Model save

.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: apache-2.0
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: r1_annotated_finqa
+  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. -->
+
+# r1_annotated_finqa
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 96
+- total_eval_batch_size: 256
+- optimizer: Use OptimizerNames.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: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1
+- Datasets 3.0.2
+- 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": 6.955414012738854,
+    "total_flos": 1.6645198251751014e+17,
+    "train_loss": 0.0,
+    "train_runtime": 5.2904,
+    "train_samples_per_second": 6615.788,
+    "train_steps_per_second": 68.804
+}

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 sha256:46ecc2d0ea36f4ef1c87a5c72162ab728ffbf9e81fde28271887b5ad16e4b34f
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03bb62a4f5f0a47f2edef6fd31468fcc82afc6fadfc47d7ae46ac853cb8a836
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad929b7ecd859bc057980f89ca6ba5e6ab0f8629068b09df6b3d8f6bc3145317
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9b59d81b1523c220fa8fbe9c7ece01ac898a8e26e2bdd3c62ba126c2d39afa
+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": 6.955414012738854,
+    "total_flos": 1.6645198251751014e+17,
+    "train_loss": 0.0,
+    "train_runtime": 5.2904,
+    "train_samples_per_second": 6615.788,
+    "train_steps_per_second": 68.804
+}

trainer_log.jsonl

@@ -0,0 +1,367 @@
+{"current_steps": 1, "total_steps": 364, "loss": 1.1132, "lr": 5.405405405405406e-07, "epoch": 0.01910828025477707, "percentage": 0.27, "elapsed_time": "0:00:09", "remaining_time": "0:54:36"}
+{"current_steps": 2, "total_steps": 364, "loss": 1.1203, "lr": 1.0810810810810812e-06, "epoch": 0.03821656050955414, "percentage": 0.55, "elapsed_time": "0:00:14", "remaining_time": "0:43:38"}
+{"current_steps": 3, "total_steps": 364, "loss": 1.072, "lr": 1.6216216216216219e-06, "epoch": 0.05732484076433121, "percentage": 0.82, "elapsed_time": "0:00:19", "remaining_time": "0:38:08"}
+{"current_steps": 4, "total_steps": 364, "loss": 1.0972, "lr": 2.1621621621621623e-06, "epoch": 0.07643312101910828, "percentage": 1.1, "elapsed_time": "0:00:22", "remaining_time": "0:34:13"}
+{"current_steps": 5, "total_steps": 364, "loss": 1.0656, "lr": 2.702702702702703e-06, "epoch": 0.09554140127388536, "percentage": 1.37, "elapsed_time": "0:00:26", "remaining_time": "0:31:58"}
+{"current_steps": 6, "total_steps": 364, "loss": 0.9882, "lr": 3.2432432432432437e-06, "epoch": 0.11464968152866242, "percentage": 1.65, "elapsed_time": "0:00:31", "remaining_time": "0:30:55"}
+{"current_steps": 7, "total_steps": 364, "loss": 0.8802, "lr": 3.7837837837837844e-06, "epoch": 0.1337579617834395, "percentage": 1.92, "elapsed_time": "0:00:35", "remaining_time": "0:30:34"}
+{"current_steps": 8, "total_steps": 364, "loss": 0.837, "lr": 4.324324324324325e-06, "epoch": 0.15286624203821655, "percentage": 2.2, "elapsed_time": "0:00:40", "remaining_time": "0:29:57"}
+{"current_steps": 9, "total_steps": 364, "loss": 0.8174, "lr": 4.864864864864866e-06, "epoch": 0.17197452229299362, "percentage": 2.47, "elapsed_time": "0:00:44", "remaining_time": "0:29:07"}
+{"current_steps": 10, "total_steps": 364, "loss": 0.7624, "lr": 5.405405405405406e-06, "epoch": 0.1910828025477707, "percentage": 2.75, "elapsed_time": "0:00:48", "remaining_time": "0:28:51"}
+{"current_steps": 11, "total_steps": 364, "loss": 0.7111, "lr": 5.945945945945947e-06, "epoch": 0.21019108280254778, "percentage": 3.02, "elapsed_time": "0:00:53", "remaining_time": "0:28:20"}
+{"current_steps": 12, "total_steps": 364, "loss": 0.6858, "lr": 6.486486486486487e-06, "epoch": 0.22929936305732485, "percentage": 3.3, "elapsed_time": "0:00:57", "remaining_time": "0:28:01"}
+{"current_steps": 13, "total_steps": 364, "loss": 0.61, "lr": 7.027027027027028e-06, "epoch": 0.2484076433121019, "percentage": 3.57, "elapsed_time": "0:01:03", "remaining_time": "0:28:36"}
+{"current_steps": 14, "total_steps": 364, "loss": 0.5898, "lr": 7.567567567567569e-06, "epoch": 0.267515923566879, "percentage": 3.85, "elapsed_time": "0:01:07", "remaining_time": "0:28:08"}
+{"current_steps": 15, "total_steps": 364, "loss": 0.5504, "lr": 8.108108108108109e-06, "epoch": 0.28662420382165604, "percentage": 4.12, "elapsed_time": "0:01:11", "remaining_time": "0:27:36"}
+{"current_steps": 16, "total_steps": 364, "loss": 0.541, "lr": 8.64864864864865e-06, "epoch": 0.3057324840764331, "percentage": 4.4, "elapsed_time": "0:01:15", "remaining_time": "0:27:26"}
+{"current_steps": 17, "total_steps": 364, "loss": 0.5369, "lr": 9.189189189189191e-06, "epoch": 0.3248407643312102, "percentage": 4.67, "elapsed_time": "0:01:21", "remaining_time": "0:27:40"}
+{"current_steps": 18, "total_steps": 364, "loss": 0.5146, "lr": 9.729729729729732e-06, "epoch": 0.34394904458598724, "percentage": 4.95, "elapsed_time": "0:01:25", "remaining_time": "0:27:24"}
+{"current_steps": 19, "total_steps": 364, "loss": 0.5047, "lr": 1.027027027027027e-05, "epoch": 0.3630573248407643, "percentage": 5.22, "elapsed_time": "0:01:29", "remaining_time": "0:27:04"}
+{"current_steps": 20, "total_steps": 364, "loss": 0.5, "lr": 1.0810810810810812e-05, "epoch": 0.3821656050955414, "percentage": 5.49, "elapsed_time": "0:01:33", "remaining_time": "0:26:45"}
+{"current_steps": 21, "total_steps": 364, "loss": 0.5057, "lr": 1.1351351351351352e-05, "epoch": 0.4012738853503185, "percentage": 5.77, "elapsed_time": "0:01:39", "remaining_time": "0:27:03"}
+{"current_steps": 22, "total_steps": 364, "loss": 0.483, "lr": 1.1891891891891894e-05, "epoch": 0.42038216560509556, "percentage": 6.04, "elapsed_time": "0:01:44", "remaining_time": "0:27:07"}
+{"current_steps": 23, "total_steps": 364, "loss": 0.4743, "lr": 1.2432432432432433e-05, "epoch": 0.4394904458598726, "percentage": 6.32, "elapsed_time": "0:01:49", "remaining_time": "0:26:58"}
+{"current_steps": 24, "total_steps": 364, "loss": 0.4617, "lr": 1.2972972972972975e-05, "epoch": 0.4585987261146497, "percentage": 6.59, "elapsed_time": "0:01:53", "remaining_time": "0:26:43"}
+{"current_steps": 25, "total_steps": 364, "loss": 0.4761, "lr": 1.3513513513513515e-05, "epoch": 0.47770700636942676, "percentage": 6.87, "elapsed_time": "0:01:57", "remaining_time": "0:26:34"}
+{"current_steps": 26, "total_steps": 364, "loss": 0.4266, "lr": 1.4054054054054055e-05, "epoch": 0.4968152866242038, "percentage": 7.14, "elapsed_time": "0:02:01", "remaining_time": "0:26:24"}
+{"current_steps": 27, "total_steps": 364, "loss": 0.4683, "lr": 1.4594594594594596e-05, "epoch": 0.5159235668789809, "percentage": 7.42, "elapsed_time": "0:02:06", "remaining_time": "0:26:15"}
+{"current_steps": 28, "total_steps": 364, "loss": 0.4009, "lr": 1.5135135135135138e-05, "epoch": 0.535031847133758, "percentage": 7.69, "elapsed_time": "0:02:10", "remaining_time": "0:26:09"}
+{"current_steps": 29, "total_steps": 364, "loss": 0.4609, "lr": 1.5675675675675676e-05, "epoch": 0.554140127388535, "percentage": 7.97, "elapsed_time": "0:02:15", "remaining_time": "0:26:05"}
+{"current_steps": 30, "total_steps": 364, "loss": 0.4173, "lr": 1.6216216216216218e-05, "epoch": 0.5732484076433121, "percentage": 8.24, "elapsed_time": "0:02:20", "remaining_time": "0:25:58"}
+{"current_steps": 31, "total_steps": 364, "loss": 0.4311, "lr": 1.6756756756756757e-05, "epoch": 0.5923566878980892, "percentage": 8.52, "elapsed_time": "0:02:24", "remaining_time": "0:25:57"}
+{"current_steps": 32, "total_steps": 364, "loss": 0.4295, "lr": 1.72972972972973e-05, "epoch": 0.6114649681528662, "percentage": 8.79, "elapsed_time": "0:02:28", "remaining_time": "0:25:45"}
+{"current_steps": 33, "total_steps": 364, "loss": 0.4211, "lr": 1.783783783783784e-05, "epoch": 0.6305732484076433, "percentage": 9.07, "elapsed_time": "0:02:33", "remaining_time": "0:25:37"}
+{"current_steps": 34, "total_steps": 364, "loss": 0.4391, "lr": 1.8378378378378383e-05, "epoch": 0.6496815286624203, "percentage": 9.34, "elapsed_time": "0:02:37", "remaining_time": "0:25:27"}
+{"current_steps": 35, "total_steps": 364, "loss": 0.4556, "lr": 1.891891891891892e-05, "epoch": 0.6687898089171974, "percentage": 9.62, "elapsed_time": "0:02:41", "remaining_time": "0:25:21"}
+{"current_steps": 36, "total_steps": 364, "loss": 0.4296, "lr": 1.9459459459459463e-05, "epoch": 0.6878980891719745, "percentage": 9.89, "elapsed_time": "0:02:45", "remaining_time": "0:25:08"}
+{"current_steps": 37, "total_steps": 364, "loss": 0.4189, "lr": 2e-05, "epoch": 0.7070063694267515, "percentage": 10.16, "elapsed_time": "0:02:50", "remaining_time": "0:25:10"}
+{"current_steps": 38, "total_steps": 364, "loss": 0.4141, "lr": 1.9999538500851633e-05, "epoch": 0.7261146496815286, "percentage": 10.44, "elapsed_time": "0:02:55", "remaining_time": "0:25:05"}
+{"current_steps": 39, "total_steps": 364, "loss": 0.4248, "lr": 1.9998154046002822e-05, "epoch": 0.7452229299363057, "percentage": 10.71, "elapsed_time": "0:03:03", "remaining_time": "0:25:31"}
+{"current_steps": 40, "total_steps": 364, "loss": 0.4054, "lr": 1.9995846763238514e-05, "epoch": 0.7643312101910829, "percentage": 10.99, "elapsed_time": "0:03:08", "remaining_time": "0:25:24"}
+{"current_steps": 41, "total_steps": 364, "loss": 0.3879, "lr": 1.9992616865520515e-05, "epoch": 0.7834394904458599, "percentage": 11.26, "elapsed_time": "0:03:12", "remaining_time": "0:25:18"}
+{"current_steps": 42, "total_steps": 364, "loss": 0.4109, "lr": 1.9988464650967834e-05, "epoch": 0.802547770700637, "percentage": 11.54, "elapsed_time": "0:03:16", "remaining_time": "0:25:09"}
+{"current_steps": 43, "total_steps": 364, "loss": 0.3974, "lr": 1.9983390502829168e-05, "epoch": 0.821656050955414, "percentage": 11.81, "elapsed_time": "0:03:20", "remaining_time": "0:24:56"}
+{"current_steps": 44, "total_steps": 364, "loss": 0.3866, "lr": 1.9977394889447526e-05, "epoch": 0.8407643312101911, "percentage": 12.09, "elapsed_time": "0:03:24", "remaining_time": "0:24:49"}
+{"current_steps": 45, "total_steps": 364, "loss": 0.3965, "lr": 1.9970478364217e-05, "epoch": 0.8598726114649682, "percentage": 12.36, "elapsed_time": "0:03:29", "remaining_time": "0:24:45"}
+{"current_steps": 46, "total_steps": 364, "loss": 0.3955, "lr": 1.9962641565531694e-05, "epoch": 0.8789808917197452, "percentage": 12.64, "elapsed_time": "0:03:33", "remaining_time": "0:24:37"}
+{"current_steps": 47, "total_steps": 364, "loss": 0.4011, "lr": 1.9953885216726788e-05, "epoch": 0.8980891719745223, "percentage": 12.91, "elapsed_time": "0:03:39", "remaining_time": "0:24:41"}
+{"current_steps": 48, "total_steps": 364, "loss": 0.3994, "lr": 1.994421012601179e-05, "epoch": 0.9171974522292994, "percentage": 13.19, "elapsed_time": "0:03:43", "remaining_time": "0:24:32"}
+{"current_steps": 49, "total_steps": 364, "loss": 0.3816, "lr": 1.9933617186395917e-05, "epoch": 0.9363057324840764, "percentage": 13.46, "elapsed_time": "0:03:48", "remaining_time": "0:24:26"}
+{"current_steps": 50, "total_steps": 364, "loss": 0.4186, "lr": 1.99221073756057e-05, "epoch": 0.9554140127388535, "percentage": 13.74, "elapsed_time": "0:03:52", "remaining_time": "0:24:23"}
+{"current_steps": 51, "total_steps": 364, "loss": 0.4176, "lr": 1.990968175599471e-05, "epoch": 0.9745222929936306, "percentage": 14.01, "elapsed_time": "0:03:58", "remaining_time": "0:24:23"}
+{"current_steps": 52, "total_steps": 364, "loss": 0.3976, "lr": 1.9896341474445526e-05, "epoch": 0.9936305732484076, "percentage": 14.29, "elapsed_time": "0:04:02", "remaining_time": "0:24:17"}
+{"current_steps": 53, "total_steps": 364, "loss": 0.3684, "lr": 1.9882087762263857e-05, "epoch": 1.0127388535031847, "percentage": 14.56, "elapsed_time": "0:05:57", "remaining_time": "0:34:55"}
+{"current_steps": 54, "total_steps": 364, "loss": 0.332, "lr": 1.9866921935064907e-05, "epoch": 1.0318471337579618, "percentage": 14.84, "elapsed_time": "0:06:01", "remaining_time": "0:34:34"}
+{"current_steps": 55, "total_steps": 364, "loss": 0.3523, "lr": 1.985084539265195e-05, "epoch": 1.0509554140127388, "percentage": 15.11, "elapsed_time": "0:06:06", "remaining_time": "0:34:19"}
+{"current_steps": 56, "total_steps": 364, "loss": 0.3353, "lr": 1.983385961888711e-05, "epoch": 1.070063694267516, "percentage": 15.38, "elapsed_time": "0:06:11", "remaining_time": "0:34:02"}
+{"current_steps": 57, "total_steps": 364, "loss": 0.3593, "lr": 1.9815966181554412e-05, "epoch": 1.089171974522293, "percentage": 15.66, "elapsed_time": "0:06:16", "remaining_time": "0:33:45"}
+{"current_steps": 58, "total_steps": 364, "loss": 0.3042, "lr": 1.9797166732215078e-05, "epoch": 1.10828025477707, "percentage": 15.93, "elapsed_time": "0:06:20", "remaining_time": "0:33:25"}
+{"current_steps": 59, "total_steps": 364, "loss": 0.3179, "lr": 1.977746300605507e-05, "epoch": 1.127388535031847, "percentage": 16.21, "elapsed_time": "0:06:24", "remaining_time": "0:33:07"}
+{"current_steps": 60, "total_steps": 364, "loss": 0.3195, "lr": 1.975685682172497e-05, "epoch": 1.1464968152866242, "percentage": 16.48, "elapsed_time": "0:06:28", "remaining_time": "0:32:50"}
+{"current_steps": 61, "total_steps": 364, "loss": 0.3361, "lr": 1.973535008117207e-05, "epoch": 1.1656050955414012, "percentage": 16.76, "elapsed_time": "0:06:34", "remaining_time": "0:32:39"}
+{"current_steps": 62, "total_steps": 364, "loss": 0.3151, "lr": 1.9712944769464864e-05, "epoch": 1.1847133757961783, "percentage": 17.03, "elapsed_time": "0:06:38", "remaining_time": "0:32:18"}
+{"current_steps": 63, "total_steps": 364, "loss": 0.3288, "lr": 1.9689642954609808e-05, "epoch": 1.2038216560509554, "percentage": 17.31, "elapsed_time": "0:06:42", "remaining_time": "0:32:03"}
+{"current_steps": 64, "total_steps": 364, "loss": 0.3403, "lr": 1.9665446787360444e-05, "epoch": 1.2229299363057324, "percentage": 17.58, "elapsed_time": "0:06:46", "remaining_time": "0:31:46"}
+{"current_steps": 65, "total_steps": 364, "loss": 0.3093, "lr": 1.9640358501018885e-05, "epoch": 1.2420382165605095, "percentage": 17.86, "elapsed_time": "0:06:51", "remaining_time": "0:31:32"}
+{"current_steps": 66, "total_steps": 364, "loss": 0.3077, "lr": 1.9614380411229693e-05, "epoch": 1.2611464968152866, "percentage": 18.13, "elapsed_time": "0:06:55", "remaining_time": "0:31:13"}
+{"current_steps": 67, "total_steps": 364, "loss": 0.3222, "lr": 1.9587514915766124e-05, "epoch": 1.2802547770700636, "percentage": 18.41, "elapsed_time": "0:06:59", "remaining_time": "0:30:59"}
+{"current_steps": 68, "total_steps": 364, "loss": 0.304, "lr": 1.9559764494308838e-05, "epoch": 1.2993630573248407, "percentage": 18.68, "elapsed_time": "0:07:03", "remaining_time": "0:30:42"}
+{"current_steps": 69, "total_steps": 364, "loss": 0.3404, "lr": 1.9531131708217005e-05, "epoch": 1.3184713375796178, "percentage": 18.96, "elapsed_time": "0:07:09", "remaining_time": "0:30:34"}
+{"current_steps": 70, "total_steps": 364, "loss": 0.3178, "lr": 1.950161920029191e-05, "epoch": 1.3375796178343948, "percentage": 19.23, "elapsed_time": "0:07:13", "remaining_time": "0:30:18"}
+{"current_steps": 71, "total_steps": 364, "loss": 0.3179, "lr": 1.9471229694533003e-05, "epoch": 1.356687898089172, "percentage": 19.51, "elapsed_time": "0:07:17", "remaining_time": "0:30:04"}
+{"current_steps": 72, "total_steps": 364, "loss": 0.3393, "lr": 1.943996599588649e-05, "epoch": 1.3757961783439492, "percentage": 19.78, "elapsed_time": "0:07:22", "remaining_time": "0:29:56"}
+{"current_steps": 73, "total_steps": 364, "loss": 0.3292, "lr": 1.940783098998643e-05, "epoch": 1.394904458598726, "percentage": 20.05, "elapsed_time": "0:07:27", "remaining_time": "0:29:42"}
+{"current_steps": 74, "total_steps": 364, "loss": 0.304, "lr": 1.93748276428884e-05, "epoch": 1.4140127388535033, "percentage": 20.33, "elapsed_time": "0:07:30", "remaining_time": "0:29:26"}
+{"current_steps": 75, "total_steps": 364, "loss": 0.2991, "lr": 1.9340959000795707e-05, "epoch": 1.4331210191082802, "percentage": 20.6, "elapsed_time": "0:07:35", "remaining_time": "0:29:13"}
+{"current_steps": 76, "total_steps": 364, "loss": 0.3389, "lr": 1.9306228189778255e-05, "epoch": 1.4522292993630574, "percentage": 20.88, "elapsed_time": "0:07:40", "remaining_time": "0:29:03"}
+{"current_steps": 77, "total_steps": 364, "loss": 0.3287, "lr": 1.927063841548398e-05, "epoch": 1.4713375796178343, "percentage": 21.15, "elapsed_time": "0:07:44", "remaining_time": "0:28:50"}
+{"current_steps": 78, "total_steps": 364, "loss": 0.3171, "lr": 1.9234192962842996e-05, "epoch": 1.4904458598726116, "percentage": 21.43, "elapsed_time": "0:07:48", "remaining_time": "0:28:38"}
+{"current_steps": 79, "total_steps": 364, "loss": 0.3211, "lr": 1.9196895195764363e-05, "epoch": 1.5095541401273884, "percentage": 21.7, "elapsed_time": "0:07:53", "remaining_time": "0:28:28"}
+{"current_steps": 80, "total_steps": 364, "loss": 0.3178, "lr": 1.9158748556825637e-05, "epoch": 1.5286624203821657, "percentage": 21.98, "elapsed_time": "0:07:57", "remaining_time": "0:28:16"}
+{"current_steps": 81, "total_steps": 364, "loss": 0.3292, "lr": 1.9119756566955092e-05, "epoch": 1.5477707006369426, "percentage": 22.25, "elapsed_time": "0:08:03", "remaining_time": "0:28:08"}
+{"current_steps": 82, "total_steps": 364, "loss": 0.3301, "lr": 1.907992282510675e-05, "epoch": 1.5668789808917198, "percentage": 22.53, "elapsed_time": "0:08:07", "remaining_time": "0:27:57"}
