Upload model

.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 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: meta_chat_reasoning_0_100_system_100k
+  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. -->
+
+# meta_chat_reasoning_0_100_system_100k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/meta_chat_reasoning_0_100_system_100k 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: 8e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 512
+- total_train_batch_size: 512
+- total_eval_batch_size: 4096
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 6794337614561280.0,
+    "train_loss": 0.42579232314486565,
+    "train_runtime": 5653.6163,
+    "train_samples_per_second": 36.455,
+    "train_steps_per_second": 0.072
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/leonardo_work/EUHPC_E03_068/DCFT_shared/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "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 sha256:32b7a46b1f219a20972d313fe7752f718d1d27dd3e6f80633d64939d6c894a0e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e7fa68abdccdda896aa33653506dc31aa68ad5ae3c5603ba6b6584c0becca2
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ec293111e0ca39abee5d10bca298f96461b5a4651b6fd1036a825a14c0c9c1
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dab0cda66d9cfbae6c68870dcabec9ed4c8dee1ebfad7b8383e786bf194ebdd
+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
+  }
+}

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-05-01 02:46:34", "end_time": "2025-05-01 04:22:25"}

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": 5.0,
+    "total_flos": 6794337614561280.0,
+    "train_loss": 0.42579232314486565,
+    "train_runtime": 5653.6163,
+    "train_samples_per_second": 36.455,
+    "train_steps_per_second": 0.072
+}

trainer_log.jsonl

@@ -0,0 +1,406 @@
+{"current_steps": 1, "total_steps": 405, "loss": 0.8713, "lr": 1.951219512195122e-06, "epoch": 0.012345679012345678, "percentage": 0.25, "elapsed_time": "0:00:41", "remaining_time": "4:39:58"}
+{"current_steps": 2, "total_steps": 405, "loss": 0.8617, "lr": 3.902439024390244e-06, "epoch": 0.024691358024691357, "percentage": 0.49, "elapsed_time": "0:00:53", "remaining_time": "3:01:03"}
+{"current_steps": 3, "total_steps": 405, "loss": 0.8557, "lr": 5.853658536585366e-06, "epoch": 0.037037037037037035, "percentage": 0.74, "elapsed_time": "0:01:06", "remaining_time": "2:28:44"}
+{"current_steps": 4, "total_steps": 405, "loss": 0.8258, "lr": 7.804878048780489e-06, "epoch": 0.04938271604938271, "percentage": 0.99, "elapsed_time": "0:01:19", "remaining_time": "2:12:11"}
+{"current_steps": 5, "total_steps": 405, "loss": 0.7756, "lr": 9.756097560975611e-06, "epoch": 0.06172839506172839, "percentage": 1.23, "elapsed_time": "0:01:31", "remaining_time": "2:01:53"}
+{"current_steps": 6, "total_steps": 405, "loss": 0.786, "lr": 1.1707317073170731e-05, "epoch": 0.07407407407407407, "percentage": 1.48, "elapsed_time": "0:01:43", "remaining_time": "1:55:08"}
+{"current_steps": 7, "total_steps": 405, "loss": 0.7873, "lr": 1.3658536585365855e-05, "epoch": 0.08641975308641975, "percentage": 1.73, "elapsed_time": "0:01:56", "remaining_time": "1:50:07"}
+{"current_steps": 8, "total_steps": 405, "loss": 0.7584, "lr": 1.5609756097560978e-05, "epoch": 0.09876543209876543, "percentage": 1.98, "elapsed_time": "0:02:08", "remaining_time": "1:46:12"}
+{"current_steps": 9, "total_steps": 405, "loss": 0.7462, "lr": 1.75609756097561e-05, "epoch": 0.1111111111111111, "percentage": 2.22, "elapsed_time": "0:02:20", "remaining_time": "1:43:11"}
+{"current_steps": 10, "total_steps": 405, "loss": 0.6981, "lr": 1.9512195121951222e-05, "epoch": 0.12345679012345678, "percentage": 2.47, "elapsed_time": "0:02:33", "remaining_time": "1:40:45"}
+{"current_steps": 11, "total_steps": 405, "loss": 0.6788, "lr": 2.1463414634146344e-05, "epoch": 0.13580246913580246, "percentage": 2.72, "elapsed_time": "0:02:45", "remaining_time": "1:38:42"}
+{"current_steps": 12, "total_steps": 405, "loss": 0.6542, "lr": 2.3414634146341463e-05, "epoch": 0.14814814814814814, "percentage": 2.96, "elapsed_time": "0:02:57", "remaining_time": "1:36:59"}
+{"current_steps": 13, "total_steps": 405, "loss": 0.6401, "lr": 2.536585365853659e-05, "epoch": 0.16049382716049382, "percentage": 3.21, "elapsed_time": "0:03:09", "remaining_time": "1:35:23"}
+{"current_steps": 14, "total_steps": 405, "loss": 0.6224, "lr": 2.731707317073171e-05, "epoch": 0.1728395061728395, "percentage": 3.46, "elapsed_time": "0:03:22", "remaining_time": "1:34:10"}
+{"current_steps": 15, "total_steps": 405, "loss": 0.6147, "lr": 2.926829268292683e-05, "epoch": 0.18518518518518517, "percentage": 3.7, "elapsed_time": "0:03:34", "remaining_time": "1:33:01"}
+{"current_steps": 16, "total_steps": 405, "loss": 0.608, "lr": 3.1219512195121955e-05, "epoch": 0.19753086419753085, "percentage": 3.95, "elapsed_time": "0:03:46", "remaining_time": "1:31:52"}
+{"current_steps": 17, "total_steps": 405, "loss": 0.5964, "lr": 3.3170731707317074e-05, "epoch": 0.20987654320987653, "percentage": 4.2, "elapsed_time": "0:03:59", "remaining_time": "1:30:55"}
+{"current_steps": 18, "total_steps": 405, "loss": 0.5827, "lr": 3.51219512195122e-05, "epoch": 0.2222222222222222, "percentage": 4.44, "elapsed_time": "0:04:11", "remaining_time": "1:30:04"}
+{"current_steps": 19, "total_steps": 405, "loss": 0.5863, "lr": 3.7073170731707325e-05, "epoch": 0.2345679012345679, "percentage": 4.69, "elapsed_time": "0:04:23", "remaining_time": "1:29:14"}
+{"current_steps": 20, "total_steps": 405, "loss": 0.5828, "lr": 3.9024390243902444e-05, "epoch": 0.24691358024691357, "percentage": 4.94, "elapsed_time": "0:04:35", "remaining_time": "1:28:32"}
+{"current_steps": 21, "total_steps": 405, "loss": 0.5699, "lr": 4.097560975609756e-05, "epoch": 0.25925925925925924, "percentage": 5.19, "elapsed_time": "0:04:47", "remaining_time": "1:27:46"}
+{"current_steps": 22, "total_steps": 405, "loss": 0.5705, "lr": 4.292682926829269e-05, "epoch": 0.2716049382716049, "percentage": 5.43, "elapsed_time": "0:05:00", "remaining_time": "1:27:10"}
+{"current_steps": 23, "total_steps": 405, "loss": 0.5505, "lr": 4.4878048780487814e-05, "epoch": 0.2839506172839506, "percentage": 5.68, "elapsed_time": "0:05:12", "remaining_time": "1:26:36"}
+{"current_steps": 24, "total_steps": 405, "loss": 0.5564, "lr": 4.6829268292682926e-05, "epoch": 0.2962962962962963, "percentage": 5.93, "elapsed_time": "0:05:25", "remaining_time": "1:26:03"}
+{"current_steps": 25, "total_steps": 405, "loss": 0.5517, "lr": 4.878048780487805e-05, "epoch": 0.30864197530864196, "percentage": 6.17, "elapsed_time": "0:05:37", "remaining_time": "1:25:32"}
+{"current_steps": 26, "total_steps": 405, "loss": 0.5488, "lr": 5.073170731707318e-05, "epoch": 0.32098765432098764, "percentage": 6.42, "elapsed_time": "0:05:49", "remaining_time": "1:24:58"}
+{"current_steps": 27, "total_steps": 405, "loss": 0.5494, "lr": 5.26829268292683e-05, "epoch": 0.3333333333333333, "percentage": 6.67, "elapsed_time": "0:06:02", "remaining_time": "1:24:30"}
+{"current_steps": 28, "total_steps": 405, "loss": 0.5527, "lr": 5.463414634146342e-05, "epoch": 0.345679012345679, "percentage": 6.91, "elapsed_time": "0:06:14", "remaining_time": "1:24:02"}
+{"current_steps": 29, "total_steps": 405, "loss": 0.5404, "lr": 5.658536585365854e-05, "epoch": 0.35802469135802467, "percentage": 7.16, "elapsed_time": "0:06:26", "remaining_time": "1:23:34"}
+{"current_steps": 30, "total_steps": 405, "loss": 0.5467, "lr": 5.853658536585366e-05, "epoch": 0.37037037037037035, "percentage": 7.41, "elapsed_time": "0:06:39", "remaining_time": "1:23:09"}
+{"current_steps": 31, "total_steps": 405, "loss": 0.5427, "lr": 6.0487804878048785e-05, "epoch": 0.38271604938271603, "percentage": 7.65, "elapsed_time": "0:06:51", "remaining_time": "1:22:44"}
+{"current_steps": 32, "total_steps": 405, "loss": 0.5364, "lr": 6.243902439024391e-05, "epoch": 0.3950617283950617, "percentage": 7.9, "elapsed_time": "0:07:03", "remaining_time": "1:22:17"}
+{"current_steps": 33, "total_steps": 405, "loss": 0.535, "lr": 6.439024390243903e-05, "epoch": 0.4074074074074074, "percentage": 8.15, "elapsed_time": "0:07:15", "remaining_time": "1:21:52"}
+{"current_steps": 34, "total_steps": 405, "loss": 0.5255, "lr": 6.634146341463415e-05, "epoch": 0.41975308641975306, "percentage": 8.4, "elapsed_time": "0:07:28", "remaining_time": "1:21:35"}
+{"current_steps": 35, "total_steps": 405, "loss": 0.5463, "lr": 6.829268292682927e-05, "epoch": 0.43209876543209874, "percentage": 8.64, "elapsed_time": "0:07:40", "remaining_time": "1:21:13"}
+{"current_steps": 36, "total_steps": 405, "loss": 0.5329, "lr": 7.02439024390244e-05, "epoch": 0.4444444444444444, "percentage": 8.89, "elapsed_time": "0:07:53", "remaining_time": "1:20:51"}
+{"current_steps": 37, "total_steps": 405, "loss": 0.5469, "lr": 7.219512195121952e-05, "epoch": 0.4567901234567901, "percentage": 9.14, "elapsed_time": "0:08:05", "remaining_time": "1:20:30"}
+{"current_steps": 38, "total_steps": 405, "loss": 0.5384, "lr": 7.414634146341465e-05, "epoch": 0.4691358024691358, "percentage": 9.38, "elapsed_time": "0:08:17", "remaining_time": "1:20:05"}
+{"current_steps": 39, "total_steps": 405, "loss": 0.5331, "lr": 7.609756097560976e-05, "epoch": 0.48148148148148145, "percentage": 9.63, "elapsed_time": "0:08:30", "remaining_time": "1:19:46"}
+{"current_steps": 40, "total_steps": 405, "loss": 0.5387, "lr": 7.804878048780489e-05, "epoch": 0.49382716049382713, "percentage": 9.88, "elapsed_time": "0:08:42", "remaining_time": "1:19:25"}
+{"current_steps": 41, "total_steps": 405, "loss": 0.5215, "lr": 8e-05, "epoch": 0.5061728395061729, "percentage": 10.12, "elapsed_time": "0:08:54", "remaining_time": "1:19:06"}
+{"current_steps": 42, "total_steps": 405, "loss": 0.5218, "lr": 7.999851021266518e-05, "epoch": 0.5185185185185185, "percentage": 10.37, "elapsed_time": "0:09:06", "remaining_time": "1:18:46"}
+{"current_steps": 43, "total_steps": 405, "loss": 0.5249, "lr": 7.999404096163398e-05, "epoch": 0.5308641975308642, "percentage": 10.62, "elapsed_time": "0:09:19", "remaining_time": "1:18:28"}
+{"current_steps": 44, "total_steps": 405, "loss": 0.5125, "lr": 7.998659257981813e-05, "epoch": 0.5432098765432098, "percentage": 10.86, "elapsed_time": "0:09:31", "remaining_time": "1:18:09"}
+{"current_steps": 45, "total_steps": 405, "loss": 0.516, "lr": 7.997616562204282e-05, "epoch": 0.5555555555555556, "percentage": 11.11, "elapsed_time": "0:09:43", "remaining_time": "1:17:49"}
+{"current_steps": 46, "total_steps": 405, "loss": 0.5175, "lr": 7.996276086500558e-05, "epoch": 0.5679012345679012, "percentage": 11.36, "elapsed_time": "0:09:55", "remaining_time": "1:17:30"}
+{"current_steps": 47, "total_steps": 405, "loss": 0.517, "lr": 7.994637930721825e-05, "epoch": 0.5802469135802469, "percentage": 11.6, "elapsed_time": "0:10:07", "remaining_time": "1:17:09"}
+{"current_steps": 48, "total_steps": 405, "loss": 0.5192, "lr": 7.99270221689327e-05, "epoch": 0.5925925925925926, "percentage": 11.85, "elapsed_time": "0:10:19", "remaining_time": "1:16:47"}
+{"current_steps": 49, "total_steps": 405, "loss": 0.5026, "lr": 7.990469089204992e-05, "epoch": 0.6049382716049383, "percentage": 12.1, "elapsed_time": "0:10:31", "remaining_time": "1:16:28"}
+{"current_steps": 50, "total_steps": 405, "loss": 0.5051, "lr": 7.987938714001254e-05, "epoch": 0.6172839506172839, "percentage": 12.35, "elapsed_time": "0:10:44", "remaining_time": "1:16:12"}
+{"current_steps": 51, "total_steps": 405, "loss": 0.5208, "lr": 7.985111279768106e-05, "epoch": 0.6296296296296297, "percentage": 12.59, "elapsed_time": "0:10:56", "remaining_time": "1:15:54"}
+{"current_steps": 52, "total_steps": 405, "loss": 0.5028, "lr": 7.981986997119334e-05, "epoch": 0.6419753086419753, "percentage": 12.84, "elapsed_time": "0:11:08", "remaining_time": "1:15:34"}
+{"current_steps": 53, "total_steps": 405, "loss": 0.5023, "lr": 7.978566098780771e-05, "epoch": 0.654320987654321, "percentage": 13.09, "elapsed_time": "0:11:20", "remaining_time": "1:15:20"}
+{"current_steps": 54, "total_steps": 405, "loss": 0.5073, "lr": 7.974848839572971e-05, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "0:11:32", "remaining_time": "1:15:02"}
+{"current_steps": 55, "total_steps": 405, "loss": 0.5197, "lr": 7.970835496392216e-05, "epoch": 0.6790123456790124, "percentage": 13.58, "elapsed_time": "0:11:44", "remaining_time": "1:14:43"}
+{"current_steps": 56, "total_steps": 405, "loss": 0.5065, "lr": 7.9665263681899e-05, "epoch": 0.691358024691358, "percentage": 13.83, "elapsed_time": "0:11:56", "remaining_time": "1:14:26"}
+{"current_steps": 57, "total_steps": 405, "loss": 0.5186, "lr": 7.961921775950254e-05, "epoch": 0.7037037037037037, "percentage": 14.07, "elapsed_time": "0:12:09", "remaining_time": "1:14:11"}
+{"current_steps": 58, "total_steps": 405, "loss": 0.5138, "lr": 7.957022062666436e-05, "epoch": 0.7160493827160493, "percentage": 14.32, "elapsed_time": "0:12:21", "remaining_time": "1:13:55"}
+{"current_steps": 59, "total_steps": 405, "loss": 0.5154, "lr": 7.951827593314987e-05, "epoch": 0.7283950617283951, "percentage": 14.57, "elapsed_time": "0:12:33", "remaining_time": "1:13:38"}
+{"current_steps": 60, "total_steps": 405, "loss": 0.508, "lr": 7.946338754828639e-05, "epoch": 0.7407407407407407, "percentage": 14.81, "elapsed_time": "0:12:45", "remaining_time": "1:13:20"}
+{"current_steps": 61, "total_steps": 405, "loss": 0.5029, "lr": 7.940555956067495e-05, "epoch": 0.7530864197530864, "percentage": 15.06, "elapsed_time": "0:12:57", "remaining_time": "1:13:05"}
+{"current_steps": 62, "total_steps": 405, "loss": 0.5081, "lr": 7.934479627788576e-05, "epoch": 0.7654320987654321, "percentage": 15.31, "elapsed_time": "0:13:10", "remaining_time": "1:12:50"}
+{"current_steps": 63, "total_steps": 405, "loss": 0.5013, "lr": 7.928110222613723e-05, "epoch": 0.7777777777777778, "percentage": 15.56, "elapsed_time": "0:13:22", "remaining_time": "1:12:34"}
+{"current_steps": 64, "total_steps": 405, "loss": 0.5009, "lr": 7.921448214995895e-05, "epoch": 0.7901234567901234, "percentage": 15.8, "elapsed_time": "0:13:34", "remaining_time": "1:12:18"}
+{"current_steps": 65, "total_steps": 405, "loss": 0.5048, "lr": 7.914494101183822e-05, "epoch": 0.8024691358024691, "percentage": 16.05, "elapsed_time": "0:13:46", "remaining_time": "1:12:01"}
+{"current_steps": 66, "total_steps": 405, "loss": 0.5068, "lr": 7.907248399185037e-05, "epoch": 0.8148148148148148, "percentage": 16.3, "elapsed_time": "0:13:58", "remaining_time": "1:11:48"}
+{"current_steps": 67, "total_steps": 405, "loss": 0.4967, "lr": 7.899711648727294e-05, "epoch": 0.8271604938271605, "percentage": 16.54, "elapsed_time": "0:14:10", "remaining_time": "1:11:32"}
+{"current_steps": 68, "total_steps": 405, "loss": 0.4876, "lr": 7.891884411218364e-05, "epoch": 0.8395061728395061, "percentage": 16.79, "elapsed_time": "0:14:22", "remaining_time": "1:11:16"}
+{"current_steps": 69, "total_steps": 405, "loss": 0.4902, "lr": 7.883767269704209e-05, "epoch": 0.8518518518518519, "percentage": 17.04, "elapsed_time": "0:14:34", "remaining_time": "1:11:00"}
+{"current_steps": 70, "total_steps": 405, "loss": 0.4926, "lr": 7.875360828825562e-05, "epoch": 0.8641975308641975, "percentage": 17.28, "elapsed_time": "0:14:47", "remaining_time": "1:10:47"}
+{"current_steps": 71, "total_steps": 405, "loss": 0.4992, "lr": 7.866665714772879e-05, "epoch": 0.8765432098765432, "percentage": 17.53, "elapsed_time": "0:14:59", "remaining_time": "1:10:31"}
+{"current_steps": 72, "total_steps": 405, "loss": 0.4944, "lr": 7.8576825752397e-05, "epoch": 0.8888888888888888, "percentage": 17.78, "elapsed_time": "0:15:11", "remaining_time": "1:10:16"}
+{"current_steps": 73, "total_steps": 405, "loss": 0.5036, "lr": 7.848412079374403e-05, "epoch": 0.9012345679012346, "percentage": 18.02, "elapsed_time": "0:15:23", "remaining_time": "1:10:00"}
+{"current_steps": 74, "total_steps": 405, "loss": 0.4956, "lr": 7.838854917730351e-05, "epoch": 0.9135802469135802, "percentage": 18.27, "elapsed_time": "0:15:35", "remaining_time": "1:09:44"}
+{"current_steps": 75, "total_steps": 405, "loss": 0.5049, "lr": 7.829011802214464e-05, "epoch": 0.9259259259259259, "percentage": 18.52, "elapsed_time": "0:15:47", "remaining_time": "1:09:30"}
+{"current_steps": 76, "total_steps": 405, "loss": 0.5073, "lr": 7.818883466034184e-05, "epoch": 0.9382716049382716, "percentage": 18.77, "elapsed_time": "0:16:00", "remaining_time": "1:09:15"}
+{"current_steps": 77, "total_steps": 405, "loss": 0.5038, "lr": 7.808470663642856e-05, "epoch": 0.9506172839506173, "percentage": 19.01, "elapsed_time": "0:16:12", "remaining_time": "1:09:01"}
+{"current_steps": 78, "total_steps": 405, "loss": 0.4987, "lr": 7.797774170683542e-05, "epoch": 0.9629629629629629, "percentage": 19.26, "elapsed_time": "0:16:24", "remaining_time": "1:08:46"}
+{"current_steps": 79, "total_steps": 405, "loss": 0.4955, "lr": 7.786794783931225e-05, "epoch": 0.9753086419753086, "percentage": 19.51, "elapsed_time": "0:16:36", "remaining_time": "1:08:30"}
+{"current_steps": 80, "total_steps": 405, "loss": 0.5098, "lr": 7.775533321233471e-05, "epoch": 0.9876543209876543, "percentage": 19.75, "elapsed_time": "0:16:48", "remaining_time": "1:08:17"}
+{"current_steps": 81, "total_steps": 405, "loss": 0.4941, "lr": 7.763990621449507e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:17:00", "remaining_time": "1:08:01"}
+{"current_steps": 82, "total_steps": 405, "loss": 0.4824, "lr": 7.752167544387728e-05, "epoch": 1.0123456790123457, "percentage": 20.25, "elapsed_time": "0:17:52", "remaining_time": "1:10:24"}
+{"current_steps": 83, "total_steps": 405, "loss": 0.4677, "lr": 7.740064970741661e-05, "epoch": 1.0246913580246915, "percentage": 20.49, "elapsed_time": "0:18:04", "remaining_time": "1:10:08"}
+{"current_steps": 84, "total_steps": 405, "loss": 0.4755, "lr": 7.727683802024347e-05, "epoch": 1.037037037037037, "percentage": 20.74, "elapsed_time": "0:18:17", "remaining_time": "1:09:53"}
+{"current_steps": 85, "total_steps": 405, "loss": 0.4626, "lr": 7.715024960501209e-05, "epoch": 1.0493827160493827, "percentage": 20.99, "elapsed_time": "0:18:29", "remaining_time": "1:09:38"}
+{"current_steps": 86, "total_steps": 405, "loss": 0.4699, "lr": 7.702089389121335e-05, "epoch": 1.0617283950617284, "percentage": 21.23, "elapsed_time": "0:18:41", "remaining_time": "1:09:20"}
+{"current_steps": 87, "total_steps": 405, "loss": 0.4632, "lr": 7.688878051447243e-05, "epoch": 1.074074074074074, "percentage": 21.48, "elapsed_time": "0:18:53", "remaining_time": "1:09:03"}
+{"current_steps": 88, "total_steps": 405, "loss": 0.4694, "lr": 7.675391931583109e-05, "epoch": 1.0864197530864197, "percentage": 21.73, "elapsed_time": "0:19:06", "remaining_time": "1:08:48"}
+{"current_steps": 89, "total_steps": 405, "loss": 0.4685, "lr": 7.661632034101466e-05, "epoch": 1.0987654320987654, "percentage": 21.98, "elapsed_time": "0:19:18", "remaining_time": "1:08:32"}
