Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,61 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: other
+# base_model: /mnt/petrelfs/qianchen1/uptodate/LLaMA-Factory/ft_models/ll/Qwen2.5-7B_pt
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-7B_pt_cls_aki_v2
+  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. -->
+
+# Qwen2.5-7B_pt_cls_aki_v2
+
+This model is a fine-tuned version of [/mnt/petrelfs/qianchen1/uptodate/LLaMA-Factory/ft_models/ll/Qwen2.5-7B_pt](https://huggingface.co//mnt/petrelfs/qianchen1/uptodate/LLaMA-Factory/ft_models/ll/Qwen2.5-7B_pt) on the cls_aki_v2 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: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.0

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": 3.0,
+    "total_flos": 130173844045824.0,
+    "train_loss": 0.32796121670620854,
+    "train_runtime": 10598.1253,
+    "train_samples_per_second": 1.995,
+    "train_steps_per_second": 0.249
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/mnt/petrelfs/qianchen1/uptodate/LLaMA-Factory/ft_models/ll/Qwen2.5-7B_pt",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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": "4.45.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.45.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a37a4bd0b29b5b5cf025f8f582c501f5171e2bdfcfc29cbad4cf61f3104b173
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0afd63a694e6b62847ee8c2e0202073f6560bec4ee838da77b7be3591b46edd
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103a6325008240472776881c0df9d670231c305e6232fe1482b16e2eb0a82f2c
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b136316d582dd08a40c189fca24a111e8f5ecc29a7ba9f0e9af83806693015e2
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are 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 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": 30000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 130173844045824.0,
+    "train_loss": 0.32796121670620854,
+    "train_runtime": 10598.1253,
+    "train_samples_per_second": 1.995,
+    "train_steps_per_second": 0.249
+}

trainer_log.jsonl

@@ -0,0 +1,265 @@
+{"current_steps": 10, "total_steps": 2643, "loss": 11.4349, "lr": 1.886792452830189e-07, "epoch": 0.011350737797956867, "percentage": 0.38, "elapsed_time": "0:00:44", "remaining_time": "3:15:19"}
+{"current_steps": 20, "total_steps": 2643, "loss": 10.7287, "lr": 3.773584905660378e-07, "epoch": 0.022701475595913734, "percentage": 0.76, "elapsed_time": "0:01:23", "remaining_time": "3:02:45"}
+{"current_steps": 30, "total_steps": 2643, "loss": 7.9114, "lr": 5.660377358490567e-07, "epoch": 0.0340522133938706, "percentage": 1.14, "elapsed_time": "0:02:03", "remaining_time": "2:59:17"}
+{"current_steps": 40, "total_steps": 2643, "loss": 5.3773, "lr": 7.547169811320755e-07, "epoch": 0.04540295119182747, "percentage": 1.51, "elapsed_time": "0:02:40", "remaining_time": "2:54:24"}
+{"current_steps": 50, "total_steps": 2643, "loss": 4.1808, "lr": 9.433962264150944e-07, "epoch": 0.056753688989784334, "percentage": 1.89, "elapsed_time": "0:03:19", "remaining_time": "2:52:45"}
+{"current_steps": 60, "total_steps": 2643, "loss": 3.391, "lr": 1.1320754716981133e-06, "epoch": 0.0681044267877412, "percentage": 2.27, "elapsed_time": "0:03:59", "remaining_time": "2:52:08"}
+{"current_steps": 70, "total_steps": 2643, "loss": 2.9224, "lr": 1.3207547169811322e-06, "epoch": 0.07945516458569807, "percentage": 2.65, "elapsed_time": "0:04:37", "remaining_time": "2:49:56"}
+{"current_steps": 80, "total_steps": 2643, "loss": 2.7385, "lr": 1.509433962264151e-06, "epoch": 0.09080590238365494, "percentage": 3.03, "elapsed_time": "0:05:15", "remaining_time": "2:48:32"}
+{"current_steps": 90, "total_steps": 2643, "loss": 2.5178, "lr": 1.6981132075471698e-06, "epoch": 0.1021566401816118, "percentage": 3.41, "elapsed_time": "0:05:55", "remaining_time": "2:48:01"}
+{"current_steps": 100, "total_steps": 2643, "loss": 2.2834, "lr": 1.8867924528301889e-06, "epoch": 0.11350737797956867, "percentage": 3.78, "elapsed_time": "0:06:34", "remaining_time": "2:47:20"}
+{"current_steps": 110, "total_steps": 2643, "loss": 2.0212, "lr": 2.075471698113208e-06, "epoch": 0.12485811577752554, "percentage": 4.16, "elapsed_time": "0:07:16", "remaining_time": "2:47:22"}
+{"current_steps": 120, "total_steps": 2643, "loss": 1.7334, "lr": 2.2641509433962266e-06, "epoch": 0.1362088535754824, "percentage": 4.54, "elapsed_time": "0:07:55", "remaining_time": "2:46:42"}
+{"current_steps": 130, "total_steps": 2643, "loss": 1.4777, "lr": 2.4528301886792453e-06, "epoch": 0.14755959137343927, "percentage": 4.92, "elapsed_time": "0:08:36", "remaining_time": "2:46:22"}
+{"current_steps": 140, "total_steps": 2643, "loss": 1.1486, "lr": 2.6415094339622644e-06, "epoch": 0.15891032917139614, "percentage": 5.3, "elapsed_time": "0:09:15", "remaining_time": "2:45:29"}
+{"current_steps": 150, "total_steps": 2643, "loss": 0.8411, "lr": 2.830188679245283e-06, "epoch": 0.170261066969353, "percentage": 5.68, "elapsed_time": "0:09:54", "remaining_time": "2:44:48"}
+{"current_steps": 160, "total_steps": 2643, "loss": 0.5991, "lr": 3.018867924528302e-06, "epoch": 0.18161180476730987, "percentage": 6.05, "elapsed_time": "0:10:34", "remaining_time": "2:44:12"}
+{"current_steps": 170, "total_steps": 2643, "loss": 0.3447, "lr": 3.207547169811321e-06, "epoch": 0.19296254256526674, "percentage": 6.43, "elapsed_time": "0:11:18", "remaining_time": "2:44:33"}
+{"current_steps": 180, "total_steps": 2643, "loss": 0.2428, "lr": 3.3962264150943395e-06, "epoch": 0.2043132803632236, "percentage": 6.81, "elapsed_time": "0:12:00", "remaining_time": "2:44:22"}
+{"current_steps": 190, "total_steps": 2643, "loss": 0.2239, "lr": 3.5849056603773586e-06, "epoch": 0.21566401816118047, "percentage": 7.19, "elapsed_time": "0:12:41", "remaining_time": "2:43:52"}
+{"current_steps": 200, "total_steps": 2643, "loss": 0.1635, "lr": 3.7735849056603777e-06, "epoch": 0.22701475595913734, "percentage": 7.57, "elapsed_time": "0:13:17", "remaining_time": "2:42:17"}
+{"current_steps": 210, "total_steps": 2643, "loss": 0.1634, "lr": 3.962264150943396e-06, "epoch": 0.2383654937570942, "percentage": 7.95, "elapsed_time": "0:13:55", "remaining_time": "2:41:16"}
+{"current_steps": 220, "total_steps": 2643, "loss": 0.2969, "lr": 4.150943396226416e-06, "epoch": 0.24971623155505107, "percentage": 8.32, "elapsed_time": "0:14:32", "remaining_time": "2:40:12"}
+{"current_steps": 230, "total_steps": 2643, "loss": 0.1923, "lr": 4.339622641509435e-06, "epoch": 0.26106696935300794, "percentage": 8.7, "elapsed_time": "0:15:12", "remaining_time": "2:39:38"}
+{"current_steps": 240, "total_steps": 2643, "loss": 0.173, "lr": 4.528301886792453e-06, "epoch": 0.2724177071509648, "percentage": 9.08, "elapsed_time": "0:15:52", "remaining_time": "2:38:52"}
+{"current_steps": 250, "total_steps": 2643, "loss": 0.1752, "lr": 4.716981132075472e-06, "epoch": 0.28376844494892167, "percentage": 9.46, "elapsed_time": "0:16:33", "remaining_time": "2:38:25"}
+{"current_steps": 260, "total_steps": 2643, "loss": 0.1466, "lr": 4.905660377358491e-06, "epoch": 0.29511918274687854, "percentage": 9.84, "elapsed_time": "0:17:14", "remaining_time": "2:38:06"}
+{"current_steps": 270, "total_steps": 2643, "loss": 0.2425, "lr": 4.999945458825315e-06, "epoch": 0.3064699205448354, "percentage": 10.22, "elapsed_time": "0:17:51", "remaining_time": "2:36:53"}
+{"current_steps": 280, "total_steps": 2643, "loss": 0.159, "lr": 4.999509143706472e-06, "epoch": 0.3178206583427923, "percentage": 10.59, "elapsed_time": "0:18:32", "remaining_time": "2:36:27"}
+{"current_steps": 290, "total_steps": 2643, "loss": 0.1815, "lr": 4.998636589618803e-06, "epoch": 0.32917139614074914, "percentage": 10.97, "elapsed_time": "0:19:12", "remaining_time": "2:35:50"}
+{"current_steps": 300, "total_steps": 2643, "loss": 0.1312, "lr": 4.997327948849044e-06, "epoch": 0.340522133938706, "percentage": 11.35, "elapsed_time": "0:19:50", "remaining_time": "2:34:54"}
+{"current_steps": 310, "total_steps": 2643, "loss": 0.1921, "lr": 4.995583449794081e-06, "epoch": 0.3518728717366629, "percentage": 11.73, "elapsed_time": "0:20:30", "remaining_time": "2:34:17"}
+{"current_steps": 320, "total_steps": 2643, "loss": 0.1768, "lr": 4.993403396921082e-06, "epoch": 0.36322360953461974, "percentage": 12.11, "elapsed_time": "0:21:10", "remaining_time": "2:33:42"}
+{"current_steps": 330, "total_steps": 2643, "loss": 0.1714, "lr": 4.990788170714355e-06, "epoch": 0.3745743473325766, "percentage": 12.49, "elapsed_time": "0:21:50", "remaining_time": "2:33:02"}
+{"current_steps": 340, "total_steps": 2643, "loss": 0.1445, "lr": 4.987738227608954e-06, "epoch": 0.3859250851305335, "percentage": 12.86, "elapsed_time": "0:22:31", "remaining_time": "2:32:31"}
+{"current_steps": 350, "total_steps": 2643, "loss": 0.1337, "lr": 4.984254099911009e-06, "epoch": 0.39727582292849034, "percentage": 13.24, "elapsed_time": "0:23:07", "remaining_time": "2:31:30"}
+{"current_steps": 360, "total_steps": 2643, "loss": 0.1908, "lr": 4.98033639570482e-06, "epoch": 0.4086265607264472, "percentage": 13.62, "elapsed_time": "0:23:47", "remaining_time": "2:30:50"}
+{"current_steps": 370, "total_steps": 2643, "loss": 0.1582, "lr": 4.975985798746736e-06, "epoch": 0.4199772985244041, "percentage": 14.0, "elapsed_time": "0:24:28", "remaining_time": "2:30:24"}
+{"current_steps": 380, "total_steps": 2643, "loss": 0.1693, "lr": 4.971203068345811e-06, "epoch": 0.43132803632236094, "percentage": 14.38, "elapsed_time": "0:25:11", "remaining_time": "2:30:03"}
+{"current_steps": 390, "total_steps": 2643, "loss": 0.1872, "lr": 4.9659890392312935e-06, "epoch": 0.4426787741203178, "percentage": 14.76, "elapsed_time": "0:25:55", "remaining_time": "2:29:45"}
+{"current_steps": 400, "total_steps": 2643, "loss": 0.1687, "lr": 4.960344621406927e-06, "epoch": 0.4540295119182747, "percentage": 15.13, "elapsed_time": "0:26:33", "remaining_time": "2:28:53"}
+{"current_steps": 410, "total_steps": 2643, "loss": 0.1842, "lr": 4.954270799992138e-06, "epoch": 0.46538024971623154, "percentage": 15.51, "elapsed_time": "0:27:07", "remaining_time": "2:27:41"}
+{"current_steps": 420, "total_steps": 2643, "loss": 0.13, "lr": 4.947768635050098e-06, "epoch": 0.4767309875141884, "percentage": 15.89, "elapsed_time": "0:27:47", "remaining_time": "2:27:06"}
+{"current_steps": 430, "total_steps": 2643, "loss": 0.2288, "lr": 4.940839261402711e-06, "epoch": 0.4880817253121453, "percentage": 16.27, "elapsed_time": "0:28:29", "remaining_time": "2:26:38"}
+{"current_steps": 440, "total_steps": 2643, "loss": 0.0884, "lr": 4.933483888432558e-06, "epoch": 0.49943246311010214, "percentage": 16.65, "elapsed_time": "0:29:14", "remaining_time": "2:26:22"}
+{"current_steps": 450, "total_steps": 2643, "loss": 0.1534, "lr": 4.925703799871818e-06, "epoch": 0.5107832009080591, "percentage": 17.03, "elapsed_time": "0:29:53", "remaining_time": "2:25:40"}
+{"current_steps": 460, "total_steps": 2643, "loss": 0.1884, "lr": 4.91750035357822e-06, "epoch": 0.5221339387060159, "percentage": 17.4, "elapsed_time": "0:30:34", "remaining_time": "2:25:07"}
+{"current_steps": 470, "total_steps": 2643, "loss": 0.1373, "lr": 4.908874981298058e-06, "epoch": 0.5334846765039728, "percentage": 17.78, "elapsed_time": "0:31:18", "remaining_time": "2:24:42"}
+{"current_steps": 480, "total_steps": 2643, "loss": 0.2131, "lr": 4.899829188416306e-06, "epoch": 0.5448354143019296, "percentage": 18.16, "elapsed_time": "0:31:56", "remaining_time": "2:23:58"}
+{"current_steps": 490, "total_steps": 2643, "loss": 0.1385, "lr": 4.890364553693886e-06, "epoch": 0.5561861520998865, "percentage": 18.54, "elapsed_time": "0:32:39", "remaining_time": "2:23:28"}
+{"current_steps": 500, "total_steps": 2643, "loss": 0.1326, "lr": 4.880482728992126e-06, "epoch": 0.5675368898978433, "percentage": 18.92, "elapsed_time": "0:33:18", "remaining_time": "2:22:46"}
+{"current_steps": 510, "total_steps": 2643, "loss": 0.1697, "lr": 4.870185438984458e-06, "epoch": 0.5788876276958003, "percentage": 19.3, "elapsed_time": "0:33:55", "remaining_time": "2:21:53"}
+{"current_steps": 520, "total_steps": 2643, "loss": 0.1196, "lr": 4.859474480855417e-06, "epoch": 0.5902383654937571, "percentage": 19.67, "elapsed_time": "0:34:33", "remaining_time": "2:21:06"}
+{"current_steps": 530, "total_steps": 2643, "loss": 0.1278, "lr": 4.848351723986974e-06, "epoch": 0.601589103291714, "percentage": 20.05, "elapsed_time": "0:35:12", "remaining_time": "2:20:21"}
+{"current_steps": 540, "total_steps": 2643, "loss": 0.1383, "lr": 4.8368191096322734e-06, "epoch": 0.6129398410896708, "percentage": 20.43, "elapsed_time": "0:35:55", "remaining_time": "2:19:54"}
