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: c1_math_0d_1s_10k
+  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. -->
+
+# c1_math_0d_1s_10k
+
+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/c1_math_0d_1s_10k 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: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0a0+ecf3bae40a.nv25.01
+- 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": 4.992,
+    "total_flos": 1.878482348849234e+18,
+    "train_loss": 0.37849522767922816,
+    "train_runtime": 19752.9737,
+    "train_samples_per_second": 2.531,
+    "train_steps_per_second": 0.02
+}

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 sha256:9ec04332dbc523d13334781a16ee335f5bbc7b46628ecee5d9b3ea3f3bdadc1d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9266292dc8e1c9dbf808deea44bbac6e137cd0a20b733803089a63a9b606e029
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc9319158bfffd3305e68ffc38c13e356f9fb677b5386f148e8daede867f1d8
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507de59c7aca5e4c20cfe6915d34633e77a4d46828ce1ff8864a78fb7edfdf70
+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/Apr26_22-53-19_jpbot-001-33.jupiter.internal/events.out.tfevents.1745700840.jpbot-001-33.jupiter.internal.1165660.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66309813485fb093c63f9ec4acca7c970cc3b20f75a5baf8c44e6cc8bc534fe
+size 87654

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": "2025-04-26 22:53:19", "end_time": "2025-04-27 04:23:19"}

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": 4.992,
+    "total_flos": 1.878482348849234e+18,
+    "train_loss": 0.37849522767922816,
+    "train_runtime": 19752.9737,
+    "train_samples_per_second": 2.531,
+    "train_steps_per_second": 0.02
+}

trainer_log.jsonl

@@ -0,0 +1,391 @@
+{"current_steps": 1, "total_steps": 390, "loss": 0.8101, "lr": 1.0256410256410257e-06, "epoch": 0.0128, "percentage": 0.26, "elapsed_time": "0:00:57", "remaining_time": "6:11:15"}
+{"current_steps": 2, "total_steps": 390, "loss": 0.8184, "lr": 2.0512820512820513e-06, "epoch": 0.0256, "percentage": 0.51, "elapsed_time": "0:01:47", "remaining_time": "5:48:52"}
+{"current_steps": 3, "total_steps": 390, "loss": 0.7754, "lr": 3.0769230769230774e-06, "epoch": 0.0384, "percentage": 0.77, "elapsed_time": "0:02:39", "remaining_time": "5:43:00"}
+{"current_steps": 4, "total_steps": 390, "loss": 0.7871, "lr": 4.102564102564103e-06, "epoch": 0.0512, "percentage": 1.03, "elapsed_time": "0:03:29", "remaining_time": "5:37:20"}
+{"current_steps": 5, "total_steps": 390, "loss": 0.7527, "lr": 5.128205128205128e-06, "epoch": 0.064, "percentage": 1.28, "elapsed_time": "0:04:18", "remaining_time": "5:31:26"}
+{"current_steps": 6, "total_steps": 390, "loss": 0.7133, "lr": 6.153846153846155e-06, "epoch": 0.0768, "percentage": 1.54, "elapsed_time": "0:05:11", "remaining_time": "5:32:43"}
+{"current_steps": 7, "total_steps": 390, "loss": 0.7011, "lr": 7.17948717948718e-06, "epoch": 0.0896, "percentage": 1.79, "elapsed_time": "0:06:02", "remaining_time": "5:30:23"}
+{"current_steps": 8, "total_steps": 390, "loss": 0.7398, "lr": 8.205128205128205e-06, "epoch": 0.1024, "percentage": 2.05, "elapsed_time": "0:06:56", "remaining_time": "5:31:31"}
+{"current_steps": 9, "total_steps": 390, "loss": 0.7094, "lr": 9.230769230769232e-06, "epoch": 0.1152, "percentage": 2.31, "elapsed_time": "0:07:53", "remaining_time": "5:33:55"}
+{"current_steps": 10, "total_steps": 390, "loss": 0.6714, "lr": 1.0256410256410256e-05, "epoch": 0.128, "percentage": 2.56, "elapsed_time": "0:08:41", "remaining_time": "5:30:20"}
+{"current_steps": 11, "total_steps": 390, "loss": 0.6735, "lr": 1.1282051282051283e-05, "epoch": 0.1408, "percentage": 2.82, "elapsed_time": "0:09:30", "remaining_time": "5:27:49"}
+{"current_steps": 12, "total_steps": 390, "loss": 0.6446, "lr": 1.230769230769231e-05, "epoch": 0.1536, "percentage": 3.08, "elapsed_time": "0:10:20", "remaining_time": "5:25:33"}
+{"current_steps": 13, "total_steps": 390, "loss": 0.6465, "lr": 1.3333333333333333e-05, "epoch": 0.1664, "percentage": 3.33, "elapsed_time": "0:11:09", "remaining_time": "5:23:28"}
+{"current_steps": 14, "total_steps": 390, "loss": 0.6262, "lr": 1.435897435897436e-05, "epoch": 0.1792, "percentage": 3.59, "elapsed_time": "0:11:59", "remaining_time": "5:22:01"}
+{"current_steps": 15, "total_steps": 390, "loss": 0.6068, "lr": 1.5384615384615387e-05, "epoch": 0.192, "percentage": 3.85, "elapsed_time": "0:12:49", "remaining_time": "5:20:30"}
+{"current_steps": 16, "total_steps": 390, "loss": 0.598, "lr": 1.641025641025641e-05, "epoch": 0.2048, "percentage": 4.1, "elapsed_time": "0:13:38", "remaining_time": "5:18:47"}
+{"current_steps": 17, "total_steps": 390, "loss": 0.5589, "lr": 1.7435897435897438e-05, "epoch": 0.2176, "percentage": 4.36, "elapsed_time": "0:14:30", "remaining_time": "5:18:29"}
+{"current_steps": 18, "total_steps": 390, "loss": 0.5617, "lr": 1.8461538461538465e-05, "epoch": 0.2304, "percentage": 4.62, "elapsed_time": "0:15:22", "remaining_time": "5:17:44"}
+{"current_steps": 19, "total_steps": 390, "loss": 0.5718, "lr": 1.9487179487179488e-05, "epoch": 0.2432, "percentage": 4.87, "elapsed_time": "0:16:14", "remaining_time": "5:17:18"}
+{"current_steps": 20, "total_steps": 390, "loss": 0.5714, "lr": 2.0512820512820512e-05, "epoch": 0.256, "percentage": 5.13, "elapsed_time": "0:17:06", "remaining_time": "5:16:37"}
+{"current_steps": 21, "total_steps": 390, "loss": 0.5418, "lr": 2.153846153846154e-05, "epoch": 0.2688, "percentage": 5.38, "elapsed_time": "0:17:53", "remaining_time": "5:14:14"}
+{"current_steps": 22, "total_steps": 390, "loss": 0.5234, "lr": 2.2564102564102566e-05, "epoch": 0.2816, "percentage": 5.64, "elapsed_time": "0:18:41", "remaining_time": "5:12:46"}
+{"current_steps": 23, "total_steps": 390, "loss": 0.5356, "lr": 2.3589743589743593e-05, "epoch": 0.2944, "percentage": 5.9, "elapsed_time": "0:19:31", "remaining_time": "5:11:33"}
+{"current_steps": 24, "total_steps": 390, "loss": 0.5502, "lr": 2.461538461538462e-05, "epoch": 0.3072, "percentage": 6.15, "elapsed_time": "0:20:22", "remaining_time": "5:10:37"}
+{"current_steps": 25, "total_steps": 390, "loss": 0.5439, "lr": 2.5641025641025646e-05, "epoch": 0.32, "percentage": 6.41, "elapsed_time": "0:21:12", "remaining_time": "5:09:44"}
+{"current_steps": 26, "total_steps": 390, "loss": 0.5282, "lr": 2.6666666666666667e-05, "epoch": 0.3328, "percentage": 6.67, "elapsed_time": "0:22:03", "remaining_time": "5:08:52"}
+{"current_steps": 27, "total_steps": 390, "loss": 0.5066, "lr": 2.7692307692307694e-05, "epoch": 0.3456, "percentage": 6.92, "elapsed_time": "0:22:54", "remaining_time": "5:08:02"}
