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: nemo_nano_science_300k
+  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. -->
+
+# nemo_nano_science_300k
+
+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/nemo_nano_science_300k 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": 4.987012987012987,
+    "total_flos": 9.572466247992345e+18,
+    "train_loss": 0.0,
+    "train_runtime": 2.6399,
+    "train_samples_per_second": 69987.374,
+    "train_steps_per_second": 136.369
+}

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 sha256:1c4921943fa12d77b72ff291494eda11f0a26815c4fb009a84b77f12396c7a92
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b982177bd508a15489d7ec0e6f76da18adf857ace58f9578c274813caaa120cf
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d98d2991fdf18aeb8ad68c3494421c8a7967a1fa168c14300e36cc34f6b634
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d441d709d5cadbc088028020ad1b79e543e51f4df3f378d7009bd4c1d4807ad2
+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/May11_18-21-07_jrc0911/events.out.tfevents.1746980590.jrc0911.2683931.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd675c805075a77d4e0f7bb841d86583cd393f16f86dd8c98954d2cecfff3cbf
+size 81323

runs/May12_17-51-15_jrc0911/events.out.tfevents.1747065196.jrc0911.2921406.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4475998d0085bb6753601b4e50db679c53b116313ed7b7f0c8a3d85c6dc9c7
+size 5940

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": "2025-05-12 17:51:15", "end_time": "2025-05-12 17:53:30"}

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": 4.987012987012987,
+    "total_flos": 9.572466247992345e+18,
+    "train_loss": 0.0,
+    "train_runtime": 2.6399,
+    "train_samples_per_second": 69987.374,
+    "train_steps_per_second": 136.369
+}

trainer_log.jsonl

@@ -0,0 +1,362 @@
+{"current_steps": 1, "total_steps": 360, "loss": 1.664, "lr": 2.222222222222222e-06, "epoch": 0.013852813852813853, "percentage": 0.28, "elapsed_time": "0:04:10", "remaining_time": "1 day, 0:57:57"}
+{"current_steps": 2, "total_steps": 360, "loss": 1.6687, "lr": 4.444444444444444e-06, "epoch": 0.027705627705627706, "percentage": 0.56, "elapsed_time": "0:08:04", "remaining_time": "1 day, 0:06:04"}
+{"current_steps": 3, "total_steps": 360, "loss": 1.6436, "lr": 6.666666666666667e-06, "epoch": 0.04155844155844156, "percentage": 0.83, "elapsed_time": "0:11:57", "remaining_time": "23:43:55"}
+{"current_steps": 4, "total_steps": 360, "loss": 1.5751, "lr": 8.888888888888888e-06, "epoch": 0.05541125541125541, "percentage": 1.11, "elapsed_time": "0:15:51", "remaining_time": "23:32:00"}
+{"current_steps": 5, "total_steps": 360, "loss": 1.4732, "lr": 1.1111111111111113e-05, "epoch": 0.06926406926406926, "percentage": 1.39, "elapsed_time": "0:19:45", "remaining_time": "23:22:56"}
+{"current_steps": 6, "total_steps": 360, "loss": 1.4929, "lr": 1.3333333333333333e-05, "epoch": 0.08311688311688312, "percentage": 1.67, "elapsed_time": "0:23:38", "remaining_time": "23:14:34"}
+{"current_steps": 7, "total_steps": 360, "loss": 1.4342, "lr": 1.555555555555556e-05, "epoch": 0.09696969696969697, "percentage": 1.94, "elapsed_time": "0:27:31", "remaining_time": "23:08:11"}
+{"current_steps": 8, "total_steps": 360, "loss": 1.4508, "lr": 1.7777777777777777e-05, "epoch": 0.11082251082251082, "percentage": 2.22, "elapsed_time": "0:31:25", "remaining_time": "23:02:43"}
+{"current_steps": 9, "total_steps": 360, "loss": 1.3993, "lr": 2e-05, "epoch": 0.12467532467532468, "percentage": 2.5, "elapsed_time": "0:35:18", "remaining_time": "22:57:09"}
+{"current_steps": 10, "total_steps": 360, "loss": 1.3716, "lr": 2.2222222222222227e-05, "epoch": 0.13852813852813853, "percentage": 2.78, "elapsed_time": "0:39:12", "remaining_time": "22:52:20"}
+{"current_steps": 11, "total_steps": 360, "loss": 1.3279, "lr": 2.444444444444445e-05, "epoch": 0.1523809523809524, "percentage": 3.06, "elapsed_time": "0:43:06", "remaining_time": "22:47:55"}
+{"current_steps": 12, "total_steps": 360, "loss": 1.2918, "lr": 2.6666666666666667e-05, "epoch": 0.16623376623376623, "percentage": 3.33, "elapsed_time": "0:47:01", "remaining_time": "22:43:32"}
+{"current_steps": 13, "total_steps": 360, "loss": 1.2683, "lr": 2.888888888888889e-05, "epoch": 0.1800865800865801, "percentage": 3.61, "elapsed_time": "0:50:54", "remaining_time": "22:38:58"}
+{"current_steps": 14, "total_steps": 360, "loss": 1.2741, "lr": 3.111111111111112e-05, "epoch": 0.19393939393939394, "percentage": 3.89, "elapsed_time": "0:54:48", "remaining_time": "22:34:23"}
+{"current_steps": 15, "total_steps": 360, "loss": 1.2498, "lr": 3.3333333333333335e-05, "epoch": 0.2077922077922078, "percentage": 4.17, "elapsed_time": "0:58:41", "remaining_time": "22:30:01"}
+{"current_steps": 16, "total_steps": 360, "loss": 1.2356, "lr": 3.555555555555555e-05, "epoch": 0.22164502164502164, "percentage": 4.44, "elapsed_time": "1:02:35", "remaining_time": "22:25:37"}
+{"current_steps": 17, "total_steps": 360, "loss": 1.2226, "lr": 3.777777777777778e-05, "epoch": 0.2354978354978355, "percentage": 4.72, "elapsed_time": "1:06:29", "remaining_time": "22:21:40"}
+{"current_steps": 18, "total_steps": 360, "loss": 1.1883, "lr": 4e-05, "epoch": 0.24935064935064935, "percentage": 5.0, "elapsed_time": "1:10:24", "remaining_time": "22:17:36"}
+{"current_steps": 19, "total_steps": 360, "loss": 1.1903, "lr": 4.222222222222223e-05, "epoch": 0.2632034632034632, "percentage": 5.28, "elapsed_time": "1:14:17", "remaining_time": "22:13:26"}
+{"current_steps": 20, "total_steps": 360, "loss": 1.1823, "lr": 4.444444444444445e-05, "epoch": 0.27705627705627706, "percentage": 5.56, "elapsed_time": "1:18:11", "remaining_time": "22:09:18"}
+{"current_steps": 21, "total_steps": 360, "loss": 1.1644, "lr": 4.666666666666667e-05, "epoch": 0.2909090909090909, "percentage": 5.83, "elapsed_time": "1:22:05", "remaining_time": "22:05:17"}
+{"current_steps": 22, "total_steps": 360, "loss": 1.1866, "lr": 4.88888888888889e-05, "epoch": 0.3047619047619048, "percentage": 6.11, "elapsed_time": "1:25:58", "remaining_time": "22:00:59"}
+{"current_steps": 23, "total_steps": 360, "loss": 1.1606, "lr": 5.111111111111111e-05, "epoch": 0.31861471861471863, "percentage": 6.39, "elapsed_time": "1:29:52", "remaining_time": "21:56:56"}
+{"current_steps": 24, "total_steps": 360, "loss": 1.1689, "lr": 5.333333333333333e-05, "epoch": 0.33246753246753247, "percentage": 6.67, "elapsed_time": "1:33:47", "remaining_time": "21:52:58"}
+{"current_steps": 25, "total_steps": 360, "loss": 1.1555, "lr": 5.555555555555556e-05, "epoch": 0.3463203463203463, "percentage": 6.94, "elapsed_time": "1:37:40", "remaining_time": "21:48:46"}
+{"current_steps": 26, "total_steps": 360, "loss": 1.1683, "lr": 5.777777777777778e-05, "epoch": 0.3601731601731602, "percentage": 7.22, "elapsed_time": "1:41:33", "remaining_time": "21:44:44"}
+{"current_steps": 27, "total_steps": 360, "loss": 1.162, "lr": 6.000000000000001e-05, "epoch": 0.37402597402597404, "percentage": 7.5, "elapsed_time": "1:45:27", "remaining_time": "21:40:41"}
+{"current_steps": 28, "total_steps": 360, "loss": 1.1588, "lr": 6.222222222222223e-05, "epoch": 0.3878787878787879, "percentage": 7.78, "elapsed_time": "1:49:21", "remaining_time": "21:36:42"}
+{"current_steps": 29, "total_steps": 360, "loss": 1.1477, "lr": 6.444444444444446e-05, "epoch": 0.4017316017316017, "percentage": 8.06, "elapsed_time": "1:53:15", "remaining_time": "21:32:37"}
+{"current_steps": 30, "total_steps": 360, "loss": 1.1463, "lr": 6.666666666666667e-05, "epoch": 0.4155844155844156, "percentage": 8.33, "elapsed_time": "1:57:09", "remaining_time": "21:28:39"}
+{"current_steps": 31, "total_steps": 360, "loss": 1.1273, "lr": 6.88888888888889e-05, "epoch": 0.42943722943722945, "percentage": 8.61, "elapsed_time": "2:01:02", "remaining_time": "21:24:30"}
+{"current_steps": 32, "total_steps": 360, "loss": 1.1468, "lr": 7.11111111111111e-05, "epoch": 0.4432900432900433, "percentage": 8.89, "elapsed_time": "2:04:56", "remaining_time": "21:20:36"}
+{"current_steps": 33, "total_steps": 360, "loss": 1.1379, "lr": 7.333333333333333e-05, "epoch": 0.45714285714285713, "percentage": 9.17, "elapsed_time": "2:08:49", "remaining_time": "21:16:34"}
+{"current_steps": 34, "total_steps": 360, "loss": 1.1309, "lr": 7.555555555555556e-05, "epoch": 0.470995670995671, "percentage": 9.44, "elapsed_time": "2:12:42", "remaining_time": "21:12:27"}
+{"current_steps": 35, "total_steps": 360, "loss": 1.1318, "lr": 7.777777777777778e-05, "epoch": 0.48484848484848486, "percentage": 9.72, "elapsed_time": "2:16:36", "remaining_time": "21:08:32"}
+{"current_steps": 36, "total_steps": 360, "loss": 1.1323, "lr": 8e-05, "epoch": 0.4987012987012987, "percentage": 10.0, "elapsed_time": "2:20:29", "remaining_time": "21:04:27"}
+{"current_steps": 37, "total_steps": 360, "loss": 1.1398, "lr": 7.999811966028904e-05, "epoch": 0.5125541125541125, "percentage": 10.28, "elapsed_time": "2:24:23", "remaining_time": "21:00:26"}
+{"current_steps": 38, "total_steps": 360, "loss": 1.1272, "lr": 7.999247881794007e-05, "epoch": 0.5264069264069264, "percentage": 10.56, "elapsed_time": "2:28:16", "remaining_time": "20:56:24"}
+{"current_steps": 39, "total_steps": 360, "loss": 1.1148, "lr": 7.998307800328803e-05, "epoch": 0.5402597402597402, "percentage": 10.83, "elapsed_time": "2:32:09", "remaining_time": "20:52:23"}
+{"current_steps": 40, "total_steps": 360, "loss": 1.1581, "lr": 7.996991810016922e-05, "epoch": 0.5541125541125541, "percentage": 11.11, "elapsed_time": "2:36:02", "remaining_time": "20:48:21"}
+{"current_steps": 41, "total_steps": 360, "loss": 1.1579, "lr": 7.995300034583802e-05, "epoch": 0.567965367965368, "percentage": 11.39, "elapsed_time": "2:39:56", "remaining_time": "20:44:22"}
+{"current_steps": 42, "total_steps": 360, "loss": 1.1154, "lr": 7.993232633085074e-05, "epoch": 0.5818181818181818, "percentage": 11.67, "elapsed_time": "2:43:49", "remaining_time": "20:40:26"}
+{"current_steps": 43, "total_steps": 360, "loss": 1.1361, "lr": 7.990789799891592e-05, "epoch": 0.5956709956709957, "percentage": 11.94, "elapsed_time": "2:47:43", "remaining_time": "20:36:31"}
+{"current_steps": 44, "total_steps": 360, "loss": 1.1437, "lr": 7.987971764671168e-05, "epoch": 0.6095238095238096, "percentage": 12.22, "elapsed_time": "2:51:37", "remaining_time": "20:32:35"}
+{"current_steps": 45, "total_steps": 360, "loss": 1.1278, "lr": 7.984778792366983e-05, "epoch": 0.6233766233766234, "percentage": 12.5, "elapsed_time": "2:55:31", "remaining_time": "20:28:39"}
+{"current_steps": 46, "total_steps": 360, "loss": 1.125, "lr": 7.981211183172663e-05, "epoch": 0.6372294372294373, "percentage": 12.78, "elapsed_time": "2:59:24", "remaining_time": "20:24:37"}
+{"current_steps": 47, "total_steps": 360, "loss": 1.1113, "lr": 7.977269272504075e-05, "epoch": 0.651082251082251, "percentage": 13.06, "elapsed_time": "3:03:17", "remaining_time": "20:20:40"}
+{"current_steps": 48, "total_steps": 360, "loss": 1.1119, "lr": 7.972953430967773e-05, "epoch": 0.6649350649350649, "percentage": 13.33, "elapsed_time": "3:07:11", "remaining_time": "20:16:47"}
+{"current_steps": 49, "total_steps": 360, "loss": 1.1047, "lr": 7.96826406432617e-05, "epoch": 0.6787878787878788, "percentage": 13.61, "elapsed_time": "3:11:05", "remaining_time": "20:12:51"}
+{"current_steps": 50, "total_steps": 360, "loss": 1.1104, "lr": 7.963201613459381e-05, "epoch": 0.6926406926406926, "percentage": 13.89, "elapsed_time": "3:14:59", "remaining_time": "20:08:54"}
+{"current_steps": 51, "total_steps": 360, "loss": 1.1008, "lr": 7.957766554323778e-05, "epoch": 0.7064935064935065, "percentage": 14.17, "elapsed_time": "3:18:52", "remaining_time": "20:04:55"}
+{"current_steps": 52, "total_steps": 360, "loss": 1.1063, "lr": 7.951959397907237e-05, "epoch": 0.7203463203463204, "percentage": 14.44, "elapsed_time": "3:22:45", "remaining_time": "20:00:58"}
+{"current_steps": 53, "total_steps": 360, "loss": 1.0958, "lr": 7.945780690181096e-05, "epoch": 0.7341991341991342, "percentage": 14.72, "elapsed_time": "3:26:38", "remaining_time": "19:57:00"}
+{"current_steps": 54, "total_steps": 360, "loss": 1.1038, "lr": 7.939231012048833e-05, "epoch": 0.7480519480519481, "percentage": 15.0, "elapsed_time": "3:30:32", "remaining_time": "19:53:01"}
+{"current_steps": 55, "total_steps": 360, "loss": 1.088, "lr": 7.932310979291441e-05, "epoch": 0.7619047619047619, "percentage": 15.28, "elapsed_time": "3:34:25", "remaining_time": "19:49:05"}
+{"current_steps": 56, "total_steps": 360, "loss": 1.1005, "lr": 7.925021242509539e-05, "epoch": 0.7757575757575758, "percentage": 15.56, "elapsed_time": "3:38:19", "remaining_time": "19:45:10"}
+{"current_steps": 57, "total_steps": 360, "loss": 1.0885, "lr": 7.917362487062207e-05, "epoch": 0.7896103896103897, "percentage": 15.83, "elapsed_time": "3:42:12", "remaining_time": "19:41:13"}
+{"current_steps": 58, "total_steps": 360, "loss": 1.0889, "lr": 7.909335433002543e-05, "epoch": 0.8034632034632034, "percentage": 16.11, "elapsed_time": "3:46:05", "remaining_time": "19:37:15"}
+{"current_steps": 59, "total_steps": 360, "loss": 1.0809, "lr": 7.900940835009974e-05, "epoch": 0.8173160173160173, "percentage": 16.39, "elapsed_time": "3:49:58", "remaining_time": "19:33:17"}
+{"current_steps": 60, "total_steps": 360, "loss": 1.0844, "lr": 7.892179482319297e-05, "epoch": 0.8311688311688312, "percentage": 16.67, "elapsed_time": "3:53:52", "remaining_time": "19:29:21"}
+{"current_steps": 61, "total_steps": 360, "loss": 1.0868, "lr": 7.883052198646481e-05, "epoch": 0.845021645021645, "percentage": 16.94, "elapsed_time": "3:57:46", "remaining_time": "19:25:27"}
+{"current_steps": 62, "total_steps": 360, "loss": 1.0711, "lr": 7.873559842111225e-05, "epoch": 0.8588744588744589, "percentage": 17.22, "elapsed_time": "4:01:39", "remaining_time": "19:21:32"}
+{"current_steps": 63, "total_steps": 360, "loss": 1.0752, "lr": 7.863703305156273e-05, "epoch": 0.8727272727272727, "percentage": 17.5, "elapsed_time": "4:05:33", "remaining_time": "19:17:38"}
+{"current_steps": 64, "total_steps": 360, "loss": 1.0766, "lr": 7.853483514463521e-05, "epoch": 0.8865800865800866, "percentage": 17.78, "elapsed_time": "4:09:27", "remaining_time": "19:13:43"}
+{"current_steps": 65, "total_steps": 360, "loss": 1.0725, "lr": 7.842901430866882e-05, "epoch": 0.9004329004329005, "percentage": 18.06, "elapsed_time": "4:13:20", "remaining_time": "19:09:46"}
+{"current_steps": 66, "total_steps": 360, "loss": 1.0612, "lr": 7.831958049261956e-05, "epoch": 0.9142857142857143, "percentage": 18.33, "elapsed_time": "4:17:13", "remaining_time": "19:05:51"}
+{"current_steps": 67, "total_steps": 360, "loss": 1.074, "lr": 7.820654398512492e-05, "epoch": 0.9281385281385282, "percentage": 18.61, "elapsed_time": "4:21:07", "remaining_time": "19:01:57"}
+{"current_steps": 68, "total_steps": 360, "loss": 1.0954, "lr": 7.808991541353662e-05, "epoch": 0.941991341991342, "percentage": 18.89, "elapsed_time": "4:25:01", "remaining_time": "18:58:03"}
+{"current_steps": 69, "total_steps": 360, "loss": 1.0752, "lr": 7.796970574292136e-05, "epoch": 0.9558441558441558, "percentage": 19.17, "elapsed_time": "4:28:55", "remaining_time": "18:54:08"}
+{"current_steps": 70, "total_steps": 360, "loss": 1.0821, "lr": 7.784592627503004e-05, "epoch": 0.9696969696969697, "percentage": 19.44, "elapsed_time": "4:32:48", "remaining_time": "18:50:11"}
+{"current_steps": 71, "total_steps": 360, "loss": 1.068, "lr": 7.771858864723504e-05, "epoch": 0.9835497835497835, "percentage": 19.72, "elapsed_time": "4:36:42", "remaining_time": "18:46:17"}
+{"current_steps": 72, "total_steps": 360, "loss": 1.0771, "lr": 7.758770483143634e-05, "epoch": 0.9974025974025974, "percentage": 20.0, "elapsed_time": "4:40:45", "remaining_time": "18:43:01"}
+{"current_steps": 73, "total_steps": 360, "loss": 1.948, "lr": 7.745328713293573e-05, "epoch": 1.0112554112554113, "percentage": 20.28, "elapsed_time": "4:45:11", "remaining_time": "18:41:14"}
+{"current_steps": 74, "total_steps": 360, "loss": 1.0427, "lr": 7.731534818928004e-05, "epoch": 1.025108225108225, "percentage": 20.56, "elapsed_time": "4:49:04", "remaining_time": "18:37:15"}
+{"current_steps": 75, "total_steps": 360, "loss": 1.0479, "lr": 7.71739009690729e-05, "epoch": 1.0389610389610389, "percentage": 20.83, "elapsed_time": "4:52:59", "remaining_time": "18:33:23"}
+{"current_steps": 76, "total_steps": 360, "loss": 1.0333, "lr": 7.702895877075563e-05, "epoch": 1.0528138528138529, "percentage": 21.11, "elapsed_time": "4:56:54", "remaining_time": "18:29:29"}
+{"current_steps": 77, "total_steps": 360, "loss": 1.0579, "lr": 7.688053522135675e-05, "epoch": 1.0666666666666667, "percentage": 21.39, "elapsed_time": "5:00:47", "remaining_time": "18:25:31"}
+{"current_steps": 78, "total_steps": 360, "loss": 1.0636, "lr": 7.672864427521097e-05, "epoch": 1.0805194805194804, "percentage": 21.67, "elapsed_time": "5:04:41", "remaining_time": "18:21:32"}
+{"current_steps": 79, "total_steps": 360, "loss": 1.0442, "lr": 7.657330021264718e-05, "epoch": 1.0943722943722944, "percentage": 21.94, "elapsed_time": "5:08:34", "remaining_time": "18:17:34"}