+{"current_steps": 90, "total_steps": 405, "loss": 0.4652, "lr": 7.64759938396836e-05, "epoch": 1.1111111111111112, "percentage": 22.22, "elapsed_time": "0:19:30", "remaining_time": "1:08:16"}
+{"current_steps": 91, "total_steps": 405, "loss": 0.4557, "lr": 7.633295026467016e-05, "epoch": 1.123456790123457, "percentage": 22.47, "elapsed_time": "0:19:42", "remaining_time": "1:07:59"}
+{"current_steps": 92, "total_steps": 405, "loss": 0.4576, "lr": 7.618720027119966e-05, "epoch": 1.1358024691358024, "percentage": 22.72, "elapsed_time": "0:19:54", "remaining_time": "1:07:43"}
+{"current_steps": 93, "total_steps": 405, "loss": 0.4602, "lr": 7.603875471609677e-05, "epoch": 1.1481481481481481, "percentage": 22.96, "elapsed_time": "0:20:06", "remaining_time": "1:07:27"}
+{"current_steps": 94, "total_steps": 405, "loss": 0.4624, "lr": 7.588762465697693e-05, "epoch": 1.1604938271604939, "percentage": 23.21, "elapsed_time": "0:20:18", "remaining_time": "1:07:12"}
+{"current_steps": 95, "total_steps": 405, "loss": 0.4641, "lr": 7.573382135142253e-05, "epoch": 1.1728395061728394, "percentage": 23.46, "elapsed_time": "0:20:30", "remaining_time": "1:06:56"}
+{"current_steps": 96, "total_steps": 405, "loss": 0.4498, "lr": 7.55773562561444e-05, "epoch": 1.1851851851851851, "percentage": 23.7, "elapsed_time": "0:20:42", "remaining_time": "1:06:40"}
+{"current_steps": 97, "total_steps": 405, "loss": 0.46, "lr": 7.541824102612839e-05, "epoch": 1.1975308641975309, "percentage": 23.95, "elapsed_time": "0:20:54", "remaining_time": "1:06:24"}
+{"current_steps": 98, "total_steps": 405, "loss": 0.456, "lr": 7.525648751376726e-05, "epoch": 1.2098765432098766, "percentage": 24.2, "elapsed_time": "0:21:07", "remaining_time": "1:06:09"}
+{"current_steps": 99, "total_steps": 405, "loss": 0.4585, "lr": 7.509210776797768e-05, "epoch": 1.2222222222222223, "percentage": 24.44, "elapsed_time": "0:21:19", "remaining_time": "1:05:53"}
+{"current_steps": 100, "total_steps": 405, "loss": 0.4543, "lr": 7.492511403330284e-05, "epoch": 1.2345679012345678, "percentage": 24.69, "elapsed_time": "0:21:31", "remaining_time": "1:05:38"}
+{"current_steps": 101, "total_steps": 405, "loss": 0.4535, "lr": 7.475551874900027e-05, "epoch": 1.2469135802469136, "percentage": 24.94, "elapsed_time": "0:21:43", "remaining_time": "1:05:23"}
+{"current_steps": 102, "total_steps": 405, "loss": 0.4558, "lr": 7.458333454811531e-05, "epoch": 1.2592592592592593, "percentage": 25.19, "elapsed_time": "0:21:55", "remaining_time": "1:05:08"}
+{"current_steps": 103, "total_steps": 405, "loss": 0.4474, "lr": 7.440857425654004e-05, "epoch": 1.2716049382716048, "percentage": 25.43, "elapsed_time": "0:22:07", "remaining_time": "1:04:53"}
+{"current_steps": 104, "total_steps": 405, "loss": 0.452, "lr": 7.42312508920579e-05, "epoch": 1.2839506172839505, "percentage": 25.68, "elapsed_time": "0:22:19", "remaining_time": "1:04:37"}
+{"current_steps": 105, "total_steps": 405, "loss": 0.4615, "lr": 7.405137766337406e-05, "epoch": 1.2962962962962963, "percentage": 25.93, "elapsed_time": "0:22:31", "remaining_time": "1:04:22"}
+{"current_steps": 106, "total_steps": 405, "loss": 0.4595, "lr": 7.386896796913137e-05, "epoch": 1.308641975308642, "percentage": 26.17, "elapsed_time": "0:22:43", "remaining_time": "1:04:07"}
+{"current_steps": 107, "total_steps": 405, "loss": 0.4526, "lr": 7.368403539691247e-05, "epoch": 1.3209876543209877, "percentage": 26.42, "elapsed_time": "0:22:56", "remaining_time": "1:03:53"}
+{"current_steps": 108, "total_steps": 405, "loss": 0.4499, "lr": 7.349659372222755e-05, "epoch": 1.3333333333333333, "percentage": 26.67, "elapsed_time": "0:23:08", "remaining_time": "1:03:38"}
+{"current_steps": 109, "total_steps": 405, "loss": 0.4598, "lr": 7.330665690748825e-05, "epoch": 1.345679012345679, "percentage": 26.91, "elapsed_time": "0:23:20", "remaining_time": "1:03:23"}
+{"current_steps": 110, "total_steps": 405, "loss": 0.4531, "lr": 7.311423910096764e-05, "epoch": 1.3580246913580247, "percentage": 27.16, "elapsed_time": "0:23:32", "remaining_time": "1:03:09"}
+{"current_steps": 111, "total_steps": 405, "loss": 0.4472, "lr": 7.291935463574626e-05, "epoch": 1.3703703703703702, "percentage": 27.41, "elapsed_time": "0:23:45", "remaining_time": "1:02:55"}
+{"current_steps": 112, "total_steps": 405, "loss": 0.4524, "lr": 7.272201802864452e-05, "epoch": 1.382716049382716, "percentage": 27.65, "elapsed_time": "0:23:57", "remaining_time": "1:02:40"}
+{"current_steps": 113, "total_steps": 405, "loss": 0.4531, "lr": 7.25222439791413e-05, "epoch": 1.3950617283950617, "percentage": 27.9, "elapsed_time": "0:24:09", "remaining_time": "1:02:25"}
+{"current_steps": 114, "total_steps": 405, "loss": 0.4614, "lr": 7.232004736827907e-05, "epoch": 1.4074074074074074, "percentage": 28.15, "elapsed_time": "0:24:21", "remaining_time": "1:02:11"}
+{"current_steps": 115, "total_steps": 405, "loss": 0.4528, "lr": 7.21154432575553e-05, "epoch": 1.4197530864197532, "percentage": 28.4, "elapsed_time": "0:24:34", "remaining_time": "1:01:57"}
+{"current_steps": 116, "total_steps": 405, "loss": 0.4492, "lr": 7.190844688780065e-05, "epoch": 1.4320987654320987, "percentage": 28.64, "elapsed_time": "0:24:46", "remaining_time": "1:01:42"}
+{"current_steps": 117, "total_steps": 405, "loss": 0.4533, "lr": 7.169907367804363e-05, "epoch": 1.4444444444444444, "percentage": 28.89, "elapsed_time": "0:24:58", "remaining_time": "1:01:29"}
+{"current_steps": 118, "total_steps": 405, "loss": 0.446, "lr": 7.148733922436201e-05, "epoch": 1.4567901234567902, "percentage": 29.14, "elapsed_time": "0:25:10", "remaining_time": "1:01:14"}
+{"current_steps": 119, "total_steps": 405, "loss": 0.4456, "lr": 7.12732592987212e-05, "epoch": 1.4691358024691357, "percentage": 29.38, "elapsed_time": "0:25:23", "remaining_time": "1:01:01"}
+{"current_steps": 120, "total_steps": 405, "loss": 0.4444, "lr": 7.105684984779928e-05, "epoch": 1.4814814814814814, "percentage": 29.63, "elapsed_time": "0:25:35", "remaining_time": "1:00:46"}
+{"current_steps": 121, "total_steps": 405, "loss": 0.4465, "lr": 7.083812699179919e-05, "epoch": 1.4938271604938271, "percentage": 29.88, "elapsed_time": "0:25:48", "remaining_time": "1:00:34"}
+{"current_steps": 122, "total_steps": 405, "loss": 0.4508, "lr": 7.061710702324799e-05, "epoch": 1.5061728395061729, "percentage": 30.12, "elapsed_time": "0:26:00", "remaining_time": "1:00:20"}
+{"current_steps": 123, "total_steps": 405, "loss": 0.4462, "lr": 7.039380640578316e-05, "epoch": 1.5185185185185186, "percentage": 30.37, "elapsed_time": "0:26:12", "remaining_time": "1:00:06"}
+{"current_steps": 124, "total_steps": 405, "loss": 0.4506, "lr": 7.016824177292629e-05, "epoch": 1.5308641975308643, "percentage": 30.62, "elapsed_time": "0:26:25", "remaining_time": "0:59:52"}
+{"current_steps": 125, "total_steps": 405, "loss": 0.444, "lr": 6.994042992684406e-05, "epoch": 1.5432098765432098, "percentage": 30.86, "elapsed_time": "0:26:37", "remaining_time": "0:59:38"}
+{"current_steps": 126, "total_steps": 405, "loss": 0.4503, "lr": 6.971038783709658e-05, "epoch": 1.5555555555555556, "percentage": 31.11, "elapsed_time": "0:26:50", "remaining_time": "0:59:25"}
+{"current_steps": 127, "total_steps": 405, "loss": 0.4606, "lr": 6.947813263937347e-05, "epoch": 1.567901234567901, "percentage": 31.36, "elapsed_time": "0:27:02", "remaining_time": "0:59:11"}
+{"current_steps": 128, "total_steps": 405, "loss": 0.4467, "lr": 6.924368163421733e-05, "epoch": 1.5802469135802468, "percentage": 31.6, "elapsed_time": "0:27:14", "remaining_time": "0:58:57"}
+{"current_steps": 129, "total_steps": 405, "loss": 0.452, "lr": 6.900705228573507e-05, "epoch": 1.5925925925925926, "percentage": 31.85, "elapsed_time": "0:27:27", "remaining_time": "0:58:44"}
+{"current_steps": 130, "total_steps": 405, "loss": 0.4497, "lr": 6.876826222029699e-05, "epoch": 1.6049382716049383, "percentage": 32.1, "elapsed_time": "0:27:39", "remaining_time": "0:58:30"}
+{"current_steps": 131, "total_steps": 405, "loss": 0.4452, "lr": 6.852732922522385e-05, "epoch": 1.617283950617284, "percentage": 32.35, "elapsed_time": "0:27:52", "remaining_time": "0:58:17"}
+{"current_steps": 132, "total_steps": 405, "loss": 0.4499, "lr": 6.828427124746191e-05, "epoch": 1.6296296296296298, "percentage": 32.59, "elapsed_time": "0:28:04", "remaining_time": "0:58:02"}
+{"current_steps": 133, "total_steps": 405, "loss": 0.4479, "lr": 6.803910639224598e-05, "epoch": 1.6419753086419753, "percentage": 32.84, "elapsed_time": "0:28:16", "remaining_time": "0:57:48"}
+{"current_steps": 134, "total_steps": 405, "loss": 0.4485, "lr": 6.77918529217509e-05, "epoch": 1.654320987654321, "percentage": 33.09, "elapsed_time": "0:28:28", "remaining_time": "0:57:35"}
+{"current_steps": 135, "total_steps": 405, "loss": 0.4369, "lr": 6.754252925373109e-05, "epoch": 1.6666666666666665, "percentage": 33.33, "elapsed_time": "0:28:40", "remaining_time": "0:57:21"}
+{"current_steps": 136, "total_steps": 405, "loss": 0.4392, "lr": 6.729115396014871e-05, "epoch": 1.6790123456790123, "percentage": 33.58, "elapsed_time": "0:28:52", "remaining_time": "0:57:07"}
+{"current_steps": 137, "total_steps": 405, "loss": 0.4466, "lr": 6.703774576579018e-05, "epoch": 1.691358024691358, "percentage": 33.83, "elapsed_time": "0:29:05", "remaining_time": "0:56:53"}
+{"current_steps": 138, "total_steps": 405, "loss": 0.4485, "lr": 6.678232354687144e-05, "epoch": 1.7037037037037037, "percentage": 34.07, "elapsed_time": "0:29:17", "remaining_time": "0:56:40"}
+{"current_steps": 139, "total_steps": 405, "loss": 0.4419, "lr": 6.652490632963182e-05, "epoch": 1.7160493827160495, "percentage": 34.32, "elapsed_time": "0:29:29", "remaining_time": "0:56:26"}
+{"current_steps": 140, "total_steps": 405, "loss": 0.4421, "lr": 6.626551328891681e-05, "epoch": 1.7283950617283952, "percentage": 34.57, "elapsed_time": "0:29:42", "remaining_time": "0:56:13"}
+{"current_steps": 141, "total_steps": 405, "loss": 0.4446, "lr": 6.600416374674978e-05, "epoch": 1.7407407407407407, "percentage": 34.81, "elapsed_time": "0:29:54", "remaining_time": "0:55:59"}
+{"current_steps": 142, "total_steps": 405, "loss": 0.4439, "lr": 6.57408771708926e-05, "epoch": 1.7530864197530864, "percentage": 35.06, "elapsed_time": "0:30:06", "remaining_time": "0:55:45"}
+{"current_steps": 143, "total_steps": 405, "loss": 0.4405, "lr": 6.547567317339557e-05, "epoch": 1.765432098765432, "percentage": 35.31, "elapsed_time": "0:30:18", "remaining_time": "0:55:31"}
+{"current_steps": 144, "total_steps": 405, "loss": 0.4468, "lr": 6.520857150913655e-05, "epoch": 1.7777777777777777, "percentage": 35.56, "elapsed_time": "0:30:30", "remaining_time": "0:55:18"}
+{"current_steps": 145, "total_steps": 405, "loss": 0.4403, "lr": 6.493959207434934e-05, "epoch": 1.7901234567901234, "percentage": 35.8, "elapsed_time": "0:30:43", "remaining_time": "0:55:04"}
+{"current_steps": 146, "total_steps": 405, "loss": 0.4441, "lr": 6.466875490514173e-05, "epoch": 1.8024691358024691, "percentage": 36.05, "elapsed_time": "0:30:55", "remaining_time": "0:54:51"}
+{"current_steps": 147, "total_steps": 405, "loss": 0.4367, "lr": 6.439608017600292e-05, "epoch": 1.8148148148148149, "percentage": 36.3, "elapsed_time": "0:31:07", "remaining_time": "0:54:37"}
+{"current_steps": 148, "total_steps": 405, "loss": 0.4383, "lr": 6.412158819830082e-05, "epoch": 1.8271604938271606, "percentage": 36.54, "elapsed_time": "0:31:20", "remaining_time": "0:54:24"}
+{"current_steps": 149, "total_steps": 405, "loss": 0.4443, "lr": 6.384529941876902e-05, "epoch": 1.8395061728395061, "percentage": 36.79, "elapsed_time": "0:31:32", "remaining_time": "0:54:11"}
+{"current_steps": 150, "total_steps": 405, "loss": 0.4343, "lr": 6.356723441798375e-05, "epoch": 1.8518518518518519, "percentage": 37.04, "elapsed_time": "0:31:44", "remaining_time": "0:53:58"}
+{"current_steps": 151, "total_steps": 405, "loss": 0.436, "lr": 6.328741390883084e-05, "epoch": 1.8641975308641974, "percentage": 37.28, "elapsed_time": "0:31:56", "remaining_time": "0:53:44"}
+{"current_steps": 152, "total_steps": 405, "loss": 0.4446, "lr": 6.300585873496279e-05, "epoch": 1.876543209876543, "percentage": 37.53, "elapsed_time": "0:32:09", "remaining_time": "0:53:31"}
+{"current_steps": 153, "total_steps": 405, "loss": 0.4376, "lr": 6.272258986924624e-05, "epoch": 1.8888888888888888, "percentage": 37.78, "elapsed_time": "0:32:21", "remaining_time": "0:53:17"}
+{"current_steps": 154, "total_steps": 405, "loss": 0.4425, "lr": 6.243762841219958e-05, "epoch": 1.9012345679012346, "percentage": 38.02, "elapsed_time": "0:32:33", "remaining_time": "0:53:04"}
+{"current_steps": 155, "total_steps": 405, "loss": 0.4438, "lr": 6.215099559042132e-05, "epoch": 1.9135802469135803, "percentage": 38.27, "elapsed_time": "0:32:46", "remaining_time": "0:52:51"}
+{"current_steps": 156, "total_steps": 405, "loss": 0.4451, "lr": 6.186271275500885e-05, "epoch": 1.925925925925926, "percentage": 38.52, "elapsed_time": "0:32:58", "remaining_time": "0:52:37"}
+{"current_steps": 157, "total_steps": 405, "loss": 0.4496, "lr": 6.157280137996797e-05, "epoch": 1.9382716049382716, "percentage": 38.77, "elapsed_time": "0:33:10", "remaining_time": "0:52:24"}
+{"current_steps": 158, "total_steps": 405, "loss": 0.4406, "lr": 6.128128306061347e-05, "epoch": 1.9506172839506173, "percentage": 39.01, "elapsed_time": "0:33:22", "remaining_time": "0:52:11"}
+{"current_steps": 159, "total_steps": 405, "loss": 0.4432, "lr": 6.098817951196032e-05, "epoch": 1.9629629629629628, "percentage": 39.26, "elapsed_time": "0:33:34", "remaining_time": "0:51:57"}
+{"current_steps": 160, "total_steps": 405, "loss": 0.4396, "lr": 6.0693512567106275e-05, "epoch": 1.9753086419753085, "percentage": 39.51, "elapsed_time": "0:33:47", "remaining_time": "0:51:43"}
+{"current_steps": 161, "total_steps": 405, "loss": 0.4397, "lr": 6.0397304175605444e-05, "epoch": 1.9876543209876543, "percentage": 39.75, "elapsed_time": "0:33:59", "remaining_time": "0:51:31"}
+{"current_steps": 162, "total_steps": 405, "loss": 0.4339, "lr": 6.009957640183333e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:34:12", "remaining_time": "0:51:18"}
+{"current_steps": 163, "total_steps": 405, "loss": 0.4037, "lr": 5.980035142334326e-05, "epoch": 2.0123456790123457, "percentage": 40.25, "elapsed_time": "0:35:06", "remaining_time": "0:52:08"}
+{"current_steps": 164, "total_steps": 405, "loss": 0.4069, "lr": 5.94996515292144e-05, "epoch": 2.0246913580246915, "percentage": 40.49, "elapsed_time": "0:35:19", "remaining_time": "0:51:55"}
+{"current_steps": 165, "total_steps": 405, "loss": 0.4072, "lr": 5.919749911839146e-05, "epoch": 2.037037037037037, "percentage": 40.74, "elapsed_time": "0:35:33", "remaining_time": "0:51:42"}
+{"current_steps": 166, "total_steps": 405, "loss": 0.409, "lr": 5.8893916698016154e-05, "epoch": 2.049382716049383, "percentage": 40.99, "elapsed_time": "0:35:45", "remaining_time": "0:51:29"}
+{"current_steps": 167, "total_steps": 405, "loss": 0.4054, "lr": 5.858892688175075e-05, "epoch": 2.0617283950617282, "percentage": 41.23, "elapsed_time": "0:35:58", "remaining_time": "0:51:15"}
+{"current_steps": 168, "total_steps": 405, "loss": 0.4102, "lr": 5.828255238809352e-05, "epoch": 2.074074074074074, "percentage": 41.48, "elapsed_time": "0:36:11", "remaining_time": "0:51:02"}
+{"current_steps": 169, "total_steps": 405, "loss": 0.4093, "lr": 5.797481603868646e-05, "epoch": 2.0864197530864197, "percentage": 41.73, "elapsed_time": "0:36:23", "remaining_time": "0:50:49"}
+{"current_steps": 170, "total_steps": 405, "loss": 0.4056, "lr": 5.766574075661538e-05, "epoch": 2.0987654320987654, "percentage": 41.98, "elapsed_time": "0:36:36", "remaining_time": "0:50:36"}
+{"current_steps": 171, "total_steps": 405, "loss": 0.4017, "lr": 5.735534956470233e-05, "epoch": 2.111111111111111, "percentage": 42.22, "elapsed_time": "0:36:48", "remaining_time": "0:50:22"}
+{"current_steps": 172, "total_steps": 405, "loss": 0.4043, "lr": 5.7043665583790627e-05, "epoch": 2.123456790123457, "percentage": 42.47, "elapsed_time": "0:37:01", "remaining_time": "0:50:09"}
+{"current_steps": 173, "total_steps": 405, "loss": 0.3978, "lr": 5.673071203102261e-05, "epoch": 2.1358024691358026, "percentage": 42.72, "elapsed_time": "0:37:14", "remaining_time": "0:49:56"}
+{"current_steps": 174, "total_steps": 405, "loss": 0.405, "lr": 5.641651221811028e-05, "epoch": 2.148148148148148, "percentage": 42.96, "elapsed_time": "0:37:27", "remaining_time": "0:49:43"}
+{"current_steps": 175, "total_steps": 405, "loss": 0.4015, "lr": 5.6101089549598704e-05, "epoch": 2.1604938271604937, "percentage": 43.21, "elapsed_time": "0:37:39", "remaining_time": "0:49:29"}
+{"current_steps": 176, "total_steps": 405, "loss": 0.3993, "lr": 5.578446752112273e-05, "epoch": 2.1728395061728394, "percentage": 43.46, "elapsed_time": "0:37:52", "remaining_time": "0:49:17"}
+{"current_steps": 177, "total_steps": 405, "loss": 0.401, "lr": 5.546666971765675e-05, "epoch": 2.185185185185185, "percentage": 43.7, "elapsed_time": "0:38:05", "remaining_time": "0:49:04"}
+{"current_steps": 178, "total_steps": 405, "loss": 0.4013, "lr": 5.5147719811757914e-05, "epoch": 2.197530864197531, "percentage": 43.95, "elapsed_time": "0:38:17", "remaining_time": "0:48:50"}
+{"current_steps": 179, "total_steps": 405, "loss": 0.4037, "lr": 5.4827641561802716e-05, "epoch": 2.2098765432098766, "percentage": 44.2, "elapsed_time": "0:38:30", "remaining_time": "0:48:37"}
+{"current_steps": 180, "total_steps": 405, "loss": 0.4084, "lr": 5.4506458810217286e-05, "epoch": 2.2222222222222223, "percentage": 44.44, "elapsed_time": "0:38:44", "remaining_time": "0:48:25"}
+{"current_steps": 181, "total_steps": 405, "loss": 0.3974, "lr": 5.4184195481701425e-05, "epoch": 2.234567901234568, "percentage": 44.69, "elapsed_time": "0:38:57", "remaining_time": "0:48:12"}
+{"current_steps": 182, "total_steps": 405, "loss": 0.3996, "lr": 5.38608755814464e-05, "epoch": 2.246913580246914, "percentage": 44.94, "elapsed_time": "0:39:09", "remaining_time": "0:47:58"}
+{"current_steps": 183, "total_steps": 405, "loss": 0.4026, "lr": 5.353652319334682e-05, "epoch": 2.259259259259259, "percentage": 45.19, "elapsed_time": "0:39:22", "remaining_time": "0:47:45"}
+{"current_steps": 184, "total_steps": 405, "loss": 0.409, "lr": 5.321116247820669e-05, "epoch": 2.271604938271605, "percentage": 45.43, "elapsed_time": "0:39:35", "remaining_time": "0:47:32"}
+{"current_steps": 185, "total_steps": 405, "loss": 0.3992, "lr": 5.288481767193963e-05, "epoch": 2.2839506172839505, "percentage": 45.68, "elapsed_time": "0:39:47", "remaining_time": "0:47:19"}
+{"current_steps": 186, "total_steps": 405, "loss": 0.4106, "lr": 5.2557513083763605e-05, "epoch": 2.2962962962962963, "percentage": 45.93, "elapsed_time": "0:40:00", "remaining_time": "0:47:05"}
+{"current_steps": 187, "total_steps": 405, "loss": 0.395, "lr": 5.2229273094390124e-05, "epoch": 2.308641975308642, "percentage": 46.17, "elapsed_time": "0:40:11", "remaining_time": "0:46:51"}