+{"current_steps": 28, "total_steps": 390, "loss": 0.505, "lr": 2.871794871794872e-05, "epoch": 0.3584, "percentage": 7.18, "elapsed_time": "0:23:45", "remaining_time": "5:07:05"}
+{"current_steps": 29, "total_steps": 390, "loss": 0.5077, "lr": 2.9743589743589747e-05, "epoch": 0.3712, "percentage": 7.44, "elapsed_time": "0:24:34", "remaining_time": "5:05:50"}
+{"current_steps": 30, "total_steps": 390, "loss": 0.5305, "lr": 3.0769230769230774e-05, "epoch": 0.384, "percentage": 7.69, "elapsed_time": "0:25:24", "remaining_time": "5:04:56"}
+{"current_steps": 31, "total_steps": 390, "loss": 0.504, "lr": 3.1794871794871795e-05, "epoch": 0.3968, "percentage": 7.95, "elapsed_time": "0:26:14", "remaining_time": "5:03:55"}
+{"current_steps": 32, "total_steps": 390, "loss": 0.5222, "lr": 3.282051282051282e-05, "epoch": 0.4096, "percentage": 8.21, "elapsed_time": "0:27:04", "remaining_time": "5:02:52"}
+{"current_steps": 33, "total_steps": 390, "loss": 0.5176, "lr": 3.384615384615385e-05, "epoch": 0.4224, "percentage": 8.46, "elapsed_time": "0:27:52", "remaining_time": "5:01:37"}
+{"current_steps": 34, "total_steps": 390, "loss": 0.5113, "lr": 3.4871794871794875e-05, "epoch": 0.4352, "percentage": 8.72, "elapsed_time": "0:28:43", "remaining_time": "5:00:46"}
+{"current_steps": 35, "total_steps": 390, "loss": 0.4983, "lr": 3.58974358974359e-05, "epoch": 0.448, "percentage": 8.97, "elapsed_time": "0:29:33", "remaining_time": "4:59:50"}
+{"current_steps": 36, "total_steps": 390, "loss": 0.5051, "lr": 3.692307692307693e-05, "epoch": 0.4608, "percentage": 9.23, "elapsed_time": "0:30:25", "remaining_time": "4:59:08"}
+{"current_steps": 37, "total_steps": 390, "loss": 0.4983, "lr": 3.794871794871795e-05, "epoch": 0.4736, "percentage": 9.49, "elapsed_time": "0:31:17", "remaining_time": "4:58:29"}
+{"current_steps": 38, "total_steps": 390, "loss": 0.4939, "lr": 3.8974358974358976e-05, "epoch": 0.4864, "percentage": 9.74, "elapsed_time": "0:32:07", "remaining_time": "4:57:37"}
+{"current_steps": 39, "total_steps": 390, "loss": 0.4896, "lr": 4e-05, "epoch": 0.4992, "percentage": 10.0, "elapsed_time": "0:32:58", "remaining_time": "4:56:46"}
+{"current_steps": 40, "total_steps": 390, "loss": 0.5069, "lr": 3.9999198907597046e-05, "epoch": 0.512, "percentage": 10.26, "elapsed_time": "0:33:46", "remaining_time": "4:55:27"}
+{"current_steps": 41, "total_steps": 390, "loss": 0.5082, "lr": 3.9996795694563096e-05, "epoch": 0.5248, "percentage": 10.51, "elapsed_time": "0:34:36", "remaining_time": "4:54:35"}
+{"current_steps": 42, "total_steps": 390, "loss": 0.4919, "lr": 3.999279055341771e-05, "epoch": 0.5376, "percentage": 10.77, "elapsed_time": "0:35:26", "remaining_time": "4:53:36"}
+{"current_steps": 43, "total_steps": 390, "loss": 0.4875, "lr": 3.998718380500971e-05, "epoch": 0.5504, "percentage": 11.03, "elapsed_time": "0:36:18", "remaining_time": "4:52:58"}
+{"current_steps": 44, "total_steps": 390, "loss": 0.4921, "lr": 3.997997589849145e-05, "epoch": 0.5632, "percentage": 11.28, "elapsed_time": "0:37:08", "remaining_time": "4:52:06"}
+{"current_steps": 45, "total_steps": 390, "loss": 0.48, "lr": 3.9971167411282835e-05, "epoch": 0.576, "percentage": 11.54, "elapsed_time": "0:37:59", "remaining_time": "4:51:14"}
+{"current_steps": 46, "total_steps": 390, "loss": 0.483, "lr": 3.99607590490251e-05, "epoch": 0.5888, "percentage": 11.79, "elapsed_time": "0:38:50", "remaining_time": "4:50:27"}
+{"current_steps": 47, "total_steps": 390, "loss": 0.4832, "lr": 3.9948751645524235e-05, "epoch": 0.6016, "percentage": 12.05, "elapsed_time": "0:39:41", "remaining_time": "4:49:38"}
+{"current_steps": 48, "total_steps": 390, "loss": 0.4853, "lr": 3.9935146162684206e-05, "epoch": 0.6144, "percentage": 12.31, "elapsed_time": "0:40:32", "remaining_time": "4:48:54"}
+{"current_steps": 49, "total_steps": 390, "loss": 0.5057, "lr": 3.9919943690429906e-05, "epoch": 0.6272, "percentage": 12.56, "elapsed_time": "0:41:21", "remaining_time": "4:47:46"}
+{"current_steps": 50, "total_steps": 390, "loss": 0.4802, "lr": 3.9903145446619837e-05, "epoch": 0.64, "percentage": 12.82, "elapsed_time": "0:42:10", "remaining_time": "4:46:44"}
+{"current_steps": 51, "total_steps": 390, "loss": 0.4769, "lr": 3.9884752776948564e-05, "epoch": 0.6528, "percentage": 13.08, "elapsed_time": "0:43:00", "remaining_time": "4:45:52"}
+{"current_steps": 52, "total_steps": 390, "loss": 0.4522, "lr": 3.9864767154838864e-05, "epoch": 0.6656, "percentage": 13.33, "elapsed_time": "0:43:52", "remaining_time": "4:45:13"}
+{"current_steps": 53, "total_steps": 390, "loss": 0.4782, "lr": 3.9843190181323744e-05, "epoch": 0.6784, "percentage": 13.59, "elapsed_time": "0:44:42", "remaining_time": "4:44:16"}
+{"current_steps": 54, "total_steps": 390, "loss": 0.4712, "lr": 3.982002358491817e-05, "epoch": 0.6912, "percentage": 13.85, "elapsed_time": "0:45:32", "remaining_time": "4:43:23"}
+{"current_steps": 55, "total_steps": 390, "loss": 0.4581, "lr": 3.979526922148058e-05, "epoch": 0.704, "percentage": 14.1, "elapsed_time": "0:46:22", "remaining_time": "4:42:28"}
+{"current_steps": 56, "total_steps": 390, "loss": 0.479, "lr": 3.9768929074064206e-05, "epoch": 0.7168, "percentage": 14.36, "elapsed_time": "0:47:09", "remaining_time": "4:41:15"}
+{"current_steps": 57, "total_steps": 390, "loss": 0.4743, "lr": 3.9741005252758255e-05, "epoch": 0.7296, "percentage": 14.62, "elapsed_time": "0:47:58", "remaining_time": "4:40:18"}
+{"current_steps": 58, "total_steps": 390, "loss": 0.4823, "lr": 3.971149999451886e-05, "epoch": 0.7424, "percentage": 14.87, "elapsed_time": "0:48:49", "remaining_time": "4:39:30"}
+{"current_steps": 59, "total_steps": 390, "loss": 0.4679, "lr": 3.9680415662989806e-05, "epoch": 0.7552, "percentage": 15.13, "elapsed_time": "0:49:36", "remaining_time": "4:38:19"}
+{"current_steps": 60, "total_steps": 390, "loss": 0.4775, "lr": 3.9647754748313294e-05, "epoch": 0.768, "percentage": 15.38, "elapsed_time": "0:50:24", "remaining_time": "4:37:16"}
+{"current_steps": 61, "total_steps": 390, "loss": 0.4578, "lr": 3.96135198669304e-05, "epoch": 0.7808, "percentage": 15.64, "elapsed_time": "0:51:16", "remaining_time": "4:36:34"}
+{"current_steps": 62, "total_steps": 390, "loss": 0.4624, "lr": 3.957771376137144e-05, "epoch": 0.7936, "percentage": 15.9, "elapsed_time": "0:52:06", "remaining_time": "4:35:37"}
+{"current_steps": 63, "total_steps": 390, "loss": 0.4623, "lr": 3.954033930003634e-05, "epoch": 0.8064, "percentage": 16.15, "elapsed_time": "0:52:53", "remaining_time": "4:34:34"}
+{"current_steps": 64, "total_steps": 390, "loss": 0.4698, "lr": 3.9501399476964806e-05, "epoch": 0.8192, "percentage": 16.41, "elapsed_time": "0:53:44", "remaining_time": "4:33:47"}