+{"current_steps": 80, "total_steps": 360, "loss": 1.045, "lr": 7.641451763864587e-05, "epoch": 1.1082251082251082, "percentage": 22.22, "elapsed_time": "5:12:27", "remaining_time": "18:13:36"}
+{"current_steps": 81, "total_steps": 360, "loss": 1.0484, "lr": 7.625231148146601e-05, "epoch": 1.122077922077922, "percentage": 22.5, "elapsed_time": "5:16:21", "remaining_time": "18:09:39"}
+{"current_steps": 82, "total_steps": 360, "loss": 1.0484, "lr": 7.608669699124153e-05, "epoch": 1.135930735930736, "percentage": 22.78, "elapsed_time": "5:20:14", "remaining_time": "18:05:40"}
+{"current_steps": 83, "total_steps": 360, "loss": 1.0453, "lr": 7.591768973854753e-05, "epoch": 1.1497835497835498, "percentage": 23.06, "elapsed_time": "5:24:07", "remaining_time": "18:01:44"}
+{"current_steps": 84, "total_steps": 360, "loss": 1.0473, "lr": 7.57453056129365e-05, "epoch": 1.1636363636363636, "percentage": 23.33, "elapsed_time": "5:28:00", "remaining_time": "17:57:45"}
+{"current_steps": 85, "total_steps": 360, "loss": 1.0432, "lr": 7.556956082144425e-05, "epoch": 1.1774891774891776, "percentage": 23.61, "elapsed_time": "5:31:54", "remaining_time": "17:53:49"}
+{"current_steps": 86, "total_steps": 360, "loss": 1.0502, "lr": 7.539047188706631e-05, "epoch": 1.1913419913419914, "percentage": 23.89, "elapsed_time": "5:35:47", "remaining_time": "17:49:51"}
+{"current_steps": 87, "total_steps": 360, "loss": 1.0389, "lr": 7.520805564720444e-05, "epoch": 1.2051948051948052, "percentage": 24.17, "elapsed_time": "5:39:40", "remaining_time": "17:45:53"}
+{"current_steps": 88, "total_steps": 360, "loss": 1.0297, "lr": 7.502232925208365e-05, "epoch": 1.2190476190476192, "percentage": 24.44, "elapsed_time": "5:43:34", "remaining_time": "17:41:57"}
+{"current_steps": 89, "total_steps": 360, "loss": 1.026, "lr": 7.483331016313969e-05, "epoch": 1.232900432900433, "percentage": 24.72, "elapsed_time": "5:47:27", "remaining_time": "17:38:00"}
+{"current_steps": 90, "total_steps": 360, "loss": 1.042, "lr": 7.464101615137756e-05, "epoch": 1.2467532467532467, "percentage": 25.0, "elapsed_time": "5:51:21", "remaining_time": "17:34:03"}
+{"current_steps": 91, "total_steps": 360, "loss": 1.0375, "lr": 7.444546529570055e-05, "epoch": 1.2606060606060607, "percentage": 25.28, "elapsed_time": "5:55:14", "remaining_time": "17:30:07"}
+{"current_steps": 92, "total_steps": 360, "loss": 1.0232, "lr": 7.424667598121067e-05, "epoch": 1.2744588744588745, "percentage": 25.56, "elapsed_time": "5:59:07", "remaining_time": "17:26:10"}
+{"current_steps": 93, "total_steps": 360, "loss": 1.0358, "lr": 7.404466689747999e-05, "epoch": 1.2883116883116883, "percentage": 25.83, "elapsed_time": "6:03:01", "remaining_time": "17:22:13"}
+{"current_steps": 94, "total_steps": 360, "loss": 1.041, "lr": 7.383945703679365e-05, "epoch": 1.3021645021645023, "percentage": 26.11, "elapsed_time": "6:06:54", "remaining_time": "17:18:16"}
+{"current_steps": 95, "total_steps": 360, "loss": 1.0373, "lr": 7.363106569236413e-05, "epoch": 1.316017316017316, "percentage": 26.39, "elapsed_time": "6:10:48", "remaining_time": "17:14:21"}
+{"current_steps": 96, "total_steps": 360, "loss": 1.0232, "lr": 7.341951245651747e-05, "epoch": 1.3298701298701299, "percentage": 26.67, "elapsed_time": "6:14:42", "remaining_time": "17:10:26"}
+{"current_steps": 97, "total_steps": 360, "loss": 1.0331, "lr": 7.320481721885116e-05, "epoch": 1.3437229437229437, "percentage": 26.94, "elapsed_time": "6:18:35", "remaining_time": "17:06:29"}
+{"current_steps": 98, "total_steps": 360, "loss": 1.0392, "lr": 7.298700016436427e-05, "epoch": 1.3575757575757577, "percentage": 27.22, "elapsed_time": "6:22:28", "remaining_time": "17:02:32"}
+{"current_steps": 99, "total_steps": 360, "loss": 1.0302, "lr": 7.276608177155968e-05, "epoch": 1.3714285714285714, "percentage": 27.5, "elapsed_time": "6:26:22", "remaining_time": "16:58:38"}
+{"current_steps": 100, "total_steps": 360, "loss": 1.0359, "lr": 7.254208281051871e-05, "epoch": 1.3852813852813852, "percentage": 27.78, "elapsed_time": "6:30:15", "remaining_time": "16:54:39"}
+{"current_steps": 101, "total_steps": 360, "loss": 1.0203, "lr": 7.231502434094845e-05, "epoch": 1.399134199134199, "percentage": 28.06, "elapsed_time": "6:34:09", "remaining_time": "16:50:45"}
+{"current_steps": 102, "total_steps": 360, "loss": 1.0198, "lr": 7.208492771020176e-05, "epoch": 1.412987012987013, "percentage": 28.33, "elapsed_time": "6:38:02", "remaining_time": "16:46:49"}
+{"current_steps": 103, "total_steps": 360, "loss": 1.0217, "lr": 7.185181455127023e-05, "epoch": 1.4268398268398268, "percentage": 28.61, "elapsed_time": "6:41:56", "remaining_time": "16:42:54"}
+{"current_steps": 104, "total_steps": 360, "loss": 1.0128, "lr": 7.161570678075038e-05, "epoch": 1.4406926406926406, "percentage": 28.89, "elapsed_time": "6:45:50", "remaining_time": "16:38:59"}
+{"current_steps": 105, "total_steps": 360, "loss": 1.0238, "lr": 7.137662659678303e-05, "epoch": 1.4545454545454546, "percentage": 29.17, "elapsed_time": "6:49:43", "remaining_time": "16:35:03"}
+{"current_steps": 106, "total_steps": 360, "loss": 1.0182, "lr": 7.113459647696641e-05, "epoch": 1.4683982683982684, "percentage": 29.44, "elapsed_time": "6:53:36", "remaining_time": "16:31:07"}
+{"current_steps": 107, "total_steps": 360, "loss": 1.012, "lr": 7.088963917624277e-05, "epoch": 1.4822510822510822, "percentage": 29.72, "elapsed_time": "6:57:30", "remaining_time": "16:27:10"}
+{"current_steps": 108, "total_steps": 360, "loss": 1.0264, "lr": 7.064177772475912e-05, "epoch": 1.4961038961038962, "percentage": 30.0, "elapsed_time": "7:01:24", "remaining_time": "16:23:16"}
+{"current_steps": 109, "total_steps": 360, "loss": 1.0151, "lr": 7.039103542570199e-05, "epoch": 1.50995670995671, "percentage": 30.28, "elapsed_time": "7:05:17", "remaining_time": "16:19:20"}
+{"current_steps": 110, "total_steps": 360, "loss": 1.0162, "lr": 7.013743585310642e-05, "epoch": 1.5238095238095237, "percentage": 30.56, "elapsed_time": "7:09:11", "remaining_time": "16:15:25"}
+{"current_steps": 111, "total_steps": 360, "loss": 1.0199, "lr": 6.988100284963985e-05, "epoch": 1.5376623376623377, "percentage": 30.83, "elapsed_time": "7:13:04", "remaining_time": "16:11:29"}
+{"current_steps": 112, "total_steps": 360, "loss": 1.0242, "lr": 6.96217605243602e-05, "epoch": 1.5515151515151515, "percentage": 31.11, "elapsed_time": "7:16:57", "remaining_time": "16:07:33"}
+{"current_steps": 113, "total_steps": 360, "loss": 1.0241, "lr": 6.935973325044941e-05, "epoch": 1.5653679653679653, "percentage": 31.39, "elapsed_time": "7:20:50", "remaining_time": "16:03:36"}
+{"current_steps": 114, "total_steps": 360, "loss": 1.0082, "lr": 6.909494566292195e-05, "epoch": 1.5792207792207793, "percentage": 31.67, "elapsed_time": "7:24:44", "remaining_time": "15:59:41"}
+{"current_steps": 115, "total_steps": 360, "loss": 1.0161, "lr": 6.882742265630859e-05, "epoch": 1.593073593073593, "percentage": 31.94, "elapsed_time": "7:28:37", "remaining_time": "15:55:46"}
+{"current_steps": 116, "total_steps": 360, "loss": 1.0223, "lr": 6.855718938231597e-05, "epoch": 1.6069264069264069, "percentage": 32.22, "elapsed_time": "7:32:31", "remaining_time": "15:51:52"}
+{"current_steps": 117, "total_steps": 360, "loss": 1.0059, "lr": 6.828427124746191e-05, "epoch": 1.6207792207792209, "percentage": 32.5, "elapsed_time": "7:36:25", "remaining_time": "15:47:57"}
+{"current_steps": 118, "total_steps": 360, "loss": 1.0161, "lr": 6.800869391068674e-05, "epoch": 1.6346320346320347, "percentage": 32.78, "elapsed_time": "7:40:18", "remaining_time": "15:44:01"}
+{"current_steps": 119, "total_steps": 360, "loss": 1.0109, "lr": 6.773048328094097e-05, "epoch": 1.6484848484848484, "percentage": 33.06, "elapsed_time": "7:44:11", "remaining_time": "15:40:05"}
+{"current_steps": 120, "total_steps": 360, "loss": 1.0187, "lr": 6.744966551474936e-05, "epoch": 1.6623376623376624, "percentage": 33.33, "elapsed_time": "7:48:04", "remaining_time": "15:36:09"}
+{"current_steps": 121, "total_steps": 360, "loss": 1.0131, "lr": 6.716626701375174e-05, "epoch": 1.6761904761904762, "percentage": 33.61, "elapsed_time": "7:51:58", "remaining_time": "15:32:14"}
+{"current_steps": 122, "total_steps": 360, "loss": 1.0084, "lr": 6.688031442222091e-05, "epoch": 1.69004329004329, "percentage": 33.89, "elapsed_time": "7:55:51", "remaining_time": "15:28:19"}
+{"current_steps": 123, "total_steps": 360, "loss": 1.0095, "lr": 6.659183462455751e-05, "epoch": 1.703896103896104, "percentage": 34.17, "elapsed_time": "7:59:45", "remaining_time": "15:24:24"}
+{"current_steps": 124, "total_steps": 360, "loss": 1.0117, "lr": 6.630085474276256e-05, "epoch": 1.7177489177489178, "percentage": 34.44, "elapsed_time": "8:03:38", "remaining_time": "15:20:29"}
+{"current_steps": 125, "total_steps": 360, "loss": 1.0055, "lr": 6.600740213388735e-05, "epoch": 1.7316017316017316, "percentage": 34.72, "elapsed_time": "8:07:31", "remaining_time": "15:16:33"}
+{"current_steps": 126, "total_steps": 360, "loss": 0.9998, "lr": 6.571150438746157e-05, "epoch": 1.7454545454545456, "percentage": 35.0, "elapsed_time": "8:11:25", "remaining_time": "15:12:39"}
+{"current_steps": 127, "total_steps": 360, "loss": 1.003, "lr": 6.54131893228994e-05, "epoch": 1.7593073593073592, "percentage": 35.28, "elapsed_time": "8:15:19", "remaining_time": "15:08:44"}
+{"current_steps": 128, "total_steps": 360, "loss": 1.0044, "lr": 6.511248498688396e-05, "epoch": 1.7731601731601732, "percentage": 35.56, "elapsed_time": "8:19:12", "remaining_time": "15:04:48"}
+{"current_steps": 129, "total_steps": 360, "loss": 1.0109, "lr": 6.480941965073041e-05, "epoch": 1.7870129870129872, "percentage": 35.83, "elapsed_time": "8:23:06", "remaining_time": "15:00:54"}
+{"current_steps": 130, "total_steps": 360, "loss": 1.0017, "lr": 6.450402180772811e-05, "epoch": 1.8008658008658007, "percentage": 36.11, "elapsed_time": "8:26:59", "remaining_time": "14:56:59"}
+{"current_steps": 131, "total_steps": 360, "loss": 1.0018, "lr": 6.419632017046167e-05, "epoch": 1.8147186147186147, "percentage": 36.39, "elapsed_time": "8:30:53", "remaining_time": "14:53:04"}
+{"current_steps": 132, "total_steps": 360, "loss": 0.9993, "lr": 6.388634366811146e-05, "epoch": 1.8285714285714287, "percentage": 36.67, "elapsed_time": "8:34:46", "remaining_time": "14:49:09"}
+{"current_steps": 133, "total_steps": 360, "loss": 1.0095, "lr": 6.35741214437338e-05, "epoch": 1.8424242424242423, "percentage": 36.94, "elapsed_time": "8:38:40", "remaining_time": "14:45:14"}
+{"current_steps": 134, "total_steps": 360, "loss": 1.0062, "lr": 6.325968285152107e-05, "epoch": 1.8562770562770563, "percentage": 37.22, "elapsed_time": "8:42:33", "remaining_time": "14:41:19"}
+{"current_steps": 135, "total_steps": 360, "loss": 1.0052, "lr": 6.294305745404185e-05, "epoch": 1.87012987012987, "percentage": 37.5, "elapsed_time": "8:46:28", "remaining_time": "14:37:27"}
+{"current_steps": 136, "total_steps": 360, "loss": 1.0067, "lr": 6.262427501946155e-05, "epoch": 1.8839826839826839, "percentage": 37.78, "elapsed_time": "8:50:21", "remaining_time": "14:33:32"}
+{"current_steps": 137, "total_steps": 360, "loss": 1.0063, "lr": 6.230336551874372e-05, "epoch": 1.8978354978354979, "percentage": 38.06, "elapsed_time": "8:54:15", "remaining_time": "14:29:38"}
+{"current_steps": 138, "total_steps": 360, "loss": 1.0011, "lr": 6.198035912283225e-05, "epoch": 1.9116883116883117, "percentage": 38.33, "elapsed_time": "8:58:09", "remaining_time": "14:25:43"}
+{"current_steps": 139, "total_steps": 360, "loss": 0.9934, "lr": 6.165528619981479e-05, "epoch": 1.9255411255411254, "percentage": 38.61, "elapsed_time": "9:02:02", "remaining_time": "14:21:48"}
+{"current_steps": 140, "total_steps": 360, "loss": 1.0023, "lr": 6.132817731206766e-05, "epoch": 1.9393939393939394, "percentage": 38.89, "elapsed_time": "9:05:56", "remaining_time": "14:17:54"}
+{"current_steps": 141, "total_steps": 360, "loss": 0.9875, "lr": 6.099906321338241e-05, "epoch": 1.9532467532467532, "percentage": 39.17, "elapsed_time": "9:09:50", "remaining_time": "14:14:00"}
+{"current_steps": 142, "total_steps": 360, "loss": 0.9969, "lr": 6.0667974846074524e-05, "epoch": 1.967099567099567, "percentage": 39.44, "elapsed_time": "9:13:44", "remaining_time": "14:10:05"}
+{"current_steps": 143, "total_steps": 360, "loss": 1.0052, "lr": 6.033494333807422e-05, "epoch": 1.980952380952381, "percentage": 39.72, "elapsed_time": "9:17:38", "remaining_time": "14:06:12"}
+{"current_steps": 144, "total_steps": 360, "loss": 0.9857, "lr": 6.000000000000001e-05, "epoch": 1.9948051948051948, "percentage": 40.0, "elapsed_time": "9:21:31", "remaining_time": "14:02:17"}
+{"current_steps": 145, "total_steps": 360, "loss": 1.8002, "lr": 5.9663176322214826e-05, "epoch": 2.0086580086580086, "percentage": 40.28, "elapsed_time": "9:25:51", "remaining_time": "13:59:02"}
+{"current_steps": 146, "total_steps": 360, "loss": 0.9591, "lr": 5.9324503971865545e-05, "epoch": 2.0225108225108226, "percentage": 40.56, "elapsed_time": "9:29:45", "remaining_time": "13:55:07"}
+{"current_steps": 147, "total_steps": 360, "loss": 0.9555, "lr": 5.8984014789905625e-05, "epoch": 2.036363636363636, "percentage": 40.83, "elapsed_time": "9:33:39", "remaining_time": "13:51:13"}
+{"current_steps": 148, "total_steps": 360, "loss": 0.9637, "lr": 5.8641740788101566e-05, "epoch": 2.05021645021645, "percentage": 41.11, "elapsed_time": "9:37:32", "remaining_time": "13:47:17"}
+{"current_steps": 149, "total_steps": 360, "loss": 0.9396, "lr": 5.8297714146023236e-05, "epoch": 2.064069264069264, "percentage": 41.39, "elapsed_time": "9:41:26", "remaining_time": "13:43:22"}
+{"current_steps": 150, "total_steps": 360, "loss": 0.9523, "lr": 5.79519672080185e-05, "epoch": 2.0779220779220777, "percentage": 41.67, "elapsed_time": "9:45:19", "remaining_time": "13:39:27"}
+{"current_steps": 151, "total_steps": 360, "loss": 0.9595, "lr": 5.76045324801722e-05, "epoch": 2.0917748917748917, "percentage": 41.94, "elapsed_time": "9:49:12", "remaining_time": "13:35:31"}
+{"current_steps": 152, "total_steps": 360, "loss": 0.9514, "lr": 5.7255442627250146e-05, "epoch": 2.1056277056277057, "percentage": 42.22, "elapsed_time": "9:53:06", "remaining_time": "13:31:36"}
+{"current_steps": 153, "total_steps": 360, "loss": 0.9482, "lr": 5.6904730469627985e-05, "epoch": 2.1194805194805193, "percentage": 42.5, "elapsed_time": "9:56:59", "remaining_time": "13:27:41"}
+{"current_steps": 154, "total_steps": 360, "loss": 0.9587, "lr": 5.6552428980205575e-05, "epoch": 2.1333333333333333, "percentage": 42.78, "elapsed_time": "10:00:52", "remaining_time": "13:23:46"}
+{"current_steps": 155, "total_steps": 360, "loss": 0.9562, "lr": 5.619857128130695e-05, "epoch": 2.1471861471861473, "percentage": 43.06, "elapsed_time": "10:04:46", "remaining_time": "13:19:51"}
+{"current_steps": 156, "total_steps": 360, "loss": 0.9459, "lr": 5.584319064156628e-05, "epoch": 2.161038961038961, "percentage": 43.33, "elapsed_time": "10:08:39", "remaining_time": "13:15:56"}
+{"current_steps": 157, "total_steps": 360, "loss": 0.9528, "lr": 5.548632047280003e-05, "epoch": 2.174891774891775, "percentage": 43.61, "elapsed_time": "10:12:33", "remaining_time": "13:12:01"}
+{"current_steps": 158, "total_steps": 360, "loss": 0.9482, "lr": 5.5127994326865706e-05, "epoch": 2.188744588744589, "percentage": 43.89, "elapsed_time": "10:16:26", "remaining_time": "13:08:05"}
+{"current_steps": 159, "total_steps": 360, "loss": 0.9429, "lr": 5.476824589250738e-05, "epoch": 2.2025974025974024, "percentage": 44.17, "elapsed_time": "10:20:19", "remaining_time": "13:04:11"}
+{"current_steps": 160, "total_steps": 360, "loss": 0.9674, "lr": 5.440710899218842e-05, "epoch": 2.2164502164502164, "percentage": 44.44, "elapsed_time": "10:24:12", "remaining_time": "13:00:15"}
+{"current_steps": 161, "total_steps": 360, "loss": 0.9667, "lr": 5.404461757891156e-05, "epoch": 2.2303030303030305, "percentage": 44.72, "elapsed_time": "10:28:05", "remaining_time": "12:56:20"}
+{"current_steps": 162, "total_steps": 360, "loss": 0.9478, "lr": 5.368080573302676e-05, "epoch": 2.244155844155844, "percentage": 45.0, "elapsed_time": "10:31:58", "remaining_time": "12:52:24"}
+{"current_steps": 163, "total_steps": 360, "loss": 0.9409, "lr": 5.331570765902706e-05, "epoch": 2.258008658008658, "percentage": 45.28, "elapsed_time": "10:35:51", "remaining_time": "12:48:29"}
+{"current_steps": 164, "total_steps": 360, "loss": 0.9416, "lr": 5.294935768233285e-05, "epoch": 2.271861471861472, "percentage": 45.56, "elapsed_time": "10:39:44", "remaining_time": "12:44:34"}
+{"current_steps": 165, "total_steps": 360, "loss": 0.9463, "lr": 5.258179024606455e-05, "epoch": 2.2857142857142856, "percentage": 45.83, "elapsed_time": "10:43:37", "remaining_time": "12:40:39"}
+{"current_steps": 166, "total_steps": 360, "loss": 0.9491, "lr": 5.2213039907804535e-05, "epoch": 2.2995670995670996, "percentage": 46.11, "elapsed_time": "10:47:32", "remaining_time": "12:36:45"}
