    },
+    {
+      "epoch": 1.4303494494973672,
+      "grad_norm": 0.3910864591598511,
+      "learning_rate": 2.271896328585114e-06,
+      "loss": 0.4852,
+      "step": 249
+    },
+    {
+      "epoch": 1.4360938247965533,
+      "grad_norm": 0.43671905994415283,
+      "learning_rate": 2.2299776477007073e-06,
+      "loss": 0.4729,
+      "step": 250
+    },
+    {
+      "epoch": 1.4418382000957397,
+      "grad_norm": 0.3937380611896515,
+      "learning_rate": 2.1883380223878004e-06,
+      "loss": 0.5039,
+      "step": 251
+    },
+    {
+      "epoch": 1.4475825753949259,
+      "grad_norm": 0.4383409023284912,
+      "learning_rate": 2.1469816474751566e-06,
+      "loss": 0.5264,
+      "step": 252
+    },
+    {
+      "epoch": 1.453326950694112,
+      "grad_norm": 0.38024550676345825,
+      "learning_rate": 2.105912689256533e-06,
+      "loss": 0.4575,
+      "step": 253
+    },
+    {
+      "epoch": 1.4590713259932984,
+      "grad_norm": 0.4220210313796997,
+      "learning_rate": 2.0651352850709656e-06,
+      "loss": 0.4846,
+      "step": 254
+    },
+    {
+      "epoch": 1.4648157012924845,
+      "grad_norm": 0.4223257005214691,
+      "learning_rate": 2.0246535428859652e-06,
+      "loss": 0.4968,
+      "step": 255
+    },
+    {
+      "epoch": 1.4705600765916707,
+      "grad_norm": 0.3835613429546356,
+      "learning_rate": 1.984471540883679e-06,
+      "loss": 0.4874,
+      "step": 256
+    },
+    {
+      "epoch": 1.4763044518908568,
+      "grad_norm": 0.43379145860671997,
+      "learning_rate": 1.9445933270500444e-06,
+      "loss": 0.5144,
+      "step": 257
+    },
+    {
+      "epoch": 1.4820488271900432,
+      "grad_norm": 0.3767804205417633,
+      "learning_rate": 1.905022918766995e-06,
+      "loss": 0.4621,
+      "step": 258
+    },
+    {
+      "epoch": 1.4877932024892293,
+      "grad_norm": 0.4112907648086548,
+      "learning_rate": 1.8657643024077431e-06,
+      "loss": 0.5212,
+      "step": 259
+    },
+    {
+      "epoch": 1.4935375777884154,
+      "grad_norm": 0.41141629219055176,
+      "learning_rate": 1.8268214329351797e-06,
+      "loss": 0.4859,
+      "step": 260
+    },
+    {
+      "epoch": 1.4992819530876016,
+      "grad_norm": 0.3843127191066742,
+      "learning_rate": 1.7881982335034625e-06,
+      "loss": 0.4308,
+      "step": 261
+    },
+    {
+      "epoch": 1.505026328386788,
+      "grad_norm": 0.3895561695098877,
+      "learning_rate": 1.7498985950627794e-06,
+      "loss": 0.4565,
+      "step": 262
+    },
+    {
+      "epoch": 1.510770703685974,
+      "grad_norm": 0.4275520443916321,
+      "learning_rate": 1.7119263759673677e-06,
+      "loss": 0.4704,
+      "step": 263
+    },
+    {
+      "epoch": 1.5165150789851602,
+      "grad_norm": 0.4638034999370575,
+      "learning_rate": 1.6742854015868349e-06,
+      "loss": 0.5137,
+      "step": 264
+    },
+    {
+      "epoch": 1.5222594542843466,
+      "grad_norm": 0.35882094502449036,
+      "learning_rate": 1.6369794639207626e-06,
+      "loss": 0.4582,
+      "step": 265
+    },
+    {
+      "epoch": 1.5280038295835328,
+      "grad_norm": 0.4297800362110138,
+      "learning_rate": 1.6000123212167158e-06,
+      "loss": 0.471,
+      "step": 266
+    },
+    {
+      "epoch": 1.533748204882719,
+      "grad_norm": 0.37162676453590393,
+      "learning_rate": 1.5633876975916261e-06,
+      "loss": 0.479,
+      "step": 267
+    },
+    {
+      "epoch": 1.5394925801819053,
+      "grad_norm": 0.4432937502861023,
+      "learning_rate": 1.5271092826566108e-06,
+      "loss": 0.4918,
+      "step": 268
+    },
+    {
+      "epoch": 1.5452369554810914,
+      "grad_norm": 0.4131205976009369,