+{"current_steps": 550, "total_steps": 2643, "loss": 0.1235, "lr": 4.824878650576829e-06, "epoch": 0.6242905788876277, "percentage": 20.81, "elapsed_time": "0:36:33", "remaining_time": "2:19:06"}
+{"current_steps": 560, "total_steps": 2643, "loss": 0.1495, "lr": 4.81253243078723e-06, "epoch": 0.6356413166855845, "percentage": 21.19, "elapsed_time": "0:37:10", "remaining_time": "2:18:15"}
+{"current_steps": 570, "total_steps": 2643, "loss": 0.1127, "lr": 4.7997826050474284e-06, "epoch": 0.6469920544835415, "percentage": 21.57, "elapsed_time": "0:37:52", "remaining_time": "2:17:44"}
+{"current_steps": 580, "total_steps": 2643, "loss": 0.1749, "lr": 4.786631398582663e-06, "epoch": 0.6583427922814983, "percentage": 21.94, "elapsed_time": "0:38:31", "remaining_time": "2:17:00"}
+{"current_steps": 590, "total_steps": 2643, "loss": 0.1344, "lr": 4.773081106671094e-06, "epoch": 0.6696935300794552, "percentage": 22.32, "elapsed_time": "0:39:07", "remaining_time": "2:16:08"}
+{"current_steps": 600, "total_steps": 2643, "loss": 0.1188, "lr": 4.759134094243206e-06, "epoch": 0.681044267877412, "percentage": 22.7, "elapsed_time": "0:39:50", "remaining_time": "2:15:38"}
+{"current_steps": 610, "total_steps": 2643, "loss": 0.1461, "lr": 4.744792795469058e-06, "epoch": 0.6923950056753689, "percentage": 23.08, "elapsed_time": "0:40:29", "remaining_time": "2:14:57"}
+{"current_steps": 620, "total_steps": 2643, "loss": 0.1846, "lr": 4.730059713333448e-06, "epoch": 0.7037457434733257, "percentage": 23.46, "elapsed_time": "0:41:10", "remaining_time": "2:14:21"}
+{"current_steps": 630, "total_steps": 2643, "loss": 0.1325, "lr": 4.714937419199067e-06, "epoch": 0.7150964812712827, "percentage": 23.84, "elapsed_time": "0:41:46", "remaining_time": "2:13:30"}
+{"current_steps": 640, "total_steps": 2643, "loss": 0.1352, "lr": 4.69942855235772e-06, "epoch": 0.7264472190692395, "percentage": 24.21, "elapsed_time": "0:42:30", "remaining_time": "2:13:02"}
+{"current_steps": 650, "total_steps": 2643, "loss": 0.1362, "lr": 4.683535819569691e-06, "epoch": 0.7377979568671964, "percentage": 24.59, "elapsed_time": "0:43:09", "remaining_time": "2:12:20"}
+{"current_steps": 660, "total_steps": 2643, "loss": 0.1706, "lr": 4.667261994591331e-06, "epoch": 0.7491486946651532, "percentage": 24.97, "elapsed_time": "0:43:51", "remaining_time": "2:11:45"}
+{"current_steps": 670, "total_steps": 2643, "loss": 0.1208, "lr": 4.650609917690957e-06, "epoch": 0.7604994324631101, "percentage": 25.35, "elapsed_time": "0:44:26", "remaining_time": "2:10:51"}
+{"current_steps": 680, "total_steps": 2643, "loss": 0.1516, "lr": 4.633582495153137e-06, "epoch": 0.771850170261067, "percentage": 25.73, "elapsed_time": "0:45:05", "remaining_time": "2:10:09"}
+{"current_steps": 690, "total_steps": 2643, "loss": 0.1419, "lr": 4.616182698771463e-06, "epoch": 0.7832009080590239, "percentage": 26.11, "elapsed_time": "0:45:47", "remaining_time": "2:09:35"}
+{"current_steps": 700, "total_steps": 2643, "loss": 0.1327, "lr": 4.598413565329876e-06, "epoch": 0.7945516458569807, "percentage": 26.49, "elapsed_time": "0:46:33", "remaining_time": "2:09:15"}
+{"current_steps": 710, "total_steps": 2643, "loss": 0.1438, "lr": 4.58027819607266e-06, "epoch": 0.8059023836549376, "percentage": 26.86, "elapsed_time": "0:47:15", "remaining_time": "2:08:39"}
+{"current_steps": 720, "total_steps": 2643, "loss": 0.1214, "lr": 4.5617797561631885e-06, "epoch": 0.8172531214528944, "percentage": 27.24, "elapsed_time": "0:47:58", "remaining_time": "2:08:06"}
+{"current_steps": 730, "total_steps": 2643, "loss": 0.1516, "lr": 4.542921474131497e-06, "epoch": 0.8286038592508513, "percentage": 27.62, "elapsed_time": "0:48:33", "remaining_time": "2:07:15"}
+{"current_steps": 740, "total_steps": 2643, "loss": 0.1339, "lr": 4.523706641310817e-06, "epoch": 0.8399545970488081, "percentage": 28.0, "elapsed_time": "0:49:11", "remaining_time": "2:06:29"}
+{"current_steps": 750, "total_steps": 2643, "loss": 0.1061, "lr": 4.5041386112631394e-06, "epoch": 0.8513053348467651, "percentage": 28.38, "elapsed_time": "0:49:54", "remaining_time": "2:05:58"}
+{"current_steps": 760, "total_steps": 2643, "loss": 0.1011, "lr": 4.484220799193913e-06, "epoch": 0.8626560726447219, "percentage": 28.76, "elapsed_time": "0:50:32", "remaining_time": "2:05:12"}
+{"current_steps": 770, "total_steps": 2643, "loss": 0.1298, "lr": 4.463956681355993e-06, "epoch": 0.8740068104426788, "percentage": 29.13, "elapsed_time": "0:51:06", "remaining_time": "2:04:18"}
+{"current_steps": 780, "total_steps": 2643, "loss": 0.1203, "lr": 4.4433497944429325e-06, "epoch": 0.8853575482406356, "percentage": 29.51, "elapsed_time": "0:51:41", "remaining_time": "2:03:28"}
+{"current_steps": 790, "total_steps": 2643, "loss": 0.1289, "lr": 4.422403734971718e-06, "epoch": 0.8967082860385925, "percentage": 29.89, "elapsed_time": "0:52:24", "remaining_time": "2:02:56"}
+{"current_steps": 800, "total_steps": 2643, "loss": 0.1039, "lr": 4.401122158655076e-06, "epoch": 0.9080590238365494, "percentage": 30.27, "elapsed_time": "0:53:03", "remaining_time": "2:02:14"}
+{"current_steps": 810, "total_steps": 2643, "loss": 0.142, "lr": 4.379508779763438e-06, "epoch": 0.9194097616345063, "percentage": 30.65, "elapsed_time": "0:53:44", "remaining_time": "2:01:36"}
+{"current_steps": 820, "total_steps": 2643, "loss": 0.1483, "lr": 4.357567370476693e-06, "epoch": 0.9307604994324631, "percentage": 31.03, "elapsed_time": "0:54:26", "remaining_time": "2:01:02"}
+{"current_steps": 830, "total_steps": 2643, "loss": 0.1388, "lr": 4.335301760225824e-06, "epoch": 0.94211123723042, "percentage": 31.4, "elapsed_time": "0:55:04", "remaining_time": "2:00:17"}
+{"current_steps": 840, "total_steps": 2643, "loss": 0.1132, "lr": 4.312715835024565e-06, "epoch": 0.9534619750283768, "percentage": 31.78, "elapsed_time": "0:55:43", "remaining_time": "1:59:36"}
+{"current_steps": 850, "total_steps": 2643, "loss": 0.0886, "lr": 4.289813536791168e-06, "epoch": 0.9648127128263337, "percentage": 32.16, "elapsed_time": "0:56:19", "remaining_time": "1:58:48"}
+{"current_steps": 860, "total_steps": 2643, "loss": 0.1119, "lr": 4.2665988626604285e-06, "epoch": 0.9761634506242906, "percentage": 32.54, "elapsed_time": "0:57:04", "remaining_time": "1:58:19"}
+{"current_steps": 870, "total_steps": 2643, "loss": 0.1049, "lr": 4.243075864286059e-06, "epoch": 0.9875141884222475, "percentage": 32.92, "elapsed_time": "0:57:47", "remaining_time": "1:57:46"}
+{"current_steps": 880, "total_steps": 2643, "loss": 0.1067, "lr": 4.219248647133559e-06, "epoch": 0.9988649262202043, "percentage": 33.3, "elapsed_time": "0:58:23", "remaining_time": "1:56:59"}
+{"current_steps": 890, "total_steps": 2643, "loss": 0.1328, "lr": 4.195121369763687e-06, "epoch": 1.0102156640181612, "percentage": 33.67, "elapsed_time": "0:59:07", "remaining_time": "1:56:26"}
+{"current_steps": 900, "total_steps": 2643, "loss": 0.0789, "lr": 4.170698243106668e-06, "epoch": 1.0215664018161181, "percentage": 34.05, "elapsed_time": "0:59:47", "remaining_time": "1:55:47"}
+{"current_steps": 910, "total_steps": 2643, "loss": 0.1287, "lr": 4.14598352972726e-06, "epoch": 1.0329171396140748, "percentage": 34.43, "elapsed_time": "1:00:27", "remaining_time": "1:55:09"}
+{"current_steps": 920, "total_steps": 2643, "loss": 0.1924, "lr": 4.12098154308081e-06, "epoch": 1.0442678774120318, "percentage": 34.81, "elapsed_time": "1:01:07", "remaining_time": "1:54:29"}
+{"current_steps": 930, "total_steps": 2643, "loss": 0.0995, "lr": 4.095696646760425e-06, "epoch": 1.0556186152099887, "percentage": 35.19, "elapsed_time": "1:01:49", "remaining_time": "1:53:52"}
+{"current_steps": 940, "total_steps": 2643, "loss": 0.0985, "lr": 4.070133253735399e-06, "epoch": 1.0669693530079456, "percentage": 35.57, "elapsed_time": "1:02:32", "remaining_time": "1:53:17"}
+{"current_steps": 950, "total_steps": 2643, "loss": 0.0467, "lr": 4.044295825581013e-06, "epoch": 1.0783200908059023, "percentage": 35.94, "elapsed_time": "1:03:13", "remaining_time": "1:52:39"}
+{"current_steps": 960, "total_steps": 2643, "loss": 0.2061, "lr": 4.018188871699861e-06, "epoch": 1.0896708286038592, "percentage": 36.32, "elapsed_time": "1:03:50", "remaining_time": "1:51:55"}
+{"current_steps": 970, "total_steps": 2643, "loss": 0.1263, "lr": 3.991816948534823e-06, "epoch": 1.1010215664018161, "percentage": 36.7, "elapsed_time": "1:04:27", "remaining_time": "1:51:10"}
+{"current_steps": 980, "total_steps": 2643, "loss": 0.1175, "lr": 3.965184658773828e-06, "epoch": 1.112372304199773, "percentage": 37.08, "elapsed_time": "1:05:02", "remaining_time": "1:50:23"}
+{"current_steps": 990, "total_steps": 2643, "loss": 0.1199, "lr": 3.938296650546552e-06, "epoch": 1.1237230419977298, "percentage": 37.46, "elapsed_time": "1:05:40", "remaining_time": "1:49:40"}
+{"current_steps": 1000, "total_steps": 2643, "loss": 0.1169, "lr": 3.911157616613176e-06, "epoch": 1.1350737797956867, "percentage": 37.84, "elapsed_time": "1:06:24", "remaining_time": "1:49:05"}
+{"current_steps": 1010, "total_steps": 2643, "loss": 0.1326, "lr": 3.8837722935453615e-06, "epoch": 1.1464245175936436, "percentage": 38.21, "elapsed_time": "1:07:05", "remaining_time": "1:48:28"}
+{"current_steps": 1020, "total_steps": 2643, "loss": 0.1049, "lr": 3.8561454608995765e-06, "epoch": 1.1577752553916005, "percentage": 38.59, "elapsed_time": "1:07:44", "remaining_time": "1:47:47"}
+{"current_steps": 1030, "total_steps": 2643, "loss": 0.0978, "lr": 3.828281940382923e-06, "epoch": 1.1691259931895572, "percentage": 38.97, "elapsed_time": "1:08:22", "remaining_time": "1:47:04"}
+{"current_steps": 1040, "total_steps": 2643, "loss": 0.19, "lr": 3.800186595011599e-06, "epoch": 1.1804767309875142, "percentage": 39.35, "elapsed_time": "1:09:01", "remaining_time": "1:46:24"}
+{"current_steps": 1050, "total_steps": 2643, "loss": 0.1121, "lr": 3.7718643282621648e-06, "epoch": 1.191827468785471, "percentage": 39.73, "elapsed_time": "1:09:40", "remaining_time": "1:45:43"}
+{"current_steps": 1060, "total_steps": 2643, "loss": 0.1125, "lr": 3.7433200832157333e-06, "epoch": 1.203178206583428, "percentage": 40.11, "elapsed_time": "1:10:20", "remaining_time": "1:45:03"}
+{"current_steps": 1070, "total_steps": 2643, "loss": 0.144, "lr": 3.714558841695258e-06, "epoch": 1.2145289443813847, "percentage": 40.48, "elapsed_time": "1:11:05", "remaining_time": "1:44:31"}
+{"current_steps": 1080, "total_steps": 2643, "loss": 0.159, "lr": 3.685585623396055e-06, "epoch": 1.2258796821793416, "percentage": 40.86, "elapsed_time": "1:11:47", "remaining_time": "1:43:54"}
+{"current_steps": 1090, "total_steps": 2643, "loss": 0.1044, "lr": 3.656405485009719e-06, "epoch": 1.2372304199772985, "percentage": 41.24, "elapsed_time": "1:12:30", "remaining_time": "1:43:18"}
+{"current_steps": 1100, "total_steps": 2643, "loss": 0.0954, "lr": 3.6270235193415754e-06, "epoch": 1.2485811577752555, "percentage": 41.62, "elapsed_time": "1:13:11", "remaining_time": "1:42:39"}
+{"current_steps": 1110, "total_steps": 2643, "loss": 0.1576, "lr": 3.597444854421837e-06, "epoch": 1.2599318955732124, "percentage": 42.0, "elapsed_time": "1:13:50", "remaining_time": "1:41:59"}
+{"current_steps": 1120, "total_steps": 2643, "loss": 0.1081, "lr": 3.5676746526106084e-06, "epoch": 1.271282633371169, "percentage": 42.38, "elapsed_time": "1:14:31", "remaining_time": "1:41:20"}
+{"current_steps": 1130, "total_steps": 2643, "loss": 0.0688, "lr": 3.537718109696899e-06, "epoch": 1.282633371169126, "percentage": 42.75, "elapsed_time": "1:15:12", "remaining_time": "1:40:42"}
+{"current_steps": 1140, "total_steps": 2643, "loss": 0.1562, "lr": 3.5075804539918047e-06, "epoch": 1.293984108967083, "percentage": 43.13, "elapsed_time": "1:15:54", "remaining_time": "1:40:04"}
+{"current_steps": 1150, "total_steps": 2643, "loss": 0.0616, "lr": 3.4772669454160113e-06, "epoch": 1.3053348467650396, "percentage": 43.51, "elapsed_time": "1:16:33", "remaining_time": "1:39:24"}
+{"current_steps": 1160, "total_steps": 2643, "loss": 0.1002, "lr": 3.44678287458178e-06, "epoch": 1.3166855845629966, "percentage": 43.89, "elapsed_time": "1:17:12", "remaining_time": "1:38:42"}
+{"current_steps": 1170, "total_steps": 2643, "loss": 0.0992, "lr": 3.4161335618695774e-06, "epoch": 1.3280363223609535, "percentage": 44.27, "elapsed_time": "1:17:52", "remaining_time": "1:38:02"}
+{"current_steps": 1180, "total_steps": 2643, "loss": 0.1226, "lr": 3.385324356499513e-06, "epoch": 1.3393870601589104, "percentage": 44.65, "elapsed_time": "1:18:32", "remaining_time": "1:37:22"}
+{"current_steps": 1190, "total_steps": 2643, "loss": 0.0733, "lr": 3.3543606355977377e-06, "epoch": 1.3507377979568673, "percentage": 45.02, "elapsed_time": "1:19:09", "remaining_time": "1:36:39"}
+{"current_steps": 1200, "total_steps": 2643, "loss": 0.1127, "lr": 3.3232478032579746e-06, "epoch": 1.362088535754824, "percentage": 45.4, "elapsed_time": "1:19:53", "remaining_time": "1:36:03"}