+{"current_steps": 83, "total_steps": 364, "loss": 0.3269, "lr": 1.90392510079282e-05, "epoch": 1.5859872611464967, "percentage": 22.8, "elapsed_time": "0:08:11", "remaining_time": "0:27:44"}
+{"current_steps": 84, "total_steps": 364, "loss": 0.3106, "lr": 1.8997744869421248e-05, "epoch": 1.605095541401274, "percentage": 23.08, "elapsed_time": "0:08:15", "remaining_time": "0:27:32"}
+{"current_steps": 85, "total_steps": 364, "loss": 0.2997, "lr": 1.8955408240595396e-05, "epoch": 1.6242038216560508, "percentage": 23.35, "elapsed_time": "0:08:19", "remaining_time": "0:27:18"}
+{"current_steps": 86, "total_steps": 364, "loss": 0.3, "lr": 1.891224502911428e-05, "epoch": 1.643312101910828, "percentage": 23.63, "elapsed_time": "0:08:22", "remaining_time": "0:27:05"}
+{"current_steps": 87, "total_steps": 364, "loss": 0.3277, "lr": 1.886825921893497e-05, "epoch": 1.662420382165605, "percentage": 23.9, "elapsed_time": "0:08:28", "remaining_time": "0:27:00"}
+{"current_steps": 88, "total_steps": 364, "loss": 0.3143, "lr": 1.8823454869940243e-05, "epoch": 1.6815286624203822, "percentage": 24.18, "elapsed_time": "0:08:33", "remaining_time": "0:26:51"}
+{"current_steps": 89, "total_steps": 364, "loss": 0.331, "lr": 1.8777836117563894e-05, "epoch": 1.700636942675159, "percentage": 24.45, "elapsed_time": "0:08:38", "remaining_time": "0:26:42"}
+{"current_steps": 90, "total_steps": 364, "loss": 0.3243, "lr": 1.873140717240899e-05, "epoch": 1.7197452229299364, "percentage": 24.73, "elapsed_time": "0:08:44", "remaining_time": "0:26:36"}
+{"current_steps": 91, "total_steps": 364, "loss": 0.3144, "lr": 1.8684172319859258e-05, "epoch": 1.7388535031847132, "percentage": 25.0, "elapsed_time": "0:08:48", "remaining_time": "0:26:25"}
+{"current_steps": 92, "total_steps": 364, "loss": 0.3367, "lr": 1.863613591968355e-05, "epoch": 1.7579617834394905, "percentage": 25.27, "elapsed_time": "0:08:53", "remaining_time": "0:26:16"}
+{"current_steps": 93, "total_steps": 364, "loss": 0.3234, "lr": 1.858730240563342e-05, "epoch": 1.7770700636942676, "percentage": 25.55, "elapsed_time": "0:08:57", "remaining_time": "0:26:07"}
+{"current_steps": 94, "total_steps": 364, "loss": 0.3118, "lr": 1.8537676285033886e-05, "epoch": 1.7961783439490446, "percentage": 25.82, "elapsed_time": "0:09:01", "remaining_time": "0:25:55"}
+{"current_steps": 95, "total_steps": 364, "loss": 0.3153, "lr": 1.848726213836744e-05, "epoch": 1.8152866242038217, "percentage": 26.1, "elapsed_time": "0:09:05", "remaining_time": "0:25:44"}
+{"current_steps": 96, "total_steps": 364, "loss": 0.3233, "lr": 1.8436064618851225e-05, "epoch": 1.8343949044585988, "percentage": 26.37, "elapsed_time": "0:09:09", "remaining_time": "0:25:33"}
+{"current_steps": 97, "total_steps": 364, "loss": 0.3059, "lr": 1.838408845200758e-05, "epoch": 1.8535031847133758, "percentage": 26.65, "elapsed_time": "0:09:13", "remaining_time": "0:25:24"}
+{"current_steps": 98, "total_steps": 364, "loss": 0.3112, "lr": 1.8331338435227838e-05, "epoch": 1.872611464968153, "percentage": 26.92, "elapsed_time": "0:09:17", "remaining_time": "0:25:13"}
+{"current_steps": 99, "total_steps": 364, "loss": 0.3312, "lr": 1.8277819437329577e-05, "epoch": 1.89171974522293, "percentage": 27.2, "elapsed_time": "0:09:22", "remaining_time": "0:25:06"}
+{"current_steps": 100, "total_steps": 364, "loss": 0.3118, "lr": 1.8223536398107177e-05, "epoch": 1.910828025477707, "percentage": 27.47, "elapsed_time": "0:09:26", "remaining_time": "0:24:56"}
+{"current_steps": 101, "total_steps": 364, "loss": 0.3129, "lr": 1.8168494327875918e-05, "epoch": 1.929936305732484, "percentage": 27.75, "elapsed_time": "0:09:35", "remaining_time": "0:24:57"}
+{"current_steps": 102, "total_steps": 364, "loss": 0.3359, "lr": 1.8112698307009506e-05, "epoch": 1.9490445859872612, "percentage": 28.02, "elapsed_time": "0:09:39", "remaining_time": "0:24:47"}
+{"current_steps": 103, "total_steps": 364, "loss": 0.322, "lr": 1.8056153485471167e-05, "epoch": 1.9681528662420382, "percentage": 28.3, "elapsed_time": "0:09:43", "remaining_time": "0:24:38"}
+{"current_steps": 104, "total_steps": 364, "loss": 0.3032, "lr": 1.799886508233829e-05, "epoch": 1.9872611464968153, "percentage": 28.57, "elapsed_time": "0:09:47", "remaining_time": "0:24:28"}
+{"current_steps": 105, "total_steps": 364, "loss": 0.2791, "lr": 1.7940838385320732e-05, "epoch": 2.0063694267515926, "percentage": 28.85, "elapsed_time": "0:11:33", "remaining_time": "0:28:31"}
+{"current_steps": 106, "total_steps": 364, "loss": 0.2362, "lr": 1.788207875027274e-05, "epoch": 2.0254777070063694, "percentage": 29.12, "elapsed_time": "0:11:39", "remaining_time": "0:28:22"}
+{"current_steps": 107, "total_steps": 364, "loss": 0.2282, "lr": 1.7822591600698632e-05, "epoch": 2.0445859872611467, "percentage": 29.4, "elapsed_time": "0:11:43", "remaining_time": "0:28:09"}
+{"current_steps": 108, "total_steps": 364, "loss": 0.229, "lr": 1.776238242725217e-05, "epoch": 2.0636942675159236, "percentage": 29.67, "elapsed_time": "0:11:47", "remaining_time": "0:27:57"}
+{"current_steps": 109, "total_steps": 364, "loss": 0.2259, "lr": 1.7701456787229805e-05, "epoch": 2.082802547770701, "percentage": 29.95, "elapsed_time": "0:11:51", "remaining_time": "0:27:44"}
+{"current_steps": 110, "total_steps": 364, "loss": 0.2335, "lr": 1.7639820304057745e-05, "epoch": 2.1019108280254777, "percentage": 30.22, "elapsed_time": "0:11:56", "remaining_time": "0:27:33"}
+{"current_steps": 111, "total_steps": 364, "loss": 0.2392, "lr": 1.7577478666772886e-05, "epoch": 2.121019108280255, "percentage": 30.49, "elapsed_time": "0:12:00", "remaining_time": "0:27:22"}
+{"current_steps": 112, "total_steps": 364, "loss": 0.218, "lr": 1.751443762949772e-05, "epoch": 2.140127388535032, "percentage": 30.77, "elapsed_time": "0:12:04", "remaining_time": "0:27:10"}
+{"current_steps": 113, "total_steps": 364, "loss": 0.2299, "lr": 1.7450703010909263e-05, "epoch": 2.159235668789809, "percentage": 31.04, "elapsed_time": "0:12:08", "remaining_time": "0:26:58"}
+{"current_steps": 114, "total_steps": 364, "loss": 0.2148, "lr": 1.738628069370195e-05, "epoch": 2.178343949044586, "percentage": 31.32, "elapsed_time": "0:12:13", "remaining_time": "0:26:47"}
+{"current_steps": 115, "total_steps": 364, "loss": 0.2192, "lr": 1.732117662404469e-05, "epoch": 2.1974522292993632, "percentage": 31.59, "elapsed_time": "0:12:17", "remaining_time": "0:26:36"}
+{"current_steps": 116, "total_steps": 364, "loss": 0.207, "lr": 1.7255396811032014e-05, "epoch": 2.21656050955414, "percentage": 31.87, "elapsed_time": "0:12:21", "remaining_time": "0:26:25"}
+{"current_steps": 117, "total_steps": 364, "loss": 0.2189, "lr": 1.718894732612947e-05, "epoch": 2.2356687898089174, "percentage": 32.14, "elapsed_time": "0:12:25", "remaining_time": "0:26:13"}
+{"current_steps": 118, "total_steps": 364, "loss": 0.2242, "lr": 1.712183430261319e-05, "epoch": 2.254777070063694, "percentage": 32.42, "elapsed_time": "0:12:29", "remaining_time": "0:26:03"}
+{"current_steps": 119, "total_steps": 364, "loss": 0.2164, "lr": 1.7054063935003813e-05, "epoch": 2.2738853503184715, "percentage": 32.69, "elapsed_time": "0:12:34", "remaining_time": "0:25:53"}
+{"current_steps": 120, "total_steps": 364, "loss": 0.2326, "lr": 1.698564247849473e-05, "epoch": 2.2929936305732483, "percentage": 32.97, "elapsed_time": "0:12:39", "remaining_time": "0:25:43"}
+{"current_steps": 121, "total_steps": 364, "loss": 0.2085, "lr": 1.691657624837472e-05, "epoch": 2.3121019108280256, "percentage": 33.24, "elapsed_time": "0:12:43", "remaining_time": "0:25:33"}
+{"current_steps": 122, "total_steps": 364, "loss": 0.1972, "lr": 1.684687161944506e-05, "epoch": 2.3312101910828025, "percentage": 33.52, "elapsed_time": "0:12:47", "remaining_time": "0:25:22"}
+{"current_steps": 123, "total_steps": 364, "loss": 0.2213, "lr": 1.677653502543113e-05, "epoch": 2.3503184713375798, "percentage": 33.79, "elapsed_time": "0:12:51", "remaining_time": "0:25:10"}
+{"current_steps": 124, "total_steps": 364, "loss": 0.1919, "lr": 1.6705572958388576e-05, "epoch": 2.3694267515923566, "percentage": 34.07, "elapsed_time": "0:12:55", "remaining_time": "0:25:00"}
+{"current_steps": 125, "total_steps": 364, "loss": 0.223, "lr": 1.6633991968104095e-05, "epoch": 2.388535031847134, "percentage": 34.34, "elapsed_time": "0:12:59", "remaining_time": "0:24:49"}
+{"current_steps": 126, "total_steps": 364, "loss": 0.232, "lr": 1.6561798661490904e-05, "epoch": 2.4076433121019107, "percentage": 34.62, "elapsed_time": "0:13:07", "remaining_time": "0:24:48"}
+{"current_steps": 127, "total_steps": 364, "loss": 0.2398, "lr": 1.6488999701978905e-05, "epoch": 2.426751592356688, "percentage": 34.89, "elapsed_time": "0:13:13", "remaining_time": "0:24:40"}
+{"current_steps": 128, "total_steps": 364, "loss": 0.2201, "lr": 1.6415601808899658e-05, "epoch": 2.445859872611465, "percentage": 35.16, "elapsed_time": "0:13:17", "remaining_time": "0:24:30"}
+{"current_steps": 129, "total_steps": 364, "loss": 0.23, "lr": 1.63416117568662e-05, "epoch": 2.464968152866242, "percentage": 35.44, "elapsed_time": "0:13:22", "remaining_time": "0:24:21"}
+{"current_steps": 130, "total_steps": 364, "loss": 0.2104, "lr": 1.6267036375147728e-05, "epoch": 2.484076433121019, "percentage": 35.71, "elapsed_time": "0:13:27", "remaining_time": "0:24:12"}
+{"current_steps": 131, "total_steps": 364, "loss": 0.2196, "lr": 1.619188254703927e-05, "epoch": 2.5031847133757963, "percentage": 35.99, "elapsed_time": "0:13:31", "remaining_time": "0:24:02"}
+{"current_steps": 132, "total_steps": 364, "loss": 0.219, "lr": 1.6116157209226356e-05, "epoch": 2.522292993630573, "percentage": 36.26, "elapsed_time": "0:13:36", "remaining_time": "0:23:55"}
+{"current_steps": 133, "total_steps": 364, "loss": 0.2087, "lr": 1.6039867351144778e-05, "epoch": 2.5414012738853504, "percentage": 36.54, "elapsed_time": "0:13:42", "remaining_time": "0:23:48"}
+{"current_steps": 134, "total_steps": 364, "loss": 0.2061, "lr": 1.5963020014335437e-05, "epoch": 2.5605095541401273, "percentage": 36.81, "elapsed_time": "0:13:46", "remaining_time": "0:23:39"}
+{"current_steps": 135, "total_steps": 364, "loss": 0.2488, "lr": 1.588562229179443e-05, "epoch": 2.5796178343949046, "percentage": 37.09, "elapsed_time": "0:13:51", "remaining_time": "0:23:30"}
+{"current_steps": 136, "total_steps": 364, "loss": 0.2078, "lr": 1.5807681327318372e-05, "epoch": 2.5987261146496814, "percentage": 37.36, "elapsed_time": "0:13:55", "remaining_time": "0:23:21"}
+{"current_steps": 137, "total_steps": 364, "loss": 0.2356, "lr": 1.5729204314845002e-05, "epoch": 2.6178343949044587, "percentage": 37.64, "elapsed_time": "0:14:00", "remaining_time": "0:23:12"}
+{"current_steps": 138, "total_steps": 364, "loss": 0.2237, "lr": 1.56501984977892e-05, "epoch": 2.6369426751592355, "percentage": 37.91, "elapsed_time": "0:14:04", "remaining_time": "0:23:03"}
+{"current_steps": 139, "total_steps": 364, "loss": 0.2207, "lr": 1.557067116837444e-05, "epoch": 2.656050955414013, "percentage": 38.19, "elapsed_time": "0:14:08", "remaining_time": "0:22:53"}
+{"current_steps": 140, "total_steps": 364, "loss": 0.2186, "lr": 1.5490629666959668e-05, "epoch": 2.6751592356687897, "percentage": 38.46, "elapsed_time": "0:14:11", "remaining_time": "0:22:43"}
+{"current_steps": 141, "total_steps": 364, "loss": 0.2317, "lr": 1.541008138136183e-05, "epoch": 2.694267515923567, "percentage": 38.74, "elapsed_time": "0:14:16", "remaining_time": "0:22:33"}
+{"current_steps": 142, "total_steps": 364, "loss": 0.2356, "lr": 1.5329033746173975e-05, "epoch": 2.713375796178344, "percentage": 39.01, "elapsed_time": "0:14:20", "remaining_time": "0:22:26"}
+{"current_steps": 143, "total_steps": 364, "loss": 0.2492, "lr": 1.5247494242079024e-05, "epoch": 2.732484076433121, "percentage": 39.29, "elapsed_time": "0:14:25", "remaining_time": "0:22:17"}
+{"current_steps": 144, "total_steps": 364, "loss": 0.2148, "lr": 1.5165470395159314e-05, "epoch": 2.7515923566878984, "percentage": 39.56, "elapsed_time": "0:14:29", "remaining_time": "0:22:08"}
+{"current_steps": 145, "total_steps": 364, "loss": 0.2244, "lr": 1.5082969776201948e-05, "epoch": 2.770700636942675, "percentage": 39.84, "elapsed_time": "0:14:33", "remaining_time": "0:21:58"}
+{"current_steps": 146, "total_steps": 364, "loss": 0.2064, "lr": 1.5000000000000002e-05, "epoch": 2.789808917197452, "percentage": 40.11, "elapsed_time": "0:14:37", "remaining_time": "0:21:49"}
+{"current_steps": 147, "total_steps": 364, "loss": 0.2195, "lr": 1.4916568724649688e-05, "epoch": 2.8089171974522293, "percentage": 40.38, "elapsed_time": "0:14:42", "remaining_time": "0:21:42"}
+{"current_steps": 148, "total_steps": 364, "loss": 0.2182, "lr": 1.483268365084351e-05, "epoch": 2.8280254777070066, "percentage": 40.66, "elapsed_time": "0:14:46", "remaining_time": "0:21:33"}
+{"current_steps": 149, "total_steps": 364, "loss": 0.2205, "lr": 1.4748352521159492e-05, "epoch": 2.8471337579617835, "percentage": 40.93, "elapsed_time": "0:14:51", "remaining_time": "0:21:25"}
+{"current_steps": 150, "total_steps": 364, "loss": 0.2237, "lr": 1.466358311934654e-05, "epoch": 2.8662420382165603, "percentage": 41.21, "elapsed_time": "0:14:55", "remaining_time": "0:21:17"}
+{"current_steps": 151, "total_steps": 364, "loss": 0.2195, "lr": 1.4578383269606004e-05, "epoch": 2.8853503184713376, "percentage": 41.48, "elapsed_time": "0:15:00", "remaining_time": "0:21:09"}
+{"current_steps": 152, "total_steps": 364, "loss": 0.2084, "lr": 1.4492760835869504e-05, "epoch": 2.904458598726115, "percentage": 41.76, "elapsed_time": "0:15:04", "remaining_time": "0:21:01"}
+{"current_steps": 153, "total_steps": 364, "loss": 0.2333, "lr": 1.4406723721073088e-05, "epoch": 2.9235668789808917, "percentage": 42.03, "elapsed_time": "0:15:09", "remaining_time": "0:20:54"}
+{"current_steps": 154, "total_steps": 364, "loss": 0.2314, "lr": 1.4320279866427798e-05, "epoch": 2.9426751592356686, "percentage": 42.31, "elapsed_time": "0:15:14", "remaining_time": "0:20:47"}
+{"current_steps": 155, "total_steps": 364, "loss": 0.2141, "lr": 1.4233437250686695e-05, "epoch": 2.961783439490446, "percentage": 42.58, "elapsed_time": "0:15:19", "remaining_time": "0:20:39"}
+{"current_steps": 156, "total_steps": 364, "loss": 0.212, "lr": 1.4146203889408418e-05, "epoch": 2.980891719745223, "percentage": 42.86, "elapsed_time": "0:15:23", "remaining_time": "0:20:30"}
+{"current_steps": 157, "total_steps": 364, "loss": 0.2119, "lr": 1.4058587834217356e-05, "epoch": 3.0, "percentage": 43.13, "elapsed_time": "0:15:28", "remaining_time": "0:20:24"}
+{"current_steps": 158, "total_steps": 364, "loss": 0.1469, "lr": 1.3970597172060482e-05, "epoch": 3.0191082802547773, "percentage": 43.41, "elapsed_time": "0:17:17", "remaining_time": "0:22:32"}
+{"current_steps": 159, "total_steps": 364, "loss": 0.1612, "lr": 1.3882240024460928e-05, "epoch": 3.038216560509554, "percentage": 43.68, "elapsed_time": "0:17:22", "remaining_time": "0:22:23"}
+{"current_steps": 160, "total_steps": 364, "loss": 0.1481, "lr": 1.3793524546768358e-05, "epoch": 3.0573248407643314, "percentage": 43.96, "elapsed_time": "0:17:26", "remaining_time": "0:22:13"}
+{"current_steps": 161, "total_steps": 364, "loss": 0.1696, "lr": 1.3704458927406261e-05, "epoch": 3.0764331210191083, "percentage": 44.23, "elapsed_time": "0:17:30", "remaining_time": "0:22:04"}
+{"current_steps": 162, "total_steps": 364, "loss": 0.1448, "lr": 1.3615051387116131e-05, "epoch": 3.0955414012738856, "percentage": 44.51, "elapsed_time": "0:17:34", "remaining_time": "0:21:54"}
+{"current_steps": 163, "total_steps": 364, "loss": 0.141, "lr": 1.3525310178198707e-05, "epoch": 3.1146496815286624, "percentage": 44.78, "elapsed_time": "0:17:39", "remaining_time": "0:21:46"}
+{"current_steps": 164, "total_steps": 364, "loss": 0.1313, "lr": 1.3435243583752294e-05, "epoch": 3.1337579617834397, "percentage": 45.05, "elapsed_time": "0:17:43", "remaining_time": "0:21:36"}
+{"current_steps": 165, "total_steps": 364, "loss": 0.1441, "lr": 1.3344859916908206e-05, "epoch": 3.1528662420382165, "percentage": 45.33, "elapsed_time": "0:17:47", "remaining_time": "0:21:27"}
+{"current_steps": 166, "total_steps": 364, "loss": 0.1263, "lr": 1.325416752006351e-05, "epoch": 3.171974522292994, "percentage": 45.6, "elapsed_time": "0:17:51", "remaining_time": "0:21:17"}
+{"current_steps": 167, "total_steps": 364, "loss": 0.1485, "lr": 1.3163174764110985e-05, "epoch": 3.1910828025477707, "percentage": 45.88, "elapsed_time": "0:17:55", "remaining_time": "0:21:09"}
+{"current_steps": 168, "total_steps": 364, "loss": 0.156, "lr": 1.3071890047666498e-05, "epoch": 3.210191082802548, "percentage": 46.15, "elapsed_time": "0:18:01", "remaining_time": "0:21:02"}
+{"current_steps": 169, "total_steps": 364, "loss": 0.1404, "lr": 1.2980321796293838e-05, "epoch": 3.229299363057325, "percentage": 46.43, "elapsed_time": "0:18:06", "remaining_time": "0:20:53"}
+{"current_steps": 170, "total_steps": 364, "loss": 0.1366, "lr": 1.288847846172701e-05, "epoch": 3.248407643312102, "percentage": 46.7, "elapsed_time": "0:18:10", "remaining_time": "0:20:44"}