+{"current_steps": 65, "total_steps": 390, "loss": 0.4641, "lr": 3.946089741159648e-05, "epoch": 0.832, "percentage": 16.67, "elapsed_time": "0:54:36", "remaining_time": "4:33:00"}
+{"current_steps": 66, "total_steps": 390, "loss": 0.458, "lr": 3.9418836348521045e-05, "epoch": 0.8448, "percentage": 16.92, "elapsed_time": "0:55:26", "remaining_time": "4:32:08"}
+{"current_steps": 67, "total_steps": 390, "loss": 0.4732, "lr": 3.937521965721831e-05, "epoch": 0.8576, "percentage": 17.18, "elapsed_time": "0:56:15", "remaining_time": "4:31:10"}
+{"current_steps": 68, "total_steps": 390, "loss": 0.4667, "lr": 3.933005083178828e-05, "epoch": 0.8704, "percentage": 17.44, "elapsed_time": "0:57:02", "remaining_time": "4:30:08"}
+{"current_steps": 69, "total_steps": 390, "loss": 0.4756, "lr": 3.928333349067125e-05, "epoch": 0.8832, "percentage": 17.69, "elapsed_time": "0:57:55", "remaining_time": "4:29:30"}
+{"current_steps": 70, "total_steps": 390, "loss": 0.4711, "lr": 3.923507137635792e-05, "epoch": 0.896, "percentage": 17.95, "elapsed_time": "0:58:46", "remaining_time": "4:28:39"}
+{"current_steps": 71, "total_steps": 390, "loss": 0.4664, "lr": 3.9185268355089606e-05, "epoch": 0.9088, "percentage": 18.21, "elapsed_time": "0:59:36", "remaining_time": "4:27:49"}
+{"current_steps": 72, "total_steps": 390, "loss": 0.4708, "lr": 3.913392841654851e-05, "epoch": 0.9216, "percentage": 18.46, "elapsed_time": "1:00:26", "remaining_time": "4:26:57"}
+{"current_steps": 73, "total_steps": 390, "loss": 0.465, "lr": 3.9081055673538093e-05, "epoch": 0.9344, "percentage": 18.72, "elapsed_time": "1:01:20", "remaining_time": "4:26:21"}
+{"current_steps": 74, "total_steps": 390, "loss": 0.4645, "lr": 3.902665436165364e-05, "epoch": 0.9472, "percentage": 18.97, "elapsed_time": "1:02:09", "remaining_time": "4:25:27"}
+{"current_steps": 75, "total_steps": 390, "loss": 0.4456, "lr": 3.897072883894291e-05, "epoch": 0.96, "percentage": 19.23, "elapsed_time": "1:03:00", "remaining_time": "4:24:37"}
+{"current_steps": 76, "total_steps": 390, "loss": 0.4566, "lr": 3.8913283585557054e-05, "epoch": 0.9728, "percentage": 19.49, "elapsed_time": "1:03:50", "remaining_time": "4:23:46"}
+{"current_steps": 77, "total_steps": 390, "loss": 0.4743, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "1:04:40", "remaining_time": "4:22:52"}
+{"current_steps": 78, "total_steps": 390, "loss": 0.4686, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "1:05:28", "remaining_time": "4:21:54"}
+{"current_steps": 79, "total_steps": 390, "loss": 0.8511, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "1:06:52", "remaining_time": "4:23:17"}
+{"current_steps": 80, "total_steps": 390, "loss": 0.4321, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "1:07:42", "remaining_time": "4:22:23"}
+{"current_steps": 81, "total_steps": 390, "loss": 0.4286, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "1:08:32", "remaining_time": "4:21:27"}
+{"current_steps": 82, "total_steps": 390, "loss": 0.436, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "1:09:24", "remaining_time": "4:20:40"}
+{"current_steps": 83, "total_steps": 390, "loss": 0.4344, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "1:10:14", "remaining_time": "4:19:49"}
+{"current_steps": 84, "total_steps": 390, "loss": 0.4135, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "1:11:05", "remaining_time": "4:18:57"}
+{"current_steps": 85, "total_steps": 390, "loss": 0.4383, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "1:11:55", "remaining_time": "4:18:05"}
+{"current_steps": 86, "total_steps": 390, "loss": 0.4189, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "1:12:42", "remaining_time": "4:17:00"}
+{"current_steps": 87, "total_steps": 390, "loss": 0.4287, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "1:13:31", "remaining_time": "4:16:04"}
+{"current_steps": 88, "total_steps": 390, "loss": 0.4251, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "1:14:19", "remaining_time": "4:15:04"}
+{"current_steps": 89, "total_steps": 390, "loss": 0.4362, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "1:15:10", "remaining_time": "4:14:15"}
+{"current_steps": 90, "total_steps": 390, "loss": 0.4143, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "1:15:56", "remaining_time": "4:13:08"}
+{"current_steps": 91, "total_steps": 390, "loss": 0.4194, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "1:16:47", "remaining_time": "4:12:20"}
+{"current_steps": 92, "total_steps": 390, "loss": 0.4272, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "1:17:38", "remaining_time": "4:11:29"}
+{"current_steps": 93, "total_steps": 390, "loss": 0.4174, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "1:18:28", "remaining_time": "4:10:36"}
+{"current_steps": 94, "total_steps": 390, "loss": 0.4152, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "1:19:20", "remaining_time": "4:09:49"}
+{"current_steps": 95, "total_steps": 390, "loss": 0.4239, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "1:20:10", "remaining_time": "4:08:56"}
+{"current_steps": 96, "total_steps": 390, "loss": 0.4216, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "1:21:01", "remaining_time": "4:08:09"}
+{"current_steps": 97, "total_steps": 390, "loss": 0.4365, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "1:21:49", "remaining_time": "4:07:11"}
+{"current_steps": 98, "total_steps": 390, "loss": 0.4124, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "1:22:36", "remaining_time": "4:06:09"}
+{"current_steps": 99, "total_steps": 390, "loss": 0.4282, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "1:23:25", "remaining_time": "4:05:12"}
+{"current_steps": 100, "total_steps": 390, "loss": 0.4184, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "1:24:15", "remaining_time": "4:04:19"}
+{"current_steps": 101, "total_steps": 390, "loss": 0.4099, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "1:25:05", "remaining_time": "4:03:27"}
+{"current_steps": 102, "total_steps": 390, "loss": 0.4285, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "1:25:53", "remaining_time": "4:02:31"}
+{"current_steps": 103, "total_steps": 390, "loss": 0.4214, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "1:26:44", "remaining_time": "4:01:41"}
+{"current_steps": 104, "total_steps": 390, "loss": 0.41, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "1:27:33", "remaining_time": "4:00:47"}
+{"current_steps": 105, "total_steps": 390, "loss": 0.4133, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "1:28:23", "remaining_time": "3:59:55"}
+{"current_steps": 106, "total_steps": 390, "loss": 0.4142, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "1:29:13", "remaining_time": "3:59:02"}