+{"current_steps": 1210, "total_steps": 2643, "loss": 0.1209, "lr": 3.291991289598347e-06, "epoch": 1.373439273552781, "percentage": 45.78, "elapsed_time": "1:20:36", "remaining_time": "1:35:28"}
+{"current_steps": 1220, "total_steps": 2643, "loss": 0.086, "lr": 3.2605965498136554e-06, "epoch": 1.3847900113507379, "percentage": 46.16, "elapsed_time": "1:21:14", "remaining_time": "1:34:45"}
+{"current_steps": 1230, "total_steps": 2643, "loss": 0.1225, "lr": 3.229069063223289e-06, "epoch": 1.3961407491486946, "percentage": 46.54, "elapsed_time": "1:21:53", "remaining_time": "1:34:04"}
+{"current_steps": 1240, "total_steps": 2643, "loss": 0.0741, "lr": 3.197414332314914e-06, "epoch": 1.4074914869466515, "percentage": 46.92, "elapsed_time": "1:22:33", "remaining_time": "1:33:24"}
+{"current_steps": 1250, "total_steps": 2643, "loss": 0.1664, "lr": 3.165637881784133e-06, "epoch": 1.4188422247446084, "percentage": 47.29, "elapsed_time": "1:23:13", "remaining_time": "1:32:44"}
+{"current_steps": 1260, "total_steps": 2643, "loss": 0.1355, "lr": 3.133745257570253e-06, "epoch": 1.4301929625425653, "percentage": 47.67, "elapsed_time": "1:23:53", "remaining_time": "1:32:04"}
+{"current_steps": 1270, "total_steps": 2643, "loss": 0.0945, "lr": 3.1017420258883607e-06, "epoch": 1.4415437003405223, "percentage": 48.05, "elapsed_time": "1:24:28", "remaining_time": "1:31:19"}
+{"current_steps": 1280, "total_steps": 2643, "loss": 0.1288, "lr": 3.0696337722578444e-06, "epoch": 1.452894438138479, "percentage": 48.43, "elapsed_time": "1:25:05", "remaining_time": "1:30:36"}
+{"current_steps": 1290, "total_steps": 2643, "loss": 0.0707, "lr": 3.0374261005275606e-06, "epoch": 1.4642451759364359, "percentage": 48.81, "elapsed_time": "1:25:46", "remaining_time": "1:29:57"}
+{"current_steps": 1300, "total_steps": 2643, "loss": 0.1143, "lr": 3.0051246318977913e-06, "epoch": 1.4755959137343928, "percentage": 49.19, "elapsed_time": "1:26:24", "remaining_time": "1:29:16"}
+{"current_steps": 1310, "total_steps": 2643, "loss": 0.0805, "lr": 2.9727350039391782e-06, "epoch": 1.4869466515323495, "percentage": 49.56, "elapsed_time": "1:27:03", "remaining_time": "1:28:35"}
+{"current_steps": 1320, "total_steps": 2643, "loss": 0.0943, "lr": 2.940262869608798e-06, "epoch": 1.4982973893303064, "percentage": 49.94, "elapsed_time": "1:27:43", "remaining_time": "1:27:55"}
+{"current_steps": 1330, "total_steps": 2643, "loss": 0.0564, "lr": 2.907713896263551e-06, "epoch": 1.5096481271282634, "percentage": 50.32, "elapsed_time": "1:28:19", "remaining_time": "1:27:11"}
+{"current_steps": 1340, "total_steps": 2643, "loss": 0.0471, "lr": 2.8750937646710416e-06, "epoch": 1.52099886492622, "percentage": 50.7, "elapsed_time": "1:29:01", "remaining_time": "1:26:34"}
+{"current_steps": 1350, "total_steps": 2643, "loss": 0.1026, "lr": 2.842408168018112e-06, "epoch": 1.5323496027241772, "percentage": 51.08, "elapsed_time": "1:29:41", "remaining_time": "1:25:54"}
+{"current_steps": 1360, "total_steps": 2643, "loss": 0.0858, "lr": 2.8096628109172125e-06, "epoch": 1.543700340522134, "percentage": 51.46, "elapsed_time": "1:30:26", "remaining_time": "1:25:18"}
+{"current_steps": 1370, "total_steps": 2643, "loss": 0.1614, "lr": 2.7768634084107736e-06, "epoch": 1.5550510783200908, "percentage": 51.84, "elapsed_time": "1:31:08", "remaining_time": "1:24:41"}
+{"current_steps": 1380, "total_steps": 2643, "loss": 0.0271, "lr": 2.744015684973766e-06, "epoch": 1.5664018161180477, "percentage": 52.21, "elapsed_time": "1:31:50", "remaining_time": "1:24:02"}
+{"current_steps": 1390, "total_steps": 2643, "loss": 0.1021, "lr": 2.711125373514602e-06, "epoch": 1.5777525539160044, "percentage": 52.59, "elapsed_time": "1:32:28", "remaining_time": "1:23:22"}
+{"current_steps": 1400, "total_steps": 2643, "loss": 0.1074, "lr": 2.6781982143745776e-06, "epoch": 1.5891032917139614, "percentage": 52.97, "elapsed_time": "1:33:07", "remaining_time": "1:22:40"}
+{"current_steps": 1410, "total_steps": 2643, "loss": 0.1118, "lr": 2.645239954326009e-06, "epoch": 1.6004540295119183, "percentage": 53.35, "elapsed_time": "1:33:49", "remaining_time": "1:22:02"}
+{"current_steps": 1420, "total_steps": 2643, "loss": 0.0898, "lr": 2.6122563455692467e-06, "epoch": 1.611804767309875, "percentage": 53.73, "elapsed_time": "1:34:25", "remaining_time": "1:21:19"}
+{"current_steps": 1430, "total_steps": 2643, "loss": 0.0668, "lr": 2.5792531447287515e-06, "epoch": 1.6231555051078321, "percentage": 54.11, "elapsed_time": "1:35:03", "remaining_time": "1:20:38"}
+{"current_steps": 1440, "total_steps": 2643, "loss": 0.1002, "lr": 2.546236111848387e-06, "epoch": 1.6345062429057888, "percentage": 54.48, "elapsed_time": "1:35:45", "remaining_time": "1:19:59"}
+{"current_steps": 1450, "total_steps": 2643, "loss": 0.0915, "lr": 2.5132110093861174e-06, "epoch": 1.6458569807037458, "percentage": 54.86, "elapsed_time": "1:36:25", "remaining_time": "1:19:19"}
+{"current_steps": 1460, "total_steps": 2643, "loss": 0.0728, "lr": 2.480183601208293e-06, "epoch": 1.6572077185017027, "percentage": 55.24, "elapsed_time": "1:37:02", "remaining_time": "1:18:37"}
+{"current_steps": 1470, "total_steps": 2643, "loss": 0.0832, "lr": 2.4471596515836797e-06, "epoch": 1.6685584562996594, "percentage": 55.62, "elapsed_time": "1:37:46", "remaining_time": "1:18:00"}
+{"current_steps": 1480, "total_steps": 2643, "loss": 0.0992, "lr": 2.414144924177422e-06, "epoch": 1.6799091940976163, "percentage": 56.0, "elapsed_time": "1:38:25", "remaining_time": "1:17:20"}
+{"current_steps": 1490, "total_steps": 2643, "loss": 0.1376, "lr": 2.3811451810451132e-06, "epoch": 1.6912599318955732, "percentage": 56.38, "elapsed_time": "1:39:07", "remaining_time": "1:16:42"}
+{"current_steps": 1500, "total_steps": 2643, "loss": 0.1048, "lr": 2.3481661816271413e-06, "epoch": 1.70261066969353, "percentage": 56.75, "elapsed_time": "1:39:45", "remaining_time": "1:16:01"}
+{"current_steps": 1510, "total_steps": 2643, "loss": 0.1075, "lr": 2.3152136817434983e-06, "epoch": 1.713961407491487, "percentage": 57.13, "elapsed_time": "1:40:26", "remaining_time": "1:15:22"}
+{"current_steps": 1520, "total_steps": 2643, "loss": 0.1121, "lr": 2.2822934325892178e-06, "epoch": 1.7253121452894438, "percentage": 57.51, "elapsed_time": "1:41:11", "remaining_time": "1:14:45"}
+{"current_steps": 1530, "total_steps": 2643, "loss": 0.1009, "lr": 2.2494111797306146e-06, "epoch": 1.7366628830874007, "percentage": 57.89, "elapsed_time": "1:41:52", "remaining_time": "1:14:06"}
+{"current_steps": 1540, "total_steps": 2643, "loss": 0.1405, "lr": 2.216572662102518e-06, "epoch": 1.7480136208853576, "percentage": 58.27, "elapsed_time": "1:42:36", "remaining_time": "1:13:29"}
+{"current_steps": 1550, "total_steps": 2643, "loss": 0.1172, "lr": 2.1837836110066544e-06, "epoch": 1.7593643586833143, "percentage": 58.65, "elapsed_time": "1:43:16", "remaining_time": "1:12:49"}
+{"current_steps": 1560, "total_steps": 2643, "loss": 0.1048, "lr": 2.151049749111361e-06, "epoch": 1.7707150964812712, "percentage": 59.02, "elapsed_time": "1:43:57", "remaining_time": "1:12:10"}
+{"current_steps": 1570, "total_steps": 2643, "loss": 0.0631, "lr": 2.1183767894528135e-06, "epoch": 1.7820658342792282, "percentage": 59.4, "elapsed_time": "1:44:38", "remaining_time": "1:11:31"}
+{"current_steps": 1580, "total_steps": 2643, "loss": 0.0908, "lr": 2.085770434437931e-06, "epoch": 1.7934165720771849, "percentage": 59.78, "elapsed_time": "1:45:19", "remaining_time": "1:10:51"}
+{"current_steps": 1590, "total_steps": 2643, "loss": 0.1064, "lr": 2.053236374849128e-06, "epoch": 1.804767309875142, "percentage": 60.16, "elapsed_time": "1:45:55", "remaining_time": "1:10:09"}
+{"current_steps": 1600, "total_steps": 2643, "loss": 0.0929, "lr": 2.0207802888511155e-06, "epoch": 1.8161180476730987, "percentage": 60.54, "elapsed_time": "1:46:31", "remaining_time": "1:09:26"}
+{"current_steps": 1610, "total_steps": 2643, "loss": 0.0941, "lr": 1.988407840999881e-06, "epoch": 1.8274687854710556, "percentage": 60.92, "elapsed_time": "1:47:13", "remaining_time": "1:08:48"}
+{"current_steps": 1620, "total_steps": 2643, "loss": 0.0907, "lr": 1.9561246812540572e-06, "epoch": 1.8388195232690125, "percentage": 61.29, "elapsed_time": "1:47:48", "remaining_time": "1:08:04"}
+{"current_steps": 1630, "total_steps": 2643, "loss": 0.0793, "lr": 1.923936443988841e-06, "epoch": 1.8501702610669692, "percentage": 61.67, "elapsed_time": "1:48:27", "remaining_time": "1:07:24"}
+{"current_steps": 1640, "total_steps": 2643, "loss": 0.0758, "lr": 1.8918487470126207e-06, "epoch": 1.8615209988649262, "percentage": 62.05, "elapsed_time": "1:49:04", "remaining_time": "1:06:42"}
+{"current_steps": 1650, "total_steps": 2643, "loss": 0.0648, "lr": 1.8598671905865002e-06, "epoch": 1.872871736662883, "percentage": 62.43, "elapsed_time": "1:49:47", "remaining_time": "1:06:04"}
+{"current_steps": 1660, "total_steps": 2643, "loss": 0.1024, "lr": 1.8279973564468906e-06, "epoch": 1.8842224744608398, "percentage": 62.81, "elapsed_time": "1:50:24", "remaining_time": "1:05:22"}
+{"current_steps": 1670, "total_steps": 2643, "loss": 0.0836, "lr": 1.7962448068313298e-06, "epoch": 1.895573212258797, "percentage": 63.19, "elapsed_time": "1:51:01", "remaining_time": "1:04:41"}
+{"current_steps": 1680, "total_steps": 2643, "loss": 0.0969, "lr": 1.7646150835077014e-06, "epoch": 1.9069239500567536, "percentage": 63.56, "elapsed_time": "1:51:37", "remaining_time": "1:03:59"}
+{"current_steps": 1690, "total_steps": 2643, "loss": 0.0756, "lr": 1.733113706807038e-06, "epoch": 1.9182746878547106, "percentage": 63.94, "elapsed_time": "1:52:17", "remaining_time": "1:03:19"}
+{"current_steps": 1700, "total_steps": 2643, "loss": 0.124, "lr": 1.7017461746600506e-06, "epoch": 1.9296254256526675, "percentage": 64.32, "elapsed_time": "1:52:59", "remaining_time": "1:02:40"}
+{"current_steps": 1710, "total_steps": 2643, "loss": 0.1292, "lr": 1.670517961637582e-06, "epoch": 1.9409761634506242, "percentage": 64.7, "elapsed_time": "1:53:39", "remaining_time": "1:02:00"}
+{"current_steps": 1720, "total_steps": 2643, "loss": 0.0718, "lr": 1.6394345179951293e-06, "epoch": 1.952326901248581, "percentage": 65.08, "elapsed_time": "1:54:16", "remaining_time": "1:01:19"}
+{"current_steps": 1730, "total_steps": 2643, "loss": 0.0897, "lr": 1.6085012687216078e-06, "epoch": 1.963677639046538, "percentage": 65.46, "elapsed_time": "1:54:55", "remaining_time": "1:00:39"}
+{"current_steps": 1740, "total_steps": 2643, "loss": 0.1087, "lr": 1.5777236125925333e-06, "epoch": 1.9750283768444947, "percentage": 65.83, "elapsed_time": "1:55:34", "remaining_time": "0:59:58"}
+{"current_steps": 1750, "total_steps": 2643, "loss": 0.0973, "lr": 1.5471069212277729e-06, "epoch": 1.9863791146424519, "percentage": 66.21, "elapsed_time": "1:56:15", "remaining_time": "0:59:19"}
+{"current_steps": 1760, "total_steps": 2643, "loss": 0.1185, "lr": 1.516656538154035e-06, "epoch": 1.9977298524404086, "percentage": 66.59, "elapsed_time": "1:56:50", "remaining_time": "0:58:37"}
+{"current_steps": 1770, "total_steps": 2643, "loss": 0.0295, "lr": 1.4863777778722682e-06, "epoch": 2.0090805902383657, "percentage": 66.97, "elapsed_time": "1:57:29", "remaining_time": "0:57:56"}
+{"current_steps": 1780, "total_steps": 2643, "loss": 0.0535, "lr": 1.4562759249301185e-06, "epoch": 2.0204313280363224, "percentage": 67.35, "elapsed_time": "1:58:11", "remaining_time": "0:57:18"}
+{"current_steps": 1790, "total_steps": 2643, "loss": 0.0435, "lr": 1.4263562329996194e-06, "epoch": 2.031782065834279, "percentage": 67.73, "elapsed_time": "1:58:52", "remaining_time": "0:56:38"}
+{"current_steps": 1800, "total_steps": 2643, "loss": 0.0444, "lr": 1.396623923960271e-06, "epoch": 2.0431328036322363, "percentage": 68.1, "elapsed_time": "1:59:32", "remaining_time": "0:55:59"}
+{"current_steps": 1810, "total_steps": 2643, "loss": 0.0738, "lr": 1.367084186987663e-06, "epoch": 2.054483541430193, "percentage": 68.48, "elapsed_time": "2:00:14", "remaining_time": "0:55:20"}
+{"current_steps": 1820, "total_steps": 2643, "loss": 0.0413, "lr": 1.3377421776478111e-06, "epoch": 2.0658342792281497, "percentage": 68.86, "elapsed_time": "2:00:51", "remaining_time": "0:54:38"}
+{"current_steps": 1830, "total_steps": 2643, "loss": 0.0777, "lr": 1.3086030169973552e-06, "epoch": 2.077185017026107, "percentage": 69.24, "elapsed_time": "2:01:31", "remaining_time": "0:53:59"}
+{"current_steps": 1840, "total_steps": 2643, "loss": 0.0753, "lr": 1.2796717906897831e-06, "epoch": 2.0885357548240635, "percentage": 69.62, "elapsed_time": "2:02:13", "remaining_time": "0:53:20"}