+{"current_steps": 167, "total_steps": 360, "loss": 0.95, "lr": 5.1843141336348e-05, "epoch": 2.3134199134199136, "percentage": 46.39, "elapsed_time": "10:51:25", "remaining_time": "12:32:51"}
+{"current_steps": 168, "total_steps": 360, "loss": 0.953, "lr": 5.1472129308443616e-05, "epoch": 2.327272727272727, "percentage": 46.67, "elapsed_time": "10:55:19", "remaining_time": "12:28:56"}
+{"current_steps": 169, "total_steps": 360, "loss": 0.957, "lr": 5.1100038705523834e-05, "epoch": 2.341125541125541, "percentage": 46.94, "elapsed_time": "10:59:12", "remaining_time": "12:25:01"}
+{"current_steps": 170, "total_steps": 360, "loss": 0.9348, "lr": 5.07269045104255e-05, "epoch": 2.354978354978355, "percentage": 47.22, "elapsed_time": "11:03:05", "remaining_time": "12:21:06"}
+{"current_steps": 171, "total_steps": 360, "loss": 0.9501, "lr": 5.0352761804100835e-05, "epoch": 2.3688311688311687, "percentage": 47.5, "elapsed_time": "11:06:58", "remaining_time": "12:17:11"}
+{"current_steps": 172, "total_steps": 360, "loss": 0.9548, "lr": 4.9977645762319255e-05, "epoch": 2.3826839826839827, "percentage": 47.78, "elapsed_time": "11:10:51", "remaining_time": "12:13:15"}
+{"current_steps": 173, "total_steps": 360, "loss": 0.9516, "lr": 4.9601591652360244e-05, "epoch": 2.3965367965367967, "percentage": 48.06, "elapsed_time": "11:14:44", "remaining_time": "12:09:20"}
+{"current_steps": 174, "total_steps": 360, "loss": 0.9537, "lr": 4.922463482969761e-05, "epoch": 2.4103896103896103, "percentage": 48.33, "elapsed_time": "11:18:38", "remaining_time": "12:05:27"}
+{"current_steps": 175, "total_steps": 360, "loss": 0.9566, "lr": 4.884681073467551e-05, "epoch": 2.4242424242424243, "percentage": 48.61, "elapsed_time": "11:22:32", "remaining_time": "12:01:32"}
+{"current_steps": 176, "total_steps": 360, "loss": 0.9602, "lr": 4.846815488917644e-05, "epoch": 2.4380952380952383, "percentage": 48.89, "elapsed_time": "11:26:26", "remaining_time": "11:57:38"}
+{"current_steps": 177, "total_steps": 360, "loss": 0.9513, "lr": 4.808870289328153e-05, "epoch": 2.451948051948052, "percentage": 49.17, "elapsed_time": "11:30:19", "remaining_time": "11:53:43"}
+{"current_steps": 178, "total_steps": 360, "loss": 0.9453, "lr": 4.7708490421923596e-05, "epoch": 2.465800865800866, "percentage": 49.44, "elapsed_time": "11:34:12", "remaining_time": "11:49:48"}
+{"current_steps": 179, "total_steps": 360, "loss": 0.9581, "lr": 4.7327553221533074e-05, "epoch": 2.47965367965368, "percentage": 49.72, "elapsed_time": "11:38:05", "remaining_time": "11:45:53"}
+{"current_steps": 180, "total_steps": 360, "loss": 0.948, "lr": 4.694592710667723e-05, "epoch": 2.4935064935064934, "percentage": 50.0, "elapsed_time": "11:41:58", "remaining_time": "11:41:58"}
+{"current_steps": 181, "total_steps": 360, "loss": 0.9505, "lr": 4.656364795669297e-05, "epoch": 2.5073593073593075, "percentage": 50.28, "elapsed_time": "11:45:52", "remaining_time": "11:38:04"}
+{"current_steps": 182, "total_steps": 360, "loss": 0.955, "lr": 4.618075171231363e-05, "epoch": 2.5212121212121215, "percentage": 50.56, "elapsed_time": "11:49:46", "remaining_time": "11:34:10"}
+{"current_steps": 183, "total_steps": 360, "loss": 0.9479, "lr": 4.579727437228987e-05, "epoch": 2.535064935064935, "percentage": 50.83, "elapsed_time": "11:53:39", "remaining_time": "11:30:15"}
+{"current_steps": 184, "total_steps": 360, "loss": 0.9444, "lr": 4.541325199000525e-05, "epoch": 2.548917748917749, "percentage": 51.11, "elapsed_time": "11:57:32", "remaining_time": "11:26:20"}
+{"current_steps": 185, "total_steps": 360, "loss": 0.9484, "lr": 4.502872067008652e-05, "epoch": 2.562770562770563, "percentage": 51.39, "elapsed_time": "12:01:25", "remaining_time": "11:22:25"}
+{"current_steps": 186, "total_steps": 360, "loss": 0.9478, "lr": 4.464371656500921e-05, "epoch": 2.5766233766233766, "percentage": 51.67, "elapsed_time": "12:05:18", "remaining_time": "11:18:31"}
+{"current_steps": 187, "total_steps": 360, "loss": 0.9642, "lr": 4.425827587169873e-05, "epoch": 2.5904761904761906, "percentage": 51.94, "elapsed_time": "12:09:11", "remaining_time": "11:14:36"}
+{"current_steps": 188, "total_steps": 360, "loss": 0.9354, "lr": 4.387243482812717e-05, "epoch": 2.6043290043290046, "percentage": 52.22, "elapsed_time": "12:13:03", "remaining_time": "11:10:40"}
+{"current_steps": 189, "total_steps": 360, "loss": 0.9608, "lr": 4.348622970990634e-05, "epoch": 2.618181818181818, "percentage": 52.5, "elapsed_time": "12:16:58", "remaining_time": "11:06:46"}
+{"current_steps": 190, "total_steps": 360, "loss": 0.9365, "lr": 4.309969682687724e-05, "epoch": 2.632034632034632, "percentage": 52.78, "elapsed_time": "12:20:51", "remaining_time": "11:02:52"}
+{"current_steps": 191, "total_steps": 360, "loss": 0.943, "lr": 4.271287251969637e-05, "epoch": 2.6458874458874457, "percentage": 53.06, "elapsed_time": "12:24:44", "remaining_time": "10:58:57"}
+{"current_steps": 192, "total_steps": 360, "loss": 0.9629, "lr": 4.2325793156419035e-05, "epoch": 2.6597402597402597, "percentage": 53.33, "elapsed_time": "12:28:37", "remaining_time": "10:55:03"}
+{"current_steps": 193, "total_steps": 360, "loss": 0.9399, "lr": 4.193849512908013e-05, "epoch": 2.6735930735930737, "percentage": 53.61, "elapsed_time": "12:32:31", "remaining_time": "10:51:08"}
+{"current_steps": 194, "total_steps": 360, "loss": 0.9517, "lr": 4.155101485027268e-05, "epoch": 2.6874458874458873, "percentage": 53.89, "elapsed_time": "12:36:24", "remaining_time": "10:47:13"}
+{"current_steps": 195, "total_steps": 360, "loss": 0.9532, "lr": 4.116338874972446e-05, "epoch": 2.7012987012987013, "percentage": 54.17, "elapsed_time": "12:40:18", "remaining_time": "10:43:20"}
+{"current_steps": 196, "total_steps": 360, "loss": 0.9443, "lr": 4.077565327087298e-05, "epoch": 2.7151515151515153, "percentage": 54.44, "elapsed_time": "12:44:11", "remaining_time": "10:39:25"}
+{"current_steps": 197, "total_steps": 360, "loss": 0.9384, "lr": 4.0387844867439143e-05, "epoch": 2.729004329004329, "percentage": 54.72, "elapsed_time": "12:48:04", "remaining_time": "10:35:30"}
+{"current_steps": 198, "total_steps": 360, "loss": 0.9506, "lr": 4e-05, "epoch": 2.742857142857143, "percentage": 55.0, "elapsed_time": "12:51:57", "remaining_time": "10:31:36"}
+{"current_steps": 199, "total_steps": 360, "loss": 0.944, "lr": 3.961215513256086e-05, "epoch": 2.7567099567099564, "percentage": 55.28, "elapsed_time": "12:55:51", "remaining_time": "10:27:42"}
+{"current_steps": 200, "total_steps": 360, "loss": 0.9423, "lr": 3.9224346729127034e-05, "epoch": 2.7705627705627704, "percentage": 55.56, "elapsed_time": "12:59:44", "remaining_time": "10:23:47"}
+{"current_steps": 201, "total_steps": 360, "loss": 0.9355, "lr": 3.8836611250275546e-05, "epoch": 2.7844155844155845, "percentage": 55.83, "elapsed_time": "13:03:38", "remaining_time": "10:19:53"}
+{"current_steps": 202, "total_steps": 360, "loss": 0.9519, "lr": 3.844898514972733e-05, "epoch": 2.798268398268398, "percentage": 56.11, "elapsed_time": "13:07:31", "remaining_time": "10:15:59"}
+{"current_steps": 203, "total_steps": 360, "loss": 0.951, "lr": 3.806150487091989e-05, "epoch": 2.812121212121212, "percentage": 56.39, "elapsed_time": "13:11:24", "remaining_time": "10:12:04"}
+{"current_steps": 204, "total_steps": 360, "loss": 0.9425, "lr": 3.767420684358097e-05, "epoch": 2.825974025974026, "percentage": 56.67, "elapsed_time": "13:15:17", "remaining_time": "10:08:10"}
+{"current_steps": 205, "total_steps": 360, "loss": 0.9496, "lr": 3.7287127480303634e-05, "epoch": 2.8398268398268396, "percentage": 56.94, "elapsed_time": "13:19:11", "remaining_time": "10:04:16"}
+{"current_steps": 206, "total_steps": 360, "loss": 0.9326, "lr": 3.690030317312277e-05, "epoch": 2.8536796536796536, "percentage": 57.22, "elapsed_time": "13:23:04", "remaining_time": "10:00:21"}
+{"current_steps": 207, "total_steps": 360, "loss": 0.958, "lr": 3.6513770290093674e-05, "epoch": 2.8675324675324676, "percentage": 57.5, "elapsed_time": "13:26:58", "remaining_time": "9:56:27"}
+{"current_steps": 208, "total_steps": 360, "loss": 0.9475, "lr": 3.612756517187284e-05, "epoch": 2.881385281385281, "percentage": 57.78, "elapsed_time": "13:30:51", "remaining_time": "9:52:33"}
+{"current_steps": 209, "total_steps": 360, "loss": 0.9446, "lr": 3.574172412830127e-05, "epoch": 2.895238095238095, "percentage": 58.06, "elapsed_time": "13:34:44", "remaining_time": "9:48:38"}
+{"current_steps": 210, "total_steps": 360, "loss": 0.9518, "lr": 3.535628343499079e-05, "epoch": 2.909090909090909, "percentage": 58.33, "elapsed_time": "13:38:37", "remaining_time": "9:44:44"}
+{"current_steps": 211, "total_steps": 360, "loss": 0.9321, "lr": 3.49712793299135e-05, "epoch": 2.9229437229437227, "percentage": 58.61, "elapsed_time": "13:42:31", "remaining_time": "9:40:50"}
+{"current_steps": 212, "total_steps": 360, "loss": 0.939, "lr": 3.458674800999477e-05, "epoch": 2.9367965367965367, "percentage": 58.89, "elapsed_time": "13:46:24", "remaining_time": "9:36:55"}
+{"current_steps": 213, "total_steps": 360, "loss": 0.9519, "lr": 3.4202725627710136e-05, "epoch": 2.9506493506493507, "percentage": 59.17, "elapsed_time": "13:50:17", "remaining_time": "9:33:00"}
+{"current_steps": 214, "total_steps": 360, "loss": 0.9408, "lr": 3.3819248287686386e-05, "epoch": 2.9645021645021643, "percentage": 59.44, "elapsed_time": "13:54:09", "remaining_time": "9:29:06"}
+{"current_steps": 215, "total_steps": 360, "loss": 0.9366, "lr": 3.343635204330704e-05, "epoch": 2.9783549783549783, "percentage": 59.72, "elapsed_time": "13:58:03", "remaining_time": "9:25:12"}
+{"current_steps": 216, "total_steps": 360, "loss": 0.9261, "lr": 3.305407289332279e-05, "epoch": 2.9922077922077923, "percentage": 60.0, "elapsed_time": "14:01:57", "remaining_time": "9:21:18"}
+{"current_steps": 217, "total_steps": 360, "loss": 1.6737, "lr": 3.267244677846693e-05, "epoch": 3.006060606060606, "percentage": 60.28, "elapsed_time": "14:06:17", "remaining_time": "9:17:41"}
+{"current_steps": 218, "total_steps": 360, "loss": 0.9065, "lr": 3.229150957807641e-05, "epoch": 3.01991341991342, "percentage": 60.56, "elapsed_time": "14:10:10", "remaining_time": "9:13:47"}
+{"current_steps": 219, "total_steps": 360, "loss": 0.8993, "lr": 3.191129710671849e-05, "epoch": 3.033766233766234, "percentage": 60.83, "elapsed_time": "14:14:03", "remaining_time": "9:09:52"}
+{"current_steps": 220, "total_steps": 360, "loss": 0.8924, "lr": 3.153184511082359e-05, "epoch": 3.0476190476190474, "percentage": 61.11, "elapsed_time": "14:17:56", "remaining_time": "9:05:57"}
+{"current_steps": 221, "total_steps": 360, "loss": 0.9091, "lr": 3.1153189265324494e-05, "epoch": 3.0614718614718615, "percentage": 61.39, "elapsed_time": "14:21:49", "remaining_time": "9:02:03"}
+{"current_steps": 222, "total_steps": 360, "loss": 0.9103, "lr": 3.07753651703024e-05, "epoch": 3.0753246753246755, "percentage": 61.67, "elapsed_time": "14:25:42", "remaining_time": "8:58:08"}
+{"current_steps": 223, "total_steps": 360, "loss": 0.8895, "lr": 3.0398408347639773e-05, "epoch": 3.089177489177489, "percentage": 61.94, "elapsed_time": "14:29:36", "remaining_time": "8:54:14"}
+{"current_steps": 224, "total_steps": 360, "loss": 0.8954, "lr": 3.0022354237680752e-05, "epoch": 3.103030303030303, "percentage": 62.22, "elapsed_time": "14:33:29", "remaining_time": "8:50:20"}
+{"current_steps": 225, "total_steps": 360, "loss": 0.8954, "lr": 2.9647238195899168e-05, "epoch": 3.116883116883117, "percentage": 62.5, "elapsed_time": "14:37:22", "remaining_time": "8:46:25"}
+{"current_steps": 226, "total_steps": 360, "loss": 0.897, "lr": 2.9273095489574502e-05, "epoch": 3.1307359307359306, "percentage": 62.78, "elapsed_time": "14:41:16", "remaining_time": "8:42:31"}
+{"current_steps": 227, "total_steps": 360, "loss": 0.907, "lr": 2.889996129447618e-05, "epoch": 3.1445887445887446, "percentage": 63.06, "elapsed_time": "14:45:09", "remaining_time": "8:38:37"}
+{"current_steps": 228, "total_steps": 360, "loss": 0.8981, "lr": 2.8527870691556404e-05, "epoch": 3.1584415584415586, "percentage": 63.33, "elapsed_time": "14:49:02", "remaining_time": "8:34:42"}
+{"current_steps": 229, "total_steps": 360, "loss": 0.9033, "lr": 2.8156858663652015e-05, "epoch": 3.172294372294372, "percentage": 63.61, "elapsed_time": "14:52:55", "remaining_time": "8:30:48"}
+{"current_steps": 230, "total_steps": 360, "loss": 0.9059, "lr": 2.778696009219548e-05, "epoch": 3.186147186147186, "percentage": 63.89, "elapsed_time": "14:56:48", "remaining_time": "8:26:53"}
+{"current_steps": 231, "total_steps": 360, "loss": 0.8894, "lr": 2.7418209753935464e-05, "epoch": 3.2, "percentage": 64.17, "elapsed_time": "15:00:41", "remaining_time": "8:22:58"}
+{"current_steps": 232, "total_steps": 360, "loss": 0.8937, "lr": 2.7050642317667164e-05, "epoch": 3.2138528138528137, "percentage": 64.44, "elapsed_time": "15:04:34", "remaining_time": "8:19:04"}
+{"current_steps": 233, "total_steps": 360, "loss": 0.9068, "lr": 2.6684292340972936e-05, "epoch": 3.2277056277056277, "percentage": 64.72, "elapsed_time": "15:08:27", "remaining_time": "8:15:10"}
+{"current_steps": 234, "total_steps": 360, "loss": 0.8999, "lr": 2.6319194266973256e-05, "epoch": 3.2415584415584417, "percentage": 65.0, "elapsed_time": "15:12:20", "remaining_time": "8:11:15"}
+{"current_steps": 235, "total_steps": 360, "loss": 0.8876, "lr": 2.5955382421088457e-05, "epoch": 3.2554112554112553, "percentage": 65.28, "elapsed_time": "15:16:13", "remaining_time": "8:07:21"}
+{"current_steps": 236, "total_steps": 360, "loss": 0.9056, "lr": 2.5592891007811594e-05, "epoch": 3.2692640692640693, "percentage": 65.56, "elapsed_time": "15:20:06", "remaining_time": "8:03:26"}
+{"current_steps": 237, "total_steps": 360, "loss": 0.9068, "lr": 2.523175410749263e-05, "epoch": 3.2831168831168833, "percentage": 65.83, "elapsed_time": "15:24:00", "remaining_time": "7:59:32"}
+{"current_steps": 238, "total_steps": 360, "loss": 0.8916, "lr": 2.4872005673134307e-05, "epoch": 3.296969696969697, "percentage": 66.11, "elapsed_time": "15:27:53", "remaining_time": "7:55:38"}
+{"current_steps": 239, "total_steps": 360, "loss": 0.9115, "lr": 2.4513679527199986e-05, "epoch": 3.310822510822511, "percentage": 66.39, "elapsed_time": "15:31:55", "remaining_time": "7:51:48"}
+{"current_steps": 240, "total_steps": 360, "loss": 0.8891, "lr": 2.4156809358433728e-05, "epoch": 3.324675324675325, "percentage": 66.67, "elapsed_time": "15:35:56", "remaining_time": "7:47:58"}
+{"current_steps": 241, "total_steps": 360, "loss": 0.8936, "lr": 2.3801428718693055e-05, "epoch": 3.3385281385281385, "percentage": 66.94, "elapsed_time": "15:39:49", "remaining_time": "7:44:03"}
+{"current_steps": 242, "total_steps": 360, "loss": 0.9079, "lr": 2.3447571019794438e-05, "epoch": 3.3523809523809525, "percentage": 67.22, "elapsed_time": "15:43:42", "remaining_time": "7:40:09"}
+{"current_steps": 243, "total_steps": 360, "loss": 0.8904, "lr": 2.3095269530372032e-05, "epoch": 3.3662337662337665, "percentage": 67.5, "elapsed_time": "15:47:36", "remaining_time": "7:36:15"}
+{"current_steps": 244, "total_steps": 360, "loss": 0.8965, "lr": 2.274455737274987e-05, "epoch": 3.38008658008658, "percentage": 67.78, "elapsed_time": "15:51:29", "remaining_time": "7:32:20"}
+{"current_steps": 245, "total_steps": 360, "loss": 0.9039, "lr": 2.239546751982782e-05, "epoch": 3.393939393939394, "percentage": 68.06, "elapsed_time": "15:55:22", "remaining_time": "7:28:26"}
+{"current_steps": 246, "total_steps": 360, "loss": 0.8921, "lr": 2.2048032791981515e-05, "epoch": 3.407792207792208, "percentage": 68.33, "elapsed_time": "15:59:16", "remaining_time": "7:24:32"}
+{"current_steps": 247, "total_steps": 360, "loss": 0.8972, "lr": 2.1702285853976774e-05, "epoch": 3.4216450216450216, "percentage": 68.61, "elapsed_time": "16:03:09", "remaining_time": "7:20:38"}
+{"current_steps": 248, "total_steps": 360, "loss": 0.8967, "lr": 2.135825921189846e-05, "epoch": 3.4354978354978356, "percentage": 68.89, "elapsed_time": "16:07:03", "remaining_time": "7:16:43"}
+{"current_steps": 249, "total_steps": 360, "loss": 0.9089, "lr": 2.1015985210094385e-05, "epoch": 3.449350649350649, "percentage": 69.17, "elapsed_time": "16:10:56", "remaining_time": "7:12:49"}
+{"current_steps": 250, "total_steps": 360, "loss": 0.9116, "lr": 2.067549602813446e-05, "epoch": 3.463203463203463, "percentage": 69.44, "elapsed_time": "16:14:49", "remaining_time": "7:08:55"}
+{"current_steps": 251, "total_steps": 360, "loss": 0.9035, "lr": 2.033682367778518e-05, "epoch": 3.477056277056277, "percentage": 69.72, "elapsed_time": "16:18:42", "remaining_time": "7:05:01"}
+{"current_steps": 252, "total_steps": 360, "loss": 0.9049, "lr": 2.0000000000000012e-05, "epoch": 3.4909090909090907, "percentage": 70.0, "elapsed_time": "16:22:36", "remaining_time": "7:01:07"}
+{"current_steps": 253, "total_steps": 360, "loss": 0.9013, "lr": 1.966505666192579e-05, "epoch": 3.5047619047619047, "percentage": 70.28, "elapsed_time": "16:26:29", "remaining_time": "6:57:12"}
+{"current_steps": 254, "total_steps": 360, "loss": 0.887, "lr": 1.9332025153925486e-05, "epoch": 3.5186147186147188, "percentage": 70.56, "elapsed_time": "16:30:22", "remaining_time": "6:53:18"}