+{"current_steps": 188, "total_steps": 405, "loss": 0.3962, "lr": 5.190012215420812e-05, "epoch": 2.3209876543209877, "percentage": 46.42, "elapsed_time": "0:40:24", "remaining_time": "0:46:39"}
+{"current_steps": 189, "total_steps": 405, "loss": 0.4009, "lr": 5.1570084781462716e-05, "epoch": 2.3333333333333335, "percentage": 46.67, "elapsed_time": "0:40:37", "remaining_time": "0:46:26"}
+{"current_steps": 190, "total_steps": 405, "loss": 0.4003, "lr": 5.123918556042878e-05, "epoch": 2.3456790123456788, "percentage": 46.91, "elapsed_time": "0:40:50", "remaining_time": "0:46:12"}
+{"current_steps": 191, "total_steps": 405, "loss": 0.407, "lr": 5.0907449139579755e-05, "epoch": 2.3580246913580245, "percentage": 47.16, "elapsed_time": "0:41:02", "remaining_time": "0:45:58"}
+{"current_steps": 192, "total_steps": 405, "loss": 0.406, "lr": 5.057490022975156e-05, "epoch": 2.3703703703703702, "percentage": 47.41, "elapsed_time": "0:41:14", "remaining_time": "0:45:45"}
+{"current_steps": 193, "total_steps": 405, "loss": 0.4087, "lr": 5.024156360230189e-05, "epoch": 2.382716049382716, "percentage": 47.65, "elapsed_time": "0:41:27", "remaining_time": "0:45:32"}
+{"current_steps": 194, "total_steps": 405, "loss": 0.4051, "lr": 4.9907464087265045e-05, "epoch": 2.3950617283950617, "percentage": 47.9, "elapsed_time": "0:41:39", "remaining_time": "0:45:18"}
+{"current_steps": 195, "total_steps": 405, "loss": 0.4115, "lr": 4.9572626571502316e-05, "epoch": 2.4074074074074074, "percentage": 48.15, "elapsed_time": "0:41:52", "remaining_time": "0:45:06"}
+{"current_steps": 196, "total_steps": 405, "loss": 0.4009, "lr": 4.9237075996848235e-05, "epoch": 2.419753086419753, "percentage": 48.4, "elapsed_time": "0:42:05", "remaining_time": "0:44:52"}
+{"current_steps": 197, "total_steps": 405, "loss": 0.4018, "lr": 4.890083735825258e-05, "epoch": 2.432098765432099, "percentage": 48.64, "elapsed_time": "0:42:17", "remaining_time": "0:44:39"}
+{"current_steps": 198, "total_steps": 405, "loss": 0.4005, "lr": 4.8563935701918646e-05, "epoch": 2.4444444444444446, "percentage": 48.89, "elapsed_time": "0:42:30", "remaining_time": "0:44:26"}
+{"current_steps": 199, "total_steps": 405, "loss": 0.4024, "lr": 4.8226396123437466e-05, "epoch": 2.45679012345679, "percentage": 49.14, "elapsed_time": "0:42:42", "remaining_time": "0:44:12"}
+{"current_steps": 200, "total_steps": 405, "loss": 0.3938, "lr": 4.788824376591849e-05, "epoch": 2.4691358024691357, "percentage": 49.38, "elapsed_time": "0:42:55", "remaining_time": "0:44:00"}
+{"current_steps": 201, "total_steps": 405, "loss": 0.4098, "lr": 4.754950381811667e-05, "epoch": 2.4814814814814814, "percentage": 49.63, "elapsed_time": "0:43:08", "remaining_time": "0:43:46"}
+{"current_steps": 202, "total_steps": 405, "loss": 0.4008, "lr": 4.721020151255624e-05, "epoch": 2.493827160493827, "percentage": 49.88, "elapsed_time": "0:43:20", "remaining_time": "0:43:33"}
+{"current_steps": 203, "total_steps": 405, "loss": 0.3958, "lr": 4.6870362123651056e-05, "epoch": 2.506172839506173, "percentage": 50.12, "elapsed_time": "0:43:33", "remaining_time": "0:43:20"}
+{"current_steps": 204, "total_steps": 405, "loss": 0.3935, "lr": 4.6530010965821984e-05, "epoch": 2.5185185185185186, "percentage": 50.37, "elapsed_time": "0:43:46", "remaining_time": "0:43:07"}
+{"current_steps": 205, "total_steps": 405, "loss": 0.3975, "lr": 4.618917339161125e-05, "epoch": 2.5308641975308643, "percentage": 50.62, "elapsed_time": "0:43:58", "remaining_time": "0:42:54"}
+{"current_steps": 206, "total_steps": 405, "loss": 0.4012, "lr": 4.584787478979394e-05, "epoch": 2.5432098765432096, "percentage": 50.86, "elapsed_time": "0:44:11", "remaining_time": "0:42:41"}
+{"current_steps": 207, "total_steps": 405, "loss": 0.3935, "lr": 4.550614058348674e-05, "epoch": 2.5555555555555554, "percentage": 51.11, "elapsed_time": "0:44:23", "remaining_time": "0:42:27"}
+{"current_steps": 208, "total_steps": 405, "loss": 0.4017, "lr": 4.516399622825428e-05, "epoch": 2.567901234567901, "percentage": 51.36, "elapsed_time": "0:44:36", "remaining_time": "0:42:14"}
+{"current_steps": 209, "total_steps": 405, "loss": 0.3986, "lr": 4.4821467210212924e-05, "epoch": 2.580246913580247, "percentage": 51.6, "elapsed_time": "0:44:48", "remaining_time": "0:42:01"}
+{"current_steps": 210, "total_steps": 405, "loss": 0.3983, "lr": 4.4478579044132314e-05, "epoch": 2.5925925925925926, "percentage": 51.85, "elapsed_time": "0:45:01", "remaining_time": "0:41:48"}
+{"current_steps": 211, "total_steps": 405, "loss": 0.4084, "lr": 4.41353572715348e-05, "epoch": 2.6049382716049383, "percentage": 52.1, "elapsed_time": "0:45:13", "remaining_time": "0:41:35"}
+{"current_steps": 212, "total_steps": 405, "loss": 0.4, "lr": 4.379182745879289e-05, "epoch": 2.617283950617284, "percentage": 52.35, "elapsed_time": "0:45:26", "remaining_time": "0:41:22"}
+{"current_steps": 213, "total_steps": 405, "loss": 0.3981, "lr": 4.344801519522478e-05, "epoch": 2.6296296296296298, "percentage": 52.59, "elapsed_time": "0:45:39", "remaining_time": "0:41:09"}
+{"current_steps": 214, "total_steps": 405, "loss": 0.4109, "lr": 4.310394609118826e-05, "epoch": 2.6419753086419755, "percentage": 52.84, "elapsed_time": "0:45:51", "remaining_time": "0:40:56"}
+{"current_steps": 215, "total_steps": 405, "loss": 0.4069, "lr": 4.2759645776172996e-05, "epoch": 2.6543209876543212, "percentage": 53.09, "elapsed_time": "0:46:04", "remaining_time": "0:40:43"}
+{"current_steps": 216, "total_steps": 405, "loss": 0.4008, "lr": 4.241513989689145e-05, "epoch": 2.6666666666666665, "percentage": 53.33, "elapsed_time": "0:46:17", "remaining_time": "0:40:30"}
+{"current_steps": 217, "total_steps": 405, "loss": 0.3977, "lr": 4.2070454115368385e-05, "epoch": 2.6790123456790123, "percentage": 53.58, "elapsed_time": "0:46:30", "remaining_time": "0:40:17"}
+{"current_steps": 218, "total_steps": 405, "loss": 0.4001, "lr": 4.1725614107029387e-05, "epoch": 2.691358024691358, "percentage": 53.83, "elapsed_time": "0:46:43", "remaining_time": "0:40:04"}
+{"current_steps": 219, "total_steps": 405, "loss": 0.3981, "lr": 4.138064555878833e-05, "epoch": 2.7037037037037037, "percentage": 54.07, "elapsed_time": "0:46:56", "remaining_time": "0:39:51"}
+{"current_steps": 220, "total_steps": 405, "loss": 0.4023, "lr": 4.1035574167133905e-05, "epoch": 2.7160493827160495, "percentage": 54.32, "elapsed_time": "0:47:09", "remaining_time": "0:39:39"}
+{"current_steps": 221, "total_steps": 405, "loss": 0.4079, "lr": 4.069042563621555e-05, "epoch": 2.728395061728395, "percentage": 54.57, "elapsed_time": "0:47:21", "remaining_time": "0:39:25"}
+{"current_steps": 222, "total_steps": 405, "loss": 0.407, "lr": 4.034522567592876e-05, "epoch": 2.7407407407407405, "percentage": 54.81, "elapsed_time": "0:47:34", "remaining_time": "0:39:12"}
+{"current_steps": 223, "total_steps": 405, "loss": 0.3969, "lr": 4e-05, "epoch": 2.753086419753086, "percentage": 55.06, "elapsed_time": "0:47:47", "remaining_time": "0:39:00"}
+{"current_steps": 224, "total_steps": 405, "loss": 0.4031, "lr": 3.965477432407125e-05, "epoch": 2.765432098765432, "percentage": 55.31, "elapsed_time": "0:47:59", "remaining_time": "0:38:47"}
+{"current_steps": 225, "total_steps": 405, "loss": 0.3973, "lr": 3.9309574363784465e-05, "epoch": 2.7777777777777777, "percentage": 55.56, "elapsed_time": "0:48:12", "remaining_time": "0:38:33"}
+{"current_steps": 226, "total_steps": 405, "loss": 0.3994, "lr": 3.8964425832866115e-05, "epoch": 2.7901234567901234, "percentage": 55.8, "elapsed_time": "0:48:25", "remaining_time": "0:38:21"}
+{"current_steps": 227, "total_steps": 405, "loss": 0.4046, "lr": 3.861935444121169e-05, "epoch": 2.802469135802469, "percentage": 56.05, "elapsed_time": "0:48:38", "remaining_time": "0:38:08"}
+{"current_steps": 228, "total_steps": 405, "loss": 0.3999, "lr": 3.827438589297062e-05, "epoch": 2.814814814814815, "percentage": 56.3, "elapsed_time": "0:48:50", "remaining_time": "0:37:55"}
+{"current_steps": 229, "total_steps": 405, "loss": 0.3929, "lr": 3.792954588463162e-05, "epoch": 2.8271604938271606, "percentage": 56.54, "elapsed_time": "0:49:03", "remaining_time": "0:37:42"}
+{"current_steps": 230, "total_steps": 405, "loss": 0.4033, "lr": 3.758486010310856e-05, "epoch": 2.8395061728395063, "percentage": 56.79, "elapsed_time": "0:49:16", "remaining_time": "0:37:29"}
+{"current_steps": 231, "total_steps": 405, "loss": 0.3952, "lr": 3.7240354223827004e-05, "epoch": 2.851851851851852, "percentage": 57.04, "elapsed_time": "0:49:30", "remaining_time": "0:37:17"}
+{"current_steps": 232, "total_steps": 405, "loss": 0.4007, "lr": 3.6896053908811755e-05, "epoch": 2.8641975308641974, "percentage": 57.28, "elapsed_time": "0:49:42", "remaining_time": "0:37:04"}
+{"current_steps": 233, "total_steps": 405, "loss": 0.3965, "lr": 3.655198480477523e-05, "epoch": 2.876543209876543, "percentage": 57.53, "elapsed_time": "0:49:56", "remaining_time": "0:36:51"}
+{"current_steps": 234, "total_steps": 405, "loss": 0.4026, "lr": 3.6208172541207114e-05, "epoch": 2.888888888888889, "percentage": 57.78, "elapsed_time": "0:50:09", "remaining_time": "0:36:39"}
+{"current_steps": 235, "total_steps": 405, "loss": 0.4019, "lr": 3.5864642728465205e-05, "epoch": 2.9012345679012346, "percentage": 58.02, "elapsed_time": "0:50:21", "remaining_time": "0:36:26"}
+{"current_steps": 236, "total_steps": 405, "loss": 0.3935, "lr": 3.552142095586769e-05, "epoch": 2.9135802469135803, "percentage": 58.27, "elapsed_time": "0:50:34", "remaining_time": "0:36:12"}
+{"current_steps": 237, "total_steps": 405, "loss": 0.4024, "lr": 3.517853278978708e-05, "epoch": 2.925925925925926, "percentage": 58.52, "elapsed_time": "0:50:46", "remaining_time": "0:35:59"}
+{"current_steps": 238, "total_steps": 405, "loss": 0.4058, "lr": 3.4836003771745736e-05, "epoch": 2.9382716049382713, "percentage": 58.77, "elapsed_time": "0:50:59", "remaining_time": "0:35:46"}
+{"current_steps": 239, "total_steps": 405, "loss": 0.4016, "lr": 3.449385941651328e-05, "epoch": 2.950617283950617, "percentage": 59.01, "elapsed_time": "0:51:12", "remaining_time": "0:35:34"}
+{"current_steps": 240, "total_steps": 405, "loss": 0.3998, "lr": 3.415212521020609e-05, "epoch": 2.962962962962963, "percentage": 59.26, "elapsed_time": "0:51:25", "remaining_time": "0:35:21"}
+{"current_steps": 241, "total_steps": 405, "loss": 0.3994, "lr": 3.381082660838875e-05, "epoch": 2.9753086419753085, "percentage": 59.51, "elapsed_time": "0:51:37", "remaining_time": "0:35:07"}
+{"current_steps": 242, "total_steps": 405, "loss": 0.3948, "lr": 3.346998903417803e-05, "epoch": 2.9876543209876543, "percentage": 59.75, "elapsed_time": "0:51:49", "remaining_time": "0:34:54"}
+{"current_steps": 243, "total_steps": 405, "loss": 0.3809, "lr": 3.312963787634896e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:52:02", "remaining_time": "0:34:41"}
+{"current_steps": 244, "total_steps": 405, "loss": 0.3664, "lr": 3.2789798487443775e-05, "epoch": 3.0123456790123457, "percentage": 60.25, "elapsed_time": "0:52:56", "remaining_time": "0:34:56"}
+{"current_steps": 245, "total_steps": 405, "loss": 0.3702, "lr": 3.245049618188334e-05, "epoch": 3.0246913580246915, "percentage": 60.49, "elapsed_time": "0:53:10", "remaining_time": "0:34:43"}
+{"current_steps": 246, "total_steps": 405, "loss": 0.369, "lr": 3.2111756234081525e-05, "epoch": 3.037037037037037, "percentage": 60.74, "elapsed_time": "0:53:23", "remaining_time": "0:34:30"}
+{"current_steps": 247, "total_steps": 405, "loss": 0.37, "lr": 3.177360387656254e-05, "epoch": 3.049382716049383, "percentage": 60.99, "elapsed_time": "0:53:35", "remaining_time": "0:34:17"}
+{"current_steps": 248, "total_steps": 405, "loss": 0.3701, "lr": 3.143606429808136e-05, "epoch": 3.0617283950617282, "percentage": 61.23, "elapsed_time": "0:53:49", "remaining_time": "0:34:04"}
+{"current_steps": 249, "total_steps": 405, "loss": 0.3707, "lr": 3.109916264174743e-05, "epoch": 3.074074074074074, "percentage": 61.48, "elapsed_time": "0:54:02", "remaining_time": "0:33:51"}
+{"current_steps": 250, "total_steps": 405, "loss": 0.3735, "lr": 3.076292400315179e-05, "epoch": 3.0864197530864197, "percentage": 61.73, "elapsed_time": "0:54:14", "remaining_time": "0:33:37"}
+{"current_steps": 251, "total_steps": 405, "loss": 0.3682, "lr": 3.0427373428497704e-05, "epoch": 3.0987654320987654, "percentage": 61.98, "elapsed_time": "0:54:27", "remaining_time": "0:33:24"}
+{"current_steps": 252, "total_steps": 405, "loss": 0.3668, "lr": 3.0092535912734965e-05, "epoch": 3.111111111111111, "percentage": 62.22, "elapsed_time": "0:54:40", "remaining_time": "0:33:11"}
+{"current_steps": 253, "total_steps": 405, "loss": 0.3653, "lr": 2.9758436397698118e-05, "epoch": 3.123456790123457, "percentage": 62.47, "elapsed_time": "0:54:53", "remaining_time": "0:32:58"}
+{"current_steps": 254, "total_steps": 405, "loss": 0.3711, "lr": 2.9425099770248446e-05, "epoch": 3.1358024691358026, "percentage": 62.72, "elapsed_time": "0:55:06", "remaining_time": "0:32:45"}
+{"current_steps": 255, "total_steps": 405, "loss": 0.3624, "lr": 2.9092550860420252e-05, "epoch": 3.148148148148148, "percentage": 62.96, "elapsed_time": "0:55:19", "remaining_time": "0:32:32"}
+{"current_steps": 256, "total_steps": 405, "loss": 0.3685, "lr": 2.8760814439571233e-05, "epoch": 3.1604938271604937, "percentage": 63.21, "elapsed_time": "0:55:32", "remaining_time": "0:32:19"}
+{"current_steps": 257, "total_steps": 405, "loss": 0.3674, "lr": 2.8429915218537297e-05, "epoch": 3.1728395061728394, "percentage": 63.46, "elapsed_time": "0:55:44", "remaining_time": "0:32:06"}
+{"current_steps": 258, "total_steps": 405, "loss": 0.3608, "lr": 2.809987784579189e-05, "epoch": 3.185185185185185, "percentage": 63.7, "elapsed_time": "0:55:58", "remaining_time": "0:31:53"}
+{"current_steps": 259, "total_steps": 405, "loss": 0.3642, "lr": 2.7770726905609896e-05, "epoch": 3.197530864197531, "percentage": 63.95, "elapsed_time": "0:56:10", "remaining_time": "0:31:40"}
+{"current_steps": 260, "total_steps": 405, "loss": 0.3563, "lr": 2.74424869162364e-05, "epoch": 3.2098765432098766, "percentage": 64.2, "elapsed_time": "0:56:23", "remaining_time": "0:31:26"}
+{"current_steps": 261, "total_steps": 405, "loss": 0.3676, "lr": 2.7115182328060385e-05, "epoch": 3.2222222222222223, "percentage": 64.44, "elapsed_time": "0:56:36", "remaining_time": "0:31:13"}
+{"current_steps": 262, "total_steps": 405, "loss": 0.3625, "lr": 2.678883752179333e-05, "epoch": 3.234567901234568, "percentage": 64.69, "elapsed_time": "0:56:50", "remaining_time": "0:31:01"}
+{"current_steps": 263, "total_steps": 405, "loss": 0.3585, "lr": 2.6463476806653185e-05, "epoch": 3.246913580246914, "percentage": 64.94, "elapsed_time": "0:57:02", "remaining_time": "0:30:47"}
+{"current_steps": 264, "total_steps": 405, "loss": 0.3605, "lr": 2.61391244185536e-05, "epoch": 3.259259259259259, "percentage": 65.19, "elapsed_time": "0:57:14", "remaining_time": "0:30:34"}
+{"current_steps": 265, "total_steps": 405, "loss": 0.3677, "lr": 2.5815804518298575e-05, "epoch": 3.271604938271605, "percentage": 65.43, "elapsed_time": "0:57:27", "remaining_time": "0:30:21"}
+{"current_steps": 266, "total_steps": 405, "loss": 0.3678, "lr": 2.549354118978272e-05, "epoch": 3.2839506172839505, "percentage": 65.68, "elapsed_time": "0:57:40", "remaining_time": "0:30:08"}
+{"current_steps": 267, "total_steps": 405, "loss": 0.3608, "lr": 2.51723584381973e-05, "epoch": 3.2962962962962963, "percentage": 65.93, "elapsed_time": "0:57:53", "remaining_time": "0:29:55"}
+{"current_steps": 268, "total_steps": 405, "loss": 0.3678, "lr": 2.4852280188242096e-05, "epoch": 3.308641975308642, "percentage": 66.17, "elapsed_time": "0:58:06", "remaining_time": "0:29:42"}
+{"current_steps": 269, "total_steps": 405, "loss": 0.3638, "lr": 2.453333028234325e-05, "epoch": 3.3209876543209877, "percentage": 66.42, "elapsed_time": "0:58:18", "remaining_time": "0:29:28"}
+{"current_steps": 270, "total_steps": 405, "loss": 0.3597, "lr": 2.4215532478877283e-05, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "0:58:32", "remaining_time": "0:29:16"}
+{"current_steps": 271, "total_steps": 405, "loss": 0.3667, "lr": 2.3898910450401306e-05, "epoch": 3.3456790123456788, "percentage": 66.91, "elapsed_time": "0:58:44", "remaining_time": "0:29:02"}
+{"current_steps": 272, "total_steps": 405, "loss": 0.3709, "lr": 2.3583487781889737e-05, "epoch": 3.3580246913580245, "percentage": 67.16, "elapsed_time": "0:58:58", "remaining_time": "0:28:49"}
+{"current_steps": 273, "total_steps": 405, "loss": 0.3637, "lr": 2.3269287968977406e-05, "epoch": 3.3703703703703702, "percentage": 67.41, "elapsed_time": "0:59:10", "remaining_time": "0:28:36"}
+{"current_steps": 274, "total_steps": 405, "loss": 0.3735, "lr": 2.2956334416209404e-05, "epoch": 3.382716049382716, "percentage": 67.65, "elapsed_time": "0:59:22", "remaining_time": "0:28:23"}
+{"current_steps": 275, "total_steps": 405, "loss": 0.3622, "lr": 2.264465043529768e-05, "epoch": 3.3950617283950617, "percentage": 67.9, "elapsed_time": "0:59:36", "remaining_time": "0:28:10"}
+{"current_steps": 276, "total_steps": 405, "loss": 0.3644, "lr": 2.233425924338463e-05, "epoch": 3.4074074074074074, "percentage": 68.15, "elapsed_time": "0:59:49", "remaining_time": "0:27:57"}
+{"current_steps": 277, "total_steps": 405, "loss": 0.3687, "lr": 2.2025183961313542e-05, "epoch": 3.419753086419753, "percentage": 68.4, "elapsed_time": "1:00:01", "remaining_time": "0:27:44"}
+{"current_steps": 278, "total_steps": 405, "loss": 0.3663, "lr": 2.1717447611906496e-05, "epoch": 3.432098765432099, "percentage": 68.64, "elapsed_time": "1:00:14", "remaining_time": "0:27:31"}
+{"current_steps": 279, "total_steps": 405, "loss": 0.3689, "lr": 2.141107311824926e-05, "epoch": 3.4444444444444446, "percentage": 68.89, "elapsed_time": "1:00:27", "remaining_time": "0:27:18"}
+{"current_steps": 280, "total_steps": 405, "loss": 0.3618, "lr": 2.1106083301983852e-05, "epoch": 3.45679012345679, "percentage": 69.14, "elapsed_time": "1:00:40", "remaining_time": "0:27:05"}
+{"current_steps": 281, "total_steps": 405, "loss": 0.3727, "lr": 2.0802500881608557e-05, "epoch": 3.4691358024691357, "percentage": 69.38, "elapsed_time": "1:00:52", "remaining_time": "0:26:51"}
+{"current_steps": 282, "total_steps": 405, "loss": 0.3692, "lr": 2.0500348470785614e-05, "epoch": 3.4814814814814814, "percentage": 69.63, "elapsed_time": "1:01:06", "remaining_time": "0:26:39"}
+{"current_steps": 283, "total_steps": 405, "loss": 0.3636, "lr": 2.0199648576656744e-05, "epoch": 3.493827160493827, "percentage": 69.88, "elapsed_time": "1:01:18", "remaining_time": "0:26:25"}
+{"current_steps": 284, "total_steps": 405, "loss": 0.3651, "lr": 1.9900423598166685e-05, "epoch": 3.506172839506173, "percentage": 70.12, "elapsed_time": "1:01:31", "remaining_time": "0:26:12"}
