Upload model

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: openthoughts_math
+  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. -->
+
+# openthoughts_math
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/openthoughts_math dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 8e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 512
+- total_eval_batch_size: 128
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.5.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.942630185348632,
+    "total_flos": 9.306564393200255e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.9909,
+    "train_samples_per_second": 91040.986,
+    "train_steps_per_second": 175.798
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a64ae99d81dc816f97114b5466c31f7262c421ffdfb2e63859eaea39d0196c0
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872caa13155c49c822cecac2c685977433a9c7e983710810a8a37db9c5528308
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71276194da339b6a5e9387f4c2a1f906511e1fae820e27c5034015e6cb650c3d
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ce992e3e4e1e106bbcd8ce60916a0fa3dcb47637f15d3019900e65453a0984
+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"
+  }
+}

runs/May10_23-17-04_jrc0927/events.out.tfevents.1746911952.jrc0927.818033.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a4d5b7a032cd6b2940383f33c15152a89742786d8144b8ae5c07fcbfa4fb90
+size 5497

runs/May12_18-08-34_jrc0911/events.out.tfevents.1747066243.jrc0911.2931372.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89256193da2b0eb77eac73c453bfc0475925d066bd805b41a858007819e5a984
+size 79193

runs/May13_16-52-23_jrc0911/events.out.tfevents.1747148074.jrc0911.3140381.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e58f5e0856f2847a9af4dda92006508b4ee1a8507e24c3b80e2b88ce801ccf
+size 5915

special_tokens_map.json

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

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-05-13 16:52:23", "end_time": "2025-05-13 16:54:48"}

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.942630185348632,
+    "total_flos": 9.306564393200255e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.9909,
+    "train_samples_per_second": 91040.986,
+    "train_steps_per_second": 175.798
+}

trainer_log.jsonl

@@ -0,0 +1,352 @@
+{"current_steps": 1, "total_steps": 350, "loss": 0.8154, "lr": 2.285714285714286e-06, "epoch": 0.01412180052956752, "percentage": 0.29, "elapsed_time": "0:04:10", "remaining_time": "1 day, 0:16:47"}
+{"current_steps": 2, "total_steps": 350, "loss": 0.8243, "lr": 4.571428571428572e-06, "epoch": 0.02824360105913504, "percentage": 0.57, "elapsed_time": "0:08:04", "remaining_time": "23:24:02"}
+{"current_steps": 3, "total_steps": 350, "loss": 0.8057, "lr": 6.857142857142858e-06, "epoch": 0.04236540158870256, "percentage": 0.86, "elapsed_time": "0:11:58", "remaining_time": "23:04:36"}
+{"current_steps": 4, "total_steps": 350, "loss": 0.7602, "lr": 9.142857142857144e-06, "epoch": 0.05648720211827008, "percentage": 1.14, "elapsed_time": "0:15:50", "remaining_time": "22:50:13"}
+{"current_steps": 5, "total_steps": 350, "loss": 0.7197, "lr": 1.1428571428571429e-05, "epoch": 0.0706090026478376, "percentage": 1.43, "elapsed_time": "0:19:42", "remaining_time": "22:40:19"}
+{"current_steps": 6, "total_steps": 350, "loss": 0.7374, "lr": 1.3714285714285716e-05, "epoch": 0.08473080317740513, "percentage": 1.71, "elapsed_time": "0:23:36", "remaining_time": "22:33:10"}
+{"current_steps": 7, "total_steps": 350, "loss": 0.7325, "lr": 1.6000000000000003e-05, "epoch": 0.09885260370697264, "percentage": 2.0, "elapsed_time": "0:27:28", "remaining_time": "22:26:24"}
+{"current_steps": 8, "total_steps": 350, "loss": 0.7502, "lr": 1.8285714285714288e-05, "epoch": 0.11297440423654016, "percentage": 2.29, "elapsed_time": "0:31:22", "remaining_time": "22:21:09"}
+{"current_steps": 9, "total_steps": 350, "loss": 0.7051, "lr": 2.057142857142857e-05, "epoch": 0.12709620476610767, "percentage": 2.57, "elapsed_time": "0:35:15", "remaining_time": "22:15:48"}
+{"current_steps": 10, "total_steps": 350, "loss": 0.6593, "lr": 2.2857142857142858e-05, "epoch": 0.1412180052956752, "percentage": 2.86, "elapsed_time": "0:39:07", "remaining_time": "22:10:29"}
+{"current_steps": 11, "total_steps": 350, "loss": 0.6276, "lr": 2.5142857142857143e-05, "epoch": 0.1553398058252427, "percentage": 3.14, "elapsed_time": "0:43:01", "remaining_time": "22:05:50"}
+{"current_steps": 12, "total_steps": 350, "loss": 0.6013, "lr": 2.742857142857143e-05, "epoch": 0.16946160635481025, "percentage": 3.43, "elapsed_time": "0:46:54", "remaining_time": "22:01:02"}
+{"current_steps": 13, "total_steps": 350, "loss": 0.5859, "lr": 2.9714285714285717e-05, "epoch": 0.18358340688437777, "percentage": 3.71, "elapsed_time": "0:50:47", "remaining_time": "21:56:29"}
+{"current_steps": 14, "total_steps": 350, "loss": 0.5824, "lr": 3.2000000000000005e-05, "epoch": 0.1977052074139453, "percentage": 4.0, "elapsed_time": "0:54:40", "remaining_time": "21:52:05"}
+{"current_steps": 15, "total_steps": 350, "loss": 0.5708, "lr": 3.4285714285714284e-05, "epoch": 0.2118270079435128, "percentage": 4.29, "elapsed_time": "0:58:32", "remaining_time": "21:47:34"}
+{"current_steps": 16, "total_steps": 350, "loss": 0.5563, "lr": 3.6571428571428576e-05, "epoch": 0.22594880847308033, "percentage": 4.57, "elapsed_time": "1:02:26", "remaining_time": "21:43:27"}
+{"current_steps": 17, "total_steps": 350, "loss": 0.5566, "lr": 3.885714285714286e-05, "epoch": 0.24007060900264784, "percentage": 4.86, "elapsed_time": "1:06:18", "remaining_time": "21:38:56"}
+{"current_steps": 18, "total_steps": 350, "loss": 0.5507, "lr": 4.114285714285714e-05, "epoch": 0.25419240953221534, "percentage": 5.14, "elapsed_time": "1:10:11", "remaining_time": "21:34:43"}
+{"current_steps": 19, "total_steps": 350, "loss": 0.5418, "lr": 4.342857142857143e-05, "epoch": 0.26831421006178285, "percentage": 5.43, "elapsed_time": "1:14:04", "remaining_time": "21:30:28"}
+{"current_steps": 20, "total_steps": 350, "loss": 0.5333, "lr": 4.5714285714285716e-05, "epoch": 0.2824360105913504, "percentage": 5.71, "elapsed_time": "1:17:58", "remaining_time": "21:26:30"}
+{"current_steps": 21, "total_steps": 350, "loss": 0.5305, "lr": 4.8e-05, "epoch": 0.2965578111209179, "percentage": 6.0, "elapsed_time": "1:21:50", "remaining_time": "21:22:12"}
+{"current_steps": 22, "total_steps": 350, "loss": 0.5189, "lr": 5.0285714285714286e-05, "epoch": 0.3106796116504854, "percentage": 6.29, "elapsed_time": "1:25:43", "remaining_time": "21:18:09"}
+{"current_steps": 23, "total_steps": 350, "loss": 0.5198, "lr": 5.257142857142858e-05, "epoch": 0.324801412180053, "percentage": 6.57, "elapsed_time": "1:29:36", "remaining_time": "21:14:03"}
+{"current_steps": 24, "total_steps": 350, "loss": 0.5102, "lr": 5.485714285714286e-05, "epoch": 0.3389232127096205, "percentage": 6.86, "elapsed_time": "1:33:29", "remaining_time": "21:10:01"}
+{"current_steps": 25, "total_steps": 350, "loss": 0.5098, "lr": 5.714285714285715e-05, "epoch": 0.353045013239188, "percentage": 7.14, "elapsed_time": "1:37:22", "remaining_time": "21:05:55"}
+{"current_steps": 26, "total_steps": 350, "loss": 0.5015, "lr": 5.9428571428571434e-05, "epoch": 0.36716681376875554, "percentage": 7.43, "elapsed_time": "1:41:15", "remaining_time": "21:01:53"}
+{"current_steps": 27, "total_steps": 350, "loss": 0.507, "lr": 6.171428571428573e-05, "epoch": 0.38128861429832306, "percentage": 7.71, "elapsed_time": "1:45:09", "remaining_time": "20:57:56"}
+{"current_steps": 28, "total_steps": 350, "loss": 0.5034, "lr": 6.400000000000001e-05, "epoch": 0.3954104148278906, "percentage": 8.0, "elapsed_time": "1:49:01", "remaining_time": "20:53:51"}
+{"current_steps": 29, "total_steps": 350, "loss": 0.4983, "lr": 6.62857142857143e-05, "epoch": 0.4095322153574581, "percentage": 8.29, "elapsed_time": "1:52:54", "remaining_time": "20:49:47"}
+{"current_steps": 30, "total_steps": 350, "loss": 0.508, "lr": 6.857142857142857e-05, "epoch": 0.4236540158870256, "percentage": 8.57, "elapsed_time": "1:56:47", "remaining_time": "20:45:50"}
+{"current_steps": 31, "total_steps": 350, "loss": 0.5016, "lr": 7.085714285714287e-05, "epoch": 0.43777581641659313, "percentage": 8.86, "elapsed_time": "2:00:40", "remaining_time": "20:41:46"}
+{"current_steps": 32, "total_steps": 350, "loss": 0.4939, "lr": 7.314285714285715e-05, "epoch": 0.45189761694616065, "percentage": 9.14, "elapsed_time": "2:04:32", "remaining_time": "20:37:39"}
+{"current_steps": 33, "total_steps": 350, "loss": 0.4924, "lr": 7.542857142857144e-05, "epoch": 0.46601941747572817, "percentage": 9.43, "elapsed_time": "2:08:26", "remaining_time": "20:33:46"}
+{"current_steps": 34, "total_steps": 350, "loss": 0.4902, "lr": 7.771428571428572e-05, "epoch": 0.4801412180052957, "percentage": 9.71, "elapsed_time": "2:12:19", "remaining_time": "20:29:49"}
+{"current_steps": 35, "total_steps": 350, "loss": 0.4852, "lr": 8e-05, "epoch": 0.4942630185348632, "percentage": 10.0, "elapsed_time": "2:16:12", "remaining_time": "20:25:49"}
+{"current_steps": 36, "total_steps": 350, "loss": 0.4853, "lr": 7.999801067823773e-05, "epoch": 0.5083848190644307, "percentage": 10.29, "elapsed_time": "2:20:04", "remaining_time": "20:21:44"}
+{"current_steps": 37, "total_steps": 350, "loss": 0.4764, "lr": 7.999204291082095e-05, "epoch": 0.5225066195939982, "percentage": 10.57, "elapsed_time": "2:23:57", "remaining_time": "20:17:44"}
+{"current_steps": 38, "total_steps": 350, "loss": 0.4809, "lr": 7.998209729134014e-05, "epoch": 0.5366284201235657, "percentage": 10.86, "elapsed_time": "2:27:50", "remaining_time": "20:13:52"}
+{"current_steps": 39, "total_steps": 350, "loss": 0.4719, "lr": 7.996817480904718e-05, "epoch": 0.5507502206531333, "percentage": 11.14, "elapsed_time": "2:31:44", "remaining_time": "20:09:59"}
+{"current_steps": 40, "total_steps": 350, "loss": 0.477, "lr": 7.99502768487569e-05, "epoch": 0.5648720211827007, "percentage": 11.43, "elapsed_time": "2:35:36", "remaining_time": "20:06:00"}
+{"current_steps": 41, "total_steps": 350, "loss": 0.4724, "lr": 7.99284051907094e-05, "epoch": 0.5789938217122683, "percentage": 11.71, "elapsed_time": "2:39:29", "remaining_time": "20:02:04"}
+{"current_steps": 42, "total_steps": 350, "loss": 0.4662, "lr": 7.990256201039297e-05, "epoch": 0.5931156222418358, "percentage": 12.0, "elapsed_time": "2:43:22", "remaining_time": "19:58:04"}
+{"current_steps": 43, "total_steps": 350, "loss": 0.4621, "lr": 7.987274987832764e-05, "epoch": 0.6072374227714034, "percentage": 12.29, "elapsed_time": "2:47:14", "remaining_time": "19:54:01"}
+{"current_steps": 44, "total_steps": 350, "loss": 0.4665, "lr": 7.983897175980957e-05, "epoch": 0.6213592233009708, "percentage": 12.57, "elapsed_time": "2:51:07", "remaining_time": "19:50:03"}
+{"current_steps": 45, "total_steps": 350, "loss": 0.4761, "lr": 7.980123101461606e-05, "epoch": 0.6354810238305384, "percentage": 12.86, "elapsed_time": "2:55:00", "remaining_time": "19:46:08"}
+{"current_steps": 46, "total_steps": 350, "loss": 0.4652, "lr": 7.975953139667141e-05, "epoch": 0.649602824360106, "percentage": 13.14, "elapsed_time": "2:58:52", "remaining_time": "19:42:10"}
+{"current_steps": 47, "total_steps": 350, "loss": 0.4619, "lr": 7.97138770536735e-05, "epoch": 0.6637246248896734, "percentage": 13.43, "elapsed_time": "3:02:46", "remaining_time": "19:38:18"}
+{"current_steps": 48, "total_steps": 350, "loss": 0.4638, "lr": 7.966427252668121e-05, "epoch": 0.677846425419241, "percentage": 13.71, "elapsed_time": "3:06:38", "remaining_time": "19:34:19"}
+{"current_steps": 49, "total_steps": 350, "loss": 0.4527, "lr": 7.961072274966282e-05, "epoch": 0.6919682259488085, "percentage": 14.0, "elapsed_time": "3:10:31", "remaining_time": "19:30:23"}
+{"current_steps": 50, "total_steps": 350, "loss": 0.4571, "lr": 7.955323304900514e-05, "epoch": 0.706090026478376, "percentage": 14.29, "elapsed_time": "3:14:24", "remaining_time": "19:26:28"}
+{"current_steps": 51, "total_steps": 350, "loss": 0.4496, "lr": 7.949180914298383e-05, "epoch": 0.7202118270079435, "percentage": 14.57, "elapsed_time": "3:18:18", "remaining_time": "19:22:36"}
+{"current_steps": 52, "total_steps": 350, "loss": 0.4593, "lr": 7.942645714119452e-05, "epoch": 0.7343336275375111, "percentage": 14.86, "elapsed_time": "3:22:10", "remaining_time": "19:18:37"}
+{"current_steps": 53, "total_steps": 350, "loss": 0.4502, "lr": 7.93571835439452e-05, "epoch": 0.7484554280670785, "percentage": 15.14, "elapsed_time": "3:26:03", "remaining_time": "19:14:44"}
+{"current_steps": 54, "total_steps": 350, "loss": 0.447, "lr": 7.928399524160956e-05, "epoch": 0.7625772285966461, "percentage": 15.43, "elapsed_time": "3:29:57", "remaining_time": "19:10:50"}
+{"current_steps": 55, "total_steps": 350, "loss": 0.4461, "lr": 7.920689951394175e-05, "epoch": 0.7766990291262136, "percentage": 15.71, "elapsed_time": "3:33:49", "remaining_time": "19:06:53"}
+{"current_steps": 56, "total_steps": 350, "loss": 0.4473, "lr": 7.912590402935223e-05, "epoch": 0.7908208296557812, "percentage": 16.0, "elapsed_time": "3:37:42", "remaining_time": "19:02:56"}
+{"current_steps": 57, "total_steps": 350, "loss": 0.4472, "lr": 7.904101684414498e-05, "epoch": 0.8049426301853486, "percentage": 16.29, "elapsed_time": "3:41:35", "remaining_time": "18:59:05"}
+{"current_steps": 58, "total_steps": 350, "loss": 0.4442, "lr": 7.895224640171625e-05, "epoch": 0.8190644307149162, "percentage": 16.57, "elapsed_time": "3:45:28", "remaining_time": "18:55:06"}
+{"current_steps": 59, "total_steps": 350, "loss": 0.4449, "lr": 7.88596015317147e-05, "epoch": 0.8331862312444837, "percentage": 16.86, "elapsed_time": "3:49:20", "remaining_time": "18:51:09"}
+{"current_steps": 60, "total_steps": 350, "loss": 0.4433, "lr": 7.876309144916312e-05, "epoch": 0.8473080317740512, "percentage": 17.14, "elapsed_time": "3:53:14", "remaining_time": "18:47:21"}
+{"current_steps": 61, "total_steps": 350, "loss": 0.4401, "lr": 7.86627257535419e-05, "epoch": 0.8614298323036187, "percentage": 17.43, "elapsed_time": "3:57:08", "remaining_time": "18:43:28"}
+{"current_steps": 62, "total_steps": 350, "loss": 0.4374, "lr": 7.855851442783414e-05, "epoch": 0.8755516328331863, "percentage": 17.71, "elapsed_time": "4:01:00", "remaining_time": "18:39:31"}
+{"current_steps": 63, "total_steps": 350, "loss": 0.4409, "lr": 7.845046783753276e-05, "epoch": 0.8896734333627537, "percentage": 18.0, "elapsed_time": "4:04:53", "remaining_time": "18:35:37"}
+{"current_steps": 64, "total_steps": 350, "loss": 0.4407, "lr": 7.833859672960943e-05, "epoch": 0.9037952338923213, "percentage": 18.29, "elapsed_time": "4:08:46", "remaining_time": "18:31:43"}
+{"current_steps": 65, "total_steps": 350, "loss": 0.4602, "lr": 7.822291223144564e-05, "epoch": 0.9179170344218888, "percentage": 18.57, "elapsed_time": "4:12:40", "remaining_time": "18:27:51"}
+{"current_steps": 66, "total_steps": 350, "loss": 0.4369, "lr": 7.810342584972585e-05, "epoch": 0.9320388349514563, "percentage": 18.86, "elapsed_time": "4:16:34", "remaining_time": "18:24:03"}
+{"current_steps": 67, "total_steps": 350, "loss": 0.4356, "lr": 7.798014946929306e-05, "epoch": 0.9461606354810238, "percentage": 19.14, "elapsed_time": "4:20:28", "remaining_time": "18:20:11"}
+{"current_steps": 68, "total_steps": 350, "loss": 0.4504, "lr": 7.785309535196657e-05, "epoch": 0.9602824360105914, "percentage": 19.43, "elapsed_time": "4:24:21", "remaining_time": "18:16:16"}
+{"current_steps": 69, "total_steps": 350, "loss": 0.4392, "lr": 7.772227613532242e-05, "epoch": 0.9744042365401588, "percentage": 19.71, "elapsed_time": "4:28:13", "remaining_time": "18:12:22"}
+{"current_steps": 70, "total_steps": 350, "loss": 0.4474, "lr": 7.758770483143634e-05, "epoch": 0.9885260370697264, "percentage": 20.0, "elapsed_time": "4:32:06", "remaining_time": "18:08:26"}
+{"current_steps": 71, "total_steps": 350, "loss": 0.5108, "lr": 7.74493948255895e-05, "epoch": 1.002647837599294, "percentage": 20.29, "elapsed_time": "4:36:47", "remaining_time": "18:07:41"}
+{"current_steps": 72, "total_steps": 350, "loss": 0.4227, "lr": 7.730735987493711e-05, "epoch": 1.0167696381288613, "percentage": 20.57, "elapsed_time": "4:40:40", "remaining_time": "18:03:41"}
+{"current_steps": 73, "total_steps": 350, "loss": 0.419, "lr": 7.71616141071401e-05, "epoch": 1.030891438658429, "percentage": 20.86, "elapsed_time": "4:44:33", "remaining_time": "17:59:46"}
+{"current_steps": 74, "total_steps": 350, "loss": 0.4182, "lr": 7.701217201895987e-05, "epoch": 1.0450132391879965, "percentage": 21.14, "elapsed_time": "4:48:26", "remaining_time": "17:55:47"}