+{"current_steps": 255, "total_steps": 360, "loss": 0.9025, "lr": 1.90009367866176e-05, "epoch": 3.5324675324675323, "percentage": 70.83, "elapsed_time": "16:34:16", "remaining_time": "6:49:24"}
+{"current_steps": 256, "total_steps": 360, "loss": 0.902, "lr": 1.867182268793236e-05, "epoch": 3.5463203463203463, "percentage": 71.11, "elapsed_time": "16:38:09", "remaining_time": "6:45:30"}
+{"current_steps": 257, "total_steps": 360, "loss": 0.8935, "lr": 1.8344713800185215e-05, "epoch": 3.5601731601731603, "percentage": 71.39, "elapsed_time": "16:42:03", "remaining_time": "6:41:36"}
+{"current_steps": 258, "total_steps": 360, "loss": 0.898, "lr": 1.8019640877167763e-05, "epoch": 3.574025974025974, "percentage": 71.67, "elapsed_time": "16:45:56", "remaining_time": "6:37:41"}
+{"current_steps": 259, "total_steps": 360, "loss": 0.8959, "lr": 1.7696634481256293e-05, "epoch": 3.587878787878788, "percentage": 71.94, "elapsed_time": "16:49:49", "remaining_time": "6:33:47"}
+{"current_steps": 260, "total_steps": 360, "loss": 0.8888, "lr": 1.7375724980538465e-05, "epoch": 3.601731601731602, "percentage": 72.22, "elapsed_time": "16:53:42", "remaining_time": "6:29:53"}
+{"current_steps": 261, "total_steps": 360, "loss": 0.9089, "lr": 1.7056942545958167e-05, "epoch": 3.6155844155844155, "percentage": 72.5, "elapsed_time": "16:57:36", "remaining_time": "6:25:59"}
+{"current_steps": 262, "total_steps": 360, "loss": 0.9055, "lr": 1.6740317148478932e-05, "epoch": 3.6294372294372295, "percentage": 72.78, "elapsed_time": "17:01:29", "remaining_time": "6:22:05"}
+{"current_steps": 263, "total_steps": 360, "loss": 0.9154, "lr": 1.642587855626621e-05, "epoch": 3.643290043290043, "percentage": 73.06, "elapsed_time": "17:05:23", "remaining_time": "6:18:11"}
+{"current_steps": 264, "total_steps": 360, "loss": 0.8954, "lr": 1.6113656331888563e-05, "epoch": 3.657142857142857, "percentage": 73.33, "elapsed_time": "17:09:16", "remaining_time": "6:14:16"}
+{"current_steps": 265, "total_steps": 360, "loss": 0.8939, "lr": 1.580367982953833e-05, "epoch": 3.670995670995671, "percentage": 73.61, "elapsed_time": "17:13:09", "remaining_time": "6:10:22"}
+{"current_steps": 266, "total_steps": 360, "loss": 0.91, "lr": 1.5495978192271887e-05, "epoch": 3.6848484848484846, "percentage": 73.89, "elapsed_time": "17:17:03", "remaining_time": "6:06:28"}
+{"current_steps": 267, "total_steps": 360, "loss": 0.9027, "lr": 1.5190580349269604e-05, "epoch": 3.6987012987012986, "percentage": 74.17, "elapsed_time": "17:20:56", "remaining_time": "6:02:34"}
+{"current_steps": 268, "total_steps": 360, "loss": 0.9106, "lr": 1.4887515013116067e-05, "epoch": 3.7125541125541126, "percentage": 74.44, "elapsed_time": "17:24:49", "remaining_time": "5:58:40"}
+{"current_steps": 269, "total_steps": 360, "loss": 0.8937, "lr": 1.4586810677100608e-05, "epoch": 3.726406926406926, "percentage": 74.72, "elapsed_time": "17:28:42", "remaining_time": "5:54:46"}
+{"current_steps": 270, "total_steps": 360, "loss": 0.9034, "lr": 1.4288495612538427e-05, "epoch": 3.74025974025974, "percentage": 75.0, "elapsed_time": "17:32:35", "remaining_time": "5:50:51"}
+{"current_steps": 271, "total_steps": 360, "loss": 0.8975, "lr": 1.3992597866112667e-05, "epoch": 3.754112554112554, "percentage": 75.28, "elapsed_time": "17:36:28", "remaining_time": "5:46:57"}
+{"current_steps": 272, "total_steps": 360, "loss": 0.8882, "lr": 1.369914525723746e-05, "epoch": 3.7679653679653677, "percentage": 75.56, "elapsed_time": "17:40:22", "remaining_time": "5:43:03"}
+{"current_steps": 273, "total_steps": 360, "loss": 0.8906, "lr": 1.3408165375442486e-05, "epoch": 3.7818181818181817, "percentage": 75.83, "elapsed_time": "17:44:15", "remaining_time": "5:39:09"}
+{"current_steps": 274, "total_steps": 360, "loss": 0.9008, "lr": 1.3119685577779105e-05, "epoch": 3.7956709956709958, "percentage": 76.11, "elapsed_time": "17:48:08", "remaining_time": "5:35:15"}
+{"current_steps": 275, "total_steps": 360, "loss": 0.8853, "lr": 1.2833732986248277e-05, "epoch": 3.8095238095238093, "percentage": 76.39, "elapsed_time": "17:52:01", "remaining_time": "5:31:21"}
+{"current_steps": 276, "total_steps": 360, "loss": 0.9051, "lr": 1.2550334485250661e-05, "epoch": 3.8233766233766233, "percentage": 76.67, "elapsed_time": "17:55:54", "remaining_time": "5:27:27"}
+{"current_steps": 277, "total_steps": 360, "loss": 0.8979, "lr": 1.2269516719059041e-05, "epoch": 3.8372294372294373, "percentage": 76.94, "elapsed_time": "17:59:48", "remaining_time": "5:23:33"}
+{"current_steps": 278, "total_steps": 360, "loss": 0.901, "lr": 1.1991306089313261e-05, "epoch": 3.851082251082251, "percentage": 77.22, "elapsed_time": "18:03:41", "remaining_time": "5:19:39"}
+{"current_steps": 279, "total_steps": 360, "loss": 0.8851, "lr": 1.1715728752538103e-05, "epoch": 3.864935064935065, "percentage": 77.5, "elapsed_time": "18:07:35", "remaining_time": "5:15:45"}
+{"current_steps": 280, "total_steps": 360, "loss": 0.8906, "lr": 1.1442810617684046e-05, "epoch": 3.878787878787879, "percentage": 77.78, "elapsed_time": "18:11:28", "remaining_time": "5:11:50"}
+{"current_steps": 281, "total_steps": 360, "loss": 0.8945, "lr": 1.1172577343691415e-05, "epoch": 3.8926406926406925, "percentage": 78.06, "elapsed_time": "18:15:21", "remaining_time": "5:07:56"}
+{"current_steps": 282, "total_steps": 360, "loss": 0.8939, "lr": 1.0905054337078051e-05, "epoch": 3.9064935064935065, "percentage": 78.33, "elapsed_time": "18:19:14", "remaining_time": "5:04:02"}
+{"current_steps": 283, "total_steps": 360, "loss": 0.8987, "lr": 1.0640266749550593e-05, "epoch": 3.9203463203463205, "percentage": 78.61, "elapsed_time": "18:23:07", "remaining_time": "5:00:08"}
+{"current_steps": 284, "total_steps": 360, "loss": 0.8954, "lr": 1.0378239475639823e-05, "epoch": 3.934199134199134, "percentage": 78.89, "elapsed_time": "18:27:01", "remaining_time": "4:56:14"}
+{"current_steps": 285, "total_steps": 360, "loss": 0.8967, "lr": 1.0118997150360169e-05, "epoch": 3.948051948051948, "percentage": 79.17, "elapsed_time": "18:30:54", "remaining_time": "4:52:20"}
+{"current_steps": 286, "total_steps": 360, "loss": 0.8942, "lr": 9.862564146893571e-06, "epoch": 3.961904761904762, "percentage": 79.44, "elapsed_time": "18:34:47", "remaining_time": "4:48:26"}
+{"current_steps": 287, "total_steps": 360, "loss": 0.8981, "lr": 9.60896457429803e-06, "epoch": 3.9757575757575756, "percentage": 79.72, "elapsed_time": "18:38:41", "remaining_time": "4:44:32"}
+{"current_steps": 288, "total_steps": 360, "loss": 0.8969, "lr": 9.358222275240884e-06, "epoch": 3.9896103896103896, "percentage": 80.0, "elapsed_time": "18:42:35", "remaining_time": "4:40:38"}
+{"current_steps": 289, "total_steps": 360, "loss": 1.6175, "lr": 9.110360823757235e-06, "epoch": 4.003463203463204, "percentage": 80.28, "elapsed_time": "18:46:55", "remaining_time": "4:36:51"}
+{"current_steps": 290, "total_steps": 360, "loss": 0.8757, "lr": 8.8654035230336e-06, "epoch": 4.017316017316017, "percentage": 80.56, "elapsed_time": "18:50:48", "remaining_time": "4:32:57"}
+{"current_steps": 291, "total_steps": 360, "loss": 0.8619, "lr": 8.623373403216972e-06, "epoch": 4.031168831168831, "percentage": 80.83, "elapsed_time": "18:54:41", "remaining_time": "4:29:02"}
+{"current_steps": 292, "total_steps": 360, "loss": 0.875, "lr": 8.384293219249633e-06, "epoch": 4.045021645021645, "percentage": 81.11, "elapsed_time": "18:58:34", "remaining_time": "4:25:08"}
+{"current_steps": 293, "total_steps": 360, "loss": 0.8712, "lr": 8.148185448729778e-06, "epoch": 4.058874458874459, "percentage": 81.39, "elapsed_time": "19:02:27", "remaining_time": "4:21:14"}
+{"current_steps": 294, "total_steps": 360, "loss": 0.8859, "lr": 7.915072289798247e-06, "epoch": 4.072727272727272, "percentage": 81.67, "elapsed_time": "19:06:21", "remaining_time": "4:17:20"}
+{"current_steps": 295, "total_steps": 360, "loss": 0.8662, "lr": 7.684975659051557e-06, "epoch": 4.086580086580087, "percentage": 81.94, "elapsed_time": "19:10:13", "remaining_time": "4:13:26"}
+{"current_steps": 296, "total_steps": 360, "loss": 0.8774, "lr": 7.457917189481301e-06, "epoch": 4.1004329004329, "percentage": 82.22, "elapsed_time": "19:14:07", "remaining_time": "4:09:32"}
+{"current_steps": 297, "total_steps": 360, "loss": 0.8774, "lr": 7.233918228440324e-06, "epoch": 4.114285714285714, "percentage": 82.5, "elapsed_time": "19:18:00", "remaining_time": "4:05:38"}
+{"current_steps": 298, "total_steps": 360, "loss": 0.863, "lr": 7.0129998356357295e-06, "epoch": 4.128138528138528, "percentage": 82.78, "elapsed_time": "19:21:53", "remaining_time": "4:01:44"}
+{"current_steps": 299, "total_steps": 360, "loss": 0.8767, "lr": 6.795182781148848e-06, "epoch": 4.141991341991342, "percentage": 83.06, "elapsed_time": "19:25:46", "remaining_time": "3:57:49"}
+{"current_steps": 300, "total_steps": 360, "loss": 0.8709, "lr": 6.58048754348255e-06, "epoch": 4.1558441558441555, "percentage": 83.33, "elapsed_time": "19:29:39", "remaining_time": "3:53:55"}
+{"current_steps": 301, "total_steps": 360, "loss": 0.8716, "lr": 6.368934307635881e-06, "epoch": 4.16969696969697, "percentage": 83.61, "elapsed_time": "19:33:33", "remaining_time": "3:50:01"}
+{"current_steps": 302, "total_steps": 360, "loss": 0.8697, "lr": 6.160542963206357e-06, "epoch": 4.1835497835497835, "percentage": 83.89, "elapsed_time": "19:37:50", "remaining_time": "3:46:12"}
+{"current_steps": 303, "total_steps": 360, "loss": 0.8628, "lr": 5.955333102520011e-06, "epoch": 4.197402597402597, "percentage": 84.17, "elapsed_time": "19:41:43", "remaining_time": "3:42:18"}
+{"current_steps": 304, "total_steps": 360, "loss": 0.8708, "lr": 5.753324018789346e-06, "epoch": 4.2112554112554115, "percentage": 84.44, "elapsed_time": "19:45:37", "remaining_time": "3:38:24"}
+{"current_steps": 305, "total_steps": 360, "loss": 0.8566, "lr": 5.554534704299448e-06, "epoch": 4.225108225108225, "percentage": 84.72, "elapsed_time": "19:49:30", "remaining_time": "3:34:30"}
+{"current_steps": 306, "total_steps": 360, "loss": 0.8764, "lr": 5.358983848622452e-06, "epoch": 4.238961038961039, "percentage": 85.0, "elapsed_time": "19:53:24", "remaining_time": "3:30:36"}
+{"current_steps": 307, "total_steps": 360, "loss": 0.8749, "lr": 5.1666898368603195e-06, "epoch": 4.252813852813853, "percentage": 85.28, "elapsed_time": "19:57:17", "remaining_time": "3:26:41"}
+{"current_steps": 308, "total_steps": 360, "loss": 0.8657, "lr": 4.97767074791637e-06, "epoch": 4.266666666666667, "percentage": 85.56, "elapsed_time": "20:01:10", "remaining_time": "3:22:47"}
+{"current_steps": 309, "total_steps": 360, "loss": 0.8919, "lr": 4.791944352795561e-06, "epoch": 4.28051948051948, "percentage": 85.83, "elapsed_time": "20:05:03", "remaining_time": "3:18:53"}
+{"current_steps": 310, "total_steps": 360, "loss": 0.8575, "lr": 4.609528112933688e-06, "epoch": 4.294372294372295, "percentage": 86.11, "elapsed_time": "20:08:57", "remaining_time": "3:14:59"}
+{"current_steps": 311, "total_steps": 360, "loss": 0.874, "lr": 4.430439178555759e-06, "epoch": 4.308225108225108, "percentage": 86.39, "elapsed_time": "20:12:50", "remaining_time": "3:11:05"}
+{"current_steps": 312, "total_steps": 360, "loss": 0.866, "lr": 4.254694387063514e-06, "epoch": 4.322077922077922, "percentage": 86.67, "elapsed_time": "20:16:43", "remaining_time": "3:07:11"}
+{"current_steps": 313, "total_steps": 360, "loss": 0.8809, "lr": 4.082310261452471e-06, "epoch": 4.335930735930736, "percentage": 86.94, "elapsed_time": "20:20:37", "remaining_time": "3:03:17"}
+{"current_steps": 314, "total_steps": 360, "loss": 0.8739, "lr": 3.913303008758491e-06, "epoch": 4.34978354978355, "percentage": 87.22, "elapsed_time": "20:24:30", "remaining_time": "2:59:23"}
+{"current_steps": 315, "total_steps": 360, "loss": 0.8764, "lr": 3.747688518534003e-06, "epoch": 4.363636363636363, "percentage": 87.5, "elapsed_time": "20:28:24", "remaining_time": "2:55:29"}
+{"current_steps": 316, "total_steps": 360, "loss": 0.874, "lr": 3.585482361354138e-06, "epoch": 4.377489177489178, "percentage": 87.78, "elapsed_time": "20:32:17", "remaining_time": "2:51:35"}
+{"current_steps": 317, "total_steps": 360, "loss": 0.8712, "lr": 3.42669978735283e-06, "epoch": 4.391341991341991, "percentage": 88.06, "elapsed_time": "20:36:10", "remaining_time": "2:47:40"}
+{"current_steps": 318, "total_steps": 360, "loss": 0.865, "lr": 3.2713557247890447e-06, "epoch": 4.405194805194805, "percentage": 88.33, "elapsed_time": "20:40:02", "remaining_time": "2:43:46"}
+{"current_steps": 319, "total_steps": 360, "loss": 0.8628, "lr": 3.1194647786432663e-06, "epoch": 4.419047619047619, "percentage": 88.61, "elapsed_time": "20:43:55", "remaining_time": "2:39:52"}
+{"current_steps": 320, "total_steps": 360, "loss": 0.8744, "lr": 2.9710412292443868e-06, "epoch": 4.432900432900433, "percentage": 88.89, "elapsed_time": "20:47:48", "remaining_time": "2:35:58"}
+{"current_steps": 321, "total_steps": 360, "loss": 0.8707, "lr": 2.8260990309270987e-06, "epoch": 4.4467532467532465, "percentage": 89.17, "elapsed_time": "20:51:41", "remaining_time": "2:32:04"}
+{"current_steps": 322, "total_steps": 360, "loss": 0.869, "lr": 2.6846518107199782e-06, "epoch": 4.460606060606061, "percentage": 89.44, "elapsed_time": "20:55:34", "remaining_time": "2:28:10"}
+{"current_steps": 323, "total_steps": 360, "loss": 0.866, "lr": 2.546712867064276e-06, "epoch": 4.4744588744588745, "percentage": 89.72, "elapsed_time": "20:59:28", "remaining_time": "2:24:16"}
+{"current_steps": 324, "total_steps": 360, "loss": 0.869, "lr": 2.4122951685636674e-06, "epoch": 4.488311688311688, "percentage": 90.0, "elapsed_time": "21:03:21", "remaining_time": "2:20:22"}
+{"current_steps": 325, "total_steps": 360, "loss": 0.8661, "lr": 2.281411352764966e-06, "epoch": 4.5021645021645025, "percentage": 90.28, "elapsed_time": "21:07:14", "remaining_time": "2:16:28"}
+{"current_steps": 326, "total_steps": 360, "loss": 0.8665, "lr": 2.1540737249699893e-06, "epoch": 4.516017316017316, "percentage": 90.56, "elapsed_time": "21:11:07", "remaining_time": "2:12:34"}
+{"current_steps": 327, "total_steps": 360, "loss": 0.8587, "lr": 2.0302942570786446e-06, "epoch": 4.52987012987013, "percentage": 90.83, "elapsed_time": "21:15:00", "remaining_time": "2:08:40"}
+{"current_steps": 328, "total_steps": 360, "loss": 0.862, "lr": 1.9100845864633875e-06, "epoch": 4.543722943722944, "percentage": 91.11, "elapsed_time": "21:18:53", "remaining_time": "2:04:46"}
+{"current_steps": 329, "total_steps": 360, "loss": 0.8667, "lr": 1.793456014875079e-06, "epoch": 4.557575757575758, "percentage": 91.39, "elapsed_time": "21:22:46", "remaining_time": "2:00:52"}
+{"current_steps": 330, "total_steps": 360, "loss": 0.8609, "lr": 1.6804195073804442e-06, "epoch": 4.571428571428571, "percentage": 91.67, "elapsed_time": "21:26:39", "remaining_time": "1:56:58"}
+{"current_steps": 331, "total_steps": 360, "loss": 0.8631, "lr": 1.5709856913311795e-06, "epoch": 4.585281385281386, "percentage": 91.94, "elapsed_time": "21:30:32", "remaining_time": "1:53:04"}
+{"current_steps": 332, "total_steps": 360, "loss": 0.874, "lr": 1.4651648553647869e-06, "epoch": 4.599134199134199, "percentage": 92.22, "elapsed_time": "21:34:25", "remaining_time": "1:49:10"}
+{"current_steps": 333, "total_steps": 360, "loss": 0.8608, "lr": 1.3629669484372722e-06, "epoch": 4.612987012987013, "percentage": 92.5, "elapsed_time": "21:38:18", "remaining_time": "1:45:16"}
+{"current_steps": 334, "total_steps": 360, "loss": 0.8776, "lr": 1.2644015788877684e-06, "epoch": 4.626839826839827, "percentage": 92.78, "elapsed_time": "21:42:11", "remaining_time": "1:41:22"}
+{"current_steps": 335, "total_steps": 360, "loss": 0.8659, "lr": 1.1694780135352013e-06, "epoch": 4.640692640692641, "percentage": 93.06, "elapsed_time": "21:46:04", "remaining_time": "1:37:28"}
+{"current_steps": 336, "total_steps": 360, "loss": 0.8822, "lr": 1.0782051768070477e-06, "epoch": 4.654545454545454, "percentage": 93.33, "elapsed_time": "21:49:57", "remaining_time": "1:33:34"}
+{"current_steps": 337, "total_steps": 360, "loss": 0.8632, "lr": 9.905916499002787e-07, "epoch": 4.668398268398269, "percentage": 93.61, "elapsed_time": "21:53:50", "remaining_time": "1:29:40"}
+{"current_steps": 338, "total_steps": 360, "loss": 0.8686, "lr": 9.066456699745774e-07, "epoch": 4.682251082251082, "percentage": 93.89, "elapsed_time": "21:57:43", "remaining_time": "1:25:46"}
+{"current_steps": 339, "total_steps": 360, "loss": 0.8709, "lr": 8.263751293779409e-07, "epoch": 4.696103896103896, "percentage": 94.17, "elapsed_time": "22:01:36", "remaining_time": "1:21:52"}
+{"current_steps": 340, "total_steps": 360, "loss": 0.8706, "lr": 7.497875749046124e-07, "epoch": 4.70995670995671, "percentage": 94.44, "elapsed_time": "22:05:29", "remaining_time": "1:17:58"}
+{"current_steps": 341, "total_steps": 360, "loss": 0.8661, "lr": 6.768902070856031e-07, "epoch": 4.723809523809524, "percentage": 94.72, "elapsed_time": "22:09:22", "remaining_time": "1:14:04"}