+{"current_steps": 171, "total_steps": 364, "loss": 0.1354, "lr": 1.2796368521090143e-05, "epoch": 3.267515923566879, "percentage": 46.98, "elapsed_time": "0:18:15", "remaining_time": "0:20:36"}
+{"current_steps": 172, "total_steps": 364, "loss": 0.148, "lr": 1.2704000476115079e-05, "epoch": 3.286624203821656, "percentage": 47.25, "elapsed_time": "0:18:19", "remaining_time": "0:20:27"}
+{"current_steps": 173, "total_steps": 364, "loss": 0.1398, "lr": 1.2611382852356632e-05, "epoch": 3.305732484076433, "percentage": 47.53, "elapsed_time": "0:18:23", "remaining_time": "0:20:18"}
+{"current_steps": 174, "total_steps": 364, "loss": 0.1396, "lr": 1.2518524198405699e-05, "epoch": 3.3248407643312103, "percentage": 47.8, "elapsed_time": "0:18:28", "remaining_time": "0:20:10"}
+{"current_steps": 175, "total_steps": 364, "loss": 0.1502, "lr": 1.2425433085100224e-05, "epoch": 3.343949044585987, "percentage": 48.08, "elapsed_time": "0:18:32", "remaining_time": "0:20:01"}
+{"current_steps": 176, "total_steps": 364, "loss": 0.1625, "lr": 1.233211810473411e-05, "epoch": 3.3630573248407645, "percentage": 48.35, "elapsed_time": "0:18:37", "remaining_time": "0:19:53"}
+{"current_steps": 177, "total_steps": 364, "loss": 0.1456, "lr": 1.2238587870264152e-05, "epoch": 3.3821656050955413, "percentage": 48.63, "elapsed_time": "0:18:41", "remaining_time": "0:19:44"}
+{"current_steps": 178, "total_steps": 364, "loss": 0.147, "lr": 1.2144851014515055e-05, "epoch": 3.4012738853503186, "percentage": 48.9, "elapsed_time": "0:18:45", "remaining_time": "0:19:36"}
+{"current_steps": 179, "total_steps": 364, "loss": 0.1621, "lr": 1.2050916189382646e-05, "epoch": 3.4203821656050954, "percentage": 49.18, "elapsed_time": "0:18:50", "remaining_time": "0:19:28"}
+{"current_steps": 180, "total_steps": 364, "loss": 0.1423, "lr": 1.1956792065035281e-05, "epoch": 3.4394904458598727, "percentage": 49.45, "elapsed_time": "0:18:54", "remaining_time": "0:19:19"}
+{"current_steps": 181, "total_steps": 364, "loss": 0.1435, "lr": 1.1862487329113606e-05, "epoch": 3.4585987261146496, "percentage": 49.73, "elapsed_time": "0:18:59", "remaining_time": "0:19:11"}
+{"current_steps": 182, "total_steps": 364, "loss": 0.1372, "lr": 1.1768010685928686e-05, "epoch": 3.477707006369427, "percentage": 50.0, "elapsed_time": "0:19:03", "remaining_time": "0:19:03"}
+{"current_steps": 183, "total_steps": 364, "loss": 0.1605, "lr": 1.1673370855658592e-05, "epoch": 3.4968152866242037, "percentage": 50.27, "elapsed_time": "0:19:07", "remaining_time": "0:18:54"}
+{"current_steps": 184, "total_steps": 364, "loss": 0.1324, "lr": 1.1578576573543541e-05, "epoch": 3.515923566878981, "percentage": 50.55, "elapsed_time": "0:19:11", "remaining_time": "0:18:46"}
+{"current_steps": 185, "total_steps": 364, "loss": 0.1312, "lr": 1.1483636589079627e-05, "epoch": 3.535031847133758, "percentage": 50.82, "elapsed_time": "0:19:16", "remaining_time": "0:18:38"}
+{"current_steps": 186, "total_steps": 364, "loss": 0.1617, "lr": 1.1388559665211241e-05, "epoch": 3.554140127388535, "percentage": 51.1, "elapsed_time": "0:19:20", "remaining_time": "0:18:30"}
+{"current_steps": 187, "total_steps": 364, "loss": 0.1624, "lr": 1.1293354577522264e-05, "epoch": 3.573248407643312, "percentage": 51.37, "elapsed_time": "0:19:24", "remaining_time": "0:18:22"}
+{"current_steps": 188, "total_steps": 364, "loss": 0.1346, "lr": 1.1198030113426074e-05, "epoch": 3.5923566878980893, "percentage": 51.65, "elapsed_time": "0:19:28", "remaining_time": "0:18:14"}
+{"current_steps": 189, "total_steps": 364, "loss": 0.1549, "lr": 1.1102595071354471e-05, "epoch": 3.611464968152866, "percentage": 51.92, "elapsed_time": "0:19:34", "remaining_time": "0:18:07"}
+{"current_steps": 190, "total_steps": 364, "loss": 0.1558, "lr": 1.1007058259945584e-05, "epoch": 3.6305732484076434, "percentage": 52.2, "elapsed_time": "0:19:38", "remaining_time": "0:17:59"}
+{"current_steps": 191, "total_steps": 364, "loss": 0.1543, "lr": 1.0911428497230834e-05, "epoch": 3.6496815286624202, "percentage": 52.47, "elapsed_time": "0:19:43", "remaining_time": "0:17:51"}
+{"current_steps": 192, "total_steps": 364, "loss": 0.1325, "lr": 1.0815714609821027e-05, "epoch": 3.6687898089171975, "percentage": 52.75, "elapsed_time": "0:19:47", "remaining_time": "0:17:43"}
+{"current_steps": 193, "total_steps": 364, "loss": 0.1668, "lr": 1.0719925432091671e-05, "epoch": 3.6878980891719744, "percentage": 53.02, "elapsed_time": "0:19:52", "remaining_time": "0:17:36"}
+{"current_steps": 194, "total_steps": 364, "loss": 0.1307, "lr": 1.0624069805367558e-05, "epoch": 3.7070063694267517, "percentage": 53.3, "elapsed_time": "0:19:55", "remaining_time": "0:17:28"}
+{"current_steps": 195, "total_steps": 364, "loss": 0.1568, "lr": 1.0528156577106703e-05, "epoch": 3.7261146496815285, "percentage": 53.57, "elapsed_time": "0:20:02", "remaining_time": "0:17:22"}
+{"current_steps": 196, "total_steps": 364, "loss": 0.1563, "lr": 1.043219460008374e-05, "epoch": 3.745222929936306, "percentage": 53.85, "elapsed_time": "0:20:07", "remaining_time": "0:17:14"}
+{"current_steps": 197, "total_steps": 364, "loss": 0.1283, "lr": 1.0336192731572805e-05, "epoch": 3.7643312101910826, "percentage": 54.12, "elapsed_time": "0:20:11", "remaining_time": "0:17:07"}
+{"current_steps": 198, "total_steps": 364, "loss": 0.148, "lr": 1.0240159832530007e-05, "epoch": 3.78343949044586, "percentage": 54.4, "elapsed_time": "0:20:16", "remaining_time": "0:16:59"}
+{"current_steps": 199, "total_steps": 364, "loss": 0.1394, "lr": 1.0144104766775574e-05, "epoch": 3.802547770700637, "percentage": 54.67, "elapsed_time": "0:20:20", "remaining_time": "0:16:52"}
+{"current_steps": 200, "total_steps": 364, "loss": 0.1423, "lr": 1.004803640017571e-05, "epoch": 3.821656050955414, "percentage": 54.95, "elapsed_time": "0:20:24", "remaining_time": "0:16:43"}
+{"current_steps": 201, "total_steps": 364, "loss": 0.1582, "lr": 9.951963599824294e-06, "epoch": 3.840764331210191, "percentage": 55.22, "elapsed_time": "0:20:29", "remaining_time": "0:16:36"}
+{"current_steps": 202, "total_steps": 364, "loss": 0.1525, "lr": 9.855895233224431e-06, "epoch": 3.859872611464968, "percentage": 55.49, "elapsed_time": "0:20:38", "remaining_time": "0:16:33"}
+{"current_steps": 203, "total_steps": 364, "loss": 0.1336, "lr": 9.759840167469995e-06, "epoch": 3.8789808917197455, "percentage": 55.77, "elapsed_time": "0:20:43", "remaining_time": "0:16:25"}
+{"current_steps": 204, "total_steps": 364, "loss": 0.154, "lr": 9.663807268427197e-06, "epoch": 3.8980891719745223, "percentage": 56.04, "elapsed_time": "0:20:47", "remaining_time": "0:16:18"}
+{"current_steps": 205, "total_steps": 364, "loss": 0.1511, "lr": 9.56780539991626e-06, "epoch": 3.917197452229299, "percentage": 56.32, "elapsed_time": "0:20:51", "remaining_time": "0:16:10"}
+{"current_steps": 206, "total_steps": 364, "loss": 0.1465, "lr": 9.471843422893299e-06, "epoch": 3.9363057324840764, "percentage": 56.59, "elapsed_time": "0:20:55", "remaining_time": "0:16:03"}
+{"current_steps": 207, "total_steps": 364, "loss": 0.1381, "lr": 9.375930194632447e-06, "epoch": 3.9554140127388537, "percentage": 56.87, "elapsed_time": "0:21:00", "remaining_time": "0:15:55"}
+{"current_steps": 208, "total_steps": 364, "loss": 0.121, "lr": 9.28007456790833e-06, "epoch": 3.9745222929936306, "percentage": 57.14, "elapsed_time": "0:21:03", "remaining_time": "0:15:47"}
+{"current_steps": 209, "total_steps": 364, "loss": 0.1384, "lr": 9.184285390178978e-06, "epoch": 3.9936305732484074, "percentage": 57.42, "elapsed_time": "0:21:08", "remaining_time": "0:15:40"}
+{"current_steps": 210, "total_steps": 364, "loss": 0.0972, "lr": 9.08857150276917e-06, "epoch": 4.012738853503185, "percentage": 57.69, "elapsed_time": "0:22:56", "remaining_time": "0:16:49"}
+{"current_steps": 211, "total_steps": 364, "loss": 0.1077, "lr": 8.992941740054418e-06, "epoch": 4.031847133757962, "percentage": 57.97, "elapsed_time": "0:23:01", "remaining_time": "0:16:41"}
+{"current_steps": 212, "total_steps": 364, "loss": 0.0803, "lr": 8.897404928645529e-06, "epoch": 4.050955414012739, "percentage": 58.24, "elapsed_time": "0:23:05", "remaining_time": "0:16:33"}
+{"current_steps": 213, "total_steps": 364, "loss": 0.0948, "lr": 8.80196988657393e-06, "epoch": 4.070063694267516, "percentage": 58.52, "elapsed_time": "0:23:10", "remaining_time": "0:16:25"}
+{"current_steps": 214, "total_steps": 364, "loss": 0.0965, "lr": 8.706645422477739e-06, "epoch": 4.089171974522293, "percentage": 58.79, "elapsed_time": "0:23:16", "remaining_time": "0:16:18"}
+{"current_steps": 215, "total_steps": 364, "loss": 0.0831, "lr": 8.611440334788762e-06, "epoch": 4.10828025477707, "percentage": 59.07, "elapsed_time": "0:23:19", "remaining_time": "0:16:10"}
+{"current_steps": 216, "total_steps": 364, "loss": 0.0933, "lr": 8.516363410920376e-06, "epoch": 4.127388535031847, "percentage": 59.34, "elapsed_time": "0:23:25", "remaining_time": "0:16:02"}
+{"current_steps": 217, "total_steps": 364, "loss": 0.0987, "lr": 8.42142342645646e-06, "epoch": 4.146496815286624, "percentage": 59.62, "elapsed_time": "0:23:29", "remaining_time": "0:15:54"}
+{"current_steps": 218, "total_steps": 364, "loss": 0.0819, "lr": 8.326629144341408e-06, "epoch": 4.165605095541402, "percentage": 59.89, "elapsed_time": "0:23:33", "remaining_time": "0:15:46"}
+{"current_steps": 219, "total_steps": 364, "loss": 0.095, "lr": 8.231989314071318e-06, "epoch": 4.1847133757961785, "percentage": 60.16, "elapsed_time": "0:23:38", "remaining_time": "0:15:38"}
+{"current_steps": 220, "total_steps": 364, "loss": 0.0903, "lr": 8.137512670886397e-06, "epoch": 4.203821656050955, "percentage": 60.44, "elapsed_time": "0:23:43", "remaining_time": "0:15:31"}
+{"current_steps": 221, "total_steps": 364, "loss": 0.1067, "lr": 8.043207934964722e-06, "epoch": 4.222929936305732, "percentage": 60.71, "elapsed_time": "0:23:48", "remaining_time": "0:15:24"}
+{"current_steps": 222, "total_steps": 364, "loss": 0.0816, "lr": 7.949083810617358e-06, "epoch": 4.24203821656051, "percentage": 60.99, "elapsed_time": "0:23:52", "remaining_time": "0:15:16"}
+{"current_steps": 223, "total_steps": 364, "loss": 0.0952, "lr": 7.855148985484946e-06, "epoch": 4.261146496815287, "percentage": 61.26, "elapsed_time": "0:23:58", "remaining_time": "0:15:09"}
+{"current_steps": 224, "total_steps": 364, "loss": 0.0909, "lr": 7.761412129735853e-06, "epoch": 4.280254777070064, "percentage": 61.54, "elapsed_time": "0:24:02", "remaining_time": "0:15:01"}
+{"current_steps": 225, "total_steps": 364, "loss": 0.0869, "lr": 7.667881895265895e-06, "epoch": 4.2993630573248405, "percentage": 61.81, "elapsed_time": "0:24:06", "remaining_time": "0:14:53"}
+{"current_steps": 226, "total_steps": 364, "loss": 0.0813, "lr": 7.574566914899779e-06, "epoch": 4.318471337579618, "percentage": 62.09, "elapsed_time": "0:24:11", "remaining_time": "0:14:46"}
+{"current_steps": 227, "total_steps": 364, "loss": 0.0865, "lr": 7.481475801594302e-06, "epoch": 4.337579617834395, "percentage": 62.36, "elapsed_time": "0:24:15", "remaining_time": "0:14:38"}
+{"current_steps": 228, "total_steps": 364, "loss": 0.0991, "lr": 7.388617147643371e-06, "epoch": 4.356687898089172, "percentage": 62.64, "elapsed_time": "0:24:19", "remaining_time": "0:14:30"}
+{"current_steps": 229, "total_steps": 364, "loss": 0.0827, "lr": 7.295999523884921e-06, "epoch": 4.375796178343949, "percentage": 62.91, "elapsed_time": "0:24:23", "remaining_time": "0:14:22"}
+{"current_steps": 230, "total_steps": 364, "loss": 0.0795, "lr": 7.203631478909857e-06, "epoch": 4.3949044585987265, "percentage": 63.19, "elapsed_time": "0:24:28", "remaining_time": "0:14:15"}
+{"current_steps": 231, "total_steps": 364, "loss": 0.0886, "lr": 7.111521538272997e-06, "epoch": 4.414012738853503, "percentage": 63.46, "elapsed_time": "0:24:32", "remaining_time": "0:14:07"}
+{"current_steps": 232, "total_steps": 364, "loss": 0.0869, "lr": 7.019678203706164e-06, "epoch": 4.43312101910828, "percentage": 63.74, "elapsed_time": "0:24:37", "remaining_time": "0:14:00"}
+{"current_steps": 233, "total_steps": 364, "loss": 0.0905, "lr": 6.928109952333506e-06, "epoch": 4.452229299363057, "percentage": 64.01, "elapsed_time": "0:24:41", "remaining_time": "0:13:52"}
+{"current_steps": 234, "total_steps": 364, "loss": 0.1021, "lr": 6.83682523588902e-06, "epoch": 4.471337579617835, "percentage": 64.29, "elapsed_time": "0:24:46", "remaining_time": "0:13:45"}
+{"current_steps": 235, "total_steps": 364, "loss": 0.1129, "lr": 6.745832479936492e-06, "epoch": 4.490445859872612, "percentage": 64.56, "elapsed_time": "0:24:51", "remaining_time": "0:13:38"}
+{"current_steps": 236, "total_steps": 364, "loss": 0.0921, "lr": 6.655140083091794e-06, "epoch": 4.509554140127388, "percentage": 64.84, "elapsed_time": "0:24:55", "remaining_time": "0:13:31"}
+{"current_steps": 237, "total_steps": 364, "loss": 0.0835, "lr": 6.564756416247712e-06, "epoch": 4.528662420382165, "percentage": 65.11, "elapsed_time": "0:24:59", "remaining_time": "0:13:23"}
+{"current_steps": 238, "total_steps": 364, "loss": 0.0712, "lr": 6.474689821801295e-06, "epoch": 4.547770700636943, "percentage": 65.38, "elapsed_time": "0:25:04", "remaining_time": "0:13:16"}
+{"current_steps": 239, "total_steps": 364, "loss": 0.0789, "lr": 6.384948612883872e-06, "epoch": 4.56687898089172, "percentage": 65.66, "elapsed_time": "0:25:08", "remaining_time": "0:13:08"}
+{"current_steps": 240, "total_steps": 364, "loss": 0.0997, "lr": 6.2955410725937405e-06, "epoch": 4.585987261146497, "percentage": 65.93, "elapsed_time": "0:25:12", "remaining_time": "0:13:01"}
+{"current_steps": 241, "total_steps": 364, "loss": 0.0818, "lr": 6.206475453231644e-06, "epoch": 4.6050955414012735, "percentage": 66.21, "elapsed_time": "0:25:16", "remaining_time": "0:12:53"}
+{"current_steps": 242, "total_steps": 364, "loss": 0.0766, "lr": 6.117759975539075e-06, "epoch": 4.624203821656051, "percentage": 66.48, "elapsed_time": "0:25:20", "remaining_time": "0:12:46"}
+{"current_steps": 243, "total_steps": 364, "loss": 0.0759, "lr": 6.029402827939519e-06, "epoch": 4.643312101910828, "percentage": 66.76, "elapsed_time": "0:25:24", "remaining_time": "0:12:39"}
+{"current_steps": 244, "total_steps": 364, "loss": 0.0793, "lr": 5.941412165782645e-06, "epoch": 4.662420382165605, "percentage": 67.03, "elapsed_time": "0:25:28", "remaining_time": "0:12:31"}
+{"current_steps": 245, "total_steps": 364, "loss": 0.0918, "lr": 5.853796110591583e-06, "epoch": 4.681528662420382, "percentage": 67.31, "elapsed_time": "0:25:34", "remaining_time": "0:12:25"}
+{"current_steps": 246, "total_steps": 364, "loss": 0.0753, "lr": 5.766562749313309e-06, "epoch": 4.7006369426751595, "percentage": 67.58, "elapsed_time": "0:25:38", "remaining_time": "0:12:18"}
+{"current_steps": 247, "total_steps": 364, "loss": 0.0928, "lr": 5.6797201335722064e-06, "epoch": 4.719745222929936, "percentage": 67.86, "elapsed_time": "0:25:43", "remaining_time": "0:12:11"}
+{"current_steps": 248, "total_steps": 364, "loss": 0.0772, "lr": 5.593276278926912e-06, "epoch": 4.738853503184713, "percentage": 68.13, "elapsed_time": "0:25:48", "remaining_time": "0:12:04"}
+{"current_steps": 249, "total_steps": 364, "loss": 0.0962, "lr": 5.507239164130501e-06, "epoch": 4.757961783439491, "percentage": 68.41, "elapsed_time": "0:25:52", "remaining_time": "0:11:57"}
+{"current_steps": 250, "total_steps": 364, "loss": 0.0854, "lr": 5.421616730394e-06, "epoch": 4.777070063694268, "percentage": 68.68, "elapsed_time": "0:25:57", "remaining_time": "0:11:50"}
+{"current_steps": 251, "total_steps": 364, "loss": 0.0855, "lr": 5.336416880653461e-06, "epoch": 4.796178343949045, "percentage": 68.96, "elapsed_time": "0:26:02", "remaining_time": "0:11:43"}
+{"current_steps": 252, "total_steps": 364, "loss": 0.0909, "lr": 5.251647478840511e-06, "epoch": 4.8152866242038215, "percentage": 69.23, "elapsed_time": "0:26:07", "remaining_time": "0:11:36"}
+{"current_steps": 253, "total_steps": 364, "loss": 0.092, "lr": 5.167316349156495e-06, "epoch": 4.834394904458598, "percentage": 69.51, "elapsed_time": "0:26:11", "remaining_time": "0:11:29"}
+{"current_steps": 254, "total_steps": 364, "loss": 0.0883, "lr": 5.083431275350312e-06, "epoch": 4.853503184713376, "percentage": 69.78, "elapsed_time": "0:26:16", "remaining_time": "0:11:22"}
+{"current_steps": 255, "total_steps": 364, "loss": 0.0947, "lr": 5.000000000000003e-06, "epoch": 4.872611464968153, "percentage": 70.05, "elapsed_time": "0:26:21", "remaining_time": "0:11:16"}
+{"current_steps": 256, "total_steps": 364, "loss": 0.0849, "lr": 4.917030223798057e-06, "epoch": 4.89171974522293, "percentage": 70.33, "elapsed_time": "0:26:26", "remaining_time": "0:11:09"}
+{"current_steps": 257, "total_steps": 364, "loss": 0.0937, "lr": 4.834529604840686e-06, "epoch": 4.9108280254777075, "percentage": 70.6, "elapsed_time": "0:26:30", "remaining_time": "0:11:02"}
+{"current_steps": 258, "total_steps": 364, "loss": 0.0933, "lr": 4.7525057579209775e-06, "epoch": 4.929936305732484, "percentage": 70.88, "elapsed_time": "0:26:34", "remaining_time": "0:10:55"}
+{"current_steps": 259, "total_steps": 364, "loss": 0.0649, "lr": 4.670966253826027e-06, "epoch": 4.949044585987261, "percentage": 71.15, "elapsed_time": "0:26:38", "remaining_time": "0:10:47"}