+{"current_steps": 75, "total_steps": 350, "loss": 0.4147, "lr": 7.685904847481631e-05, "epoch": 1.059135039717564, "percentage": 21.43, "elapsed_time": "4:52:20", "remaining_time": "17:51:53"}
+{"current_steps": 76, "total_steps": 350, "loss": 0.4192, "lr": 7.670225870530936e-05, "epoch": 1.0732568402471314, "percentage": 21.71, "elapsed_time": "4:56:13", "remaining_time": "17:47:59"}
+{"current_steps": 77, "total_steps": 350, "loss": 0.4193, "lr": 7.654181830570404e-05, "epoch": 1.087378640776699, "percentage": 22.0, "elapsed_time": "5:00:06", "remaining_time": "17:43:59"}
+{"current_steps": 78, "total_steps": 350, "loss": 0.4126, "lr": 7.637774323437929e-05, "epoch": 1.1015004413062666, "percentage": 22.29, "elapsed_time": "5:03:59", "remaining_time": "17:40:03"}
+{"current_steps": 79, "total_steps": 350, "loss": 0.4193, "lr": 7.62100498112406e-05, "epoch": 1.1156222418358341, "percentage": 22.57, "elapsed_time": "5:07:51", "remaining_time": "17:36:05"}
+{"current_steps": 80, "total_steps": 350, "loss": 0.4069, "lr": 7.603875471609677e-05, "epoch": 1.1297440423654015, "percentage": 22.86, "elapsed_time": "5:11:44", "remaining_time": "17:32:07"}
+{"current_steps": 81, "total_steps": 350, "loss": 0.4187, "lr": 7.586387498700084e-05, "epoch": 1.143865842894969, "percentage": 23.14, "elapsed_time": "5:15:37", "remaining_time": "17:28:11"}
+{"current_steps": 82, "total_steps": 350, "loss": 0.4101, "lr": 7.568542801855535e-05, "epoch": 1.1579876434245366, "percentage": 23.43, "elapsed_time": "5:19:29", "remaining_time": "17:24:12"}
+{"current_steps": 83, "total_steps": 350, "loss": 0.4074, "lr": 7.550343156018217e-05, "epoch": 1.1721094439541042, "percentage": 23.71, "elapsed_time": "5:23:21", "remaining_time": "17:20:13"}
+{"current_steps": 84, "total_steps": 350, "loss": 0.4105, "lr": 7.531790371435709e-05, "epoch": 1.1862312444836718, "percentage": 24.0, "elapsed_time": "5:27:13", "remaining_time": "17:16:12"}
+{"current_steps": 85, "total_steps": 350, "loss": 0.4131, "lr": 7.512886293480914e-05, "epoch": 1.2003530450132391, "percentage": 24.29, "elapsed_time": "5:31:06", "remaining_time": "17:12:15"}
+{"current_steps": 86, "total_steps": 350, "loss": 0.4123, "lr": 7.49363280246852e-05, "epoch": 1.2144748455428067, "percentage": 24.57, "elapsed_time": "5:34:58", "remaining_time": "17:08:17"}
+{"current_steps": 87, "total_steps": 350, "loss": 0.4199, "lr": 7.474031813467956e-05, "epoch": 1.2285966460723743, "percentage": 24.86, "elapsed_time": "5:38:51", "remaining_time": "17:04:22"}
+{"current_steps": 88, "total_steps": 350, "loss": 0.4152, "lr": 7.454085276112925e-05, "epoch": 1.2427184466019416, "percentage": 25.14, "elapsed_time": "5:42:43", "remaining_time": "17:00:23"}
+{"current_steps": 89, "total_steps": 350, "loss": 0.4064, "lr": 7.433795174407465e-05, "epoch": 1.2568402471315092, "percentage": 25.43, "elapsed_time": "5:46:35", "remaining_time": "16:56:25"}
+{"current_steps": 90, "total_steps": 350, "loss": 0.409, "lr": 7.413163526528623e-05, "epoch": 1.2709620476610768, "percentage": 25.71, "elapsed_time": "5:50:27", "remaining_time": "16:52:26"}
+{"current_steps": 91, "total_steps": 350, "loss": 0.4054, "lr": 7.392192384625704e-05, "epoch": 1.2850838481906444, "percentage": 26.0, "elapsed_time": "5:54:19", "remaining_time": "16:48:28"}
+{"current_steps": 92, "total_steps": 350, "loss": 0.4099, "lr": 7.370883834616157e-05, "epoch": 1.299205648720212, "percentage": 26.29, "elapsed_time": "5:58:11", "remaining_time": "16:44:30"}
+{"current_steps": 93, "total_steps": 350, "loss": 0.4084, "lr": 7.349239995978095e-05, "epoch": 1.3133274492497793, "percentage": 26.57, "elapsed_time": "6:02:03", "remaining_time": "16:40:32"}
+{"current_steps": 94, "total_steps": 350, "loss": 0.4048, "lr": 7.327263021539478e-05, "epoch": 1.3274492497793469, "percentage": 26.86, "elapsed_time": "6:05:55", "remaining_time": "16:36:34"}
+{"current_steps": 95, "total_steps": 350, "loss": 0.4068, "lr": 7.30495509726398e-05, "epoch": 1.3415710503089144, "percentage": 27.14, "elapsed_time": "6:09:47", "remaining_time": "16:32:35"}
+{"current_steps": 96, "total_steps": 350, "loss": 0.4034, "lr": 7.282318442033567e-05, "epoch": 1.3556928508384818, "percentage": 27.43, "elapsed_time": "6:13:40", "remaining_time": "16:28:40"}
+{"current_steps": 97, "total_steps": 350, "loss": 0.4078, "lr": 7.259355307427781e-05, "epoch": 1.3698146513680494, "percentage": 27.71, "elapsed_time": "6:17:33", "remaining_time": "16:24:46"}
+{"current_steps": 98, "total_steps": 350, "loss": 0.4084, "lr": 7.236067977499791e-05, "epoch": 1.383936451897617, "percentage": 28.0, "elapsed_time": "6:21:25", "remaining_time": "16:20:49"}
+{"current_steps": 99, "total_steps": 350, "loss": 0.4069, "lr": 7.212458768549208e-05, "epoch": 1.3980582524271845, "percentage": 28.29, "elapsed_time": "6:25:18", "remaining_time": "16:16:52"}
+{"current_steps": 100, "total_steps": 350, "loss": 0.4047, "lr": 7.188530028891691e-05, "epoch": 1.412180052956752, "percentage": 28.57, "elapsed_time": "6:29:11", "remaining_time": "16:12:58"}
+{"current_steps": 101, "total_steps": 350, "loss": 0.4075, "lr": 7.164284138625367e-05, "epoch": 1.4263018534863194, "percentage": 28.86, "elapsed_time": "6:33:03", "remaining_time": "16:09:01"}
+{"current_steps": 102, "total_steps": 350, "loss": 0.4036, "lr": 7.13972350939409e-05, "epoch": 1.440423654015887, "percentage": 29.14, "elapsed_time": "6:36:55", "remaining_time": "16:05:05"}
+{"current_steps": 103, "total_steps": 350, "loss": 0.4068, "lr": 7.114850584147577e-05, "epoch": 1.4545454545454546, "percentage": 29.43, "elapsed_time": "6:40:47", "remaining_time": "16:01:08"}
+{"current_steps": 104, "total_steps": 350, "loss": 0.4053, "lr": 7.089667836898399e-05, "epoch": 1.468667255075022, "percentage": 29.71, "elapsed_time": "6:44:40", "remaining_time": "15:57:11"}
+{"current_steps": 105, "total_steps": 350, "loss": 0.4002, "lr": 7.064177772475912e-05, "epoch": 1.4827890556045895, "percentage": 30.0, "elapsed_time": "6:48:33", "remaining_time": "15:53:17"}
+{"current_steps": 106, "total_steps": 350, "loss": 0.4013, "lr": 7.038382926277113e-05, "epoch": 1.496910856134157, "percentage": 30.29, "elapsed_time": "6:52:26", "remaining_time": "15:49:23"}
+{"current_steps": 107, "total_steps": 350, "loss": 0.404, "lr": 7.012285864014445e-05, "epoch": 1.5110326566637247, "percentage": 30.57, "elapsed_time": "6:56:19", "remaining_time": "15:45:29"}
+{"current_steps": 108, "total_steps": 350, "loss": 0.3992, "lr": 6.985889181460602e-05, "epoch": 1.5251544571932922, "percentage": 30.86, "elapsed_time": "7:00:12", "remaining_time": "15:41:33"}
+{"current_steps": 109, "total_steps": 350, "loss": 0.4022, "lr": 6.959195504190337e-05, "epoch": 1.5392762577228596, "percentage": 31.14, "elapsed_time": "7:04:05", "remaining_time": "15:37:40"}
+{"current_steps": 110, "total_steps": 350, "loss": 0.3933, "lr": 6.932207487319305e-05, "epoch": 1.5533980582524272, "percentage": 31.43, "elapsed_time": "7:07:58", "remaining_time": "15:33:45"}
+{"current_steps": 111, "total_steps": 350, "loss": 0.4014, "lr": 6.904927815239972e-05, "epoch": 1.5675198587819947, "percentage": 31.71, "elapsed_time": "7:11:51", "remaining_time": "15:29:51"}
+{"current_steps": 112, "total_steps": 350, "loss": 0.4014, "lr": 6.877359201354606e-05, "epoch": 1.581641659311562, "percentage": 32.0, "elapsed_time": "7:15:43", "remaining_time": "15:25:55"}
+{"current_steps": 113, "total_steps": 350, "loss": 0.4021, "lr": 6.84950438780538e-05, "epoch": 1.5957634598411299, "percentage": 32.29, "elapsed_time": "7:19:36", "remaining_time": "15:22:00"}
+{"current_steps": 114, "total_steps": 350, "loss": 0.4003, "lr": 6.821366145201636e-05, "epoch": 1.6098852603706972, "percentage": 32.57, "elapsed_time": "7:23:29", "remaining_time": "15:18:05"}
+{"current_steps": 115, "total_steps": 350, "loss": 0.3992, "lr": 6.792947272344292e-05, "epoch": 1.6240070609002648, "percentage": 32.86, "elapsed_time": "7:27:22", "remaining_time": "15:14:11"}
+{"current_steps": 116, "total_steps": 350, "loss": 0.3982, "lr": 6.76425059594746e-05, "epoch": 1.6381288614298324, "percentage": 33.14, "elapsed_time": "7:31:15", "remaining_time": "15:10:17"}
+{"current_steps": 117, "total_steps": 350, "loss": 0.4053, "lr": 6.73527897035728e-05, "epoch": 1.6522506619593997, "percentage": 33.43, "elapsed_time": "7:35:08", "remaining_time": "15:06:23"}
+{"current_steps": 118, "total_steps": 350, "loss": 0.4024, "lr": 6.706035277268022e-05, "epoch": 1.6663724624889673, "percentage": 33.71, "elapsed_time": "7:39:01", "remaining_time": "15:02:28"}
+{"current_steps": 119, "total_steps": 350, "loss": 0.3945, "lr": 6.676522425435433e-05, "epoch": 1.6804942630185349, "percentage": 34.0, "elapsed_time": "7:42:54", "remaining_time": "14:58:34"}
+{"current_steps": 120, "total_steps": 350, "loss": 0.3984, "lr": 6.646743350387438e-05, "epoch": 1.6946160635481022, "percentage": 34.29, "elapsed_time": "7:46:47", "remaining_time": "14:54:40"}
+{"current_steps": 121, "total_steps": 350, "loss": 0.4021, "lr": 6.616701014132138e-05, "epoch": 1.70873786407767, "percentage": 34.57, "elapsed_time": "7:50:39", "remaining_time": "14:50:45"}
+{"current_steps": 122, "total_steps": 350, "loss": 0.4026, "lr": 6.586398404863198e-05, "epoch": 1.7228596646072374, "percentage": 34.86, "elapsed_time": "7:54:32", "remaining_time": "14:46:51"}
+{"current_steps": 123, "total_steps": 350, "loss": 0.3925, "lr": 6.555838536662624e-05, "epoch": 1.736981465136805, "percentage": 35.14, "elapsed_time": "7:58:25", "remaining_time": "14:42:57"}
+{"current_steps": 124, "total_steps": 350, "loss": 0.3976, "lr": 6.525024449200956e-05, "epoch": 1.7511032656663725, "percentage": 35.43, "elapsed_time": "8:02:18", "remaining_time": "14:39:02"}
+{"current_steps": 125, "total_steps": 350, "loss": 0.3982, "lr": 6.493959207434934e-05, "epoch": 1.7652250661959399, "percentage": 35.71, "elapsed_time": "8:06:11", "remaining_time": "14:35:08"}
+{"current_steps": 126, "total_steps": 350, "loss": 0.3947, "lr": 6.462645901302633e-05, "epoch": 1.7793468667255075, "percentage": 36.0, "elapsed_time": "8:10:04", "remaining_time": "14:31:14"}
+{"current_steps": 127, "total_steps": 350, "loss": 0.4015, "lr": 6.431087645416121e-05, "epoch": 1.793468667255075, "percentage": 36.29, "elapsed_time": "8:13:58", "remaining_time": "14:27:21"}
+{"current_steps": 128, "total_steps": 350, "loss": 0.3959, "lr": 6.399287578751656e-05, "epoch": 1.8075904677846424, "percentage": 36.57, "elapsed_time": "8:17:51", "remaining_time": "14:23:28"}
+{"current_steps": 129, "total_steps": 350, "loss": 0.3975, "lr": 6.367248864337471e-05, "epoch": 1.8217122683142102, "percentage": 36.86, "elapsed_time": "8:21:44", "remaining_time": "14:19:34"}
+{"current_steps": 130, "total_steps": 350, "loss": 0.3961, "lr": 6.334974688939161e-05, "epoch": 1.8358340688437775, "percentage": 37.14, "elapsed_time": "8:25:37", "remaining_time": "14:15:40"}
+{"current_steps": 131, "total_steps": 350, "loss": 0.3923, "lr": 6.302468262742695e-05, "epoch": 1.849955869373345, "percentage": 37.43, "elapsed_time": "8:29:30", "remaining_time": "14:11:47"}
+{"current_steps": 132, "total_steps": 350, "loss": 0.3895, "lr": 6.269732819035128e-05, "epoch": 1.8640776699029127, "percentage": 37.71, "elapsed_time": "8:33:23", "remaining_time": "14:07:53"}
+{"current_steps": 133, "total_steps": 350, "loss": 0.3933, "lr": 6.236771613882987e-05, "epoch": 1.87819947043248, "percentage": 38.0, "elapsed_time": "8:37:17", "remaining_time": "14:04:00"}
+{"current_steps": 134, "total_steps": 350, "loss": 0.3865, "lr": 6.20358792580841e-05, "epoch": 1.8923212709620476, "percentage": 38.29, "elapsed_time": "8:41:10", "remaining_time": "14:00:05"}
+{"current_steps": 135, "total_steps": 350, "loss": 0.3985, "lr": 6.170185055463039e-05, "epoch": 1.9064430714916152, "percentage": 38.57, "elapsed_time": "8:45:03", "remaining_time": "13:56:11"}
+{"current_steps": 136, "total_steps": 350, "loss": 0.3972, "lr": 6.136566325299715e-05, "epoch": 1.9205648720211828, "percentage": 38.86, "elapsed_time": "8:48:55", "remaining_time": "13:52:16"}
+{"current_steps": 137, "total_steps": 350, "loss": 0.398, "lr": 6.102735079242019e-05, "epoch": 1.9346866725507503, "percentage": 39.14, "elapsed_time": "8:52:48", "remaining_time": "13:48:22"}
+{"current_steps": 138, "total_steps": 350, "loss": 0.3957, "lr": 6.068694682351651e-05, "epoch": 1.9488084730803177, "percentage": 39.43, "elapsed_time": "8:56:41", "remaining_time": "13:44:29"}
+{"current_steps": 139, "total_steps": 350, "loss": 0.3953, "lr": 6.0344485204937274e-05, "epoch": 1.9629302736098853, "percentage": 39.71, "elapsed_time": "9:00:34", "remaining_time": "13:40:34"}
+{"current_steps": 140, "total_steps": 350, "loss": 0.3955, "lr": 6.000000000000001e-05, "epoch": 1.9770520741394528, "percentage": 40.0, "elapsed_time": "9:04:26", "remaining_time": "13:36:39"}
+{"current_steps": 141, "total_steps": 350, "loss": 0.4096, "lr": 5.965352547330046e-05, "epoch": 1.9911738746690202, "percentage": 40.29, "elapsed_time": "9:08:14", "remaining_time": "13:32:38"}
+{"current_steps": 142, "total_steps": 350, "loss": 0.4441, "lr": 5.930509608730444e-05, "epoch": 2.005295675198588, "percentage": 40.57, "elapsed_time": "9:12:34", "remaining_time": "13:29:23"}
+{"current_steps": 143, "total_steps": 350, "loss": 0.3728, "lr": 5.895474649891995e-05, "epoch": 2.0194174757281553, "percentage": 40.86, "elapsed_time": "9:16:26", "remaining_time": "13:25:28"}
+{"current_steps": 144, "total_steps": 350, "loss": 0.3745, "lr": 5.860251155605003e-05, "epoch": 2.0335392762577227, "percentage": 41.14, "elapsed_time": "9:20:19", "remaining_time": "13:21:34"}
+{"current_steps": 145, "total_steps": 350, "loss": 0.3832, "lr": 5.824842629412653e-05, "epoch": 2.0476610767872905, "percentage": 41.43, "elapsed_time": "9:24:12", "remaining_time": "13:17:39"}
+{"current_steps": 146, "total_steps": 350, "loss": 0.3779, "lr": 5.7892525932625305e-05, "epoch": 2.061782877316858, "percentage": 41.71, "elapsed_time": "9:28:04", "remaining_time": "13:13:44"}
+{"current_steps": 147, "total_steps": 350, "loss": 0.3718, "lr": 5.75348458715631e-05, "epoch": 2.0759046778464256, "percentage": 42.0, "elapsed_time": "9:31:56", "remaining_time": "13:09:49"}
+{"current_steps": 148, "total_steps": 350, "loss": 0.3699, "lr": 5.7175421687976374e-05, "epoch": 2.090026478375993, "percentage": 42.29, "elapsed_time": "9:35:49", "remaining_time": "13:05:55"}
+{"current_steps": 149, "total_steps": 350, "loss": 0.367, "lr": 5.681428913238263e-05, "epoch": 2.1041482789055603, "percentage": 42.57, "elapsed_time": "9:39:42", "remaining_time": "13:02:00"}
+{"current_steps": 150, "total_steps": 350, "loss": 0.3752, "lr": 5.645148412522447e-05, "epoch": 2.118270079435128, "percentage": 42.86, "elapsed_time": "9:43:34", "remaining_time": "12:58:05"}
+{"current_steps": 151, "total_steps": 350, "loss": 0.3657, "lr": 5.60870427532967e-05, "epoch": 2.1323918799646955, "percentage": 43.14, "elapsed_time": "9:47:27", "remaining_time": "12:54:11"}
+{"current_steps": 152, "total_steps": 350, "loss": 0.3701, "lr": 5.572100126615695e-05, "epoch": 2.146513680494263, "percentage": 43.43, "elapsed_time": "9:51:20", "remaining_time": "12:50:17"}
+{"current_steps": 153, "total_steps": 350, "loss": 0.364, "lr": 5.535339607252003e-05, "epoch": 2.1606354810238306, "percentage": 43.71, "elapsed_time": "9:55:13", "remaining_time": "12:46:23"}
+{"current_steps": 154, "total_steps": 350, "loss": 0.3641, "lr": 5.4984263736636494e-05, "epoch": 2.174757281553398, "percentage": 44.0, "elapsed_time": "9:59:06", "remaining_time": "12:42:29"}
+{"current_steps": 155, "total_steps": 350, "loss": 0.3634, "lr": 5.461364097465581e-05, "epoch": 2.1888790820829658, "percentage": 44.29, "elapsed_time": "10:02:59", "remaining_time": "12:38:36"}
+{"current_steps": 156, "total_steps": 350, "loss": 0.3676, "lr": 5.424156465097428e-05, "epoch": 2.203000882612533, "percentage": 44.57, "elapsed_time": "10:06:52", "remaining_time": "12:34:42"}
+{"current_steps": 157, "total_steps": 350, "loss": 0.3649, "lr": 5.38680717745683e-05, "epoch": 2.2171226831421005, "percentage": 44.86, "elapsed_time": "10:10:45", "remaining_time": "12:30:47"}
+{"current_steps": 158, "total_steps": 350, "loss": 0.3646, "lr": 5.349319949531321e-05, "epoch": 2.2312444836716683, "percentage": 45.14, "elapsed_time": "10:14:38", "remaining_time": "12:26:54"}
+{"current_steps": 159, "total_steps": 350, "loss": 0.3682, "lr": 5.3116985100288185e-05, "epoch": 2.2453662842012356, "percentage": 45.43, "elapsed_time": "10:18:31", "remaining_time": "12:23:00"}
+{"current_steps": 160, "total_steps": 350, "loss": 0.3606, "lr": 5.2739466010067385e-05, "epoch": 2.259488084730803, "percentage": 45.71, "elapsed_time": "10:22:24", "remaining_time": "12:19:06"}