+{"current_steps": 107, "total_steps": 390, "loss": 0.4241, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "1:30:01", "remaining_time": "3:58:05"}
+{"current_steps": 108, "total_steps": 390, "loss": 0.4134, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "1:30:52", "remaining_time": "3:57:17"}
+{"current_steps": 109, "total_steps": 390, "loss": 0.4156, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "1:31:42", "remaining_time": "3:56:25"}
+{"current_steps": 110, "total_steps": 390, "loss": 0.4162, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "1:32:31", "remaining_time": "3:55:30"}
+{"current_steps": 111, "total_steps": 390, "loss": 0.4065, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "1:33:21", "remaining_time": "3:54:38"}
+{"current_steps": 112, "total_steps": 390, "loss": 0.426, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "1:34:11", "remaining_time": "3:53:47"}
+{"current_steps": 113, "total_steps": 390, "loss": 0.4058, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "1:35:00", "remaining_time": "3:52:53"}
+{"current_steps": 114, "total_steps": 390, "loss": 0.4117, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "1:35:50", "remaining_time": "3:52:02"}
+{"current_steps": 115, "total_steps": 390, "loss": 0.4233, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "1:36:41", "remaining_time": "3:51:13"}
+{"current_steps": 116, "total_steps": 390, "loss": 0.3932, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "1:37:29", "remaining_time": "3:50:17"}
+{"current_steps": 117, "total_steps": 390, "loss": 0.4104, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "1:38:20", "remaining_time": "3:49:27"}
+{"current_steps": 118, "total_steps": 390, "loss": 0.4311, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "1:39:11", "remaining_time": "3:48:38"}
+{"current_steps": 119, "total_steps": 390, "loss": 0.3961, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "1:40:00", "remaining_time": "3:47:44"}
+{"current_steps": 120, "total_steps": 390, "loss": 0.4145, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "1:40:48", "remaining_time": "3:46:49"}
+{"current_steps": 121, "total_steps": 390, "loss": 0.4176, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "1:41:41", "remaining_time": "3:46:05"}
+{"current_steps": 122, "total_steps": 390, "loss": 0.4267, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "1:42:30", "remaining_time": "3:45:11"}
+{"current_steps": 123, "total_steps": 390, "loss": 0.4094, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "1:43:18", "remaining_time": "3:44:15"}
+{"current_steps": 124, "total_steps": 390, "loss": 0.4258, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "1:44:10", "remaining_time": "3:43:27"}
+{"current_steps": 125, "total_steps": 390, "loss": 0.4215, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "1:45:00", "remaining_time": "3:42:37"}
+{"current_steps": 126, "total_steps": 390, "loss": 0.3974, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "1:45:51", "remaining_time": "3:41:47"}
+{"current_steps": 127, "total_steps": 390, "loss": 0.4052, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "1:46:40", "remaining_time": "3:40:55"}
+{"current_steps": 128, "total_steps": 390, "loss": 0.4034, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "1:47:26", "remaining_time": "3:39:55"}
+{"current_steps": 129, "total_steps": 390, "loss": 0.4123, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "1:48:16", "remaining_time": "3:39:04"}
+{"current_steps": 130, "total_steps": 390, "loss": 0.4078, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "1:49:04", "remaining_time": "3:38:08"}
+{"current_steps": 131, "total_steps": 390, "loss": 0.4159, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "1:49:54", "remaining_time": "3:37:17"}
+{"current_steps": 132, "total_steps": 390, "loss": 0.4161, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "1:50:46", "remaining_time": "3:36:31"}
+{"current_steps": 133, "total_steps": 390, "loss": 0.4053, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "1:51:38", "remaining_time": "3:35:43"}
+{"current_steps": 134, "total_steps": 390, "loss": 0.423, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "1:52:27", "remaining_time": "3:34:51"}
+{"current_steps": 135, "total_steps": 390, "loss": 0.4131, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "1:53:19", "remaining_time": "3:34:03"}
+{"current_steps": 136, "total_steps": 390, "loss": 0.4098, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "1:54:11", "remaining_time": "3:33:16"}
+{"current_steps": 137, "total_steps": 390, "loss": 0.4018, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "1:55:01", "remaining_time": "3:32:25"}
+{"current_steps": 138, "total_steps": 390, "loss": 0.4194, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "1:55:49", "remaining_time": "3:31:31"}
+{"current_steps": 139, "total_steps": 390, "loss": 0.4087, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "1:56:40", "remaining_time": "3:30:41"}
+{"current_steps": 140, "total_steps": 390, "loss": 0.4213, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "1:57:31", "remaining_time": "3:29:51"}
+{"current_steps": 141, "total_steps": 390, "loss": 0.4124, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "1:58:21", "remaining_time": "3:29:00"}
+{"current_steps": 142, "total_steps": 390, "loss": 0.411, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "1:59:12", "remaining_time": "3:28:12"}
+{"current_steps": 143, "total_steps": 390, "loss": 0.4093, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "2:00:02", "remaining_time": "3:27:20"}
+{"current_steps": 144, "total_steps": 390, "loss": 0.4213, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "2:00:53", "remaining_time": "3:26:30"}
+{"current_steps": 145, "total_steps": 390, "loss": 0.4219, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "2:01:43", "remaining_time": "3:25:40"}
+{"current_steps": 146, "total_steps": 390, "loss": 0.3926, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "2:02:31", "remaining_time": "3:24:46"}
+{"current_steps": 147, "total_steps": 390, "loss": 0.4096, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "2:03:18", "remaining_time": "3:23:50"}
+{"current_steps": 148, "total_steps": 390, "loss": 0.4177, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "2:04:06", "remaining_time": "3:22:55"}
+{"current_steps": 149, "total_steps": 390, "loss": 0.4055, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "2:04:58", "remaining_time": "3:22:08"}
+{"current_steps": 150, "total_steps": 390, "loss": 0.4236, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "2:05:46", "remaining_time": "3:21:14"}