+{"current_steps": 1850, "total_steps": 2643, "loss": 0.0217, "lr": 1.2509535480878325e-06, "epoch": 2.09988649262202, "percentage": 70.0, "elapsed_time": "2:02:52", "remaining_time": "0:52:40"}
+{"current_steps": 1860, "total_steps": 2643, "loss": 0.0787, "lr": 1.2224533013822237e-06, "epoch": 2.1112372304199774, "percentage": 70.37, "elapsed_time": "2:03:27", "remaining_time": "0:51:58"}
+{"current_steps": 1870, "total_steps": 2643, "loss": 0.0918, "lr": 1.1941760247168893e-06, "epoch": 2.122587968217934, "percentage": 70.75, "elapsed_time": "2:04:08", "remaining_time": "0:51:18"}
+{"current_steps": 1880, "total_steps": 2643, "loss": 0.1123, "lr": 1.1661266533208274e-06, "epoch": 2.133938706015891, "percentage": 71.13, "elapsed_time": "2:04:46", "remaining_time": "0:50:38"}
+{"current_steps": 1890, "total_steps": 2643, "loss": 0.1148, "lr": 1.1383100826467653e-06, "epoch": 2.145289443813848, "percentage": 71.51, "elapsed_time": "2:05:23", "remaining_time": "0:49:57"}
+{"current_steps": 1900, "total_steps": 2643, "loss": 0.0902, "lr": 1.1107311675167558e-06, "epoch": 2.1566401816118046, "percentage": 71.89, "elapsed_time": "2:06:03", "remaining_time": "0:49:17"}
+{"current_steps": 1910, "total_steps": 2643, "loss": 0.0576, "lr": 1.0833947212748597e-06, "epoch": 2.1679909194097617, "percentage": 72.27, "elapsed_time": "2:06:46", "remaining_time": "0:48:39"}
+{"current_steps": 1920, "total_steps": 2643, "loss": 0.0209, "lr": 1.056305514947082e-06, "epoch": 2.1793416572077184, "percentage": 72.64, "elapsed_time": "2:07:33", "remaining_time": "0:48:01"}
+{"current_steps": 1930, "total_steps": 2643, "loss": 0.0414, "lr": 1.0294682764086794e-06, "epoch": 2.1906923950056756, "percentage": 73.02, "elapsed_time": "2:08:13", "remaining_time": "0:47:22"}
+{"current_steps": 1940, "total_steps": 2643, "loss": 0.0688, "lr": 1.002887689559005e-06, "epoch": 2.2020431328036323, "percentage": 73.4, "elapsed_time": "2:08:56", "remaining_time": "0:46:43"}
+{"current_steps": 1950, "total_steps": 2643, "loss": 0.0725, "lr": 9.765683935040343e-07, "epoch": 2.213393870601589, "percentage": 73.78, "elapsed_time": "2:09:33", "remaining_time": "0:46:02"}
+{"current_steps": 1960, "total_steps": 2643, "loss": 0.0867, "lr": 9.505149817466952e-07, "epoch": 2.224744608399546, "percentage": 74.16, "elapsed_time": "2:10:14", "remaining_time": "0:45:23"}
+{"current_steps": 1970, "total_steps": 2643, "loss": 0.0995, "lr": 9.247320013851663e-07, "epoch": 2.236095346197503, "percentage": 74.54, "elapsed_time": "2:10:50", "remaining_time": "0:44:41"}
+{"current_steps": 1980, "total_steps": 2643, "loss": 0.0742, "lr": 8.992239523192778e-07, "epoch": 2.2474460839954595, "percentage": 74.91, "elapsed_time": "2:11:31", "remaining_time": "0:44:02"}
+{"current_steps": 1990, "total_steps": 2643, "loss": 0.048, "lr": 8.739952864651379e-07, "epoch": 2.2587968217934167, "percentage": 75.29, "elapsed_time": "2:12:14", "remaining_time": "0:43:23"}
+{"current_steps": 2000, "total_steps": 2643, "loss": 0.0612, "lr": 8.490504069781444e-07, "epoch": 2.2701475595913734, "percentage": 75.67, "elapsed_time": "2:12:53", "remaining_time": "0:42:43"}
+{"current_steps": 2010, "total_steps": 2643, "loss": 0.0671, "lr": 8.243936674845016e-07, "epoch": 2.28149829738933, "percentage": 76.05, "elapsed_time": "2:13:35", "remaining_time": "0:42:04"}
+{"current_steps": 2020, "total_steps": 2643, "loss": 0.0607, "lr": 8.000293713213798e-07, "epoch": 2.292849035187287, "percentage": 76.43, "elapsed_time": "2:14:15", "remaining_time": "0:41:24"}
+{"current_steps": 2030, "total_steps": 2643, "loss": 0.0585, "lr": 7.759617707858619e-07, "epoch": 2.304199772985244, "percentage": 76.81, "elapsed_time": "2:14:54", "remaining_time": "0:40:44"}
+{"current_steps": 2040, "total_steps": 2643, "loss": 0.0358, "lr": 7.521950663927824e-07, "epoch": 2.315550510783201, "percentage": 77.19, "elapsed_time": "2:15:38", "remaining_time": "0:40:05"}
+{"current_steps": 2050, "total_steps": 2643, "loss": 0.0685, "lr": 7.287334061416174e-07, "epoch": 2.3269012485811578, "percentage": 77.56, "elapsed_time": "2:16:18", "remaining_time": "0:39:25"}
+{"current_steps": 2060, "total_steps": 2643, "loss": 0.0798, "lr": 7.055808847925316e-07, "epoch": 2.3382519863791145, "percentage": 77.94, "elapsed_time": "2:16:57", "remaining_time": "0:38:45"}
+{"current_steps": 2070, "total_steps": 2643, "loss": 0.0863, "lr": 6.827415431517232e-07, "epoch": 2.3496027241770716, "percentage": 78.32, "elapsed_time": "2:17:35", "remaining_time": "0:38:05"}
+{"current_steps": 2080, "total_steps": 2643, "loss": 0.0741, "lr": 6.602193673661805e-07, "epoch": 2.3609534619750283, "percentage": 78.7, "elapsed_time": "2:18:14", "remaining_time": "0:37:25"}
+{"current_steps": 2090, "total_steps": 2643, "loss": 0.0403, "lr": 6.380182882279817e-07, "epoch": 2.3723041997729855, "percentage": 79.08, "elapsed_time": "2:18:51", "remaining_time": "0:36:44"}
+{"current_steps": 2100, "total_steps": 2643, "loss": 0.0736, "lr": 6.161421804882528e-07, "epoch": 2.383654937570942, "percentage": 79.46, "elapsed_time": "2:19:31", "remaining_time": "0:36:04"}
+{"current_steps": 2110, "total_steps": 2643, "loss": 0.0671, "lr": 5.945948621809092e-07, "epoch": 2.395005675368899, "percentage": 79.83, "elapsed_time": "2:20:13", "remaining_time": "0:35:25"}
+{"current_steps": 2120, "total_steps": 2643, "loss": 0.0527, "lr": 5.733800939562941e-07, "epoch": 2.406356413166856, "percentage": 80.21, "elapsed_time": "2:20:51", "remaining_time": "0:34:45"}
+{"current_steps": 2130, "total_steps": 2643, "loss": 0.0212, "lr": 5.525015784248336e-07, "epoch": 2.4177071509648127, "percentage": 80.59, "elapsed_time": "2:21:34", "remaining_time": "0:34:05"}
+{"current_steps": 2140, "total_steps": 2643, "loss": 0.0411, "lr": 5.319629595108189e-07, "epoch": 2.4290578887627694, "percentage": 80.97, "elapsed_time": "2:22:18", "remaining_time": "0:33:26"}
+{"current_steps": 2150, "total_steps": 2643, "loss": 0.0386, "lr": 5.117678218164337e-07, "epoch": 2.4404086265607265, "percentage": 81.35, "elapsed_time": "2:22:55", "remaining_time": "0:32:46"}
+{"current_steps": 2160, "total_steps": 2643, "loss": 0.0663, "lr": 4.919196899961367e-07, "epoch": 2.4517593643586832, "percentage": 81.73, "elapsed_time": "2:23:36", "remaining_time": "0:32:06"}
+{"current_steps": 2170, "total_steps": 2643, "loss": 0.0314, "lr": 4.724220281414979e-07, "epoch": 2.46311010215664, "percentage": 82.1, "elapsed_time": "2:24:16", "remaining_time": "0:31:26"}
+{"current_steps": 2180, "total_steps": 2643, "loss": 0.0482, "lr": 4.532782391766169e-07, "epoch": 2.474460839954597, "percentage": 82.48, "elapsed_time": "2:24:56", "remaining_time": "0:30:46"}
+{"current_steps": 2190, "total_steps": 2643, "loss": 0.046, "lr": 4.344916642642108e-07, "epoch": 2.485811577752554, "percentage": 82.86, "elapsed_time": "2:25:37", "remaining_time": "0:30:07"}
+{"current_steps": 2200, "total_steps": 2643, "loss": 0.1535, "lr": 4.1606558222247543e-07, "epoch": 2.497162315550511, "percentage": 83.24, "elapsed_time": "2:26:20", "remaining_time": "0:29:27"}
+{"current_steps": 2210, "total_steps": 2643, "loss": 0.0618, "lr": 3.9800320895284264e-07, "epoch": 2.5085130533484676, "percentage": 83.62, "elapsed_time": "2:26:59", "remaining_time": "0:28:48"}
+{"current_steps": 2220, "total_steps": 2643, "loss": 0.0313, "lr": 3.803076968787034e-07, "epoch": 2.519863791146425, "percentage": 84.0, "elapsed_time": "2:27:39", "remaining_time": "0:28:08"}
+{"current_steps": 2230, "total_steps": 2643, "loss": 0.0379, "lr": 3.629821343952147e-07, "epoch": 2.5312145289443815, "percentage": 84.37, "elapsed_time": "2:28:22", "remaining_time": "0:27:28"}
+{"current_steps": 2240, "total_steps": 2643, "loss": 0.0483, "lr": 3.4602954533028946e-07, "epoch": 2.542565266742338, "percentage": 84.75, "elapsed_time": "2:29:01", "remaining_time": "0:26:48"}
+{"current_steps": 2250, "total_steps": 2643, "loss": 0.0354, "lr": 3.2945288841684103e-07, "epoch": 2.5539160045402953, "percentage": 85.13, "elapsed_time": "2:29:46", "remaining_time": "0:26:09"}
+{"current_steps": 2260, "total_steps": 2643, "loss": 0.0608, "lr": 3.1325505677639977e-07, "epoch": 2.565266742338252, "percentage": 85.51, "elapsed_time": "2:30:26", "remaining_time": "0:25:29"}
+{"current_steps": 2270, "total_steps": 2643, "loss": 0.053, "lr": 2.974388774141759e-07, "epoch": 2.5766174801362087, "percentage": 85.89, "elapsed_time": "2:31:05", "remaining_time": "0:24:49"}
+{"current_steps": 2280, "total_steps": 2643, "loss": 0.0267, "lr": 2.820071107256625e-07, "epoch": 2.587968217934166, "percentage": 86.27, "elapsed_time": "2:31:42", "remaining_time": "0:24:09"}
+{"current_steps": 2290, "total_steps": 2643, "loss": 0.0478, "lr": 2.669624500148646e-07, "epoch": 2.5993189557321226, "percentage": 86.64, "elapsed_time": "2:32:24", "remaining_time": "0:23:29"}
+{"current_steps": 2300, "total_steps": 2643, "loss": 0.0298, "lr": 2.523075210242376e-07, "epoch": 2.6106696935300793, "percentage": 87.02, "elapsed_time": "2:33:03", "remaining_time": "0:22:49"}
+{"current_steps": 2310, "total_steps": 2643, "loss": 0.0663, "lr": 2.3804488147641443e-07, "epoch": 2.6220204313280364, "percentage": 87.4, "elapsed_time": "2:33:43", "remaining_time": "0:22:09"}
+{"current_steps": 2320, "total_steps": 2643, "loss": 0.0189, "lr": 2.241770206278107e-07, "epoch": 2.633371169125993, "percentage": 87.78, "elapsed_time": "2:34:20", "remaining_time": "0:21:29"}
+{"current_steps": 2330, "total_steps": 2643, "loss": 0.0407, "lr": 2.1070635883417124e-07, "epoch": 2.64472190692395, "percentage": 88.16, "elapsed_time": "2:35:01", "remaining_time": "0:20:49"}
+{"current_steps": 2340, "total_steps": 2643, "loss": 0.0389, "lr": 1.9763524712814812e-07, "epoch": 2.656072644721907, "percentage": 88.54, "elapsed_time": "2:35:43", "remaining_time": "0:20:09"}
+{"current_steps": 2350, "total_steps": 2643, "loss": 0.0649, "lr": 1.8496596680897398e-07, "epoch": 2.6674233825198637, "percentage": 88.91, "elapsed_time": "2:36:24", "remaining_time": "0:19:30"}
+{"current_steps": 2360, "total_steps": 2643, "loss": 0.0404, "lr": 1.7270072904430806e-07, "epoch": 2.678774120317821, "percentage": 89.29, "elapsed_time": "2:37:04", "remaining_time": "0:18:50"}
+{"current_steps": 2370, "total_steps": 2643, "loss": 0.0567, "lr": 1.608416744843208e-07, "epoch": 2.6901248581157775, "percentage": 89.67, "elapsed_time": "2:37:46", "remaining_time": "0:18:10"}
+{"current_steps": 2380, "total_steps": 2643, "loss": 0.046, "lr": 1.4939087288808718e-07, "epoch": 2.7014755959137347, "percentage": 90.05, "elapsed_time": "2:38:21", "remaining_time": "0:17:29"}
+{"current_steps": 2390, "total_steps": 2643, "loss": 0.0576, "lr": 1.3835032276235088e-07, "epoch": 2.7128263337116914, "percentage": 90.43, "elapsed_time": "2:38:58", "remaining_time": "0:16:49"}
+{"current_steps": 2400, "total_steps": 2643, "loss": 0.0925, "lr": 1.2772195101272645e-07, "epoch": 2.724177071509648, "percentage": 90.81, "elapsed_time": "2:39:34", "remaining_time": "0:16:09"}
+{"current_steps": 2410, "total_steps": 2643, "loss": 0.0627, "lr": 1.1750761260739596e-07, "epoch": 2.735527809307605, "percentage": 91.18, "elapsed_time": "2:40:12", "remaining_time": "0:15:29"}
+{"current_steps": 2420, "total_steps": 2643, "loss": 0.0325, "lr": 1.0770909025336202e-07, "epoch": 2.746878547105562, "percentage": 91.56, "elapsed_time": "2:40:53", "remaining_time": "0:14:49"}
+{"current_steps": 2430, "total_steps": 2643, "loss": 0.0616, "lr": 9.83280940853118e-08, "epoch": 2.7582292849035186, "percentage": 91.94, "elapsed_time": "2:41:37", "remaining_time": "0:14:09"}
+{"current_steps": 2440, "total_steps": 2643, "loss": 0.0424, "lr": 8.936626136714754e-08, "epoch": 2.7695800227014757, "percentage": 92.32, "elapsed_time": "2:42:11", "remaining_time": "0:13:29"}
+{"current_steps": 2450, "total_steps": 2643, "loss": 0.0253, "lr": 8.082515620623593e-08, "epoch": 2.7809307604994324, "percentage": 92.7, "elapsed_time": "2:42:52", "remaining_time": "0:12:49"}
+{"current_steps": 2460, "total_steps": 2643, "loss": 0.0585, "lr": 7.27062692804234e-08, "epoch": 2.792281498297389, "percentage": 93.08, "elapsed_time": "2:43:31", "remaining_time": "0:12:09"}
+{"current_steps": 2470, "total_steps": 2643, "loss": 0.0536, "lr": 6.501101757786898e-08, "epoch": 2.8036322360953463, "percentage": 93.45, "elapsed_time": "2:44:12", "remaining_time": "0:11:30"}
+{"current_steps": 2480, "total_steps": 2643, "loss": 0.0795, "lr": 5.7740744149738516e-08, "epoch": 2.814982973893303, "percentage": 93.83, "elapsed_time": "2:44:49", "remaining_time": "0:10:49"}
+{"current_steps": 2490, "total_steps": 2643, "loss": 0.09, "lr": 5.089671787579936e-08, "epoch": 2.8263337116912597, "percentage": 94.21, "elapsed_time": "2:45:31", "remaining_time": "0:10:10"}