+{"current_steps": 161, "total_steps": 350, "loss": 0.3638, "lr": 5.23606797749979e-05, "epoch": 2.2736098852603708, "percentage": 46.0, "elapsed_time": "10:26:17", "remaining_time": "12:15:12"}
+{"current_steps": 162, "total_steps": 350, "loss": 0.3667, "lr": 5.1980664071464776e-05, "epoch": 2.287731685789938, "percentage": 46.29, "elapsed_time": "10:30:09", "remaining_time": "12:11:17"}
+{"current_steps": 163, "total_steps": 350, "loss": 0.3696, "lr": 5.159945669814345e-05, "epoch": 2.301853486319506, "percentage": 46.57, "elapsed_time": "10:34:01", "remaining_time": "12:07:23"}
+{"current_steps": 164, "total_steps": 350, "loss": 0.3606, "lr": 5.121709557224011e-05, "epoch": 2.3159752868490733, "percentage": 46.86, "elapsed_time": "10:37:54", "remaining_time": "12:03:28"}
+{"current_steps": 165, "total_steps": 350, "loss": 0.365, "lr": 5.0833618725720214e-05, "epoch": 2.3300970873786406, "percentage": 47.14, "elapsed_time": "10:41:47", "remaining_time": "11:59:35"}
+{"current_steps": 166, "total_steps": 350, "loss": 0.3667, "lr": 5.044906430152554e-05, "epoch": 2.3442188879082084, "percentage": 47.43, "elapsed_time": "10:45:41", "remaining_time": "11:55:42"}
+{"current_steps": 167, "total_steps": 350, "loss": 0.3699, "lr": 5.006347054978035e-05, "epoch": 2.358340688437776, "percentage": 47.71, "elapsed_time": "10:49:33", "remaining_time": "11:51:47"}
+{"current_steps": 168, "total_steps": 350, "loss": 0.3587, "lr": 4.967687582398671e-05, "epoch": 2.3724624889673436, "percentage": 48.0, "elapsed_time": "10:53:26", "remaining_time": "11:47:53"}
+{"current_steps": 169, "total_steps": 350, "loss": 0.3636, "lr": 4.9289318577209706e-05, "epoch": 2.386584289496911, "percentage": 48.29, "elapsed_time": "10:57:17", "remaining_time": "11:43:58"}
+{"current_steps": 170, "total_steps": 350, "loss": 0.3605, "lr": 4.890083735825258e-05, "epoch": 2.4007060900264783, "percentage": 48.57, "elapsed_time": "11:01:11", "remaining_time": "11:40:05"}
+{"current_steps": 171, "total_steps": 350, "loss": 0.3648, "lr": 4.851147080782249e-05, "epoch": 2.414827890556046, "percentage": 48.86, "elapsed_time": "11:05:04", "remaining_time": "11:36:11"}
+{"current_steps": 172, "total_steps": 350, "loss": 0.3606, "lr": 4.812125765468705e-05, "epoch": 2.4289496910856134, "percentage": 49.14, "elapsed_time": "11:08:57", "remaining_time": "11:32:17"}
+{"current_steps": 173, "total_steps": 350, "loss": 0.3637, "lr": 4.773023671182213e-05, "epoch": 2.443071491615181, "percentage": 49.43, "elapsed_time": "11:12:49", "remaining_time": "11:28:23"}
+{"current_steps": 174, "total_steps": 350, "loss": 0.3636, "lr": 4.73384468725513e-05, "epoch": 2.4571932921447486, "percentage": 49.71, "elapsed_time": "11:16:42", "remaining_time": "11:24:29"}
+{"current_steps": 175, "total_steps": 350, "loss": 0.3645, "lr": 4.694592710667723e-05, "epoch": 2.471315092674316, "percentage": 50.0, "elapsed_time": "11:20:34", "remaining_time": "11:20:34"}
+{"current_steps": 176, "total_steps": 350, "loss": 0.3605, "lr": 4.6552716456605514e-05, "epoch": 2.4854368932038833, "percentage": 50.29, "elapsed_time": "11:24:27", "remaining_time": "11:16:40"}
+{"current_steps": 177, "total_steps": 350, "loss": 0.3562, "lr": 4.615885403346134e-05, "epoch": 2.499558693733451, "percentage": 50.57, "elapsed_time": "11:28:20", "remaining_time": "11:12:46"}
+{"current_steps": 178, "total_steps": 350, "loss": 0.3636, "lr": 4.576437901319921e-05, "epoch": 2.5136804942630184, "percentage": 50.86, "elapsed_time": "11:32:12", "remaining_time": "11:08:52"}
+{"current_steps": 179, "total_steps": 350, "loss": 0.3648, "lr": 4.5369330632706223e-05, "epoch": 2.5278022947925862, "percentage": 51.14, "elapsed_time": "11:36:05", "remaining_time": "11:04:59"}
+{"current_steps": 180, "total_steps": 350, "loss": 0.3612, "lr": 4.4973748185899416e-05, "epoch": 2.5419240953221536, "percentage": 51.43, "elapsed_time": "11:39:58", "remaining_time": "11:01:05"}
+{"current_steps": 181, "total_steps": 350, "loss": 0.3677, "lr": 4.457767101981728e-05, "epoch": 2.556045895851721, "percentage": 51.71, "elapsed_time": "11:43:50", "remaining_time": "10:57:10"}
+{"current_steps": 182, "total_steps": 350, "loss": 0.3626, "lr": 4.418113853070614e-05, "epoch": 2.5701676963812887, "percentage": 52.0, "elapsed_time": "11:47:42", "remaining_time": "10:53:16"}
+{"current_steps": 183, "total_steps": 350, "loss": 0.364, "lr": 4.378419016010149e-05, "epoch": 2.584289496910856, "percentage": 52.29, "elapsed_time": "11:51:35", "remaining_time": "10:49:22"}
+{"current_steps": 184, "total_steps": 350, "loss": 0.3615, "lr": 4.338686539090493e-05, "epoch": 2.598411297440424, "percentage": 52.57, "elapsed_time": "11:55:28", "remaining_time": "10:45:29"}
+{"current_steps": 185, "total_steps": 350, "loss": 0.3596, "lr": 4.298920374345698e-05, "epoch": 2.6125330979699912, "percentage": 52.86, "elapsed_time": "11:59:21", "remaining_time": "10:41:35"}
+{"current_steps": 186, "total_steps": 350, "loss": 0.3625, "lr": 4.259124477160607e-05, "epoch": 2.6266548984995586, "percentage": 53.14, "elapsed_time": "12:03:13", "remaining_time": "10:37:40"}
+{"current_steps": 187, "total_steps": 350, "loss": 0.3617, "lr": 4.219302805877441e-05, "epoch": 2.6407766990291264, "percentage": 53.43, "elapsed_time": "12:07:05", "remaining_time": "10:33:46"}
+{"current_steps": 188, "total_steps": 350, "loss": 0.3666, "lr": 4.17945932140206e-05, "epoch": 2.6548984995586937, "percentage": 53.71, "elapsed_time": "12:10:58", "remaining_time": "10:29:52"}
+{"current_steps": 189, "total_steps": 350, "loss": 0.3629, "lr": 4.139597986810005e-05, "epoch": 2.6690203000882615, "percentage": 54.0, "elapsed_time": "12:14:50", "remaining_time": "10:25:58"}
+{"current_steps": 190, "total_steps": 350, "loss": 0.3628, "lr": 4.0997227669522924e-05, "epoch": 2.683142100617829, "percentage": 54.29, "elapsed_time": "12:18:43", "remaining_time": "10:22:05"}
+{"current_steps": 191, "total_steps": 350, "loss": 0.3638, "lr": 4.059837628061055e-05, "epoch": 2.6972639011473962, "percentage": 54.57, "elapsed_time": "12:22:36", "remaining_time": "10:18:11"}
+{"current_steps": 192, "total_steps": 350, "loss": 0.3614, "lr": 4.019946537355033e-05, "epoch": 2.7113857016769636, "percentage": 54.86, "elapsed_time": "12:26:29", "remaining_time": "10:14:17"}
+{"current_steps": 193, "total_steps": 350, "loss": 0.3634, "lr": 3.9800534626449683e-05, "epoch": 2.7255075022065314, "percentage": 55.14, "elapsed_time": "12:30:21", "remaining_time": "10:10:24"}
+{"current_steps": 194, "total_steps": 350, "loss": 0.3587, "lr": 3.940162371938947e-05, "epoch": 2.7396293027360987, "percentage": 55.43, "elapsed_time": "12:34:14", "remaining_time": "10:06:30"}
+{"current_steps": 195, "total_steps": 350, "loss": 0.3599, "lr": 3.9002772330477096e-05, "epoch": 2.7537511032656665, "percentage": 55.71, "elapsed_time": "12:38:07", "remaining_time": "10:02:36"}
+{"current_steps": 196, "total_steps": 350, "loss": 0.3575, "lr": 3.860402013189998e-05, "epoch": 2.767872903795234, "percentage": 56.0, "elapsed_time": "12:42:00", "remaining_time": "9:58:43"}
+{"current_steps": 197, "total_steps": 350, "loss": 0.3648, "lr": 3.820540678597942e-05, "epoch": 2.7819947043248012, "percentage": 56.29, "elapsed_time": "12:45:53", "remaining_time": "9:54:49"}
+{"current_steps": 198, "total_steps": 350, "loss": 0.3609, "lr": 3.78069719412256e-05, "epoch": 2.796116504854369, "percentage": 56.57, "elapsed_time": "12:49:46", "remaining_time": "9:50:56"}
+{"current_steps": 199, "total_steps": 350, "loss": 0.3608, "lr": 3.740875522839393e-05, "epoch": 2.8102383053839364, "percentage": 56.86, "elapsed_time": "12:53:38", "remaining_time": "9:47:02"}
+{"current_steps": 200, "total_steps": 350, "loss": 0.3549, "lr": 3.7010796256543034e-05, "epoch": 2.824360105913504, "percentage": 57.14, "elapsed_time": "12:57:31", "remaining_time": "9:43:08"}
+{"current_steps": 201, "total_steps": 350, "loss": 0.3593, "lr": 3.661313460909507e-05, "epoch": 2.8384819064430715, "percentage": 57.43, "elapsed_time": "13:01:24", "remaining_time": "9:39:15"}
+{"current_steps": 202, "total_steps": 350, "loss": 0.3608, "lr": 3.621580983989852e-05, "epoch": 2.852603706972639, "percentage": 57.71, "elapsed_time": "13:05:17", "remaining_time": "9:35:21"}
+{"current_steps": 203, "total_steps": 350, "loss": 0.3605, "lr": 3.581886146929387e-05, "epoch": 2.8667255075022067, "percentage": 58.0, "elapsed_time": "13:09:09", "remaining_time": "9:31:27"}
+{"current_steps": 204, "total_steps": 350, "loss": 0.3582, "lr": 3.542232898018273e-05, "epoch": 2.880847308031774, "percentage": 58.29, "elapsed_time": "13:13:01", "remaining_time": "9:27:33"}
+{"current_steps": 205, "total_steps": 350, "loss": 0.359, "lr": 3.5026251814100604e-05, "epoch": 2.894969108561342, "percentage": 58.57, "elapsed_time": "13:16:53", "remaining_time": "9:23:39"}
+{"current_steps": 206, "total_steps": 350, "loss": 0.3562, "lr": 3.4630669367293797e-05, "epoch": 2.909090909090909, "percentage": 58.86, "elapsed_time": "13:20:46", "remaining_time": "9:19:45"}
+{"current_steps": 207, "total_steps": 350, "loss": 0.3641, "lr": 3.4235620986800806e-05, "epoch": 2.9232127096204765, "percentage": 59.14, "elapsed_time": "13:24:39", "remaining_time": "9:15:52"}
+{"current_steps": 208, "total_steps": 350, "loss": 0.361, "lr": 3.384114596653866e-05, "epoch": 2.937334510150044, "percentage": 59.43, "elapsed_time": "13:28:32", "remaining_time": "9:11:58"}
+{"current_steps": 209, "total_steps": 350, "loss": 0.3586, "lr": 3.344728354339449e-05, "epoch": 2.9514563106796117, "percentage": 59.71, "elapsed_time": "13:32:24", "remaining_time": "9:08:05"}
+{"current_steps": 210, "total_steps": 350, "loss": 0.3559, "lr": 3.305407289332279e-05, "epoch": 2.965578111209179, "percentage": 60.0, "elapsed_time": "13:36:16", "remaining_time": "9:04:11"}
+{"current_steps": 211, "total_steps": 350, "loss": 0.3631, "lr": 3.266155312744871e-05, "epoch": 2.979699911738747, "percentage": 60.29, "elapsed_time": "13:40:08", "remaining_time": "9:00:17"}
+{"current_steps": 212, "total_steps": 350, "loss": 0.3927, "lr": 3.226976328817788e-05, "epoch": 2.993821712268314, "percentage": 60.57, "elapsed_time": "13:43:56", "remaining_time": "8:56:20"}
+{"current_steps": 213, "total_steps": 350, "loss": 0.3822, "lr": 3.187874234531296e-05, "epoch": 3.0079435127978815, "percentage": 60.86, "elapsed_time": "13:48:16", "remaining_time": "8:52:44"}
+{"current_steps": 214, "total_steps": 350, "loss": 0.3393, "lr": 3.1488529192177526e-05, "epoch": 3.0220653133274493, "percentage": 61.14, "elapsed_time": "13:52:08", "remaining_time": "8:48:50"}
+{"current_steps": 215, "total_steps": 350, "loss": 0.3373, "lr": 3.109916264174743e-05, "epoch": 3.0361871138570167, "percentage": 61.43, "elapsed_time": "13:56:00", "remaining_time": "8:44:56"}
+{"current_steps": 216, "total_steps": 350, "loss": 0.3371, "lr": 3.071068142279031e-05, "epoch": 3.0503089143865845, "percentage": 61.71, "elapsed_time": "13:59:53", "remaining_time": "8:41:02"}
+{"current_steps": 217, "total_steps": 350, "loss": 0.3355, "lr": 3.0323124176013297e-05, "epoch": 3.064430714916152, "percentage": 62.0, "elapsed_time": "14:03:46", "remaining_time": "8:37:08"}
+{"current_steps": 218, "total_steps": 350, "loss": 0.3377, "lr": 2.993652945021966e-05, "epoch": 3.078552515445719, "percentage": 62.29, "elapsed_time": "14:07:40", "remaining_time": "8:33:16"}
+{"current_steps": 219, "total_steps": 350, "loss": 0.3366, "lr": 2.955093569847447e-05, "epoch": 3.092674315975287, "percentage": 62.57, "elapsed_time": "14:11:32", "remaining_time": "8:29:21"}
+{"current_steps": 220, "total_steps": 350, "loss": 0.3312, "lr": 2.9166381274279803e-05, "epoch": 3.1067961165048543, "percentage": 62.86, "elapsed_time": "14:15:24", "remaining_time": "8:25:28"}
+{"current_steps": 221, "total_steps": 350, "loss": 0.3311, "lr": 2.8782904427759898e-05, "epoch": 3.120917917034422, "percentage": 63.14, "elapsed_time": "14:19:16", "remaining_time": "8:21:34"}
+{"current_steps": 222, "total_steps": 350, "loss": 0.3282, "lr": 2.8400543301856553e-05, "epoch": 3.1350397175639895, "percentage": 63.43, "elapsed_time": "14:23:08", "remaining_time": "8:17:40"}
+{"current_steps": 223, "total_steps": 350, "loss": 0.3297, "lr": 2.8019335928535234e-05, "epoch": 3.149161518093557, "percentage": 63.71, "elapsed_time": "14:27:01", "remaining_time": "8:13:46"}
+{"current_steps": 224, "total_steps": 350, "loss": 0.327, "lr": 2.7639320225002108e-05, "epoch": 3.1632833186231246, "percentage": 64.0, "elapsed_time": "14:30:53", "remaining_time": "8:09:52"}
+{"current_steps": 225, "total_steps": 350, "loss": 0.3346, "lr": 2.7260533989932628e-05, "epoch": 3.177405119152692, "percentage": 64.29, "elapsed_time": "14:34:45", "remaining_time": "8:05:58"}
+{"current_steps": 226, "total_steps": 350, "loss": 0.3271, "lr": 2.688301489971183e-05, "epoch": 3.1915269196822593, "percentage": 64.57, "elapsed_time": "14:38:38", "remaining_time": "8:02:05"}
+{"current_steps": 227, "total_steps": 350, "loss": 0.328, "lr": 2.6506800504686806e-05, "epoch": 3.205648720211827, "percentage": 64.86, "elapsed_time": "14:42:31", "remaining_time": "7:58:11"}
+{"current_steps": 228, "total_steps": 350, "loss": 0.33, "lr": 2.6131928225431713e-05, "epoch": 3.2197705207413945, "percentage": 65.14, "elapsed_time": "14:46:23", "remaining_time": "7:54:17"}
+{"current_steps": 229, "total_steps": 350, "loss": 0.3358, "lr": 2.575843534902573e-05, "epoch": 3.233892321270962, "percentage": 65.43, "elapsed_time": "14:50:16", "remaining_time": "7:50:24"}
+{"current_steps": 230, "total_steps": 350, "loss": 0.3364, "lr": 2.53863590253442e-05, "epoch": 3.2480141218005296, "percentage": 65.71, "elapsed_time": "14:54:08", "remaining_time": "7:46:30"}
+{"current_steps": 231, "total_steps": 350, "loss": 0.3337, "lr": 2.501573626336352e-05, "epoch": 3.262135922330097, "percentage": 66.0, "elapsed_time": "14:58:00", "remaining_time": "7:42:36"}
+{"current_steps": 232, "total_steps": 350, "loss": 0.3301, "lr": 2.464660392747999e-05, "epoch": 3.2762577228596648, "percentage": 66.29, "elapsed_time": "15:01:51", "remaining_time": "7:38:42"}
+{"current_steps": 233, "total_steps": 350, "loss": 0.332, "lr": 2.427899873384306e-05, "epoch": 3.290379523389232, "percentage": 66.57, "elapsed_time": "15:05:44", "remaining_time": "7:34:49"}
+{"current_steps": 234, "total_steps": 350, "loss": 0.3377, "lr": 2.3912957246703305e-05, "epoch": 3.3045013239187995, "percentage": 66.86, "elapsed_time": "15:09:36", "remaining_time": "7:30:55"}
+{"current_steps": 235, "total_steps": 350, "loss": 0.3297, "lr": 2.3548515874775547e-05, "epoch": 3.3186231244483673, "percentage": 67.14, "elapsed_time": "15:13:29", "remaining_time": "7:27:01"}
+{"current_steps": 236, "total_steps": 350, "loss": 0.3361, "lr": 2.3185710867617387e-05, "epoch": 3.3327449249779346, "percentage": 67.43, "elapsed_time": "15:17:20", "remaining_time": "7:23:07"}
+{"current_steps": 237, "total_steps": 350, "loss": 0.3322, "lr": 2.2824578312023632e-05, "epoch": 3.3468667255075024, "percentage": 67.71, "elapsed_time": "15:21:13", "remaining_time": "7:19:13"}
+{"current_steps": 238, "total_steps": 350, "loss": 0.3361, "lr": 2.24651541284369e-05, "epoch": 3.3609885260370698, "percentage": 68.0, "elapsed_time": "15:25:04", "remaining_time": "7:15:19"}
+{"current_steps": 239, "total_steps": 350, "loss": 0.3344, "lr": 2.210747406737469e-05, "epoch": 3.375110326566637, "percentage": 68.29, "elapsed_time": "15:28:56", "remaining_time": "7:11:25"}
+{"current_steps": 240, "total_steps": 350, "loss": 0.3324, "lr": 2.175157370587348e-05, "epoch": 3.389232127096205, "percentage": 68.57, "elapsed_time": "15:32:48", "remaining_time": "7:07:32"}
+{"current_steps": 241, "total_steps": 350, "loss": 0.3366, "lr": 2.1397488443949985e-05, "epoch": 3.4033539276257723, "percentage": 68.86, "elapsed_time": "15:36:40", "remaining_time": "7:03:38"}
+{"current_steps": 242, "total_steps": 350, "loss": 0.3335, "lr": 2.1045253501080058e-05, "epoch": 3.4174757281553396, "percentage": 69.14, "elapsed_time": "15:40:33", "remaining_time": "6:59:45"}
+{"current_steps": 243, "total_steps": 350, "loss": 0.3342, "lr": 2.0694903912695574e-05, "epoch": 3.4315975286849074, "percentage": 69.43, "elapsed_time": "15:44:26", "remaining_time": "6:55:51"}
+{"current_steps": 244, "total_steps": 350, "loss": 0.3343, "lr": 2.0346474526699552e-05, "epoch": 3.4457193292144748, "percentage": 69.71, "elapsed_time": "15:48:19", "remaining_time": "6:51:58"}
+{"current_steps": 245, "total_steps": 350, "loss": 0.3342, "lr": 2.0000000000000012e-05, "epoch": 3.459841129744042, "percentage": 70.0, "elapsed_time": "15:52:11", "remaining_time": "6:48:05"}
+{"current_steps": 246, "total_steps": 350, "loss": 0.3317, "lr": 1.9655514795062746e-05, "epoch": 3.47396293027361, "percentage": 70.29, "elapsed_time": "15:56:03", "remaining_time": "6:44:11"}