+      "learning_rate": 1.4911807311452874e-06,
+      "loss": 0.4862,
+      "step": 269
+    },
+    {
+      "epoch": 1.5509813307802776,
+      "grad_norm": 0.39494404196739197,
+      "learning_rate": 1.4556056625455922e-06,
+      "loss": 0.472,
+      "step": 270
+    },
+    {
+      "epoch": 1.556725706079464,
+      "grad_norm": 0.3842601776123047,
+      "learning_rate": 1.4203876607351347e-06,
+      "loss": 0.5468,
+      "step": 271
+    },
+    {
+      "epoch": 1.56247008137865,
+      "grad_norm": 0.39018625020980835,
+      "learning_rate": 1.3855302736201686e-06,
+      "loss": 0.4695,
+      "step": 272
+    },
+    {
+      "epoch": 1.5682144566778362,
+      "grad_norm": 0.4116652011871338,
+      "learning_rate": 1.3510370127781635e-06,
+      "loss": 0.5009,
+      "step": 273
+    },
+    {
+      "epoch": 1.5739588319770226,
+      "grad_norm": 0.4268287420272827,
+      "learning_rate": 1.3169113531040462e-06,
+      "loss": 0.509,
+      "step": 274
+    },
+    {
+      "epoch": 1.5797032072762087,
+      "grad_norm": 0.403522253036499,
+      "learning_rate": 1.2831567324601325e-06,
+      "loss": 0.4961,
+      "step": 275
+    },
+    {
+      "epoch": 1.5854475825753949,
+      "grad_norm": 0.37210026383399963,
+      "learning_rate": 1.2497765513297976e-06,
+      "loss": 0.4923,
+      "step": 276
+    },
+    {
+      "epoch": 1.5911919578745812,
+      "grad_norm": 0.4218740463256836,
+      "learning_rate": 1.2167741724749026e-06,
+      "loss": 0.4894,
+      "step": 277
+    },
+    {
+      "epoch": 1.5969363331737674,
+      "grad_norm": 0.3306220769882202,
+      "learning_rate": 1.1841529205970281e-06,
+      "loss": 0.4224,
+      "step": 278
+    },
+    {
+      "epoch": 1.6026807084729535,
+      "grad_norm": 0.4241751730442047,
+      "learning_rate": 1.1519160820025382e-06,
+      "loss": 0.4937,
+      "step": 279
+    },
+    {
+      "epoch": 1.6084250837721399,
+      "grad_norm": 0.3803061842918396,
+      "learning_rate": 1.1200669042715163e-06,
+      "loss": 0.4921,
+      "step": 280
+    },
+    {
+      "epoch": 1.614169459071326,
+      "grad_norm": 0.40259426832199097,
+      "learning_rate": 1.0886085959305915e-06,
+      "loss": 0.5068,
+      "step": 281
+    },
+    {
+      "epoch": 1.6199138343705122,
+      "grad_norm": 0.3979838490486145,
+      "learning_rate": 1.057544326129723e-06,
+      "loss": 0.4888,
+      "step": 282
+    },
+    {
+      "epoch": 1.6256582096696985,
+      "grad_norm": 0.39289093017578125,
+      "learning_rate": 1.026877224322923e-06,
+      "loss": 0.5025,
+      "step": 283
+    },
+    {
+      "epoch": 1.6314025849688847,
+      "grad_norm": 0.3723068833351135,
+      "learning_rate": 9.966103799529891e-07,
+      "loss": 0.5262,
+      "step": 284
+    },
+    {
+      "epoch": 1.6371469602680708,
+      "grad_norm": 0.3888184726238251,
+      "learning_rate": 9.66746842140287e-07,
+      "loss": 0.4623,
+      "step": 285
+    },
+    {
+      "epoch": 1.6428913355672572,
+      "grad_norm": 0.38385969400405884,
+      "learning_rate": 9.372896193755621e-07,
+      "loss": 0.4814,
+      "step": 286
+    },
+    {
+      "epoch": 1.6486357108664431,
+      "grad_norm": 0.386476069688797,
+      "learning_rate": 9.082416792168608e-07,
+      "loss": 0.5195,
+      "step": 287
+    },
+    {
+      "epoch": 1.6543800861656295,
+      "grad_norm": 0.3499607741832733,
+      "learning_rate": 8.7960594799059e-07,
+      "loss": 0.4491,
+      "step": 288
+    },
+    {
+      "epoch": 1.6601244614648158,
+      "grad_norm": 0.3445354402065277,
+      "learning_rate": 8.513853104966951e-07,
+      "loss": 0.5042,
+      "step": 289