+{"current_steps": 342, "total_steps": 360, "loss": 0.8662, "lr": 6.076898795116792e-07, "epoch": 4.7376623376623375, "percentage": 95.0, "elapsed_time": "22:13:15", "remaining_time": "1:10:10"}
+{"current_steps": 343, "total_steps": 360, "loss": 0.877, "lr": 5.421930981890455e-07, "epoch": 4.751515151515152, "percentage": 95.28, "elapsed_time": "22:17:09", "remaining_time": "1:06:16"}
+{"current_steps": 344, "total_steps": 360, "loss": 0.8658, "lr": 4.804060209276396e-07, "epoch": 4.7653679653679655, "percentage": 95.56, "elapsed_time": "22:21:04", "remaining_time": "1:02:22"}
+{"current_steps": 345, "total_steps": 360, "loss": 0.8718, "lr": 4.223344567622212e-07, "epoch": 4.779220779220779, "percentage": 95.83, "elapsed_time": "22:24:57", "remaining_time": "0:58:28"}
+{"current_steps": 346, "total_steps": 360, "loss": 0.8672, "lr": 3.679838654061874e-07, "epoch": 4.7930735930735935, "percentage": 96.11, "elapsed_time": "22:28:51", "remaining_time": "0:54:34"}
+{"current_steps": 347, "total_steps": 360, "loss": 0.8762, "lr": 3.173593567383071e-07, "epoch": 4.806926406926407, "percentage": 96.39, "elapsed_time": "22:32:45", "remaining_time": "0:50:40"}
+{"current_steps": 348, "total_steps": 360, "loss": 0.8792, "lr": 2.704656903222791e-07, "epoch": 4.820779220779221, "percentage": 96.67, "elapsed_time": "22:36:39", "remaining_time": "0:46:46"}
+{"current_steps": 349, "total_steps": 360, "loss": 0.864, "lr": 2.273072749592631e-07, "epoch": 4.834632034632035, "percentage": 96.94, "elapsed_time": "22:40:33", "remaining_time": "0:42:52"}
+{"current_steps": 350, "total_steps": 360, "loss": 0.8827, "lr": 1.8788816827336686e-07, "epoch": 4.848484848484849, "percentage": 97.22, "elapsed_time": "22:44:27", "remaining_time": "0:38:59"}
+{"current_steps": 351, "total_steps": 360, "loss": 0.8634, "lr": 1.522120763301782e-07, "epoch": 4.862337662337662, "percentage": 97.5, "elapsed_time": "22:48:21", "remaining_time": "0:35:05"}
+{"current_steps": 352, "total_steps": 360, "loss": 0.8782, "lr": 1.2028235328831906e-07, "epoch": 4.876190476190477, "percentage": 97.78, "elapsed_time": "22:52:16", "remaining_time": "0:31:11"}
+{"current_steps": 353, "total_steps": 360, "loss": 0.8721, "lr": 9.21020010840934e-08, "epoch": 4.89004329004329, "percentage": 98.06, "elapsed_time": "22:56:09", "remaining_time": "0:27:17"}
+{"current_steps": 354, "total_steps": 360, "loss": 0.8784, "lr": 6.767366914927298e-08, "epoch": 4.903896103896104, "percentage": 98.33, "elapsed_time": "23:00:02", "remaining_time": "0:23:23"}
+{"current_steps": 355, "total_steps": 360, "loss": 0.8794, "lr": 4.699965416198549e-08, "epoch": 4.917748917748918, "percentage": 98.61, "elapsed_time": "23:03:55", "remaining_time": "0:19:29"}
+{"current_steps": 356, "total_steps": 360, "loss": 0.8658, "lr": 3.0081899830798345e-08, "epoch": 4.931601731601732, "percentage": 98.89, "elapsed_time": "23:07:48", "remaining_time": "0:15:35"}
+{"current_steps": 357, "total_steps": 360, "loss": 0.8666, "lr": 1.6921996711976028e-08, "epoch": 4.945454545454545, "percentage": 99.17, "elapsed_time": "23:11:42", "remaining_time": "0:11:41"}
+{"current_steps": 358, "total_steps": 360, "loss": 0.866, "lr": 7.521182059946342e-09, "epoch": 4.95930735930736, "percentage": 99.44, "elapsed_time": "23:15:35", "remaining_time": "0:07:47"}
+{"current_steps": 359, "total_steps": 360, "loss": 0.8639, "lr": 1.8803397109534715e-09, "epoch": 4.973160173160173, "percentage": 99.72, "elapsed_time": "23:19:29", "remaining_time": "0:03:53"}
+{"current_steps": 360, "total_steps": 360, "loss": 0.8814, "lr": 0.0, "epoch": 4.987012987012987, "percentage": 100.0, "elapsed_time": "23:23:22", "remaining_time": "0:00:00"}
+{"current_steps": 360, "total_steps": 360, "epoch": 4.987012987012987, "percentage": 100.0, "elapsed_time": "23:23:52", "remaining_time": "0:00:00"}
+{"current_steps": 360, "total_steps": 360, "epoch": 4.987012987012987, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2562 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.987012987012987,
+  "eval_steps": 500,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013852813852813853,
+      "grad_norm": 10.690503047217376,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.664,
+      "step": 1
+    },
+    {
+      "epoch": 0.027705627705627706,
+      "grad_norm": 10.549038500876918,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.6687,
+      "step": 2
+    },
+    {
+      "epoch": 0.04155844155844156,
+      "grad_norm": 9.952372502868275,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.6436,
+      "step": 3
+    },
+    {
+      "epoch": 0.05541125541125541,
+      "grad_norm": 7.525381680312214,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.5751,
+      "step": 4
+    },
+    {
+      "epoch": 0.06926406926406926,
+      "grad_norm": 3.6488707097222806,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.4732,
+      "step": 5
+    },
+    {
+      "epoch": 0.08311688311688312,
+      "grad_norm": 5.9440833747387405,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.4929,
+      "step": 6
+    },
+    {
+      "epoch": 0.09696969696969697,
+      "grad_norm": 7.008224469434576,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 1.4342,
+      "step": 7
+    },
+    {
+      "epoch": 0.11082251082251082,
+      "grad_norm": 9.129791969259458,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 1.4508,
+      "step": 8
+    },
+    {
+      "epoch": 0.12467532467532468,
+      "grad_norm": 7.157661170613076,
+      "learning_rate": 2e-05,
+      "loss": 1.3993,
+      "step": 9
+    },
+    {
+      "epoch": 0.13852813852813853,
+      "grad_norm": 5.878397281654449,
+      "learning_rate": 2.2222222222222227e-05,
+      "loss": 1.3716,
+      "step": 10
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 4.04814199716087,
+      "learning_rate": 2.444444444444445e-05,
+      "loss": 1.3279,
+      "step": 11
+    },
+    {
+      "epoch": 0.16623376623376623,
+      "grad_norm": 4.367325147342624,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.2918,
+      "step": 12
+    },
+    {
+      "epoch": 0.1800865800865801,
+      "grad_norm": 3.013051181093589,
+      "learning_rate": 2.888888888888889e-05,
+      "loss": 1.2683,
+      "step": 13
+    },
+    {
+      "epoch": 0.19393939393939394,
+      "grad_norm": 2.7017616202077597,
+      "learning_rate": 3.111111111111112e-05,
+      "loss": 1.2741,
+      "step": 14
+    },
+    {
+      "epoch": 0.2077922077922078,
+      "grad_norm": 2.4447347796035936,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.2498,
+      "step": 15
+    },
+    {
+      "epoch": 0.22164502164502164,
+      "grad_norm": 2.3013073090511016,
+      "learning_rate": 3.555555555555555e-05,
+      "loss": 1.2356,
+      "step": 16
+    },
+    {
+      "epoch": 0.2354978354978355,
+      "grad_norm": 2.676331737240606,
+      "learning_rate": 3.777777777777778e-05,
+      "loss": 1.2226,
+      "step": 17
+    },
+    {
+      "epoch": 0.24935064935064935,
+      "grad_norm": 1.8653678395700215,
+      "learning_rate": 4e-05,
+      "loss": 1.1883,
+      "step": 18
+    },
+    {
+      "epoch": 0.2632034632034632,
+      "grad_norm": 2.489502341694411,
+      "learning_rate": 4.222222222222223e-05,
+      "loss": 1.1903,
+      "step": 19
+    },
+    {
+      "epoch": 0.27705627705627706,
+      "grad_norm": 2.2381168497877746,
+      "learning_rate": 4.444444444444445e-05,
+      "loss": 1.1823,
+      "step": 20
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 1.0658561341621282,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.1644,
+      "step": 21
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 3.3353632520282024,
+      "learning_rate": 4.88888888888889e-05,
+      "loss": 1.1866,
+      "step": 22
+    },
+    {
+      "epoch": 0.31861471861471863,
+      "grad_norm": 2.0828413940584256,
+      "learning_rate": 5.111111111111111e-05,
+      "loss": 1.1606,
+      "step": 23
+    },
+    {
+      "epoch": 0.33246753246753247,
+      "grad_norm": 2.0722285174850334,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.1689,
+      "step": 24
+    },
+    {
+      "epoch": 0.3463203463203463,
+      "grad_norm": 2.6579102865439035,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 1.1555,
+      "step": 25
+    },
+    {
+      "epoch": 0.3601731601731602,
+      "grad_norm": 1.9616156182284334,
+      "learning_rate": 5.777777777777778e-05,
+      "loss": 1.1683,
+      "step": 26
+    },
+    {
+      "epoch": 0.37402597402597404,
+      "grad_norm": 3.2895161663522225,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 1.162,
+      "step": 27
+    },
+    {
+      "epoch": 0.3878787878787879,
+      "grad_norm": 2.2524763564895447,
+      "learning_rate": 6.222222222222223e-05,
+      "loss": 1.1588,
+      "step": 28
+    },
+    {
+      "epoch": 0.4017316017316017,
+      "grad_norm": 2.9587565231476036,
+      "learning_rate": 6.444444444444446e-05,
+      "loss": 1.1477,
+      "step": 29
+    },
+    {
+      "epoch": 0.4155844155844156,
+      "grad_norm": 2.0001168739095387,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.1463,
+      "step": 30
+    },
+    {
+      "epoch": 0.42943722943722945,
+      "grad_norm": 3.0781839410346756,
+      "learning_rate": 6.88888888888889e-05,
+      "loss": 1.1273,
+      "step": 31
+    },
+    {
+      "epoch": 0.4432900432900433,
+      "grad_norm": 2.155490334097704,
+      "learning_rate": 7.11111111111111e-05,
+      "loss": 1.1468,
+      "step": 32
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 2.3875247457053566,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 1.1379,
+      "step": 33
+    },
+    {
+      "epoch": 0.470995670995671,
+      "grad_norm": 1.71586428053475,
+      "learning_rate": 7.555555555555556e-05,
+      "loss": 1.1309,
+      "step": 34
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 2.6858291279872,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 1.1318,
+      "step": 35
+    },
+    {
+      "epoch": 0.4987012987012987,
+      "grad_norm": 1.997759995167864,
+      "learning_rate": 8e-05,
+      "loss": 1.1323,
+      "step": 36
+    },
+    {
+      "epoch": 0.5125541125541125,
+      "grad_norm": 2.629649063991005,
+      "learning_rate": 7.999811966028904e-05,
+      "loss": 1.1398,
+      "step": 37
+    },
+    {
+      "epoch": 0.5264069264069264,
+      "grad_norm": 2.6927398202491544,
+      "learning_rate": 7.999247881794007e-05,
+      "loss": 1.1272,
+      "step": 38
+    },
+    {
+      "epoch": 0.5402597402597402,
+      "grad_norm": 1.0260444389642347,
+      "learning_rate": 7.998307800328803e-05,
+      "loss": 1.1148,
+      "step": 39
+    },
+    {
+      "epoch": 0.5541125541125541,
+      "grad_norm": 3.1260836757156496,
+      "learning_rate": 7.996991810016922e-05,
+      "loss": 1.1581,
+      "step": 40
+    },
+    {
+      "epoch": 0.567965367965368,
+      "grad_norm": 2.408162449515958,
+      "learning_rate": 7.995300034583802e-05,
+      "loss": 1.1579,
+      "step": 41
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 1.7233621870783713,
+      "learning_rate": 7.993232633085074e-05,
+      "loss": 1.1154,
+      "step": 42
+    },
+    {
+      "epoch": 0.5956709956709957,
+      "grad_norm": 3.2143011392314524,
+      "learning_rate": 7.990789799891592e-05,
+      "loss": 1.1361,
+      "step": 43
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "grad_norm": 2.541057275107033,
+      "learning_rate": 7.987971764671168e-05,
+      "loss": 1.1437,
+      "step": 44
+    },
+    {
+      "epoch": 0.6233766233766234,
+      "grad_norm": 2.554077948353239,
+      "learning_rate": 7.984778792366983e-05,
+      "loss": 1.1278,
+      "step": 45
+    },
+    {
+      "epoch": 0.6372294372294373,
+      "grad_norm": 1.9556507030666455,
+      "learning_rate": 7.981211183172663e-05,
+      "loss": 1.125,
+      "step": 46
+    },
+    {
+      "epoch": 0.651082251082251,
+      "grad_norm": 2.4591106418916024,
+      "learning_rate": 7.977269272504075e-05,
+      "loss": 1.1113,
+      "step": 47
+    },
+    {
+      "epoch": 0.6649350649350649,
+      "grad_norm": 1.7374508763969678,
+      "learning_rate": 7.972953430967773e-05,
+      "loss": 1.1119,
+      "step": 48
+    },
+    {
+      "epoch": 0.6787878787878788,
+      "grad_norm": 2.271122042411741,
+      "learning_rate": 7.96826406432617e-05,
+      "loss": 1.1047,
+      "step": 49
+    },
+    {
+      "epoch": 0.6926406926406926,
+      "grad_norm": 1.385329225067948,
+      "learning_rate": 7.963201613459381e-05,
+      "loss": 1.1104,
+      "step": 50
+    },
+    {
+      "epoch": 0.7064935064935065,
+      "grad_norm": 2.0797667060906853,
+      "learning_rate": 7.957766554323778e-05,
+      "loss": 1.1008,
+      "step": 51
+    },
+    {
+      "epoch": 0.7203463203463204,
+      "grad_norm": 1.4769275764871517,
+      "learning_rate": 7.951959397907237e-05,
+      "loss": 1.1063,
+      "step": 52
+    },
+    {
+      "epoch": 0.7341991341991342,
+      "grad_norm": 1.5969040026842134,
+      "learning_rate": 7.945780690181096e-05,
+      "loss": 1.0958,
+      "step": 53
+    },
+    {
+      "epoch": 0.7480519480519481,
+      "grad_norm": 1.5076777523334957,
+      "learning_rate": 7.939231012048833e-05,
+      "loss": 1.1038,
+      "step": 54
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.5353741235556218,
+      "learning_rate": 7.932310979291441e-05,
+      "loss": 1.088,
+      "step": 55
+    },
+    {
+      "epoch": 0.7757575757575758,
+      "grad_norm": 1.6688683700597435,
+      "learning_rate": 7.925021242509539e-05,
+      "loss": 1.1005,
+      "step": 56
+    },
+    {
+      "epoch": 0.7896103896103897,
+      "grad_norm": 1.5907176050250653,
+      "learning_rate": 7.917362487062207e-05,
+      "loss": 1.0885,
+      "step": 57
+    },
+    {
+      "epoch": 0.8034632034632034,
+      "grad_norm": 1.5886283739500444,
+      "learning_rate": 7.909335433002543e-05,
+      "loss": 1.0889,
+      "step": 58
+    },
+    {
+      "epoch": 0.8173160173160173,
+      "grad_norm": 1.1345065452265992,
+      "learning_rate": 7.900940835009974e-05,
+      "loss": 1.0809,
+      "step": 59
+    },
+    {
+      "epoch": 0.8311688311688312,
+      "grad_norm": 1.6727620200346303,
+      "learning_rate": 7.892179482319297e-05,
+      "loss": 1.0844,
+      "step": 60
+    },
+    {
+      "epoch": 0.845021645021645,
+      "grad_norm": 1.726654683160669,
+      "learning_rate": 7.883052198646481e-05,
+      "loss": 1.0868,
+      "step": 61
+    },
+    {
+      "epoch": 0.8588744588744589,
+      "grad_norm": 0.7828989407478679,
+      "learning_rate": 7.873559842111225e-05,
+      "loss": 1.0711,
+      "step": 62
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 1.3882694170960725,
+      "learning_rate": 7.863703305156273e-05,
+      "loss": 1.0752,
+      "step": 63
+    },
+    {
+      "epoch": 0.8865800865800866,
+      "grad_norm": 1.5779873659792967,
+      "learning_rate": 7.853483514463521e-05,
+      "loss": 1.0766,
+      "step": 64
+    },
+    {
+      "epoch": 0.9004329004329005,
+      "grad_norm": 1.4180034460400448,
+      "learning_rate": 7.842901430866882e-05,
+      "loss": 1.0725,
+      "step": 65
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.9127219395084748,
+      "learning_rate": 7.831958049261956e-05,
+      "loss": 1.0612,
+      "step": 66
+    },
+    {
+      "epoch": 0.9281385281385282,
+      "grad_norm": 1.0847846746337275,
+      "learning_rate": 7.820654398512492e-05,
+      "loss": 1.074,
+      "step": 67
+    },
+    {
+      "epoch": 0.941991341991342,
+      "grad_norm": 1.8013647852774308,
+      "learning_rate": 7.808991541353662e-05,
+      "loss": 1.0954,
+      "step": 68
+    },
+    {
+      "epoch": 0.9558441558441558,
+      "grad_norm": 1.377128616335908,
+      "learning_rate": 7.796970574292136e-05,
+      "loss": 1.0752,
+      "step": 69
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 1.6958522149590192,
+      "learning_rate": 7.784592627503004e-05,
+      "loss": 1.0821,
+      "step": 70
+    },
+    {
+      "epoch": 0.9835497835497835,
+      "grad_norm": 1.0049024746726356,
+      "learning_rate": 7.771858864723504e-05,
+      "loss": 1.068,
+      "step": 71
+    },
+    {
+      "epoch": 0.9974025974025974,
+      "grad_norm": 2.6484071234844953,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 1.0771,
+      "step": 72
+    },
+    {
+      "epoch": 1.0112554112554113,
+      "grad_norm": 4.246067022400895,
+      "learning_rate": 7.745328713293573e-05,
+      "loss": 1.948,
+      "step": 73
+    },
+    {
+      "epoch": 1.025108225108225,
+      "grad_norm": 1.7220828208048158,
+      "learning_rate": 7.731534818928004e-05,
+      "loss": 1.0427,
+      "step": 74
+    },
+    {
+      "epoch": 1.0389610389610389,
+      "grad_norm": 1.8447923963725428,
+      "learning_rate": 7.71739009690729e-05,
+      "loss": 1.0479,
+      "step": 75
+    },
+    {
+      "epoch": 1.0528138528138529,
+      "grad_norm": 0.9341938628888585,
+      "learning_rate": 7.702895877075563e-05,