+{"current_steps": 285, "total_steps": 405, "loss": 0.3651, "lr": 1.9602695824394576e-05, "epoch": 3.5185185185185186, "percentage": 70.37, "elapsed_time": "1:01:45", "remaining_time": "0:26:00"}
+{"current_steps": 286, "total_steps": 405, "loss": 0.3662, "lr": 1.9306487432893725e-05, "epoch": 3.5308641975308643, "percentage": 70.62, "elapsed_time": "1:01:58", "remaining_time": "0:25:47"}
+{"current_steps": 287, "total_steps": 405, "loss": 0.3651, "lr": 1.901182048803968e-05, "epoch": 3.5432098765432096, "percentage": 70.86, "elapsed_time": "1:02:12", "remaining_time": "0:25:34"}
+{"current_steps": 288, "total_steps": 405, "loss": 0.3698, "lr": 1.8718716939386543e-05, "epoch": 3.5555555555555554, "percentage": 71.11, "elapsed_time": "1:02:27", "remaining_time": "0:25:22"}
+{"current_steps": 289, "total_steps": 405, "loss": 0.3661, "lr": 1.8427198620032037e-05, "epoch": 3.567901234567901, "percentage": 71.36, "elapsed_time": "1:02:41", "remaining_time": "0:25:09"}
+{"current_steps": 290, "total_steps": 405, "loss": 0.3708, "lr": 1.8137287244991162e-05, "epoch": 3.580246913580247, "percentage": 71.6, "elapsed_time": "1:02:54", "remaining_time": "0:24:56"}
+{"current_steps": 291, "total_steps": 405, "loss": 0.37, "lr": 1.7849004409578678e-05, "epoch": 3.5925925925925926, "percentage": 71.85, "elapsed_time": "1:03:07", "remaining_time": "0:24:43"}
+{"current_steps": 292, "total_steps": 405, "loss": 0.3621, "lr": 1.7562371587800422e-05, "epoch": 3.6049382716049383, "percentage": 72.1, "elapsed_time": "1:03:21", "remaining_time": "0:24:31"}
+{"current_steps": 293, "total_steps": 405, "loss": 0.3705, "lr": 1.7277410130753775e-05, "epoch": 3.617283950617284, "percentage": 72.35, "elapsed_time": "1:03:35", "remaining_time": "0:24:18"}
+{"current_steps": 294, "total_steps": 405, "loss": 0.3583, "lr": 1.6994141265037222e-05, "epoch": 3.6296296296296298, "percentage": 72.59, "elapsed_time": "1:03:48", "remaining_time": "0:24:05"}
+{"current_steps": 295, "total_steps": 405, "loss": 0.3706, "lr": 1.6712586091169183e-05, "epoch": 3.6419753086419755, "percentage": 72.84, "elapsed_time": "1:04:01", "remaining_time": "0:23:52"}
+{"current_steps": 296, "total_steps": 405, "loss": 0.3627, "lr": 1.6432765582016257e-05, "epoch": 3.6543209876543212, "percentage": 73.09, "elapsed_time": "1:04:15", "remaining_time": "0:23:39"}
+{"current_steps": 297, "total_steps": 405, "loss": 0.3683, "lr": 1.615470058123099e-05, "epoch": 3.6666666666666665, "percentage": 73.33, "elapsed_time": "1:04:29", "remaining_time": "0:23:26"}
+{"current_steps": 298, "total_steps": 405, "loss": 0.3677, "lr": 1.5878411801699182e-05, "epoch": 3.6790123456790123, "percentage": 73.58, "elapsed_time": "1:04:42", "remaining_time": "0:23:14"}
+{"current_steps": 299, "total_steps": 405, "loss": 0.3725, "lr": 1.5603919823997083e-05, "epoch": 3.691358024691358, "percentage": 73.83, "elapsed_time": "1:04:55", "remaining_time": "0:23:01"}
+{"current_steps": 300, "total_steps": 405, "loss": 0.3632, "lr": 1.5331245094858277e-05, "epoch": 3.7037037037037037, "percentage": 74.07, "elapsed_time": "1:05:09", "remaining_time": "0:22:48"}
+{"current_steps": 301, "total_steps": 405, "loss": 0.363, "lr": 1.5060407925650662e-05, "epoch": 3.7160493827160495, "percentage": 74.32, "elapsed_time": "1:05:23", "remaining_time": "0:22:35"}
+{"current_steps": 302, "total_steps": 405, "loss": 0.3636, "lr": 1.4791428490863462e-05, "epoch": 3.728395061728395, "percentage": 74.57, "elapsed_time": "1:05:36", "remaining_time": "0:22:22"}
+{"current_steps": 303, "total_steps": 405, "loss": 0.3662, "lr": 1.4524326826604442e-05, "epoch": 3.7407407407407405, "percentage": 74.81, "elapsed_time": "1:05:51", "remaining_time": "0:22:10"}
+{"current_steps": 304, "total_steps": 405, "loss": 0.3612, "lr": 1.425912282910741e-05, "epoch": 3.753086419753086, "percentage": 75.06, "elapsed_time": "1:06:04", "remaining_time": "0:21:57"}
+{"current_steps": 305, "total_steps": 405, "loss": 0.3632, "lr": 1.3995836253250233e-05, "epoch": 3.765432098765432, "percentage": 75.31, "elapsed_time": "1:06:18", "remaining_time": "0:21:44"}
+{"current_steps": 306, "total_steps": 405, "loss": 0.3656, "lr": 1.3734486711083199e-05, "epoch": 3.7777777777777777, "percentage": 75.56, "elapsed_time": "1:06:31", "remaining_time": "0:21:31"}
+{"current_steps": 307, "total_steps": 405, "loss": 0.3625, "lr": 1.3475093670368202e-05, "epoch": 3.7901234567901234, "percentage": 75.8, "elapsed_time": "1:06:45", "remaining_time": "0:21:18"}
+{"current_steps": 308, "total_steps": 405, "loss": 0.3681, "lr": 1.3217676453128583e-05, "epoch": 3.802469135802469, "percentage": 76.05, "elapsed_time": "1:06:59", "remaining_time": "0:21:05"}
+{"current_steps": 309, "total_steps": 405, "loss": 0.3702, "lr": 1.2962254234209826e-05, "epoch": 3.814814814814815, "percentage": 76.3, "elapsed_time": "1:07:12", "remaining_time": "0:20:52"}
+{"current_steps": 310, "total_steps": 405, "loss": 0.3596, "lr": 1.2708846039851306e-05, "epoch": 3.8271604938271606, "percentage": 76.54, "elapsed_time": "1:07:25", "remaining_time": "0:20:39"}
+{"current_steps": 311, "total_steps": 405, "loss": 0.3597, "lr": 1.2457470746268912e-05, "epoch": 3.8395061728395063, "percentage": 76.79, "elapsed_time": "1:07:38", "remaining_time": "0:20:26"}
+{"current_steps": 312, "total_steps": 405, "loss": 0.3705, "lr": 1.2208147078249106e-05, "epoch": 3.851851851851852, "percentage": 77.04, "elapsed_time": "1:07:52", "remaining_time": "0:20:14"}
+{"current_steps": 313, "total_steps": 405, "loss": 0.378, "lr": 1.1960893607754022e-05, "epoch": 3.8641975308641974, "percentage": 77.28, "elapsed_time": "1:08:06", "remaining_time": "0:20:01"}
+{"current_steps": 314, "total_steps": 405, "loss": 0.3709, "lr": 1.1715728752538103e-05, "epoch": 3.876543209876543, "percentage": 77.53, "elapsed_time": "1:08:19", "remaining_time": "0:19:47"}
+{"current_steps": 315, "total_steps": 405, "loss": 0.3734, "lr": 1.1472670774776159e-05, "epoch": 3.888888888888889, "percentage": 77.78, "elapsed_time": "1:08:32", "remaining_time": "0:19:35"}
+{"current_steps": 316, "total_steps": 405, "loss": 0.3644, "lr": 1.123173777970303e-05, "epoch": 3.9012345679012346, "percentage": 78.02, "elapsed_time": "1:08:46", "remaining_time": "0:19:22"}
+{"current_steps": 317, "total_steps": 405, "loss": 0.3639, "lr": 1.0992947714264952e-05, "epoch": 3.9135802469135803, "percentage": 78.27, "elapsed_time": "1:09:00", "remaining_time": "0:19:09"}
+{"current_steps": 318, "total_steps": 405, "loss": 0.3705, "lr": 1.0756318365782672e-05, "epoch": 3.925925925925926, "percentage": 78.52, "elapsed_time": "1:09:12", "remaining_time": "0:18:56"}
+{"current_steps": 319, "total_steps": 405, "loss": 0.3649, "lr": 1.0521867360626534e-05, "epoch": 3.9382716049382713, "percentage": 78.77, "elapsed_time": "1:09:26", "remaining_time": "0:18:43"}
+{"current_steps": 320, "total_steps": 405, "loss": 0.3702, "lr": 1.028961216290342e-05, "epoch": 3.950617283950617, "percentage": 79.01, "elapsed_time": "1:09:39", "remaining_time": "0:18:30"}
+{"current_steps": 321, "total_steps": 405, "loss": 0.3686, "lr": 1.0059570073155953e-05, "epoch": 3.962962962962963, "percentage": 79.26, "elapsed_time": "1:09:52", "remaining_time": "0:18:17"}
+{"current_steps": 322, "total_steps": 405, "loss": 0.3622, "lr": 9.831758227073714e-06, "epoch": 3.9753086419753085, "percentage": 79.51, "elapsed_time": "1:10:05", "remaining_time": "0:18:03"}
+{"current_steps": 323, "total_steps": 405, "loss": 0.3662, "lr": 9.606193594216852e-06, "epoch": 3.9876543209876543, "percentage": 79.75, "elapsed_time": "1:10:17", "remaining_time": "0:17:50"}
+{"current_steps": 324, "total_steps": 405, "loss": 0.3514, "lr": 9.382892976752024e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "1:10:30", "remaining_time": "0:17:37"}
+{"current_steps": 325, "total_steps": 405, "loss": 0.3447, "lr": 9.161873008200816e-06, "epoch": 4.012345679012346, "percentage": 80.25, "elapsed_time": "1:11:29", "remaining_time": "0:17:35"}
+{"current_steps": 326, "total_steps": 405, "loss": 0.3564, "lr": 8.943150152200734e-06, "epoch": 4.0246913580246915, "percentage": 80.49, "elapsed_time": "1:11:42", "remaining_time": "0:17:22"}
+{"current_steps": 327, "total_steps": 405, "loss": 0.3399, "lr": 8.72674070127881e-06, "epoch": 4.037037037037037, "percentage": 80.74, "elapsed_time": "1:11:56", "remaining_time": "0:17:09"}
+{"current_steps": 328, "total_steps": 405, "loss": 0.3434, "lr": 8.512660775637998e-06, "epoch": 4.049382716049383, "percentage": 80.99, "elapsed_time": "1:12:09", "remaining_time": "0:16:56"}
+{"current_steps": 329, "total_steps": 405, "loss": 0.3416, "lr": 8.300926321956391e-06, "epoch": 4.061728395061729, "percentage": 81.23, "elapsed_time": "1:12:22", "remaining_time": "0:16:43"}
+{"current_steps": 330, "total_steps": 405, "loss": 0.3518, "lr": 8.091553112199362e-06, "epoch": 4.074074074074074, "percentage": 81.48, "elapsed_time": "1:12:36", "remaining_time": "0:16:30"}
+{"current_steps": 331, "total_steps": 405, "loss": 0.3446, "lr": 7.884556742444704e-06, "epoch": 4.08641975308642, "percentage": 81.73, "elapsed_time": "1:12:50", "remaining_time": "0:16:17"}
+{"current_steps": 332, "total_steps": 405, "loss": 0.3466, "lr": 7.679952631720944e-06, "epoch": 4.098765432098766, "percentage": 81.98, "elapsed_time": "1:13:04", "remaining_time": "0:16:04"}
+{"current_steps": 333, "total_steps": 405, "loss": 0.355, "lr": 7.477756020858695e-06, "epoch": 4.111111111111111, "percentage": 82.22, "elapsed_time": "1:13:18", "remaining_time": "0:15:50"}
+{"current_steps": 334, "total_steps": 405, "loss": 0.3432, "lr": 7.277981971355487e-06, "epoch": 4.1234567901234565, "percentage": 82.47, "elapsed_time": "1:13:31", "remaining_time": "0:15:37"}
+{"current_steps": 335, "total_steps": 405, "loss": 0.3451, "lr": 7.080645364253747e-06, "epoch": 4.135802469135802, "percentage": 82.72, "elapsed_time": "1:13:45", "remaining_time": "0:15:24"}
+{"current_steps": 336, "total_steps": 405, "loss": 0.345, "lr": 6.885760899032368e-06, "epoch": 4.148148148148148, "percentage": 82.96, "elapsed_time": "1:13:59", "remaining_time": "0:15:11"}
+{"current_steps": 337, "total_steps": 405, "loss": 0.3472, "lr": 6.69334309251175e-06, "epoch": 4.160493827160494, "percentage": 83.21, "elapsed_time": "1:14:12", "remaining_time": "0:14:58"}
+{"current_steps": 338, "total_steps": 405, "loss": 0.345, "lr": 6.503406277772457e-06, "epoch": 4.172839506172839, "percentage": 83.46, "elapsed_time": "1:14:25", "remaining_time": "0:14:45"}
+{"current_steps": 339, "total_steps": 405, "loss": 0.3431, "lr": 6.31596460308753e-06, "epoch": 4.185185185185185, "percentage": 83.7, "elapsed_time": "1:14:38", "remaining_time": "0:14:31"}
+{"current_steps": 340, "total_steps": 405, "loss": 0.3492, "lr": 6.1310320308686354e-06, "epoch": 4.197530864197531, "percentage": 83.95, "elapsed_time": "1:14:53", "remaining_time": "0:14:19"}
+{"current_steps": 341, "total_steps": 405, "loss": 0.3406, "lr": 5.9486223366259555e-06, "epoch": 4.209876543209877, "percentage": 84.2, "elapsed_time": "1:15:05", "remaining_time": "0:14:05"}
+{"current_steps": 342, "total_steps": 405, "loss": 0.3458, "lr": 5.768749107942105e-06, "epoch": 4.222222222222222, "percentage": 84.44, "elapsed_time": "1:15:18", "remaining_time": "0:13:52"}
+{"current_steps": 343, "total_steps": 405, "loss": 0.3427, "lr": 5.5914257434599705e-06, "epoch": 4.234567901234568, "percentage": 84.69, "elapsed_time": "1:15:32", "remaining_time": "0:13:39"}
+{"current_steps": 344, "total_steps": 405, "loss": 0.3478, "lr": 5.416665451884706e-06, "epoch": 4.246913580246914, "percentage": 84.94, "elapsed_time": "1:15:46", "remaining_time": "0:13:26"}
+{"current_steps": 345, "total_steps": 405, "loss": 0.3604, "lr": 5.24448125099974e-06, "epoch": 4.2592592592592595, "percentage": 85.19, "elapsed_time": "1:16:00", "remaining_time": "0:13:13"}
+{"current_steps": 346, "total_steps": 405, "loss": 0.3439, "lr": 5.074885966697167e-06, "epoch": 4.271604938271605, "percentage": 85.43, "elapsed_time": "1:16:12", "remaining_time": "0:12:59"}
+{"current_steps": 347, "total_steps": 405, "loss": 0.338, "lr": 4.9078922320223225e-06, "epoch": 4.283950617283951, "percentage": 85.68, "elapsed_time": "1:16:26", "remaining_time": "0:12:46"}
+{"current_steps": 348, "total_steps": 405, "loss": 0.3456, "lr": 4.7435124862327445e-06, "epoch": 4.296296296296296, "percentage": 85.93, "elapsed_time": "1:16:40", "remaining_time": "0:12:33"}
+{"current_steps": 349, "total_steps": 405, "loss": 0.3435, "lr": 4.581758973871609e-06, "epoch": 4.308641975308642, "percentage": 86.17, "elapsed_time": "1:16:53", "remaining_time": "0:12:20"}
+{"current_steps": 350, "total_steps": 405, "loss": 0.3387, "lr": 4.422643743855611e-06, "epoch": 4.320987654320987, "percentage": 86.42, "elapsed_time": "1:17:06", "remaining_time": "0:12:07"}
+{"current_steps": 351, "total_steps": 405, "loss": 0.3465, "lr": 4.266178648577484e-06, "epoch": 4.333333333333333, "percentage": 86.67, "elapsed_time": "1:17:19", "remaining_time": "0:11:53"}
+{"current_steps": 352, "total_steps": 405, "loss": 0.3402, "lr": 4.112375343023076e-06, "epoch": 4.345679012345679, "percentage": 86.91, "elapsed_time": "1:17:33", "remaining_time": "0:11:40"}
+{"current_steps": 353, "total_steps": 405, "loss": 0.3417, "lr": 3.961245283903239e-06, "epoch": 4.3580246913580245, "percentage": 87.16, "elapsed_time": "1:17:47", "remaining_time": "0:11:27"}
+{"current_steps": 354, "total_steps": 405, "loss": 0.3494, "lr": 3.812799728800354e-06, "epoch": 4.37037037037037, "percentage": 87.41, "elapsed_time": "1:18:00", "remaining_time": "0:11:14"}
+{"current_steps": 355, "total_steps": 405, "loss": 0.3486, "lr": 3.6670497353298396e-06, "epoch": 4.382716049382716, "percentage": 87.65, "elapsed_time": "1:18:13", "remaining_time": "0:11:01"}
+{"current_steps": 356, "total_steps": 405, "loss": 0.3439, "lr": 3.5240061603163977e-06, "epoch": 4.395061728395062, "percentage": 87.9, "elapsed_time": "1:18:27", "remaining_time": "0:10:47"}
+{"current_steps": 357, "total_steps": 405, "loss": 0.3399, "lr": 3.3836796589853484e-06, "epoch": 4.407407407407407, "percentage": 88.15, "elapsed_time": "1:18:40", "remaining_time": "0:10:34"}
+{"current_steps": 358, "total_steps": 405, "loss": 0.3374, "lr": 3.246080684168913e-06, "epoch": 4.419753086419753, "percentage": 88.4, "elapsed_time": "1:18:54", "remaining_time": "0:10:21"}
+{"current_steps": 359, "total_steps": 405, "loss": 0.347, "lr": 3.11121948552759e-06, "epoch": 4.432098765432099, "percentage": 88.64, "elapsed_time": "1:19:07", "remaining_time": "0:10:08"}
+{"current_steps": 360, "total_steps": 405, "loss": 0.3517, "lr": 2.9791061087866625e-06, "epoch": 4.444444444444445, "percentage": 88.89, "elapsed_time": "1:19:21", "remaining_time": "0:09:55"}
+{"current_steps": 361, "total_steps": 405, "loss": 0.3507, "lr": 2.849750394987907e-06, "epoch": 4.45679012345679, "percentage": 89.14, "elapsed_time": "1:19:34", "remaining_time": "0:09:41"}
+{"current_steps": 362, "total_steps": 405, "loss": 0.3462, "lr": 2.7231619797565278e-06, "epoch": 4.469135802469136, "percentage": 89.38, "elapsed_time": "1:19:48", "remaining_time": "0:09:28"}
+{"current_steps": 363, "total_steps": 405, "loss": 0.3475, "lr": 2.5993502925834115e-06, "epoch": 4.481481481481482, "percentage": 89.63, "elapsed_time": "1:20:02", "remaining_time": "0:09:15"}
+{"current_steps": 364, "total_steps": 405, "loss": 0.3436, "lr": 2.4783245561227264e-06, "epoch": 4.493827160493828, "percentage": 89.88, "elapsed_time": "1:20:16", "remaining_time": "0:09:02"}
+{"current_steps": 365, "total_steps": 405, "loss": 0.3489, "lr": 2.3600937855049467e-06, "epoch": 4.506172839506172, "percentage": 90.12, "elapsed_time": "1:20:28", "remaining_time": "0:08:49"}
+{"current_steps": 366, "total_steps": 405, "loss": 0.3479, "lr": 2.244666787665297e-06, "epoch": 4.518518518518518, "percentage": 90.37, "elapsed_time": "1:24:15", "remaining_time": "0:08:58"}
+{"current_steps": 367, "total_steps": 405, "loss": 0.3491, "lr": 2.1320521606877653e-06, "epoch": 4.530864197530864, "percentage": 90.62, "elapsed_time": "1:24:30", "remaining_time": "0:08:44"}
+{"current_steps": 368, "total_steps": 405, "loss": 0.3444, "lr": 2.022258293164585e-06, "epoch": 4.54320987654321, "percentage": 90.86, "elapsed_time": "1:24:43", "remaining_time": "0:08:31"}
+{"current_steps": 369, "total_steps": 405, "loss": 0.3402, "lr": 1.9152933635714354e-06, "epoch": 4.555555555555555, "percentage": 91.11, "elapsed_time": "1:24:55", "remaining_time": "0:08:17"}
+{"current_steps": 370, "total_steps": 405, "loss": 0.3497, "lr": 1.8111653396581762e-06, "epoch": 4.567901234567901, "percentage": 91.36, "elapsed_time": "1:25:10", "remaining_time": "0:08:03"}
+{"current_steps": 371, "total_steps": 405, "loss": 0.3451, "lr": 1.709881977855372e-06, "epoch": 4.580246913580247, "percentage": 91.6, "elapsed_time": "1:25:26", "remaining_time": "0:07:49"}
+{"current_steps": 372, "total_steps": 405, "loss": 0.3446, "lr": 1.6114508226965009e-06, "epoch": 4.592592592592593, "percentage": 91.85, "elapsed_time": "1:25:39", "remaining_time": "0:07:35"}
+{"current_steps": 373, "total_steps": 405, "loss": 0.3472, "lr": 1.5158792062559813e-06, "epoch": 4.604938271604938, "percentage": 92.1, "elapsed_time": "1:25:53", "remaining_time": "0:07:22"}
+{"current_steps": 374, "total_steps": 405, "loss": 0.3464, "lr": 1.4231742476029965e-06, "epoch": 4.617283950617284, "percentage": 92.35, "elapsed_time": "1:26:07", "remaining_time": "0:07:08"}
+{"current_steps": 375, "total_steps": 405, "loss": 0.3464, "lr": 1.33334285227122e-06, "epoch": 4.62962962962963, "percentage": 92.59, "elapsed_time": "1:26:21", "remaining_time": "0:06:54"}
+{"current_steps": 376, "total_steps": 405, "loss": 0.3485, "lr": 1.2463917117443968e-06, "epoch": 4.6419753086419755, "percentage": 92.84, "elapsed_time": "1:26:35", "remaining_time": "0:06:40"}
+{"current_steps": 377, "total_steps": 405, "loss": 0.3466, "lr": 1.1623273029579195e-06, "epoch": 4.654320987654321, "percentage": 93.09, "elapsed_time": "1:26:49", "remaining_time": "0:06:26"}
+{"current_steps": 378, "total_steps": 405, "loss": 0.3449, "lr": 1.0811558878163698e-06, "epoch": 4.666666666666667, "percentage": 93.33, "elapsed_time": "1:27:02", "remaining_time": "0:06:13"}
+{"current_steps": 379, "total_steps": 405, "loss": 0.3429, "lr": 1.0028835127270553e-06, "epoch": 4.679012345679013, "percentage": 93.58, "elapsed_time": "1:27:16", "remaining_time": "0:05:59"}
+{"current_steps": 380, "total_steps": 405, "loss": 0.346, "lr": 9.275160081496337e-07, "epoch": 4.6913580246913575, "percentage": 93.83, "elapsed_time": "1:27:30", "remaining_time": "0:05:45"}
+{"current_steps": 381, "total_steps": 405, "loss": 0.3416, "lr": 8.550589881617877e-07, "epoch": 4.703703703703704, "percentage": 94.07, "elapsed_time": "1:27:44", "remaining_time": "0:05:31"}
+{"current_steps": 382, "total_steps": 405, "loss": 0.3398, "lr": 7.85517850041062e-07, "epoch": 4.716049382716049, "percentage": 94.32, "elapsed_time": "1:27:56", "remaining_time": "0:05:17"}