+    },
+    {
+      "epoch": 1.6658688367640018,
+      "grad_norm": 0.41543084383010864,
+      "learning_rate": 8.235826097180566e-07,
+      "loss": 0.4904,
+      "step": 290
+    },
+    {
+      "epoch": 1.6716132120631881,
+      "grad_norm": 0.40791216492652893,
+      "learning_rate": 7.962006465340821e-07,
+      "loss": 0.4554,
+      "step": 291
+    },
+    {
+      "epoch": 1.6773575873623745,
+      "grad_norm": 0.36069628596305847,
+      "learning_rate": 7.692421794385313e-07,
+      "loss": 0.473,
+      "step": 292
+    },
+    {
+      "epoch": 1.6831019626615604,
+      "grad_norm": 0.44029319286346436,
+      "learning_rate": 7.427099242616348e-07,
+      "loss": 0.5168,
+      "step": 293
+    },
+    {
+      "epoch": 1.6888463379607468,
+      "grad_norm": 0.4227386713027954,
+      "learning_rate": 7.166065538964955e-07,
+      "loss": 0.5405,
+      "step": 294
+    },
+    {
+      "epoch": 1.694590713259933,
+      "grad_norm": 0.37983396649360657,
+      "learning_rate": 6.909346980298093e-07,
+      "loss": 0.4794,
+      "step": 295
+    },
+    {
+      "epoch": 1.700335088559119,
+      "grad_norm": 0.3403533101081848,
+      "learning_rate": 6.656969428769567e-07,
+      "loss": 0.4514,
+      "step": 296
+    },
+    {
+      "epoch": 1.7060794638583054,
+      "grad_norm": 0.3760150372982025,
+      "learning_rate": 6.408958309214597e-07,
+      "loss": 0.4801,
+      "step": 297
+    },
+    {
+      "epoch": 1.7118238391574916,
+      "grad_norm": 0.4047829508781433,
+      "learning_rate": 6.165338606588517e-07,
+      "loss": 0.5115,
+      "step": 298
+    },
+    {
+      "epoch": 1.7175682144566777,
+      "grad_norm": 0.38393792510032654,
+      "learning_rate": 5.926134863449712e-07,
+      "loss": 0.4826,
+      "step": 299
+    },
+    {
+      "epoch": 1.723312589755864,
+      "grad_norm": 0.3590121865272522,
+      "learning_rate": 5.691371177487215e-07,
+      "loss": 0.4491,
+      "step": 300
+    },
+    {
+      "epoch": 1.7290569650550502,
+      "grad_norm": 0.4042126536369324,
+      "learning_rate": 5.461071199093048e-07,
+      "loss": 0.5254,
+      "step": 301
+    },
+    {
+      "epoch": 1.7348013403542364,
+      "grad_norm": 0.3463343381881714,
+      "learning_rate": 5.235258128979676e-07,
+      "loss": 0.4591,
+      "step": 302
+    },
+    {
+      "epoch": 1.7405457156534228,
+      "grad_norm": 0.37464749813079834,
+      "learning_rate": 5.0139547158427e-07,
+      "loss": 0.4621,
+      "step": 303
+    },
+    {
+      "epoch": 1.746290090952609,
+      "grad_norm": 0.386735737323761,
+      "learning_rate": 4.797183254069176e-07,
+      "loss": 0.499,
+      "step": 304
+    },
+    {
+      "epoch": 1.752034466251795,
+      "grad_norm": 0.3763267695903778,
+      "learning_rate": 4.5849655814915683e-07,
+      "loss": 0.5162,
+      "step": 305
+    },
+    {
+      "epoch": 1.7577788415509814,
+      "grad_norm": 0.37057819962501526,
+      "learning_rate": 4.3773230771879004e-07,
+      "loss": 0.4925,
+      "step": 306
+    },
+    {
+      "epoch": 1.7635232168501676,
+      "grad_norm": 0.35524293780326843,
+      "learning_rate": 4.1742766593278974e-07,
+      "loss": 0.4587,
+      "step": 307
+    },
+    {
+      "epoch": 1.7692675921493537,
+      "grad_norm": 0.40347564220428467,
+      "learning_rate": 3.9758467830656623e-07,
+      "loss": 0.5026,
+      "step": 308
+    },
+    {
+      "epoch": 1.77501196744854,
+      "grad_norm": 0.3765867054462433,
+      "learning_rate": 3.782053438479094e-07,
+      "loss": 0.4692,
+      "step": 309
+    },
+    {
+      "epoch": 1.7807563427477262,
+      "grad_norm": 0.35763201117515564,