+{"current_steps": 151, "total_steps": 390, "loss": 0.4006, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "2:06:37", "remaining_time": "3:20:24"}
+{"current_steps": 152, "total_steps": 390, "loss": 0.402, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "2:07:26", "remaining_time": "3:19:32"}
+{"current_steps": 153, "total_steps": 390, "loss": 0.421, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "2:08:15", "remaining_time": "3:18:40"}
+{"current_steps": 154, "total_steps": 390, "loss": 0.3982, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "2:09:06", "remaining_time": "3:17:51"}
+{"current_steps": 155, "total_steps": 390, "loss": 0.4026, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "2:09:56", "remaining_time": "3:17:01"}
+{"current_steps": 156, "total_steps": 390, "loss": 0.4276, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "2:10:47", "remaining_time": "3:16:10"}
+{"current_steps": 157, "total_steps": 390, "loss": 0.7805, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "2:12:14", "remaining_time": "3:16:14"}
+{"current_steps": 158, "total_steps": 390, "loss": 0.3596, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "2:13:02", "remaining_time": "3:15:21"}
+{"current_steps": 159, "total_steps": 390, "loss": 0.3473, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "2:13:53", "remaining_time": "3:14:30"}
+{"current_steps": 160, "total_steps": 390, "loss": 0.3838, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "2:14:45", "remaining_time": "3:13:42"}
+{"current_steps": 161, "total_steps": 390, "loss": 0.3502, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "2:15:32", "remaining_time": "3:12:47"}
+{"current_steps": 162, "total_steps": 390, "loss": 0.3758, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "2:16:22", "remaining_time": "3:11:56"}
+{"current_steps": 163, "total_steps": 390, "loss": 0.3532, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "2:17:11", "remaining_time": "3:11:03"}
+{"current_steps": 164, "total_steps": 390, "loss": 0.3581, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "2:17:59", "remaining_time": "3:10:09"}
+{"current_steps": 165, "total_steps": 390, "loss": 0.3688, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "2:18:48", "remaining_time": "3:09:16"}
+{"current_steps": 166, "total_steps": 390, "loss": 0.375, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "2:19:40", "remaining_time": "3:08:28"}
+{"current_steps": 167, "total_steps": 390, "loss": 0.3646, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "2:20:30", "remaining_time": "3:07:37"}
+{"current_steps": 168, "total_steps": 390, "loss": 0.3531, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "2:21:21", "remaining_time": "3:06:48"}
+{"current_steps": 169, "total_steps": 390, "loss": 0.3694, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "2:22:12", "remaining_time": "3:05:57"}
+{"current_steps": 170, "total_steps": 390, "loss": 0.3507, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "2:23:01", "remaining_time": "3:05:05"}
+{"current_steps": 171, "total_steps": 390, "loss": 0.3602, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "2:23:52", "remaining_time": "3:04:15"}
+{"current_steps": 172, "total_steps": 390, "loss": 0.3565, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "2:24:43", "remaining_time": "3:03:25"}
+{"current_steps": 173, "total_steps": 390, "loss": 0.3689, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "2:25:28", "remaining_time": "3:02:29"}
+{"current_steps": 174, "total_steps": 390, "loss": 0.3569, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "2:26:20", "remaining_time": "3:01:39"}
+{"current_steps": 175, "total_steps": 390, "loss": 0.3627, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "2:27:12", "remaining_time": "3:00:51"}
+{"current_steps": 176, "total_steps": 390, "loss": 0.3625, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "2:28:03", "remaining_time": "3:00:01"}
+{"current_steps": 177, "total_steps": 390, "loss": 0.3495, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "2:28:51", "remaining_time": "2:59:08"}
+{"current_steps": 178, "total_steps": 390, "loss": 0.3499, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "2:29:40", "remaining_time": "2:58:16"}
+{"current_steps": 179, "total_steps": 390, "loss": 0.3718, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "2:30:31", "remaining_time": "2:57:26"}
+{"current_steps": 180, "total_steps": 390, "loss": 0.3462, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "2:31:23", "remaining_time": "2:56:37"}
+{"current_steps": 181, "total_steps": 390, "loss": 0.362, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "2:32:13", "remaining_time": "2:55:46"}
+{"current_steps": 182, "total_steps": 390, "loss": 0.3488, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "2:33:02", "remaining_time": "2:54:54"}
+{"current_steps": 183, "total_steps": 390, "loss": 0.3574, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "2:33:54", "remaining_time": "2:54:05"}
+{"current_steps": 184, "total_steps": 390, "loss": 0.339, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "2:34:42", "remaining_time": "2:53:11"}
+{"current_steps": 185, "total_steps": 390, "loss": 0.3541, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "2:35:30", "remaining_time": "2:52:18"}
+{"current_steps": 186, "total_steps": 390, "loss": 0.355, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "2:36:21", "remaining_time": "2:51:29"}
+{"current_steps": 187, "total_steps": 390, "loss": 0.3391, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "2:37:10", "remaining_time": "2:50:37"}
+{"current_steps": 188, "total_steps": 390, "loss": 0.3687, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "2:38:00", "remaining_time": "2:49:46"}
+{"current_steps": 189, "total_steps": 390, "loss": 0.3417, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "2:38:51", "remaining_time": "2:48:56"}
+{"current_steps": 190, "total_steps": 390, "loss": 0.3563, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "2:39:40", "remaining_time": "2:48:04"}
+{"current_steps": 191, "total_steps": 390, "loss": 0.3542, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "2:40:28", "remaining_time": "2:47:11"}
+{"current_steps": 192, "total_steps": 390, "loss": 0.3671, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "2:41:21", "remaining_time": "2:46:24"}
+{"current_steps": 193, "total_steps": 390, "loss": 0.3586, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "2:42:11", "remaining_time": "2:45:32"}
+{"current_steps": 194, "total_steps": 390, "loss": 0.3437, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "2:43:02", "remaining_time": "2:44:43"}