+{"current_steps": 383, "total_steps": 405, "loss": 0.3453, "lr": 7.188977738627901e-07, "epoch": 4.728395061728395, "percentage": 94.57, "elapsed_time": "1:28:10", "remaining_time": "0:05:03"}
+{"current_steps": 384, "total_steps": 405, "loss": 0.3393, "lr": 6.552037221142593e-07, "epoch": 4.7407407407407405, "percentage": 94.81, "elapsed_time": "1:28:23", "remaining_time": "0:04:50"}
+{"current_steps": 385, "total_steps": 405, "loss": 0.3416, "lr": 5.944404393250481e-07, "epoch": 4.753086419753086, "percentage": 95.06, "elapsed_time": "1:28:36", "remaining_time": "0:04:36"}
+{"current_steps": 386, "total_steps": 405, "loss": 0.342, "lr": 5.366124517136184e-07, "epoch": 4.765432098765432, "percentage": 95.31, "elapsed_time": "1:28:50", "remaining_time": "0:04:22"}
+{"current_steps": 387, "total_steps": 405, "loss": 0.3401, "lr": 4.817240668501421e-07, "epoch": 4.777777777777778, "percentage": 95.56, "elapsed_time": "1:29:03", "remaining_time": "0:04:08"}
+{"current_steps": 388, "total_steps": 405, "loss": 0.3427, "lr": 4.297793733356548e-07, "epoch": 4.790123456790123, "percentage": 95.8, "elapsed_time": "1:29:16", "remaining_time": "0:03:54"}
+{"current_steps": 389, "total_steps": 405, "loss": 0.3483, "lr": 3.807822404974726e-07, "epoch": 4.802469135802469, "percentage": 96.05, "elapsed_time": "1:29:30", "remaining_time": "0:03:40"}
+{"current_steps": 390, "total_steps": 405, "loss": 0.3327, "lr": 3.3473631810100103e-07, "epoch": 4.814814814814815, "percentage": 96.3, "elapsed_time": "1:29:43", "remaining_time": "0:03:27"}
+{"current_steps": 391, "total_steps": 405, "loss": 0.3365, "lr": 2.916450360778411e-07, "epoch": 4.827160493827161, "percentage": 96.54, "elapsed_time": "1:29:56", "remaining_time": "0:03:13"}
+{"current_steps": 392, "total_steps": 405, "loss": 0.3475, "lr": 2.5151160427029584e-07, "epoch": 4.839506172839506, "percentage": 96.79, "elapsed_time": "1:30:09", "remaining_time": "0:02:59"}
+{"current_steps": 393, "total_steps": 405, "loss": 0.3467, "lr": 2.1433901219229502e-07, "epoch": 4.851851851851852, "percentage": 97.04, "elapsed_time": "1:30:23", "remaining_time": "0:02:45"}
+{"current_steps": 394, "total_steps": 405, "loss": 0.3445, "lr": 1.8013002880667096e-07, "epoch": 4.864197530864198, "percentage": 97.28, "elapsed_time": "1:30:37", "remaining_time": "0:02:31"}
+{"current_steps": 395, "total_steps": 405, "loss": 0.3489, "lr": 1.4888720231894138e-07, "epoch": 4.8765432098765435, "percentage": 97.53, "elapsed_time": "1:30:51", "remaining_time": "0:02:18"}
+{"current_steps": 396, "total_steps": 405, "loss": 0.3469, "lr": 1.2061285998746562e-07, "epoch": 4.888888888888889, "percentage": 97.78, "elapsed_time": "1:31:03", "remaining_time": "0:02:04"}
+{"current_steps": 397, "total_steps": 405, "loss": 0.3448, "lr": 9.530910795009895e-08, "epoch": 4.901234567901234, "percentage": 98.02, "elapsed_time": "1:31:17", "remaining_time": "0:01:50"}
+{"current_steps": 398, "total_steps": 405, "loss": 0.341, "lr": 7.297783106730016e-08, "epoch": 4.91358024691358, "percentage": 98.27, "elapsed_time": "1:31:30", "remaining_time": "0:01:36"}
+{"current_steps": 399, "total_steps": 405, "loss": 0.347, "lr": 5.362069278175508e-08, "epoch": 4.925925925925926, "percentage": 98.52, "elapsed_time": "1:31:44", "remaining_time": "0:01:22"}
+{"current_steps": 400, "total_steps": 405, "loss": 0.3399, "lr": 3.7239134994426775e-08, "epoch": 4.938271604938271, "percentage": 98.77, "elapsed_time": "1:31:56", "remaining_time": "0:01:08"}
+{"current_steps": 401, "total_steps": 405, "loss": 0.3363, "lr": 2.3834377957183684e-08, "epoch": 4.950617283950617, "percentage": 99.01, "elapsed_time": "1:32:10", "remaining_time": "0:00:55"}
+{"current_steps": 402, "total_steps": 405, "loss": 0.3397, "lr": 1.3407420181885678e-08, "epoch": 4.962962962962963, "percentage": 99.26, "elapsed_time": "1:32:23", "remaining_time": "0:00:41"}
+{"current_steps": 403, "total_steps": 405, "loss": 0.3475, "lr": 5.959038366021297e-09, "epoch": 4.9753086419753085, "percentage": 99.51, "elapsed_time": "1:32:37", "remaining_time": "0:00:27"}
+{"current_steps": 404, "total_steps": 405, "loss": 0.344, "lr": 1.4897873348340697e-09, "epoch": 4.987654320987654, "percentage": 99.75, "elapsed_time": "1:32:50", "remaining_time": "0:00:13"}
+{"current_steps": 405, "total_steps": 405, "loss": 0.3412, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:33:04", "remaining_time": "0:00:00"}
+{"current_steps": 405, "total_steps": 405, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:34:04", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2877 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 405,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012345679012345678,
+      "grad_norm": 5.322886485316676,
+      "learning_rate": 1.951219512195122e-06,
+      "loss": 0.8713,
+      "step": 1
+    },
+    {
+      "epoch": 0.024691358024691357,
+      "grad_norm": 5.297045656067237,
+      "learning_rate": 3.902439024390244e-06,
+      "loss": 0.8617,
+      "step": 2
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 4.964177426655451,
+      "learning_rate": 5.853658536585366e-06,
+      "loss": 0.8557,
+      "step": 3
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 3.773649879416999,
+      "learning_rate": 7.804878048780489e-06,
+      "loss": 0.8258,
+      "step": 4
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 2.0170140516019943,
+      "learning_rate": 9.756097560975611e-06,
+      "loss": 0.7756,
+      "step": 5
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 3.884073569291856,
+      "learning_rate": 1.1707317073170731e-05,
+      "loss": 0.786,
+      "step": 6
+    },
+    {
+      "epoch": 0.08641975308641975,
+      "grad_norm": 4.3463765308085005,
+      "learning_rate": 1.3658536585365855e-05,
+      "loss": 0.7873,
+      "step": 7
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 4.931673812582102,
+      "learning_rate": 1.5609756097560978e-05,
+      "loss": 0.7584,
+      "step": 8
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 3.834447178572324,
+      "learning_rate": 1.75609756097561e-05,
+      "loss": 0.7462,
+      "step": 9
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 2.179837729025759,
+      "learning_rate": 1.9512195121951222e-05,
+      "loss": 0.6981,
+      "step": 10
+    },
+    {
+      "epoch": 0.13580246913580246,
+      "grad_norm": 2.101488664762724,
+      "learning_rate": 2.1463414634146344e-05,
+      "loss": 0.6788,
+      "step": 11
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 1.5969780288722668,
+      "learning_rate": 2.3414634146341463e-05,
+      "loss": 0.6542,
+      "step": 12
+    },
+    {
+      "epoch": 0.16049382716049382,
+      "grad_norm": 1.2878152911707546,
+      "learning_rate": 2.536585365853659e-05,
+      "loss": 0.6401,
+      "step": 13
+    },
+    {
+      "epoch": 0.1728395061728395,
+      "grad_norm": 1.110122058562916,
+      "learning_rate": 2.731707317073171e-05,
+      "loss": 0.6224,
+      "step": 14
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 0.9441382009144876,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 0.6147,
+      "step": 15
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 1.0755606503445887,
+      "learning_rate": 3.1219512195121955e-05,
+      "loss": 0.608,
+      "step": 16
+    },
+    {
+      "epoch": 0.20987654320987653,
+      "grad_norm": 1.0317574737428319,
+      "learning_rate": 3.3170731707317074e-05,
+      "loss": 0.5964,
+      "step": 17
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.1016699420428528,
+      "learning_rate": 3.51219512195122e-05,
+      "loss": 0.5827,
+      "step": 18
+    },
+    {
+      "epoch": 0.2345679012345679,
+      "grad_norm": 1.2684998671325824,
+      "learning_rate": 3.7073170731707325e-05,
+      "loss": 0.5863,
+      "step": 19
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 1.1450067110010247,
+      "learning_rate": 3.9024390243902444e-05,
+      "loss": 0.5828,
+      "step": 20
+    },
+    {
+      "epoch": 0.25925925925925924,
+      "grad_norm": 0.9761661263181526,
+      "learning_rate": 4.097560975609756e-05,
+      "loss": 0.5699,
+      "step": 21
+    },
+    {
+      "epoch": 0.2716049382716049,
+      "grad_norm": 0.8094703924890408,
+      "learning_rate": 4.292682926829269e-05,
+      "loss": 0.5705,
+      "step": 22
+    },
+    {
+      "epoch": 0.2839506172839506,
+      "grad_norm": 1.1556501519240183,
+      "learning_rate": 4.4878048780487814e-05,
+      "loss": 0.5505,
+      "step": 23
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 1.1904158496263302,
+      "learning_rate": 4.6829268292682926e-05,
+      "loss": 0.5564,
+      "step": 24
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 1.3992365789774508,
+      "learning_rate": 4.878048780487805e-05,
+      "loss": 0.5517,
+      "step": 25
+    },
+    {
+      "epoch": 0.32098765432098764,
+      "grad_norm": 0.7997862572956267,
+      "learning_rate": 5.073170731707318e-05,
+      "loss": 0.5488,
+      "step": 26
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.952625422206775,
+      "learning_rate": 5.26829268292683e-05,
+      "loss": 0.5494,
+      "step": 27
+    },
+    {
+      "epoch": 0.345679012345679,
+      "grad_norm": 1.5935135402175304,
+      "learning_rate": 5.463414634146342e-05,
+      "loss": 0.5527,
+      "step": 28
+    },
+    {
+      "epoch": 0.35802469135802467,
+      "grad_norm": 1.2248225513278832,
+      "learning_rate": 5.658536585365854e-05,
+      "loss": 0.5404,
+      "step": 29
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.1987238686766297,
+      "learning_rate": 5.853658536585366e-05,
+      "loss": 0.5467,
+      "step": 30
+    },
+    {
+      "epoch": 0.38271604938271603,
+      "grad_norm": 1.7560415296488376,
+      "learning_rate": 6.0487804878048785e-05,
+      "loss": 0.5427,
+      "step": 31
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 0.9869800217044912,
+      "learning_rate": 6.243902439024391e-05,
+      "loss": 0.5364,
+      "step": 32
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": 1.3759308961313441,
+      "learning_rate": 6.439024390243903e-05,
+      "loss": 0.535,
+      "step": 33
+    },
+    {
+      "epoch": 0.41975308641975306,
+      "grad_norm": 0.848280656571499,
+      "learning_rate": 6.634146341463415e-05,
+      "loss": 0.5255,
+      "step": 34
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 1.5834791375974373,
+      "learning_rate": 6.829268292682927e-05,
+      "loss": 0.5463,
+      "step": 35
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.3946299749030078,
+      "learning_rate": 7.02439024390244e-05,
+      "loss": 0.5329,
+      "step": 36
+    },
+    {
+      "epoch": 0.4567901234567901,
+      "grad_norm": 2.4553544008908896,
+      "learning_rate": 7.219512195121952e-05,
+      "loss": 0.5469,
+      "step": 37
+    },
+    {
+      "epoch": 0.4691358024691358,
+      "grad_norm": 1.4448518801644223,
+      "learning_rate": 7.414634146341465e-05,
+      "loss": 0.5384,
+      "step": 38
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": 2.366228950235355,
+      "learning_rate": 7.609756097560976e-05,
+      "loss": 0.5331,
+      "step": 39
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 1.606851424746494,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 0.5387,
+      "step": 40
+    },
+    {
+      "epoch": 0.5061728395061729,
+      "grad_norm": 1.5736626742577726,
+      "learning_rate": 8e-05,
+      "loss": 0.5215,
+      "step": 41
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 1.9430399946541783,
+      "learning_rate": 7.999851021266518e-05,
+      "loss": 0.5218,
+      "step": 42
+    },
+    {
+      "epoch": 0.5308641975308642,
+      "grad_norm": 1.5970596690336833,
+      "learning_rate": 7.999404096163398e-05,
+      "loss": 0.5249,
+      "step": 43
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 1.3518955116038844,
+      "learning_rate": 7.998659257981813e-05,
+      "loss": 0.5125,
+      "step": 44
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.065342246785812,
+      "learning_rate": 7.997616562204282e-05,
+      "loss": 0.516,
+      "step": 45
+    },
+    {
+      "epoch": 0.5679012345679012,
+      "grad_norm": 0.961399130642479,
+      "learning_rate": 7.996276086500558e-05,
+      "loss": 0.5175,
+      "step": 46
+    },
+    {
+      "epoch": 0.5802469135802469,
+      "grad_norm": 1.6746336809141793,
+      "learning_rate": 7.994637930721825e-05,
+      "loss": 0.517,
+      "step": 47
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 1.5584433959820718,
+      "learning_rate": 7.99270221689327e-05,
+      "loss": 0.5192,
+      "step": 48
+    },
+    {
+      "epoch": 0.6049382716049383,
+      "grad_norm": 1.1658481619505876,
+      "learning_rate": 7.990469089204992e-05,
+      "loss": 0.5026,
+      "step": 49
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 1.1432735287000564,
+      "learning_rate": 7.987938714001254e-05,
+      "loss": 0.5051,
+      "step": 50
+    },
+    {
+      "epoch": 0.6296296296296297,
+      "grad_norm": 1.6729263804344565,
+      "learning_rate": 7.985111279768106e-05,
+      "loss": 0.5208,
+      "step": 51
+    },
+    {
+      "epoch": 0.6419753086419753,
+      "grad_norm": 1.8058261166724783,
+      "learning_rate": 7.981986997119334e-05,
+      "loss": 0.5028,
+      "step": 52
+    },
+    {
+      "epoch": 0.654320987654321,
+      "grad_norm": 0.9551798887699284,
+      "learning_rate": 7.978566098780771e-05,
+      "loss": 0.5023,
+      "step": 53
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.6120888775776003,
+      "learning_rate": 7.974848839572971e-05,
+      "loss": 0.5073,
+      "step": 54
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 1.6504732308976957,
+      "learning_rate": 7.970835496392216e-05,
+      "loss": 0.5197,
+      "step": 55
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 2.4813850162470694,
+      "learning_rate": 7.9665263681899e-05,
+      "loss": 0.5065,
+      "step": 56
+    },
+    {
+      "epoch": 0.7037037037037037,
+      "grad_norm": 2.0085317140110464,
+      "learning_rate": 7.961921775950254e-05,
+      "loss": 0.5186,
+      "step": 57
+    },
+    {
+      "epoch": 0.7160493827160493,
+      "grad_norm": 2.1727130740463254,
+      "learning_rate": 7.957022062666436e-05,
+      "loss": 0.5138,
+      "step": 58
+    },
+    {
+      "epoch": 0.7283950617283951,
+      "grad_norm": 1.7923872395834526,
+      "learning_rate": 7.951827593314987e-05,
+      "loss": 0.5154,
+      "step": 59
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 1.6455141916519003,
+      "learning_rate": 7.946338754828639e-05,
+      "loss": 0.508,
+      "step": 60
+    },
+    {
+      "epoch": 0.7530864197530864,
+      "grad_norm": 1.2020850632554296,
+      "learning_rate": 7.940555956067495e-05,
+      "loss": 0.5029,
+      "step": 61
+    },
+    {
+      "epoch": 0.7654320987654321,
+      "grad_norm": 1.4345699160882657,
+      "learning_rate": 7.934479627788576e-05,
+      "loss": 0.5081,
+      "step": 62
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 1.1706979555619268,
+      "learning_rate": 7.928110222613723e-05,
+      "loss": 0.5013,
+      "step": 63
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 1.0822260503444048,
+      "learning_rate": 7.921448214995895e-05,
+      "loss": 0.5009,
+      "step": 64
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.9538983846582979,
+      "learning_rate": 7.914494101183822e-05,
+      "loss": 0.5048,
+      "step": 65
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 1.2772663076589637,
+      "learning_rate": 7.907248399185037e-05,
+      "loss": 0.5068,
+      "step": 66
+    },
+    {
+      "epoch": 0.8271604938271605,
+      "grad_norm": 0.9753447960969902,
+      "learning_rate": 7.899711648727294e-05,
+      "loss": 0.4967,
+      "step": 67
+    },
+    {
+      "epoch": 0.8395061728395061,
+      "grad_norm": 1.278582421674819,
+      "learning_rate": 7.891884411218364e-05,
+      "loss": 0.4876,
+      "step": 68
+    },
+    {
+      "epoch": 0.8518518518518519,
+      "grad_norm": 1.2296613613599487,
+      "learning_rate": 7.883767269704209e-05,
+      "loss": 0.4902,
+      "step": 69
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 1.1659409845757795,
+      "learning_rate": 7.875360828825562e-05,
+      "loss": 0.4926,
+      "step": 70
+    },
+    {
+      "epoch": 0.8765432098765432,
+      "grad_norm": 0.9109060592449263,
+      "learning_rate": 7.866665714772879e-05,
+      "loss": 0.4992,
+      "step": 71
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.1413101315936145,
+      "learning_rate": 7.8576825752397e-05,
+      "loss": 0.4944,
+      "step": 72
+    },
+    {
+      "epoch": 0.9012345679012346,
+      "grad_norm": 1.5501956716372292,
+      "learning_rate": 7.848412079374403e-05,
+      "loss": 0.5036,
+      "step": 73
+    },
+    {
+      "epoch": 0.9135802469135802,
+      "grad_norm": 0.8833612034769314,
+      "learning_rate": 7.838854917730351e-05,
+      "loss": 0.4956,
+      "step": 74
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 1.6382790184141087,
+      "learning_rate": 7.829011802214464e-05,
+      "loss": 0.5049,
+      "step": 75
+    },
+    {
+      "epoch": 0.9382716049382716,
+      "grad_norm": 0.8824015261456967,
+      "learning_rate": 7.818883466034184e-05,
+      "loss": 0.5073,
+      "step": 76
+    },
+    {
+      "epoch": 0.9506172839506173,
+      "grad_norm": 1.8874422790227483,
+      "learning_rate": 7.808470663642856e-05,
+      "loss": 0.5038,
+      "step": 77
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 1.151698216260373,
+      "learning_rate": 7.797774170683542e-05,
+      "loss": 0.4987,
+      "step": 78
+    },
+    {
+      "epoch": 0.9753086419753086,
+      "grad_norm": 1.8822125796547127,
+      "learning_rate": 7.786794783931225e-05,
+      "loss": 0.4955,
+      "step": 79
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 1.3793553962064276,
+      "learning_rate": 7.775533321233471e-05,
+      "loss": 0.5098,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4900485689809222,
+      "learning_rate": 7.763990621449507e-05,
+      "loss": 0.4941,
+      "step": 81
+    },
+    {
+      "epoch": 1.0123456790123457,
+      "grad_norm": 1.2191759152743815,
+      "learning_rate": 7.752167544387728e-05,
+      "loss": 0.4824,
+      "step": 82
+    },
+    {
+      "epoch": 1.0246913580246915,
+      "grad_norm": 0.9817036892343542,
+      "learning_rate": 7.740064970741661e-05,
+      "loss": 0.4677,
+      "step": 83
+    },
+    {
+      "epoch": 1.037037037037037,
+      "grad_norm": 0.9505715870347944,
+      "learning_rate": 7.727683802024347e-05,
+      "loss": 0.4755,
+      "step": 84
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.9315786466714934,
+      "learning_rate": 7.715024960501209e-05,