+      "learning_rate": 3.5929161485559694e-07,
+      "loss": 0.4576,
+      "step": 310
+    },
+    {
+      "epoch": 1.7865007180469124,
+      "grad_norm": 0.4578535556793213,
+      "learning_rate": 3.4084539672271764e-07,
+      "loss": 0.5168,
+      "step": 311
+    },
+    {
+      "epoch": 1.7922450933460987,
+      "grad_norm": 0.36126625537872314,
+      "learning_rate": 3.228685477447291e-07,
+      "loss": 0.4769,
+      "step": 312
+    },
+    {
+      "epoch": 1.7979894686452849,
+      "grad_norm": 0.40714967250823975,
+      "learning_rate": 3.0536287893223603e-07,
+      "loss": 0.4646,
+      "step": 313
+    },
+    {
+      "epoch": 1.803733843944471,
+      "grad_norm": 0.35251492261886597,
+      "learning_rate": 2.883301538285582e-07,
+      "loss": 0.4506,
+      "step": 314
+    },
+    {
+      "epoch": 1.8094782192436574,
+      "grad_norm": 0.36679378151893616,
+      "learning_rate": 2.717720883320685e-07,
+      "loss": 0.4858,
+      "step": 315
+    },
+    {
+      "epoch": 1.8152225945428435,
+      "grad_norm": 0.39732909202575684,
+      "learning_rate": 2.556903505233216e-07,
+      "loss": 0.5302,
+      "step": 316
+    },
+    {
+      "epoch": 1.8209669698420297,
+      "grad_norm": 0.37163034081459045,
+      "learning_rate": 2.4008656049701875e-07,
+      "loss": 0.4868,
+      "step": 317
+    },
+    {
+      "epoch": 1.826711345141216,
+      "grad_norm": 0.37081223726272583,
+      "learning_rate": 2.2496229019879635e-07,
+      "loss": 0.4698,
+      "step": 318
+    },
+    {
+      "epoch": 1.832455720440402,
+      "grad_norm": 0.3732491135597229,
+      "learning_rate": 2.1031906326685946e-07,
+      "loss": 0.4716,
+      "step": 319
+    },
+    {
+      "epoch": 1.8382000957395883,
+      "grad_norm": 0.437520831823349,
+      "learning_rate": 1.9615835487849677e-07,
+      "loss": 0.4804,
+      "step": 320
+    },
+    {
+      "epoch": 1.8439444710387747,
+      "grad_norm": 0.3673948645591736,
+      "learning_rate": 1.824815916014644e-07,
+      "loss": 0.5048,
+      "step": 321
+    },
+    {
+      "epoch": 1.8496888463379606,
+      "grad_norm": 0.3330841064453125,
+      "learning_rate": 1.6929015125027314e-07,
+      "loss": 0.4454,
+      "step": 322
+    },
+    {
+      "epoch": 1.855433221637147,
+      "grad_norm": 0.3728371560573578,
+      "learning_rate": 1.5658536274738623e-07,
+      "loss": 0.5037,
+      "step": 323
+    },
+    {
+      "epoch": 1.8611775969363333,
+      "grad_norm": 0.36687803268432617,
+      "learning_rate": 1.443685059893396e-07,
+      "loss": 0.5074,
+      "step": 324
+    },
+    {
+      "epoch": 1.8669219722355193,
+      "grad_norm": 0.3871447741985321,
+      "learning_rate": 1.3264081171780797e-07,
+      "loss": 0.4878,
+      "step": 325
+    },
+    {
+      "epoch": 1.8726663475347056,
+      "grad_norm": 0.34846240282058716,
+      "learning_rate": 1.2140346139561277e-07,
+      "loss": 0.4694,
+      "step": 326
+    },
+    {
+      "epoch": 1.8784107228338918,
+      "grad_norm": 0.37107598781585693,
+      "learning_rate": 1.1065758708770468e-07,
+      "loss": 0.4856,
+      "step": 327
+    },
+    {
+      "epoch": 1.884155098133078,
+      "grad_norm": 0.38006165623664856,
+      "learning_rate": 1.004042713471165e-07,
+      "loss": 0.5022,
+      "step": 328
+    },
+    {
+      "epoch": 1.8898994734322643,
+      "grad_norm": 0.36080440878868103,
+      "learning_rate": 9.064454710590253e-08,
+      "loss": 0.4619,
+      "step": 329
+    },
+    {
+      "epoch": 1.8956438487314504,
+      "grad_norm": 0.350732684135437,
+      "learning_rate": 8.137939757108526e-08,
+      "loss": 0.4584,
+      "step": 330
+    },