+{"current_steps": 195, "total_steps": 390, "loss": 0.3555, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "2:43:51", "remaining_time": "2:43:51"}
+{"current_steps": 196, "total_steps": 390, "loss": 0.3462, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "2:44:40", "remaining_time": "2:42:59"}
+{"current_steps": 197, "total_steps": 390, "loss": 0.3551, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "2:45:30", "remaining_time": "2:42:08"}
+{"current_steps": 198, "total_steps": 390, "loss": 0.3642, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "2:46:23", "remaining_time": "2:41:21"}
+{"current_steps": 199, "total_steps": 390, "loss": 0.3478, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "2:47:12", "remaining_time": "2:40:29"}
+{"current_steps": 200, "total_steps": 390, "loss": 0.3601, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "2:48:02", "remaining_time": "2:39:38"}
+{"current_steps": 201, "total_steps": 390, "loss": 0.3635, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "2:48:53", "remaining_time": "2:38:48"}
+{"current_steps": 202, "total_steps": 390, "loss": 0.3498, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "2:49:42", "remaining_time": "2:37:56"}
+{"current_steps": 203, "total_steps": 390, "loss": 0.3544, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "2:50:35", "remaining_time": "2:37:08"}
+{"current_steps": 204, "total_steps": 390, "loss": 0.3425, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "2:51:25", "remaining_time": "2:36:17"}
+{"current_steps": 205, "total_steps": 390, "loss": 0.3563, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "2:52:14", "remaining_time": "2:35:25"}
+{"current_steps": 206, "total_steps": 390, "loss": 0.3729, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "2:53:03", "remaining_time": "2:34:34"}
+{"current_steps": 207, "total_steps": 390, "loss": 0.3619, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "2:53:53", "remaining_time": "2:33:44"}
+{"current_steps": 208, "total_steps": 390, "loss": 0.361, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "2:54:45", "remaining_time": "2:32:54"}
+{"current_steps": 209, "total_steps": 390, "loss": 0.3456, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "2:55:34", "remaining_time": "2:32:03"}
+{"current_steps": 210, "total_steps": 390, "loss": 0.3603, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "2:56:24", "remaining_time": "2:31:12"}
+{"current_steps": 211, "total_steps": 390, "loss": 0.3602, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "2:57:14", "remaining_time": "2:30:21"}
+{"current_steps": 212, "total_steps": 390, "loss": 0.3531, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "2:58:04", "remaining_time": "2:29:30"}
+{"current_steps": 213, "total_steps": 390, "loss": 0.361, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "2:58:55", "remaining_time": "2:28:40"}
+{"current_steps": 214, "total_steps": 390, "loss": 0.3344, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "2:59:43", "remaining_time": "2:27:48"}
+{"current_steps": 215, "total_steps": 390, "loss": 0.365, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "3:00:35", "remaining_time": "2:26:59"}
+{"current_steps": 216, "total_steps": 390, "loss": 0.3591, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "3:01:21", "remaining_time": "2:26:05"}
+{"current_steps": 217, "total_steps": 390, "loss": 0.3625, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "3:02:10", "remaining_time": "2:25:14"}
+{"current_steps": 218, "total_steps": 390, "loss": 0.3493, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "3:03:00", "remaining_time": "2:24:23"}
+{"current_steps": 219, "total_steps": 390, "loss": 0.3583, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "3:03:50", "remaining_time": "2:23:32"}
+{"current_steps": 220, "total_steps": 390, "loss": 0.3605, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "3:04:41", "remaining_time": "2:22:42"}
+{"current_steps": 221, "total_steps": 390, "loss": 0.3464, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "3:05:30", "remaining_time": "2:21:51"}
+{"current_steps": 222, "total_steps": 390, "loss": 0.3703, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "3:06:20", "remaining_time": "2:21:01"}
+{"current_steps": 223, "total_steps": 390, "loss": 0.3502, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "3:07:11", "remaining_time": "2:20:10"}
+{"current_steps": 224, "total_steps": 390, "loss": 0.3573, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "3:08:00", "remaining_time": "2:19:19"}
+{"current_steps": 225, "total_steps": 390, "loss": 0.342, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "3:08:51", "remaining_time": "2:18:29"}
+{"current_steps": 226, "total_steps": 390, "loss": 0.355, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "3:09:41", "remaining_time": "2:17:39"}
+{"current_steps": 227, "total_steps": 390, "loss": 0.3335, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "3:10:31", "remaining_time": "2:16:48"}
+{"current_steps": 228, "total_steps": 390, "loss": 0.349, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "3:11:18", "remaining_time": "2:15:56"}
+{"current_steps": 229, "total_steps": 390, "loss": 0.3525, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "3:12:10", "remaining_time": "2:15:06"}
+{"current_steps": 230, "total_steps": 390, "loss": 0.3291, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "3:12:57", "remaining_time": "2:14:13"}
+{"current_steps": 231, "total_steps": 390, "loss": 0.3561, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "3:13:46", "remaining_time": "2:13:22"}
+{"current_steps": 232, "total_steps": 390, "loss": 0.3548, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "3:14:38", "remaining_time": "2:12:33"}
+{"current_steps": 233, "total_steps": 390, "loss": 0.3594, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "3:15:26", "remaining_time": "2:11:41"}
+{"current_steps": 234, "total_steps": 390, "loss": 0.3589, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "3:16:17", "remaining_time": "2:10:51"}
+{"current_steps": 235, "total_steps": 390, "loss": 0.6686, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "3:17:37", "remaining_time": "2:10:20"}
+{"current_steps": 236, "total_steps": 390, "loss": 0.297, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "3:18:24", "remaining_time": "2:09:28"}
+{"current_steps": 237, "total_steps": 390, "loss": 0.2975, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "3:19:13", "remaining_time": "2:08:37"}
+{"current_steps": 238, "total_steps": 390, "loss": 0.3079, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "3:20:03", "remaining_time": "2:07:45"}