+{"current_steps": 2500, "total_steps": 2643, "loss": 0.0511, "lr": 4.448013324296646e-08, "epoch": 2.837684449489217, "percentage": 94.59, "elapsed_time": "2:46:12", "remaining_time": "0:09:30"}
+{"current_steps": 2510, "total_steps": 2643, "loss": 0.0278, "lr": 3.849211013682658e-08, "epoch": 2.8490351872871735, "percentage": 94.97, "elapsed_time": "2:46:52", "remaining_time": "0:08:50"}
+{"current_steps": 2520, "total_steps": 2643, "loss": 0.0411, "lr": 3.293369364618465e-08, "epoch": 2.8603859250851307, "percentage": 95.35, "elapsed_time": "2:47:31", "remaining_time": "0:08:10"}
+{"current_steps": 2530, "total_steps": 2643, "loss": 0.0527, "lr": 2.780585388066581e-08, "epoch": 2.8717366628830874, "percentage": 95.72, "elapsed_time": "2:48:12", "remaining_time": "0:07:30"}
+{"current_steps": 2540, "total_steps": 2643, "loss": 0.0313, "lr": 2.3109485801402208e-08, "epoch": 2.8830874006810445, "percentage": 96.1, "elapsed_time": "2:48:55", "remaining_time": "0:06:51"}
+{"current_steps": 2550, "total_steps": 2643, "loss": 0.0344, "lr": 1.8845409064833787e-08, "epoch": 2.894438138479001, "percentage": 96.48, "elapsed_time": "2:49:34", "remaining_time": "0:06:11"}
+{"current_steps": 2560, "total_steps": 2643, "loss": 0.052, "lr": 1.5014367879655765e-08, "epoch": 2.905788876276958, "percentage": 96.86, "elapsed_time": "2:50:19", "remaining_time": "0:05:31"}
+{"current_steps": 2570, "total_steps": 2643, "loss": 0.0398, "lr": 1.1617030876932001e-08, "epoch": 2.917139614074915, "percentage": 97.24, "elapsed_time": "2:51:00", "remaining_time": "0:04:51"}
+{"current_steps": 2580, "total_steps": 2643, "loss": 0.0711, "lr": 8.653990993396921e-09, "epoch": 2.9284903518728718, "percentage": 97.62, "elapsed_time": "2:51:36", "remaining_time": "0:04:11"}
+{"current_steps": 2590, "total_steps": 2643, "loss": 0.0641, "lr": 6.125765367972492e-09, "epoch": 2.9398410896708285, "percentage": 97.99, "elapsed_time": "2:52:17", "remaining_time": "0:03:31"}
+{"current_steps": 2600, "total_steps": 2643, "loss": 0.0095, "lr": 4.032795251510957e-09, "epoch": 2.9511918274687856, "percentage": 98.37, "elapsed_time": "2:52:53", "remaining_time": "0:02:51"}
+{"current_steps": 2610, "total_steps": 2643, "loss": 0.0419, "lr": 2.3754459297833932e-09, "epoch": 2.9625425652667423, "percentage": 98.75, "elapsed_time": "2:53:31", "remaining_time": "0:02:11"}
+{"current_steps": 2620, "total_steps": 2643, "loss": 0.1211, "lr": 1.1540066597270916e-09, "epoch": 2.973893303064699, "percentage": 99.13, "elapsed_time": "2:54:09", "remaining_time": "0:01:31"}
+{"current_steps": 2630, "total_steps": 2643, "loss": 0.0493, "lr": 3.6869061896066536e-10, "epoch": 2.985244040862656, "percentage": 99.51, "elapsed_time": "2:54:55", "remaining_time": "0:00:51"}
+{"current_steps": 2640, "total_steps": 2643, "loss": 0.0414, "lr": 1.9634868579365696e-11, "epoch": 2.996594778660613, "percentage": 99.89, "elapsed_time": "2:55:35", "remaining_time": "0:00:11"}
+{"current_steps": 2643, "total_steps": 2643, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:56:38", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1890 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2643,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011350737797956867,
+      "grad_norm": 1698.2979187914962,
+      "learning_rate": 1.886792452830189e-07,
+      "loss": 11.4349,
+      "step": 10
+    },
+    {
+      "epoch": 0.022701475595913734,
+      "grad_norm": 1715.9478636120436,
+      "learning_rate": 3.773584905660378e-07,
+      "loss": 10.7287,
+      "step": 20
+    },
+    {
+      "epoch": 0.0340522133938706,
+      "grad_norm": 357.11923483514187,
+      "learning_rate": 5.660377358490567e-07,
+      "loss": 7.9114,
+      "step": 30
+    },
+    {
+      "epoch": 0.04540295119182747,
+      "grad_norm": 204.4272724165726,
+      "learning_rate": 7.547169811320755e-07,
+      "loss": 5.3773,
+      "step": 40
+    },
+    {
+      "epoch": 0.056753688989784334,
+      "grad_norm": 114.04670191645393,
+      "learning_rate": 9.433962264150944e-07,
+      "loss": 4.1808,
+      "step": 50
+    },
+    {
+      "epoch": 0.0681044267877412,
+      "grad_norm": 97.74863975137248,
+      "learning_rate": 1.1320754716981133e-06,
+      "loss": 3.391,
+      "step": 60
+    },
+    {
+      "epoch": 0.07945516458569807,
+      "grad_norm": 83.85826671008647,
+      "learning_rate": 1.3207547169811322e-06,
+      "loss": 2.9224,
+      "step": 70
+    },
+    {
+      "epoch": 0.09080590238365494,
+      "grad_norm": 81.81468518019015,
+      "learning_rate": 1.509433962264151e-06,
+      "loss": 2.7385,
+      "step": 80
+    },
+    {
+      "epoch": 0.1021566401816118,
+      "grad_norm": 81.12682810087568,
+      "learning_rate": 1.6981132075471698e-06,
+      "loss": 2.5178,
+      "step": 90
+    },
+    {
+      "epoch": 0.11350737797956867,
+      "grad_norm": 80.85347421686487,
+      "learning_rate": 1.8867924528301889e-06,
+      "loss": 2.2834,
+      "step": 100
+    },
+    {
+      "epoch": 0.12485811577752554,
+      "grad_norm": 82.47614053239027,
+      "learning_rate": 2.075471698113208e-06,
+      "loss": 2.0212,
+      "step": 110
+    },
+    {
+      "epoch": 0.1362088535754824,
+      "grad_norm": 86.62520026408484,
+      "learning_rate": 2.2641509433962266e-06,
+      "loss": 1.7334,
+      "step": 120
+    },
+    {
+      "epoch": 0.14755959137343927,
+      "grad_norm": 80.45183334276052,
+      "learning_rate": 2.4528301886792453e-06,
+      "loss": 1.4777,
+      "step": 130
+    },
+    {
+      "epoch": 0.15891032917139614,
+      "grad_norm": 79.21574368328108,
+      "learning_rate": 2.6415094339622644e-06,
+      "loss": 1.1486,
+      "step": 140
+    },
+    {
+      "epoch": 0.170261066969353,
+      "grad_norm": 74.01719011960272,
+      "learning_rate": 2.830188679245283e-06,
+      "loss": 0.8411,
+      "step": 150
+    },
+    {
+      "epoch": 0.18161180476730987,
+      "grad_norm": 51.89253929462267,
+      "learning_rate": 3.018867924528302e-06,
+      "loss": 0.5991,
+      "step": 160
+    },
+    {
+      "epoch": 0.19296254256526674,
+      "grad_norm": 32.21614195805101,
+      "learning_rate": 3.207547169811321e-06,
+      "loss": 0.3447,
+      "step": 170
+    },
+    {
+      "epoch": 0.2043132803632236,
+      "grad_norm": 19.001109449561184,
+      "learning_rate": 3.3962264150943395e-06,
+      "loss": 0.2428,
+      "step": 180
+    },
+    {
+      "epoch": 0.21566401816118047,
+      "grad_norm": 13.591403736514234,
+      "learning_rate": 3.5849056603773586e-06,
+      "loss": 0.2239,
+      "step": 190
+    },
+    {
+      "epoch": 0.22701475595913734,
+      "grad_norm": 13.448898680419939,
+      "learning_rate": 3.7735849056603777e-06,
+      "loss": 0.1635,
+      "step": 200
+    },
+    {
+      "epoch": 0.2383654937570942,
+      "grad_norm": 36.227059302392355,
+      "learning_rate": 3.962264150943396e-06,
+      "loss": 0.1634,
+      "step": 210
+    },
+    {
+      "epoch": 0.24971623155505107,
+      "grad_norm": 7.663015541152662,
+      "learning_rate": 4.150943396226416e-06,
+      "loss": 0.2969,
+      "step": 220
+    },
+    {
+      "epoch": 0.26106696935300794,
+      "grad_norm": 14.54749266726622,
+      "learning_rate": 4.339622641509435e-06,
+      "loss": 0.1923,
+      "step": 230
+    },
+    {
+      "epoch": 0.2724177071509648,
+      "grad_norm": 2.313868847454448,
+      "learning_rate": 4.528301886792453e-06,
+      "loss": 0.173,
+      "step": 240
+    },
+    {
+      "epoch": 0.28376844494892167,
+      "grad_norm": 6.460084440691116,
+      "learning_rate": 4.716981132075472e-06,
+      "loss": 0.1752,
+      "step": 250
+    },
+    {
+      "epoch": 0.29511918274687854,
+      "grad_norm": 2.0859035921114373,
+      "learning_rate": 4.905660377358491e-06,
+      "loss": 0.1466,
+      "step": 260
+    },
+    {
+      "epoch": 0.3064699205448354,
+      "grad_norm": 6.562559706748138,
+      "learning_rate": 4.999945458825315e-06,
+      "loss": 0.2425,
+      "step": 270
+    },
+    {
+      "epoch": 0.3178206583427923,
+      "grad_norm": 12.775706641336116,
+      "learning_rate": 4.999509143706472e-06,
+      "loss": 0.159,
+      "step": 280
+    },
+    {
+      "epoch": 0.32917139614074914,
+      "grad_norm": 6.317651713345659,
+      "learning_rate": 4.998636589618803e-06,
+      "loss": 0.1815,
+      "step": 290
+    },
+    {
+      "epoch": 0.340522133938706,
+      "grad_norm": 1.5036062720791235,
+      "learning_rate": 4.997327948849044e-06,
+      "loss": 0.1312,
+      "step": 300
+    },
+    {
+      "epoch": 0.3518728717366629,
+      "grad_norm": 6.030878230884589,
+      "learning_rate": 4.995583449794081e-06,
+      "loss": 0.1921,
+      "step": 310
+    },
+    {
+      "epoch": 0.36322360953461974,
+      "grad_norm": 10.37100502274357,
+      "learning_rate": 4.993403396921082e-06,
+      "loss": 0.1768,
+      "step": 320
+    },
+    {
+      "epoch": 0.3745743473325766,
+      "grad_norm": 3.8501803420046756,
+      "learning_rate": 4.990788170714355e-06,
+      "loss": 0.1714,
+      "step": 330
+    },
+    {
+      "epoch": 0.3859250851305335,
+      "grad_norm": 11.372431671658788,
+      "learning_rate": 4.987738227608954e-06,
+      "loss": 0.1445,
+      "step": 340
+    },
+    {
+      "epoch": 0.39727582292849034,
+      "grad_norm": 14.259075499950056,
+      "learning_rate": 4.984254099911009e-06,
+      "loss": 0.1337,
+      "step": 350
+    },
+    {
+      "epoch": 0.4086265607264472,
+      "grad_norm": 9.445055852659305,
+      "learning_rate": 4.98033639570482e-06,
+      "loss": 0.1908,
+      "step": 360
+    },
+    {
+      "epoch": 0.4199772985244041,
+      "grad_norm": 10.699934111645568,
+      "learning_rate": 4.975985798746736e-06,
+      "loss": 0.1582,
+      "step": 370
+    },
+    {
+      "epoch": 0.43132803632236094,
+      "grad_norm": 2.0231358005945377,
+      "learning_rate": 4.971203068345811e-06,
+      "loss": 0.1693,
+      "step": 380
+    },
+    {
+      "epoch": 0.4426787741203178,
+      "grad_norm": 2.862769306726289,
+      "learning_rate": 4.9659890392312935e-06,
+      "loss": 0.1872,
+      "step": 390
+    },
+    {
+      "epoch": 0.4540295119182747,
+      "grad_norm": 12.285642072800846,
+      "learning_rate": 4.960344621406927e-06,
+      "loss": 0.1687,
+      "step": 400
+    },
+    {
+      "epoch": 0.46538024971623154,
+      "grad_norm": 3.344948970261047,
+      "learning_rate": 4.954270799992138e-06,
+      "loss": 0.1842,
+      "step": 410
+    },
+    {
+      "epoch": 0.4767309875141884,
+      "grad_norm": 10.259497150782368,
+      "learning_rate": 4.947768635050098e-06,
+      "loss": 0.13,
+      "step": 420
+    },
+    {
+      "epoch": 0.4880817253121453,
+      "grad_norm": 3.790249696004914,
+      "learning_rate": 4.940839261402711e-06,
+      "loss": 0.2288,
+      "step": 430
+    },
+    {
+      "epoch": 0.49943246311010214,
+      "grad_norm": 5.501844538152769,
+      "learning_rate": 4.933483888432558e-06,
+      "loss": 0.0884,
+      "step": 440
+    },
+    {
+      "epoch": 0.5107832009080591,
+      "grad_norm": 4.577226609737793,
+      "learning_rate": 4.925703799871818e-06,
+      "loss": 0.1534,
+      "step": 450
+    },
+    {
+      "epoch": 0.5221339387060159,
+      "grad_norm": 6.504007138408929,
+      "learning_rate": 4.91750035357822e-06,
+      "loss": 0.1884,
+      "step": 460
+    },
+    {
+      "epoch": 0.5334846765039728,
+      "grad_norm": 9.703964220834072,
+      "learning_rate": 4.908874981298058e-06,
+      "loss": 0.1373,
+      "step": 470
+    },
+    {
+      "epoch": 0.5448354143019296,
+      "grad_norm": 6.729985856749859,
+      "learning_rate": 4.899829188416306e-06,
+      "loss": 0.2131,
+      "step": 480
+    },
+    {
+      "epoch": 0.5561861520998865,
+      "grad_norm": 10.837103551470959,
+      "learning_rate": 4.890364553693886e-06,
+      "loss": 0.1385,
+      "step": 490
+    },
+    {
+      "epoch": 0.5675368898978433,
+      "grad_norm": 5.681784964714727,
+      "learning_rate": 4.880482728992126e-06,
+      "loss": 0.1326,
+      "step": 500
+    },
+    {
+      "epoch": 0.5788876276958003,
+      "grad_norm": 7.269735955872282,
+      "learning_rate": 4.870185438984458e-06,
+      "loss": 0.1697,
+      "step": 510
+    },
+    {
+      "epoch": 0.5902383654937571,
+      "grad_norm": 2.714819037626597,
+      "learning_rate": 4.859474480855417e-06,
+      "loss": 0.1196,
+      "step": 520
+    },
+    {
+      "epoch": 0.601589103291714,
+      "grad_norm": 4.859213826030436,
+      "learning_rate": 4.848351723986974e-06,
+      "loss": 0.1278,
+      "step": 530
+    },
+    {
+      "epoch": 0.6129398410896708,
+      "grad_norm": 5.451460876916098,
+      "learning_rate": 4.8368191096322734e-06,
+      "loss": 0.1383,