+{"current_steps": 260, "total_steps": 364, "loss": 0.0888, "lr": 4.589918618638173e-06, "epoch": 4.968152866242038, "percentage": 71.43, "elapsed_time": "0:26:43", "remaining_time": "0:10:41"}
+{"current_steps": 261, "total_steps": 364, "loss": 0.0882, "lr": 4.5093703330403385e-06, "epoch": 4.987261146496815, "percentage": 71.7, "elapsed_time": "0:26:47", "remaining_time": "0:10:34"}
+{"current_steps": 262, "total_steps": 364, "loss": 0.08, "lr": 4.429328831625565e-06, "epoch": 5.006369426751593, "percentage": 71.98, "elapsed_time": "0:28:44", "remaining_time": "0:11:11"}
+{"current_steps": 263, "total_steps": 364, "loss": 0.0577, "lr": 4.349801502210801e-06, "epoch": 5.025477707006369, "percentage": 72.25, "elapsed_time": "0:28:48", "remaining_time": "0:11:03"}
+{"current_steps": 264, "total_steps": 364, "loss": 0.0738, "lr": 4.270795685155001e-06, "epoch": 5.044585987261146, "percentage": 72.53, "elapsed_time": "0:28:53", "remaining_time": "0:10:56"}
+{"current_steps": 265, "total_steps": 364, "loss": 0.0535, "lr": 4.192318672681631e-06, "epoch": 5.063694267515924, "percentage": 72.8, "elapsed_time": "0:28:56", "remaining_time": "0:10:48"}
+{"current_steps": 266, "total_steps": 364, "loss": 0.0466, "lr": 4.1143777082055715e-06, "epoch": 5.082802547770701, "percentage": 73.08, "elapsed_time": "0:29:01", "remaining_time": "0:10:41"}
+{"current_steps": 267, "total_steps": 364, "loss": 0.0567, "lr": 4.036979985664566e-06, "epoch": 5.101910828025478, "percentage": 73.35, "elapsed_time": "0:29:05", "remaining_time": "0:10:34"}
+{"current_steps": 268, "total_steps": 364, "loss": 0.0588, "lr": 3.960132648855226e-06, "epoch": 5.1210191082802545, "percentage": 73.63, "elapsed_time": "0:29:09", "remaining_time": "0:10:26"}
+{"current_steps": 269, "total_steps": 364, "loss": 0.0542, "lr": 3.883842790773647e-06, "epoch": 5.140127388535032, "percentage": 73.9, "elapsed_time": "0:29:13", "remaining_time": "0:10:19"}
+{"current_steps": 270, "total_steps": 364, "loss": 0.0713, "lr": 3.8081174529607346e-06, "epoch": 5.159235668789809, "percentage": 74.18, "elapsed_time": "0:29:18", "remaining_time": "0:10:12"}
+{"current_steps": 271, "total_steps": 364, "loss": 0.0516, "lr": 3.732963624852275e-06, "epoch": 5.178343949044586, "percentage": 74.45, "elapsed_time": "0:29:22", "remaining_time": "0:10:04"}
+{"current_steps": 272, "total_steps": 364, "loss": 0.0515, "lr": 3.6583882431338047e-06, "epoch": 5.197452229299363, "percentage": 74.73, "elapsed_time": "0:29:27", "remaining_time": "0:09:57"}
+{"current_steps": 273, "total_steps": 364, "loss": 0.0473, "lr": 3.584398191100341e-06, "epoch": 5.2165605095541405, "percentage": 75.0, "elapsed_time": "0:29:31", "remaining_time": "0:09:50"}
+{"current_steps": 274, "total_steps": 364, "loss": 0.04, "lr": 3.511000298021098e-06, "epoch": 5.235668789808917, "percentage": 75.27, "elapsed_time": "0:29:34", "remaining_time": "0:09:42"}
+{"current_steps": 275, "total_steps": 364, "loss": 0.0508, "lr": 3.4382013385090985e-06, "epoch": 5.254777070063694, "percentage": 75.55, "elapsed_time": "0:29:38", "remaining_time": "0:09:35"}
+{"current_steps": 276, "total_steps": 364, "loss": 0.0533, "lr": 3.3660080318959043e-06, "epoch": 5.273885350318471, "percentage": 75.82, "elapsed_time": "0:29:43", "remaining_time": "0:09:28"}
+{"current_steps": 277, "total_steps": 364, "loss": 0.0615, "lr": 3.2944270416114256e-06, "epoch": 5.292993630573249, "percentage": 76.1, "elapsed_time": "0:29:47", "remaining_time": "0:09:21"}
+{"current_steps": 278, "total_steps": 364, "loss": 0.0624, "lr": 3.223464974568874e-06, "epoch": 5.312101910828026, "percentage": 76.37, "elapsed_time": "0:29:53", "remaining_time": "0:09:14"}
+{"current_steps": 279, "total_steps": 364, "loss": 0.0497, "lr": 3.153128380554941e-06, "epoch": 5.3312101910828025, "percentage": 76.65, "elapsed_time": "0:30:01", "remaining_time": "0:09:08"}
+{"current_steps": 280, "total_steps": 364, "loss": 0.0514, "lr": 3.0834237516252817e-06, "epoch": 5.350318471337579, "percentage": 76.92, "elapsed_time": "0:30:06", "remaining_time": "0:09:01"}
+{"current_steps": 281, "total_steps": 364, "loss": 0.0567, "lr": 3.0143575215052732e-06, "epoch": 5.369426751592357, "percentage": 77.2, "elapsed_time": "0:30:10", "remaining_time": "0:08:54"}
+{"current_steps": 282, "total_steps": 364, "loss": 0.0569, "lr": 2.94593606499619e-06, "epoch": 5.388535031847134, "percentage": 77.47, "elapsed_time": "0:30:15", "remaining_time": "0:08:47"}
+{"current_steps": 283, "total_steps": 364, "loss": 0.0638, "lr": 2.878165697386812e-06, "epoch": 5.407643312101911, "percentage": 77.75, "elapsed_time": "0:30:19", "remaining_time": "0:08:40"}
+{"current_steps": 284, "total_steps": 364, "loss": 0.0481, "lr": 2.8110526738705345e-06, "epoch": 5.426751592356688, "percentage": 78.02, "elapsed_time": "0:30:25", "remaining_time": "0:08:34"}
+{"current_steps": 285, "total_steps": 364, "loss": 0.0453, "lr": 2.7446031889679893e-06, "epoch": 5.445859872611465, "percentage": 78.3, "elapsed_time": "0:30:29", "remaining_time": "0:08:27"}
+{"current_steps": 286, "total_steps": 364, "loss": 0.0435, "lr": 2.678823375955314e-06, "epoch": 5.464968152866242, "percentage": 78.57, "elapsed_time": "0:30:32", "remaining_time": "0:08:19"}
+{"current_steps": 287, "total_steps": 364, "loss": 0.0415, "lr": 2.6137193062980506e-06, "epoch": 5.484076433121019, "percentage": 78.85, "elapsed_time": "0:30:37", "remaining_time": "0:08:12"}
+{"current_steps": 288, "total_steps": 364, "loss": 0.0489, "lr": 2.5492969890907383e-06, "epoch": 5.503184713375796, "percentage": 79.12, "elapsed_time": "0:30:41", "remaining_time": "0:08:05"}
+{"current_steps": 289, "total_steps": 364, "loss": 0.0655, "lr": 2.485562370502279e-06, "epoch": 5.522292993630574, "percentage": 79.4, "elapsed_time": "0:30:46", "remaining_time": "0:07:59"}
+{"current_steps": 290, "total_steps": 364, "loss": 0.0485, "lr": 2.4225213332271203e-06, "epoch": 5.54140127388535, "percentage": 79.67, "elapsed_time": "0:30:50", "remaining_time": "0:07:52"}
+{"current_steps": 291, "total_steps": 364, "loss": 0.0558, "lr": 2.3601796959422585e-06, "epoch": 5.560509554140127, "percentage": 79.95, "elapsed_time": "0:30:54", "remaining_time": "0:07:45"}
+{"current_steps": 292, "total_steps": 364, "loss": 0.0454, "lr": 2.2985432127701945e-06, "epoch": 5.579617834394904, "percentage": 80.22, "elapsed_time": "0:31:00", "remaining_time": "0:07:38"}
+{"current_steps": 293, "total_steps": 364, "loss": 0.045, "lr": 2.2376175727478346e-06, "epoch": 5.598726114649682, "percentage": 80.49, "elapsed_time": "0:31:05", "remaining_time": "0:07:31"}
+{"current_steps": 294, "total_steps": 364, "loss": 0.0549, "lr": 2.1774083993013715e-06, "epoch": 5.617834394904459, "percentage": 80.77, "elapsed_time": "0:31:09", "remaining_time": "0:07:25"}
+{"current_steps": 295, "total_steps": 364, "loss": 0.0587, "lr": 2.1179212497272582e-06, "epoch": 5.6369426751592355, "percentage": 81.04, "elapsed_time": "0:31:14", "remaining_time": "0:07:18"}
+{"current_steps": 296, "total_steps": 364, "loss": 0.0487, "lr": 2.0591616146792705e-06, "epoch": 5.656050955414012, "percentage": 81.32, "elapsed_time": "0:31:19", "remaining_time": "0:07:11"}
+{"current_steps": 297, "total_steps": 364, "loss": 0.063, "lr": 2.0011349176617133e-06, "epoch": 5.67515923566879, "percentage": 81.59, "elapsed_time": "0:31:25", "remaining_time": "0:07:05"}
+{"current_steps": 298, "total_steps": 364, "loss": 0.0462, "lr": 1.9438465145288377e-06, "epoch": 5.694267515923567, "percentage": 81.87, "elapsed_time": "0:31:29", "remaining_time": "0:06:58"}
+{"current_steps": 299, "total_steps": 364, "loss": 0.0633, "lr": 1.8873016929904942e-06, "epoch": 5.713375796178344, "percentage": 82.14, "elapsed_time": "0:31:33", "remaining_time": "0:06:51"}
+{"current_steps": 300, "total_steps": 364, "loss": 0.0428, "lr": 1.8315056721240831e-06, "epoch": 5.732484076433121, "percentage": 82.42, "elapsed_time": "0:31:38", "remaining_time": "0:06:45"}
+{"current_steps": 301, "total_steps": 364, "loss": 0.0538, "lr": 1.7764636018928249e-06, "epoch": 5.751592356687898, "percentage": 82.69, "elapsed_time": "0:31:42", "remaining_time": "0:06:38"}
+{"current_steps": 302, "total_steps": 364, "loss": 0.056, "lr": 1.722180562670428e-06, "epoch": 5.770700636942675, "percentage": 82.97, "elapsed_time": "0:31:47", "remaining_time": "0:06:31"}
+{"current_steps": 303, "total_steps": 364, "loss": 0.0552, "lr": 1.6686615647721638e-06, "epoch": 5.789808917197452, "percentage": 83.24, "elapsed_time": "0:31:51", "remaining_time": "0:06:24"}
+{"current_steps": 304, "total_steps": 364, "loss": 0.0525, "lr": 1.6159115479924259e-06, "epoch": 5.80891719745223, "percentage": 83.52, "elapsed_time": "0:31:56", "remaining_time": "0:06:18"}
+{"current_steps": 305, "total_steps": 364, "loss": 0.0364, "lr": 1.5639353811487744e-06, "epoch": 5.828025477707007, "percentage": 83.79, "elapsed_time": "0:32:00", "remaining_time": "0:06:11"}
+{"current_steps": 306, "total_steps": 364, "loss": 0.0613, "lr": 1.5127378616325606e-06, "epoch": 5.8471337579617835, "percentage": 84.07, "elapsed_time": "0:32:04", "remaining_time": "0:06:04"}
+{"current_steps": 307, "total_steps": 364, "loss": 0.0542, "lr": 1.462323714966114e-06, "epoch": 5.86624203821656, "percentage": 84.34, "elapsed_time": "0:32:09", "remaining_time": "0:05:58"}
+{"current_steps": 308, "total_steps": 364, "loss": 0.0547, "lr": 1.4126975943665844e-06, "epoch": 5.885350318471337, "percentage": 84.62, "elapsed_time": "0:32:13", "remaining_time": "0:05:51"}
+{"current_steps": 309, "total_steps": 364, "loss": 0.0645, "lr": 1.3638640803164516e-06, "epoch": 5.904458598726115, "percentage": 84.89, "elapsed_time": "0:32:18", "remaining_time": "0:05:45"}
+{"current_steps": 310, "total_steps": 364, "loss": 0.0495, "lr": 1.3158276801407432e-06, "epoch": 5.923566878980892, "percentage": 85.16, "elapsed_time": "0:32:22", "remaining_time": "0:05:38"}
+{"current_steps": 311, "total_steps": 364, "loss": 0.0456, "lr": 1.2685928275910142e-06, "epoch": 5.942675159235669, "percentage": 85.44, "elapsed_time": "0:32:26", "remaining_time": "0:05:31"}
+{"current_steps": 312, "total_steps": 364, "loss": 0.0535, "lr": 1.222163882436107e-06, "epoch": 5.961783439490446, "percentage": 85.71, "elapsed_time": "0:32:31", "remaining_time": "0:05:25"}
+{"current_steps": 313, "total_steps": 364, "loss": 0.0609, "lr": 1.1765451300597574e-06, "epoch": 5.980891719745223, "percentage": 85.99, "elapsed_time": "0:32:36", "remaining_time": "0:05:18"}
+{"current_steps": 314, "total_steps": 364, "loss": 0.0518, "lr": 1.1317407810650372e-06, "epoch": 6.0, "percentage": 86.26, "elapsed_time": "0:32:40", "remaining_time": "0:05:12"}
+{"current_steps": 315, "total_steps": 364, "loss": 0.0388, "lr": 1.0877549708857228e-06, "epoch": 6.019108280254777, "percentage": 86.54, "elapsed_time": "0:34:33", "remaining_time": "0:05:22"}
+{"current_steps": 316, "total_steps": 364, "loss": 0.0377, "lr": 1.0445917594046073e-06, "epoch": 6.038216560509555, "percentage": 86.81, "elapsed_time": "0:34:39", "remaining_time": "0:05:15"}
+{"current_steps": 317, "total_steps": 364, "loss": 0.0452, "lr": 1.0022551305787564e-06, "epoch": 6.057324840764331, "percentage": 87.09, "elapsed_time": "0:34:43", "remaining_time": "0:05:08"}
+{"current_steps": 318, "total_steps": 364, "loss": 0.0434, "lr": 9.607489920717983e-07, "epoch": 6.076433121019108, "percentage": 87.36, "elapsed_time": "0:34:48", "remaining_time": "0:05:02"}
+{"current_steps": 319, "total_steps": 364, "loss": 0.0436, "lr": 9.200771748932513e-07, "epoch": 6.095541401273885, "percentage": 87.64, "elapsed_time": "0:34:52", "remaining_time": "0:04:55"}
+{"current_steps": 320, "total_steps": 364, "loss": 0.0416, "lr": 8.802434330449128e-07, "epoch": 6.114649681528663, "percentage": 87.91, "elapsed_time": "0:34:58", "remaining_time": "0:04:48"}
+{"current_steps": 321, "total_steps": 364, "loss": 0.0505, "lr": 8.412514431743657e-07, "epoch": 6.13375796178344, "percentage": 88.19, "elapsed_time": "0:35:03", "remaining_time": "0:04:41"}
+{"current_steps": 322, "total_steps": 364, "loss": 0.051, "lr": 8.031048042356393e-07, "epoch": 6.1528662420382165, "percentage": 88.46, "elapsed_time": "0:35:08", "remaining_time": "0:04:34"}
+{"current_steps": 323, "total_steps": 364, "loss": 0.0462, "lr": 7.65807037157007e-07, "epoch": 6.171974522292993, "percentage": 88.74, "elapsed_time": "0:35:12", "remaining_time": "0:04:28"}
+{"current_steps": 324, "total_steps": 364, "loss": 0.041, "lr": 7.293615845160196e-07, "epoch": 6.191082802547771, "percentage": 89.01, "elapsed_time": "0:35:16", "remaining_time": "0:04:21"}
+{"current_steps": 325, "total_steps": 364, "loss": 0.0302, "lr": 6.937718102217461e-07, "epoch": 6.210191082802548, "percentage": 89.29, "elapsed_time": "0:35:20", "remaining_time": "0:04:14"}
+{"current_steps": 326, "total_steps": 364, "loss": 0.0206, "lr": 6.590409992042957e-07, "epoch": 6.229299363057325, "percentage": 89.56, "elapsed_time": "0:35:24", "remaining_time": "0:04:07"}
+{"current_steps": 327, "total_steps": 364, "loss": 0.0344, "lr": 6.251723571116031e-07, "epoch": 6.248407643312102, "percentage": 89.84, "elapsed_time": "0:35:28", "remaining_time": "0:04:00"}
+{"current_steps": 328, "total_steps": 364, "loss": 0.0343, "lr": 5.921690100135713e-07, "epoch": 6.267515923566879, "percentage": 90.11, "elapsed_time": "0:35:32", "remaining_time": "0:03:54"}
+{"current_steps": 329, "total_steps": 364, "loss": 0.0336, "lr": 5.600340041135133e-07, "epoch": 6.286624203821656, "percentage": 90.38, "elapsed_time": "0:35:37", "remaining_time": "0:03:47"}
+{"current_steps": 330, "total_steps": 364, "loss": 0.0354, "lr": 5.287703054670012e-07, "epoch": 6.305732484076433, "percentage": 90.66, "elapsed_time": "0:35:41", "remaining_time": "0:03:40"}
+{"current_steps": 331, "total_steps": 364, "loss": 0.036, "lr": 4.983807997080925e-07, "epoch": 6.32484076433121, "percentage": 90.93, "elapsed_time": "0:35:45", "remaining_time": "0:03:33"}
+{"current_steps": 332, "total_steps": 364, "loss": 0.0371, "lr": 4.6886829178299676e-07, "epoch": 6.343949044585988, "percentage": 91.21, "elapsed_time": "0:35:49", "remaining_time": "0:03:27"}
+{"current_steps": 333, "total_steps": 364, "loss": 0.0489, "lr": 4.402355056911656e-07, "epoch": 6.3630573248407645, "percentage": 91.48, "elapsed_time": "0:35:53", "remaining_time": "0:03:20"}
+{"current_steps": 334, "total_steps": 364, "loss": 0.0487, "lr": 4.124850842338779e-07, "epoch": 6.382165605095541, "percentage": 91.76, "elapsed_time": "0:35:58", "remaining_time": "0:03:13"}
+{"current_steps": 335, "total_steps": 364, "loss": 0.0437, "lr": 3.8561958877030957e-07, "epoch": 6.401273885350318, "percentage": 92.03, "elapsed_time": "0:36:02", "remaining_time": "0:03:07"}
+{"current_steps": 336, "total_steps": 364, "loss": 0.0356, "lr": 3.5964149898111587e-07, "epoch": 6.420382165605096, "percentage": 92.31, "elapsed_time": "0:36:07", "remaining_time": "0:03:00"}
+{"current_steps": 337, "total_steps": 364, "loss": 0.0349, "lr": 3.345532126395579e-07, "epoch": 6.439490445859873, "percentage": 92.58, "elapsed_time": "0:36:11", "remaining_time": "0:02:53"}
+{"current_steps": 338, "total_steps": 364, "loss": 0.0378, "lr": 3.1035704539019384e-07, "epoch": 6.45859872611465, "percentage": 92.86, "elapsed_time": "0:36:15", "remaining_time": "0:02:47"}
+{"current_steps": 339, "total_steps": 364, "loss": 0.0445, "lr": 2.870552305351382e-07, "epoch": 6.477707006369426, "percentage": 93.13, "elapsed_time": "0:36:20", "remaining_time": "0:02:40"}
+{"current_steps": 340, "total_steps": 364, "loss": 0.0353, "lr": 2.646499188279328e-07, "epoch": 6.496815286624204, "percentage": 93.41, "elapsed_time": "0:36:24", "remaining_time": "0:02:34"}
+{"current_steps": 341, "total_steps": 364, "loss": 0.0379, "lr": 2.4314317827503375e-07, "epoch": 6.515923566878981, "percentage": 93.68, "elapsed_time": "0:36:32", "remaining_time": "0:02:27"}
+{"current_steps": 342, "total_steps": 364, "loss": 0.0356, "lr": 2.2253699394493066e-07, "epoch": 6.535031847133758, "percentage": 93.96, "elapsed_time": "0:36:36", "remaining_time": "0:02:21"}
+{"current_steps": 343, "total_steps": 364, "loss": 0.0368, "lr": 2.028332677849254e-07, "epoch": 6.554140127388535, "percentage": 94.23, "elapsed_time": "0:36:40", "remaining_time": "0:02:14"}
+{"current_steps": 344, "total_steps": 364, "loss": 0.0507, "lr": 1.840338184455881e-07, "epoch": 6.573248407643312, "percentage": 94.51, "elapsed_time": "0:36:45", "remaining_time": "0:02:08"}
+{"current_steps": 345, "total_steps": 364, "loss": 0.0343, "lr": 1.6614038111289034e-07, "epoch": 6.592356687898089, "percentage": 94.78, "elapsed_time": "0:36:49", "remaining_time": "0:02:01"}
+{"current_steps": 346, "total_steps": 364, "loss": 0.0378, "lr": 1.49154607348051e-07, "epoch": 6.611464968152866, "percentage": 95.05, "elapsed_time": "0:36:53", "remaining_time": "0:01:55"}
+{"current_steps": 347, "total_steps": 364, "loss": 0.0582, "lr": 1.330780649350938e-07, "epoch": 6.630573248407643, "percentage": 95.33, "elapsed_time": "0:36:59", "remaining_time": "0:01:48"}
+{"current_steps": 348, "total_steps": 364, "loss": 0.0348, "lr": 1.1791223773614635e-07, "epoch": 6.649681528662421, "percentage": 95.6, "elapsed_time": "0:37:03", "remaining_time": "0:01:42"}
+{"current_steps": 349, "total_steps": 364, "loss": 0.0314, "lr": 1.0365852555447642e-07, "epoch": 6.6687898089171975, "percentage": 95.88, "elapsed_time": "0:37:07", "remaining_time": "0:01:35"}