+      "loss": 0.4626,
+      "step": 85
+    },
+    {
+      "epoch": 1.0617283950617284,
+      "grad_norm": 1.088912497598927,
+      "learning_rate": 7.702089389121335e-05,
+      "loss": 0.4699,
+      "step": 86
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 0.7664961821150688,
+      "learning_rate": 7.688878051447243e-05,
+      "loss": 0.4632,
+      "step": 87
+    },
+    {
+      "epoch": 1.0864197530864197,
+      "grad_norm": 0.7118117556462173,
+      "learning_rate": 7.675391931583109e-05,
+      "loss": 0.4694,
+      "step": 88
+    },
+    {
+      "epoch": 1.0987654320987654,
+      "grad_norm": 0.8838029650550034,
+      "learning_rate": 7.661632034101466e-05,
+      "loss": 0.4685,
+      "step": 89
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.0456749479001006,
+      "learning_rate": 7.64759938396836e-05,
+      "loss": 0.4652,
+      "step": 90
+    },
+    {
+      "epoch": 1.123456790123457,
+      "grad_norm": 0.9296714999836658,
+      "learning_rate": 7.633295026467016e-05,
+      "loss": 0.4557,
+      "step": 91
+    },
+    {
+      "epoch": 1.1358024691358024,
+      "grad_norm": 0.7784127512214979,
+      "learning_rate": 7.618720027119966e-05,
+      "loss": 0.4576,
+      "step": 92
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "grad_norm": 0.7773052206833756,
+      "learning_rate": 7.603875471609677e-05,
+      "loss": 0.4602,
+      "step": 93
+    },
+    {
+      "epoch": 1.1604938271604939,
+      "grad_norm": 1.1454144308753773,
+      "learning_rate": 7.588762465697693e-05,
+      "loss": 0.4624,
+      "step": 94
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.9378102331091442,
+      "learning_rate": 7.573382135142253e-05,
+      "loss": 0.4641,
+      "step": 95
+    },
+    {
+      "epoch": 1.1851851851851851,
+      "grad_norm": 0.9068527199171179,
+      "learning_rate": 7.55773562561444e-05,
+      "loss": 0.4498,
+      "step": 96
+    },
+    {
+      "epoch": 1.1975308641975309,
+      "grad_norm": 0.9300994723441598,
+      "learning_rate": 7.541824102612839e-05,
+      "loss": 0.46,
+      "step": 97
+    },
+    {
+      "epoch": 1.2098765432098766,
+      "grad_norm": 1.0104590943724414,
+      "learning_rate": 7.525648751376726e-05,
+      "loss": 0.456,
+      "step": 98
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 1.0168144609561725,
+      "learning_rate": 7.509210776797768e-05,
+      "loss": 0.4585,
+      "step": 99
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.8394713299392315,
+      "learning_rate": 7.492511403330284e-05,
+      "loss": 0.4543,
+      "step": 100
+    },
+    {
+      "epoch": 1.2469135802469136,
+      "grad_norm": 0.6254433810264461,
+      "learning_rate": 7.475551874900027e-05,
+      "loss": 0.4535,
+      "step": 101
+    },
+    {
+      "epoch": 1.2592592592592593,
+      "grad_norm": 0.6014772324908465,
+      "learning_rate": 7.458333454811531e-05,
+      "loss": 0.4558,
+      "step": 102
+    },
+    {
+      "epoch": 1.2716049382716048,
+      "grad_norm": 0.6719474936653222,
+      "learning_rate": 7.440857425654004e-05,
+      "loss": 0.4474,
+      "step": 103
+    },
+    {
+      "epoch": 1.2839506172839505,
+      "grad_norm": 0.8289366172315764,
+      "learning_rate": 7.42312508920579e-05,
+      "loss": 0.452,
+      "step": 104
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 1.1119177471943609,
+      "learning_rate": 7.405137766337406e-05,
+      "loss": 0.4615,
+      "step": 105
+    },
+    {
+      "epoch": 1.308641975308642,
+      "grad_norm": 1.1864543763821342,
+      "learning_rate": 7.386896796913137e-05,
+      "loss": 0.4595,
+      "step": 106
+    },
+    {
+      "epoch": 1.3209876543209877,
+      "grad_norm": 0.7739869856668281,
+      "learning_rate": 7.368403539691247e-05,
+      "loss": 0.4526,
+      "step": 107
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.7500250889954546,
+      "learning_rate": 7.349659372222755e-05,
+      "loss": 0.4499,
+      "step": 108
+    },
+    {
+      "epoch": 1.345679012345679,
+      "grad_norm": 1.0110160098128433,
+      "learning_rate": 7.330665690748825e-05,
+      "loss": 0.4598,
+      "step": 109
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 1.240318418546968,
+      "learning_rate": 7.311423910096764e-05,
+      "loss": 0.4531,
+      "step": 110
+    },
+    {
+      "epoch": 1.3703703703703702,
+      "grad_norm": 0.7673358482948583,
+      "learning_rate": 7.291935463574626e-05,
+      "loss": 0.4472,
+      "step": 111
+    },
+    {
+      "epoch": 1.382716049382716,
+      "grad_norm": 0.9290397269601804,
+      "learning_rate": 7.272201802864452e-05,
+      "loss": 0.4524,
+      "step": 112
+    },
+    {
+      "epoch": 1.3950617283950617,
+      "grad_norm": 1.200427789224473,
+      "learning_rate": 7.25222439791413e-05,
+      "loss": 0.4531,
+      "step": 113
+    },
+    {
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.8914574952010766,
+      "learning_rate": 7.232004736827907e-05,
+      "loss": 0.4614,
+      "step": 114
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 1.072583649734927,
+      "learning_rate": 7.21154432575553e-05,
+      "loss": 0.4528,
+      "step": 115
+    },
+    {
+      "epoch": 1.4320987654320987,
+      "grad_norm": 0.7180130997337799,
+      "learning_rate": 7.190844688780065e-05,
+      "loss": 0.4492,
+      "step": 116
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.672503509002727,
+      "learning_rate": 7.169907367804363e-05,
+      "loss": 0.4533,
+      "step": 117
+    },
+    {
+      "epoch": 1.4567901234567902,
+      "grad_norm": 0.69958335114305,
+      "learning_rate": 7.148733922436201e-05,
+      "loss": 0.446,
+      "step": 118
+    },
+    {
+      "epoch": 1.4691358024691357,
+      "grad_norm": 0.7653453417783888,
+      "learning_rate": 7.12732592987212e-05,
+      "loss": 0.4456,
+      "step": 119
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.6310721044962515,
+      "learning_rate": 7.105684984779928e-05,
+      "loss": 0.4444,
+      "step": 120
+    },
+    {
+      "epoch": 1.4938271604938271,
+      "grad_norm": 0.6151795732030567,
+      "learning_rate": 7.083812699179919e-05,
+      "loss": 0.4465,
+      "step": 121
+    },
+    {
+      "epoch": 1.5061728395061729,
+      "grad_norm": 0.6874616448091606,
+      "learning_rate": 7.061710702324799e-05,
+      "loss": 0.4508,
+      "step": 122
+    },
+    {
+      "epoch": 1.5185185185185186,
+      "grad_norm": 0.6395722108011573,
+      "learning_rate": 7.039380640578316e-05,
+      "loss": 0.4462,
+      "step": 123
+    },
+    {
+      "epoch": 1.5308641975308643,
+      "grad_norm": 1.0391636044709032,
+      "learning_rate": 7.016824177292629e-05,
+      "loss": 0.4506,
+      "step": 124
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 1.209612143815189,
+      "learning_rate": 6.994042992684406e-05,
+      "loss": 0.444,
+      "step": 125
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.6126615919119747,
+      "learning_rate": 6.971038783709658e-05,
+      "loss": 0.4503,
+      "step": 126
+    },
+    {
+      "epoch": 1.567901234567901,
+      "grad_norm": 0.7148367458249104,
+      "learning_rate": 6.947813263937347e-05,
+      "loss": 0.4606,
+      "step": 127
+    },
+    {
+      "epoch": 1.5802469135802468,
+      "grad_norm": 1.0428988763055895,
+      "learning_rate": 6.924368163421733e-05,
+      "loss": 0.4467,
+      "step": 128
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 1.1843461844631857,
+      "learning_rate": 6.900705228573507e-05,
+      "loss": 0.452,
+      "step": 129
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 0.7127612179405008,
+      "learning_rate": 6.876826222029699e-05,
+      "loss": 0.4497,
+      "step": 130
+    },
+    {
+      "epoch": 1.617283950617284,
+      "grad_norm": 0.48971010045507035,
+      "learning_rate": 6.852732922522385e-05,
+      "loss": 0.4452,
+      "step": 131
+    },
+    {
+      "epoch": 1.6296296296296298,
+      "grad_norm": 0.6614951195691181,
+      "learning_rate": 6.828427124746191e-05,
+      "loss": 0.4499,
+      "step": 132
+    },
+    {
+      "epoch": 1.6419753086419753,
+      "grad_norm": 0.759726041736274,
+      "learning_rate": 6.803910639224598e-05,
+      "loss": 0.4479,
+      "step": 133
+    },
+    {
+      "epoch": 1.654320987654321,
+      "grad_norm": 0.7326050738916848,
+      "learning_rate": 6.77918529217509e-05,
+      "loss": 0.4485,
+      "step": 134
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.664731323528839,
+      "learning_rate": 6.754252925373109e-05,
+      "loss": 0.4369,
+      "step": 135
+    },
+    {
+      "epoch": 1.6790123456790123,
+      "grad_norm": 0.6194905151290093,
+      "learning_rate": 6.729115396014871e-05,
+      "loss": 0.4392,
+      "step": 136
+    },
+    {
+      "epoch": 1.691358024691358,
+      "grad_norm": 0.7257710866052547,
+      "learning_rate": 6.703774576579018e-05,
+      "loss": 0.4466,
+      "step": 137
+    },
+    {
+      "epoch": 1.7037037037037037,
+      "grad_norm": 0.913815195106407,
+      "learning_rate": 6.678232354687144e-05,
+      "loss": 0.4485,
+      "step": 138
+    },
+    {
+      "epoch": 1.7160493827160495,
+      "grad_norm": 1.1501420885353775,
+      "learning_rate": 6.652490632963182e-05,
+      "loss": 0.4419,
+      "step": 139
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.7814972803848219,
+      "learning_rate": 6.626551328891681e-05,
+      "loss": 0.4421,
+      "step": 140
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 0.6809040763876827,
+      "learning_rate": 6.600416374674978e-05,
+      "loss": 0.4446,
+      "step": 141
+    },
+    {
+      "epoch": 1.7530864197530864,
+      "grad_norm": 0.6937546616216443,
+      "learning_rate": 6.57408771708926e-05,
+      "loss": 0.4439,
+      "step": 142
+    },
+    {
+      "epoch": 1.765432098765432,
+      "grad_norm": 0.6133971132082513,
+      "learning_rate": 6.547567317339557e-05,
+      "loss": 0.4405,
+      "step": 143
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.5795946877354976,
+      "learning_rate": 6.520857150913655e-05,
+      "loss": 0.4468,
+      "step": 144
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.6272260508720054,
+      "learning_rate": 6.493959207434934e-05,
+      "loss": 0.4403,
+      "step": 145
+    },
+    {
+      "epoch": 1.8024691358024691,
+      "grad_norm": 0.6607250320416114,
+      "learning_rate": 6.466875490514173e-05,
+      "loss": 0.4441,
+      "step": 146
+    },
+    {
+      "epoch": 1.8148148148148149,
+      "grad_norm": 0.666515803916981,
+      "learning_rate": 6.439608017600292e-05,
+      "loss": 0.4367,
+      "step": 147
+    },
+    {
+      "epoch": 1.8271604938271606,
+      "grad_norm": 0.6563646888406403,
+      "learning_rate": 6.412158819830082e-05,
+      "loss": 0.4383,
+      "step": 148
+    },
+    {
+      "epoch": 1.8395061728395061,
+      "grad_norm": 0.6751228037264413,
+      "learning_rate": 6.384529941876902e-05,
+      "loss": 0.4443,
+      "step": 149
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.6037023672290093,
+      "learning_rate": 6.356723441798375e-05,
+      "loss": 0.4343,
+      "step": 150
+    },
+    {
+      "epoch": 1.8641975308641974,
+      "grad_norm": 0.7575004210332137,
+      "learning_rate": 6.328741390883084e-05,
+      "loss": 0.436,
+      "step": 151
+    },
+    {
+      "epoch": 1.876543209876543,
+      "grad_norm": 1.053664259204655,
+      "learning_rate": 6.300585873496279e-05,
+      "loss": 0.4446,
+      "step": 152
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 1.143162590447998,
+      "learning_rate": 6.272258986924624e-05,
+      "loss": 0.4376,
+      "step": 153
+    },
+    {
+      "epoch": 1.9012345679012346,
+      "grad_norm": 0.8056844525604071,
+      "learning_rate": 6.243762841219958e-05,
+      "loss": 0.4425,
+      "step": 154
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.7005815828988159,
+      "learning_rate": 6.215099559042132e-05,
+      "loss": 0.4438,
+      "step": 155
+    },
+    {
+      "epoch": 1.925925925925926,
+      "grad_norm": 0.5395123726786041,
+      "learning_rate": 6.186271275500885e-05,
+      "loss": 0.4451,
+      "step": 156
+    },
+    {
+      "epoch": 1.9382716049382716,
+      "grad_norm": 0.447328421246998,
+      "learning_rate": 6.157280137996797e-05,
+      "loss": 0.4496,
+      "step": 157
+    },
+    {
+      "epoch": 1.9506172839506173,
+      "grad_norm": 0.5525549829334637,
+      "learning_rate": 6.128128306061347e-05,
+      "loss": 0.4406,
+      "step": 158
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.6119311049360817,
+      "learning_rate": 6.098817951196032e-05,
+      "loss": 0.4432,
+      "step": 159
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5999595846933212,
+      "learning_rate": 6.0693512567106275e-05,
+      "loss": 0.4396,
+      "step": 160
+    },
+    {
+      "epoch": 1.9876543209876543,
+      "grad_norm": 0.6329428597314521,
+      "learning_rate": 6.0397304175605444e-05,
+      "loss": 0.4397,
+      "step": 161
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6165900475914675,
+      "learning_rate": 6.009957640183333e-05,
+      "loss": 0.4339,
+      "step": 162
+    },
+    {
+      "epoch": 2.0123456790123457,
+      "grad_norm": 0.6175294635421779,
+      "learning_rate": 5.980035142334326e-05,
+      "loss": 0.4037,
+      "step": 163
+    },
+    {
+      "epoch": 2.0246913580246915,
+      "grad_norm": 0.5464603695576591,
+      "learning_rate": 5.94996515292144e-05,
+      "loss": 0.4069,
+      "step": 164
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 0.5961811075021233,
+      "learning_rate": 5.919749911839146e-05,
+      "loss": 0.4072,
+      "step": 165
+    },
+    {
+      "epoch": 2.049382716049383,
+      "grad_norm": 0.7162072119334066,
+      "learning_rate": 5.8893916698016154e-05,
+      "loss": 0.409,
+      "step": 166
+    },
+    {
+      "epoch": 2.0617283950617282,
+      "grad_norm": 0.7531665562571003,
+      "learning_rate": 5.858892688175075e-05,
+      "loss": 0.4054,
+      "step": 167
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.6634967768803004,
+      "learning_rate": 5.828255238809352e-05,
+      "loss": 0.4102,
+      "step": 168
+    },
+    {
+      "epoch": 2.0864197530864197,
+      "grad_norm": 0.5214973502711097,
+      "learning_rate": 5.797481603868646e-05,
+      "loss": 0.4093,
+      "step": 169
+    },
+    {
+      "epoch": 2.0987654320987654,
+      "grad_norm": 0.48817555796705103,
+      "learning_rate": 5.766574075661538e-05,
+      "loss": 0.4056,
+      "step": 170
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.46995270511301984,
+      "learning_rate": 5.735534956470233e-05,
+      "loss": 0.4017,
+      "step": 171
+    },
+    {
+      "epoch": 2.123456790123457,
+      "grad_norm": 0.4001954795848698,
+      "learning_rate": 5.7043665583790627e-05,
+      "loss": 0.4043,
+      "step": 172
+    },
+    {
+      "epoch": 2.1358024691358026,
+      "grad_norm": 0.3352773336486886,
+      "learning_rate": 5.673071203102261e-05,
+      "loss": 0.3978,
+      "step": 173
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.36429657583588576,
+      "learning_rate": 5.641651221811028e-05,
+      "loss": 0.405,
+      "step": 174
+    },
+    {
+      "epoch": 2.1604938271604937,
+      "grad_norm": 0.3696795489355164,
+      "learning_rate": 5.6101089549598704e-05,
+      "loss": 0.4015,
+      "step": 175
+    },
+    {
+      "epoch": 2.1728395061728394,
+      "grad_norm": 0.37732718419035066,
+      "learning_rate": 5.578446752112273e-05,
+      "loss": 0.3993,
+      "step": 176
+    },
+    {
+      "epoch": 2.185185185185185,
+      "grad_norm": 0.3610852145730118,
+      "learning_rate": 5.546666971765675e-05,
+      "loss": 0.401,
+      "step": 177
+    },
+    {
+      "epoch": 2.197530864197531,
+      "grad_norm": 0.375404848711513,
+      "learning_rate": 5.5147719811757914e-05,
+      "loss": 0.4013,
+      "step": 178
+    },
+    {
+      "epoch": 2.2098765432098766,
+      "grad_norm": 0.39144573818004924,
+      "learning_rate": 5.4827641561802716e-05,
+      "loss": 0.4037,
+      "step": 179
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.46921938093624016,
+      "learning_rate": 5.4506458810217286e-05,
+      "loss": 0.4084,
+      "step": 180
+    },
+    {
+      "epoch": 2.234567901234568,
+      "grad_norm": 0.39178530019945007,
+      "learning_rate": 5.4184195481701425e-05,
+      "loss": 0.3974,
+      "step": 181
+    },
+    {
+      "epoch": 2.246913580246914,
+      "grad_norm": 0.31454106942243093,
+      "learning_rate": 5.38608755814464e-05,
+      "loss": 0.3996,
+      "step": 182
+    },
+    {
+      "epoch": 2.259259259259259,
+      "grad_norm": 0.32288914490706055,
+      "learning_rate": 5.353652319334682e-05,
+      "loss": 0.4026,
+      "step": 183
+    },
+    {
+      "epoch": 2.271604938271605,
+      "grad_norm": 0.3480461509407278,
+      "learning_rate": 5.321116247820669e-05,
+      "loss": 0.409,
+      "step": 184
+    },
+    {
+      "epoch": 2.2839506172839505,
+      "grad_norm": 0.32317305352669917,
+      "learning_rate": 5.288481767193963e-05,
+      "loss": 0.3992,
+      "step": 185
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": 0.3491754615190072,
+      "learning_rate": 5.2557513083763605e-05,
+      "loss": 0.4106,
+      "step": 186
+    },
+    {
+      "epoch": 2.308641975308642,
+      "grad_norm": 0.2654352934184053,
+      "learning_rate": 5.2229273094390124e-05,
+      "loss": 0.395,
+      "step": 187
+    },
+    {
+      "epoch": 2.3209876543209877,
+      "grad_norm": 0.240507325939916,
+      "learning_rate": 5.190012215420812e-05,
+      "loss": 0.3962,
+      "step": 188
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.3096781461722714,
+      "learning_rate": 5.1570084781462716e-05,
+      "loss": 0.4009,
+      "step": 189
+    },
+    {
+      "epoch": 2.3456790123456788,
+      "grad_norm": 0.3254620628162861,
+      "learning_rate": 5.123918556042878e-05,
+      "loss": 0.4003,
+      "step": 190
+    },
+    {
+      "epoch": 2.3580246913580245,
+      "grad_norm": 0.30442823004858754,
+      "learning_rate": 5.0907449139579755e-05,
+      "loss": 0.407,
+      "step": 191
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.24609813176288364,
+      "learning_rate": 5.057490022975156e-05,
+      "loss": 0.406,
+      "step": 192
+    },
+    {
+      "epoch": 2.382716049382716,
+      "grad_norm": 0.2645811599665009,
+      "learning_rate": 5.024156360230189e-05,
+      "loss": 0.4087,
+      "step": 193
+    },
+    {
+      "epoch": 2.3950617283950617,
+      "grad_norm": 0.29950051962612906,
+      "learning_rate": 4.9907464087265045e-05,
+      "loss": 0.4051,
+      "step": 194