+{"current_steps": 247, "total_steps": 350, "loss": 0.336, "lr": 1.931305317648349e-05, "epoch": 3.4880847308031773, "percentage": 70.57, "elapsed_time": "15:59:56", "remaining_time": "6:40:17"}
+{"current_steps": 248, "total_steps": 350, "loss": 0.3329, "lr": 1.897264920757981e-05, "epoch": 3.502206531332745, "percentage": 70.86, "elapsed_time": "16:03:48", "remaining_time": "6:36:24"}
+{"current_steps": 249, "total_steps": 350, "loss": 0.3363, "lr": 1.8634336747002853e-05, "epoch": 3.5163283318623124, "percentage": 71.14, "elapsed_time": "16:07:40", "remaining_time": "6:32:30"}
+{"current_steps": 250, "total_steps": 350, "loss": 0.3366, "lr": 1.829814944536963e-05, "epoch": 3.5304501323918798, "percentage": 71.43, "elapsed_time": "16:11:32", "remaining_time": "6:28:37"}
+{"current_steps": 251, "total_steps": 350, "loss": 0.3359, "lr": 1.7964120741915905e-05, "epoch": 3.5445719329214476, "percentage": 71.71, "elapsed_time": "16:15:25", "remaining_time": "6:24:43"}
+{"current_steps": 252, "total_steps": 350, "loss": 0.33, "lr": 1.7632283861170135e-05, "epoch": 3.558693733451015, "percentage": 72.0, "elapsed_time": "16:19:17", "remaining_time": "6:20:50"}
+{"current_steps": 253, "total_steps": 350, "loss": 0.3336, "lr": 1.7302671809648735e-05, "epoch": 3.5728155339805827, "percentage": 72.29, "elapsed_time": "16:23:09", "remaining_time": "6:16:56"}
+{"current_steps": 254, "total_steps": 350, "loss": 0.334, "lr": 1.6975317372573066e-05, "epoch": 3.58693733451015, "percentage": 72.57, "elapsed_time": "16:27:03", "remaining_time": "6:13:03"}
+{"current_steps": 255, "total_steps": 350, "loss": 0.3352, "lr": 1.6650253110608415e-05, "epoch": 3.6010591350397174, "percentage": 72.86, "elapsed_time": "16:30:56", "remaining_time": "6:09:10"}
+{"current_steps": 256, "total_steps": 350, "loss": 0.3339, "lr": 1.6327511356625302e-05, "epoch": 3.615180935569285, "percentage": 73.14, "elapsed_time": "16:34:48", "remaining_time": "6:05:17"}
+{"current_steps": 257, "total_steps": 350, "loss": 0.3303, "lr": 1.6007124212483453e-05, "epoch": 3.6293027360988526, "percentage": 73.43, "elapsed_time": "16:38:41", "remaining_time": "6:01:23"}
+{"current_steps": 258, "total_steps": 350, "loss": 0.3319, "lr": 1.5689123545838804e-05, "epoch": 3.6434245366284204, "percentage": 73.71, "elapsed_time": "16:42:33", "remaining_time": "5:57:30"}
+{"current_steps": 259, "total_steps": 350, "loss": 0.3285, "lr": 1.537354098697367e-05, "epoch": 3.6575463371579877, "percentage": 74.0, "elapsed_time": "16:46:27", "remaining_time": "5:53:37"}
+{"current_steps": 260, "total_steps": 350, "loss": 0.3346, "lr": 1.5060407925650662e-05, "epoch": 3.671668137687555, "percentage": 74.29, "elapsed_time": "16:50:20", "remaining_time": "5:49:43"}
+{"current_steps": 261, "total_steps": 350, "loss": 0.3265, "lr": 1.4749755507990449e-05, "epoch": 3.6857899382171224, "percentage": 74.57, "elapsed_time": "16:54:12", "remaining_time": "5:45:50"}
+{"current_steps": 262, "total_steps": 350, "loss": 0.3367, "lr": 1.4441614633373773e-05, "epoch": 3.69991173874669, "percentage": 74.86, "elapsed_time": "16:58:05", "remaining_time": "5:41:57"}
+{"current_steps": 263, "total_steps": 350, "loss": 0.335, "lr": 1.413601595136802e-05, "epoch": 3.7140335392762576, "percentage": 75.14, "elapsed_time": "17:01:58", "remaining_time": "5:38:04"}
+{"current_steps": 264, "total_steps": 350, "loss": 0.3324, "lr": 1.383298985867863e-05, "epoch": 3.7281553398058254, "percentage": 75.43, "elapsed_time": "17:05:51", "remaining_time": "5:34:10"}
+{"current_steps": 265, "total_steps": 350, "loss": 0.3313, "lr": 1.3532566496125634e-05, "epoch": 3.7422771403353927, "percentage": 75.71, "elapsed_time": "17:09:44", "remaining_time": "5:30:17"}
+{"current_steps": 266, "total_steps": 350, "loss": 0.3351, "lr": 1.3234775745645684e-05, "epoch": 3.75639894086496, "percentage": 76.0, "elapsed_time": "17:13:37", "remaining_time": "5:26:24"}
+{"current_steps": 267, "total_steps": 350, "loss": 0.3353, "lr": 1.2939647227319791e-05, "epoch": 3.770520741394528, "percentage": 76.29, "elapsed_time": "17:17:30", "remaining_time": "5:22:31"}
+{"current_steps": 268, "total_steps": 350, "loss": 0.3323, "lr": 1.2647210296427197e-05, "epoch": 3.784642541924095, "percentage": 76.57, "elapsed_time": "17:21:23", "remaining_time": "5:18:37"}
+{"current_steps": 269, "total_steps": 350, "loss": 0.3391, "lr": 1.2357494040525416e-05, "epoch": 3.798764342453663, "percentage": 76.86, "elapsed_time": "17:25:15", "remaining_time": "5:14:44"}
+{"current_steps": 270, "total_steps": 350, "loss": 0.3327, "lr": 1.2070527276557092e-05, "epoch": 3.8128861429832304, "percentage": 77.14, "elapsed_time": "17:29:08", "remaining_time": "5:10:51"}
+{"current_steps": 271, "total_steps": 350, "loss": 0.33, "lr": 1.178633854798365e-05, "epoch": 3.8270079435127977, "percentage": 77.43, "elapsed_time": "17:33:01", "remaining_time": "5:06:58"}
+{"current_steps": 272, "total_steps": 350, "loss": 0.3317, "lr": 1.1504956121946216e-05, "epoch": 3.8411297440423655, "percentage": 77.71, "elapsed_time": "17:36:54", "remaining_time": "5:03:04"}
+{"current_steps": 273, "total_steps": 350, "loss": 0.3294, "lr": 1.1226407986453963e-05, "epoch": 3.855251544571933, "percentage": 78.0, "elapsed_time": "17:40:47", "remaining_time": "4:59:11"}
+{"current_steps": 274, "total_steps": 350, "loss": 0.3282, "lr": 1.0950721847600282e-05, "epoch": 3.8693733451015007, "percentage": 78.29, "elapsed_time": "17:44:38", "remaining_time": "4:55:18"}
+{"current_steps": 275, "total_steps": 350, "loss": 0.335, "lr": 1.0677925126806956e-05, "epoch": 3.883495145631068, "percentage": 78.57, "elapsed_time": "17:48:31", "remaining_time": "4:51:24"}
+{"current_steps": 276, "total_steps": 350, "loss": 0.3352, "lr": 1.040804495809665e-05, "epoch": 3.8976169461606354, "percentage": 78.86, "elapsed_time": "17:52:23", "remaining_time": "4:47:31"}
+{"current_steps": 277, "total_steps": 350, "loss": 0.3307, "lr": 1.0141108185393995e-05, "epoch": 3.911738746690203, "percentage": 79.14, "elapsed_time": "17:56:15", "remaining_time": "4:43:38"}
+{"current_steps": 278, "total_steps": 350, "loss": 0.3316, "lr": 9.877141359855567e-06, "epoch": 3.9258605472197705, "percentage": 79.43, "elapsed_time": "18:00:07", "remaining_time": "4:39:44"}
+{"current_steps": 279, "total_steps": 350, "loss": 0.3301, "lr": 9.616170737228882e-06, "epoch": 3.9399823477493383, "percentage": 79.71, "elapsed_time": "18:03:59", "remaining_time": "4:35:51"}
+{"current_steps": 280, "total_steps": 350, "loss": 0.3309, "lr": 9.358222275240884e-06, "epoch": 3.9541041482789057, "percentage": 80.0, "elapsed_time": "18:07:51", "remaining_time": "4:31:57"}
+{"current_steps": 281, "total_steps": 350, "loss": 0.3294, "lr": 9.103321631016024e-06, "epoch": 3.968225948808473, "percentage": 80.29, "elapsed_time": "18:11:43", "remaining_time": "4:28:04"}
+{"current_steps": 282, "total_steps": 350, "loss": 0.3299, "lr": 8.851494158524242e-06, "epoch": 3.9823477493380404, "percentage": 80.57, "elapsed_time": "18:15:37", "remaining_time": "4:24:11"}
+{"current_steps": 283, "total_steps": 350, "loss": 0.3734, "lr": 8.602764906059109e-06, "epoch": 3.996469549867608, "percentage": 80.86, "elapsed_time": "18:19:25", "remaining_time": "4:20:17"}
+{"current_steps": 284, "total_steps": 350, "loss": 0.3432, "lr": 8.35715861374636e-06, "epoch": 4.010591350397176, "percentage": 81.14, "elapsed_time": "18:23:45", "remaining_time": "4:16:30"}
+{"current_steps": 285, "total_steps": 350, "loss": 0.3187, "lr": 8.114699711083113e-06, "epoch": 4.024713150926743, "percentage": 81.43, "elapsed_time": "18:27:37", "remaining_time": "4:12:37"}
+{"current_steps": 286, "total_steps": 350, "loss": 0.3213, "lr": 7.875412314507942e-06, "epoch": 4.038834951456311, "percentage": 81.71, "elapsed_time": "18:31:30", "remaining_time": "4:08:43"}
+{"current_steps": 287, "total_steps": 350, "loss": 0.3169, "lr": 7.639320225002106e-06, "epoch": 4.052956751985878, "percentage": 82.0, "elapsed_time": "18:35:22", "remaining_time": "4:04:50"}
+{"current_steps": 288, "total_steps": 350, "loss": 0.3148, "lr": 7.406446925722211e-06, "epoch": 4.067078552515445, "percentage": 82.29, "elapsed_time": "18:39:14", "remaining_time": "4:00:56"}
+{"current_steps": 289, "total_steps": 350, "loss": 0.3132, "lr": 7.176815579664343e-06, "epoch": 4.081200353045014, "percentage": 82.57, "elapsed_time": "18:43:06", "remaining_time": "3:57:03"}
+{"current_steps": 290, "total_steps": 350, "loss": 0.3175, "lr": 6.950449027360213e-06, "epoch": 4.095322153574581, "percentage": 82.86, "elapsed_time": "18:46:58", "remaining_time": "3:53:09"}
+{"current_steps": 291, "total_steps": 350, "loss": 0.3184, "lr": 6.7273697846052515e-06, "epoch": 4.109443954104148, "percentage": 83.14, "elapsed_time": "18:50:50", "remaining_time": "3:49:16"}
+{"current_steps": 292, "total_steps": 350, "loss": 0.3164, "lr": 6.507600040219073e-06, "epoch": 4.123565754633716, "percentage": 83.43, "elapsed_time": "18:54:42", "remaining_time": "3:45:23"}
+{"current_steps": 293, "total_steps": 350, "loss": 0.3177, "lr": 6.291161653838434e-06, "epoch": 4.137687555163283, "percentage": 83.71, "elapsed_time": "18:58:34", "remaining_time": "3:41:29"}
+{"current_steps": 294, "total_steps": 350, "loss": 0.3131, "lr": 6.078076153742962e-06, "epoch": 4.151809355692851, "percentage": 84.0, "elapsed_time": "19:02:27", "remaining_time": "3:37:36"}
+{"current_steps": 295, "total_steps": 350, "loss": 0.3142, "lr": 5.868364734713776e-06, "epoch": 4.165931156222419, "percentage": 84.29, "elapsed_time": "19:06:19", "remaining_time": "3:33:43"}
+{"current_steps": 296, "total_steps": 350, "loss": 0.3204, "lr": 5.662048255925357e-06, "epoch": 4.180052956751986, "percentage": 84.57, "elapsed_time": "19:10:12", "remaining_time": "3:29:50"}
+{"current_steps": 297, "total_steps": 350, "loss": 0.3158, "lr": 5.459147238870768e-06, "epoch": 4.194174757281553, "percentage": 84.86, "elapsed_time": "19:14:05", "remaining_time": "3:25:56"}
+{"current_steps": 298, "total_steps": 350, "loss": 0.3194, "lr": 5.259681865320447e-06, "epoch": 4.208296557811121, "percentage": 85.14, "elapsed_time": "19:17:58", "remaining_time": "3:22:03"}
+{"current_steps": 299, "total_steps": 350, "loss": 0.3163, "lr": 5.063671975314814e-06, "epoch": 4.222418358340688, "percentage": 85.43, "elapsed_time": "19:21:50", "remaining_time": "3:18:10"}
+{"current_steps": 300, "total_steps": 350, "loss": 0.315, "lr": 4.871137065190854e-06, "epoch": 4.236540158870256, "percentage": 85.71, "elapsed_time": "19:25:42", "remaining_time": "3:14:17"}
+{"current_steps": 301, "total_steps": 350, "loss": 0.3176, "lr": 4.6820962856429205e-06, "epoch": 4.250661959399824, "percentage": 86.0, "elapsed_time": "19:29:34", "remaining_time": "3:10:23"}
+{"current_steps": 302, "total_steps": 350, "loss": 0.322, "lr": 4.496568439817836e-06, "epoch": 4.264783759929391, "percentage": 86.29, "elapsed_time": "19:33:27", "remaining_time": "3:06:30"}
+{"current_steps": 303, "total_steps": 350, "loss": 0.311, "lr": 4.314571981444666e-06, "epoch": 4.278905560458958, "percentage": 86.57, "elapsed_time": "19:37:19", "remaining_time": "3:02:37"}
+{"current_steps": 304, "total_steps": 350, "loss": 0.3203, "lr": 4.136125012999168e-06, "epoch": 4.293027360988526, "percentage": 86.86, "elapsed_time": "19:41:11", "remaining_time": "2:58:44"}
+{"current_steps": 305, "total_steps": 350, "loss": 0.3161, "lr": 3.961245283903239e-06, "epoch": 4.307149161518094, "percentage": 87.14, "elapsed_time": "19:45:04", "remaining_time": "2:54:50"}
+{"current_steps": 306, "total_steps": 350, "loss": 0.315, "lr": 3.7899501887594102e-06, "epoch": 4.321270962047661, "percentage": 87.43, "elapsed_time": "19:48:56", "remaining_time": "2:50:57"}
+{"current_steps": 307, "total_steps": 350, "loss": 0.3165, "lr": 3.622256765620713e-06, "epoch": 4.335392762577229, "percentage": 87.71, "elapsed_time": "19:52:49", "remaining_time": "2:47:04"}
+{"current_steps": 308, "total_steps": 350, "loss": 0.3114, "lr": 3.458181694295961e-06, "epoch": 4.349514563106796, "percentage": 88.0, "elapsed_time": "19:56:42", "remaining_time": "2:43:11"}
+{"current_steps": 309, "total_steps": 350, "loss": 0.3125, "lr": 3.297741294690644e-06, "epoch": 4.363636363636363, "percentage": 88.29, "elapsed_time": "20:00:34", "remaining_time": "2:39:18"}
+{"current_steps": 310, "total_steps": 350, "loss": 0.3156, "lr": 3.140951525183691e-06, "epoch": 4.3777581641659316, "percentage": 88.57, "elapsed_time": "20:04:27", "remaining_time": "2:35:24"}
+{"current_steps": 311, "total_steps": 350, "loss": 0.3144, "lr": 2.987827981040132e-06, "epoch": 4.391879964695499, "percentage": 88.86, "elapsed_time": "20:08:20", "remaining_time": "2:31:31"}
+{"current_steps": 312, "total_steps": 350, "loss": 0.3157, "lr": 2.8383858928598963e-06, "epoch": 4.406001765225066, "percentage": 89.14, "elapsed_time": "20:12:12", "remaining_time": "2:27:38"}
+{"current_steps": 313, "total_steps": 350, "loss": 0.3116, "lr": 2.692640125062895e-06, "epoch": 4.420123565754634, "percentage": 89.43, "elapsed_time": "20:16:04", "remaining_time": "2:23:45"}
+{"current_steps": 314, "total_steps": 350, "loss": 0.3206, "lr": 2.550605174410512e-06, "epoch": 4.434245366284201, "percentage": 89.71, "elapsed_time": "20:19:56", "remaining_time": "2:19:51"}
+{"current_steps": 315, "total_steps": 350, "loss": 0.3119, "lr": 2.4122951685636674e-06, "epoch": 4.448367166813769, "percentage": 90.0, "elapsed_time": "20:23:47", "remaining_time": "2:15:58"}
+{"current_steps": 316, "total_steps": 350, "loss": 0.314, "lr": 2.2777238646775768e-06, "epoch": 4.4624889673433366, "percentage": 90.29, "elapsed_time": "20:27:39", "remaining_time": "2:12:05"}
+{"current_steps": 317, "total_steps": 350, "loss": 0.3116, "lr": 2.14690464803343e-06, "epoch": 4.476610767872904, "percentage": 90.57, "elapsed_time": "20:31:33", "remaining_time": "2:08:12"}
+{"current_steps": 318, "total_steps": 350, "loss": 0.3162, "lr": 2.0198505307069462e-06, "epoch": 4.490732568402471, "percentage": 90.86, "elapsed_time": "20:35:25", "remaining_time": "2:04:19"}
+{"current_steps": 319, "total_steps": 350, "loss": 0.318, "lr": 1.896574150274151e-06, "epoch": 4.504854368932039, "percentage": 91.14, "elapsed_time": "20:39:18", "remaining_time": "2:00:26"}
+{"current_steps": 320, "total_steps": 350, "loss": 0.3146, "lr": 1.7770877685543687e-06, "epoch": 4.518976169461606, "percentage": 91.43, "elapsed_time": "20:43:10", "remaining_time": "1:56:32"}
+{"current_steps": 321, "total_steps": 350, "loss": 0.3188, "lr": 1.6614032703905714e-06, "epoch": 4.533097969991174, "percentage": 91.71, "elapsed_time": "20:47:03", "remaining_time": "1:52:39"}
+{"current_steps": 322, "total_steps": 350, "loss": 0.3117, "lr": 1.5495321624672443e-06, "epoch": 4.5472197705207416, "percentage": 92.0, "elapsed_time": "20:50:55", "remaining_time": "1:48:46"}
+{"current_steps": 323, "total_steps": 350, "loss": 0.3179, "lr": 1.4414855721658705e-06, "epoch": 4.561341571050309, "percentage": 92.29, "elapsed_time": "20:54:47", "remaining_time": "1:44:53"}
+{"current_steps": 324, "total_steps": 350, "loss": 0.3169, "lr": 1.3372742464581134e-06, "epoch": 4.575463371579876, "percentage": 92.57, "elapsed_time": "20:58:39", "remaining_time": "1:41:00"}
+{"current_steps": 325, "total_steps": 350, "loss": 0.313, "lr": 1.2369085508368862e-06, "epoch": 4.589585172109444, "percentage": 92.86, "elapsed_time": "21:02:32", "remaining_time": "1:37:07"}
+{"current_steps": 326, "total_steps": 350, "loss": 0.3162, "lr": 1.1403984682852998e-06, "epoch": 4.603706972639012, "percentage": 93.14, "elapsed_time": "21:06:24", "remaining_time": "1:33:13"}
+{"current_steps": 327, "total_steps": 350, "loss": 0.3169, "lr": 1.0477535982837473e-06, "epoch": 4.617828773168579, "percentage": 93.43, "elapsed_time": "21:10:18", "remaining_time": "1:29:20"}
+{"current_steps": 328, "total_steps": 350, "loss": 0.3147, "lr": 9.589831558550222e-07, "epoch": 4.631950573698147, "percentage": 93.71, "elapsed_time": "21:14:10", "remaining_time": "1:25:27"}
+{"current_steps": 329, "total_steps": 350, "loss": 0.3155, "lr": 8.740959706477725e-07, "epoch": 4.646072374227714, "percentage": 94.0, "elapsed_time": "21:18:02", "remaining_time": "1:21:34"}
+{"current_steps": 330, "total_steps": 350, "loss": 0.3172, "lr": 7.93100486058247e-07, "epoch": 4.660194174757281, "percentage": 94.29, "elapsed_time": "21:21:55", "remaining_time": "1:17:41"}
+{"current_steps": 331, "total_steps": 350, "loss": 0.3123, "lr": 7.160047583904473e-07, "epoch": 4.674315975286849, "percentage": 94.57, "elapsed_time": "21:25:47", "remaining_time": "1:13:48"}
+{"current_steps": 332, "total_steps": 350, "loss": 0.3126, "lr": 6.428164560548134e-07, "epoch": 4.688437775816417, "percentage": 94.86, "elapsed_time": "21:29:39", "remaining_time": "1:09:55"}