+{"current_steps": 350, "total_steps": 364, "loss": 0.0353, "lr": 9.031824400528854e-08, "epoch": 6.687898089171974, "percentage": 96.15, "elapsed_time": "0:37:11", "remaining_time": "0:01:29"}
+{"current_steps": 351, "total_steps": 364, "loss": 0.0528, "lr": 7.789262439430012e-08, "epoch": 6.707006369426751, "percentage": 96.43, "elapsed_time": "0:37:16", "remaining_time": "0:01:22"}
+{"current_steps": 352, "total_steps": 364, "loss": 0.0252, "lr": 6.638281360408339e-08, "epoch": 6.726114649681529, "percentage": 96.7, "elapsed_time": "0:37:20", "remaining_time": "0:01:16"}
+{"current_steps": 353, "total_steps": 364, "loss": 0.0398, "lr": 5.578987398821345e-08, "epoch": 6.745222929936306, "percentage": 96.98, "elapsed_time": "0:37:24", "remaining_time": "0:01:09"}
+{"current_steps": 354, "total_steps": 364, "loss": 0.0454, "lr": 4.6114783273213395e-08, "epoch": 6.764331210191083, "percentage": 97.25, "elapsed_time": "0:37:29", "remaining_time": "0:01:03"}
+{"current_steps": 355, "total_steps": 364, "loss": 0.0525, "lr": 3.735843446830867e-08, "epoch": 6.7834394904458595, "percentage": 97.53, "elapsed_time": "0:37:34", "remaining_time": "0:00:57"}
+{"current_steps": 356, "total_steps": 364, "loss": 0.0341, "lr": 2.9521635783001932e-08, "epoch": 6.802547770700637, "percentage": 97.8, "elapsed_time": "0:37:41", "remaining_time": "0:00:50"}
+{"current_steps": 357, "total_steps": 364, "loss": 0.0516, "lr": 2.2605110552477162e-08, "epoch": 6.821656050955414, "percentage": 98.08, "elapsed_time": "0:37:46", "remaining_time": "0:00:44"}
+{"current_steps": 358, "total_steps": 364, "loss": 0.0413, "lr": 1.6609497170834154e-08, "epoch": 6.840764331210191, "percentage": 98.35, "elapsed_time": "0:37:50", "remaining_time": "0:00:38"}
+{"current_steps": 359, "total_steps": 364, "loss": 0.0442, "lr": 1.1535349032167908e-08, "epoch": 6.859872611464969, "percentage": 98.63, "elapsed_time": "0:37:54", "remaining_time": "0:00:31"}
+{"current_steps": 360, "total_steps": 364, "loss": 0.0449, "lr": 7.3831344794872415e-09, "epoch": 6.8789808917197455, "percentage": 98.9, "elapsed_time": "0:37:59", "remaining_time": "0:00:25"}
+{"current_steps": 361, "total_steps": 364, "loss": 0.0263, "lr": 4.153236761488266e-09, "epoch": 6.898089171974522, "percentage": 99.18, "elapsed_time": "0:38:03", "remaining_time": "0:00:18"}
+{"current_steps": 362, "total_steps": 364, "loss": 0.0342, "lr": 1.8459539971804608e-09, "epoch": 6.917197452229299, "percentage": 99.45, "elapsed_time": "0:38:07", "remaining_time": "0:00:12"}
+{"current_steps": 363, "total_steps": 364, "loss": 0.0365, "lr": 4.614991483686826e-10, "epoch": 6.936305732484076, "percentage": 99.73, "elapsed_time": "0:38:12", "remaining_time": "0:00:06"}
+{"current_steps": 364, "total_steps": 364, "loss": 0.027, "lr": 0.0, "epoch": 6.955414012738854, "percentage": 100.0, "elapsed_time": "0:38:16", "remaining_time": "0:00:00"}
+{"current_steps": 364, "total_steps": 364, "epoch": 6.955414012738854, "percentage": 100.0, "elapsed_time": "0:41:18", "remaining_time": "0:00:00"}
+{"current_steps": 364, "total_steps": 364, "epoch": 6.955414012738854, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 364, "total_steps": 364, "epoch": 6.955414012738854, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2590 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.955414012738854,
+  "eval_steps": 500,
+  "global_step": 364,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01910828025477707,
+      "grad_norm": 13.061121504783694,
+      "learning_rate": 5.405405405405406e-07,
+      "loss": 1.1132,
+      "step": 1
+    },
+    {
+      "epoch": 0.03821656050955414,
+      "grad_norm": 13.004687369701202,
+      "learning_rate": 1.0810810810810812e-06,
+      "loss": 1.1203,
+      "step": 2
+    },
+    {
+      "epoch": 0.05732484076433121,
+      "grad_norm": 11.681093590032702,
+      "learning_rate": 1.6216216216216219e-06,
+      "loss": 1.072,
+      "step": 3
+    },
+    {
+      "epoch": 0.07643312101910828,
+      "grad_norm": 12.885995611098418,
+      "learning_rate": 2.1621621621621623e-06,
+      "loss": 1.0972,
+      "step": 4
+    },
+    {
+      "epoch": 0.09554140127388536,
+      "grad_norm": 10.753696451577982,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 1.0656,
+      "step": 5
+    },
+    {
+      "epoch": 0.11464968152866242,
+      "grad_norm": 8.70727988814562,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 0.9882,
+      "step": 6
+    },
+    {
+      "epoch": 0.1337579617834395,
+      "grad_norm": 5.828222678913531,
+      "learning_rate": 3.7837837837837844e-06,
+      "loss": 0.8802,
+      "step": 7
+    },
+    {
+      "epoch": 0.15286624203821655,
+      "grad_norm": 5.103320399232066,
+      "learning_rate": 4.324324324324325e-06,
+      "loss": 0.837,
+      "step": 8
+    },
+    {
+      "epoch": 0.17197452229299362,
+      "grad_norm": 4.667040332925033,
+      "learning_rate": 4.864864864864866e-06,
+      "loss": 0.8174,
+      "step": 9
+    },
+    {
+      "epoch": 0.1910828025477707,
+      "grad_norm": 5.9739073975563555,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 0.7624,
+      "step": 10
+    },
+    {
+      "epoch": 0.21019108280254778,
+      "grad_norm": 3.9163337836796552,
+      "learning_rate": 5.945945945945947e-06,
+      "loss": 0.7111,
+      "step": 11
+    },
+    {
+      "epoch": 0.22929936305732485,
+      "grad_norm": 3.3678455551817708,
+      "learning_rate": 6.486486486486487e-06,
+      "loss": 0.6858,
+      "step": 12
+    },
+    {
+      "epoch": 0.2484076433121019,
+      "grad_norm": 3.594154528384116,
+      "learning_rate": 7.027027027027028e-06,
+      "loss": 0.61,
+      "step": 13
+    },
+    {
+      "epoch": 0.267515923566879,
+      "grad_norm": 3.8733441586553266,
+      "learning_rate": 7.567567567567569e-06,
+      "loss": 0.5898,
+      "step": 14
+    },
+    {
+      "epoch": 0.28662420382165604,
+      "grad_norm": 3.3071183628933105,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 0.5504,
+      "step": 15
+    },
+    {
+      "epoch": 0.3057324840764331,
+      "grad_norm": 2.386602910953986,
+      "learning_rate": 8.64864864864865e-06,
+      "loss": 0.541,
+      "step": 16
+    },
+    {
+      "epoch": 0.3248407643312102,
+      "grad_norm": 1.7159227951209641,
+      "learning_rate": 9.189189189189191e-06,
+      "loss": 0.5369,
+      "step": 17
+    },
+    {
+      "epoch": 0.34394904458598724,
+      "grad_norm": 1.7955558727613306,
+      "learning_rate": 9.729729729729732e-06,
+      "loss": 0.5146,
+      "step": 18
+    },
+    {
+      "epoch": 0.3630573248407643,
+      "grad_norm": 1.8510654262469546,
+      "learning_rate": 1.027027027027027e-05,
+      "loss": 0.5047,
+      "step": 19
+    },
+    {
+      "epoch": 0.3821656050955414,
+      "grad_norm": 1.730654926481599,
+      "learning_rate": 1.0810810810810812e-05,
+      "loss": 0.5,
+      "step": 20
+    },
+    {
+      "epoch": 0.4012738853503185,
+      "grad_norm": 1.3280300305670263,
+      "learning_rate": 1.1351351351351352e-05,
+      "loss": 0.5057,
+      "step": 21
+    },
+    {
+      "epoch": 0.42038216560509556,
+      "grad_norm": 1.536606504206581,
+      "learning_rate": 1.1891891891891894e-05,
+      "loss": 0.483,
+      "step": 22
+    },
+    {
+      "epoch": 0.4394904458598726,
+      "grad_norm": 1.2909577362737017,
+      "learning_rate": 1.2432432432432433e-05,
+      "loss": 0.4743,
+      "step": 23
+    },
+    {
+      "epoch": 0.4585987261146497,
+      "grad_norm": 1.192667433323808,
+      "learning_rate": 1.2972972972972975e-05,
+      "loss": 0.4617,
+      "step": 24
+    },
+    {
+      "epoch": 0.47770700636942676,
+      "grad_norm": 1.3716595605419695,
+      "learning_rate": 1.3513513513513515e-05,
+      "loss": 0.4761,
+      "step": 25
+    },
+    {
+      "epoch": 0.4968152866242038,
+      "grad_norm": 1.0555595300584986,
+      "learning_rate": 1.4054054054054055e-05,
+      "loss": 0.4266,
+      "step": 26
+    },
+    {
+      "epoch": 0.5159235668789809,
+      "grad_norm": 1.0860853764278031,
+      "learning_rate": 1.4594594594594596e-05,
+      "loss": 0.4683,
+      "step": 27
+    },
+    {
+      "epoch": 0.535031847133758,
+      "grad_norm": 1.256758308024579,
+      "learning_rate": 1.5135135135135138e-05,
+      "loss": 0.4009,
+      "step": 28
+    },
+    {
+      "epoch": 0.554140127388535,
+      "grad_norm": 0.9945171549350766,
+      "learning_rate": 1.5675675675675676e-05,
+      "loss": 0.4609,
+      "step": 29
+    },
+    {
+      "epoch": 0.5732484076433121,
+      "grad_norm": 1.198075159689085,
+      "learning_rate": 1.6216216216216218e-05,
+      "loss": 0.4173,
+      "step": 30
+    },
+    {
+      "epoch": 0.5923566878980892,
+      "grad_norm": 1.1442607301532552,
+      "learning_rate": 1.6756756756756757e-05,
+      "loss": 0.4311,
+      "step": 31
+    },
+    {
+      "epoch": 0.6114649681528662,
+      "grad_norm": 1.129629164024121,
+      "learning_rate": 1.72972972972973e-05,
+      "loss": 0.4295,
+      "step": 32
+    },
+    {
+      "epoch": 0.6305732484076433,
+      "grad_norm": 1.0190838463058471,
+      "learning_rate": 1.783783783783784e-05,
+      "loss": 0.4211,
+      "step": 33
+    },
+    {
+      "epoch": 0.6496815286624203,
+      "grad_norm": 1.2143494438878666,
+      "learning_rate": 1.8378378378378383e-05,
+      "loss": 0.4391,
+      "step": 34
+    },
+    {
+      "epoch": 0.6687898089171974,
+      "grad_norm": 1.0693980542690755,
+      "learning_rate": 1.891891891891892e-05,
+      "loss": 0.4556,
+      "step": 35
+    },
+    {
+      "epoch": 0.6878980891719745,
+      "grad_norm": 1.1792054590625514,
+      "learning_rate": 1.9459459459459463e-05,
+      "loss": 0.4296,
+      "step": 36
+    },
+    {
+      "epoch": 0.7070063694267515,
+      "grad_norm": 1.1955493792662424,
+      "learning_rate": 2e-05,
+      "loss": 0.4189,
+      "step": 37
+    },
+    {
+      "epoch": 0.7261146496815286,
+      "grad_norm": 0.9777134544638197,
+      "learning_rate": 1.9999538500851633e-05,
+      "loss": 0.4141,
+      "step": 38
+    },
+    {
+      "epoch": 0.7452229299363057,
+      "grad_norm": 1.275259254590866,
+      "learning_rate": 1.9998154046002822e-05,
+      "loss": 0.4248,
+      "step": 39
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": 1.1432833678643584,
+      "learning_rate": 1.9995846763238514e-05,
+      "loss": 0.4054,
+      "step": 40
+    },
+    {
+      "epoch": 0.7834394904458599,
+      "grad_norm": 1.3172231020503005,
+      "learning_rate": 1.9992616865520515e-05,
+      "loss": 0.3879,
+      "step": 41
+    },
+    {
+      "epoch": 0.802547770700637,
+      "grad_norm": 1.0583780017735775,
+      "learning_rate": 1.9988464650967834e-05,
+      "loss": 0.4109,
+      "step": 42
+    },
+    {
+      "epoch": 0.821656050955414,
+      "grad_norm": 0.9617173379690138,
+      "learning_rate": 1.9983390502829168e-05,
+      "loss": 0.3974,
+      "step": 43
+    },
+    {
+      "epoch": 0.8407643312101911,
+      "grad_norm": 0.9367732241820612,
+      "learning_rate": 1.9977394889447526e-05,
+      "loss": 0.3866,
+      "step": 44
+    },
+    {
+      "epoch": 0.8598726114649682,
+      "grad_norm": 0.9127964038098744,
+      "learning_rate": 1.9970478364217e-05,
+      "loss": 0.3965,
+      "step": 45
+    },
+    {
+      "epoch": 0.8789808917197452,
+      "grad_norm": 0.8549449240355445,
+      "learning_rate": 1.9962641565531694e-05,
+      "loss": 0.3955,
+      "step": 46
+    },
+    {
+      "epoch": 0.8980891719745223,
+      "grad_norm": 0.9867301722628401,
+      "learning_rate": 1.9953885216726788e-05,
+      "loss": 0.4011,
+      "step": 47
+    },
+    {
+      "epoch": 0.9171974522292994,
+      "grad_norm": 0.9394602334631543,
+      "learning_rate": 1.994421012601179e-05,
+      "loss": 0.3994,
+      "step": 48
+    },
+    {
+      "epoch": 0.9363057324840764,
+      "grad_norm": 0.8821538501470763,
+      "learning_rate": 1.9933617186395917e-05,
+      "loss": 0.3816,
+      "step": 49
+    },
+    {
+      "epoch": 0.9554140127388535,
+      "grad_norm": 1.0127344001139693,
+      "learning_rate": 1.99221073756057e-05,
+      "loss": 0.4186,
+      "step": 50
+    },
+    {
+      "epoch": 0.9745222929936306,
+      "grad_norm": 0.8834622594396443,
+      "learning_rate": 1.990968175599471e-05,
+      "loss": 0.4176,
+      "step": 51
+    },
+    {
+      "epoch": 0.9936305732484076,
+      "grad_norm": 0.8884121911786073,
+      "learning_rate": 1.9896341474445526e-05,
+      "loss": 0.3976,
+      "step": 52
+    },
+    {
+      "epoch": 1.0127388535031847,
+      "grad_norm": 0.9752480208328478,
+      "learning_rate": 1.9882087762263857e-05,
+      "loss": 0.3684,
+      "step": 53
+    },
+    {
+      "epoch": 1.0318471337579618,
+      "grad_norm": 0.8827492310600606,
+      "learning_rate": 1.9866921935064907e-05,
+      "loss": 0.332,
+      "step": 54
+    },
+    {
+      "epoch": 1.0509554140127388,
+      "grad_norm": 1.0592500053036995,
+      "learning_rate": 1.985084539265195e-05,
+      "loss": 0.3523,
+      "step": 55
+    },
+    {
+      "epoch": 1.070063694267516,
+      "grad_norm": 0.8894543457755348,
+      "learning_rate": 1.983385961888711e-05,
+      "loss": 0.3353,
+      "step": 56
+    },
+    {
+      "epoch": 1.089171974522293,
+      "grad_norm": 1.0144016620696499,
+      "learning_rate": 1.9815966181554412e-05,
+      "loss": 0.3593,
+      "step": 57
+    },
+    {
+      "epoch": 1.10828025477707,
+      "grad_norm": 0.8338972951363072,
+      "learning_rate": 1.9797166732215078e-05,
+      "loss": 0.3042,
+      "step": 58
+    },
+    {
+      "epoch": 1.127388535031847,
+      "grad_norm": 0.8620369330635748,
+      "learning_rate": 1.977746300605507e-05,
+      "loss": 0.3179,
+      "step": 59
+    },
+    {
+      "epoch": 1.1464968152866242,
+      "grad_norm": 0.857609450862733,
+      "learning_rate": 1.975685682172497e-05,
+      "loss": 0.3195,
+      "step": 60
+    },
+    {
+      "epoch": 1.1656050955414012,
+      "grad_norm": 0.9137478597580723,
+      "learning_rate": 1.973535008117207e-05,
+      "loss": 0.3361,
+      "step": 61
+    },
+    {
+      "epoch": 1.1847133757961783,
+      "grad_norm": 0.8283885349913659,
+      "learning_rate": 1.9712944769464864e-05,
+      "loss": 0.3151,
+      "step": 62
+    },
+    {
+      "epoch": 1.2038216560509554,
+      "grad_norm": 0.8550343289316428,
+      "learning_rate": 1.9689642954609808e-05,
+      "loss": 0.3288,
+      "step": 63
+    },
+    {
+      "epoch": 1.2229299363057324,
+      "grad_norm": 0.8208472982782141,
+      "learning_rate": 1.9665446787360444e-05,
+      "loss": 0.3403,
+      "step": 64
+    },
+    {
+      "epoch": 1.2420382165605095,
+      "grad_norm": 0.882504462864626,
+      "learning_rate": 1.9640358501018885e-05,
+      "loss": 0.3093,
+      "step": 65
+    },
+    {
+      "epoch": 1.2611464968152866,
+      "grad_norm": 0.7671621002994656,
+      "learning_rate": 1.9614380411229693e-05,
+      "loss": 0.3077,
+      "step": 66
+    },
+    {
+      "epoch": 1.2802547770700636,
+      "grad_norm": 0.8647735112563046,
+      "learning_rate": 1.9587514915766124e-05,
+      "loss": 0.3222,
+      "step": 67
+    },
+    {
+      "epoch": 1.2993630573248407,
+      "grad_norm": 0.8954403576127878,
+      "learning_rate": 1.9559764494308838e-05,
+      "loss": 0.304,
+      "step": 68
+    },
+    {
+      "epoch": 1.3184713375796178,
+      "grad_norm": 0.8088711570430884,
+      "learning_rate": 1.9531131708217005e-05,
+      "loss": 0.3404,
+      "step": 69
+    },
+    {
+      "epoch": 1.3375796178343948,
+      "grad_norm": 0.8224093302041183,
+      "learning_rate": 1.950161920029191e-05,
+      "loss": 0.3178,
+      "step": 70
+    },
+    {
+      "epoch": 1.356687898089172,
+      "grad_norm": 0.8105986300173356,
+      "learning_rate": 1.9471229694533003e-05,
+      "loss": 0.3179,
+      "step": 71
+    },
+    {
+      "epoch": 1.3757961783439492,
+      "grad_norm": 0.7874255867976999,
+      "learning_rate": 1.943996599588649e-05,
+      "loss": 0.3393,
+      "step": 72
+    },
+    {
+      "epoch": 1.394904458598726,
+      "grad_norm": 0.781901263359997,
+      "learning_rate": 1.940783098998643e-05,
+      "loss": 0.3292,
+      "step": 73
+    },
+    {
+      "epoch": 1.4140127388535033,
+      "grad_norm": 0.7464815439188515,
+      "learning_rate": 1.93748276428884e-05,
+      "loss": 0.304,
+      "step": 74
+    },
+    {
+      "epoch": 1.4331210191082802,
+      "grad_norm": 0.7432622748403789,
+      "learning_rate": 1.9340959000795707e-05,
+      "loss": 0.2991,
+      "step": 75
+    },
+    {
+      "epoch": 1.4522292993630574,
+      "grad_norm": 0.7992820400351971,
+      "learning_rate": 1.9306228189778255e-05,
+      "loss": 0.3389,
+      "step": 76
+    },
+    {
+      "epoch": 1.4713375796178343,
+      "grad_norm": 0.8258539894170773,
+      "learning_rate": 1.927063841548398e-05,
+      "loss": 0.3287,
+      "step": 77
+    },
+    {
+      "epoch": 1.4904458598726116,
+      "grad_norm": 0.7922657009240832,