+      "step": 540
+    },
+    {
+      "epoch": 0.6242905788876277,
+      "grad_norm": 6.638147694909045,
+      "learning_rate": 4.824878650576829e-06,
+      "loss": 0.1235,
+      "step": 550
+    },
+    {
+      "epoch": 0.6356413166855845,
+      "grad_norm": 1.7580573391181251,
+      "learning_rate": 4.81253243078723e-06,
+      "loss": 0.1495,
+      "step": 560
+    },
+    {
+      "epoch": 0.6469920544835415,
+      "grad_norm": 4.496989393019484,
+      "learning_rate": 4.7997826050474284e-06,
+      "loss": 0.1127,
+      "step": 570
+    },
+    {
+      "epoch": 0.6583427922814983,
+      "grad_norm": 2.446667502094507,
+      "learning_rate": 4.786631398582663e-06,
+      "loss": 0.1749,
+      "step": 580
+    },
+    {
+      "epoch": 0.6696935300794552,
+      "grad_norm": 6.832338256010423,
+      "learning_rate": 4.773081106671094e-06,
+      "loss": 0.1344,
+      "step": 590
+    },
+    {
+      "epoch": 0.681044267877412,
+      "grad_norm": 7.1481219400148435,
+      "learning_rate": 4.759134094243206e-06,
+      "loss": 0.1188,
+      "step": 600
+    },
+    {
+      "epoch": 0.6923950056753689,
+      "grad_norm": 2.2164696749091353,
+      "learning_rate": 4.744792795469058e-06,
+      "loss": 0.1461,
+      "step": 610
+    },
+    {
+      "epoch": 0.7037457434733257,
+      "grad_norm": 7.191845232523166,
+      "learning_rate": 4.730059713333448e-06,
+      "loss": 0.1846,
+      "step": 620
+    },
+    {
+      "epoch": 0.7150964812712827,
+      "grad_norm": 1.4136399900098233,
+      "learning_rate": 4.714937419199067e-06,
+      "loss": 0.1325,
+      "step": 630
+    },
+    {
+      "epoch": 0.7264472190692395,
+      "grad_norm": 4.299537462900032,
+      "learning_rate": 4.69942855235772e-06,
+      "loss": 0.1352,
+      "step": 640
+    },
+    {
+      "epoch": 0.7377979568671964,
+      "grad_norm": 1.0384507478186595,
+      "learning_rate": 4.683535819569691e-06,
+      "loss": 0.1362,
+      "step": 650
+    },
+    {
+      "epoch": 0.7491486946651532,
+      "grad_norm": 13.982613118228628,
+      "learning_rate": 4.667261994591331e-06,
+      "loss": 0.1706,
+      "step": 660
+    },
+    {
+      "epoch": 0.7604994324631101,
+      "grad_norm": 3.227347083041028,
+      "learning_rate": 4.650609917690957e-06,
+      "loss": 0.1208,
+      "step": 670
+    },
+    {
+      "epoch": 0.771850170261067,
+      "grad_norm": 4.080502292732569,
+      "learning_rate": 4.633582495153137e-06,
+      "loss": 0.1516,
+      "step": 680
+    },
+    {
+      "epoch": 0.7832009080590239,
+      "grad_norm": 8.485813586268012,
+      "learning_rate": 4.616182698771463e-06,
+      "loss": 0.1419,
+      "step": 690
+    },
+    {
+      "epoch": 0.7945516458569807,
+      "grad_norm": 1.4110543221413474,
+      "learning_rate": 4.598413565329876e-06,
+      "loss": 0.1327,
+      "step": 700
+    },
+    {
+      "epoch": 0.8059023836549376,
+      "grad_norm": 5.188520387076118,
+      "learning_rate": 4.58027819607266e-06,
+      "loss": 0.1438,
+      "step": 710
+    },
+    {
+      "epoch": 0.8172531214528944,
+      "grad_norm": 14.402414909123417,
+      "learning_rate": 4.5617797561631885e-06,
+      "loss": 0.1214,
+      "step": 720
+    },
+    {
+      "epoch": 0.8286038592508513,
+      "grad_norm": 3.2887042762187364,
+      "learning_rate": 4.542921474131497e-06,
+      "loss": 0.1516,
+      "step": 730
+    },
+    {
+      "epoch": 0.8399545970488081,
+      "grad_norm": 8.950465768826493,
+      "learning_rate": 4.523706641310817e-06,
+      "loss": 0.1339,
+      "step": 740
+    },
+    {
+      "epoch": 0.8513053348467651,
+      "grad_norm": 7.132814447263203,
+      "learning_rate": 4.5041386112631394e-06,
+      "loss": 0.1061,
+      "step": 750
+    },
+    {
+      "epoch": 0.8626560726447219,
+      "grad_norm": 9.762861748224212,
+      "learning_rate": 4.484220799193913e-06,
+      "loss": 0.1011,
+      "step": 760
+    },
+    {
+      "epoch": 0.8740068104426788,
+      "grad_norm": 14.288034605598874,
+      "learning_rate": 4.463956681355993e-06,
+      "loss": 0.1298,
+      "step": 770
+    },
+    {
+      "epoch": 0.8853575482406356,
+      "grad_norm": 2.8446847525051524,
+      "learning_rate": 4.4433497944429325e-06,
+      "loss": 0.1203,
+      "step": 780
+    },
+    {
+      "epoch": 0.8967082860385925,
+      "grad_norm": 1.479832068691713,
+      "learning_rate": 4.422403734971718e-06,
+      "loss": 0.1289,
+      "step": 790
+    },
+    {
+      "epoch": 0.9080590238365494,
+      "grad_norm": 9.186524889671574,
+      "learning_rate": 4.401122158655076e-06,
+      "loss": 0.1039,
+      "step": 800
+    },
+    {
+      "epoch": 0.9194097616345063,
+      "grad_norm": 1.7652174707129338,
+      "learning_rate": 4.379508779763438e-06,
+      "loss": 0.142,
+      "step": 810
+    },
+    {
+      "epoch": 0.9307604994324631,
+      "grad_norm": 2.3999930262675524,
+      "learning_rate": 4.357567370476693e-06,
+      "loss": 0.1483,
+      "step": 820
+    },
+    {
+      "epoch": 0.94211123723042,
+      "grad_norm": 2.0203809635081216,
+      "learning_rate": 4.335301760225824e-06,
+      "loss": 0.1388,
+      "step": 830
+    },
+    {
+      "epoch": 0.9534619750283768,
+      "grad_norm": 6.570252196832083,
+      "learning_rate": 4.312715835024565e-06,
+      "loss": 0.1132,
+      "step": 840
+    },
+    {
+      "epoch": 0.9648127128263337,
+      "grad_norm": 8.694169049942309,
+      "learning_rate": 4.289813536791168e-06,
+      "loss": 0.0886,
+      "step": 850
+    },
+    {
+      "epoch": 0.9761634506242906,
+      "grad_norm": 0.665758848556138,
+      "learning_rate": 4.2665988626604285e-06,
+      "loss": 0.1119,
+      "step": 860
+    },
+    {
+      "epoch": 0.9875141884222475,
+      "grad_norm": 3.408206675708319,
+      "learning_rate": 4.243075864286059e-06,
+      "loss": 0.1049,
+      "step": 870
+    },
+    {
+      "epoch": 0.9988649262202043,
+      "grad_norm": 6.496904281473155,
+      "learning_rate": 4.219248647133559e-06,
+      "loss": 0.1067,
+      "step": 880
+    },
+    {
+      "epoch": 1.0102156640181612,
+      "grad_norm": 6.318482209546192,
+      "learning_rate": 4.195121369763687e-06,
+      "loss": 0.1328,
+      "step": 890
+    },
+    {
+      "epoch": 1.0215664018161181,
+      "grad_norm": 0.12366856429278299,
+      "learning_rate": 4.170698243106668e-06,
+      "loss": 0.0789,
+      "step": 900
+    },
+    {
+      "epoch": 1.0329171396140748,
+      "grad_norm": 2.892704125187497,
+      "learning_rate": 4.14598352972726e-06,
+      "loss": 0.1287,
+      "step": 910
+    },
+    {
+      "epoch": 1.0442678774120318,
+      "grad_norm": 10.213754089778735,
+      "learning_rate": 4.12098154308081e-06,
+      "loss": 0.1924,
+      "step": 920
+    },
+    {
+      "epoch": 1.0556186152099887,
+      "grad_norm": 7.247963791700357,
+      "learning_rate": 4.095696646760425e-06,
+      "loss": 0.0995,
+      "step": 930
+    },
+    {
+      "epoch": 1.0669693530079456,
+      "grad_norm": 4.929548257635512,
+      "learning_rate": 4.070133253735399e-06,
+      "loss": 0.0985,
+      "step": 940
+    },
+    {
+      "epoch": 1.0783200908059023,
+      "grad_norm": 6.123766237774935,
+      "learning_rate": 4.044295825581013e-06,
+      "loss": 0.0467,
+      "step": 950
+    },
+    {
+      "epoch": 1.0896708286038592,
+      "grad_norm": 4.7904026758844855,
+      "learning_rate": 4.018188871699861e-06,
+      "loss": 0.2061,
+      "step": 960
+    },
+    {
+      "epoch": 1.1010215664018161,
+      "grad_norm": 0.6786343511201274,
+      "learning_rate": 3.991816948534823e-06,
+      "loss": 0.1263,
+      "step": 970
+    },
+    {
+      "epoch": 1.112372304199773,
+      "grad_norm": 4.293100093143904,
+      "learning_rate": 3.965184658773828e-06,
+      "loss": 0.1175,
+      "step": 980
+    },
+    {
+      "epoch": 1.1237230419977298,
+      "grad_norm": 3.375509232222427,
+      "learning_rate": 3.938296650546552e-06,
+      "loss": 0.1199,
+      "step": 990
+    },
+    {
+      "epoch": 1.1350737797956867,
+      "grad_norm": 3.6936463749871487,
+      "learning_rate": 3.911157616613176e-06,
+      "loss": 0.1169,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1464245175936436,
+      "grad_norm": 5.033595510215138,
+      "learning_rate": 3.8837722935453615e-06,
+      "loss": 0.1326,
+      "step": 1010
+    },
+    {
+      "epoch": 1.1577752553916005,
+      "grad_norm": 1.1806777716425099,
+      "learning_rate": 3.8561454608995765e-06,
+      "loss": 0.1049,
+      "step": 1020
+    },
+    {
+      "epoch": 1.1691259931895572,
+      "grad_norm": 5.613945679887687,
+      "learning_rate": 3.828281940382923e-06,
+      "loss": 0.0978,
+      "step": 1030
+    },
+    {
+      "epoch": 1.1804767309875142,
+      "grad_norm": 11.074114312002287,
+      "learning_rate": 3.800186595011599e-06,
+      "loss": 0.19,
+      "step": 1040
+    },
+    {
+      "epoch": 1.191827468785471,
+      "grad_norm": 6.543875702026283,
+      "learning_rate": 3.7718643282621648e-06,
+      "loss": 0.1121,
+      "step": 1050
+    },
+    {
+      "epoch": 1.203178206583428,
+      "grad_norm": 4.830576085274986,
+      "learning_rate": 3.7433200832157333e-06,
+      "loss": 0.1125,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2145289443813847,
+      "grad_norm": 1.1695778203493483,
+      "learning_rate": 3.714558841695258e-06,
+      "loss": 0.144,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2258796821793416,
+      "grad_norm": 3.4535216961458275,
+      "learning_rate": 3.685585623396055e-06,
+      "loss": 0.159,
+      "step": 1080
+    },
+    {
+      "epoch": 1.2372304199772985,
+      "grad_norm": 5.495394022771164,
+      "learning_rate": 3.656405485009719e-06,
+      "loss": 0.1044,
+      "step": 1090
+    },
+    {
+      "epoch": 1.2485811577752555,
+      "grad_norm": 1.632127452923236,
+      "learning_rate": 3.6270235193415754e-06,
+      "loss": 0.0954,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2599318955732124,
+      "grad_norm": 22.50519126324992,
+      "learning_rate": 3.597444854421837e-06,
+      "loss": 0.1576,
+      "step": 1110
+    },
+    {
+      "epoch": 1.271282633371169,
+      "grad_norm": 1.3800511219133857,
+      "learning_rate": 3.5676746526106084e-06,
+      "loss": 0.1081,
+      "step": 1120
+    },
+    {
+      "epoch": 1.282633371169126,
+      "grad_norm": 9.384054185672928,
+      "learning_rate": 3.537718109696899e-06,
+      "loss": 0.0688,
+      "step": 1130
+    },
+    {
+      "epoch": 1.293984108967083,
+      "grad_norm": 8.609201641981887,
+      "learning_rate": 3.5075804539918047e-06,
+      "loss": 0.1562,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3053348467650396,
+      "grad_norm": 10.72094281108933,
+      "learning_rate": 3.4772669454160113e-06,
+      "loss": 0.0616,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3166855845629966,
+      "grad_norm": 1.033026440388663,
+      "learning_rate": 3.44678287458178e-06,
+      "loss": 0.1002,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3280363223609535,
+      "grad_norm": 6.3993440529706,
+      "learning_rate": 3.4161335618695774e-06,
+      "loss": 0.0992,
+      "step": 1170
+    },
+    {
+      "epoch": 1.3393870601589104,
+      "grad_norm": 5.7196887859906695,
+      "learning_rate": 3.385324356499513e-06,
+      "loss": 0.1226,
+      "step": 1180
+    },
+    {
+      "epoch": 1.3507377979568673,
+      "grad_norm": 3.558047516816503,
+      "learning_rate": 3.3543606355977377e-06,
+      "loss": 0.0733,
+      "step": 1190
+    },
+    {
+      "epoch": 1.362088535754824,
+      "grad_norm": 3.417141923587784,
+      "learning_rate": 3.3232478032579746e-06,
+      "loss": 0.1127,
+      "step": 1200
+    },
+    {
+      "epoch": 1.373439273552781,
+      "grad_norm": 1.4667598966411892,
+      "learning_rate": 3.291991289598347e-06,
+      "loss": 0.1209,
+      "step": 1210
+    },
+    {
+      "epoch": 1.3847900113507379,
+      "grad_norm": 10.429323033457198,
+      "learning_rate": 3.2605965498136554e-06,
+      "loss": 0.086,
+      "step": 1220
+    },
+    {
+      "epoch": 1.3961407491486946,
+      "grad_norm": 0.6593997341635577,
+      "learning_rate": 3.229069063223289e-06,
+      "loss": 0.1225,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4074914869466515,
+      "grad_norm": 5.189796586998311,
+      "learning_rate": 3.197414332314914e-06,
+      "loss": 0.0741,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4188422247446084,
+      "grad_norm": 5.315717279596233,
+      "learning_rate": 3.165637881784133e-06,
+      "loss": 0.1664,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4301929625425653,