+{"current_steps": 333, "total_steps": 350, "loss": 0.3091, "lr": 5.735428588054825e-07, "epoch": 4.702559576345984, "percentage": 95.14, "elapsed_time": "21:33:33", "remaining_time": "1:06:02"}
+{"current_steps": 334, "total_steps": 350, "loss": 0.3168, "lr": 5.081908570161753e-07, "epoch": 4.716681376875552, "percentage": 95.43, "elapsed_time": "21:37:26", "remaining_time": "1:02:09"}
+{"current_steps": 335, "total_steps": 350, "loss": 0.3168, "lr": 4.467669509948591e-07, "epoch": 4.730803177405119, "percentage": 95.71, "elapsed_time": "21:41:17", "remaining_time": "0:58:16"}
+{"current_steps": 336, "total_steps": 350, "loss": 0.3096, "lr": 3.8927725033718553e-07, "epoch": 4.744924977934687, "percentage": 96.0, "elapsed_time": "21:45:09", "remaining_time": "0:54:22"}
+{"current_steps": 337, "total_steps": 350, "loss": 0.3127, "lr": 3.3572747331878984e-07, "epoch": 4.7590467784642545, "percentage": 96.29, "elapsed_time": "21:49:02", "remaining_time": "0:50:29"}
+{"current_steps": 338, "total_steps": 350, "loss": 0.3165, "lr": 2.8612294632650586e-07, "epoch": 4.773168578993822, "percentage": 96.57, "elapsed_time": "21:52:54", "remaining_time": "0:46:36"}
+{"current_steps": 339, "total_steps": 350, "loss": 0.3211, "lr": 2.404686033285897e-07, "epoch": 4.787290379523389, "percentage": 96.86, "elapsed_time": "21:56:46", "remaining_time": "0:42:43"}
+{"current_steps": 340, "total_steps": 350, "loss": 0.3139, "lr": 1.9876898538394362e-07, "epoch": 4.801412180052957, "percentage": 97.14, "elapsed_time": "22:00:40", "remaining_time": "0:38:50"}
+{"current_steps": 341, "total_steps": 350, "loss": 0.3119, "lr": 1.6102824019043728e-07, "epoch": 4.815533980582524, "percentage": 97.43, "elapsed_time": "22:04:32", "remaining_time": "0:34:57"}
+{"current_steps": 342, "total_steps": 350, "loss": 0.3189, "lr": 1.2725012167236207e-07, "epoch": 4.829655781112092, "percentage": 97.71, "elapsed_time": "22:08:24", "remaining_time": "0:31:04"}
+{"current_steps": 343, "total_steps": 350, "loss": 0.3144, "lr": 9.74379896070321e-08, "epoch": 4.8437775816416595, "percentage": 98.0, "elapsed_time": "22:12:17", "remaining_time": "0:27:11"}
+{"current_steps": 344, "total_steps": 350, "loss": 0.3208, "lr": 7.159480929059381e-08, "epoch": 4.857899382171227, "percentage": 98.29, "elapsed_time": "22:16:10", "remaining_time": "0:23:18"}
+{"current_steps": 345, "total_steps": 350, "loss": 0.3164, "lr": 4.9723151243106225e-08, "epoch": 4.872021182700794, "percentage": 98.57, "elapsed_time": "22:20:03", "remaining_time": "0:19:25"}
+{"current_steps": 346, "total_steps": 350, "loss": 0.3183, "lr": 3.1825190952829986e-08, "epoch": 4.886142983230362, "percentage": 98.86, "elapsed_time": "22:23:56", "remaining_time": "0:15:32"}
+{"current_steps": 347, "total_steps": 350, "loss": 0.3185, "lr": 1.7902708659867096e-08, "epoch": 4.90026478375993, "percentage": 99.14, "elapsed_time": "22:27:49", "remaining_time": "0:11:39"}
+{"current_steps": 348, "total_steps": 350, "loss": 0.3142, "lr": 7.957089179058131e-09, "epoch": 4.914386584289497, "percentage": 99.43, "elapsed_time": "22:31:43", "remaining_time": "0:07:46"}
+{"current_steps": 349, "total_steps": 350, "loss": 0.3181, "lr": 1.9893217622790616e-09, "epoch": 4.9285083848190645, "percentage": 99.71, "elapsed_time": "22:35:35", "remaining_time": "0:03:53"}
+{"current_steps": 350, "total_steps": 350, "loss": 0.313, "lr": 0.0, "epoch": 4.942630185348632, "percentage": 100.0, "elapsed_time": "22:39:28", "remaining_time": "0:00:00"}
+{"current_steps": 350, "total_steps": 350, "epoch": 4.942630185348632, "percentage": 100.0, "elapsed_time": "22:39:58", "remaining_time": "0:00:00"}
+{"current_steps": 350, "total_steps": 350, "epoch": 4.942630185348632, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2492 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.942630185348632,
+  "eval_steps": 500,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01412180052956752,
+      "grad_norm": 5.979931009348192,
+      "learning_rate": 2.285714285714286e-06,
+      "loss": 0.8154,
+      "step": 1
+    },
+    {
+      "epoch": 0.02824360105913504,
+      "grad_norm": 6.047301062181586,
+      "learning_rate": 4.571428571428572e-06,
+      "loss": 0.8243,
+      "step": 2
+    },
+    {
+      "epoch": 0.04236540158870256,
+      "grad_norm": 5.589397434568418,
+      "learning_rate": 6.857142857142858e-06,
+      "loss": 0.8057,
+      "step": 3
+    },
+    {
+      "epoch": 0.05648720211827008,
+      "grad_norm": 4.017126644109988,
+      "learning_rate": 9.142857142857144e-06,
+      "loss": 0.7602,
+      "step": 4
+    },
+    {
+      "epoch": 0.0706090026478376,
+      "grad_norm": 2.1627060531795967,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.7197,
+      "step": 5
+    },
+    {
+      "epoch": 0.08473080317740513,
+      "grad_norm": 4.667143281538081,
+      "learning_rate": 1.3714285714285716e-05,
+      "loss": 0.7374,
+      "step": 6
+    },
+    {
+      "epoch": 0.09885260370697264,
+      "grad_norm": 6.545492179001986,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7325,
+      "step": 7
+    },
+    {
+      "epoch": 0.11297440423654016,
+      "grad_norm": 7.281711055430636,
+      "learning_rate": 1.8285714285714288e-05,
+      "loss": 0.7502,
+      "step": 8
+    },
+    {
+      "epoch": 0.12709620476610767,
+      "grad_norm": 4.392674048119666,
+      "learning_rate": 2.057142857142857e-05,
+      "loss": 0.7051,
+      "step": 9
+    },
+    {
+      "epoch": 0.1412180052956752,
+      "grad_norm": 2.9074563359884973,
+      "learning_rate": 2.2857142857142858e-05,
+      "loss": 0.6593,
+      "step": 10
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 2.205323794009288,
+      "learning_rate": 2.5142857142857143e-05,
+      "loss": 0.6276,
+      "step": 11
+    },
+    {
+      "epoch": 0.16946160635481025,
+      "grad_norm": 1.4150033586173336,
+      "learning_rate": 2.742857142857143e-05,
+      "loss": 0.6013,
+      "step": 12
+    },
+    {
+      "epoch": 0.18358340688437777,
+      "grad_norm": 1.3251831618492345,
+      "learning_rate": 2.9714285714285717e-05,
+      "loss": 0.5859,
+      "step": 13
+    },
+    {
+      "epoch": 0.1977052074139453,
+      "grad_norm": 3.1805546649918544,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.5824,
+      "step": 14
+    },
+    {
+      "epoch": 0.2118270079435128,
+      "grad_norm": 1.4989971887780031,
+      "learning_rate": 3.4285714285714284e-05,
+      "loss": 0.5708,
+      "step": 15
+    },
+    {
+      "epoch": 0.22594880847308033,
+      "grad_norm": 1.203788524759605,
+      "learning_rate": 3.6571428571428576e-05,
+      "loss": 0.5563,
+      "step": 16
+    },
+    {
+      "epoch": 0.24007060900264784,
+      "grad_norm": 1.3578810581727971,
+      "learning_rate": 3.885714285714286e-05,
+      "loss": 0.5566,
+      "step": 17
+    },
+    {
+      "epoch": 0.25419240953221534,
+      "grad_norm": 0.8074275719021523,
+      "learning_rate": 4.114285714285714e-05,
+      "loss": 0.5507,
+      "step": 18
+    },
+    {
+      "epoch": 0.26831421006178285,
+      "grad_norm": 1.1227844753364196,
+      "learning_rate": 4.342857142857143e-05,
+      "loss": 0.5418,
+      "step": 19
+    },
+    {
+      "epoch": 0.2824360105913504,
+      "grad_norm": 0.8760389990351023,
+      "learning_rate": 4.5714285714285716e-05,
+      "loss": 0.5333,
+      "step": 20
+    },
+    {
+      "epoch": 0.2965578111209179,
+      "grad_norm": 1.1881496989284341,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5305,
+      "step": 21
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.9681459485298871,
+      "learning_rate": 5.0285714285714286e-05,
+      "loss": 0.5189,
+      "step": 22
+    },
+    {
+      "epoch": 0.324801412180053,
+      "grad_norm": 1.4344211614758422,
+      "learning_rate": 5.257142857142858e-05,
+      "loss": 0.5198,
+      "step": 23
+    },
+    {
+      "epoch": 0.3389232127096205,
+      "grad_norm": 0.8492140987790524,
+      "learning_rate": 5.485714285714286e-05,
+      "loss": 0.5102,
+      "step": 24
+    },
+    {
+      "epoch": 0.353045013239188,
+      "grad_norm": 1.2351656998878342,
+      "learning_rate": 5.714285714285715e-05,
+      "loss": 0.5098,
+      "step": 25
+    },
+    {
+      "epoch": 0.36716681376875554,
+      "grad_norm": 0.898578091846962,
+      "learning_rate": 5.9428571428571434e-05,
+      "loss": 0.5015,
+      "step": 26
+    },
+    {
+      "epoch": 0.38128861429832306,
+      "grad_norm": 1.5089247050740433,
+      "learning_rate": 6.171428571428573e-05,
+      "loss": 0.507,
+      "step": 27
+    },
+    {
+      "epoch": 0.3954104148278906,
+      "grad_norm": 0.9864208925736987,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.5034,
+      "step": 28
+    },
+    {
+      "epoch": 0.4095322153574581,
+      "grad_norm": 1.0206985743120736,
+      "learning_rate": 6.62857142857143e-05,
+      "loss": 0.4983,
+      "step": 29
+    },
+    {
+      "epoch": 0.4236540158870256,
+      "grad_norm": 1.4229934179471342,
+      "learning_rate": 6.857142857142857e-05,
+      "loss": 0.508,
+      "step": 30
+    },
+    {
+      "epoch": 0.43777581641659313,
+      "grad_norm": 0.9625460430091453,
+      "learning_rate": 7.085714285714287e-05,
+      "loss": 0.5016,
+      "step": 31
+    },
+    {
+      "epoch": 0.45189761694616065,
+      "grad_norm": 1.1144628190568628,
+      "learning_rate": 7.314285714285715e-05,
+      "loss": 0.4939,
+      "step": 32
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.9463549200929555,
+      "learning_rate": 7.542857142857144e-05,
+      "loss": 0.4924,
+      "step": 33
+    },
+    {
+      "epoch": 0.4801412180052957,
+      "grad_norm": 0.8892598203382347,
+      "learning_rate": 7.771428571428572e-05,
+      "loss": 0.4902,
+      "step": 34
+    },
+    {
+      "epoch": 0.4942630185348632,
+      "grad_norm": 0.9413854750510515,
+      "learning_rate": 8e-05,
+      "loss": 0.4852,
+      "step": 35
+    },
+    {
+      "epoch": 0.5083848190644307,
+      "grad_norm": 0.9034630826375731,
+      "learning_rate": 7.999801067823773e-05,
+      "loss": 0.4853,
+      "step": 36
+    },
+    {
+      "epoch": 0.5225066195939982,
+      "grad_norm": 1.2269858722315412,
+      "learning_rate": 7.999204291082095e-05,
+      "loss": 0.4764,
+      "step": 37
+    },
+    {
+      "epoch": 0.5366284201235657,
+      "grad_norm": 0.9045227868888749,
+      "learning_rate": 7.998209729134014e-05,
+      "loss": 0.4809,
+      "step": 38
+    },
+    {
+      "epoch": 0.5507502206531333,
+      "grad_norm": 1.2176978127037603,
+      "learning_rate": 7.996817480904718e-05,
+      "loss": 0.4719,
+      "step": 39
+    },
+    {
+      "epoch": 0.5648720211827007,
+      "grad_norm": 1.2333419409501036,
+      "learning_rate": 7.99502768487569e-05,
+      "loss": 0.477,
+      "step": 40
+    },
+    {
+      "epoch": 0.5789938217122683,
+      "grad_norm": 0.7483281237491166,
+      "learning_rate": 7.99284051907094e-05,
+      "loss": 0.4724,
+      "step": 41
+    },
+    {
+      "epoch": 0.5931156222418358,
+      "grad_norm": 0.6151558817864059,
+      "learning_rate": 7.990256201039297e-05,
+      "loss": 0.4662,
+      "step": 42
+    },
+    {
+      "epoch": 0.6072374227714034,
+      "grad_norm": 0.6814568571856022,
+      "learning_rate": 7.987274987832764e-05,
+      "loss": 0.4621,
+      "step": 43
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.9240497143419791,
+      "learning_rate": 7.983897175980957e-05,
+      "loss": 0.4665,
+      "step": 44
+    },
+    {
+      "epoch": 0.6354810238305384,
+      "grad_norm": 1.2034986971304784,
+      "learning_rate": 7.980123101461606e-05,
+      "loss": 0.4761,
+      "step": 45
+    },
+    {
+      "epoch": 0.649602824360106,
+      "grad_norm": 0.8192788227089312,
+      "learning_rate": 7.975953139667141e-05,
+      "loss": 0.4652,
+      "step": 46
+    },
+    {
+      "epoch": 0.6637246248896734,
+      "grad_norm": 0.7683306980890072,
+      "learning_rate": 7.97138770536735e-05,
+      "loss": 0.4619,
+      "step": 47
+    },
+    {
+      "epoch": 0.677846425419241,
+      "grad_norm": 0.7567015766907312,
+      "learning_rate": 7.966427252668121e-05,
+      "loss": 0.4638,
+      "step": 48
+    },
+    {
+      "epoch": 0.6919682259488085,
+      "grad_norm": 0.6846820764750615,
+      "learning_rate": 7.961072274966282e-05,
+      "loss": 0.4527,
+      "step": 49
+    },
+    {
+      "epoch": 0.706090026478376,
+      "grad_norm": 0.7395598100512276,
+      "learning_rate": 7.955323304900514e-05,
+      "loss": 0.4571,
+      "step": 50
+    },
+    {
+      "epoch": 0.7202118270079435,
+      "grad_norm": 0.5351232158771764,
+      "learning_rate": 7.949180914298383e-05,
+      "loss": 0.4496,
+      "step": 51
+    },
+    {
+      "epoch": 0.7343336275375111,
+      "grad_norm": 0.6324424558337066,
+      "learning_rate": 7.942645714119452e-05,
+      "loss": 0.4593,
+      "step": 52
+    },
+    {
+      "epoch": 0.7484554280670785,
+      "grad_norm": 0.547964739600884,
+      "learning_rate": 7.93571835439452e-05,
+      "loss": 0.4502,
+      "step": 53
+    },
+    {
+      "epoch": 0.7625772285966461,
+      "grad_norm": 0.7115536296101671,
+      "learning_rate": 7.928399524160956e-05,
+      "loss": 0.447,
+      "step": 54
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.742782814289987,
+      "learning_rate": 7.920689951394175e-05,
+      "loss": 0.4461,
+      "step": 55
+    },
+    {
+      "epoch": 0.7908208296557812,
+      "grad_norm": 0.6862659469941464,
+      "learning_rate": 7.912590402935223e-05,
+      "loss": 0.4473,
+      "step": 56
+    },
+    {
+      "epoch": 0.8049426301853486,
+      "grad_norm": 0.6235041641613883,
+      "learning_rate": 7.904101684414498e-05,
+      "loss": 0.4472,
+      "step": 57
+    },
+    {
+      "epoch": 0.8190644307149162,
+      "grad_norm": 0.44600795869954046,
+      "learning_rate": 7.895224640171625e-05,
+      "loss": 0.4442,
+      "step": 58
+    },
+    {
+      "epoch": 0.8331862312444837,
+      "grad_norm": 0.48251979778530707,
+      "learning_rate": 7.88596015317147e-05,
+      "loss": 0.4449,
+      "step": 59
+    },
+    {
+      "epoch": 0.8473080317740512,
+      "grad_norm": 0.4787558150068957,
+      "learning_rate": 7.876309144916312e-05,
+      "loss": 0.4433,
+      "step": 60
+    },
+    {
+      "epoch": 0.8614298323036187,
+      "grad_norm": 0.41827598666685606,
+      "learning_rate": 7.86627257535419e-05,
+      "loss": 0.4401,
+      "step": 61
+    },
+    {
+      "epoch": 0.8755516328331863,
+      "grad_norm": 0.4724100749619687,
+      "learning_rate": 7.855851442783414e-05,
+      "loss": 0.4374,
+      "step": 62
+    },
+    {
+      "epoch": 0.8896734333627537,
+      "grad_norm": 0.6571994588226032,
+      "learning_rate": 7.845046783753276e-05,
+      "loss": 0.4409,
+      "step": 63
+    },
+    {
+      "epoch": 0.9037952338923213,
+      "grad_norm": 0.9369294338435781,
+      "learning_rate": 7.833859672960943e-05,
+      "loss": 0.4407,
+      "step": 64
+    },
+    {
+      "epoch": 0.9179170344218888,
+      "grad_norm": 1.1601560447987704,
+      "learning_rate": 7.822291223144564e-05,
+      "loss": 0.4602,
+      "step": 65
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.6934703654331164,
+      "learning_rate": 7.810342584972585e-05,
+      "loss": 0.4369,
+      "step": 66
+    },
+    {
+      "epoch": 0.9461606354810238,
+      "grad_norm": 0.5791439547503463,
+      "learning_rate": 7.798014946929306e-05,
+      "loss": 0.4356,
+      "step": 67
+    },
+    {
+      "epoch": 0.9602824360105914,
+      "grad_norm": 0.8373041828808443,
+      "learning_rate": 7.785309535196657e-05,
+      "loss": 0.4504,
+      "step": 68
+    },
+    {
+      "epoch": 0.9744042365401588,
+      "grad_norm": 0.6796500376958069,
+      "learning_rate": 7.772227613532242e-05,
+      "loss": 0.4392,
+      "step": 69
+    },
+    {
+      "epoch": 0.9885260370697264,
+      "grad_norm": 0.6686880597044009,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.4474,
+      "step": 70
+    },
+    {
+      "epoch": 1.002647837599294,
+      "grad_norm": 0.6901488338737102,
+      "learning_rate": 7.74493948255895e-05,
+      "loss": 0.5108,
+      "step": 71
+    },
+    {
+      "epoch": 1.0167696381288613,
+      "grad_norm": 0.7139924415191212,
+      "learning_rate": 7.730735987493711e-05,
+      "loss": 0.4227,
+      "step": 72
+    },
+    {
+      "epoch": 1.030891438658429,
+      "grad_norm": 0.7623382444431029,
+      "learning_rate": 7.71616141071401e-05,
+      "loss": 0.419,