+      "learning_rate": 1.9234192962842996e-05,
+      "loss": 0.3171,
+      "step": 78
+    },
+    {
+      "epoch": 1.5095541401273884,
+      "grad_norm": 0.8477548969242173,
+      "learning_rate": 1.9196895195764363e-05,
+      "loss": 0.3211,
+      "step": 79
+    },
+    {
+      "epoch": 1.5286624203821657,
+      "grad_norm": 0.8173452598897418,
+      "learning_rate": 1.9158748556825637e-05,
+      "loss": 0.3178,
+      "step": 80
+    },
+    {
+      "epoch": 1.5477707006369426,
+      "grad_norm": 0.9606115469544766,
+      "learning_rate": 1.9119756566955092e-05,
+      "loss": 0.3292,
+      "step": 81
+    },
+    {
+      "epoch": 1.5668789808917198,
+      "grad_norm": 0.8342406535066685,
+      "learning_rate": 1.907992282510675e-05,
+      "loss": 0.3301,
+      "step": 82
+    },
+    {
+      "epoch": 1.5859872611464967,
+      "grad_norm": 0.8693183657458963,
+      "learning_rate": 1.90392510079282e-05,
+      "loss": 0.3269,
+      "step": 83
+    },
+    {
+      "epoch": 1.605095541401274,
+      "grad_norm": 0.8292008033326259,
+      "learning_rate": 1.8997744869421248e-05,
+      "loss": 0.3106,
+      "step": 84
+    },
+    {
+      "epoch": 1.6242038216560508,
+      "grad_norm": 0.8346381762675072,
+      "learning_rate": 1.8955408240595396e-05,
+      "loss": 0.2997,
+      "step": 85
+    },
+    {
+      "epoch": 1.643312101910828,
+      "grad_norm": 0.8137875698610653,
+      "learning_rate": 1.891224502911428e-05,
+      "loss": 0.3,
+      "step": 86
+    },
+    {
+      "epoch": 1.662420382165605,
+      "grad_norm": 0.8274055442526331,
+      "learning_rate": 1.886825921893497e-05,
+      "loss": 0.3277,
+      "step": 87
+    },
+    {
+      "epoch": 1.6815286624203822,
+      "grad_norm": 0.7827697609836849,
+      "learning_rate": 1.8823454869940243e-05,
+      "loss": 0.3143,
+      "step": 88
+    },
+    {
+      "epoch": 1.700636942675159,
+      "grad_norm": 0.8280008352451795,
+      "learning_rate": 1.8777836117563894e-05,
+      "loss": 0.331,
+      "step": 89
+    },
+    {
+      "epoch": 1.7197452229299364,
+      "grad_norm": 0.8435002081853953,
+      "learning_rate": 1.873140717240899e-05,
+      "loss": 0.3243,
+      "step": 90
+    },
+    {
+      "epoch": 1.7388535031847132,
+      "grad_norm": 0.8207347908459873,
+      "learning_rate": 1.8684172319859258e-05,
+      "loss": 0.3144,
+      "step": 91
+    },
+    {
+      "epoch": 1.7579617834394905,
+      "grad_norm": 0.7996796478766166,
+      "learning_rate": 1.863613591968355e-05,
+      "loss": 0.3367,
+      "step": 92
+    },
+    {
+      "epoch": 1.7770700636942676,
+      "grad_norm": 0.7605595917256908,
+      "learning_rate": 1.858730240563342e-05,
+      "loss": 0.3234,
+      "step": 93
+    },
+    {
+      "epoch": 1.7961783439490446,
+      "grad_norm": 0.8494651563432526,
+      "learning_rate": 1.8537676285033886e-05,
+      "loss": 0.3118,
+      "step": 94
+    },
+    {
+      "epoch": 1.8152866242038217,
+      "grad_norm": 0.837292745103268,
+      "learning_rate": 1.848726213836744e-05,
+      "loss": 0.3153,
+      "step": 95
+    },
+    {
+      "epoch": 1.8343949044585988,
+      "grad_norm": 0.8385839835422961,
+      "learning_rate": 1.8436064618851225e-05,
+      "loss": 0.3233,
+      "step": 96
+    },
+    {
+      "epoch": 1.8535031847133758,
+      "grad_norm": 0.749500397970389,
+      "learning_rate": 1.838408845200758e-05,
+      "loss": 0.3059,
+      "step": 97
+    },
+    {
+      "epoch": 1.872611464968153,
+      "grad_norm": 0.8273190127592467,
+      "learning_rate": 1.8331338435227838e-05,
+      "loss": 0.3112,
+      "step": 98
+    },
+    {
+      "epoch": 1.89171974522293,
+      "grad_norm": 0.7859806352358789,
+      "learning_rate": 1.8277819437329577e-05,
+      "loss": 0.3312,
+      "step": 99
+    },
+    {
+      "epoch": 1.910828025477707,
+      "grad_norm": 0.8457471823864225,
+      "learning_rate": 1.8223536398107177e-05,
+      "loss": 0.3118,
+      "step": 100
+    },
+    {
+      "epoch": 1.929936305732484,
+      "grad_norm": 0.7532076153649954,
+      "learning_rate": 1.8168494327875918e-05,
+      "loss": 0.3129,
+      "step": 101
+    },
+    {
+      "epoch": 1.9490445859872612,
+      "grad_norm": 0.7303913673017364,
+      "learning_rate": 1.8112698307009506e-05,
+      "loss": 0.3359,
+      "step": 102
+    },
+    {
+      "epoch": 1.9681528662420382,
+      "grad_norm": 0.8099892264373676,
+      "learning_rate": 1.8056153485471167e-05,
+      "loss": 0.322,
+      "step": 103
+    },
+    {
+      "epoch": 1.9872611464968153,
+      "grad_norm": 0.7156973850063414,
+      "learning_rate": 1.799886508233829e-05,
+      "loss": 0.3032,
+      "step": 104
+    },
+    {
+      "epoch": 2.0063694267515926,
+      "grad_norm": 0.8786299179043141,
+      "learning_rate": 1.7940838385320732e-05,
+      "loss": 0.2791,
+      "step": 105
+    },
+    {
+      "epoch": 2.0254777070063694,
+      "grad_norm": 0.7339705194786788,
+      "learning_rate": 1.788207875027274e-05,
+      "loss": 0.2362,
+      "step": 106
+    },
+    {
+      "epoch": 2.0445859872611467,
+      "grad_norm": 0.8215525831052096,
+      "learning_rate": 1.7822591600698632e-05,
+      "loss": 0.2282,
+      "step": 107
+    },
+    {
+      "epoch": 2.0636942675159236,
+      "grad_norm": 1.0200364445695218,
+      "learning_rate": 1.776238242725217e-05,
+      "loss": 0.229,
+      "step": 108
+    },
+    {
+      "epoch": 2.082802547770701,
+      "grad_norm": 0.7199268686358128,
+      "learning_rate": 1.7701456787229805e-05,
+      "loss": 0.2259,
+      "step": 109
+    },
+    {
+      "epoch": 2.1019108280254777,
+      "grad_norm": 0.7690060643003057,
+      "learning_rate": 1.7639820304057745e-05,
+      "loss": 0.2335,
+      "step": 110
+    },
+    {
+      "epoch": 2.121019108280255,
+      "grad_norm": 0.7691552552958395,
+      "learning_rate": 1.7577478666772886e-05,
+      "loss": 0.2392,
+      "step": 111
+    },
+    {
+      "epoch": 2.140127388535032,
+      "grad_norm": 0.7623742417857657,
+      "learning_rate": 1.751443762949772e-05,
+      "loss": 0.218,
+      "step": 112
+    },
+    {
+      "epoch": 2.159235668789809,
+      "grad_norm": 0.7453231612323414,
+      "learning_rate": 1.7450703010909263e-05,
+      "loss": 0.2299,
+      "step": 113
+    },
+    {
+      "epoch": 2.178343949044586,
+      "grad_norm": 0.7286978309025909,
+      "learning_rate": 1.738628069370195e-05,
+      "loss": 0.2148,
+      "step": 114
+    },
+    {
+      "epoch": 2.1974522292993632,
+      "grad_norm": 0.7257194609747826,
+      "learning_rate": 1.732117662404469e-05,
+      "loss": 0.2192,
+      "step": 115
+    },
+    {
+      "epoch": 2.21656050955414,
+      "grad_norm": 0.7672551296978565,
+      "learning_rate": 1.7255396811032014e-05,
+      "loss": 0.207,
+      "step": 116
+    },
+    {
+      "epoch": 2.2356687898089174,
+      "grad_norm": 0.6947911224147608,
+      "learning_rate": 1.718894732612947e-05,
+      "loss": 0.2189,
+      "step": 117
+    },
+    {
+      "epoch": 2.254777070063694,
+      "grad_norm": 0.7016304029732124,
+      "learning_rate": 1.712183430261319e-05,
+      "loss": 0.2242,
+      "step": 118
+    },
+    {
+      "epoch": 2.2738853503184715,
+      "grad_norm": 0.8082701007835484,
+      "learning_rate": 1.7054063935003813e-05,
+      "loss": 0.2164,
+      "step": 119
+    },
+    {
+      "epoch": 2.2929936305732483,
+      "grad_norm": 0.7220294352827958,
+      "learning_rate": 1.698564247849473e-05,
+      "loss": 0.2326,
+      "step": 120
+    },
+    {
+      "epoch": 2.3121019108280256,
+      "grad_norm": 0.771410967281071,
+      "learning_rate": 1.691657624837472e-05,
+      "loss": 0.2085,
+      "step": 121
+    },
+    {
+      "epoch": 2.3312101910828025,
+      "grad_norm": 0.7724058012223507,
+      "learning_rate": 1.684687161944506e-05,
+      "loss": 0.1972,
+      "step": 122
+    },
+    {
+      "epoch": 2.3503184713375798,
+      "grad_norm": 0.7661404719047822,
+      "learning_rate": 1.677653502543113e-05,
+      "loss": 0.2213,
+      "step": 123
+    },
+    {
+      "epoch": 2.3694267515923566,
+      "grad_norm": 0.6738257717857431,
+      "learning_rate": 1.6705572958388576e-05,
+      "loss": 0.1919,
+      "step": 124
+    },
+    {
+      "epoch": 2.388535031847134,
+      "grad_norm": 0.8382199898018106,
+      "learning_rate": 1.6633991968104095e-05,
+      "loss": 0.223,
+      "step": 125
+    },
+    {
+      "epoch": 2.4076433121019107,
+      "grad_norm": 0.7383963648701479,
+      "learning_rate": 1.6561798661490904e-05,
+      "loss": 0.232,
+      "step": 126
+    },
+    {
+      "epoch": 2.426751592356688,
+      "grad_norm": 0.6708065713740249,
+      "learning_rate": 1.6488999701978905e-05,
+      "loss": 0.2398,
+      "step": 127
+    },
+    {
+      "epoch": 2.445859872611465,
+      "grad_norm": 0.7102536685773432,
+      "learning_rate": 1.6415601808899658e-05,
+      "loss": 0.2201,
+      "step": 128
+    },
+    {
+      "epoch": 2.464968152866242,
+      "grad_norm": 0.7340226922958114,
+      "learning_rate": 1.63416117568662e-05,
+      "loss": 0.23,
+      "step": 129
+    },
+    {
+      "epoch": 2.484076433121019,
+      "grad_norm": 0.6863912101829568,
+      "learning_rate": 1.6267036375147728e-05,
+      "loss": 0.2104,
+      "step": 130
+    },
+    {
+      "epoch": 2.5031847133757963,
+      "grad_norm": 0.7146938908241688,
+      "learning_rate": 1.619188254703927e-05,
+      "loss": 0.2196,
+      "step": 131
+    },
+    {
+      "epoch": 2.522292993630573,
+      "grad_norm": 0.7400106936261759,
+      "learning_rate": 1.6116157209226356e-05,
+      "loss": 0.219,
+      "step": 132
+    },
+    {
+      "epoch": 2.5414012738853504,
+      "grad_norm": 0.729546945096026,
+      "learning_rate": 1.6039867351144778e-05,
+      "loss": 0.2087,
+      "step": 133
+    },
+    {
+      "epoch": 2.5605095541401273,
+      "grad_norm": 0.7155341534978575,
+      "learning_rate": 1.5963020014335437e-05,
+      "loss": 0.2061,
+      "step": 134
+    },
+    {
+      "epoch": 2.5796178343949046,
+      "grad_norm": 0.6957987252330176,
+      "learning_rate": 1.588562229179443e-05,
+      "loss": 0.2488,
+      "step": 135
+    },
+    {
+      "epoch": 2.5987261146496814,
+      "grad_norm": 0.6499631048940339,
+      "learning_rate": 1.5807681327318372e-05,
+      "loss": 0.2078,
+      "step": 136
+    },
+    {
+      "epoch": 2.6178343949044587,
+      "grad_norm": 0.6814737907080584,
+      "learning_rate": 1.5729204314845002e-05,
+      "loss": 0.2356,
+      "step": 137
+    },
+    {
+      "epoch": 2.6369426751592355,
+      "grad_norm": 0.7192501496005376,
+      "learning_rate": 1.56501984977892e-05,
+      "loss": 0.2237,
+      "step": 138
+    },
+    {
+      "epoch": 2.656050955414013,
+      "grad_norm": 0.6460239347566714,
+      "learning_rate": 1.557067116837444e-05,
+      "loss": 0.2207,
+      "step": 139
+    },
+    {
+      "epoch": 2.6751592356687897,
+      "grad_norm": 0.681845919595809,
+      "learning_rate": 1.5490629666959668e-05,
+      "loss": 0.2186,
+      "step": 140
+    },
+    {
+      "epoch": 2.694267515923567,
+      "grad_norm": 0.6809596022956802,
+      "learning_rate": 1.541008138136183e-05,
+      "loss": 0.2317,
+      "step": 141
+    },
+    {
+      "epoch": 2.713375796178344,
+      "grad_norm": 0.7493561663715341,
+      "learning_rate": 1.5329033746173975e-05,
+      "loss": 0.2356,
+      "step": 142
+    },
+    {
+      "epoch": 2.732484076433121,
+      "grad_norm": 0.7176706940288995,
+      "learning_rate": 1.5247494242079024e-05,
+      "loss": 0.2492,
+      "step": 143
+    },
+    {
+      "epoch": 2.7515923566878984,
+      "grad_norm": 0.7340152150846796,
+      "learning_rate": 1.5165470395159314e-05,
+      "loss": 0.2148,
+      "step": 144
+    },
+    {
+      "epoch": 2.770700636942675,
+      "grad_norm": 0.6971800536161769,
+      "learning_rate": 1.5082969776201948e-05,
+      "loss": 0.2244,
+      "step": 145
+    },
+    {
+      "epoch": 2.789808917197452,
+      "grad_norm": 0.6423294390732299,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2064,
+      "step": 146
+    },
+    {
+      "epoch": 2.8089171974522293,
+      "grad_norm": 0.6449855098152328,
+      "learning_rate": 1.4916568724649688e-05,
+      "loss": 0.2195,
+      "step": 147
+    },
+    {
+      "epoch": 2.8280254777070066,
+      "grad_norm": 0.6456522077145121,
+      "learning_rate": 1.483268365084351e-05,
+      "loss": 0.2182,
+      "step": 148
+    },
+    {
+      "epoch": 2.8471337579617835,
+      "grad_norm": 0.6951034427850712,
+      "learning_rate": 1.4748352521159492e-05,
+      "loss": 0.2205,
+      "step": 149
+    },
+    {
+      "epoch": 2.8662420382165603,
+      "grad_norm": 0.7483091211255399,
+      "learning_rate": 1.466358311934654e-05,
+      "loss": 0.2237,
+      "step": 150
+    },
+    {
+      "epoch": 2.8853503184713376,
+      "grad_norm": 0.6883367100562658,
+      "learning_rate": 1.4578383269606004e-05,
+      "loss": 0.2195,
+      "step": 151
+    },
+    {
+      "epoch": 2.904458598726115,
+      "grad_norm": 0.7284907501161144,
+      "learning_rate": 1.4492760835869504e-05,
+      "loss": 0.2084,
+      "step": 152
+    },
+    {
+      "epoch": 2.9235668789808917,
+      "grad_norm": 0.7447694394278404,
+      "learning_rate": 1.4406723721073088e-05,
+      "loss": 0.2333,
+      "step": 153
+    },
+    {
+      "epoch": 2.9426751592356686,
+      "grad_norm": 0.67492470531107,
+      "learning_rate": 1.4320279866427798e-05,
+      "loss": 0.2314,
+      "step": 154
+    },
+    {
+      "epoch": 2.961783439490446,
+      "grad_norm": 0.6702225436247404,
+      "learning_rate": 1.4233437250686695e-05,
+      "loss": 0.2141,
+      "step": 155
+    },
+    {
+      "epoch": 2.980891719745223,
+      "grad_norm": 0.7764093894079096,
+      "learning_rate": 1.4146203889408418e-05,
+      "loss": 0.212,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7313308826851314,
+      "learning_rate": 1.4058587834217356e-05,
+      "loss": 0.2119,
+      "step": 157
+    },
+    {
+      "epoch": 3.0191082802547773,
+      "grad_norm": 0.7530776586523136,
+      "learning_rate": 1.3970597172060482e-05,
+      "loss": 0.1469,
+      "step": 158
+    },
+    {
+      "epoch": 3.038216560509554,
+      "grad_norm": 0.6611962341522755,
+      "learning_rate": 1.3882240024460928e-05,
+      "loss": 0.1612,
+      "step": 159
+    },
+    {
+      "epoch": 3.0573248407643314,
+      "grad_norm": 0.6357740044432496,
+      "learning_rate": 1.3793524546768358e-05,
+      "loss": 0.1481,
+      "step": 160
+    },
+    {
+      "epoch": 3.0764331210191083,
+      "grad_norm": 0.8864508304938629,
+      "learning_rate": 1.3704458927406261e-05,
+      "loss": 0.1696,
+      "step": 161
+    },
+    {
+      "epoch": 3.0955414012738856,
+      "grad_norm": 0.8069256551649886,
+      "learning_rate": 1.3615051387116131e-05,
+      "loss": 0.1448,
+      "step": 162
+    },
+    {
+      "epoch": 3.1146496815286624,
+      "grad_norm": 0.6676046649310723,
+      "learning_rate": 1.3525310178198707e-05,
+      "loss": 0.141,
+      "step": 163
+    },
+    {
+      "epoch": 3.1337579617834397,
+      "grad_norm": 0.6472538605206934,
+      "learning_rate": 1.3435243583752294e-05,
+      "loss": 0.1313,
+      "step": 164
+    },
+    {
+      "epoch": 3.1528662420382165,
+      "grad_norm": 0.6878661872765675,
+      "learning_rate": 1.3344859916908206e-05,
+      "loss": 0.1441,
+      "step": 165
+    },
+    {
+      "epoch": 3.171974522292994,
+      "grad_norm": 0.6835263760912518,
+      "learning_rate": 1.325416752006351e-05,
+      "loss": 0.1263,
+      "step": 166
+    },
+    {
+      "epoch": 3.1910828025477707,
+      "grad_norm": 0.6092343553397929,
+      "learning_rate": 1.3163174764110985e-05,
+      "loss": 0.1485,
+      "step": 167
+    },
+    {
+      "epoch": 3.210191082802548,
+      "grad_norm": 0.644634711013181,
+      "learning_rate": 1.3071890047666498e-05,
+      "loss": 0.156,
+      "step": 168
+    },
+    {
+      "epoch": 3.229299363057325,
+      "grad_norm": 0.6289787607697578,
+      "learning_rate": 1.2980321796293838e-05,
+      "loss": 0.1404,
+      "step": 169
+    },
+    {
+      "epoch": 3.248407643312102,
+      "grad_norm": 0.6456910690374158,
+      "learning_rate": 1.288847846172701e-05,
+      "loss": 0.1366,
+      "step": 170
+    },
+    {
+      "epoch": 3.267515923566879,
+      "grad_norm": 0.684838061887636,
+      "learning_rate": 1.2796368521090143e-05,
+      "loss": 0.1354,
+      "step": 171
+    },
+    {
+      "epoch": 3.286624203821656,
+      "grad_norm": 0.6337711938504159,
+      "learning_rate": 1.2704000476115079e-05,
+      "loss": 0.148,
+      "step": 172
+    },
+    {
+      "epoch": 3.305732484076433,
+      "grad_norm": 0.5978370836663967,
+      "learning_rate": 1.2611382852356632e-05,
+      "loss": 0.1398,
+      "step": 173
+    },
+    {
+      "epoch": 3.3248407643312103,
+      "grad_norm": 0.6332332089790007,
+      "learning_rate": 1.2518524198405699e-05,
+      "loss": 0.1396,
+      "step": 174