+      "grad_norm": 2.5922568372048396,
+      "learning_rate": 3.133745257570253e-06,
+      "loss": 0.1355,
+      "step": 1260
+    },
+    {
+      "epoch": 1.4415437003405223,
+      "grad_norm": 4.807463414524541,
+      "learning_rate": 3.1017420258883607e-06,
+      "loss": 0.0945,
+      "step": 1270
+    },
+    {
+      "epoch": 1.452894438138479,
+      "grad_norm": 6.3118612924547755,
+      "learning_rate": 3.0696337722578444e-06,
+      "loss": 0.1288,
+      "step": 1280
+    },
+    {
+      "epoch": 1.4642451759364359,
+      "grad_norm": 4.9487309557769334,
+      "learning_rate": 3.0374261005275606e-06,
+      "loss": 0.0707,
+      "step": 1290
+    },
+    {
+      "epoch": 1.4755959137343928,
+      "grad_norm": 2.742348930372723,
+      "learning_rate": 3.0051246318977913e-06,
+      "loss": 0.1143,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4869466515323495,
+      "grad_norm": 4.751757205070613,
+      "learning_rate": 2.9727350039391782e-06,
+      "loss": 0.0805,
+      "step": 1310
+    },
+    {
+      "epoch": 1.4982973893303064,
+      "grad_norm": 4.196706305756519,
+      "learning_rate": 2.940262869608798e-06,
+      "loss": 0.0943,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5096481271282634,
+      "grad_norm": 3.2942511414526443,
+      "learning_rate": 2.907713896263551e-06,
+      "loss": 0.0564,
+      "step": 1330
+    },
+    {
+      "epoch": 1.52099886492622,
+      "grad_norm": 14.11917089724621,
+      "learning_rate": 2.8750937646710416e-06,
+      "loss": 0.0471,
+      "step": 1340
+    },
+    {
+      "epoch": 1.5323496027241772,
+      "grad_norm": 0.5572781856983822,
+      "learning_rate": 2.842408168018112e-06,
+      "loss": 0.1026,
+      "step": 1350
+    },
+    {
+      "epoch": 1.543700340522134,
+      "grad_norm": 4.8778881968669525,
+      "learning_rate": 2.8096628109172125e-06,
+      "loss": 0.0858,
+      "step": 1360
+    },
+    {
+      "epoch": 1.5550510783200908,
+      "grad_norm": 3.462366587313288,
+      "learning_rate": 2.7768634084107736e-06,
+      "loss": 0.1614,
+      "step": 1370
+    },
+    {
+      "epoch": 1.5664018161180477,
+      "grad_norm": 1.741346685901154,
+      "learning_rate": 2.744015684973766e-06,
+      "loss": 0.0271,
+      "step": 1380
+    },
+    {
+      "epoch": 1.5777525539160044,
+      "grad_norm": 0.3396882513904551,
+      "learning_rate": 2.711125373514602e-06,
+      "loss": 0.1021,
+      "step": 1390
+    },
+    {
+      "epoch": 1.5891032917139614,
+      "grad_norm": 0.8760532067910843,
+      "learning_rate": 2.6781982143745776e-06,
+      "loss": 0.1074,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6004540295119183,
+      "grad_norm": 5.835360058589467,
+      "learning_rate": 2.645239954326009e-06,
+      "loss": 0.1118,
+      "step": 1410
+    },
+    {
+      "epoch": 1.611804767309875,
+      "grad_norm": 1.5184172732893502,
+      "learning_rate": 2.6122563455692467e-06,
+      "loss": 0.0898,
+      "step": 1420
+    },
+    {
+      "epoch": 1.6231555051078321,
+      "grad_norm": 0.8829766157224805,
+      "learning_rate": 2.5792531447287515e-06,
+      "loss": 0.0668,
+      "step": 1430
+    },
+    {
+      "epoch": 1.6345062429057888,
+      "grad_norm": 4.567945936076311,
+      "learning_rate": 2.546236111848387e-06,
+      "loss": 0.1002,
+      "step": 1440
+    },
+    {
+      "epoch": 1.6458569807037458,
+      "grad_norm": 5.924471519919804,
+      "learning_rate": 2.5132110093861174e-06,
+      "loss": 0.0915,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6572077185017027,
+      "grad_norm": 5.241948497812272,
+      "learning_rate": 2.480183601208293e-06,
+      "loss": 0.0728,
+      "step": 1460
+    },
+    {
+      "epoch": 1.6685584562996594,
+      "grad_norm": 0.9103309238230624,
+      "learning_rate": 2.4471596515836797e-06,
+      "loss": 0.0832,
+      "step": 1470
+    },
+    {
+      "epoch": 1.6799091940976163,
+      "grad_norm": 5.902192630082476,
+      "learning_rate": 2.414144924177422e-06,
+      "loss": 0.0992,
+      "step": 1480
+    },
+    {
+      "epoch": 1.6912599318955732,
+      "grad_norm": 5.542753149797352,
+      "learning_rate": 2.3811451810451132e-06,
+      "loss": 0.1376,
+      "step": 1490
+    },
+    {
+      "epoch": 1.70261066969353,
+      "grad_norm": 2.079910130147066,
+      "learning_rate": 2.3481661816271413e-06,
+      "loss": 0.1048,
+      "step": 1500
+    },
+    {
+      "epoch": 1.713961407491487,
+      "grad_norm": 9.988363254853992,
+      "learning_rate": 2.3152136817434983e-06,
+      "loss": 0.1075,
+      "step": 1510
+    },
+    {
+      "epoch": 1.7253121452894438,
+      "grad_norm": 4.264471331176181,
+      "learning_rate": 2.2822934325892178e-06,
+      "loss": 0.1121,
+      "step": 1520
+    },
+    {
+      "epoch": 1.7366628830874007,
+      "grad_norm": 0.41819988751325843,
+      "learning_rate": 2.2494111797306146e-06,
+      "loss": 0.1009,
+      "step": 1530
+    },
+    {
+      "epoch": 1.7480136208853576,
+      "grad_norm": 3.129032071006884,
+      "learning_rate": 2.216572662102518e-06,
+      "loss": 0.1405,
+      "step": 1540
+    },
+    {
+      "epoch": 1.7593643586833143,
+      "grad_norm": 6.840381293999739,
+      "learning_rate": 2.1837836110066544e-06,
+      "loss": 0.1172,
+      "step": 1550
+    },
+    {
+      "epoch": 1.7707150964812712,
+      "grad_norm": 10.965691247426783,
+      "learning_rate": 2.151049749111361e-06,
+      "loss": 0.1048,
+      "step": 1560
+    },
+    {
+      "epoch": 1.7820658342792282,
+      "grad_norm": 3.350923692736231,
+      "learning_rate": 2.1183767894528135e-06,
+      "loss": 0.0631,
+      "step": 1570
+    },
+    {
+      "epoch": 1.7934165720771849,
+      "grad_norm": 2.386724332698608,
+      "learning_rate": 2.085770434437931e-06,
+      "loss": 0.0908,
+      "step": 1580
+    },
+    {
+      "epoch": 1.804767309875142,
+      "grad_norm": 2.7765578684736725,
+      "learning_rate": 2.053236374849128e-06,
+      "loss": 0.1064,
+      "step": 1590
+    },
+    {
+      "epoch": 1.8161180476730987,
+      "grad_norm": 2.1935113605962395,
+      "learning_rate": 2.0207802888511155e-06,
+      "loss": 0.0929,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8274687854710556,
+      "grad_norm": 1.6758715379011846,
+      "learning_rate": 1.988407840999881e-06,
+      "loss": 0.0941,
+      "step": 1610
+    },
+    {
+      "epoch": 1.8388195232690125,
+      "grad_norm": 1.248060350449922,
+      "learning_rate": 1.9561246812540572e-06,
+      "loss": 0.0907,
+      "step": 1620
+    },
+    {
+      "epoch": 1.8501702610669692,
+      "grad_norm": 1.7569330315190796,
+      "learning_rate": 1.923936443988841e-06,
+      "loss": 0.0793,
+      "step": 1630
+    },
+    {
+      "epoch": 1.8615209988649262,
+      "grad_norm": 1.037210865216885,
+      "learning_rate": 1.8918487470126207e-06,
+      "loss": 0.0758,
+      "step": 1640
+    },
+    {
+      "epoch": 1.872871736662883,
+      "grad_norm": 1.6171549381169084,
+      "learning_rate": 1.8598671905865002e-06,
+      "loss": 0.0648,
+      "step": 1650
+    },
+    {
+      "epoch": 1.8842224744608398,
+      "grad_norm": 1.0342795380634235,
+      "learning_rate": 1.8279973564468906e-06,
+      "loss": 0.1024,
+      "step": 1660
+    },
+    {
+      "epoch": 1.895573212258797,
+      "grad_norm": 2.8676197128323366,
+      "learning_rate": 1.7962448068313298e-06,
+      "loss": 0.0836,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9069239500567536,
+      "grad_norm": 4.038378184168931,
+      "learning_rate": 1.7646150835077014e-06,
+      "loss": 0.0969,
+      "step": 1680
+    },
+    {
+      "epoch": 1.9182746878547106,
+      "grad_norm": 3.9864637976794057,
+      "learning_rate": 1.733113706807038e-06,
+      "loss": 0.0756,
+      "step": 1690
+    },
+    {
+      "epoch": 1.9296254256526675,
+      "grad_norm": 0.20549930730007024,
+      "learning_rate": 1.7017461746600506e-06,
+      "loss": 0.124,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9409761634506242,
+      "grad_norm": 9.07668892500117,
+      "learning_rate": 1.670517961637582e-06,
+      "loss": 0.1292,
+      "step": 1710
+    },
+    {
+      "epoch": 1.952326901248581,
+      "grad_norm": 7.75514295416776,
+      "learning_rate": 1.6394345179951293e-06,
+      "loss": 0.0718,
+      "step": 1720
+    },
+    {
+      "epoch": 1.963677639046538,
+      "grad_norm": 3.9663573159802037,
+      "learning_rate": 1.6085012687216078e-06,
+      "loss": 0.0897,
+      "step": 1730
+    },
+    {
+      "epoch": 1.9750283768444947,
+      "grad_norm": 7.281368671013816,
+      "learning_rate": 1.5777236125925333e-06,
+      "loss": 0.1087,
+      "step": 1740
+    },
+    {
+      "epoch": 1.9863791146424519,
+      "grad_norm": 3.682988149304066,
+      "learning_rate": 1.5471069212277729e-06,
+      "loss": 0.0973,
+      "step": 1750
+    },
+    {
+      "epoch": 1.9977298524404086,
+      "grad_norm": 10.757901893388249,
+      "learning_rate": 1.516656538154035e-06,
+      "loss": 0.1185,
+      "step": 1760
+    },
+    {
+      "epoch": 2.0090805902383657,
+      "grad_norm": 3.9977547029166924,
+      "learning_rate": 1.4863777778722682e-06,
+      "loss": 0.0295,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0204313280363224,
+      "grad_norm": 0.3839917363760503,
+      "learning_rate": 1.4562759249301185e-06,
+      "loss": 0.0535,
+      "step": 1780
+    },
+    {
+      "epoch": 2.031782065834279,
+      "grad_norm": 0.04005398561849314,
+      "learning_rate": 1.4263562329996194e-06,
+      "loss": 0.0435,
+      "step": 1790
+    },
+    {
+      "epoch": 2.0431328036322363,
+      "grad_norm": 5.3004949945081,
+      "learning_rate": 1.396623923960271e-06,
+      "loss": 0.0444,
+      "step": 1800
+    },
+    {
+      "epoch": 2.054483541430193,
+      "grad_norm": 0.693308833242502,
+      "learning_rate": 1.367084186987663e-06,
+      "loss": 0.0738,
+      "step": 1810
+    },
+    {
+      "epoch": 2.0658342792281497,
+      "grad_norm": 2.38026116146638,
+      "learning_rate": 1.3377421776478111e-06,
+      "loss": 0.0413,
+      "step": 1820
+    },
+    {
+      "epoch": 2.077185017026107,
+      "grad_norm": 0.8248424564976408,
+      "learning_rate": 1.3086030169973552e-06,
+      "loss": 0.0777,
+      "step": 1830
+    },
+    {
+      "epoch": 2.0885357548240635,
+      "grad_norm": 0.7034274141736396,
+      "learning_rate": 1.2796717906897831e-06,
+      "loss": 0.0753,
+      "step": 1840
+    },
+    {
+      "epoch": 2.09988649262202,
+      "grad_norm": 5.594790712339865,
+      "learning_rate": 1.2509535480878325e-06,
+      "loss": 0.0217,
+      "step": 1850
+    },
+    {
+      "epoch": 2.1112372304199774,
+      "grad_norm": 2.267180272136545,
+      "learning_rate": 1.2224533013822237e-06,
+      "loss": 0.0787,
+      "step": 1860
+    },
+    {
+      "epoch": 2.122587968217934,
+      "grad_norm": 6.989338497656842,
+      "learning_rate": 1.1941760247168893e-06,
+      "loss": 0.0918,
+      "step": 1870
+    },
+    {
+      "epoch": 2.133938706015891,
+      "grad_norm": 8.671147847692886,
+      "learning_rate": 1.1661266533208274e-06,
+      "loss": 0.1123,
+      "step": 1880
+    },
+    {
+      "epoch": 2.145289443813848,
+      "grad_norm": 5.4698413382008395,
+      "learning_rate": 1.1383100826467653e-06,
+      "loss": 0.1148,
+      "step": 1890
+    },
+    {
+      "epoch": 2.1566401816118046,
+      "grad_norm": 0.22754634659047315,
+      "learning_rate": 1.1107311675167558e-06,
+      "loss": 0.0902,
+      "step": 1900
+    },
+    {
+      "epoch": 2.1679909194097617,
+      "grad_norm": 3.149990990261543,
+      "learning_rate": 1.0833947212748597e-06,
+      "loss": 0.0576,
+      "step": 1910
+    },
+    {
+      "epoch": 2.1793416572077184,
+      "grad_norm": 1.4213881249353393,
+      "learning_rate": 1.056305514947082e-06,
+      "loss": 0.0209,
+      "step": 1920
+    },
+    {
+      "epoch": 2.1906923950056756,
+      "grad_norm": 3.731385777873592,
+      "learning_rate": 1.0294682764086794e-06,
+      "loss": 0.0414,
+      "step": 1930
+    },
+    {
+      "epoch": 2.2020431328036323,
+      "grad_norm": 1.4005631532419822,
+      "learning_rate": 1.002887689559005e-06,
+      "loss": 0.0688,
+      "step": 1940
+    },
+    {
+      "epoch": 2.213393870601589,
+      "grad_norm": 5.277740757576594,
+      "learning_rate": 9.765683935040343e-07,
+      "loss": 0.0725,
+      "step": 1950
+    },
+    {
+      "epoch": 2.224744608399546,
+      "grad_norm": 0.23197604199738106,
+      "learning_rate": 9.505149817466952e-07,
+      "loss": 0.0867,
+      "step": 1960
+    },