+      "step": 73
+    },
+    {
+      "epoch": 1.0450132391879965,
+      "grad_norm": 0.8179708530719029,
+      "learning_rate": 7.701217201895987e-05,
+      "loss": 0.4182,
+      "step": 74
+    },
+    {
+      "epoch": 1.059135039717564,
+      "grad_norm": 0.6036364923611257,
+      "learning_rate": 7.685904847481631e-05,
+      "loss": 0.4147,
+      "step": 75
+    },
+    {
+      "epoch": 1.0732568402471314,
+      "grad_norm": 0.5415944966587694,
+      "learning_rate": 7.670225870530936e-05,
+      "loss": 0.4192,
+      "step": 76
+    },
+    {
+      "epoch": 1.087378640776699,
+      "grad_norm": 0.548496642769106,
+      "learning_rate": 7.654181830570404e-05,
+      "loss": 0.4193,
+      "step": 77
+    },
+    {
+      "epoch": 1.1015004413062666,
+      "grad_norm": 0.4357435844414465,
+      "learning_rate": 7.637774323437929e-05,
+      "loss": 0.4126,
+      "step": 78
+    },
+    {
+      "epoch": 1.1156222418358341,
+      "grad_norm": 0.5890851003105865,
+      "learning_rate": 7.62100498112406e-05,
+      "loss": 0.4193,
+      "step": 79
+    },
+    {
+      "epoch": 1.1297440423654015,
+      "grad_norm": 0.5417176133106055,
+      "learning_rate": 7.603875471609677e-05,
+      "loss": 0.4069,
+      "step": 80
+    },
+    {
+      "epoch": 1.143865842894969,
+      "grad_norm": 0.5234067170715418,
+      "learning_rate": 7.586387498700084e-05,
+      "loss": 0.4187,
+      "step": 81
+    },
+    {
+      "epoch": 1.1579876434245366,
+      "grad_norm": 0.4795761329002007,
+      "learning_rate": 7.568542801855535e-05,
+      "loss": 0.4101,
+      "step": 82
+    },
+    {
+      "epoch": 1.1721094439541042,
+      "grad_norm": 0.510485207368403,
+      "learning_rate": 7.550343156018217e-05,
+      "loss": 0.4074,
+      "step": 83
+    },
+    {
+      "epoch": 1.1862312444836718,
+      "grad_norm": 0.5160993194955293,
+      "learning_rate": 7.531790371435709e-05,
+      "loss": 0.4105,
+      "step": 84
+    },
+    {
+      "epoch": 1.2003530450132391,
+      "grad_norm": 0.6272135654421417,
+      "learning_rate": 7.512886293480914e-05,
+      "loss": 0.4131,
+      "step": 85
+    },
+    {
+      "epoch": 1.2144748455428067,
+      "grad_norm": 0.7144516241332823,
+      "learning_rate": 7.49363280246852e-05,
+      "loss": 0.4123,
+      "step": 86
+    },
+    {
+      "epoch": 1.2285966460723743,
+      "grad_norm": 1.0197175196301183,
+      "learning_rate": 7.474031813467956e-05,
+      "loss": 0.4199,
+      "step": 87
+    },
+    {
+      "epoch": 1.2427184466019416,
+      "grad_norm": 0.9885970877399597,
+      "learning_rate": 7.454085276112925e-05,
+      "loss": 0.4152,
+      "step": 88
+    },
+    {
+      "epoch": 1.2568402471315092,
+      "grad_norm": 0.5518795345815659,
+      "learning_rate": 7.433795174407465e-05,
+      "loss": 0.4064,
+      "step": 89
+    },
+    {
+      "epoch": 1.2709620476610768,
+      "grad_norm": 0.42697954065556326,
+      "learning_rate": 7.413163526528623e-05,
+      "loss": 0.409,
+      "step": 90
+    },
+    {
+      "epoch": 1.2850838481906444,
+      "grad_norm": 0.698380780251885,
+      "learning_rate": 7.392192384625704e-05,
+      "loss": 0.4054,
+      "step": 91
+    },
+    {
+      "epoch": 1.299205648720212,
+      "grad_norm": 0.6703174317830842,
+      "learning_rate": 7.370883834616157e-05,
+      "loss": 0.4099,
+      "step": 92
+    },
+    {
+      "epoch": 1.3133274492497793,
+      "grad_norm": 0.3951173073488556,
+      "learning_rate": 7.349239995978095e-05,
+      "loss": 0.4084,
+      "step": 93
+    },
+    {
+      "epoch": 1.3274492497793469,
+      "grad_norm": 0.43174109319559356,
+      "learning_rate": 7.327263021539478e-05,
+      "loss": 0.4048,
+      "step": 94
+    },
+    {
+      "epoch": 1.3415710503089144,
+      "grad_norm": 0.5360712514545947,
+      "learning_rate": 7.30495509726398e-05,
+      "loss": 0.4068,
+      "step": 95
+    },
+    {
+      "epoch": 1.3556928508384818,
+      "grad_norm": 0.42774436448586106,
+      "learning_rate": 7.282318442033567e-05,
+      "loss": 0.4034,
+      "step": 96
+    },
+    {
+      "epoch": 1.3698146513680494,
+      "grad_norm": 0.5210499488927217,
+      "learning_rate": 7.259355307427781e-05,
+      "loss": 0.4078,
+      "step": 97
+    },
+    {
+      "epoch": 1.383936451897617,
+      "grad_norm": 0.7093148406292331,
+      "learning_rate": 7.236067977499791e-05,
+      "loss": 0.4084,
+      "step": 98
+    },
+    {
+      "epoch": 1.3980582524271845,
+      "grad_norm": 0.8196300420238753,
+      "learning_rate": 7.212458768549208e-05,
+      "loss": 0.4069,
+      "step": 99
+    },
+    {
+      "epoch": 1.412180052956752,
+      "grad_norm": 0.9973540383790642,
+      "learning_rate": 7.188530028891691e-05,
+      "loss": 0.4047,
+      "step": 100
+    },
+    {
+      "epoch": 1.4263018534863194,
+      "grad_norm": 1.0704815886198962,
+      "learning_rate": 7.164284138625367e-05,
+      "loss": 0.4075,
+      "step": 101
+    },
+    {
+      "epoch": 1.440423654015887,
+      "grad_norm": 0.5848553932345868,
+      "learning_rate": 7.13972350939409e-05,
+      "loss": 0.4036,
+      "step": 102
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.37289550464762866,
+      "learning_rate": 7.114850584147577e-05,
+      "loss": 0.4068,
+      "step": 103
+    },
+    {
+      "epoch": 1.468667255075022,
+      "grad_norm": 0.6651429035225815,
+      "learning_rate": 7.089667836898399e-05,
+      "loss": 0.4053,
+      "step": 104
+    },
+    {
+      "epoch": 1.4827890556045895,
+      "grad_norm": 0.6931193008736451,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.4002,
+      "step": 105
+    },
+    {
+      "epoch": 1.496910856134157,
+      "grad_norm": 0.3938085941153356,
+      "learning_rate": 7.038382926277113e-05,
+      "loss": 0.4013,
+      "step": 106
+    },
+    {
+      "epoch": 1.5110326566637247,
+      "grad_norm": 0.410899316731272,
+      "learning_rate": 7.012285864014445e-05,
+      "loss": 0.404,
+      "step": 107
+    },
+    {
+      "epoch": 1.5251544571932922,
+      "grad_norm": 0.5933306150673846,
+      "learning_rate": 6.985889181460602e-05,
+      "loss": 0.3992,
+      "step": 108
+    },
+    {
+      "epoch": 1.5392762577228596,
+      "grad_norm": 0.47465582200581674,
+      "learning_rate": 6.959195504190337e-05,
+      "loss": 0.4022,
+      "step": 109
+    },
+    {
+      "epoch": 1.5533980582524272,
+      "grad_norm": 0.29047076547162964,
+      "learning_rate": 6.932207487319305e-05,
+      "loss": 0.3933,
+      "step": 110
+    },
+    {
+      "epoch": 1.5675198587819947,
+      "grad_norm": 0.3955673661524972,
+      "learning_rate": 6.904927815239972e-05,
+      "loss": 0.4014,
+      "step": 111
+    },
+    {
+      "epoch": 1.581641659311562,
+      "grad_norm": 0.4729958849916794,
+      "learning_rate": 6.877359201354606e-05,
+      "loss": 0.4014,
+      "step": 112
+    },
+    {
+      "epoch": 1.5957634598411299,
+      "grad_norm": 0.3117935062342313,
+      "learning_rate": 6.84950438780538e-05,
+      "loss": 0.4021,
+      "step": 113
+    },
+    {
+      "epoch": 1.6098852603706972,
+      "grad_norm": 0.29707807435124145,
+      "learning_rate": 6.821366145201636e-05,
+      "loss": 0.4003,
+      "step": 114
+    },
+    {
+      "epoch": 1.6240070609002648,
+      "grad_norm": 0.43753418225532925,
+      "learning_rate": 6.792947272344292e-05,
+      "loss": 0.3992,
+      "step": 115
+    },
+    {
+      "epoch": 1.6381288614298324,
+      "grad_norm": 0.27791625901461003,
+      "learning_rate": 6.76425059594746e-05,
+      "loss": 0.3982,
+      "step": 116
+    },
+    {
+      "epoch": 1.6522506619593997,
+      "grad_norm": 0.2525501356536547,
+      "learning_rate": 6.73527897035728e-05,
+      "loss": 0.4053,
+      "step": 117
+    },
+    {
+      "epoch": 1.6663724624889673,
+      "grad_norm": 0.3669470139311434,
+      "learning_rate": 6.706035277268022e-05,
+      "loss": 0.4024,
+      "step": 118
+    },
+    {
+      "epoch": 1.6804942630185349,
+      "grad_norm": 0.30825865476024705,
+      "learning_rate": 6.676522425435433e-05,
+      "loss": 0.3945,
+      "step": 119
+    },
+    {
+      "epoch": 1.6946160635481022,
+      "grad_norm": 0.28018108144253323,
+      "learning_rate": 6.646743350387438e-05,
+      "loss": 0.3984,
+      "step": 120
+    },
+    {
+      "epoch": 1.70873786407767,
+      "grad_norm": 0.30987982118204843,
+      "learning_rate": 6.616701014132138e-05,
+      "loss": 0.4021,
+      "step": 121
+    },
+    {
+      "epoch": 1.7228596646072374,
+      "grad_norm": 0.3633571089136772,
+      "learning_rate": 6.586398404863198e-05,
+      "loss": 0.4026,
+      "step": 122
+    },
+    {
+      "epoch": 1.736981465136805,
+      "grad_norm": 0.36013913213670684,
+      "learning_rate": 6.555838536662624e-05,
+      "loss": 0.3925,
+      "step": 123
+    },
+    {
+      "epoch": 1.7511032656663725,
+      "grad_norm": 0.36709693358558493,
+      "learning_rate": 6.525024449200956e-05,
+      "loss": 0.3976,
+      "step": 124
+    },
+    {
+      "epoch": 1.7652250661959399,
+      "grad_norm": 0.44695442666677676,
+      "learning_rate": 6.493959207434934e-05,
+      "loss": 0.3982,
+      "step": 125
+    },
+    {
+      "epoch": 1.7793468667255075,
+      "grad_norm": 0.4500722428050271,
+      "learning_rate": 6.462645901302633e-05,
+      "loss": 0.3947,
+      "step": 126
+    },
+    {
+      "epoch": 1.793468667255075,
+      "grad_norm": 0.39821702121821073,
+      "learning_rate": 6.431087645416121e-05,
+      "loss": 0.4015,
+      "step": 127
+    },
+    {
+      "epoch": 1.8075904677846424,
+      "grad_norm": 0.42798393839154475,
+      "learning_rate": 6.399287578751656e-05,
+      "loss": 0.3959,
+      "step": 128
+    },
+    {
+      "epoch": 1.8217122683142102,
+      "grad_norm": 0.4978207058435827,
+      "learning_rate": 6.367248864337471e-05,
+      "loss": 0.3975,
+      "step": 129
+    },
+    {
+      "epoch": 1.8358340688437775,
+      "grad_norm": 0.4727933665511357,
+      "learning_rate": 6.334974688939161e-05,
+      "loss": 0.3961,
+      "step": 130
+    },
+    {
+      "epoch": 1.849955869373345,
+      "grad_norm": 0.30157997491072186,
+      "learning_rate": 6.302468262742695e-05,
+      "loss": 0.3923,
+      "step": 131
+    },
+    {
+      "epoch": 1.8640776699029127,
+      "grad_norm": 0.30111696128126747,
+      "learning_rate": 6.269732819035128e-05,
+      "loss": 0.3895,
+      "step": 132
+    },
+    {
+      "epoch": 1.87819947043248,
+      "grad_norm": 0.33866239621320493,
+      "learning_rate": 6.236771613882987e-05,
+      "loss": 0.3933,
+      "step": 133
+    },
+    {
+      "epoch": 1.8923212709620476,
+      "grad_norm": 0.2963866045397337,
+      "learning_rate": 6.20358792580841e-05,
+      "loss": 0.3865,
+      "step": 134
+    },
+    {
+      "epoch": 1.9064430714916152,
+      "grad_norm": 0.2821832464959724,
+      "learning_rate": 6.170185055463039e-05,
+      "loss": 0.3985,
+      "step": 135
+    },
+    {
+      "epoch": 1.9205648720211828,
+      "grad_norm": 0.26513081199542754,
+      "learning_rate": 6.136566325299715e-05,
+      "loss": 0.3972,
+      "step": 136
+    },
+    {
+      "epoch": 1.9346866725507503,
+      "grad_norm": 0.25040847849987535,
+      "learning_rate": 6.102735079242019e-05,
+      "loss": 0.398,
+      "step": 137
+    },
+    {
+      "epoch": 1.9488084730803177,
+      "grad_norm": 0.303971008854815,
+      "learning_rate": 6.068694682351651e-05,
+      "loss": 0.3957,
+      "step": 138
+    },
+    {
+      "epoch": 1.9629302736098853,
+      "grad_norm": 0.2610849344447032,
+      "learning_rate": 6.0344485204937274e-05,
+      "loss": 0.3953,
+      "step": 139
+    },
+    {
+      "epoch": 1.9770520741394528,
+      "grad_norm": 0.24540141466965165,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.3955,
+      "step": 140
+    },
+    {
+      "epoch": 1.9911738746690202,
+      "grad_norm": 0.2807585102662493,
+      "learning_rate": 5.965352547330046e-05,
+      "loss": 0.4096,
+      "step": 141
+    },
+    {
+      "epoch": 2.005295675198588,
+      "grad_norm": 0.4269953277008037,
+      "learning_rate": 5.930509608730444e-05,
+      "loss": 0.4441,
+      "step": 142
+    },
+    {
+      "epoch": 2.0194174757281553,
+      "grad_norm": 0.5672907609303462,
+      "learning_rate": 5.895474649891995e-05,
+      "loss": 0.3728,
+      "step": 143
+    },
+    {
+      "epoch": 2.0335392762577227,
+      "grad_norm": 0.7266748405757633,
+      "learning_rate": 5.860251155605003e-05,
+      "loss": 0.3745,
+      "step": 144
+    },
+    {
+      "epoch": 2.0476610767872905,
+      "grad_norm": 1.0069160934332146,
+      "learning_rate": 5.824842629412653e-05,
+      "loss": 0.3832,
+      "step": 145
+    },
+    {
+      "epoch": 2.061782877316858,
+      "grad_norm": 0.9424187541004289,
+      "learning_rate": 5.7892525932625305e-05,
+      "loss": 0.3779,
+      "step": 146
+    },
+    {
+      "epoch": 2.0759046778464256,
+      "grad_norm": 0.42574191446629944,
+      "learning_rate": 5.75348458715631e-05,
+      "loss": 0.3718,
+      "step": 147
+    },
+    {
+      "epoch": 2.090026478375993,
+      "grad_norm": 0.7408316783846461,
+      "learning_rate": 5.7175421687976374e-05,
+      "loss": 0.3699,
+      "step": 148
+    },
+    {
+      "epoch": 2.1041482789055603,
+      "grad_norm": 0.6750908749341442,
+      "learning_rate": 5.681428913238263e-05,
+      "loss": 0.367,
+      "step": 149
+    },
+    {
+      "epoch": 2.118270079435128,
+      "grad_norm": 0.486610272879909,
+      "learning_rate": 5.645148412522447e-05,
+      "loss": 0.3752,
+      "step": 150
+    },
+    {
+      "epoch": 2.1323918799646955,
+      "grad_norm": 0.5306866815139071,
+      "learning_rate": 5.60870427532967e-05,
+      "loss": 0.3657,
+      "step": 151
+    },
+    {
+      "epoch": 2.146513680494263,
+      "grad_norm": 0.4884339447717486,
+      "learning_rate": 5.572100126615695e-05,
+      "loss": 0.3701,
+      "step": 152
+    },
+    {
+      "epoch": 2.1606354810238306,
+      "grad_norm": 0.39396923901380754,
+      "learning_rate": 5.535339607252003e-05,
+      "loss": 0.364,
+      "step": 153
+    },
+    {
+      "epoch": 2.174757281553398,
+      "grad_norm": 0.3784748162116266,
+      "learning_rate": 5.4984263736636494e-05,
+      "loss": 0.3641,
+      "step": 154
+    },
+    {
+      "epoch": 2.1888790820829658,
+      "grad_norm": 0.38537106208995364,
+      "learning_rate": 5.461364097465581e-05,
+      "loss": 0.3634,
+      "step": 155
+    },
+    {
+      "epoch": 2.203000882612533,
+      "grad_norm": 0.33639666599879814,
+      "learning_rate": 5.424156465097428e-05,
+      "loss": 0.3676,
+      "step": 156
+    },
+    {
+      "epoch": 2.2171226831421005,
+      "grad_norm": 0.3286791724075738,
+      "learning_rate": 5.38680717745683e-05,
+      "loss": 0.3649,
+      "step": 157
+    },
+    {
+      "epoch": 2.2312444836716683,
+      "grad_norm": 0.3129994921836922,
+      "learning_rate": 5.349319949531321e-05,
+      "loss": 0.3646,
+      "step": 158
+    },
+    {
+      "epoch": 2.2453662842012356,
+      "grad_norm": 0.3031016329231297,
+      "learning_rate": 5.3116985100288185e-05,
+      "loss": 0.3682,
+      "step": 159
+    },
+    {
+      "epoch": 2.259488084730803,
+      "grad_norm": 0.27541410223019297,
+      "learning_rate": 5.2739466010067385e-05,
+      "loss": 0.3606,
+      "step": 160
+    },
+    {
+      "epoch": 2.2736098852603708,
+      "grad_norm": 0.36257443661095795,
+      "learning_rate": 5.23606797749979e-05,
+      "loss": 0.3638,
+      "step": 161
+    },
+    {
+      "epoch": 2.287731685789938,
+      "grad_norm": 0.2567579985831816,
+      "learning_rate": 5.1980664071464776e-05,
+      "loss": 0.3667,
+      "step": 162
+    },
+    {
+      "epoch": 2.301853486319506,
+      "grad_norm": 0.31190867351244567,
+      "learning_rate": 5.159945669814345e-05,
+      "loss": 0.3696,
+      "step": 163
+    },
+    {
+      "epoch": 2.3159752868490733,
+      "grad_norm": 0.2937382011800516,
+      "learning_rate": 5.121709557224011e-05,
+      "loss": 0.3606,
+      "step": 164
+    },
+    {
+      "epoch": 2.3300970873786406,
+      "grad_norm": 0.2256249267158452,
+      "learning_rate": 5.0833618725720214e-05,
+      "loss": 0.365,
+      "step": 165
+    },
+    {
+      "epoch": 2.3442188879082084,
+      "grad_norm": 0.298331814145165,
+      "learning_rate": 5.044906430152554e-05,
+      "loss": 0.3667,
+      "step": 166
+    },
+    {
+      "epoch": 2.358340688437776,
+      "grad_norm": 0.18895739371171252,