+{"current_steps": 239, "total_steps": 390, "loss": 0.2912, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "3:20:53", "remaining_time": "2:06:55"}
+{"current_steps": 240, "total_steps": 390, "loss": 0.3029, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "3:21:42", "remaining_time": "2:06:04"}
+{"current_steps": 241, "total_steps": 390, "loss": 0.2984, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "3:22:32", "remaining_time": "2:05:13"}
+{"current_steps": 242, "total_steps": 390, "loss": 0.3022, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "3:23:23", "remaining_time": "2:04:23"}
+{"current_steps": 243, "total_steps": 390, "loss": 0.3022, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "3:24:15", "remaining_time": "2:03:34"}
+{"current_steps": 244, "total_steps": 390, "loss": 0.3007, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "3:25:06", "remaining_time": "2:02:43"}
+{"current_steps": 245, "total_steps": 390, "loss": 0.3009, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "3:25:51", "remaining_time": "2:01:50"}
+{"current_steps": 246, "total_steps": 390, "loss": 0.293, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "3:26:41", "remaining_time": "2:00:59"}
+{"current_steps": 247, "total_steps": 390, "loss": 0.2941, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "3:27:33", "remaining_time": "2:00:09"}
+{"current_steps": 248, "total_steps": 390, "loss": 0.3075, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "3:28:24", "remaining_time": "1:59:19"}
+{"current_steps": 249, "total_steps": 390, "loss": 0.3057, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "3:29:16", "remaining_time": "1:58:30"}
+{"current_steps": 250, "total_steps": 390, "loss": 0.2841, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "3:30:06", "remaining_time": "1:57:39"}
+{"current_steps": 251, "total_steps": 390, "loss": 0.3005, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "3:30:57", "remaining_time": "1:56:49"}
+{"current_steps": 252, "total_steps": 390, "loss": 0.2963, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "3:31:46", "remaining_time": "1:55:58"}
+{"current_steps": 253, "total_steps": 390, "loss": 0.3163, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "3:32:37", "remaining_time": "1:55:08"}
+{"current_steps": 254, "total_steps": 390, "loss": 0.3098, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "3:33:28", "remaining_time": "1:54:18"}
+{"current_steps": 255, "total_steps": 390, "loss": 0.3036, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "3:34:17", "remaining_time": "1:53:27"}
+{"current_steps": 256, "total_steps": 390, "loss": 0.3097, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "3:35:04", "remaining_time": "1:52:34"}
+{"current_steps": 257, "total_steps": 390, "loss": 0.2943, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "3:35:51", "remaining_time": "1:51:42"}
+{"current_steps": 258, "total_steps": 390, "loss": 0.2975, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "3:36:43", "remaining_time": "1:50:52"}
+{"current_steps": 259, "total_steps": 390, "loss": 0.2985, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "3:37:32", "remaining_time": "1:50:02"}
+{"current_steps": 260, "total_steps": 390, "loss": 0.3193, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "3:38:23", "remaining_time": "1:49:11"}
+{"current_steps": 261, "total_steps": 390, "loss": 0.2978, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "3:39:12", "remaining_time": "1:48:20"}
+{"current_steps": 262, "total_steps": 390, "loss": 0.2993, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "3:40:02", "remaining_time": "1:47:29"}
+{"current_steps": 263, "total_steps": 390, "loss": 0.301, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "3:40:52", "remaining_time": "1:46:39"}
+{"current_steps": 264, "total_steps": 390, "loss": 0.2919, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "3:41:42", "remaining_time": "1:45:48"}
+{"current_steps": 265, "total_steps": 390, "loss": 0.2917, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "3:42:31", "remaining_time": "1:44:57"}
+{"current_steps": 266, "total_steps": 390, "loss": 0.3012, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "3:43:21", "remaining_time": "1:44:07"}
+{"current_steps": 267, "total_steps": 390, "loss": 0.2919, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "3:44:12", "remaining_time": "1:43:17"}
+{"current_steps": 268, "total_steps": 390, "loss": 0.3048, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "3:45:03", "remaining_time": "1:42:27"}
+{"current_steps": 269, "total_steps": 390, "loss": 0.2888, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "3:45:53", "remaining_time": "1:41:36"}
+{"current_steps": 270, "total_steps": 390, "loss": 0.3008, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "3:46:43", "remaining_time": "1:40:46"}
+{"current_steps": 271, "total_steps": 390, "loss": 0.3117, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "3:47:35", "remaining_time": "1:39:56"}
+{"current_steps": 272, "total_steps": 390, "loss": 0.2978, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "3:48:25", "remaining_time": "1:39:05"}
+{"current_steps": 273, "total_steps": 390, "loss": 0.3022, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "3:49:15", "remaining_time": "1:38:15"}
+{"current_steps": 274, "total_steps": 390, "loss": 0.2898, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "3:50:03", "remaining_time": "1:37:23"}
+{"current_steps": 275, "total_steps": 390, "loss": 0.299, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "3:50:53", "remaining_time": "1:36:33"}
+{"current_steps": 276, "total_steps": 390, "loss": 0.2992, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "3:51:42", "remaining_time": "1:35:42"}
+{"current_steps": 277, "total_steps": 390, "loss": 0.3204, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "3:52:33", "remaining_time": "1:34:52"}
+{"current_steps": 278, "total_steps": 390, "loss": 0.3043, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "3:53:23", "remaining_time": "1:34:01"}
+{"current_steps": 279, "total_steps": 390, "loss": 0.2974, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "3:54:15", "remaining_time": "1:33:12"}
+{"current_steps": 280, "total_steps": 390, "loss": 0.3005, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "3:55:05", "remaining_time": "1:32:21"}
+{"current_steps": 281, "total_steps": 390, "loss": 0.3011, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "3:55:52", "remaining_time": "1:31:29"}
+{"current_steps": 282, "total_steps": 390, "loss": 0.3023, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "3:56:44", "remaining_time": "1:30:39"}