+      "loss": 1.0333,
+      "step": 76
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 2.424773237088678,
+      "learning_rate": 7.688053522135675e-05,
+      "loss": 1.0579,
+      "step": 77
+    },
+    {
+      "epoch": 1.0805194805194804,
+      "grad_norm": 1.6058600540175567,
+      "learning_rate": 7.672864427521097e-05,
+      "loss": 1.0636,
+      "step": 78
+    },
+    {
+      "epoch": 1.0943722943722944,
+      "grad_norm": 2.091045151793165,
+      "learning_rate": 7.657330021264718e-05,
+      "loss": 1.0442,
+      "step": 79
+    },
+    {
+      "epoch": 1.1082251082251082,
+      "grad_norm": 1.318962052033536,
+      "learning_rate": 7.641451763864587e-05,
+      "loss": 1.045,
+      "step": 80
+    },
+    {
+      "epoch": 1.122077922077922,
+      "grad_norm": 2.317561720529343,
+      "learning_rate": 7.625231148146601e-05,
+      "loss": 1.0484,
+      "step": 81
+    },
+    {
+      "epoch": 1.135930735930736,
+      "grad_norm": 1.4987484149413424,
+      "learning_rate": 7.608669699124153e-05,
+      "loss": 1.0484,
+      "step": 82
+    },
+    {
+      "epoch": 1.1497835497835498,
+      "grad_norm": 2.3968225100015816,
+      "learning_rate": 7.591768973854753e-05,
+      "loss": 1.0453,
+      "step": 83
+    },
+    {
+      "epoch": 1.1636363636363636,
+      "grad_norm": 2.0769969941809454,
+      "learning_rate": 7.57453056129365e-05,
+      "loss": 1.0473,
+      "step": 84
+    },
+    {
+      "epoch": 1.1774891774891776,
+      "grad_norm": 1.5328425512954666,
+      "learning_rate": 7.556956082144425e-05,
+      "loss": 1.0432,
+      "step": 85
+    },
+    {
+      "epoch": 1.1913419913419914,
+      "grad_norm": 1.5329379349699184,
+      "learning_rate": 7.539047188706631e-05,
+      "loss": 1.0502,
+      "step": 86
+    },
+    {
+      "epoch": 1.2051948051948052,
+      "grad_norm": 1.2635424997786673,
+      "learning_rate": 7.520805564720444e-05,
+      "loss": 1.0389,
+      "step": 87
+    },
+    {
+      "epoch": 1.2190476190476192,
+      "grad_norm": 0.9180899722416639,
+      "learning_rate": 7.502232925208365e-05,
+      "loss": 1.0297,
+      "step": 88
+    },
+    {
+      "epoch": 1.232900432900433,
+      "grad_norm": 0.9088421536152287,
+      "learning_rate": 7.483331016313969e-05,
+      "loss": 1.026,
+      "step": 89
+    },
+    {
+      "epoch": 1.2467532467532467,
+      "grad_norm": 0.9759584263195824,
+      "learning_rate": 7.464101615137756e-05,
+      "loss": 1.042,
+      "step": 90
+    },
+    {
+      "epoch": 1.2606060606060607,
+      "grad_norm": 1.7816477052359974,
+      "learning_rate": 7.444546529570055e-05,
+      "loss": 1.0375,
+      "step": 91
+    },
+    {
+      "epoch": 1.2744588744588745,
+      "grad_norm": 1.0505006199756568,
+      "learning_rate": 7.424667598121067e-05,
+      "loss": 1.0232,
+      "step": 92
+    },
+    {
+      "epoch": 1.2883116883116883,
+      "grad_norm": 1.1076363899720796,
+      "learning_rate": 7.404466689747999e-05,
+      "loss": 1.0358,
+      "step": 93
+    },
+    {
+      "epoch": 1.3021645021645023,
+      "grad_norm": 1.766746417129588,
+      "learning_rate": 7.383945703679365e-05,
+      "loss": 1.041,
+      "step": 94
+    },
+    {
+      "epoch": 1.316017316017316,
+      "grad_norm": 1.1727210609875833,
+      "learning_rate": 7.363106569236413e-05,
+      "loss": 1.0373,
+      "step": 95
+    },
+    {
+      "epoch": 1.3298701298701299,
+      "grad_norm": 1.3811377730593195,
+      "learning_rate": 7.341951245651747e-05,
+      "loss": 1.0232,
+      "step": 96
+    },
+    {
+      "epoch": 1.3437229437229437,
+      "grad_norm": 1.8848088994220173,
+      "learning_rate": 7.320481721885116e-05,
+      "loss": 1.0331,
+      "step": 97
+    },
+    {
+      "epoch": 1.3575757575757577,
+      "grad_norm": 1.5407669706222948,
+      "learning_rate": 7.298700016436427e-05,
+      "loss": 1.0392,
+      "step": 98
+    },
+    {
+      "epoch": 1.3714285714285714,
+      "grad_norm": 1.6439258533934764,
+      "learning_rate": 7.276608177155968e-05,
+      "loss": 1.0302,
+      "step": 99
+    },
+    {
+      "epoch": 1.3852813852813852,
+      "grad_norm": 1.6555083210158104,
+      "learning_rate": 7.254208281051871e-05,
+      "loss": 1.0359,
+      "step": 100
+    },
+    {
+      "epoch": 1.399134199134199,
+      "grad_norm": 1.2444215446875204,
+      "learning_rate": 7.231502434094845e-05,
+      "loss": 1.0203,
+      "step": 101
+    },
+    {
+      "epoch": 1.412987012987013,
+      "grad_norm": 1.4648122676877777,
+      "learning_rate": 7.208492771020176e-05,
+      "loss": 1.0198,
+      "step": 102
+    },
+    {
+      "epoch": 1.4268398268398268,
+      "grad_norm": 0.9173692823505156,
+      "learning_rate": 7.185181455127023e-05,
+      "loss": 1.0217,
+      "step": 103
+    },
+    {
+      "epoch": 1.4406926406926406,
+      "grad_norm": 1.1009749853774418,
+      "learning_rate": 7.161570678075038e-05,
+      "loss": 1.0128,
+      "step": 104
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 1.0933932370696173,
+      "learning_rate": 7.137662659678303e-05,
+      "loss": 1.0238,
+      "step": 105
+    },
+    {
+      "epoch": 1.4683982683982684,
+      "grad_norm": 1.1757437604660779,
+      "learning_rate": 7.113459647696641e-05,
+      "loss": 1.0182,
+      "step": 106
+    },
+    {
+      "epoch": 1.4822510822510822,
+      "grad_norm": 0.7527900271083177,
+      "learning_rate": 7.088963917624277e-05,
+      "loss": 1.012,
+      "step": 107
+    },
+    {
+      "epoch": 1.4961038961038962,
+      "grad_norm": 1.1702807594476543,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 1.0264,
+      "step": 108
+    },
+    {
+      "epoch": 1.50995670995671,
+      "grad_norm": 0.6981814585755302,
+      "learning_rate": 7.039103542570199e-05,
+      "loss": 1.0151,
+      "step": 109
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 1.1192032445094018,
+      "learning_rate": 7.013743585310642e-05,
+      "loss": 1.0162,
+      "step": 110
+    },
+    {
+      "epoch": 1.5376623376623377,
+      "grad_norm": 1.0770568024481744,
+      "learning_rate": 6.988100284963985e-05,
+      "loss": 1.0199,
+      "step": 111
+    },
+    {
+      "epoch": 1.5515151515151515,
+      "grad_norm": 1.2005325967972154,
+      "learning_rate": 6.96217605243602e-05,
+      "loss": 1.0242,
+      "step": 112
+    },
+    {
+      "epoch": 1.5653679653679653,
+      "grad_norm": 0.7699858239179544,
+      "learning_rate": 6.935973325044941e-05,
+      "loss": 1.0241,
+      "step": 113
+    },
+    {
+      "epoch": 1.5792207792207793,
+      "grad_norm": 1.1064626845196381,
+      "learning_rate": 6.909494566292195e-05,
+      "loss": 1.0082,
+      "step": 114
+    },
+    {
+      "epoch": 1.593073593073593,
+      "grad_norm": 1.4162206055932687,
+      "learning_rate": 6.882742265630859e-05,
+      "loss": 1.0161,
+      "step": 115
+    },
+    {
+      "epoch": 1.6069264069264069,
+      "grad_norm": 0.9857373401383442,
+      "learning_rate": 6.855718938231597e-05,
+      "loss": 1.0223,
+      "step": 116
+    },
+    {
+      "epoch": 1.6207792207792209,
+      "grad_norm": 1.4328471449116547,
+      "learning_rate": 6.828427124746191e-05,
+      "loss": 1.0059,
+      "step": 117
+    },
+    {
+      "epoch": 1.6346320346320347,
+      "grad_norm": 0.929598786782075,
+      "learning_rate": 6.800869391068674e-05,
+      "loss": 1.0161,
+      "step": 118
+    },
+    {
+      "epoch": 1.6484848484848484,
+      "grad_norm": 1.5271277070860276,
+      "learning_rate": 6.773048328094097e-05,
+      "loss": 1.0109,
+      "step": 119
+    },
+    {
+      "epoch": 1.6623376623376624,
+      "grad_norm": 0.7369342923177392,
+      "learning_rate": 6.744966551474936e-05,
+      "loss": 1.0187,
+      "step": 120
+    },
+    {
+      "epoch": 1.6761904761904762,
+      "grad_norm": 1.1411511227164497,
+      "learning_rate": 6.716626701375174e-05,
+      "loss": 1.0131,
+      "step": 121
+    },
+    {
+      "epoch": 1.69004329004329,
+      "grad_norm": 1.2904195611318852,
+      "learning_rate": 6.688031442222091e-05,
+      "loss": 1.0084,
+      "step": 122
+    },
+    {
+      "epoch": 1.703896103896104,
+      "grad_norm": 0.5757097623806057,
+      "learning_rate": 6.659183462455751e-05,
+      "loss": 1.0095,
+      "step": 123
+    },
+    {
+      "epoch": 1.7177489177489178,
+      "grad_norm": 0.9291802416250161,
+      "learning_rate": 6.630085474276256e-05,
+      "loss": 1.0117,
+      "step": 124
+    },
+    {
+      "epoch": 1.7316017316017316,
+      "grad_norm": 1.0033464839111939,
+      "learning_rate": 6.600740213388735e-05,
+      "loss": 1.0055,
+      "step": 125
+    },
+    {
+      "epoch": 1.7454545454545456,
+      "grad_norm": 1.0577865447630987,
+      "learning_rate": 6.571150438746157e-05,
+      "loss": 0.9998,
+      "step": 126
+    },
+    {
+      "epoch": 1.7593073593073592,
+      "grad_norm": 0.9644457639091424,
+      "learning_rate": 6.54131893228994e-05,
+      "loss": 1.003,
+      "step": 127
+    },
+    {
+      "epoch": 1.7731601731601732,
+      "grad_norm": 0.80334378142282,
+      "learning_rate": 6.511248498688396e-05,
+      "loss": 1.0044,
+      "step": 128
+    },
+    {
+      "epoch": 1.7870129870129872,
+      "grad_norm": 0.823547694775696,
+      "learning_rate": 6.480941965073041e-05,
+      "loss": 1.0109,
+      "step": 129
+    },
+    {
+      "epoch": 1.8008658008658007,
+      "grad_norm": 0.7273863270792912,
+      "learning_rate": 6.450402180772811e-05,
+      "loss": 1.0017,
+      "step": 130
+    },
+    {
+      "epoch": 1.8147186147186147,
+      "grad_norm": 0.762963999004941,
+      "learning_rate": 6.419632017046167e-05,
+      "loss": 1.0018,
+      "step": 131
+    },
+    {
+      "epoch": 1.8285714285714287,
+      "grad_norm": 0.8148201089426899,
+      "learning_rate": 6.388634366811146e-05,
+      "loss": 0.9993,
+      "step": 132
+    },
+    {
+      "epoch": 1.8424242424242423,
+      "grad_norm": 0.8416363889161061,
+      "learning_rate": 6.35741214437338e-05,
+      "loss": 1.0095,
+      "step": 133
+    },
+    {
+      "epoch": 1.8562770562770563,
+      "grad_norm": 1.142390867021583,
+      "learning_rate": 6.325968285152107e-05,
+      "loss": 1.0062,
+      "step": 134
+    },
+    {
+      "epoch": 1.87012987012987,
+      "grad_norm": 0.7962536559784616,
+      "learning_rate": 6.294305745404185e-05,
+      "loss": 1.0052,
+      "step": 135
+    },
+    {
+      "epoch": 1.8839826839826839,
+      "grad_norm": 0.5650336880636371,
+      "learning_rate": 6.262427501946155e-05,
+      "loss": 1.0067,
+      "step": 136
+    },
+    {
+      "epoch": 1.8978354978354979,
+      "grad_norm": 0.5818038902731943,
+      "learning_rate": 6.230336551874372e-05,
+      "loss": 1.0063,
+      "step": 137
+    },
+    {
+      "epoch": 1.9116883116883117,
+      "grad_norm": 0.9977727916003996,
+      "learning_rate": 6.198035912283225e-05,
+      "loss": 1.0011,
+      "step": 138
+    },
+    {
+      "epoch": 1.9255411255411254,
+      "grad_norm": 0.9993134068472553,
+      "learning_rate": 6.165528619981479e-05,
+      "loss": 0.9934,
+      "step": 139
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 0.6309774026937955,
+      "learning_rate": 6.132817731206766e-05,
+      "loss": 1.0023,
+      "step": 140
+    },
+    {
+      "epoch": 1.9532467532467532,
+      "grad_norm": 0.5631788726393073,
+      "learning_rate": 6.099906321338241e-05,
+      "loss": 0.9875,
+      "step": 141
+    },
+    {
+      "epoch": 1.967099567099567,
+      "grad_norm": 0.6994904876843244,
+      "learning_rate": 6.0667974846074524e-05,
+      "loss": 0.9969,
+      "step": 142
+    },
+    {
+      "epoch": 1.980952380952381,
+      "grad_norm": 0.6611818685825782,
+      "learning_rate": 6.033494333807422e-05,
+      "loss": 1.0052,
+      "step": 143
+    },
+    {
+      "epoch": 1.9948051948051948,
+      "grad_norm": 0.5004771960590909,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.9857,
+      "step": 144
+    },
+    {
+      "epoch": 2.0086580086580086,
+      "grad_norm": 1.0514858543746186,
+      "learning_rate": 5.9663176322214826e-05,
+      "loss": 1.8002,
+      "step": 145
+    },
+    {
+      "epoch": 2.0225108225108226,
+      "grad_norm": 1.5590490021626622,
+      "learning_rate": 5.9324503971865545e-05,
+      "loss": 0.9591,
+      "step": 146
+    },
+    {
+      "epoch": 2.036363636363636,
+      "grad_norm": 0.613252686965761,
+      "learning_rate": 5.8984014789905625e-05,
+      "loss": 0.9555,
+      "step": 147
+    },
+    {
+      "epoch": 2.05021645021645,
+      "grad_norm": 1.5183857859367584,
+      "learning_rate": 5.8641740788101566e-05,
+      "loss": 0.9637,
+      "step": 148
+    },
+    {
+      "epoch": 2.064069264069264,
+      "grad_norm": 0.599406946967003,
+      "learning_rate": 5.8297714146023236e-05,
+      "loss": 0.9396,
+      "step": 149
+    },
+    {
+      "epoch": 2.0779220779220777,
+      "grad_norm": 1.171195638149606,
+      "learning_rate": 5.79519672080185e-05,
+      "loss": 0.9523,
+      "step": 150
+    },
+    {
+      "epoch": 2.0917748917748917,
+      "grad_norm": 0.6714077570634802,
+      "learning_rate": 5.76045324801722e-05,
+      "loss": 0.9595,
+      "step": 151
+    },
+    {
+      "epoch": 2.1056277056277057,
+      "grad_norm": 1.2318697934613918,
+      "learning_rate": 5.7255442627250146e-05,
+      "loss": 0.9514,
+      "step": 152
+    },
+    {
+      "epoch": 2.1194805194805193,
+      "grad_norm": 0.746989496141657,
+      "learning_rate": 5.6904730469627985e-05,
+      "loss": 0.9482,
+      "step": 153
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.901261215101538,
+      "learning_rate": 5.6552428980205575e-05,
+      "loss": 0.9587,
+      "step": 154
+    },
+    {
+      "epoch": 2.1471861471861473,
+      "grad_norm": 0.674529916922478,
+      "learning_rate": 5.619857128130695e-05,
+      "loss": 0.9562,
+      "step": 155
+    },
+    {
+      "epoch": 2.161038961038961,
+      "grad_norm": 0.8844375890562896,
+      "learning_rate": 5.584319064156628e-05,
+      "loss": 0.9459,
+      "step": 156
+    },
+    {
+      "epoch": 2.174891774891775,
+      "grad_norm": 0.5176842951829833,
+      "learning_rate": 5.548632047280003e-05,
+      "loss": 0.9528,
+      "step": 157
+    },
+    {
+      "epoch": 2.188744588744589,
+      "grad_norm": 0.6248120662111469,
+      "learning_rate": 5.5127994326865706e-05,
+      "loss": 0.9482,
+      "step": 158
+    },
+    {
+      "epoch": 2.2025974025974024,
+      "grad_norm": 0.6093640758186603,
+      "learning_rate": 5.476824589250738e-05,
+      "loss": 0.9429,
+      "step": 159
+    },
+    {
+      "epoch": 2.2164502164502164,
+      "grad_norm": 0.5492958980107647,
+      "learning_rate": 5.440710899218842e-05,
+      "loss": 0.9674,
+      "step": 160
+    },
+    {
+      "epoch": 2.2303030303030305,
+      "grad_norm": 0.5903789766574798,
+      "learning_rate": 5.404461757891156e-05,
+      "loss": 0.9667,
+      "step": 161
+    },
+    {
+      "epoch": 2.244155844155844,
+      "grad_norm": 0.5486871479315714,
+      "learning_rate": 5.368080573302676e-05,
+      "loss": 0.9478,
+      "step": 162
+    },
+    {
+      "epoch": 2.258008658008658,
+      "grad_norm": 0.45428134417688254,
+      "learning_rate": 5.331570765902706e-05,
+      "loss": 0.9409,
+      "step": 163
+    },
+    {
+      "epoch": 2.271861471861472,
+      "grad_norm": 0.42847012632012216,
+      "learning_rate": 5.294935768233285e-05,
+      "loss": 0.9416,
+      "step": 164
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.4848698252601225,
+      "learning_rate": 5.258179024606455e-05,
+      "loss": 0.9463,
+      "step": 165
+    },
+    {
+      "epoch": 2.2995670995670996,
+      "grad_norm": 0.3534788789389581,
+      "learning_rate": 5.2213039907804535e-05,
+      "loss": 0.9491,
+      "step": 166
+    },
+    {
+      "epoch": 2.3134199134199136,
+      "grad_norm": 0.5082308518432114,
+      "learning_rate": 5.1843141336348e-05,
+      "loss": 0.95,
+      "step": 167
+    },
+    {
+      "epoch": 2.327272727272727,
+      "grad_norm": 0.33208032748656197,
+      "learning_rate": 5.1472129308443616e-05,
+      "loss": 0.953,
+      "step": 168
+    },
+    {
+      "epoch": 2.341125541125541,
+      "grad_norm": 0.35843782187780426,
+      "learning_rate": 5.1100038705523834e-05,
+      "loss": 0.957,
+      "step": 169
+    },
+    {
+      "epoch": 2.354978354978355,
+      "grad_norm": 0.33243645634228375,
+      "learning_rate": 5.07269045104255e-05,
+      "loss": 0.9348,
+      "step": 170
+    },
+    {
+      "epoch": 2.3688311688311687,
+      "grad_norm": 0.37544932004082693,
+      "learning_rate": 5.0352761804100835e-05,
+      "loss": 0.9501,
+      "step": 171
+    },
+    {
+      "epoch": 2.3826839826839827,
+      "grad_norm": 0.3396549463565156,
+      "learning_rate": 4.9977645762319255e-05,
+      "loss": 0.9548,