+      "learning_rate": 5.006347054978035e-05,
+      "loss": 0.3699,
+      "step": 167
+    },
+    {
+      "epoch": 2.3724624889673436,
+      "grad_norm": 0.25034317840687215,
+      "learning_rate": 4.967687582398671e-05,
+      "loss": 0.3587,
+      "step": 168
+    },
+    {
+      "epoch": 2.386584289496911,
+      "grad_norm": 0.17907966208059622,
+      "learning_rate": 4.9289318577209706e-05,
+      "loss": 0.3636,
+      "step": 169
+    },
+    {
+      "epoch": 2.4007060900264783,
+      "grad_norm": 0.21210095036882018,
+      "learning_rate": 4.890083735825258e-05,
+      "loss": 0.3605,
+      "step": 170
+    },
+    {
+      "epoch": 2.414827890556046,
+      "grad_norm": 0.16489305774518265,
+      "learning_rate": 4.851147080782249e-05,
+      "loss": 0.3648,
+      "step": 171
+    },
+    {
+      "epoch": 2.4289496910856134,
+      "grad_norm": 0.19143993377462817,
+      "learning_rate": 4.812125765468705e-05,
+      "loss": 0.3606,
+      "step": 172
+    },
+    {
+      "epoch": 2.443071491615181,
+      "grad_norm": 0.17804983590295367,
+      "learning_rate": 4.773023671182213e-05,
+      "loss": 0.3637,
+      "step": 173
+    },
+    {
+      "epoch": 2.4571932921447486,
+      "grad_norm": 0.16707259472270428,
+      "learning_rate": 4.73384468725513e-05,
+      "loss": 0.3636,
+      "step": 174
+    },
+    {
+      "epoch": 2.471315092674316,
+      "grad_norm": 0.17481885632199456,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.3645,
+      "step": 175
+    },
+    {
+      "epoch": 2.4854368932038833,
+      "grad_norm": 0.1681053608116463,
+      "learning_rate": 4.6552716456605514e-05,
+      "loss": 0.3605,
+      "step": 176
+    },
+    {
+      "epoch": 2.499558693733451,
+      "grad_norm": 0.14964611415536702,
+      "learning_rate": 4.615885403346134e-05,
+      "loss": 0.3562,
+      "step": 177
+    },
+    {
+      "epoch": 2.5136804942630184,
+      "grad_norm": 0.14164675176141614,
+      "learning_rate": 4.576437901319921e-05,
+      "loss": 0.3636,
+      "step": 178
+    },
+    {
+      "epoch": 2.5278022947925862,
+      "grad_norm": 0.16548274190466053,
+      "learning_rate": 4.5369330632706223e-05,
+      "loss": 0.3648,
+      "step": 179
+    },
+    {
+      "epoch": 2.5419240953221536,
+      "grad_norm": 0.15269683467677936,
+      "learning_rate": 4.4973748185899416e-05,
+      "loss": 0.3612,
+      "step": 180
+    },
+    {
+      "epoch": 2.556045895851721,
+      "grad_norm": 0.16869434151649507,
+      "learning_rate": 4.457767101981728e-05,
+      "loss": 0.3677,
+      "step": 181
+    },
+    {
+      "epoch": 2.5701676963812887,
+      "grad_norm": 0.13337265767063033,
+      "learning_rate": 4.418113853070614e-05,
+      "loss": 0.3626,
+      "step": 182
+    },
+    {
+      "epoch": 2.584289496910856,
+      "grad_norm": 0.14682144236789746,
+      "learning_rate": 4.378419016010149e-05,
+      "loss": 0.364,
+      "step": 183
+    },
+    {
+      "epoch": 2.598411297440424,
+      "grad_norm": 0.150937900490833,
+      "learning_rate": 4.338686539090493e-05,
+      "loss": 0.3615,
+      "step": 184
+    },
+    {
+      "epoch": 2.6125330979699912,
+      "grad_norm": 0.1341377364551312,
+      "learning_rate": 4.298920374345698e-05,
+      "loss": 0.3596,
+      "step": 185
+    },
+    {
+      "epoch": 2.6266548984995586,
+      "grad_norm": 0.15572962430762588,
+      "learning_rate": 4.259124477160607e-05,
+      "loss": 0.3625,
+      "step": 186
+    },
+    {
+      "epoch": 2.6407766990291264,
+      "grad_norm": 0.1475404012486826,
+      "learning_rate": 4.219302805877441e-05,
+      "loss": 0.3617,
+      "step": 187
+    },
+    {
+      "epoch": 2.6548984995586937,
+      "grad_norm": 0.1781262720167099,
+      "learning_rate": 4.17945932140206e-05,
+      "loss": 0.3666,
+      "step": 188
+    },
+    {
+      "epoch": 2.6690203000882615,
+      "grad_norm": 0.13824587532461255,
+      "learning_rate": 4.139597986810005e-05,
+      "loss": 0.3629,
+      "step": 189
+    },
+    {
+      "epoch": 2.683142100617829,
+      "grad_norm": 0.15963593698467365,
+      "learning_rate": 4.0997227669522924e-05,
+      "loss": 0.3628,
+      "step": 190
+    },
+    {
+      "epoch": 2.6972639011473962,
+      "grad_norm": 0.12511715922220792,
+      "learning_rate": 4.059837628061055e-05,
+      "loss": 0.3638,
+      "step": 191
+    },
+    {
+      "epoch": 2.7113857016769636,
+      "grad_norm": 0.15752313446706914,
+      "learning_rate": 4.019946537355033e-05,
+      "loss": 0.3614,
+      "step": 192
+    },
+    {
+      "epoch": 2.7255075022065314,
+      "grad_norm": 0.13647413322377422,
+      "learning_rate": 3.9800534626449683e-05,
+      "loss": 0.3634,
+      "step": 193
+    },
+    {
+      "epoch": 2.7396293027360987,
+      "grad_norm": 0.13525074863232164,
+      "learning_rate": 3.940162371938947e-05,
+      "loss": 0.3587,
+      "step": 194
+    },
+    {
+      "epoch": 2.7537511032656665,
+      "grad_norm": 0.13297285710552217,
+      "learning_rate": 3.9002772330477096e-05,
+      "loss": 0.3599,
+      "step": 195
+    },
+    {
+      "epoch": 2.767872903795234,
+      "grad_norm": 0.14225004712058384,
+      "learning_rate": 3.860402013189998e-05,
+      "loss": 0.3575,
+      "step": 196
+    },
+    {
+      "epoch": 2.7819947043248012,
+      "grad_norm": 0.13373630438071715,
+      "learning_rate": 3.820540678597942e-05,
+      "loss": 0.3648,
+      "step": 197
+    },
+    {
+      "epoch": 2.796116504854369,
+      "grad_norm": 0.12615478953418785,
+      "learning_rate": 3.78069719412256e-05,
+      "loss": 0.3609,
+      "step": 198
+    },
+    {
+      "epoch": 2.8102383053839364,
+      "grad_norm": 0.12669967225071216,
+      "learning_rate": 3.740875522839393e-05,
+      "loss": 0.3608,
+      "step": 199
+    },
+    {
+      "epoch": 2.824360105913504,
+      "grad_norm": 0.13635382545910668,
+      "learning_rate": 3.7010796256543034e-05,
+      "loss": 0.3549,
+      "step": 200
+    },
+    {
+      "epoch": 2.8384819064430715,
+      "grad_norm": 0.11546629160995592,
+      "learning_rate": 3.661313460909507e-05,
+      "loss": 0.3593,
+      "step": 201
+    },
+    {
+      "epoch": 2.852603706972639,
+      "grad_norm": 0.12139128794186867,
+      "learning_rate": 3.621580983989852e-05,
+      "loss": 0.3608,
+      "step": 202
+    },
+    {
+      "epoch": 2.8667255075022067,
+      "grad_norm": 0.12319344865206981,
+      "learning_rate": 3.581886146929387e-05,
+      "loss": 0.3605,
+      "step": 203
+    },
+    {
+      "epoch": 2.880847308031774,
+      "grad_norm": 0.14742473593815408,
+      "learning_rate": 3.542232898018273e-05,
+      "loss": 0.3582,
+      "step": 204
+    },
+    {
+      "epoch": 2.894969108561342,
+      "grad_norm": 0.11086460953888361,
+      "learning_rate": 3.5026251814100604e-05,
+      "loss": 0.359,
+      "step": 205
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.13533789741325936,
+      "learning_rate": 3.4630669367293797e-05,
+      "loss": 0.3562,
+      "step": 206
+    },
+    {
+      "epoch": 2.9232127096204765,
+      "grad_norm": 0.11573276006772669,
+      "learning_rate": 3.4235620986800806e-05,
+      "loss": 0.3641,
+      "step": 207
+    },
+    {
+      "epoch": 2.937334510150044,
+      "grad_norm": 0.12838446326005826,
+      "learning_rate": 3.384114596653866e-05,
+      "loss": 0.361,
+      "step": 208
+    },
+    {
+      "epoch": 2.9514563106796117,
+      "grad_norm": 0.12304575149956651,
+      "learning_rate": 3.344728354339449e-05,
+      "loss": 0.3586,
+      "step": 209
+    },
+    {
+      "epoch": 2.965578111209179,
+      "grad_norm": 0.12773291501034634,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.3559,
+      "step": 210
+    },
+    {
+      "epoch": 2.979699911738747,
+      "grad_norm": 0.16335068209235123,
+      "learning_rate": 3.266155312744871e-05,
+      "loss": 0.3631,
+      "step": 211
+    },
+    {
+      "epoch": 2.993821712268314,
+      "grad_norm": 0.1186978138033666,
+      "learning_rate": 3.226976328817788e-05,
+      "loss": 0.3927,
+      "step": 212
+    },
+    {
+      "epoch": 3.0079435127978815,
+      "grad_norm": 0.16211984652497452,
+      "learning_rate": 3.187874234531296e-05,
+      "loss": 0.3822,
+      "step": 213
+    },
+    {
+      "epoch": 3.0220653133274493,
+      "grad_norm": 0.14214772364476422,
+      "learning_rate": 3.1488529192177526e-05,
+      "loss": 0.3393,
+      "step": 214
+    },
+    {
+      "epoch": 3.0361871138570167,
+      "grad_norm": 0.13255124874063956,
+      "learning_rate": 3.109916264174743e-05,
+      "loss": 0.3373,
+      "step": 215
+    },
+    {
+      "epoch": 3.0503089143865845,
+      "grad_norm": 0.16606000923059963,
+      "learning_rate": 3.071068142279031e-05,
+      "loss": 0.3371,
+      "step": 216
+    },
+    {
+      "epoch": 3.064430714916152,
+      "grad_norm": 0.14657630327267304,
+      "learning_rate": 3.0323124176013297e-05,
+      "loss": 0.3355,
+      "step": 217
+    },
+    {
+      "epoch": 3.078552515445719,
+      "grad_norm": 0.1341605905929287,
+      "learning_rate": 2.993652945021966e-05,
+      "loss": 0.3377,
+      "step": 218
+    },
+    {
+      "epoch": 3.092674315975287,
+      "grad_norm": 0.14490108611743277,
+      "learning_rate": 2.955093569847447e-05,
+      "loss": 0.3366,
+      "step": 219
+    },
+    {
+      "epoch": 3.1067961165048543,
+      "grad_norm": 0.13919821523407064,
+      "learning_rate": 2.9166381274279803e-05,
+      "loss": 0.3312,
+      "step": 220
+    },
+    {
+      "epoch": 3.120917917034422,
+      "grad_norm": 0.16300975058477254,
+      "learning_rate": 2.8782904427759898e-05,
+      "loss": 0.3311,
+      "step": 221
+    },
+    {
+      "epoch": 3.1350397175639895,
+      "grad_norm": 0.1183225077661534,
+      "learning_rate": 2.8400543301856553e-05,
+      "loss": 0.3282,
+      "step": 222
+    },
+    {
+      "epoch": 3.149161518093557,
+      "grad_norm": 0.14092204872317698,
+      "learning_rate": 2.8019335928535234e-05,
+      "loss": 0.3297,
+      "step": 223
+    },
+    {
+      "epoch": 3.1632833186231246,
+      "grad_norm": 0.1282390396455681,
+      "learning_rate": 2.7639320225002108e-05,
+      "loss": 0.327,
+      "step": 224
+    },
+    {
+      "epoch": 3.177405119152692,
+      "grad_norm": 0.12936573725572997,
+      "learning_rate": 2.7260533989932628e-05,
+      "loss": 0.3346,
+      "step": 225
+    },
+    {
+      "epoch": 3.1915269196822593,
+      "grad_norm": 0.11727309920196596,
+      "learning_rate": 2.688301489971183e-05,
+      "loss": 0.3271,
+      "step": 226
+    },
+    {
+      "epoch": 3.205648720211827,
+      "grad_norm": 0.12274146196879084,
+      "learning_rate": 2.6506800504686806e-05,
+      "loss": 0.328,
+      "step": 227
+    },
+    {
+      "epoch": 3.2197705207413945,
+      "grad_norm": 0.11029811005681434,
+      "learning_rate": 2.6131928225431713e-05,
+      "loss": 0.33,
+      "step": 228
+    },
+    {
+      "epoch": 3.233892321270962,
+      "grad_norm": 0.12463320131443856,
+      "learning_rate": 2.575843534902573e-05,
+      "loss": 0.3358,
+      "step": 229
+    },
+    {
+      "epoch": 3.2480141218005296,
+      "grad_norm": 0.11256203223325899,
+      "learning_rate": 2.53863590253442e-05,
+      "loss": 0.3364,
+      "step": 230
+    },
+    {
+      "epoch": 3.262135922330097,
+      "grad_norm": 0.10841743259905046,
+      "learning_rate": 2.501573626336352e-05,
+      "loss": 0.3337,
+      "step": 231
+    },
+    {
+      "epoch": 3.2762577228596648,
+      "grad_norm": 0.11593566286716334,
+      "learning_rate": 2.464660392747999e-05,
+      "loss": 0.3301,
+      "step": 232
+    },
+    {
+      "epoch": 3.290379523389232,
+      "grad_norm": 0.10969283000201786,
+      "learning_rate": 2.427899873384306e-05,
+      "loss": 0.332,
+      "step": 233
+    },
+    {
+      "epoch": 3.3045013239187995,
+      "grad_norm": 0.12033857141829916,
+      "learning_rate": 2.3912957246703305e-05,
+      "loss": 0.3377,
+      "step": 234
+    },
+    {
+      "epoch": 3.3186231244483673,
+      "grad_norm": 0.10210001952439796,
+      "learning_rate": 2.3548515874775547e-05,
+      "loss": 0.3297,
+      "step": 235
+    },
+    {
+      "epoch": 3.3327449249779346,
+      "grad_norm": 0.12241287674636975,
+      "learning_rate": 2.3185710867617387e-05,
+      "loss": 0.3361,
+      "step": 236
+    },
+    {
+      "epoch": 3.3468667255075024,
+      "grad_norm": 0.10969299118083352,
+      "learning_rate": 2.2824578312023632e-05,
+      "loss": 0.3322,
+      "step": 237
+    },
+    {
+      "epoch": 3.3609885260370698,
+      "grad_norm": 0.12151530040465547,
+      "learning_rate": 2.24651541284369e-05,
+      "loss": 0.3361,
+      "step": 238
+    },
+    {
+      "epoch": 3.375110326566637,
+      "grad_norm": 0.10631863902215113,
+      "learning_rate": 2.210747406737469e-05,
+      "loss": 0.3344,
+      "step": 239
+    },
+    {
+      "epoch": 3.389232127096205,
+      "grad_norm": 0.11983276963310185,
+      "learning_rate": 2.175157370587348e-05,
+      "loss": 0.3324,
+      "step": 240
+    },
+    {
+      "epoch": 3.4033539276257723,
+      "grad_norm": 0.10203118790788067,
+      "learning_rate": 2.1397488443949985e-05,
+      "loss": 0.3366,
+      "step": 241
+    },
+    {
+      "epoch": 3.4174757281553396,
+      "grad_norm": 0.11460733945580791,
+      "learning_rate": 2.1045253501080058e-05,
+      "loss": 0.3335,
+      "step": 242
+    },
+    {
+      "epoch": 3.4315975286849074,
+      "grad_norm": 0.10361959122829918,
+      "learning_rate": 2.0694903912695574e-05,
+      "loss": 0.3342,
+      "step": 243
+    },
+    {
+      "epoch": 3.4457193292144748,
+      "grad_norm": 0.10602009006473866,
+      "learning_rate": 2.0346474526699552e-05,
+      "loss": 0.3343,
+      "step": 244
+    },
+    {
+      "epoch": 3.459841129744042,
+      "grad_norm": 0.0981614565374733,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.3342,
+      "step": 245
+    },
+    {
+      "epoch": 3.47396293027361,
+      "grad_norm": 0.10563881070295801,
+      "learning_rate": 1.9655514795062746e-05,
+      "loss": 0.3317,
+      "step": 246
+    },
+    {
+      "epoch": 3.4880847308031773,
+      "grad_norm": 0.0982393867459211,
+      "learning_rate": 1.931305317648349e-05,
+      "loss": 0.336,
+      "step": 247
+    },
+    {
+      "epoch": 3.502206531332745,
+      "grad_norm": 0.10341107342114168,
+      "learning_rate": 1.897264920757981e-05,
+      "loss": 0.3329,
+      "step": 248
+    },
+    {
+      "epoch": 3.5163283318623124,
+      "grad_norm": 0.1009205150822494,
+      "learning_rate": 1.8634336747002853e-05,
+      "loss": 0.3363,
+      "step": 249
+    },
+    {
+      "epoch": 3.5304501323918798,
+      "grad_norm": 0.09562831286129422,
+      "learning_rate": 1.829814944536963e-05,
+      "loss": 0.3366,
+      "step": 250
+    },
+    {
+      "epoch": 3.5445719329214476,
+      "grad_norm": 0.10055162803558056,
+      "learning_rate": 1.7964120741915905e-05,
+      "loss": 0.3359,
+      "step": 251
+    },
+    {
+      "epoch": 3.558693733451015,
+      "grad_norm": 0.10362087580690618,
+      "learning_rate": 1.7632283861170135e-05,
+      "loss": 0.33,
+      "step": 252
+    },
+    {
+      "epoch": 3.5728155339805827,
+      "grad_norm": 0.09578324331311534,
+      "learning_rate": 1.7302671809648735e-05,
+      "loss": 0.3336,
+      "step": 253
+    },
+    {
+      "epoch": 3.58693733451015,
+      "grad_norm": 0.1021943484963981,
+      "learning_rate": 1.6975317372573066e-05,
+      "loss": 0.334,
+      "step": 254
+    },
+    {
+      "epoch": 3.6010591350397174,
+      "grad_norm": 0.10104477227737499,
+      "learning_rate": 1.6650253110608415e-05,
+      "loss": 0.3352,
+      "step": 255
+    },
+    {
+      "epoch": 3.615180935569285,
+      "grad_norm": 0.09719144111824624,
+      "learning_rate": 1.6327511356625302e-05,
+      "loss": 0.3339,
+      "step": 256
+    },
+    {
+      "epoch": 3.6293027360988526,
+      "grad_norm": 0.10082549447043057,
+      "learning_rate": 1.6007124212483453e-05,
+      "loss": 0.3303,
+      "step": 257
+    },
+    {
+      "epoch": 3.6434245366284204,
+      "grad_norm": 0.09855344501708733,
+      "learning_rate": 1.5689123545838804e-05,
+      "loss": 0.3319,
+      "step": 258
+    },
+    {
+      "epoch": 3.6575463371579877,
+      "grad_norm": 0.10038693196972406,
+      "learning_rate": 1.537354098697367e-05,
+      "loss": 0.3285,
+      "step": 259
+    },
+    {
+      "epoch": 3.671668137687555,
+      "grad_norm": 0.10993218050906065,