+    },
+    {
+      "epoch": 3.343949044585987,
+      "grad_norm": 0.6477361858083517,
+      "learning_rate": 1.2425433085100224e-05,
+      "loss": 0.1502,
+      "step": 175
+    },
+    {
+      "epoch": 3.3630573248407645,
+      "grad_norm": 0.6643933524216447,
+      "learning_rate": 1.233211810473411e-05,
+      "loss": 0.1625,
+      "step": 176
+    },
+    {
+      "epoch": 3.3821656050955413,
+      "grad_norm": 0.6247707544349919,
+      "learning_rate": 1.2238587870264152e-05,
+      "loss": 0.1456,
+      "step": 177
+    },
+    {
+      "epoch": 3.4012738853503186,
+      "grad_norm": 0.6689444359666585,
+      "learning_rate": 1.2144851014515055e-05,
+      "loss": 0.147,
+      "step": 178
+    },
+    {
+      "epoch": 3.4203821656050954,
+      "grad_norm": 0.6497397655937013,
+      "learning_rate": 1.2050916189382646e-05,
+      "loss": 0.1621,
+      "step": 179
+    },
+    {
+      "epoch": 3.4394904458598727,
+      "grad_norm": 0.6818698518486883,
+      "learning_rate": 1.1956792065035281e-05,
+      "loss": 0.1423,
+      "step": 180
+    },
+    {
+      "epoch": 3.4585987261146496,
+      "grad_norm": 0.593513542354787,
+      "learning_rate": 1.1862487329113606e-05,
+      "loss": 0.1435,
+      "step": 181
+    },
+    {
+      "epoch": 3.477707006369427,
+      "grad_norm": 0.6690546132714484,
+      "learning_rate": 1.1768010685928686e-05,
+      "loss": 0.1372,
+      "step": 182
+    },
+    {
+      "epoch": 3.4968152866242037,
+      "grad_norm": 0.6581783248536756,
+      "learning_rate": 1.1673370855658592e-05,
+      "loss": 0.1605,
+      "step": 183
+    },
+    {
+      "epoch": 3.515923566878981,
+      "grad_norm": 0.6379212541115541,
+      "learning_rate": 1.1578576573543541e-05,
+      "loss": 0.1324,
+      "step": 184
+    },
+    {
+      "epoch": 3.535031847133758,
+      "grad_norm": 0.600687727011327,
+      "learning_rate": 1.1483636589079627e-05,
+      "loss": 0.1312,
+      "step": 185
+    },
+    {
+      "epoch": 3.554140127388535,
+      "grad_norm": 0.6418013587643382,
+      "learning_rate": 1.1388559665211241e-05,
+      "loss": 0.1617,
+      "step": 186
+    },
+    {
+      "epoch": 3.573248407643312,
+      "grad_norm": 0.6339297581036465,
+      "learning_rate": 1.1293354577522264e-05,
+      "loss": 0.1624,
+      "step": 187
+    },
+    {
+      "epoch": 3.5923566878980893,
+      "grad_norm": 0.5817749236320355,
+      "learning_rate": 1.1198030113426074e-05,
+      "loss": 0.1346,
+      "step": 188
+    },
+    {
+      "epoch": 3.611464968152866,
+      "grad_norm": 0.6276381965084356,
+      "learning_rate": 1.1102595071354471e-05,
+      "loss": 0.1549,
+      "step": 189
+    },
+    {
+      "epoch": 3.6305732484076434,
+      "grad_norm": 0.6195637812445436,
+      "learning_rate": 1.1007058259945584e-05,
+      "loss": 0.1558,
+      "step": 190
+    },
+    {
+      "epoch": 3.6496815286624202,
+      "grad_norm": 0.6428563189336818,
+      "learning_rate": 1.0911428497230834e-05,
+      "loss": 0.1543,
+      "step": 191
+    },
+    {
+      "epoch": 3.6687898089171975,
+      "grad_norm": 0.5896919367538869,
+      "learning_rate": 1.0815714609821027e-05,
+      "loss": 0.1325,
+      "step": 192
+    },
+    {
+      "epoch": 3.6878980891719744,
+      "grad_norm": 0.6036673420283875,
+      "learning_rate": 1.0719925432091671e-05,
+      "loss": 0.1668,
+      "step": 193
+    },
+    {
+      "epoch": 3.7070063694267517,
+      "grad_norm": 0.6085161249391848,
+      "learning_rate": 1.0624069805367558e-05,
+      "loss": 0.1307,
+      "step": 194
+    },
+    {
+      "epoch": 3.7261146496815285,
+      "grad_norm": 0.5869321522437492,
+      "learning_rate": 1.0528156577106703e-05,
+      "loss": 0.1568,
+      "step": 195
+    },
+    {
+      "epoch": 3.745222929936306,
+      "grad_norm": 0.5924933753607252,
+      "learning_rate": 1.043219460008374e-05,
+      "loss": 0.1563,
+      "step": 196
+    },
+    {
+      "epoch": 3.7643312101910826,
+      "grad_norm": 0.5850121501448747,
+      "learning_rate": 1.0336192731572805e-05,
+      "loss": 0.1283,
+      "step": 197
+    },
+    {
+      "epoch": 3.78343949044586,
+      "grad_norm": 0.5977736436214779,
+      "learning_rate": 1.0240159832530007e-05,
+      "loss": 0.148,
+      "step": 198
+    },
+    {
+      "epoch": 3.802547770700637,
+      "grad_norm": 0.5902857834706218,
+      "learning_rate": 1.0144104766775574e-05,
+      "loss": 0.1394,
+      "step": 199
+    },
+    {
+      "epoch": 3.821656050955414,
+      "grad_norm": 0.6175785594017269,
+      "learning_rate": 1.004803640017571e-05,
+      "loss": 0.1423,
+      "step": 200
+    },
+    {
+      "epoch": 3.840764331210191,
+      "grad_norm": 0.6081802512853927,
+      "learning_rate": 9.951963599824294e-06,
+      "loss": 0.1582,
+      "step": 201
+    },
+    {
+      "epoch": 3.859872611464968,
+      "grad_norm": 0.6314563069212991,
+      "learning_rate": 9.855895233224431e-06,
+      "loss": 0.1525,
+      "step": 202
+    },
+    {
+      "epoch": 3.8789808917197455,
+      "grad_norm": 0.5789919260908164,
+      "learning_rate": 9.759840167469995e-06,
+      "loss": 0.1336,
+      "step": 203
+    },
+    {
+      "epoch": 3.8980891719745223,
+      "grad_norm": 0.6121971930148541,
+      "learning_rate": 9.663807268427197e-06,
+      "loss": 0.154,
+      "step": 204
+    },
+    {
+      "epoch": 3.917197452229299,
+      "grad_norm": 0.5752358774196049,
+      "learning_rate": 9.56780539991626e-06,
+      "loss": 0.1511,
+      "step": 205
+    },
+    {
+      "epoch": 3.9363057324840764,
+      "grad_norm": 0.5472481872997582,
+      "learning_rate": 9.471843422893299e-06,
+      "loss": 0.1465,
+      "step": 206
+    },
+    {
+      "epoch": 3.9554140127388537,
+      "grad_norm": 0.5980054190679414,
+      "learning_rate": 9.375930194632447e-06,
+      "loss": 0.1381,
+      "step": 207
+    },
+    {
+      "epoch": 3.9745222929936306,
+      "grad_norm": 0.5758032790054801,
+      "learning_rate": 9.28007456790833e-06,
+      "loss": 0.121,
+      "step": 208
+    },
+    {
+      "epoch": 3.9936305732484074,
+      "grad_norm": 0.5737444653471964,
+      "learning_rate": 9.184285390178978e-06,
+      "loss": 0.1384,
+      "step": 209
+    },
+    {
+      "epoch": 4.012738853503185,
+      "grad_norm": 0.5805744461465226,
+      "learning_rate": 9.08857150276917e-06,
+      "loss": 0.0972,
+      "step": 210
+    },
+    {
+      "epoch": 4.031847133757962,
+      "grad_norm": 0.5348990869157657,
+      "learning_rate": 8.992941740054418e-06,
+      "loss": 0.1077,
+      "step": 211
+    },
+    {
+      "epoch": 4.050955414012739,
+      "grad_norm": 0.48367178609199385,
+      "learning_rate": 8.897404928645529e-06,
+      "loss": 0.0803,
+      "step": 212
+    },
+    {
+      "epoch": 4.070063694267516,
+      "grad_norm": 0.5634222929575672,
+      "learning_rate": 8.80196988657393e-06,
+      "loss": 0.0948,
+      "step": 213
+    },
+    {
+      "epoch": 4.089171974522293,
+      "grad_norm": 0.6019132311810791,
+      "learning_rate": 8.706645422477739e-06,
+      "loss": 0.0965,
+      "step": 214
+    },
+    {
+      "epoch": 4.10828025477707,
+      "grad_norm": 0.61592782973345,
+      "learning_rate": 8.611440334788762e-06,
+      "loss": 0.0831,
+      "step": 215
+    },
+    {
+      "epoch": 4.127388535031847,
+      "grad_norm": 0.6528434064361442,
+      "learning_rate": 8.516363410920376e-06,
+      "loss": 0.0933,
+      "step": 216
+    },
+    {
+      "epoch": 4.146496815286624,
+      "grad_norm": 0.5354471738692738,
+      "learning_rate": 8.42142342645646e-06,
+      "loss": 0.0987,
+      "step": 217
+    },
+    {
+      "epoch": 4.165605095541402,
+      "grad_norm": 0.5143138688861675,
+      "learning_rate": 8.326629144341408e-06,
+      "loss": 0.0819,
+      "step": 218
+    },
+    {
+      "epoch": 4.1847133757961785,
+      "grad_norm": 0.5379471061356808,
+      "learning_rate": 8.231989314071318e-06,
+      "loss": 0.095,
+      "step": 219
+    },
+    {
+      "epoch": 4.203821656050955,
+      "grad_norm": 0.5301933527370177,
+      "learning_rate": 8.137512670886397e-06,
+      "loss": 0.0903,
+      "step": 220
+    },
+    {
+      "epoch": 4.222929936305732,
+      "grad_norm": 0.4809348216113543,
+      "learning_rate": 8.043207934964722e-06,
+      "loss": 0.1067,
+      "step": 221
+    },
+    {
+      "epoch": 4.24203821656051,
+      "grad_norm": 0.48871006521483196,
+      "learning_rate": 7.949083810617358e-06,
+      "loss": 0.0816,
+      "step": 222
+    },
+    {
+      "epoch": 4.261146496815287,
+      "grad_norm": 0.4904322084835216,
+      "learning_rate": 7.855148985484946e-06,
+      "loss": 0.0952,
+      "step": 223
+    },
+    {
+      "epoch": 4.280254777070064,
+      "grad_norm": 0.5088144932632028,
+      "learning_rate": 7.761412129735853e-06,
+      "loss": 0.0909,
+      "step": 224
+    },
+    {
+      "epoch": 4.2993630573248405,
+      "grad_norm": 0.5497328370577785,
+      "learning_rate": 7.667881895265895e-06,
+      "loss": 0.0869,
+      "step": 225
+    },
+    {
+      "epoch": 4.318471337579618,
+      "grad_norm": 0.5110943090824636,
+      "learning_rate": 7.574566914899779e-06,
+      "loss": 0.0813,
+      "step": 226
+    },
+    {
+      "epoch": 4.337579617834395,
+      "grad_norm": 0.5149089338611477,
+      "learning_rate": 7.481475801594302e-06,
+      "loss": 0.0865,
+      "step": 227
+    },
+    {
+      "epoch": 4.356687898089172,
+      "grad_norm": 0.5086479577422177,
+      "learning_rate": 7.388617147643371e-06,
+      "loss": 0.0991,
+      "step": 228
+    },
+    {
+      "epoch": 4.375796178343949,
+      "grad_norm": 0.4701354710526979,
+      "learning_rate": 7.295999523884921e-06,
+      "loss": 0.0827,
+      "step": 229
+    },
+    {
+      "epoch": 4.3949044585987265,
+      "grad_norm": 0.5206239752911271,
+      "learning_rate": 7.203631478909857e-06,
+      "loss": 0.0795,
+      "step": 230
+    },
+    {
+      "epoch": 4.414012738853503,
+      "grad_norm": 0.5062969363443023,
+      "learning_rate": 7.111521538272997e-06,
+      "loss": 0.0886,
+      "step": 231
+    },
+    {
+      "epoch": 4.43312101910828,
+      "grad_norm": 0.49268774094148876,
+      "learning_rate": 7.019678203706164e-06,
+      "loss": 0.0869,
+      "step": 232
+    },
+    {
+      "epoch": 4.452229299363057,
+      "grad_norm": 0.5076932844039229,
+      "learning_rate": 6.928109952333506e-06,
+      "loss": 0.0905,
+      "step": 233
+    },
+    {
+      "epoch": 4.471337579617835,
+      "grad_norm": 0.5084419206033639,
+      "learning_rate": 6.83682523588902e-06,
+      "loss": 0.1021,
+      "step": 234
+    },
+    {
+      "epoch": 4.490445859872612,
+      "grad_norm": 0.5912777924999364,
+      "learning_rate": 6.745832479936492e-06,
+      "loss": 0.1129,
+      "step": 235
+    },
+    {
+      "epoch": 4.509554140127388,
+      "grad_norm": 0.548233633544218,
+      "learning_rate": 6.655140083091794e-06,
+      "loss": 0.0921,
+      "step": 236
+    },
+    {
+      "epoch": 4.528662420382165,
+      "grad_norm": 0.508627703160152,
+      "learning_rate": 6.564756416247712e-06,
+      "loss": 0.0835,
+      "step": 237
+    },
+    {
+      "epoch": 4.547770700636943,
+      "grad_norm": 0.5156683698314931,
+      "learning_rate": 6.474689821801295e-06,
+      "loss": 0.0712,
+      "step": 238
+    },
+    {
+      "epoch": 4.56687898089172,
+      "grad_norm": 0.49059494688186706,
+      "learning_rate": 6.384948612883872e-06,
+      "loss": 0.0789,
+      "step": 239
+    },
+    {
+      "epoch": 4.585987261146497,
+      "grad_norm": 0.5127200586788684,
+      "learning_rate": 6.2955410725937405e-06,
+      "loss": 0.0997,
+      "step": 240
+    },
+    {
+      "epoch": 4.6050955414012735,
+      "grad_norm": 0.4770691725952168,
+      "learning_rate": 6.206475453231644e-06,
+      "loss": 0.0818,
+      "step": 241
+    },
+    {
+      "epoch": 4.624203821656051,
+      "grad_norm": 0.4697666184207905,
+      "learning_rate": 6.117759975539075e-06,
+      "loss": 0.0766,
+      "step": 242
+    },
+    {
+      "epoch": 4.643312101910828,
+      "grad_norm": 0.5075783739916174,
+      "learning_rate": 6.029402827939519e-06,
+      "loss": 0.0759,
+      "step": 243
+    },
+    {
+      "epoch": 4.662420382165605,
+      "grad_norm": 0.5534086756707526,
+      "learning_rate": 5.941412165782645e-06,
+      "loss": 0.0793,
+      "step": 244
+    },
+    {
+      "epoch": 4.681528662420382,
+      "grad_norm": 0.5060342392711934,
+      "learning_rate": 5.853796110591583e-06,
+      "loss": 0.0918,
+      "step": 245
+    },
+    {
+      "epoch": 4.7006369426751595,
+      "grad_norm": 0.4781213852566722,
+      "learning_rate": 5.766562749313309e-06,
+      "loss": 0.0753,
+      "step": 246
+    },
+    {
+      "epoch": 4.719745222929936,
+      "grad_norm": 0.4795478672031684,
+      "learning_rate": 5.6797201335722064e-06,
+      "loss": 0.0928,
+      "step": 247
+    },
+    {
+      "epoch": 4.738853503184713,
+      "grad_norm": 0.48158145235931976,
+      "learning_rate": 5.593276278926912e-06,
+      "loss": 0.0772,
+      "step": 248
+    },
+    {
+      "epoch": 4.757961783439491,
+      "grad_norm": 0.5122863904654429,
+      "learning_rate": 5.507239164130501e-06,
+      "loss": 0.0962,
+      "step": 249
+    },
+    {
+      "epoch": 4.777070063694268,
+      "grad_norm": 0.523012497529763,
+      "learning_rate": 5.421616730394e-06,
+      "loss": 0.0854,
+      "step": 250
+    },
+    {
+      "epoch": 4.796178343949045,
+      "grad_norm": 0.5089559461953321,
+      "learning_rate": 5.336416880653461e-06,
+      "loss": 0.0855,
+      "step": 251
+    },
+    {
+      "epoch": 4.8152866242038215,
+      "grad_norm": 0.5032592066222847,
+      "learning_rate": 5.251647478840511e-06,
+      "loss": 0.0909,
+      "step": 252
+    },
+    {
+      "epoch": 4.834394904458598,
+      "grad_norm": 0.5124638291414283,
+      "learning_rate": 5.167316349156495e-06,
+      "loss": 0.092,
+      "step": 253
+    },
+    {
+      "epoch": 4.853503184713376,
+      "grad_norm": 0.5115529046038896,
+      "learning_rate": 5.083431275350312e-06,
+      "loss": 0.0883,
+      "step": 254
+    },
+    {
+      "epoch": 4.872611464968153,
+      "grad_norm": 0.48365797359771834,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0947,
+      "step": 255
+    },
+    {
+      "epoch": 4.89171974522293,
+      "grad_norm": 0.5087248022387761,
+      "learning_rate": 4.917030223798057e-06,
+      "loss": 0.0849,
+      "step": 256
+    },
+    {
+      "epoch": 4.9108280254777075,
+      "grad_norm": 0.49240853298346426,
+      "learning_rate": 4.834529604840686e-06,
+      "loss": 0.0937,
+      "step": 257
+    },
+    {
+      "epoch": 4.929936305732484,
+      "grad_norm": 0.470771551543723,
+      "learning_rate": 4.7525057579209775e-06,
+      "loss": 0.0933,
+      "step": 258
+    },
+    {
+      "epoch": 4.949044585987261,
+      "grad_norm": 0.4484688017223916,
+      "learning_rate": 4.670966253826027e-06,
+      "loss": 0.0649,
+      "step": 259
+    },
+    {
+      "epoch": 4.968152866242038,
+      "grad_norm": 0.4864262253332728,
+      "learning_rate": 4.589918618638173e-06,
+      "loss": 0.0888,
+      "step": 260
+    },
+    {
+      "epoch": 4.987261146496815,
+      "grad_norm": 0.4861002442900688,
+      "learning_rate": 4.5093703330403385e-06,
+      "loss": 0.0882,
+      "step": 261
+    },
+    {
+      "epoch": 5.006369426751593,
+      "grad_norm": 0.45102446457412987,
+      "learning_rate": 4.429328831625565e-06,
+      "loss": 0.08,
+      "step": 262
+    },
+    {
+      "epoch": 5.025477707006369,
+      "grad_norm": 0.40880071238495125,
+      "learning_rate": 4.349801502210801e-06,
+      "loss": 0.0577,
+      "step": 263
+    },
+    {
+      "epoch": 5.044585987261146,
+      "grad_norm": 0.4137140795976911,
+      "learning_rate": 4.270795685155001e-06,
+      "loss": 0.0738,
+      "step": 264
+    },
+    {
+      "epoch": 5.063694267515924,
+      "grad_norm": 0.3773764844039832,
+      "learning_rate": 4.192318672681631e-06,
+      "loss": 0.0535,
+      "step": 265
+    },
+    {
+      "epoch": 5.082802547770701,
+      "grad_norm": 0.3658659872822271,
+      "learning_rate": 4.1143777082055715e-06,
+      "loss": 0.0466,
+      "step": 266
+    },
+    {
+      "epoch": 5.101910828025478,
+      "grad_norm": 0.42458236903719826,
+      "learning_rate": 4.036979985664566e-06,
+      "loss": 0.0567,
+      "step": 267
+    },
+    {
+      "epoch": 5.1210191082802545,
+      "grad_norm": 0.5048661268928728,
+      "learning_rate": 3.960132648855226e-06,
+      "loss": 0.0588,
+      "step": 268
+    },
+    {
+      "epoch": 5.140127388535032,
+      "grad_norm": 0.5087004297994075,
+      "learning_rate": 3.883842790773647e-06,
+      "loss": 0.0542,
+      "step": 269
+    },
+    {
+      "epoch": 5.159235668789809,
+      "grad_norm": 0.5327906885184548,
+      "learning_rate": 3.8081174529607346e-06,
+      "loss": 0.0713,
+      "step": 270
+    },
+    {
+      "epoch": 5.178343949044586,
+      "grad_norm": 0.4272127039360007,