+      "step": 172
+    },
+    {
+      "epoch": 2.3965367965367967,
+      "grad_norm": 0.27413219762637864,
+      "learning_rate": 4.9601591652360244e-05,
+      "loss": 0.9516,
+      "step": 173
+    },
+    {
+      "epoch": 2.4103896103896103,
+      "grad_norm": 0.2935194857656813,
+      "learning_rate": 4.922463482969761e-05,
+      "loss": 0.9537,
+      "step": 174
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.31679378581933954,
+      "learning_rate": 4.884681073467551e-05,
+      "loss": 0.9566,
+      "step": 175
+    },
+    {
+      "epoch": 2.4380952380952383,
+      "grad_norm": 0.2917510642085385,
+      "learning_rate": 4.846815488917644e-05,
+      "loss": 0.9602,
+      "step": 176
+    },
+    {
+      "epoch": 2.451948051948052,
+      "grad_norm": 0.29512012950255556,
+      "learning_rate": 4.808870289328153e-05,
+      "loss": 0.9513,
+      "step": 177
+    },
+    {
+      "epoch": 2.465800865800866,
+      "grad_norm": 0.24808203045159094,
+      "learning_rate": 4.7708490421923596e-05,
+      "loss": 0.9453,
+      "step": 178
+    },
+    {
+      "epoch": 2.47965367965368,
+      "grad_norm": 0.21937289844225158,
+      "learning_rate": 4.7327553221533074e-05,
+      "loss": 0.9581,
+      "step": 179
+    },
+    {
+      "epoch": 2.4935064935064934,
+      "grad_norm": 0.20437241337234358,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.948,
+      "step": 180
+    },
+    {
+      "epoch": 2.5073593073593075,
+      "grad_norm": 0.20182625174185811,
+      "learning_rate": 4.656364795669297e-05,
+      "loss": 0.9505,
+      "step": 181
+    },
+    {
+      "epoch": 2.5212121212121215,
+      "grad_norm": 0.2157700828054003,
+      "learning_rate": 4.618075171231363e-05,
+      "loss": 0.955,
+      "step": 182
+    },
+    {
+      "epoch": 2.535064935064935,
+      "grad_norm": 0.20198999241369922,
+      "learning_rate": 4.579727437228987e-05,
+      "loss": 0.9479,
+      "step": 183
+    },
+    {
+      "epoch": 2.548917748917749,
+      "grad_norm": 0.19349997377276865,
+      "learning_rate": 4.541325199000525e-05,
+      "loss": 0.9444,
+      "step": 184
+    },
+    {
+      "epoch": 2.562770562770563,
+      "grad_norm": 0.20821593855670595,
+      "learning_rate": 4.502872067008652e-05,
+      "loss": 0.9484,
+      "step": 185
+    },
+    {
+      "epoch": 2.5766233766233766,
+      "grad_norm": 0.22714292711765166,
+      "learning_rate": 4.464371656500921e-05,
+      "loss": 0.9478,
+      "step": 186
+    },
+    {
+      "epoch": 2.5904761904761906,
+      "grad_norm": 0.22439821970405607,
+      "learning_rate": 4.425827587169873e-05,
+      "loss": 0.9642,
+      "step": 187
+    },
+    {
+      "epoch": 2.6043290043290046,
+      "grad_norm": 0.19017166723603593,
+      "learning_rate": 4.387243482812717e-05,
+      "loss": 0.9354,
+      "step": 188
+    },
+    {
+      "epoch": 2.618181818181818,
+      "grad_norm": 0.2338760203213592,
+      "learning_rate": 4.348622970990634e-05,
+      "loss": 0.9608,
+      "step": 189
+    },
+    {
+      "epoch": 2.632034632034632,
+      "grad_norm": 0.19433184424361064,
+      "learning_rate": 4.309969682687724e-05,
+      "loss": 0.9365,
+      "step": 190
+    },
+    {
+      "epoch": 2.6458874458874457,
+      "grad_norm": 0.2006639594796061,
+      "learning_rate": 4.271287251969637e-05,
+      "loss": 0.943,
+      "step": 191
+    },
+    {
+      "epoch": 2.6597402597402597,
+      "grad_norm": 0.19675542180216962,
+      "learning_rate": 4.2325793156419035e-05,
+      "loss": 0.9629,
+      "step": 192
+    },
+    {
+      "epoch": 2.6735930735930737,
+      "grad_norm": 0.22882862992661218,
+      "learning_rate": 4.193849512908013e-05,
+      "loss": 0.9399,
+      "step": 193
+    },
+    {
+      "epoch": 2.6874458874458873,
+      "grad_norm": 0.27628995792251587,
+      "learning_rate": 4.155101485027268e-05,
+      "loss": 0.9517,
+      "step": 194
+    },
+    {
+      "epoch": 2.7012987012987013,
+      "grad_norm": 0.25152494788624064,
+      "learning_rate": 4.116338874972446e-05,
+      "loss": 0.9532,
+      "step": 195
+    },
+    {
+      "epoch": 2.7151515151515153,
+      "grad_norm": 0.17237631990944813,
+      "learning_rate": 4.077565327087298e-05,
+      "loss": 0.9443,
+      "step": 196
+    },
+    {
+      "epoch": 2.729004329004329,
+      "grad_norm": 0.22052058799944804,
+      "learning_rate": 4.0387844867439143e-05,
+      "loss": 0.9384,
+      "step": 197
+    },
+    {
+      "epoch": 2.742857142857143,
+      "grad_norm": 0.2821185693525401,
+      "learning_rate": 4e-05,
+      "loss": 0.9506,
+      "step": 198
+    },
+    {
+      "epoch": 2.7567099567099564,
+      "grad_norm": 0.23974193332071514,
+      "learning_rate": 3.961215513256086e-05,
+      "loss": 0.944,
+      "step": 199
+    },
+    {
+      "epoch": 2.7705627705627704,
+      "grad_norm": 0.23881720962641614,
+      "learning_rate": 3.9224346729127034e-05,
+      "loss": 0.9423,
+      "step": 200
+    },
+    {
+      "epoch": 2.7844155844155845,
+      "grad_norm": 0.1774343946075327,
+      "learning_rate": 3.8836611250275546e-05,
+      "loss": 0.9355,
+      "step": 201
+    },
+    {
+      "epoch": 2.798268398268398,
+      "grad_norm": 0.23570113544248983,
+      "learning_rate": 3.844898514972733e-05,
+      "loss": 0.9519,
+      "step": 202
+    },
+    {
+      "epoch": 2.812121212121212,
+      "grad_norm": 0.21653970566029948,
+      "learning_rate": 3.806150487091989e-05,
+      "loss": 0.951,
+      "step": 203
+    },
+    {
+      "epoch": 2.825974025974026,
+      "grad_norm": 0.1881655573837289,
+      "learning_rate": 3.767420684358097e-05,
+      "loss": 0.9425,
+      "step": 204
+    },
+    {
+      "epoch": 2.8398268398268396,
+      "grad_norm": 0.19487964543004402,
+      "learning_rate": 3.7287127480303634e-05,
+      "loss": 0.9496,
+      "step": 205
+    },
+    {
+      "epoch": 2.8536796536796536,
+      "grad_norm": 0.21940934921746677,
+      "learning_rate": 3.690030317312277e-05,
+      "loss": 0.9326,
+      "step": 206
+    },
+    {
+      "epoch": 2.8675324675324676,
+      "grad_norm": 0.22419835861035028,
+      "learning_rate": 3.6513770290093674e-05,
+      "loss": 0.958,
+      "step": 207
+    },
+    {
+      "epoch": 2.881385281385281,
+      "grad_norm": 0.20379473922199545,
+      "learning_rate": 3.612756517187284e-05,
+      "loss": 0.9475,
+      "step": 208
+    },
+    {
+      "epoch": 2.895238095238095,
+      "grad_norm": 0.15734328009114276,
+      "learning_rate": 3.574172412830127e-05,
+      "loss": 0.9446,
+      "step": 209
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.2577374514137676,
+      "learning_rate": 3.535628343499079e-05,
+      "loss": 0.9518,
+      "step": 210
+    },
+    {
+      "epoch": 2.9229437229437227,
+      "grad_norm": 0.21560632289046236,
+      "learning_rate": 3.49712793299135e-05,
+      "loss": 0.9321,
+      "step": 211
+    },
+    {
+      "epoch": 2.9367965367965367,
+      "grad_norm": 0.19086166501572058,
+      "learning_rate": 3.458674800999477e-05,
+      "loss": 0.939,
+      "step": 212
+    },
+    {
+      "epoch": 2.9506493506493507,
+      "grad_norm": 0.1635737725085455,
+      "learning_rate": 3.4202725627710136e-05,
+      "loss": 0.9519,
+      "step": 213
+    },
+    {
+      "epoch": 2.9645021645021643,
+      "grad_norm": 0.2063878664719065,
+      "learning_rate": 3.3819248287686386e-05,
+      "loss": 0.9408,
+      "step": 214
+    },
+    {
+      "epoch": 2.9783549783549783,
+      "grad_norm": 0.21758034147643424,
+      "learning_rate": 3.343635204330704e-05,
+      "loss": 0.9366,
+      "step": 215
+    },
+    {
+      "epoch": 2.9922077922077923,
+      "grad_norm": 0.1756516719858461,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.9261,
+      "step": 216
+    },
+    {
+      "epoch": 3.006060606060606,
+      "grad_norm": 0.44437950709772883,
+      "learning_rate": 3.267244677846693e-05,
+      "loss": 1.6737,
+      "step": 217
+    },
+    {
+      "epoch": 3.01991341991342,
+      "grad_norm": 0.5202547459859553,
+      "learning_rate": 3.229150957807641e-05,
+      "loss": 0.9065,
+      "step": 218
+    },
+    {
+      "epoch": 3.033766233766234,
+      "grad_norm": 0.4201768177217496,
+      "learning_rate": 3.191129710671849e-05,
+      "loss": 0.8993,
+      "step": 219
+    },
+    {
+      "epoch": 3.0476190476190474,
+      "grad_norm": 0.3469006955241282,
+      "learning_rate": 3.153184511082359e-05,
+      "loss": 0.8924,
+      "step": 220
+    },
+    {
+      "epoch": 3.0614718614718615,
+      "grad_norm": 0.34894763894121467,
+      "learning_rate": 3.1153189265324494e-05,
+      "loss": 0.9091,
+      "step": 221
+    },
+    {
+      "epoch": 3.0753246753246755,
+      "grad_norm": 0.3951659967368868,
+      "learning_rate": 3.07753651703024e-05,
+      "loss": 0.9103,
+      "step": 222
+    },
+    {
+      "epoch": 3.089177489177489,
+      "grad_norm": 0.33506373060928457,
+      "learning_rate": 3.0398408347639773e-05,
+      "loss": 0.8895,
+      "step": 223
+    },
+    {
+      "epoch": 3.103030303030303,
+      "grad_norm": 0.2808678451376146,
+      "learning_rate": 3.0022354237680752e-05,
+      "loss": 0.8954,
+      "step": 224
+    },
+    {
+      "epoch": 3.116883116883117,
+      "grad_norm": 0.3452617358086684,
+      "learning_rate": 2.9647238195899168e-05,
+      "loss": 0.8954,
+      "step": 225
+    },
+    {
+      "epoch": 3.1307359307359306,
+      "grad_norm": 0.32553230647238945,
+      "learning_rate": 2.9273095489574502e-05,
+      "loss": 0.897,
+      "step": 226
+    },
+    {
+      "epoch": 3.1445887445887446,
+      "grad_norm": 0.2604914839354281,
+      "learning_rate": 2.889996129447618e-05,
+      "loss": 0.907,
+      "step": 227
+    },
+    {
+      "epoch": 3.1584415584415586,
+      "grad_norm": 0.34111866816202957,
+      "learning_rate": 2.8527870691556404e-05,
+      "loss": 0.8981,
+      "step": 228
+    },
+    {
+      "epoch": 3.172294372294372,
+      "grad_norm": 0.28026302405180475,
+      "learning_rate": 2.8156858663652015e-05,
+      "loss": 0.9033,
+      "step": 229
+    },
+    {
+      "epoch": 3.186147186147186,
+      "grad_norm": 0.26870372034953893,
+      "learning_rate": 2.778696009219548e-05,
+      "loss": 0.9059,
+      "step": 230
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.3798626491614641,
+      "learning_rate": 2.7418209753935464e-05,
+      "loss": 0.8894,
+      "step": 231
+    },
+    {
+      "epoch": 3.2138528138528137,
+      "grad_norm": 0.21379716918544014,
+      "learning_rate": 2.7050642317667164e-05,
+      "loss": 0.8937,
+      "step": 232
+    },
+    {
+      "epoch": 3.2277056277056277,
+      "grad_norm": 0.31956814421124774,
+      "learning_rate": 2.6684292340972936e-05,
+      "loss": 0.9068,
+      "step": 233
+    },
+    {
+      "epoch": 3.2415584415584417,
+      "grad_norm": 0.194502129845176,
+      "learning_rate": 2.6319194266973256e-05,
+      "loss": 0.8999,
+      "step": 234
+    },
+    {
+      "epoch": 3.2554112554112553,
+      "grad_norm": 0.25288436825501515,
+      "learning_rate": 2.5955382421088457e-05,
+      "loss": 0.8876,
+      "step": 235
+    },
+    {
+      "epoch": 3.2692640692640693,
+      "grad_norm": 0.2045328796636946,
+      "learning_rate": 2.5592891007811594e-05,
+      "loss": 0.9056,
+      "step": 236
+    },
+    {
+      "epoch": 3.2831168831168833,
+      "grad_norm": 0.17690924985251477,
+      "learning_rate": 2.523175410749263e-05,
+      "loss": 0.9068,
+      "step": 237
+    },
+    {
+      "epoch": 3.296969696969697,
+      "grad_norm": 0.20432688291964138,
+      "learning_rate": 2.4872005673134307e-05,
+      "loss": 0.8916,
+      "step": 238
+    },
+    {
+      "epoch": 3.310822510822511,
+      "grad_norm": 0.17738981903795317,
+      "learning_rate": 2.4513679527199986e-05,
+      "loss": 0.9115,
+      "step": 239
+    },
+    {
+      "epoch": 3.324675324675325,
+      "grad_norm": 0.16833331057473214,
+      "learning_rate": 2.4156809358433728e-05,
+      "loss": 0.8891,
+      "step": 240
+    },
+    {
+      "epoch": 3.3385281385281385,
+      "grad_norm": 0.17407822439034182,
+      "learning_rate": 2.3801428718693055e-05,
+      "loss": 0.8936,
+      "step": 241
+    },
+    {
+      "epoch": 3.3523809523809525,
+      "grad_norm": 0.16434385080662373,
+      "learning_rate": 2.3447571019794438e-05,
+      "loss": 0.9079,
+      "step": 242
+    },
+    {
+      "epoch": 3.3662337662337665,
+      "grad_norm": 0.1647420511208294,
+      "learning_rate": 2.3095269530372032e-05,
+      "loss": 0.8904,
+      "step": 243
+    },
+    {
+      "epoch": 3.38008658008658,
+      "grad_norm": 0.16465200281562736,
+      "learning_rate": 2.274455737274987e-05,
+      "loss": 0.8965,
+      "step": 244
+    },
+    {
+      "epoch": 3.393939393939394,
+      "grad_norm": 0.1942259697042446,
+      "learning_rate": 2.239546751982782e-05,
+      "loss": 0.9039,
+      "step": 245
+    },
+    {
+      "epoch": 3.407792207792208,
+      "grad_norm": 0.15418958599426286,
+      "learning_rate": 2.2048032791981515e-05,
+      "loss": 0.8921,
+      "step": 246
+    },
+    {
+      "epoch": 3.4216450216450216,
+      "grad_norm": 0.15256309020808106,
+      "learning_rate": 2.1702285853976774e-05,
+      "loss": 0.8972,
+      "step": 247
+    },
+    {
+      "epoch": 3.4354978354978356,
+      "grad_norm": 0.14590845303296213,
+      "learning_rate": 2.135825921189846e-05,
+      "loss": 0.8967,
+      "step": 248
+    },
+    {
+      "epoch": 3.449350649350649,
+      "grad_norm": 0.1756342017642444,
+      "learning_rate": 2.1015985210094385e-05,
+      "loss": 0.9089,
+      "step": 249
+    },
+    {
+      "epoch": 3.463203463203463,
+      "grad_norm": 0.14928130402546771,
+      "learning_rate": 2.067549602813446e-05,
+      "loss": 0.9116,
+      "step": 250
+    },
+    {
+      "epoch": 3.477056277056277,
+      "grad_norm": 0.19622196885081308,
+      "learning_rate": 2.033682367778518e-05,
+      "loss": 0.9035,
+      "step": 251
+    },
+    {
+      "epoch": 3.4909090909090907,
+      "grad_norm": 0.16833682605095,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.9049,
+      "step": 252
+    },
+    {
+      "epoch": 3.5047619047619047,
+      "grad_norm": 0.1700606136967009,
+      "learning_rate": 1.966505666192579e-05,
+      "loss": 0.9013,
+      "step": 253
+    },
+    {
+      "epoch": 3.5186147186147188,
+      "grad_norm": 0.1795362591013133,
+      "learning_rate": 1.9332025153925486e-05,
+      "loss": 0.887,
+      "step": 254
+    },
+    {
+      "epoch": 3.5324675324675323,
+      "grad_norm": 0.16623457555792936,
+      "learning_rate": 1.90009367866176e-05,
+      "loss": 0.9025,
+      "step": 255
+    },
+    {
+      "epoch": 3.5463203463203463,
+      "grad_norm": 0.1724331408670692,
+      "learning_rate": 1.867182268793236e-05,
+      "loss": 0.902,
+      "step": 256
+    },
+    {
+      "epoch": 3.5601731601731603,
+      "grad_norm": 0.156738658049747,
+      "learning_rate": 1.8344713800185215e-05,
+      "loss": 0.8935,
+      "step": 257
+    },
+    {
+      "epoch": 3.574025974025974,
+      "grad_norm": 0.16288790800709219,
+      "learning_rate": 1.8019640877167763e-05,
+      "loss": 0.898,
+      "step": 258
+    },
+    {
+      "epoch": 3.587878787878788,
+      "grad_norm": 0.15690946638171066,
+      "learning_rate": 1.7696634481256293e-05,
+      "loss": 0.8959,
+      "step": 259
+    },
+    {
+      "epoch": 3.601731601731602,
+      "grad_norm": 0.16001262583220252,
+      "learning_rate": 1.7375724980538465e-05,
+      "loss": 0.8888,
+      "step": 260
+    },
+    {
+      "epoch": 3.6155844155844155,
+      "grad_norm": 0.15064377615121663,
+      "learning_rate": 1.7056942545958167e-05,
+      "loss": 0.9089,
+      "step": 261
+    },
+    {
+      "epoch": 3.6294372294372295,
+      "grad_norm": 0.13096790236650285,
+      "learning_rate": 1.6740317148478932e-05,
+      "loss": 0.9055,
+      "step": 262
+    },
+    {
+      "epoch": 3.643290043290043,
+      "grad_norm": 0.14921599598853594,
+      "learning_rate": 1.642587855626621e-05,
+      "loss": 0.9154,
+      "step": 263
+    },
+    {
+      "epoch": 3.657142857142857,
+      "grad_norm": 0.13367750739235254,
+      "learning_rate": 1.6113656331888563e-05,
+      "loss": 0.8954,
+      "step": 264
+    },
+    {
+      "epoch": 3.670995670995671,
+      "grad_norm": 0.14168194296838715,
+      "learning_rate": 1.580367982953833e-05,
+      "loss": 0.8939,
+      "step": 265
+    },
+    {
+      "epoch": 3.6848484848484846,
+      "grad_norm": 0.14492593957298525,
+      "learning_rate": 1.5495978192271887e-05,
+      "loss": 0.91,
+      "step": 266
+    },
+    {
+      "epoch": 3.6987012987012986,
+      "grad_norm": 0.1316497818256666,
+      "learning_rate": 1.5190580349269604e-05,
+      "loss": 0.9027,
+      "step": 267
+    },
+    {
+      "epoch": 3.7125541125541126,