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.25413630356733447,
+      "learning_rate": 4.9572626571502316e-05,
+      "loss": 0.4115,
+      "step": 195
+    },
+    {
+      "epoch": 2.419753086419753,
+      "grad_norm": 0.1982329593965016,
+      "learning_rate": 4.9237075996848235e-05,
+      "loss": 0.4009,
+      "step": 196
+    },
+    {
+      "epoch": 2.432098765432099,
+      "grad_norm": 0.2793566075797078,
+      "learning_rate": 4.890083735825258e-05,
+      "loss": 0.4018,
+      "step": 197
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.2501185111375193,
+      "learning_rate": 4.8563935701918646e-05,
+      "loss": 0.4005,
+      "step": 198
+    },
+    {
+      "epoch": 2.45679012345679,
+      "grad_norm": 0.2508812489655374,
+      "learning_rate": 4.8226396123437466e-05,
+      "loss": 0.4024,
+      "step": 199
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 0.23763312456408484,
+      "learning_rate": 4.788824376591849e-05,
+      "loss": 0.3938,
+      "step": 200
+    },
+    {
+      "epoch": 2.4814814814814814,
+      "grad_norm": 0.2505474740052618,
+      "learning_rate": 4.754950381811667e-05,
+      "loss": 0.4098,
+      "step": 201
+    },
+    {
+      "epoch": 2.493827160493827,
+      "grad_norm": 0.32543257673329773,
+      "learning_rate": 4.721020151255624e-05,
+      "loss": 0.4008,
+      "step": 202
+    },
+    {
+      "epoch": 2.506172839506173,
+      "grad_norm": 0.31344361733289505,
+      "learning_rate": 4.6870362123651056e-05,
+      "loss": 0.3958,
+      "step": 203
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": 0.2808667743552056,
+      "learning_rate": 4.6530010965821984e-05,
+      "loss": 0.3935,
+      "step": 204
+    },
+    {
+      "epoch": 2.5308641975308643,
+      "grad_norm": 0.2799818958240018,
+      "learning_rate": 4.618917339161125e-05,
+      "loss": 0.3975,
+      "step": 205
+    },
+    {
+      "epoch": 2.5432098765432096,
+      "grad_norm": 0.40415793903369035,
+      "learning_rate": 4.584787478979394e-05,
+      "loss": 0.4012,
+      "step": 206
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 0.36820613398161905,
+      "learning_rate": 4.550614058348674e-05,
+      "loss": 0.3935,
+      "step": 207
+    },
+    {
+      "epoch": 2.567901234567901,
+      "grad_norm": 0.22878484205266533,
+      "learning_rate": 4.516399622825428e-05,
+      "loss": 0.4017,
+      "step": 208
+    },
+    {
+      "epoch": 2.580246913580247,
+      "grad_norm": 0.2526602623885084,
+      "learning_rate": 4.4821467210212924e-05,
+      "loss": 0.3986,
+      "step": 209
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.2857441977382452,
+      "learning_rate": 4.4478579044132314e-05,
+      "loss": 0.3983,
+      "step": 210
+    },
+    {
+      "epoch": 2.6049382716049383,
+      "grad_norm": 0.31335609029960937,
+      "learning_rate": 4.41353572715348e-05,
+      "loss": 0.4084,
+      "step": 211
+    },
+    {
+      "epoch": 2.617283950617284,
+      "grad_norm": 0.29329552295291217,
+      "learning_rate": 4.379182745879289e-05,
+      "loss": 0.4,
+      "step": 212
+    },
+    {
+      "epoch": 2.6296296296296298,
+      "grad_norm": 0.2464006577647208,
+      "learning_rate": 4.344801519522478e-05,
+      "loss": 0.3981,
+      "step": 213
+    },
+    {
+      "epoch": 2.6419753086419755,
+      "grad_norm": 0.21757828305891083,
+      "learning_rate": 4.310394609118826e-05,
+      "loss": 0.4109,
+      "step": 214
+    },
+    {
+      "epoch": 2.6543209876543212,
+      "grad_norm": 0.3210249559146646,
+      "learning_rate": 4.2759645776172996e-05,
+      "loss": 0.4069,
+      "step": 215
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.3477320907889876,
+      "learning_rate": 4.241513989689145e-05,
+      "loss": 0.4008,
+      "step": 216
+    },
+    {
+      "epoch": 2.6790123456790123,
+      "grad_norm": 0.24803139007843356,
+      "learning_rate": 4.2070454115368385e-05,
+      "loss": 0.3977,
+      "step": 217
+    },
+    {
+      "epoch": 2.691358024691358,
+      "grad_norm": 0.20440440035218216,
+      "learning_rate": 4.1725614107029387e-05,
+      "loss": 0.4001,
+      "step": 218
+    },
+    {
+      "epoch": 2.7037037037037037,
+      "grad_norm": 0.27538798360958056,
+      "learning_rate": 4.138064555878833e-05,
+      "loss": 0.3981,
+      "step": 219
+    },
+    {
+      "epoch": 2.7160493827160495,
+      "grad_norm": 0.2858784452038823,
+      "learning_rate": 4.1035574167133905e-05,
+      "loss": 0.4023,
+      "step": 220
+    },
+    {
+      "epoch": 2.728395061728395,
+      "grad_norm": 0.2008423560120923,
+      "learning_rate": 4.069042563621555e-05,
+      "loss": 0.4079,
+      "step": 221
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": 0.24293176835950328,
+      "learning_rate": 4.034522567592876e-05,
+      "loss": 0.407,
+      "step": 222
+    },
+    {
+      "epoch": 2.753086419753086,
+      "grad_norm": 0.3091409408215162,
+      "learning_rate": 4e-05,
+      "loss": 0.3969,
+      "step": 223
+    },
+    {
+      "epoch": 2.765432098765432,
+      "grad_norm": 0.31288462010722656,
+      "learning_rate": 3.965477432407125e-05,
+      "loss": 0.4031,
+      "step": 224
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.2567222355035599,
+      "learning_rate": 3.9309574363784465e-05,
+      "loss": 0.3973,
+      "step": 225
+    },
+    {
+      "epoch": 2.7901234567901234,
+      "grad_norm": 0.19069072798190304,
+      "learning_rate": 3.8964425832866115e-05,
+      "loss": 0.3994,
+      "step": 226
+    },
+    {
+      "epoch": 2.802469135802469,
+      "grad_norm": 0.3116244915598422,
+      "learning_rate": 3.861935444121169e-05,
+      "loss": 0.4046,
+      "step": 227
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.28128541699160603,
+      "learning_rate": 3.827438589297062e-05,
+      "loss": 0.3999,
+      "step": 228
+    },
+    {
+      "epoch": 2.8271604938271606,
+      "grad_norm": 0.167533219149008,
+      "learning_rate": 3.792954588463162e-05,
+      "loss": 0.3929,
+      "step": 229
+    },
+    {
+      "epoch": 2.8395061728395063,
+      "grad_norm": 0.2904700089197945,
+      "learning_rate": 3.758486010310856e-05,
+      "loss": 0.4033,
+      "step": 230
+    },
+    {
+      "epoch": 2.851851851851852,
+      "grad_norm": 0.222742797773903,
+      "learning_rate": 3.7240354223827004e-05,
+      "loss": 0.3952,
+      "step": 231
+    },
+    {
+      "epoch": 2.8641975308641974,
+      "grad_norm": 0.22495887212575763,
+      "learning_rate": 3.6896053908811755e-05,
+      "loss": 0.4007,
+      "step": 232
+    },
+    {
+      "epoch": 2.876543209876543,
+      "grad_norm": 0.20272044370534606,
+      "learning_rate": 3.655198480477523e-05,
+      "loss": 0.3965,
+      "step": 233
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.20159603268883686,
+      "learning_rate": 3.6208172541207114e-05,
+      "loss": 0.4026,
+      "step": 234
+    },
+    {
+      "epoch": 2.9012345679012346,
+      "grad_norm": 0.1857016078801328,
+      "learning_rate": 3.5864642728465205e-05,
+      "loss": 0.4019,
+      "step": 235
+    },
+    {
+      "epoch": 2.9135802469135803,
+      "grad_norm": 0.19657456599113443,
+      "learning_rate": 3.552142095586769e-05,
+      "loss": 0.3935,
+      "step": 236
+    },
+    {
+      "epoch": 2.925925925925926,
+      "grad_norm": 0.20263796973832712,
+      "learning_rate": 3.517853278978708e-05,
+      "loss": 0.4024,
+      "step": 237
+    },
+    {
+      "epoch": 2.9382716049382713,
+      "grad_norm": 0.21927632477325718,
+      "learning_rate": 3.4836003771745736e-05,
+      "loss": 0.4058,
+      "step": 238
+    },
+    {
+      "epoch": 2.950617283950617,
+      "grad_norm": 0.18668045348448897,
+      "learning_rate": 3.449385941651328e-05,
+      "loss": 0.4016,
+      "step": 239
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.22387285374410273,
+      "learning_rate": 3.415212521020609e-05,
+      "loss": 0.3998,
+      "step": 240
+    },
+    {
+      "epoch": 2.9753086419753085,
+      "grad_norm": 0.1986946786033834,
+      "learning_rate": 3.381082660838875e-05,
+      "loss": 0.3994,
+      "step": 241
+    },
+    {
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.17106247031701255,
+      "learning_rate": 3.346998903417803e-05,
+      "loss": 0.3948,
+      "step": 242
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19730260856315138,
+      "learning_rate": 3.312963787634896e-05,
+      "loss": 0.3809,
+      "step": 243
+    },
+    {
+      "epoch": 3.0123456790123457,
+      "grad_norm": 0.22215703145843618,
+      "learning_rate": 3.2789798487443775e-05,
+      "loss": 0.3664,
+      "step": 244
+    },
+    {
+      "epoch": 3.0246913580246915,
+      "grad_norm": 0.18982786875890348,
+      "learning_rate": 3.245049618188334e-05,
+      "loss": 0.3702,
+      "step": 245
+    },
+    {
+      "epoch": 3.037037037037037,
+      "grad_norm": 0.2659144149445534,
+      "learning_rate": 3.2111756234081525e-05,
+      "loss": 0.369,
+      "step": 246
+    },
+    {
+      "epoch": 3.049382716049383,
+      "grad_norm": 0.21145023138083482,
+      "learning_rate": 3.177360387656254e-05,
+      "loss": 0.37,
+      "step": 247
+    },
+    {
+      "epoch": 3.0617283950617282,
+      "grad_norm": 0.24865516246035863,
+      "learning_rate": 3.143606429808136e-05,
+      "loss": 0.3701,
+      "step": 248
+    },
+    {
+      "epoch": 3.074074074074074,
+      "grad_norm": 0.2308219847168512,
+      "learning_rate": 3.109916264174743e-05,
+      "loss": 0.3707,
+      "step": 249
+    },
+    {
+      "epoch": 3.0864197530864197,
+      "grad_norm": 0.2246388176582276,
+      "learning_rate": 3.076292400315179e-05,
+      "loss": 0.3735,
+      "step": 250
+    },
+    {
+      "epoch": 3.0987654320987654,
+      "grad_norm": 0.22125008039208874,
+      "learning_rate": 3.0427373428497704e-05,
+      "loss": 0.3682,
+      "step": 251
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 0.20085617720181384,
+      "learning_rate": 3.0092535912734965e-05,
+      "loss": 0.3668,
+      "step": 252
+    },
+    {
+      "epoch": 3.123456790123457,
+      "grad_norm": 0.2177257993468155,
+      "learning_rate": 2.9758436397698118e-05,
+      "loss": 0.3653,
+      "step": 253
+    },
+    {
+      "epoch": 3.1358024691358026,
+      "grad_norm": 0.2087241919659811,
+      "learning_rate": 2.9425099770248446e-05,
+      "loss": 0.3711,
+      "step": 254
+    },
+    {
+      "epoch": 3.148148148148148,
+      "grad_norm": 0.1946566571469163,
+      "learning_rate": 2.9092550860420252e-05,
+      "loss": 0.3624,
+      "step": 255
+    },
+    {
+      "epoch": 3.1604938271604937,
+      "grad_norm": 0.22054171431244854,
+      "learning_rate": 2.8760814439571233e-05,
+      "loss": 0.3685,
+      "step": 256
+    },
+    {
+      "epoch": 3.1728395061728394,
+      "grad_norm": 0.17240280564444063,
+      "learning_rate": 2.8429915218537297e-05,
+      "loss": 0.3674,
+      "step": 257
+    },
+    {
+      "epoch": 3.185185185185185,
+      "grad_norm": 0.1848593449888633,
+      "learning_rate": 2.809987784579189e-05,
+      "loss": 0.3608,
+      "step": 258
+    },
+    {
+      "epoch": 3.197530864197531,
+      "grad_norm": 0.18266249121254657,
+      "learning_rate": 2.7770726905609896e-05,
+      "loss": 0.3642,
+      "step": 259
+    },
+    {
+      "epoch": 3.2098765432098766,
+      "grad_norm": 0.16073855445767077,
+      "learning_rate": 2.74424869162364e-05,
+      "loss": 0.3563,
+      "step": 260
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "grad_norm": 0.17531367979315252,
+      "learning_rate": 2.7115182328060385e-05,
+      "loss": 0.3676,
+      "step": 261
+    },
+    {
+      "epoch": 3.234567901234568,
+      "grad_norm": 0.14796201932709915,
+      "learning_rate": 2.678883752179333e-05,
+      "loss": 0.3625,
+      "step": 262
+    },
+    {
+      "epoch": 3.246913580246914,
+      "grad_norm": 0.19310186654814873,
+      "learning_rate": 2.6463476806653185e-05,
+      "loss": 0.3585,
+      "step": 263
+    },
+    {
+      "epoch": 3.259259259259259,
+      "grad_norm": 0.17358347178863473,
+      "learning_rate": 2.61391244185536e-05,
+      "loss": 0.3605,
+      "step": 264
+    },
+    {
+      "epoch": 3.271604938271605,
+      "grad_norm": 0.17684421859741475,
+      "learning_rate": 2.5815804518298575e-05,
+      "loss": 0.3677,
+      "step": 265
+    },
+    {
+      "epoch": 3.2839506172839505,
+      "grad_norm": 0.203480321127498,
+      "learning_rate": 2.549354118978272e-05,
+      "loss": 0.3678,
+      "step": 266
+    },
+    {
+      "epoch": 3.2962962962962963,
+      "grad_norm": 0.17547188883389694,
+      "learning_rate": 2.51723584381973e-05,
+      "loss": 0.3608,
+      "step": 267
+    },
+    {
+      "epoch": 3.308641975308642,
+      "grad_norm": 0.18602067695611346,
+      "learning_rate": 2.4852280188242096e-05,
+      "loss": 0.3678,
+      "step": 268
+    },
+    {
+      "epoch": 3.3209876543209877,
+      "grad_norm": 0.17140539371210345,
+      "learning_rate": 2.453333028234325e-05,
+      "loss": 0.3638,
+      "step": 269
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.15224985187441373,
+      "learning_rate": 2.4215532478877283e-05,
+      "loss": 0.3597,
+      "step": 270
+    },
+    {
+      "epoch": 3.3456790123456788,
+      "grad_norm": 0.16134052410438623,
+      "learning_rate": 2.3898910450401306e-05,
+      "loss": 0.3667,
+      "step": 271
+    },
+    {
+      "epoch": 3.3580246913580245,
+      "grad_norm": 0.14386569537644786,
+      "learning_rate": 2.3583487781889737e-05,
+      "loss": 0.3709,
+      "step": 272
+    },
+    {
+      "epoch": 3.3703703703703702,
+      "grad_norm": 0.15151232350322325,
+      "learning_rate": 2.3269287968977406e-05,
+      "loss": 0.3637,
+      "step": 273
+    },
+    {
+      "epoch": 3.382716049382716,
+      "grad_norm": 0.15707589935891128,
+      "learning_rate": 2.2956334416209404e-05,
+      "loss": 0.3735,
+      "step": 274
+    },
+    {
+      "epoch": 3.3950617283950617,
+      "grad_norm": 0.1477749720910393,
+      "learning_rate": 2.264465043529768e-05,
+      "loss": 0.3622,
+      "step": 275
+    },
+    {
+      "epoch": 3.4074074074074074,
+      "grad_norm": 0.14885929712006027,
+      "learning_rate": 2.233425924338463e-05,
+      "loss": 0.3644,
+      "step": 276
+    },
+    {
+      "epoch": 3.419753086419753,
+      "grad_norm": 0.14340772251052653,
+      "learning_rate": 2.2025183961313542e-05,
+      "loss": 0.3687,
+      "step": 277
+    },
+    {
+      "epoch": 3.432098765432099,
+      "grad_norm": 0.13763533911676756,
+      "learning_rate": 2.1717447611906496e-05,
+      "loss": 0.3663,
+      "step": 278
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 0.14639101329943424,
+      "learning_rate": 2.141107311824926e-05,
+      "loss": 0.3689,
+      "step": 279
+    },
+    {
+      "epoch": 3.45679012345679,
+      "grad_norm": 0.1276571096925691,
+      "learning_rate": 2.1106083301983852e-05,
+      "loss": 0.3618,
+      "step": 280
+    },
+    {
+      "epoch": 3.4691358024691357,
+      "grad_norm": 0.14363458047447658,
+      "learning_rate": 2.0802500881608557e-05,
+      "loss": 0.3727,
+      "step": 281
+    },
+    {
+      "epoch": 3.4814814814814814,
+      "grad_norm": 0.12886295792105223,
+      "learning_rate": 2.0500348470785614e-05,
+      "loss": 0.3692,
+      "step": 282
+    },
+    {
+      "epoch": 3.493827160493827,
+      "grad_norm": 0.1490463167300804,
+      "learning_rate": 2.0199648576656744e-05,
+      "loss": 0.3636,
+      "step": 283
+    },
+    {
+      "epoch": 3.506172839506173,
+      "grad_norm": 0.12848412841426096,
+      "learning_rate": 1.9900423598166685e-05,
+      "loss": 0.3651,
+      "step": 284
+    },
+    {
+      "epoch": 3.5185185185185186,
+      "grad_norm": 0.15574442730245652,
+      "learning_rate": 1.9602695824394576e-05,
+      "loss": 0.3651,
+      "step": 285
+    },
+    {
+      "epoch": 3.5308641975308643,
+      "grad_norm": 0.13229685022791354,
+      "learning_rate": 1.9306487432893725e-05,
+      "loss": 0.3662,
+      "step": 286
+    },
+    {
+      "epoch": 3.5432098765432096,
+      "grad_norm": 0.12772394530331901,
+      "learning_rate": 1.901182048803968e-05,
+      "loss": 0.3651,
+      "step": 287
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 0.1465151284584716,
+      "learning_rate": 1.8718716939386543e-05,
+      "loss": 0.3698,
+      "step": 288
+    },
+    {
+      "epoch": 3.567901234567901,
+      "grad_norm": 0.14047354187123118,
+      "learning_rate": 1.8427198620032037e-05,
+      "loss": 0.3661,
+      "step": 289
+    },
+    {
+      "epoch": 3.580246913580247,
+      "grad_norm": 0.1410397043933752,
+      "learning_rate": 1.8137287244991162e-05,
+      "loss": 0.3708,
+      "step": 290
+    },
+    {
+      "epoch": 3.5925925925925926,
+      "grad_norm": 0.14850797574149896,
+      "learning_rate": 1.7849004409578678e-05,
+      "loss": 0.37,
+      "step": 291
+    },
+    {
+      "epoch": 3.6049382716049383,
+      "grad_norm": 0.14770512288892354,
+      "learning_rate": 1.7562371587800422e-05,
+      "loss": 0.3621,
+      "step": 292
+    },
+    {
+      "epoch": 3.617283950617284,
+      "grad_norm": 0.1301969671247391,
+      "learning_rate": 1.7277410130753775e-05,
+      "loss": 0.3705,
+      "step": 293
+    },
+    {
+      "epoch": 3.6296296296296298,
+      "grad_norm": 0.13324724802934845,
+      "learning_rate": 1.6994141265037222e-05,
+      "loss": 0.3583,
+      "step": 294
+    },
+    {
+      "epoch": 3.6419753086419755,
+      "grad_norm": 0.12335331492186778,
+      "learning_rate": 1.6712586091169183e-05,
+      "loss": 0.3706,
+      "step": 295
+    },
+    {
+      "epoch": 3.6543209876543212,
+      "grad_norm": 0.12483228986767417,
+      "learning_rate": 1.6432765582016257e-05,
+      "loss": 0.3627,
+      "step": 296
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.1224822064632684,
+      "learning_rate": 1.615470058123099e-05,
+      "loss": 0.3683,
+      "step": 297
+    },
+    {
+      "epoch": 3.6790123456790123,
+      "grad_norm": 0.12870125642053606,
+      "learning_rate": 1.5878411801699182e-05,
+      "loss": 0.3677,
+      "step": 298
+    },
+    {
+      "epoch": 3.691358024691358,
+      "grad_norm": 0.11464105740669171,
+      "learning_rate": 1.5603919823997083e-05,
+      "loss": 0.3725,
+      "step": 299
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.1259473229571899,
+      "learning_rate": 1.5331245094858277e-05,
+      "loss": 0.3632,
+      "step": 300
+    },
+    {
+      "epoch": 3.7160493827160495,
+      "grad_norm": 0.11989849457004843,
+      "learning_rate": 1.5060407925650662e-05,
+      "loss": 0.363,
+      "step": 301
+    },
+    {
+      "epoch": 3.728395061728395,