+      "learning_rate": 3.732963624852275e-06,
+      "loss": 0.0516,
+      "step": 271
+    },
+    {
+      "epoch": 5.197452229299363,
+      "grad_norm": 0.40873506898418366,
+      "learning_rate": 3.6583882431338047e-06,
+      "loss": 0.0515,
+      "step": 272
+    },
+    {
+      "epoch": 5.2165605095541405,
+      "grad_norm": 0.4047129278009763,
+      "learning_rate": 3.584398191100341e-06,
+      "loss": 0.0473,
+      "step": 273
+    },
+    {
+      "epoch": 5.235668789808917,
+      "grad_norm": 0.39604058720591795,
+      "learning_rate": 3.511000298021098e-06,
+      "loss": 0.04,
+      "step": 274
+    },
+    {
+      "epoch": 5.254777070063694,
+      "grad_norm": 0.392803862362966,
+      "learning_rate": 3.4382013385090985e-06,
+      "loss": 0.0508,
+      "step": 275
+    },
+    {
+      "epoch": 5.273885350318471,
+      "grad_norm": 0.43110874125602366,
+      "learning_rate": 3.3660080318959043e-06,
+      "loss": 0.0533,
+      "step": 276
+    },
+    {
+      "epoch": 5.292993630573249,
+      "grad_norm": 0.39397000402858284,
+      "learning_rate": 3.2944270416114256e-06,
+      "loss": 0.0615,
+      "step": 277
+    },
+    {
+      "epoch": 5.312101910828026,
+      "grad_norm": 0.3914047603261904,
+      "learning_rate": 3.223464974568874e-06,
+      "loss": 0.0624,
+      "step": 278
+    },
+    {
+      "epoch": 5.3312101910828025,
+      "grad_norm": 0.3965596924707276,
+      "learning_rate": 3.153128380554941e-06,
+      "loss": 0.0497,
+      "step": 279
+    },
+    {
+      "epoch": 5.350318471337579,
+      "grad_norm": 0.38778374913306757,
+      "learning_rate": 3.0834237516252817e-06,
+      "loss": 0.0514,
+      "step": 280
+    },
+    {
+      "epoch": 5.369426751592357,
+      "grad_norm": 0.3903177863949038,
+      "learning_rate": 3.0143575215052732e-06,
+      "loss": 0.0567,
+      "step": 281
+    },
+    {
+      "epoch": 5.388535031847134,
+      "grad_norm": 0.39634007179905534,
+      "learning_rate": 2.94593606499619e-06,
+      "loss": 0.0569,
+      "step": 282
+    },
+    {
+      "epoch": 5.407643312101911,
+      "grad_norm": 0.3957032751811854,
+      "learning_rate": 2.878165697386812e-06,
+      "loss": 0.0638,
+      "step": 283
+    },
+    {
+      "epoch": 5.426751592356688,
+      "grad_norm": 0.37913890578373255,
+      "learning_rate": 2.8110526738705345e-06,
+      "loss": 0.0481,
+      "step": 284
+    },
+    {
+      "epoch": 5.445859872611465,
+      "grad_norm": 0.3862676172421124,
+      "learning_rate": 2.7446031889679893e-06,
+      "loss": 0.0453,
+      "step": 285
+    },
+    {
+      "epoch": 5.464968152866242,
+      "grad_norm": 0.36960164256953587,
+      "learning_rate": 2.678823375955314e-06,
+      "loss": 0.0435,
+      "step": 286
+    },
+    {
+      "epoch": 5.484076433121019,
+      "grad_norm": 0.36796691847799007,
+      "learning_rate": 2.6137193062980506e-06,
+      "loss": 0.0415,
+      "step": 287
+    },
+    {
+      "epoch": 5.503184713375796,
+      "grad_norm": 0.3755847108481153,
+      "learning_rate": 2.5492969890907383e-06,
+      "loss": 0.0489,
+      "step": 288
+    },
+    {
+      "epoch": 5.522292993630574,
+      "grad_norm": 0.3970659484476639,
+      "learning_rate": 2.485562370502279e-06,
+      "loss": 0.0655,
+      "step": 289
+    },
+    {
+      "epoch": 5.54140127388535,
+      "grad_norm": 0.3886555225685734,
+      "learning_rate": 2.4225213332271203e-06,
+      "loss": 0.0485,
+      "step": 290
+    },
+    {
+      "epoch": 5.560509554140127,
+      "grad_norm": 0.4080301431502637,
+      "learning_rate": 2.3601796959422585e-06,
+      "loss": 0.0558,
+      "step": 291
+    },
+    {
+      "epoch": 5.579617834394904,
+      "grad_norm": 0.4026513091903469,
+      "learning_rate": 2.2985432127701945e-06,
+      "loss": 0.0454,
+      "step": 292
+    },
+    {
+      "epoch": 5.598726114649682,
+      "grad_norm": 0.38443639881358604,
+      "learning_rate": 2.2376175727478346e-06,
+      "loss": 0.045,
+      "step": 293
+    },
+    {
+      "epoch": 5.617834394904459,
+      "grad_norm": 0.3813676391798709,
+      "learning_rate": 2.1774083993013715e-06,
+      "loss": 0.0549,
+      "step": 294
+    },
+    {
+      "epoch": 5.6369426751592355,
+      "grad_norm": 0.3929714841302261,
+      "learning_rate": 2.1179212497272582e-06,
+      "loss": 0.0587,
+      "step": 295
+    },
+    {
+      "epoch": 5.656050955414012,
+      "grad_norm": 0.3773594056347788,
+      "learning_rate": 2.0591616146792705e-06,
+      "loss": 0.0487,
+      "step": 296
+    },
+    {
+      "epoch": 5.67515923566879,
+      "grad_norm": 0.3903375432212494,
+      "learning_rate": 2.0011349176617133e-06,
+      "loss": 0.063,
+      "step": 297
+    },
+    {
+      "epoch": 5.694267515923567,
+      "grad_norm": 0.34549204730201716,
+      "learning_rate": 1.9438465145288377e-06,
+      "loss": 0.0462,
+      "step": 298
+    },
+    {
+      "epoch": 5.713375796178344,
+      "grad_norm": 0.36960015169605626,
+      "learning_rate": 1.8873016929904942e-06,
+      "loss": 0.0633,
+      "step": 299
+    },
+    {
+      "epoch": 5.732484076433121,
+      "grad_norm": 0.37395191526503396,
+      "learning_rate": 1.8315056721240831e-06,
+      "loss": 0.0428,
+      "step": 300
+    },
+    {
+      "epoch": 5.751592356687898,
+      "grad_norm": 0.36658848107156783,
+      "learning_rate": 1.7764636018928249e-06,
+      "loss": 0.0538,
+      "step": 301
+    },
+    {
+      "epoch": 5.770700636942675,
+      "grad_norm": 0.3693412972827775,
+      "learning_rate": 1.722180562670428e-06,
+      "loss": 0.056,
+      "step": 302
+    },
+    {
+      "epoch": 5.789808917197452,
+      "grad_norm": 0.4062939571036632,
+      "learning_rate": 1.6686615647721638e-06,
+      "loss": 0.0552,
+      "step": 303
+    },
+    {
+      "epoch": 5.80891719745223,
+      "grad_norm": 0.3626788457560018,
+      "learning_rate": 1.6159115479924259e-06,
+      "loss": 0.0525,
+      "step": 304
+    },
+    {
+      "epoch": 5.828025477707007,
+      "grad_norm": 0.3610840433614963,
+      "learning_rate": 1.5639353811487744e-06,
+      "loss": 0.0364,
+      "step": 305
+    },
+    {
+      "epoch": 5.8471337579617835,
+      "grad_norm": 0.3922140659041584,
+      "learning_rate": 1.5127378616325606e-06,
+      "loss": 0.0613,
+      "step": 306
+    },
+    {
+      "epoch": 5.86624203821656,
+      "grad_norm": 0.361124017995247,
+      "learning_rate": 1.462323714966114e-06,
+      "loss": 0.0542,
+      "step": 307
+    },
+    {
+      "epoch": 5.885350318471337,
+      "grad_norm": 0.4128671491321561,
+      "learning_rate": 1.4126975943665844e-06,
+      "loss": 0.0547,
+      "step": 308
+    },
+    {
+      "epoch": 5.904458598726115,
+      "grad_norm": 0.37760902053107187,
+      "learning_rate": 1.3638640803164516e-06,
+      "loss": 0.0645,
+      "step": 309
+    },
+    {
+      "epoch": 5.923566878980892,
+      "grad_norm": 0.3737414906310694,
+      "learning_rate": 1.3158276801407432e-06,
+      "loss": 0.0495,
+      "step": 310
+    },
+    {
+      "epoch": 5.942675159235669,
+      "grad_norm": 0.3508045282975538,
+      "learning_rate": 1.2685928275910142e-06,
+      "loss": 0.0456,
+      "step": 311
+    },
+    {
+      "epoch": 5.961783439490446,
+      "grad_norm": 0.493787137717777,
+      "learning_rate": 1.222163882436107e-06,
+      "loss": 0.0535,
+      "step": 312
+    },
+    {
+      "epoch": 5.980891719745223,
+      "grad_norm": 0.3798144889333946,
+      "learning_rate": 1.1765451300597574e-06,
+      "loss": 0.0609,
+      "step": 313
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.4087442056284942,
+      "learning_rate": 1.1317407810650372e-06,
+      "loss": 0.0518,
+      "step": 314
+    },
+    {
+      "epoch": 6.019108280254777,
+      "grad_norm": 0.30487081690094364,
+      "learning_rate": 1.0877549708857228e-06,
+      "loss": 0.0388,
+      "step": 315
+    },
+    {
+      "epoch": 6.038216560509555,
+      "grad_norm": 0.2699655230730048,
+      "learning_rate": 1.0445917594046073e-06,
+      "loss": 0.0377,
+      "step": 316
+    },
+    {
+      "epoch": 6.057324840764331,
+      "grad_norm": 0.2867153182593771,
+      "learning_rate": 1.0022551305787564e-06,
+      "loss": 0.0452,
+      "step": 317
+    },
+    {
+      "epoch": 6.076433121019108,
+      "grad_norm": 0.26342991214091904,
+      "learning_rate": 9.607489920717983e-07,
+      "loss": 0.0434,
+      "step": 318
+    },
+    {
+      "epoch": 6.095541401273885,
+      "grad_norm": 0.28033330058347683,
+      "learning_rate": 9.200771748932513e-07,
+      "loss": 0.0436,
+      "step": 319
+    },
+    {
+      "epoch": 6.114649681528663,
+      "grad_norm": 0.259399019168197,
+      "learning_rate": 8.802434330449128e-07,
+      "loss": 0.0416,
+      "step": 320
+    },
+    {
+      "epoch": 6.13375796178344,
+      "grad_norm": 0.2754171324258554,
+      "learning_rate": 8.412514431743657e-07,
+      "loss": 0.0505,
+      "step": 321
+    },
+    {
+      "epoch": 6.1528662420382165,
+      "grad_norm": 0.2856414738248389,
+      "learning_rate": 8.031048042356393e-07,
+      "loss": 0.051,
+      "step": 322
+    },
+    {
+      "epoch": 6.171974522292993,
+      "grad_norm": 0.2810268066293626,
+      "learning_rate": 7.65807037157007e-07,
+      "loss": 0.0462,
+      "step": 323
+    },
+    {
+      "epoch": 6.191082802547771,
+      "grad_norm": 0.2606780851040478,
+      "learning_rate": 7.293615845160196e-07,
+      "loss": 0.041,
+      "step": 324
+    },
+    {
+      "epoch": 6.210191082802548,
+      "grad_norm": 0.2497627684435795,
+      "learning_rate": 6.937718102217461e-07,
+      "loss": 0.0302,
+      "step": 325
+    },
+    {
+      "epoch": 6.229299363057325,
+      "grad_norm": 0.25648090925447947,
+      "learning_rate": 6.590409992042957e-07,
+      "loss": 0.0206,
+      "step": 326
+    },
+    {
+      "epoch": 6.248407643312102,
+      "grad_norm": 0.2732773593679712,
+      "learning_rate": 6.251723571116031e-07,
+      "loss": 0.0344,
+      "step": 327
+    },
+    {
+      "epoch": 6.267515923566879,
+      "grad_norm": 0.2706497203055574,
+      "learning_rate": 5.921690100135713e-07,
+      "loss": 0.0343,
+      "step": 328
+    },
+    {
+      "epoch": 6.286624203821656,
+      "grad_norm": 0.27402581087581407,
+      "learning_rate": 5.600340041135133e-07,
+      "loss": 0.0336,
+      "step": 329
+    },
+    {
+      "epoch": 6.305732484076433,
+      "grad_norm": 0.2869104777512817,
+      "learning_rate": 5.287703054670012e-07,
+      "loss": 0.0354,
+      "step": 330
+    },
+    {
+      "epoch": 6.32484076433121,
+      "grad_norm": 0.31117990503136667,
+      "learning_rate": 4.983807997080925e-07,
+      "loss": 0.036,
+      "step": 331
+    },
+    {
+      "epoch": 6.343949044585988,
+      "grad_norm": 0.28653101402552555,
+      "learning_rate": 4.6886829178299676e-07,
+      "loss": 0.0371,
+      "step": 332
+    },
+    {
+      "epoch": 6.3630573248407645,
+      "grad_norm": 0.29311659146987085,
+      "learning_rate": 4.402355056911656e-07,
+      "loss": 0.0489,
+      "step": 333
+    },
+    {
+      "epoch": 6.382165605095541,
+      "grad_norm": 0.27500919353424896,
+      "learning_rate": 4.124850842338779e-07,
+      "loss": 0.0487,
+      "step": 334
+    },
+    {
+      "epoch": 6.401273885350318,
+      "grad_norm": 0.30431445491411296,
+      "learning_rate": 3.8561958877030957e-07,
+      "loss": 0.0437,
+      "step": 335
+    },
+    {
+      "epoch": 6.420382165605096,
+      "grad_norm": 0.2608500497142074,
+      "learning_rate": 3.5964149898111587e-07,
+      "loss": 0.0356,
+      "step": 336
+    },
+    {
+      "epoch": 6.439490445859873,
+      "grad_norm": 0.260154976904735,
+      "learning_rate": 3.345532126395579e-07,
+      "loss": 0.0349,
+      "step": 337
+    },
+    {
+      "epoch": 6.45859872611465,
+      "grad_norm": 0.2816167832716319,
+      "learning_rate": 3.1035704539019384e-07,
+      "loss": 0.0378,
+      "step": 338
+    },
+    {
+      "epoch": 6.477707006369426,
+      "grad_norm": 0.2992804585391855,
+      "learning_rate": 2.870552305351382e-07,
+      "loss": 0.0445,
+      "step": 339
+    },
+    {
+      "epoch": 6.496815286624204,
+      "grad_norm": 0.3088560543019621,
+      "learning_rate": 2.646499188279328e-07,
+      "loss": 0.0353,
+      "step": 340
+    },
+    {
+      "epoch": 6.515923566878981,
+      "grad_norm": 0.26569766409932116,
+      "learning_rate": 2.4314317827503375e-07,
+      "loss": 0.0379,
+      "step": 341
+    },
+    {
+      "epoch": 6.535031847133758,
+      "grad_norm": 0.30574727361946874,
+      "learning_rate": 2.2253699394493066e-07,
+      "loss": 0.0356,
+      "step": 342
+    },
+    {
+      "epoch": 6.554140127388535,
+      "grad_norm": 0.3001247846887106,
+      "learning_rate": 2.028332677849254e-07,
+      "loss": 0.0368,
+      "step": 343
+    },
+    {
+      "epoch": 6.573248407643312,
+      "grad_norm": 0.29763323650437873,
+      "learning_rate": 1.840338184455881e-07,
+      "loss": 0.0507,
+      "step": 344
+    },
+    {
+      "epoch": 6.592356687898089,
+      "grad_norm": 0.27309646456822756,
+      "learning_rate": 1.6614038111289034e-07,
+      "loss": 0.0343,
+      "step": 345
+    },
+    {
+      "epoch": 6.611464968152866,
+      "grad_norm": 0.27466426701411034,
+      "learning_rate": 1.49154607348051e-07,
+      "loss": 0.0378,
+      "step": 346
+    },
+    {
+      "epoch": 6.630573248407643,
+      "grad_norm": 0.28226571036965337,
+      "learning_rate": 1.330780649350938e-07,
+      "loss": 0.0582,
+      "step": 347
+    },
+    {
+      "epoch": 6.649681528662421,
+      "grad_norm": 0.2694935961046363,
+      "learning_rate": 1.1791223773614635e-07,
+      "loss": 0.0348,
+      "step": 348
+    },
+    {
+      "epoch": 6.6687898089171975,
+      "grad_norm": 0.2724111613798266,
+      "learning_rate": 1.0365852555447642e-07,
+      "loss": 0.0314,
+      "step": 349
+    },
+    {
+      "epoch": 6.687898089171974,
+      "grad_norm": 0.28904653828067023,
+      "learning_rate": 9.031824400528854e-08,
+      "loss": 0.0353,
+      "step": 350
+    },
+    {
+      "epoch": 6.707006369426751,
+      "grad_norm": 0.29655624643647244,
+      "learning_rate": 7.789262439430012e-08,
+      "loss": 0.0528,
+      "step": 351
+    },
+    {
+      "epoch": 6.726114649681529,
+      "grad_norm": 0.2741380117575981,
+      "learning_rate": 6.638281360408339e-08,
+      "loss": 0.0252,
+      "step": 352
+    },
+    {
+      "epoch": 6.745222929936306,
+      "grad_norm": 0.2913801880498479,
+      "learning_rate": 5.578987398821345e-08,
+      "loss": 0.0398,
+      "step": 353
+    },
+    {
+      "epoch": 6.764331210191083,
+      "grad_norm": 0.2636221684547299,
+      "learning_rate": 4.6114783273213395e-08,
+      "loss": 0.0454,
+      "step": 354
+    },
+    {
+      "epoch": 6.7834394904458595,
+      "grad_norm": 0.31723482244249407,
+      "learning_rate": 3.735843446830867e-08,
+      "loss": 0.0525,
+      "step": 355
+    },
+    {
+      "epoch": 6.802547770700637,
+      "grad_norm": 0.2417825523335372,
+      "learning_rate": 2.9521635783001932e-08,
+      "loss": 0.0341,
+      "step": 356
+    },
+    {
+      "epoch": 6.821656050955414,
+      "grad_norm": 0.24805911632324373,
+      "learning_rate": 2.2605110552477162e-08,
+      "loss": 0.0516,
+      "step": 357
+    },
+    {
+      "epoch": 6.840764331210191,
+      "grad_norm": 0.3237653261630499,
+      "learning_rate": 1.6609497170834154e-08,
+      "loss": 0.0413,
+      "step": 358
+    },
+    {
+      "epoch": 6.859872611464969,
+      "grad_norm": 0.25586790017596245,
+      "learning_rate": 1.1535349032167908e-08,
+      "loss": 0.0442,
+      "step": 359
+    },
+    {
+      "epoch": 6.8789808917197455,
+      "grad_norm": 0.2840506079479181,
+      "learning_rate": 7.3831344794872415e-09,
+      "loss": 0.0449,
+      "step": 360
+    },
+    {
+      "epoch": 6.898089171974522,
+      "grad_norm": 0.24998104092788856,
+      "learning_rate": 4.153236761488266e-09,
+      "loss": 0.0263,
+      "step": 361
+    },
+    {
+      "epoch": 6.917197452229299,
+      "grad_norm": 0.2791347320317074,
+      "learning_rate": 1.8459539971804608e-09,
+      "loss": 0.0342,
+      "step": 362
+    },
+    {
+      "epoch": 6.936305732484076,
+      "grad_norm": 0.246275836419641,
+      "learning_rate": 4.614991483686826e-10,
+      "loss": 0.0365,
+      "step": 363
+    },
+    {
+      "epoch": 6.955414012738854,
+      "grad_norm": 0.2466211490023853,
+      "learning_rate": 0.0,
+      "loss": 0.027,
+      "step": 364
+    },
+    {
+      "epoch": 6.955414012738854,
+      "step": 364,
+      "total_flos": 1.6645198251751014e+17,
+      "train_loss": 0.0,
+      "train_runtime": 5.2904,
+      "train_samples_per_second": 6615.788,
+      "train_steps_per_second": 68.804
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 364,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6645198251751014e+17,
+  "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 sha256:2e1e5474c4ef7fdf28941b3dff7baa84fcb76567b1f9a05bfef72a5fbaf29743
+size 7352