+      "grad_norm": 0.15841380793742146,
+      "learning_rate": 1.4887515013116067e-05,
+      "loss": 0.9106,
+      "step": 268
+    },
+    {
+      "epoch": 3.726406926406926,
+      "grad_norm": 0.13126491215447147,
+      "learning_rate": 1.4586810677100608e-05,
+      "loss": 0.8937,
+      "step": 269
+    },
+    {
+      "epoch": 3.74025974025974,
+      "grad_norm": 0.1495403663254427,
+      "learning_rate": 1.4288495612538427e-05,
+      "loss": 0.9034,
+      "step": 270
+    },
+    {
+      "epoch": 3.754112554112554,
+      "grad_norm": 0.12429246476808327,
+      "learning_rate": 1.3992597866112667e-05,
+      "loss": 0.8975,
+      "step": 271
+    },
+    {
+      "epoch": 3.7679653679653677,
+      "grad_norm": 0.13097022929593902,
+      "learning_rate": 1.369914525723746e-05,
+      "loss": 0.8882,
+      "step": 272
+    },
+    {
+      "epoch": 3.7818181818181817,
+      "grad_norm": 0.13482171999455558,
+      "learning_rate": 1.3408165375442486e-05,
+      "loss": 0.8906,
+      "step": 273
+    },
+    {
+      "epoch": 3.7956709956709958,
+      "grad_norm": 0.12515899928871424,
+      "learning_rate": 1.3119685577779105e-05,
+      "loss": 0.9008,
+      "step": 274
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 0.13069692054136395,
+      "learning_rate": 1.2833732986248277e-05,
+      "loss": 0.8853,
+      "step": 275
+    },
+    {
+      "epoch": 3.8233766233766233,
+      "grad_norm": 0.13447223817691295,
+      "learning_rate": 1.2550334485250661e-05,
+      "loss": 0.9051,
+      "step": 276
+    },
+    {
+      "epoch": 3.8372294372294373,
+      "grad_norm": 0.12306949358534137,
+      "learning_rate": 1.2269516719059041e-05,
+      "loss": 0.8979,
+      "step": 277
+    },
+    {
+      "epoch": 3.851082251082251,
+      "grad_norm": 0.13274764900634733,
+      "learning_rate": 1.1991306089313261e-05,
+      "loss": 0.901,
+      "step": 278
+    },
+    {
+      "epoch": 3.864935064935065,
+      "grad_norm": 0.12496506975650054,
+      "learning_rate": 1.1715728752538103e-05,
+      "loss": 0.8851,
+      "step": 279
+    },
+    {
+      "epoch": 3.878787878787879,
+      "grad_norm": 0.12342700776133213,
+      "learning_rate": 1.1442810617684046e-05,
+      "loss": 0.8906,
+      "step": 280
+    },
+    {
+      "epoch": 3.8926406926406925,
+      "grad_norm": 0.11718555769651504,
+      "learning_rate": 1.1172577343691415e-05,
+      "loss": 0.8945,
+      "step": 281
+    },
+    {
+      "epoch": 3.9064935064935065,
+      "grad_norm": 0.11900571530829156,
+      "learning_rate": 1.0905054337078051e-05,
+      "loss": 0.8939,
+      "step": 282
+    },
+    {
+      "epoch": 3.9203463203463205,
+      "grad_norm": 0.11761709393948508,
+      "learning_rate": 1.0640266749550593e-05,
+      "loss": 0.8987,
+      "step": 283
+    },
+    {
+      "epoch": 3.934199134199134,
+      "grad_norm": 0.12426098474964,
+      "learning_rate": 1.0378239475639823e-05,
+      "loss": 0.8954,
+      "step": 284
+    },
+    {
+      "epoch": 3.948051948051948,
+      "grad_norm": 0.11342564958505907,
+      "learning_rate": 1.0118997150360169e-05,
+      "loss": 0.8967,
+      "step": 285
+    },
+    {
+      "epoch": 3.961904761904762,
+      "grad_norm": 0.12414751882404233,
+      "learning_rate": 9.862564146893571e-06,
+      "loss": 0.8942,
+      "step": 286
+    },
+    {
+      "epoch": 3.9757575757575756,
+      "grad_norm": 0.11821007668599343,
+      "learning_rate": 9.60896457429803e-06,
+      "loss": 0.8981,
+      "step": 287
+    },
+    {
+      "epoch": 3.9896103896103896,
+      "grad_norm": 0.11207748566968422,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.8969,
+      "step": 288
+    },
+    {
+      "epoch": 4.003463203463204,
+      "grad_norm": 0.24776696231966608,
+      "learning_rate": 9.110360823757235e-06,
+      "loss": 1.6175,
+      "step": 289
+    },
+    {
+      "epoch": 4.017316017316017,
+      "grad_norm": 0.1639268139321257,
+      "learning_rate": 8.8654035230336e-06,
+      "loss": 0.8757,
+      "step": 290
+    },
+    {
+      "epoch": 4.031168831168831,
+      "grad_norm": 0.1430026414045171,
+      "learning_rate": 8.623373403216972e-06,
+      "loss": 0.8619,
+      "step": 291
+    },
+    {
+      "epoch": 4.045021645021645,
+      "grad_norm": 0.13983259059672157,
+      "learning_rate": 8.384293219249633e-06,
+      "loss": 0.875,
+      "step": 292
+    },
+    {
+      "epoch": 4.058874458874459,
+      "grad_norm": 0.14776698103121835,
+      "learning_rate": 8.148185448729778e-06,
+      "loss": 0.8712,
+      "step": 293
+    },
+    {
+      "epoch": 4.072727272727272,
+      "grad_norm": 0.1453264011082169,
+      "learning_rate": 7.915072289798247e-06,
+      "loss": 0.8859,
+      "step": 294
+    },
+    {
+      "epoch": 4.086580086580087,
+      "grad_norm": 0.15943779551259862,
+      "learning_rate": 7.684975659051557e-06,
+      "loss": 0.8662,
+      "step": 295
+    },
+    {
+      "epoch": 4.1004329004329,
+      "grad_norm": 0.1456231807293276,
+      "learning_rate": 7.457917189481301e-06,
+      "loss": 0.8774,
+      "step": 296
+    },
+    {
+      "epoch": 4.114285714285714,
+      "grad_norm": 0.14340143561096827,
+      "learning_rate": 7.233918228440324e-06,
+      "loss": 0.8774,
+      "step": 297
+    },
+    {
+      "epoch": 4.128138528138528,
+      "grad_norm": 0.14023071744580373,
+      "learning_rate": 7.0129998356357295e-06,
+      "loss": 0.863,
+      "step": 298
+    },
+    {
+      "epoch": 4.141991341991342,
+      "grad_norm": 0.14172173606520722,
+      "learning_rate": 6.795182781148848e-06,
+      "loss": 0.8767,
+      "step": 299
+    },
+    {
+      "epoch": 4.1558441558441555,
+      "grad_norm": 0.1318876467621652,
+      "learning_rate": 6.58048754348255e-06,
+      "loss": 0.8709,
+      "step": 300
+    },
+    {
+      "epoch": 4.16969696969697,
+      "grad_norm": 0.1517460979685681,
+      "learning_rate": 6.368934307635881e-06,
+      "loss": 0.8716,
+      "step": 301
+    },
+    {
+      "epoch": 4.1835497835497835,
+      "grad_norm": 0.15120519716651545,
+      "learning_rate": 6.160542963206357e-06,
+      "loss": 0.8697,
+      "step": 302
+    },
+    {
+      "epoch": 4.197402597402597,
+      "grad_norm": 0.12276533641084203,
+      "learning_rate": 5.955333102520011e-06,
+      "loss": 0.8628,
+      "step": 303
+    },
+    {
+      "epoch": 4.2112554112554115,
+      "grad_norm": 0.1303847318332295,
+      "learning_rate": 5.753324018789346e-06,
+      "loss": 0.8708,
+      "step": 304
+    },
+    {
+      "epoch": 4.225108225108225,
+      "grad_norm": 0.13706452110864129,
+      "learning_rate": 5.554534704299448e-06,
+      "loss": 0.8566,
+      "step": 305
+    },
+    {
+      "epoch": 4.238961038961039,
+      "grad_norm": 0.15781002543920747,
+      "learning_rate": 5.358983848622452e-06,
+      "loss": 0.8764,
+      "step": 306
+    },
+    {
+      "epoch": 4.252813852813853,
+      "grad_norm": 0.11520912795530423,
+      "learning_rate": 5.1666898368603195e-06,
+      "loss": 0.8749,
+      "step": 307
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 0.11508546810833122,
+      "learning_rate": 4.97767074791637e-06,
+      "loss": 0.8657,
+      "step": 308
+    },
+    {
+      "epoch": 4.28051948051948,
+      "grad_norm": 0.14352142083453215,
+      "learning_rate": 4.791944352795561e-06,
+      "loss": 0.8919,
+      "step": 309
+    },
+    {
+      "epoch": 4.294372294372295,
+      "grad_norm": 0.13642778141475553,
+      "learning_rate": 4.609528112933688e-06,
+      "loss": 0.8575,
+      "step": 310
+    },
+    {
+      "epoch": 4.308225108225108,
+      "grad_norm": 0.11645525287361383,
+      "learning_rate": 4.430439178555759e-06,
+      "loss": 0.874,
+      "step": 311
+    },
+    {
+      "epoch": 4.322077922077922,
+      "grad_norm": 0.11198885083380229,
+      "learning_rate": 4.254694387063514e-06,
+      "loss": 0.866,
+      "step": 312
+    },
+    {
+      "epoch": 4.335930735930736,
+      "grad_norm": 0.11999719505276203,
+      "learning_rate": 4.082310261452471e-06,
+      "loss": 0.8809,
+      "step": 313
+    },
+    {
+      "epoch": 4.34978354978355,
+      "grad_norm": 0.11431861199461578,
+      "learning_rate": 3.913303008758491e-06,
+      "loss": 0.8739,
+      "step": 314
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 0.1089763284328194,
+      "learning_rate": 3.747688518534003e-06,
+      "loss": 0.8764,
+      "step": 315
+    },
+    {
+      "epoch": 4.377489177489178,
+      "grad_norm": 0.11083535668146678,
+      "learning_rate": 3.585482361354138e-06,
+      "loss": 0.874,
+      "step": 316
+    },
+    {
+      "epoch": 4.391341991341991,
+      "grad_norm": 0.10462111723473196,
+      "learning_rate": 3.42669978735283e-06,
+      "loss": 0.8712,
+      "step": 317
+    },
+    {
+      "epoch": 4.405194805194805,
+      "grad_norm": 0.11192874060919457,
+      "learning_rate": 3.2713557247890447e-06,
+      "loss": 0.865,
+      "step": 318
+    },
+    {
+      "epoch": 4.419047619047619,
+      "grad_norm": 0.0998639300176411,
+      "learning_rate": 3.1194647786432663e-06,
+      "loss": 0.8628,
+      "step": 319
+    },
+    {
+      "epoch": 4.432900432900433,
+      "grad_norm": 0.1037388404966585,
+      "learning_rate": 2.9710412292443868e-06,
+      "loss": 0.8744,
+      "step": 320
+    },
+    {
+      "epoch": 4.4467532467532465,
+      "grad_norm": 0.10341839983438926,
+      "learning_rate": 2.8260990309270987e-06,
+      "loss": 0.8707,
+      "step": 321
+    },
+    {
+      "epoch": 4.460606060606061,
+      "grad_norm": 0.10245055505097513,
+      "learning_rate": 2.6846518107199782e-06,
+      "loss": 0.869,
+      "step": 322
+    },
+    {
+      "epoch": 4.4744588744588745,
+      "grad_norm": 0.10245685258161713,
+      "learning_rate": 2.546712867064276e-06,
+      "loss": 0.866,
+      "step": 323
+    },
+    {
+      "epoch": 4.488311688311688,
+      "grad_norm": 0.10246348212442796,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.869,
+      "step": 324
+    },
+    {
+      "epoch": 4.5021645021645025,
+      "grad_norm": 0.10133630585516906,
+      "learning_rate": 2.281411352764966e-06,
+      "loss": 0.8661,
+      "step": 325
+    },
+    {
+      "epoch": 4.516017316017316,
+      "grad_norm": 0.10385457357599492,
+      "learning_rate": 2.1540737249699893e-06,
+      "loss": 0.8665,
+      "step": 326
+    },
+    {
+      "epoch": 4.52987012987013,
+      "grad_norm": 0.09787930849328196,
+      "learning_rate": 2.0302942570786446e-06,
+      "loss": 0.8587,
+      "step": 327
+    },
+    {
+      "epoch": 4.543722943722944,
+      "grad_norm": 0.09875061097653641,
+      "learning_rate": 1.9100845864633875e-06,
+      "loss": 0.862,
+      "step": 328
+    },
+    {
+      "epoch": 4.557575757575758,
+      "grad_norm": 0.10019109859451927,
+      "learning_rate": 1.793456014875079e-06,
+      "loss": 0.8667,
+      "step": 329
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.09607007590769094,
+      "learning_rate": 1.6804195073804442e-06,
+      "loss": 0.8609,
+      "step": 330
+    },
+    {
+      "epoch": 4.585281385281386,
+      "grad_norm": 0.0995091150688806,
+      "learning_rate": 1.5709856913311795e-06,
+      "loss": 0.8631,
+      "step": 331
+    },
+    {
+      "epoch": 4.599134199134199,
+      "grad_norm": 0.10237535339157534,
+      "learning_rate": 1.4651648553647869e-06,
+      "loss": 0.874,
+      "step": 332
+    },
+    {
+      "epoch": 4.612987012987013,
+      "grad_norm": 0.09685943360360758,
+      "learning_rate": 1.3629669484372722e-06,
+      "loss": 0.8608,
+      "step": 333
+    },
+    {
+      "epoch": 4.626839826839827,
+      "grad_norm": 0.10088872360008577,
+      "learning_rate": 1.2644015788877684e-06,
+      "loss": 0.8776,
+      "step": 334
+    },
+    {
+      "epoch": 4.640692640692641,
+      "grad_norm": 0.09659731541025765,
+      "learning_rate": 1.1694780135352013e-06,
+      "loss": 0.8659,
+      "step": 335
+    },
+    {
+      "epoch": 4.654545454545454,
+      "grad_norm": 0.09754069143347813,
+      "learning_rate": 1.0782051768070477e-06,
+      "loss": 0.8822,
+      "step": 336
+    },
+    {
+      "epoch": 4.668398268398269,
+      "grad_norm": 0.09529068088084004,
+      "learning_rate": 9.905916499002787e-07,
+      "loss": 0.8632,
+      "step": 337
+    },
+    {
+      "epoch": 4.682251082251082,
+      "grad_norm": 0.09443098915190634,
+      "learning_rate": 9.066456699745774e-07,
+      "loss": 0.8686,
+      "step": 338
+    },
+    {
+      "epoch": 4.696103896103896,
+      "grad_norm": 0.09719204747726426,
+      "learning_rate": 8.263751293779409e-07,
+      "loss": 0.8709,
+      "step": 339
+    },
+    {
+      "epoch": 4.70995670995671,
+      "grad_norm": 0.0989300648418707,
+      "learning_rate": 7.497875749046124e-07,
+      "loss": 0.8706,
+      "step": 340
+    },
+    {
+      "epoch": 4.723809523809524,
+      "grad_norm": 0.09639393839499397,
+      "learning_rate": 6.768902070856031e-07,
+      "loss": 0.8661,
+      "step": 341
+    },
+    {
+      "epoch": 4.7376623376623375,
+      "grad_norm": 0.09557188345066484,
+      "learning_rate": 6.076898795116792e-07,
+      "loss": 0.8662,
+      "step": 342
+    },
+    {
+      "epoch": 4.751515151515152,
+      "grad_norm": 0.09944408893779064,
+      "learning_rate": 5.421930981890455e-07,
+      "loss": 0.877,
+      "step": 343
+    },
+    {
+      "epoch": 4.7653679653679655,
+      "grad_norm": 0.0977504011176678,
+      "learning_rate": 4.804060209276396e-07,
+      "loss": 0.8658,
+      "step": 344
+    },
+    {
+      "epoch": 4.779220779220779,
+      "grad_norm": 0.09464762553229625,
+      "learning_rate": 4.223344567622212e-07,
+      "loss": 0.8718,
+      "step": 345
+    },
+    {
+      "epoch": 4.7930735930735935,
+      "grad_norm": 0.09515637845594775,
+      "learning_rate": 3.679838654061874e-07,
+      "loss": 0.8672,
+      "step": 346
+    },
+    {
+      "epoch": 4.806926406926407,
+      "grad_norm": 0.09692757545190614,
+      "learning_rate": 3.173593567383071e-07,
+      "loss": 0.8762,
+      "step": 347
+    },
+    {
+      "epoch": 4.820779220779221,
+      "grad_norm": 0.09525175615621749,
+      "learning_rate": 2.704656903222791e-07,
+      "loss": 0.8792,
+      "step": 348
+    },
+    {
+      "epoch": 4.834632034632035,
+      "grad_norm": 0.09621257866702408,
+      "learning_rate": 2.273072749592631e-07,
+      "loss": 0.864,
+      "step": 349
+    },
+    {
+      "epoch": 4.848484848484849,
+      "grad_norm": 0.09435391607466348,
+      "learning_rate": 1.8788816827336686e-07,
+      "loss": 0.8827,
+      "step": 350
+    },
+    {
+      "epoch": 4.862337662337662,
+      "grad_norm": 0.09330676760639534,
+      "learning_rate": 1.522120763301782e-07,
+      "loss": 0.8634,
+      "step": 351
+    },
+    {
+      "epoch": 4.876190476190477,
+      "grad_norm": 0.09377768092440732,
+      "learning_rate": 1.2028235328831906e-07,
+      "loss": 0.8782,
+      "step": 352
+    },
+    {
+      "epoch": 4.89004329004329,
+      "grad_norm": 0.09540719747182097,
+      "learning_rate": 9.21020010840934e-08,
+      "loss": 0.8721,
+      "step": 353
+    },
+    {
+      "epoch": 4.903896103896104,
+      "grad_norm": 0.09356725286148478,
+      "learning_rate": 6.767366914927298e-08,
+      "loss": 0.8784,
+      "step": 354
+    },
+    {
+      "epoch": 4.917748917748918,
+      "grad_norm": 0.09257225973193513,
+      "learning_rate": 4.699965416198549e-08,
+      "loss": 0.8794,
+      "step": 355
+    },
+    {
+      "epoch": 4.931601731601732,
+      "grad_norm": 0.09315617718680014,
+      "learning_rate": 3.0081899830798345e-08,
+      "loss": 0.8658,
+      "step": 356
+    },
+    {
+      "epoch": 4.945454545454545,
+      "grad_norm": 0.09320193350709476,
+      "learning_rate": 1.6921996711976028e-08,
+      "loss": 0.8666,
+      "step": 357
+    },
+    {
+      "epoch": 4.95930735930736,
+      "grad_norm": 0.09451963386678745,
+      "learning_rate": 7.521182059946342e-09,
+      "loss": 0.866,
+      "step": 358
+    },
+    {
+      "epoch": 4.973160173160173,
+      "grad_norm": 0.09250072566157394,
+      "learning_rate": 1.8803397109534715e-09,
+      "loss": 0.8639,
+      "step": 359
+    },
+    {
+      "epoch": 4.987012987012987,
+      "grad_norm": 0.09138839375450408,
+      "learning_rate": 0.0,
+      "loss": 0.8814,
+      "step": 360
+    },
+    {
+      "epoch": 4.987012987012987,
+      "step": 360,
+      "total_flos": 9.572466247992345e+18,
+      "train_loss": 0.0,
+      "train_runtime": 2.6399,
+      "train_samples_per_second": 69987.374,
+      "train_steps_per_second": 136.369
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 360,
+  "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": 9.572466247992345e+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:b301e81146294ca16fcad31b5b422906ba1c95be32b5089ec43f3d392b082116
+size 7416