+    {
+      "epoch": 1.9013882240306366,
+      "grad_norm": 0.37510958313941956,
+      "learning_rate": 7.260975612560173e-08,
+      "loss": 0.4813,
+      "step": 331
+    },
+    {
+      "epoch": 1.907132599329823,
+      "grad_norm": 0.3882618844509125,
+      "learning_rate": 6.433650623427379e-08,
+      "loss": 0.4304,
+      "step": 332
+    },
+    {
+      "epoch": 1.912876974629009,
+      "grad_norm": 0.4088869094848633,
+      "learning_rate": 5.6560481354807625e-08,
+      "loss": 0.4624,
+      "step": 333
+    },
+    {
+      "epoch": 1.9186213499281952,
+      "grad_norm": 0.3656178414821625,
+      "learning_rate": 4.928246485383148e-08,
+      "loss": 0.5049,
+      "step": 334
+    },
+    {
+      "epoch": 1.9243657252273816,
+      "grad_norm": 0.39486929774284363,
+      "learning_rate": 4.250318992797375e-08,
+      "loss": 0.5062,
+      "step": 335
+    },
+    {
+      "epoch": 1.9301101005265677,
+      "grad_norm": 0.39059191942214966,
+      "learning_rate": 3.622333953000601e-08,
+      "loss": 0.4485,
+      "step": 336
+    },
+    {
+      "epoch": 1.9358544758257539,
+      "grad_norm": 0.3584195673465729,
+      "learning_rate": 3.0443546300035764e-08,
+      "loss": 0.4358,
+      "step": 337
+    },
+    {
+      "epoch": 1.9415988511249402,
+      "grad_norm": 0.3339657187461853,
+      "learning_rate": 2.516439250177749e-08,
+      "loss": 0.46,
+      "step": 338
+    },
+    {
+      "epoch": 1.9473432264241264,
+      "grad_norm": 0.36130189895629883,
+      "learning_rate": 2.038640996389285e-08,
+      "loss": 0.5263,
+      "step": 339
+    },
+    {
+      "epoch": 1.9530876017233125,
+      "grad_norm": 0.3555588722229004,
+      "learning_rate": 1.6110080026414123e-08,
+      "loss": 0.4882,
+      "step": 340
+    },
+    {
+      "epoch": 1.958831977022499,
+      "grad_norm": 0.38061201572418213,
+      "learning_rate": 1.2335833492252425e-08,
+      "loss": 0.4988,
+      "step": 341
+    },
+    {
+      "epoch": 1.964576352321685,
+      "grad_norm": 0.3624252676963806,
+      "learning_rate": 9.06405058380022e-09,
+      "loss": 0.5049,
+      "step": 342
+    },
+    {
+      "epoch": 1.9703207276208712,
+      "grad_norm": 0.39548906683921814,
+      "learning_rate": 6.295060904623618e-09,
+      "loss": 0.4578,
+      "step": 343
+    },
+    {
+      "epoch": 1.9760651029200575,
+      "grad_norm": 0.37694376707077026,
+      "learning_rate": 4.02914340626226e-09,
+      "loss": 0.4775,
+      "step": 344
+    },
+    {
+      "epoch": 1.9818094782192437,
+      "grad_norm": 0.3581026494503021,
+      "learning_rate": 2.2665263601240328e-09,
+      "loss": 0.491,
+      "step": 345
+    },
+    {
+      "epoch": 1.9875538535184298,
+      "grad_norm": 0.37684017419815063,
+      "learning_rate": 1.0073873344895735e-09,
+      "loss": 0.5071,
+      "step": 346
+    },
+    {
+      "epoch": 1.9932982288176162,
+      "grad_norm": 0.3794161379337311,
+      "learning_rate": 2.5185317662490547e-10,
+      "loss": 0.5096,
+      "step": 347
+    },
+    {
+      "epoch": 1.9990426041168023,
+      "grad_norm": 0.35005468130111694,
+      "learning_rate": 0.0,
+      "loss": 0.436,
+      "step": 348
+    },
+    {
+      "epoch": 1.9990426041168023,
+      "step": 348,
+      "total_flos": 358710641426432.0,
+      "train_loss": 0.5378552473139488,
+      "train_runtime": 32465.3196,
+      "train_samples_per_second": 1.029,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 348,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 358710641426432.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7c7a0d4e1b7bbeb53817c80c5e006deb6ba490db92dc382b4091ac872ee332
+size 7416