+      "grad_norm": 0.11838170070815705,
+      "learning_rate": 1.4791428490863462e-05,
+      "loss": 0.3636,
+      "step": 302
+    },
+    {
+      "epoch": 3.7407407407407405,
+      "grad_norm": 0.11542631237011597,
+      "learning_rate": 1.4524326826604442e-05,
+      "loss": 0.3662,
+      "step": 303
+    },
+    {
+      "epoch": 3.753086419753086,
+      "grad_norm": 0.10853513336233153,
+      "learning_rate": 1.425912282910741e-05,
+      "loss": 0.3612,
+      "step": 304
+    },
+    {
+      "epoch": 3.765432098765432,
+      "grad_norm": 0.12927711782224877,
+      "learning_rate": 1.3995836253250233e-05,
+      "loss": 0.3632,
+      "step": 305
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 0.11124438692244316,
+      "learning_rate": 1.3734486711083199e-05,
+      "loss": 0.3656,
+      "step": 306
+    },
+    {
+      "epoch": 3.7901234567901234,
+      "grad_norm": 0.11829671034615585,
+      "learning_rate": 1.3475093670368202e-05,
+      "loss": 0.3625,
+      "step": 307
+    },
+    {
+      "epoch": 3.802469135802469,
+      "grad_norm": 0.1171711805914509,
+      "learning_rate": 1.3217676453128583e-05,
+      "loss": 0.3681,
+      "step": 308
+    },
+    {
+      "epoch": 3.814814814814815,
+      "grad_norm": 0.12136369786981609,
+      "learning_rate": 1.2962254234209826e-05,
+      "loss": 0.3702,
+      "step": 309
+    },
+    {
+      "epoch": 3.8271604938271606,
+      "grad_norm": 0.11625055457136292,
+      "learning_rate": 1.2708846039851306e-05,
+      "loss": 0.3596,
+      "step": 310
+    },
+    {
+      "epoch": 3.8395061728395063,
+      "grad_norm": 0.1249883414445167,
+      "learning_rate": 1.2457470746268912e-05,
+      "loss": 0.3597,
+      "step": 311
+    },
+    {
+      "epoch": 3.851851851851852,
+      "grad_norm": 0.11998786571991671,
+      "learning_rate": 1.2208147078249106e-05,
+      "loss": 0.3705,
+      "step": 312
+    },
+    {
+      "epoch": 3.8641975308641974,
+      "grad_norm": 0.12324835771363575,
+      "learning_rate": 1.1960893607754022e-05,
+      "loss": 0.378,
+      "step": 313
+    },
+    {
+      "epoch": 3.876543209876543,
+      "grad_norm": 0.13292216219148154,
+      "learning_rate": 1.1715728752538103e-05,
+      "loss": 0.3709,
+      "step": 314
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.12363035327325136,
+      "learning_rate": 1.1472670774776159e-05,
+      "loss": 0.3734,
+      "step": 315
+    },
+    {
+      "epoch": 3.9012345679012346,
+      "grad_norm": 0.12095948017126495,
+      "learning_rate": 1.123173777970303e-05,
+      "loss": 0.3644,
+      "step": 316
+    },
+    {
+      "epoch": 3.9135802469135803,
+      "grad_norm": 0.12223767053256172,
+      "learning_rate": 1.0992947714264952e-05,
+      "loss": 0.3639,
+      "step": 317
+    },
+    {
+      "epoch": 3.925925925925926,
+      "grad_norm": 0.11556671111818939,
+      "learning_rate": 1.0756318365782672e-05,
+      "loss": 0.3705,
+      "step": 318
+    },
+    {
+      "epoch": 3.9382716049382713,
+      "grad_norm": 0.11863503874267803,
+      "learning_rate": 1.0521867360626534e-05,
+      "loss": 0.3649,
+      "step": 319
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.1220737146765024,
+      "learning_rate": 1.028961216290342e-05,
+      "loss": 0.3702,
+      "step": 320
+    },
+    {
+      "epoch": 3.962962962962963,
+      "grad_norm": 0.10688177437745146,
+      "learning_rate": 1.0059570073155953e-05,
+      "loss": 0.3686,
+      "step": 321
+    },
+    {
+      "epoch": 3.9753086419753085,
+      "grad_norm": 0.1115239690090056,
+      "learning_rate": 9.831758227073714e-06,
+      "loss": 0.3622,
+      "step": 322
+    },
+    {
+      "epoch": 3.9876543209876543,
+      "grad_norm": 0.1013118549435552,
+      "learning_rate": 9.606193594216852e-06,
+      "loss": 0.3662,
+      "step": 323
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.13078127831261904,
+      "learning_rate": 9.382892976752024e-06,
+      "loss": 0.3514,
+      "step": 324
+    },
+    {
+      "epoch": 4.012345679012346,
+      "grad_norm": 0.14120097496571368,
+      "learning_rate": 9.161873008200816e-06,
+      "loss": 0.3447,
+      "step": 325
+    },
+    {
+      "epoch": 4.0246913580246915,
+      "grad_norm": 0.131610168014187,
+      "learning_rate": 8.943150152200734e-06,
+      "loss": 0.3564,
+      "step": 326
+    },
+    {
+      "epoch": 4.037037037037037,
+      "grad_norm": 0.1197175249959368,
+      "learning_rate": 8.72674070127881e-06,
+      "loss": 0.3399,
+      "step": 327
+    },
+    {
+      "epoch": 4.049382716049383,
+      "grad_norm": 0.1381715130606439,
+      "learning_rate": 8.512660775637998e-06,
+      "loss": 0.3434,
+      "step": 328
+    },
+    {
+      "epoch": 4.061728395061729,
+      "grad_norm": 0.13276158035183344,
+      "learning_rate": 8.300926321956391e-06,
+      "loss": 0.3416,
+      "step": 329
+    },
+    {
+      "epoch": 4.074074074074074,
+      "grad_norm": 0.13242822539056381,
+      "learning_rate": 8.091553112199362e-06,
+      "loss": 0.3518,
+      "step": 330
+    },
+    {
+      "epoch": 4.08641975308642,
+      "grad_norm": 0.12212877221315457,
+      "learning_rate": 7.884556742444704e-06,
+      "loss": 0.3446,
+      "step": 331
+    },
+    {
+      "epoch": 4.098765432098766,
+      "grad_norm": 0.11698141950653529,
+      "learning_rate": 7.679952631720944e-06,
+      "loss": 0.3466,
+      "step": 332
+    },
+    {
+      "epoch": 4.111111111111111,
+      "grad_norm": 0.1304559116220868,
+      "learning_rate": 7.477756020858695e-06,
+      "loss": 0.355,
+      "step": 333
+    },
+    {
+      "epoch": 4.1234567901234565,
+      "grad_norm": 0.13089784593559015,
+      "learning_rate": 7.277981971355487e-06,
+      "loss": 0.3432,
+      "step": 334
+    },
+    {
+      "epoch": 4.135802469135802,
+      "grad_norm": 0.12263988117511435,
+      "learning_rate": 7.080645364253747e-06,
+      "loss": 0.3451,
+      "step": 335
+    },
+    {
+      "epoch": 4.148148148148148,
+      "grad_norm": 0.11728846389962917,
+      "learning_rate": 6.885760899032368e-06,
+      "loss": 0.345,
+      "step": 336
+    },
+    {
+      "epoch": 4.160493827160494,
+      "grad_norm": 0.11392519861587432,
+      "learning_rate": 6.69334309251175e-06,
+      "loss": 0.3472,
+      "step": 337
+    },
+    {
+      "epoch": 4.172839506172839,
+      "grad_norm": 0.12602381332743814,
+      "learning_rate": 6.503406277772457e-06,
+      "loss": 0.345,
+      "step": 338
+    },
+    {
+      "epoch": 4.185185185185185,
+      "grad_norm": 0.10134725138589995,
+      "learning_rate": 6.31596460308753e-06,
+      "loss": 0.3431,
+      "step": 339
+    },
+    {
+      "epoch": 4.197530864197531,
+      "grad_norm": 0.11429337446344612,
+      "learning_rate": 6.1310320308686354e-06,
+      "loss": 0.3492,
+      "step": 340
+    },
+    {
+      "epoch": 4.209876543209877,
+      "grad_norm": 0.12482104702813673,
+      "learning_rate": 5.9486223366259555e-06,
+      "loss": 0.3406,
+      "step": 341
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 0.11483630989866628,
+      "learning_rate": 5.768749107942105e-06,
+      "loss": 0.3458,
+      "step": 342
+    },
+    {
+      "epoch": 4.234567901234568,
+      "grad_norm": 0.10641915634927608,
+      "learning_rate": 5.5914257434599705e-06,
+      "loss": 0.3427,
+      "step": 343
+    },
+    {
+      "epoch": 4.246913580246914,
+      "grad_norm": 0.11187178257279115,
+      "learning_rate": 5.416665451884706e-06,
+      "loss": 0.3478,
+      "step": 344
+    },
+    {
+      "epoch": 4.2592592592592595,
+      "grad_norm": 0.10328829320916721,
+      "learning_rate": 5.24448125099974e-06,
+      "loss": 0.3604,
+      "step": 345
+    },
+    {
+      "epoch": 4.271604938271605,
+      "grad_norm": 0.10325046605157456,
+      "learning_rate": 5.074885966697167e-06,
+      "loss": 0.3439,
+      "step": 346
+    },
+    {
+      "epoch": 4.283950617283951,
+      "grad_norm": 0.09783875518175919,
+      "learning_rate": 4.9078922320223225e-06,
+      "loss": 0.338,
+      "step": 347
+    },
+    {
+      "epoch": 4.296296296296296,
+      "grad_norm": 0.09584121801157325,
+      "learning_rate": 4.7435124862327445e-06,
+      "loss": 0.3456,
+      "step": 348
+    },
+    {
+      "epoch": 4.308641975308642,
+      "grad_norm": 0.10257946096157032,
+      "learning_rate": 4.581758973871609e-06,
+      "loss": 0.3435,
+      "step": 349
+    },
+    {
+      "epoch": 4.320987654320987,
+      "grad_norm": 0.09622559695473883,
+      "learning_rate": 4.422643743855611e-06,
+      "loss": 0.3387,
+      "step": 350
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.08985291405803897,
+      "learning_rate": 4.266178648577484e-06,
+      "loss": 0.3465,
+      "step": 351
+    },
+    {
+      "epoch": 4.345679012345679,
+      "grad_norm": 0.09083798833221284,
+      "learning_rate": 4.112375343023076e-06,
+      "loss": 0.3402,
+      "step": 352
+    },
+    {
+      "epoch": 4.3580246913580245,
+      "grad_norm": 0.0928368108514207,
+      "learning_rate": 3.961245283903239e-06,
+      "loss": 0.3417,
+      "step": 353
+    },
+    {
+      "epoch": 4.37037037037037,
+      "grad_norm": 0.09858890680167014,
+      "learning_rate": 3.812799728800354e-06,
+      "loss": 0.3494,
+      "step": 354
+    },
+    {
+      "epoch": 4.382716049382716,
+      "grad_norm": 0.09253195368124226,
+      "learning_rate": 3.6670497353298396e-06,
+      "loss": 0.3486,
+      "step": 355
+    },
+    {
+      "epoch": 4.395061728395062,
+      "grad_norm": 0.09138349778139458,
+      "learning_rate": 3.5240061603163977e-06,
+      "loss": 0.3439,
+      "step": 356
+    },
+    {
+      "epoch": 4.407407407407407,
+      "grad_norm": 0.09207502583455726,
+      "learning_rate": 3.3836796589853484e-06,
+      "loss": 0.3399,
+      "step": 357
+    },
+    {
+      "epoch": 4.419753086419753,
+      "grad_norm": 0.09098178054496783,
+      "learning_rate": 3.246080684168913e-06,
+      "loss": 0.3374,
+      "step": 358
+    },
+    {
+      "epoch": 4.432098765432099,
+      "grad_norm": 0.09461477122622283,
+      "learning_rate": 3.11121948552759e-06,
+      "loss": 0.347,
+      "step": 359
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.08873177760685183,
+      "learning_rate": 2.9791061087866625e-06,
+      "loss": 0.3517,
+      "step": 360
+    },
+    {
+      "epoch": 4.45679012345679,
+      "grad_norm": 0.08923078431705038,
+      "learning_rate": 2.849750394987907e-06,
+      "loss": 0.3507,
+      "step": 361
+    },
+    {
+      "epoch": 4.469135802469136,
+      "grad_norm": 0.09262596320456881,
+      "learning_rate": 2.7231619797565278e-06,
+      "loss": 0.3462,
+      "step": 362
+    },
+    {
+      "epoch": 4.481481481481482,
+      "grad_norm": 0.09034563106603927,
+      "learning_rate": 2.5993502925834115e-06,
+      "loss": 0.3475,
+      "step": 363
+    },
+    {
+      "epoch": 4.493827160493828,
+      "grad_norm": 0.08464664656906902,
+      "learning_rate": 2.4783245561227264e-06,
+      "loss": 0.3436,
+      "step": 364
+    },
+    {
+      "epoch": 4.506172839506172,
+      "grad_norm": 0.08516291301856833,
+      "learning_rate": 2.3600937855049467e-06,
+      "loss": 0.3489,
+      "step": 365
+    },
+    {
+      "epoch": 4.518518518518518,
+      "grad_norm": 0.08613713073759806,
+      "learning_rate": 2.244666787665297e-06,
+      "loss": 0.3479,
+      "step": 366
+    },
+    {
+      "epoch": 4.530864197530864,
+      "grad_norm": 0.08766949672032548,
+      "learning_rate": 2.1320521606877653e-06,
+      "loss": 0.3491,
+      "step": 367
+    },
+    {
+      "epoch": 4.54320987654321,
+      "grad_norm": 0.08233473579098213,
+      "learning_rate": 2.022258293164585e-06,
+      "loss": 0.3444,
+      "step": 368
+    },
+    {
+      "epoch": 4.555555555555555,
+      "grad_norm": 0.08546306867171963,
+      "learning_rate": 1.9152933635714354e-06,
+      "loss": 0.3402,
+      "step": 369
+    },
+    {
+      "epoch": 4.567901234567901,
+      "grad_norm": 0.0838918934654388,
+      "learning_rate": 1.8111653396581762e-06,
+      "loss": 0.3497,
+      "step": 370
+    },
+    {
+      "epoch": 4.580246913580247,
+      "grad_norm": 0.08391928692735219,
+      "learning_rate": 1.709881977855372e-06,
+      "loss": 0.3451,
+      "step": 371
+    },
+    {
+      "epoch": 4.592592592592593,
+      "grad_norm": 0.0871181996609232,
+      "learning_rate": 1.6114508226965009e-06,
+      "loss": 0.3446,
+      "step": 372
+    },
+    {
+      "epoch": 4.604938271604938,
+      "grad_norm": 0.08989815759315828,
+      "learning_rate": 1.5158792062559813e-06,
+      "loss": 0.3472,
+      "step": 373
+    },
+    {
+      "epoch": 4.617283950617284,
+      "grad_norm": 0.08525583975432947,
+      "learning_rate": 1.4231742476029965e-06,
+      "loss": 0.3464,
+      "step": 374
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 0.08702616238335954,
+      "learning_rate": 1.33334285227122e-06,
+      "loss": 0.3464,
+      "step": 375
+    },
+    {
+      "epoch": 4.6419753086419755,
+      "grad_norm": 0.0798577947590892,
+      "learning_rate": 1.2463917117443968e-06,
+      "loss": 0.3485,
+      "step": 376
+    },
+    {
+      "epoch": 4.654320987654321,
+      "grad_norm": 0.08199514353400199,
+      "learning_rate": 1.1623273029579195e-06,
+      "loss": 0.3466,
+      "step": 377
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.08036935320442855,
+      "learning_rate": 1.0811558878163698e-06,
+      "loss": 0.3449,
+      "step": 378
+    },
+    {
+      "epoch": 4.679012345679013,
+      "grad_norm": 0.09004723861019338,
+      "learning_rate": 1.0028835127270553e-06,
+      "loss": 0.3429,
+      "step": 379
+    },
+    {
+      "epoch": 4.6913580246913575,
+      "grad_norm": 0.08561873370258896,
+      "learning_rate": 9.275160081496337e-07,
+      "loss": 0.346,
+      "step": 380
+    },
+    {
+      "epoch": 4.703703703703704,
+      "grad_norm": 0.08084419918008226,
+      "learning_rate": 8.550589881617877e-07,
+      "loss": 0.3416,
+      "step": 381
+    },
+    {
+      "epoch": 4.716049382716049,
+      "grad_norm": 0.08104505949528973,
+      "learning_rate": 7.85517850041062e-07,
+      "loss": 0.3398,
+      "step": 382
+    },
+    {
+      "epoch": 4.728395061728395,
+      "grad_norm": 0.08076162479144416,
+      "learning_rate": 7.188977738627901e-07,
+      "loss": 0.3453,
+      "step": 383
+    },
+    {
+      "epoch": 4.7407407407407405,
+      "grad_norm": 0.07770391544716708,
+      "learning_rate": 6.552037221142593e-07,
+      "loss": 0.3393,
+      "step": 384
+    },
+    {
+      "epoch": 4.753086419753086,
+      "grad_norm": 0.08331286393559116,
+      "learning_rate": 5.944404393250481e-07,
+      "loss": 0.3416,
+      "step": 385
+    },
+    {
+      "epoch": 4.765432098765432,
+      "grad_norm": 0.0804668471427177,
+      "learning_rate": 5.366124517136184e-07,
+      "loss": 0.342,
+      "step": 386
+    },
+    {
+      "epoch": 4.777777777777778,
+      "grad_norm": 0.08538622755026046,
+      "learning_rate": 4.817240668501421e-07,
+      "loss": 0.3401,
+      "step": 387
+    },
+    {
+      "epoch": 4.790123456790123,
+      "grad_norm": 0.08146413045412997,
+      "learning_rate": 4.297793733356548e-07,
+      "loss": 0.3427,
+      "step": 388
+    },
+    {
+      "epoch": 4.802469135802469,
+      "grad_norm": 0.08133595326521681,
+      "learning_rate": 3.807822404974726e-07,
+      "loss": 0.3483,
+      "step": 389
+    },
+    {
+      "epoch": 4.814814814814815,
+      "grad_norm": 0.07919579475608875,
+      "learning_rate": 3.3473631810100103e-07,
+      "loss": 0.3327,
+      "step": 390
+    },
+    {
+      "epoch": 4.827160493827161,
+      "grad_norm": 0.08123223258851157,
+      "learning_rate": 2.916450360778411e-07,
+      "loss": 0.3365,
+      "step": 391
+    },
+    {
+      "epoch": 4.839506172839506,
+      "grad_norm": 0.08257891936662312,
+      "learning_rate": 2.5151160427029584e-07,
+      "loss": 0.3475,
+      "step": 392
+    },
+    {
+      "epoch": 4.851851851851852,
+      "grad_norm": 0.07932897839921949,
+      "learning_rate": 2.1433901219229502e-07,
+      "loss": 0.3467,
+      "step": 393
+    },
+    {
+      "epoch": 4.864197530864198,
+      "grad_norm": 0.08087497808227699,
+      "learning_rate": 1.8013002880667096e-07,
+      "loss": 0.3445,
+      "step": 394
+    },
+    {
+      "epoch": 4.8765432098765435,
+      "grad_norm": 0.09555289840502959,
+      "learning_rate": 1.4888720231894138e-07,
+      "loss": 0.3489,
+      "step": 395
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 0.07961294947105259,
+      "learning_rate": 1.2061285998746562e-07,
+      "loss": 0.3469,
+      "step": 396
+    },
+    {
+      "epoch": 4.901234567901234,
+      "grad_norm": 0.08343057365407185,
+      "learning_rate": 9.530910795009895e-08,
+      "loss": 0.3448,
+      "step": 397
+    },
+    {
+      "epoch": 4.91358024691358,
+      "grad_norm": 0.07711854846564468,
+      "learning_rate": 7.297783106730016e-08,
+      "loss": 0.341,
+      "step": 398
+    },
+    {
+      "epoch": 4.925925925925926,
+      "grad_norm": 0.07943450346405932,
+      "learning_rate": 5.362069278175508e-08,
+      "loss": 0.347,
+      "step": 399
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 0.07870891626937102,
+      "learning_rate": 3.7239134994426775e-08,
+      "loss": 0.3399,
+      "step": 400
+    },
+    {
+      "epoch": 4.950617283950617,
+      "grad_norm": 0.08172348680504911,
+      "learning_rate": 2.3834377957183684e-08,
+      "loss": 0.3363,
+      "step": 401
+    },
+    {
+      "epoch": 4.962962962962963,
+      "grad_norm": 0.08219122509641905,
+      "learning_rate": 1.3407420181885678e-08,
+      "loss": 0.3397,
+      "step": 402
+    },
+    {
+      "epoch": 4.9753086419753085,
+      "grad_norm": 0.079358090049586,
+      "learning_rate": 5.959038366021297e-09,
+      "loss": 0.3475,
+      "step": 403
+    },
+    {
+      "epoch": 4.987654320987654,
+      "grad_norm": 0.07720406166190734,
+      "learning_rate": 1.4897873348340697e-09,
+      "loss": 0.344,
+      "step": 404
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.08228065193505166,
+      "learning_rate": 0.0,
+      "loss": 0.3412,
+      "step": 405
+    },
+    {
+      "epoch": 5.0,
+      "step": 405,
+      "total_flos": 6794337614561280.0,
+      "train_loss": 0.42579232314486565,
+      "train_runtime": 5653.6163,
+      "train_samples_per_second": 36.455,
+      "train_steps_per_second": 0.072
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 405,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 6794337614561280.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ee3d71a14ae4bff18e51119e69ab5a6025813482ed4a87fce9d1beb51aa9ff
+size 7416