+      "learning_rate": 1.5060407925650662e-05,
+      "loss": 0.3346,
+      "step": 260
+    },
+    {
+      "epoch": 3.6857899382171224,
+      "grad_norm": 0.09881058692426582,
+      "learning_rate": 1.4749755507990449e-05,
+      "loss": 0.3265,
+      "step": 261
+    },
+    {
+      "epoch": 3.69991173874669,
+      "grad_norm": 0.11110424733317653,
+      "learning_rate": 1.4441614633373773e-05,
+      "loss": 0.3367,
+      "step": 262
+    },
+    {
+      "epoch": 3.7140335392762576,
+      "grad_norm": 0.09507466207790345,
+      "learning_rate": 1.413601595136802e-05,
+      "loss": 0.335,
+      "step": 263
+    },
+    {
+      "epoch": 3.7281553398058254,
+      "grad_norm": 0.10341229060389236,
+      "learning_rate": 1.383298985867863e-05,
+      "loss": 0.3324,
+      "step": 264
+    },
+    {
+      "epoch": 3.7422771403353927,
+      "grad_norm": 0.09734360531860331,
+      "learning_rate": 1.3532566496125634e-05,
+      "loss": 0.3313,
+      "step": 265
+    },
+    {
+      "epoch": 3.75639894086496,
+      "grad_norm": 0.09174570798780135,
+      "learning_rate": 1.3234775745645684e-05,
+      "loss": 0.3351,
+      "step": 266
+    },
+    {
+      "epoch": 3.770520741394528,
+      "grad_norm": 0.10147835781586892,
+      "learning_rate": 1.2939647227319791e-05,
+      "loss": 0.3353,
+      "step": 267
+    },
+    {
+      "epoch": 3.784642541924095,
+      "grad_norm": 0.09808246222031777,
+      "learning_rate": 1.2647210296427197e-05,
+      "loss": 0.3323,
+      "step": 268
+    },
+    {
+      "epoch": 3.798764342453663,
+      "grad_norm": 0.09735163985861015,
+      "learning_rate": 1.2357494040525416e-05,
+      "loss": 0.3391,
+      "step": 269
+    },
+    {
+      "epoch": 3.8128861429832304,
+      "grad_norm": 0.08930562493255255,
+      "learning_rate": 1.2070527276557092e-05,
+      "loss": 0.3327,
+      "step": 270
+    },
+    {
+      "epoch": 3.8270079435127977,
+      "grad_norm": 0.09744814905553326,
+      "learning_rate": 1.178633854798365e-05,
+      "loss": 0.33,
+      "step": 271
+    },
+    {
+      "epoch": 3.8411297440423655,
+      "grad_norm": 0.09183836496663382,
+      "learning_rate": 1.1504956121946216e-05,
+      "loss": 0.3317,
+      "step": 272
+    },
+    {
+      "epoch": 3.855251544571933,
+      "grad_norm": 0.08801876422756064,
+      "learning_rate": 1.1226407986453963e-05,
+      "loss": 0.3294,
+      "step": 273
+    },
+    {
+      "epoch": 3.8693733451015007,
+      "grad_norm": 0.08798928229950856,
+      "learning_rate": 1.0950721847600282e-05,
+      "loss": 0.3282,
+      "step": 274
+    },
+    {
+      "epoch": 3.883495145631068,
+      "grad_norm": 0.09000845113363774,
+      "learning_rate": 1.0677925126806956e-05,
+      "loss": 0.335,
+      "step": 275
+    },
+    {
+      "epoch": 3.8976169461606354,
+      "grad_norm": 0.09609952332604478,
+      "learning_rate": 1.040804495809665e-05,
+      "loss": 0.3352,
+      "step": 276
+    },
+    {
+      "epoch": 3.911738746690203,
+      "grad_norm": 0.09426777621829556,
+      "learning_rate": 1.0141108185393995e-05,
+      "loss": 0.3307,
+      "step": 277
+    },
+    {
+      "epoch": 3.9258605472197705,
+      "grad_norm": 0.08749576305220681,
+      "learning_rate": 9.877141359855567e-06,
+      "loss": 0.3316,
+      "step": 278
+    },
+    {
+      "epoch": 3.9399823477493383,
+      "grad_norm": 0.08573388419725536,
+      "learning_rate": 9.616170737228882e-06,
+      "loss": 0.3301,
+      "step": 279
+    },
+    {
+      "epoch": 3.9541041482789057,
+      "grad_norm": 0.08677743094561904,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.3309,
+      "step": 280
+    },
+    {
+      "epoch": 3.968225948808473,
+      "grad_norm": 0.08456912932018501,
+      "learning_rate": 9.103321631016024e-06,
+      "loss": 0.3294,
+      "step": 281
+    },
+    {
+      "epoch": 3.9823477493380404,
+      "grad_norm": 0.0892840459688823,
+      "learning_rate": 8.851494158524242e-06,
+      "loss": 0.3299,
+      "step": 282
+    },
+    {
+      "epoch": 3.996469549867608,
+      "grad_norm": 0.09785834932292316,
+      "learning_rate": 8.602764906059109e-06,
+      "loss": 0.3734,
+      "step": 283
+    },
+    {
+      "epoch": 4.010591350397176,
+      "grad_norm": 0.1159182382828669,
+      "learning_rate": 8.35715861374636e-06,
+      "loss": 0.3432,
+      "step": 284
+    },
+    {
+      "epoch": 4.024713150926743,
+      "grad_norm": 0.11348869033645836,
+      "learning_rate": 8.114699711083113e-06,
+      "loss": 0.3187,
+      "step": 285
+    },
+    {
+      "epoch": 4.038834951456311,
+      "grad_norm": 0.09626843456466473,
+      "learning_rate": 7.875412314507942e-06,
+      "loss": 0.3213,
+      "step": 286
+    },
+    {
+      "epoch": 4.052956751985878,
+      "grad_norm": 0.0918806636447836,
+      "learning_rate": 7.639320225002106e-06,
+      "loss": 0.3169,
+      "step": 287
+    },
+    {
+      "epoch": 4.067078552515445,
+      "grad_norm": 0.09514043448978982,
+      "learning_rate": 7.406446925722211e-06,
+      "loss": 0.3148,
+      "step": 288
+    },
+    {
+      "epoch": 4.081200353045014,
+      "grad_norm": 0.10508295602012874,
+      "learning_rate": 7.176815579664343e-06,
+      "loss": 0.3132,
+      "step": 289
+    },
+    {
+      "epoch": 4.095322153574581,
+      "grad_norm": 0.10091079365331981,
+      "learning_rate": 6.950449027360213e-06,
+      "loss": 0.3175,
+      "step": 290
+    },
+    {
+      "epoch": 4.109443954104148,
+      "grad_norm": 0.0973346460822993,
+      "learning_rate": 6.7273697846052515e-06,
+      "loss": 0.3184,
+      "step": 291
+    },
+    {
+      "epoch": 4.123565754633716,
+      "grad_norm": 0.09115379235697503,
+      "learning_rate": 6.507600040219073e-06,
+      "loss": 0.3164,
+      "step": 292
+    },
+    {
+      "epoch": 4.137687555163283,
+      "grad_norm": 0.08901902718597547,
+      "learning_rate": 6.291161653838434e-06,
+      "loss": 0.3177,
+      "step": 293
+    },
+    {
+      "epoch": 4.151809355692851,
+      "grad_norm": 0.09132299423316595,
+      "learning_rate": 6.078076153742962e-06,
+      "loss": 0.3131,
+      "step": 294
+    },
+    {
+      "epoch": 4.165931156222419,
+      "grad_norm": 0.09543903005749907,
+      "learning_rate": 5.868364734713776e-06,
+      "loss": 0.3142,
+      "step": 295
+    },
+    {
+      "epoch": 4.180052956751986,
+      "grad_norm": 0.09061531269851537,
+      "learning_rate": 5.662048255925357e-06,
+      "loss": 0.3204,
+      "step": 296
+    },
+    {
+      "epoch": 4.194174757281553,
+      "grad_norm": 0.08551951038992002,
+      "learning_rate": 5.459147238870768e-06,
+      "loss": 0.3158,
+      "step": 297
+    },
+    {
+      "epoch": 4.208296557811121,
+      "grad_norm": 0.08387425510980595,
+      "learning_rate": 5.259681865320447e-06,
+      "loss": 0.3194,
+      "step": 298
+    },
+    {
+      "epoch": 4.222418358340688,
+      "grad_norm": 0.0901228464398898,
+      "learning_rate": 5.063671975314814e-06,
+      "loss": 0.3163,
+      "step": 299
+    },
+    {
+      "epoch": 4.236540158870256,
+      "grad_norm": 0.08691256583540367,
+      "learning_rate": 4.871137065190854e-06,
+      "loss": 0.315,
+      "step": 300
+    },
+    {
+      "epoch": 4.250661959399824,
+      "grad_norm": 0.0878527835574059,
+      "learning_rate": 4.6820962856429205e-06,
+      "loss": 0.3176,
+      "step": 301
+    },
+    {
+      "epoch": 4.264783759929391,
+      "grad_norm": 0.0840437037057203,
+      "learning_rate": 4.496568439817836e-06,
+      "loss": 0.322,
+      "step": 302
+    },
+    {
+      "epoch": 4.278905560458958,
+      "grad_norm": 0.08904988122589128,
+      "learning_rate": 4.314571981444666e-06,
+      "loss": 0.311,
+      "step": 303
+    },
+    {
+      "epoch": 4.293027360988526,
+      "grad_norm": 0.08120215219780037,
+      "learning_rate": 4.136125012999168e-06,
+      "loss": 0.3203,
+      "step": 304
+    },
+    {
+      "epoch": 4.307149161518094,
+      "grad_norm": 0.08522052695009742,
+      "learning_rate": 3.961245283903239e-06,
+      "loss": 0.3161,
+      "step": 305
+    },
+    {
+      "epoch": 4.321270962047661,
+      "grad_norm": 0.08319753808748938,
+      "learning_rate": 3.7899501887594102e-06,
+      "loss": 0.315,
+      "step": 306
+    },
+    {
+      "epoch": 4.335392762577229,
+      "grad_norm": 0.08198211403858394,
+      "learning_rate": 3.622256765620713e-06,
+      "loss": 0.3165,
+      "step": 307
+    },
+    {
+      "epoch": 4.349514563106796,
+      "grad_norm": 0.07827444542073485,
+      "learning_rate": 3.458181694295961e-06,
+      "loss": 0.3114,
+      "step": 308
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 0.07827005931051699,
+      "learning_rate": 3.297741294690644e-06,
+      "loss": 0.3125,
+      "step": 309
+    },
+    {
+      "epoch": 4.3777581641659316,
+      "grad_norm": 0.07833274350751808,
+      "learning_rate": 3.140951525183691e-06,
+      "loss": 0.3156,
+      "step": 310
+    },
+    {
+      "epoch": 4.391879964695499,
+      "grad_norm": 0.08055700180528477,
+      "learning_rate": 2.987827981040132e-06,
+      "loss": 0.3144,
+      "step": 311
+    },
+    {
+      "epoch": 4.406001765225066,
+      "grad_norm": 0.0799614180245514,
+      "learning_rate": 2.8383858928598963e-06,
+      "loss": 0.3157,
+      "step": 312
+    },
+    {
+      "epoch": 4.420123565754634,
+      "grad_norm": 0.0722165779006397,
+      "learning_rate": 2.692640125062895e-06,
+      "loss": 0.3116,
+      "step": 313
+    },
+    {
+      "epoch": 4.434245366284201,
+      "grad_norm": 0.07776220076295337,
+      "learning_rate": 2.550605174410512e-06,
+      "loss": 0.3206,
+      "step": 314
+    },
+    {
+      "epoch": 4.448367166813769,
+      "grad_norm": 0.07577160557474086,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.3119,
+      "step": 315
+    },
+    {
+      "epoch": 4.4624889673433366,
+      "grad_norm": 0.07292199486310709,
+      "learning_rate": 2.2777238646775768e-06,
+      "loss": 0.314,
+      "step": 316
+    },
+    {
+      "epoch": 4.476610767872904,
+      "grad_norm": 0.07321270589774292,
+      "learning_rate": 2.14690464803343e-06,
+      "loss": 0.3116,
+      "step": 317
+    },
+    {
+      "epoch": 4.490732568402471,
+      "grad_norm": 0.07971761444372055,
+      "learning_rate": 2.0198505307069462e-06,
+      "loss": 0.3162,
+      "step": 318
+    },
+    {
+      "epoch": 4.504854368932039,
+      "grad_norm": 0.0823725656624792,
+      "learning_rate": 1.896574150274151e-06,
+      "loss": 0.318,
+      "step": 319
+    },
+    {
+      "epoch": 4.518976169461606,
+      "grad_norm": 0.07311612247681858,
+      "learning_rate": 1.7770877685543687e-06,
+      "loss": 0.3146,
+      "step": 320
+    },
+    {
+      "epoch": 4.533097969991174,
+      "grad_norm": 0.0754285797360244,
+      "learning_rate": 1.6614032703905714e-06,
+      "loss": 0.3188,
+      "step": 321
+    },
+    {
+      "epoch": 4.5472197705207416,
+      "grad_norm": 0.07192329712907819,
+      "learning_rate": 1.5495321624672443e-06,
+      "loss": 0.3117,
+      "step": 322
+    },
+    {
+      "epoch": 4.561341571050309,
+      "grad_norm": 0.07683729191513318,
+      "learning_rate": 1.4414855721658705e-06,
+      "loss": 0.3179,
+      "step": 323
+    },
+    {
+      "epoch": 4.575463371579876,
+      "grad_norm": 0.07466087193345237,
+      "learning_rate": 1.3372742464581134e-06,
+      "loss": 0.3169,
+      "step": 324
+    },
+    {
+      "epoch": 4.589585172109444,
+      "grad_norm": 0.07472750780066512,
+      "learning_rate": 1.2369085508368862e-06,
+      "loss": 0.313,
+      "step": 325
+    },
+    {
+      "epoch": 4.603706972639012,
+      "grad_norm": 0.07567268942020543,
+      "learning_rate": 1.1403984682852998e-06,
+      "loss": 0.3162,
+      "step": 326
+    },
+    {
+      "epoch": 4.617828773168579,
+      "grad_norm": 0.07193466653913613,
+      "learning_rate": 1.0477535982837473e-06,
+      "loss": 0.3169,
+      "step": 327
+    },
+    {
+      "epoch": 4.631950573698147,
+      "grad_norm": 0.07310364397796111,
+      "learning_rate": 9.589831558550222e-07,
+      "loss": 0.3147,
+      "step": 328
+    },
+    {
+      "epoch": 4.646072374227714,
+      "grad_norm": 0.07226831665121733,
+      "learning_rate": 8.740959706477725e-07,
+      "loss": 0.3155,
+      "step": 329
+    },
+    {
+      "epoch": 4.660194174757281,
+      "grad_norm": 0.07380784680617208,
+      "learning_rate": 7.93100486058247e-07,
+      "loss": 0.3172,
+      "step": 330
+    },
+    {
+      "epoch": 4.674315975286849,
+      "grad_norm": 0.07265097137199653,
+      "learning_rate": 7.160047583904473e-07,
+      "loss": 0.3123,
+      "step": 331
+    },
+    {
+      "epoch": 4.688437775816417,
+      "grad_norm": 0.07526606061681983,
+      "learning_rate": 6.428164560548134e-07,
+      "loss": 0.3126,
+      "step": 332
+    },
+    {
+      "epoch": 4.702559576345984,
+      "grad_norm": 0.07096951660387449,
+      "learning_rate": 5.735428588054825e-07,
+      "loss": 0.3091,
+      "step": 333
+    },
+    {
+      "epoch": 4.716681376875552,
+      "grad_norm": 0.07491929428893927,
+      "learning_rate": 5.081908570161753e-07,
+      "loss": 0.3168,
+      "step": 334
+    },
+    {
+      "epoch": 4.730803177405119,
+      "grad_norm": 0.07068035565889964,
+      "learning_rate": 4.467669509948591e-07,
+      "loss": 0.3168,
+      "step": 335
+    },
+    {
+      "epoch": 4.744924977934687,
+      "grad_norm": 0.07006153238881019,
+      "learning_rate": 3.8927725033718553e-07,
+      "loss": 0.3096,
+      "step": 336
+    },
+    {
+      "epoch": 4.7590467784642545,
+      "grad_norm": 0.07031296479074185,
+      "learning_rate": 3.3572747331878984e-07,
+      "loss": 0.3127,
+      "step": 337
+    },
+    {
+      "epoch": 4.773168578993822,
+      "grad_norm": 0.07086156685048181,
+      "learning_rate": 2.8612294632650586e-07,
+      "loss": 0.3165,
+      "step": 338
+    },
+    {
+      "epoch": 4.787290379523389,
+      "grad_norm": 0.07041702874195928,
+      "learning_rate": 2.404686033285897e-07,
+      "loss": 0.3211,
+      "step": 339
+    },
+    {
+      "epoch": 4.801412180052957,
+      "grad_norm": 0.07111545002538634,
+      "learning_rate": 1.9876898538394362e-07,
+      "loss": 0.3139,
+      "step": 340
+    },
+    {
+      "epoch": 4.815533980582524,
+      "grad_norm": 0.06964445264833816,
+      "learning_rate": 1.6102824019043728e-07,
+      "loss": 0.3119,
+      "step": 341
+    },
+    {
+      "epoch": 4.829655781112092,
+      "grad_norm": 0.07185826317569316,
+      "learning_rate": 1.2725012167236207e-07,
+      "loss": 0.3189,
+      "step": 342
+    },
+    {
+      "epoch": 4.8437775816416595,
+      "grad_norm": 0.07175971991165786,
+      "learning_rate": 9.74379896070321e-08,
+      "loss": 0.3144,
+      "step": 343
+    },
+    {
+      "epoch": 4.857899382171227,
+      "grad_norm": 0.07027377563502572,
+      "learning_rate": 7.159480929059381e-08,
+      "loss": 0.3208,
+      "step": 344
+    },
+    {
+      "epoch": 4.872021182700794,
+      "grad_norm": 0.07130198834034268,
+      "learning_rate": 4.9723151243106225e-08,
+      "loss": 0.3164,
+      "step": 345
+    },
+    {
+      "epoch": 4.886142983230362,
+      "grad_norm": 0.07512577557190175,
+      "learning_rate": 3.1825190952829986e-08,
+      "loss": 0.3183,
+      "step": 346
+    },
+    {
+      "epoch": 4.90026478375993,
+      "grad_norm": 0.0718819094759202,
+      "learning_rate": 1.7902708659867096e-08,
+      "loss": 0.3185,
+      "step": 347
+    },
+    {
+      "epoch": 4.914386584289497,
+      "grad_norm": 0.0706893833001464,
+      "learning_rate": 7.957089179058131e-09,
+      "loss": 0.3142,
+      "step": 348
+    },
+    {
+      "epoch": 4.9285083848190645,
+      "grad_norm": 0.07170028442056126,
+      "learning_rate": 1.9893217622790616e-09,
+      "loss": 0.3181,
+      "step": 349
+    },
+    {
+      "epoch": 4.942630185348632,
+      "grad_norm": 0.07142066838497432,
+      "learning_rate": 0.0,
+      "loss": 0.313,
+      "step": 350
+    },
+    {
+      "epoch": 4.942630185348632,
+      "step": 350,
+      "total_flos": 9.306564393200255e+18,
+      "train_loss": 0.0,
+      "train_runtime": 1.9909,
+      "train_samples_per_second": 91040.986,
+      "train_steps_per_second": 175.798
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 350,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.306564393200255e+18,
+  "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 sha256:039e32e706bff12cff024410b904be7a320b0461bffe60ae4b85e290ebfee2ea
+size 7416