+    {
+      "epoch": 2.236095346197503,
+      "grad_norm": 5.653129670824799,
+      "learning_rate": 9.247320013851663e-07,
+      "loss": 0.0995,
+      "step": 1970
+    },
+    {
+      "epoch": 2.2474460839954595,
+      "grad_norm": 0.38494105515318466,
+      "learning_rate": 8.992239523192778e-07,
+      "loss": 0.0742,
+      "step": 1980
+    },
+    {
+      "epoch": 2.2587968217934167,
+      "grad_norm": 5.78569357166171,
+      "learning_rate": 8.739952864651379e-07,
+      "loss": 0.048,
+      "step": 1990
+    },
+    {
+      "epoch": 2.2701475595913734,
+      "grad_norm": 0.8109906329530279,
+      "learning_rate": 8.490504069781444e-07,
+      "loss": 0.0612,
+      "step": 2000
+    },
+    {
+      "epoch": 2.28149829738933,
+      "grad_norm": 3.1195154688900244,
+      "learning_rate": 8.243936674845016e-07,
+      "loss": 0.0671,
+      "step": 2010
+    },
+    {
+      "epoch": 2.292849035187287,
+      "grad_norm": 0.20743083169700335,
+      "learning_rate": 8.000293713213798e-07,
+      "loss": 0.0607,
+      "step": 2020
+    },
+    {
+      "epoch": 2.304199772985244,
+      "grad_norm": 0.2315994749909462,
+      "learning_rate": 7.759617707858619e-07,
+      "loss": 0.0585,
+      "step": 2030
+    },
+    {
+      "epoch": 2.315550510783201,
+      "grad_norm": 0.048616209525463916,
+      "learning_rate": 7.521950663927824e-07,
+      "loss": 0.0358,
+      "step": 2040
+    },
+    {
+      "epoch": 2.3269012485811578,
+      "grad_norm": 4.235127505493877,
+      "learning_rate": 7.287334061416174e-07,
+      "loss": 0.0685,
+      "step": 2050
+    },
+    {
+      "epoch": 2.3382519863791145,
+      "grad_norm": 7.130061647365395,
+      "learning_rate": 7.055808847925316e-07,
+      "loss": 0.0798,
+      "step": 2060
+    },
+    {
+      "epoch": 2.3496027241770716,
+      "grad_norm": 5.280177307812628,
+      "learning_rate": 6.827415431517232e-07,
+      "loss": 0.0863,
+      "step": 2070
+    },
+    {
+      "epoch": 2.3609534619750283,
+      "grad_norm": 4.524586817903732,
+      "learning_rate": 6.602193673661805e-07,
+      "loss": 0.0741,
+      "step": 2080
+    },
+    {
+      "epoch": 2.3723041997729855,
+      "grad_norm": 6.615120826799002,
+      "learning_rate": 6.380182882279817e-07,
+      "loss": 0.0403,
+      "step": 2090
+    },
+    {
+      "epoch": 2.383654937570942,
+      "grad_norm": 7.204782892023176,
+      "learning_rate": 6.161421804882528e-07,
+      "loss": 0.0736,
+      "step": 2100
+    },
+    {
+      "epoch": 2.395005675368899,
+      "grad_norm": 4.652271416196355,
+      "learning_rate": 5.945948621809092e-07,
+      "loss": 0.0671,
+      "step": 2110
+    },
+    {
+      "epoch": 2.406356413166856,
+      "grad_norm": 7.364539748390817,
+      "learning_rate": 5.733800939562941e-07,
+      "loss": 0.0527,
+      "step": 2120
+    },
+    {
+      "epoch": 2.4177071509648127,
+      "grad_norm": 0.25707463242318057,
+      "learning_rate": 5.525015784248336e-07,
+      "loss": 0.0212,
+      "step": 2130
+    },
+    {
+      "epoch": 2.4290578887627694,
+      "grad_norm": 5.875818604365401,
+      "learning_rate": 5.319629595108189e-07,
+      "loss": 0.0411,
+      "step": 2140
+    },
+    {
+      "epoch": 2.4404086265607265,
+      "grad_norm": 0.7877520921047158,
+      "learning_rate": 5.117678218164337e-07,
+      "loss": 0.0386,
+      "step": 2150
+    },
+    {
+      "epoch": 2.4517593643586832,
+      "grad_norm": 10.800221983599814,
+      "learning_rate": 4.919196899961367e-07,
+      "loss": 0.0663,
+      "step": 2160
+    },
+    {
+      "epoch": 2.46311010215664,
+      "grad_norm": 1.3134487933959456,
+      "learning_rate": 4.724220281414979e-07,
+      "loss": 0.0314,
+      "step": 2170
+    },
+    {
+      "epoch": 2.474460839954597,
+      "grad_norm": 0.9855800151128657,
+      "learning_rate": 4.532782391766169e-07,
+      "loss": 0.0482,
+      "step": 2180
+    },
+    {
+      "epoch": 2.485811577752554,
+      "grad_norm": 0.0737715113639799,
+      "learning_rate": 4.344916642642108e-07,
+      "loss": 0.046,
+      "step": 2190
+    },
+    {
+      "epoch": 2.497162315550511,
+      "grad_norm": 7.1629316214213485,
+      "learning_rate": 4.1606558222247543e-07,
+      "loss": 0.1535,
+      "step": 2200
+    },
+    {
+      "epoch": 2.5085130533484676,
+      "grad_norm": 0.08329760250651277,
+      "learning_rate": 3.9800320895284264e-07,
+      "loss": 0.0618,
+      "step": 2210
+    },
+    {
+      "epoch": 2.519863791146425,
+      "grad_norm": 2.5343289285776853,
+      "learning_rate": 3.803076968787034e-07,
+      "loss": 0.0313,
+      "step": 2220
+    },
+    {
+      "epoch": 2.5312145289443815,
+      "grad_norm": 5.919205383656731,
+      "learning_rate": 3.629821343952147e-07,
+      "loss": 0.0379,
+      "step": 2230
+    },
+    {
+      "epoch": 2.542565266742338,
+      "grad_norm": 0.03881848686168996,
+      "learning_rate": 3.4602954533028946e-07,
+      "loss": 0.0483,
+      "step": 2240
+    },
+    {
+      "epoch": 2.5539160045402953,
+      "grad_norm": 0.18949910276010634,
+      "learning_rate": 3.2945288841684103e-07,
+      "loss": 0.0354,
+      "step": 2250
+    },
+    {
+      "epoch": 2.565266742338252,
+      "grad_norm": 4.662116015922482,
+      "learning_rate": 3.1325505677639977e-07,
+      "loss": 0.0608,
+      "step": 2260
+    },
+    {
+      "epoch": 2.5766174801362087,
+      "grad_norm": 10.323403528348715,
+      "learning_rate": 2.974388774141759e-07,
+      "loss": 0.053,
+      "step": 2270
+    },
+    {
+      "epoch": 2.587968217934166,
+      "grad_norm": 5.1188402568799845,
+      "learning_rate": 2.820071107256625e-07,
+      "loss": 0.0267,
+      "step": 2280
+    },
+    {
+      "epoch": 2.5993189557321226,
+      "grad_norm": 0.10111701455499049,
+      "learning_rate": 2.669624500148646e-07,
+      "loss": 0.0478,
+      "step": 2290
+    },
+    {
+      "epoch": 2.6106696935300793,
+      "grad_norm": 0.9800333714837519,
+      "learning_rate": 2.523075210242376e-07,
+      "loss": 0.0298,
+      "step": 2300
+    },
+    {
+      "epoch": 2.6220204313280364,
+      "grad_norm": 1.4782390039786926,
+      "learning_rate": 2.3804488147641443e-07,
+      "loss": 0.0663,
+      "step": 2310
+    },
+    {
+      "epoch": 2.633371169125993,
+      "grad_norm": 2.416909835102068,
+      "learning_rate": 2.241770206278107e-07,
+      "loss": 0.0189,
+      "step": 2320
+    },
+    {
+      "epoch": 2.64472190692395,
+      "grad_norm": 0.17696821901805793,
+      "learning_rate": 2.1070635883417124e-07,
+      "loss": 0.0407,
+      "step": 2330
+    },
+    {
+      "epoch": 2.656072644721907,
+      "grad_norm": 0.8013523700822813,
+      "learning_rate": 1.9763524712814812e-07,
+      "loss": 0.0389,
+      "step": 2340
+    },
+    {
+      "epoch": 2.6674233825198637,
+      "grad_norm": 0.13612222053062578,
+      "learning_rate": 1.8496596680897398e-07,
+      "loss": 0.0649,
+      "step": 2350
+    },
+    {
+      "epoch": 2.678774120317821,
+      "grad_norm": 0.8239843030304835,
+      "learning_rate": 1.7270072904430806e-07,
+      "loss": 0.0404,
+      "step": 2360
+    },
+    {
+      "epoch": 2.6901248581157775,
+      "grad_norm": 2.0704079536541617,
+      "learning_rate": 1.608416744843208e-07,
+      "loss": 0.0567,
+      "step": 2370
+    },
+    {
+      "epoch": 2.7014755959137347,
+      "grad_norm": 3.2577304351460445,
+      "learning_rate": 1.4939087288808718e-07,
+      "loss": 0.046,
+      "step": 2380
+    },
+    {
+      "epoch": 2.7128263337116914,
+      "grad_norm": 9.981537154516658,
+      "learning_rate": 1.3835032276235088e-07,
+      "loss": 0.0576,
+      "step": 2390
+    },
+    {
+      "epoch": 2.724177071509648,
+      "grad_norm": 5.704050324905945,
+      "learning_rate": 1.2772195101272645e-07,
+      "loss": 0.0925,
+      "step": 2400
+    },
+    {
+      "epoch": 2.735527809307605,
+      "grad_norm": 1.3756958845173786,
+      "learning_rate": 1.1750761260739596e-07,
+      "loss": 0.0627,
+      "step": 2410
+    },
+    {
+      "epoch": 2.746878547105562,
+      "grad_norm": 8.13235929955815,
+      "learning_rate": 1.0770909025336202e-07,
+      "loss": 0.0325,
+      "step": 2420
+    },
+    {
+      "epoch": 2.7582292849035186,
+      "grad_norm": 0.17235125110595084,
+      "learning_rate": 9.83280940853118e-08,
+      "loss": 0.0616,
+      "step": 2430
+    },
+    {
+      "epoch": 2.7695800227014757,
+      "grad_norm": 5.873955549616704,
+      "learning_rate": 8.936626136714754e-08,
+      "loss": 0.0424,
+      "step": 2440
+    },
+    {
+      "epoch": 2.7809307604994324,
+      "grad_norm": 0.17753402782466365,
+      "learning_rate": 8.082515620623593e-08,
+      "loss": 0.0253,
+      "step": 2450
+    },
+    {
+      "epoch": 2.792281498297389,
+      "grad_norm": 0.06207306412666676,
+      "learning_rate": 7.27062692804234e-08,
+      "loss": 0.0585,
+      "step": 2460
+    },
+    {
+      "epoch": 2.8036322360953463,
+      "grad_norm": 0.6499405088971257,
+      "learning_rate": 6.501101757786898e-08,
+      "loss": 0.0536,
+      "step": 2470
+    },
+    {
+      "epoch": 2.814982973893303,
+      "grad_norm": 4.920856595800931,
+      "learning_rate": 5.7740744149738516e-08,
+      "loss": 0.0795,
+      "step": 2480
+    },
+    {
+      "epoch": 2.8263337116912597,
+      "grad_norm": 0.08802887390877849,
+      "learning_rate": 5.089671787579936e-08,
+      "loss": 0.09,
+      "step": 2490
+    },
+    {
+      "epoch": 2.837684449489217,
+      "grad_norm": 0.9119840575805679,
+      "learning_rate": 4.448013324296646e-08,
+      "loss": 0.0511,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8490351872871735,
+      "grad_norm": 0.3318639596122148,
+      "learning_rate": 3.849211013682658e-08,
+      "loss": 0.0278,
+      "step": 2510
+    },
+    {
+      "epoch": 2.8603859250851307,
+      "grad_norm": 9.771929232558433,
+      "learning_rate": 3.293369364618465e-08,
+      "loss": 0.0411,
+      "step": 2520
+    },
+    {
+      "epoch": 2.8717366628830874,
+      "grad_norm": 4.634245009884485,
+      "learning_rate": 2.780585388066581e-08,
+      "loss": 0.0527,
+      "step": 2530
+    },
+    {
+      "epoch": 2.8830874006810445,
+      "grad_norm": 5.509503329690719,
+      "learning_rate": 2.3109485801402208e-08,
+      "loss": 0.0313,
+      "step": 2540
+    },
+    {
+      "epoch": 2.894438138479001,
+      "grad_norm": 0.6312570349344234,
+      "learning_rate": 1.8845409064833787e-08,
+      "loss": 0.0344,
+      "step": 2550
+    },
+    {
+      "epoch": 2.905788876276958,
+      "grad_norm": 7.612882204362058,
+      "learning_rate": 1.5014367879655765e-08,
+      "loss": 0.052,
+      "step": 2560
+    },
+    {
+      "epoch": 2.917139614074915,
+      "grad_norm": 0.5134906139680172,
+      "learning_rate": 1.1617030876932001e-08,
+      "loss": 0.0398,
+      "step": 2570
+    },
+    {
+      "epoch": 2.9284903518728718,
+      "grad_norm": 0.2021032827858405,
+      "learning_rate": 8.653990993396921e-09,
+      "loss": 0.0711,
+      "step": 2580
+    },
+    {
+      "epoch": 2.9398410896708285,
+      "grad_norm": 0.5469399923890682,
+      "learning_rate": 6.125765367972492e-09,
+      "loss": 0.0641,
+      "step": 2590
+    },
+    {
+      "epoch": 2.9511918274687856,
+      "grad_norm": 0.11492556820368983,
+      "learning_rate": 4.032795251510957e-09,
+      "loss": 0.0095,
+      "step": 2600
+    },
+    {
+      "epoch": 2.9625425652667423,
+      "grad_norm": 0.02879337383162824,
+      "learning_rate": 2.3754459297833932e-09,
+      "loss": 0.0419,
+      "step": 2610
+    },
+    {
+      "epoch": 2.973893303064699,
+      "grad_norm": 2.144583462175888,
+      "learning_rate": 1.1540066597270916e-09,
+      "loss": 0.1211,
+      "step": 2620
+    },
+    {
+      "epoch": 2.985244040862656,
+      "grad_norm": 0.5856229499773629,
+      "learning_rate": 3.6869061896066536e-10,
+      "loss": 0.0493,
+      "step": 2630
+    },
+    {
+      "epoch": 2.996594778660613,
+      "grad_norm": 0.1718989447743379,
+      "learning_rate": 1.9634868579365696e-11,
+      "loss": 0.0414,
+      "step": 2640
+    },
+    {
+      "epoch": 3.0,
+      "step": 2643,
+      "total_flos": 130173844045824.0,
+      "train_loss": 0.32796121670620854,
+      "train_runtime": 10598.1253,
+      "train_samples_per_second": 1.995,
+      "train_steps_per_second": 0.249
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2643,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 130173844045824.0,
+  "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 sha256:11835004010d47ee83b96d47ff9d6e41e402b7198aa905838515d521c8588a03
+size 7288