+{"current_steps": 283, "total_steps": 390, "loss": 0.2984, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "3:57:32", "remaining_time": "1:29:48"}
+{"current_steps": 284, "total_steps": 390, "loss": 0.3003, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "3:58:23", "remaining_time": "1:28:58"}
+{"current_steps": 285, "total_steps": 390, "loss": 0.3051, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "3:59:14", "remaining_time": "1:28:08"}
+{"current_steps": 286, "total_steps": 390, "loss": 0.288, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "4:00:04", "remaining_time": "1:27:17"}
+{"current_steps": 287, "total_steps": 390, "loss": 0.2992, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "4:00:53", "remaining_time": "1:26:27"}
+{"current_steps": 288, "total_steps": 390, "loss": 0.3007, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "4:01:41", "remaining_time": "1:25:35"}
+{"current_steps": 289, "total_steps": 390, "loss": 0.2986, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "4:02:31", "remaining_time": "1:24:45"}
+{"current_steps": 290, "total_steps": 390, "loss": 0.2961, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "4:03:21", "remaining_time": "1:23:55"}
+{"current_steps": 291, "total_steps": 390, "loss": 0.3115, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "4:04:11", "remaining_time": "1:23:04"}
+{"current_steps": 292, "total_steps": 390, "loss": 0.2981, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "4:04:59", "remaining_time": "1:22:13"}
+{"current_steps": 293, "total_steps": 390, "loss": 0.2912, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "4:05:48", "remaining_time": "1:21:22"}
+{"current_steps": 294, "total_steps": 390, "loss": 0.298, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "4:06:37", "remaining_time": "1:20:31"}
+{"current_steps": 295, "total_steps": 390, "loss": 0.2956, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "4:07:28", "remaining_time": "1:19:41"}
+{"current_steps": 296, "total_steps": 390, "loss": 0.3166, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "4:08:18", "remaining_time": "1:18:51"}
+{"current_steps": 297, "total_steps": 390, "loss": 0.2968, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "4:09:11", "remaining_time": "1:18:01"}
+{"current_steps": 298, "total_steps": 390, "loss": 0.3072, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "4:10:01", "remaining_time": "1:17:11"}
+{"current_steps": 299, "total_steps": 390, "loss": 0.2936, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "4:10:53", "remaining_time": "1:16:21"}
+{"current_steps": 300, "total_steps": 390, "loss": 0.3086, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "4:11:43", "remaining_time": "1:15:31"}
+{"current_steps": 301, "total_steps": 390, "loss": 0.2963, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "4:12:33", "remaining_time": "1:14:40"}
+{"current_steps": 302, "total_steps": 390, "loss": 0.289, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "4:13:25", "remaining_time": "1:13:50"}
+{"current_steps": 303, "total_steps": 390, "loss": 0.2941, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "4:14:16", "remaining_time": "1:13:00"}
+{"current_steps": 304, "total_steps": 390, "loss": 0.2986, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "4:15:05", "remaining_time": "1:12:09"}
+{"current_steps": 305, "total_steps": 390, "loss": 0.3042, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "4:15:52", "remaining_time": "1:11:18"}
+{"current_steps": 306, "total_steps": 390, "loss": 0.2986, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "4:16:43", "remaining_time": "1:10:28"}
+{"current_steps": 307, "total_steps": 390, "loss": 0.3106, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "4:17:32", "remaining_time": "1:09:37"}
+{"current_steps": 308, "total_steps": 390, "loss": 0.291, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "4:18:24", "remaining_time": "1:08:47"}
+{"current_steps": 309, "total_steps": 390, "loss": 0.2992, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "4:19:14", "remaining_time": "1:07:57"}
+{"current_steps": 310, "total_steps": 390, "loss": 0.2946, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "4:20:03", "remaining_time": "1:07:06"}
+{"current_steps": 311, "total_steps": 390, "loss": 0.3105, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "4:20:54", "remaining_time": "1:06:16"}
+{"current_steps": 312, "total_steps": 390, "loss": 0.3029, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "4:21:46", "remaining_time": "1:05:26"}
+{"current_steps": 313, "total_steps": 390, "loss": 0.5375, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "4:23:03", "remaining_time": "1:04:42"}
+{"current_steps": 314, "total_steps": 390, "loss": 0.2642, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "4:23:53", "remaining_time": "1:03:52"}
+{"current_steps": 315, "total_steps": 390, "loss": 0.2618, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "4:24:43", "remaining_time": "1:03:01"}
+{"current_steps": 316, "total_steps": 390, "loss": 0.2759, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "4:25:35", "remaining_time": "1:02:11"}
+{"current_steps": 317, "total_steps": 390, "loss": 0.2715, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "4:26:23", "remaining_time": "1:01:20"}
+{"current_steps": 318, "total_steps": 390, "loss": 0.2681, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "4:27:12", "remaining_time": "1:00:29"}
+{"current_steps": 319, "total_steps": 390, "loss": 0.2664, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "4:28:02", "remaining_time": "0:59:39"}
+{"current_steps": 320, "total_steps": 390, "loss": 0.2768, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "4:28:51", "remaining_time": "0:58:48"}
+{"current_steps": 321, "total_steps": 390, "loss": 0.2815, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "4:29:41", "remaining_time": "0:57:58"}
+{"current_steps": 322, "total_steps": 390, "loss": 0.2606, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "4:30:34", "remaining_time": "0:57:08"}
+{"current_steps": 323, "total_steps": 390, "loss": 0.2614, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "4:31:26", "remaining_time": "0:56:18"}
+{"current_steps": 324, "total_steps": 390, "loss": 0.2695, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "4:32:17", "remaining_time": "0:55:28"}
+{"current_steps": 325, "total_steps": 390, "loss": 0.2759, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "4:33:08", "remaining_time": "0:54:37"}
+{"current_steps": 326, "total_steps": 390, "loss": 0.2562, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "4:33:56", "remaining_time": "0:53:46"}
+{"current_steps": 327, "total_steps": 390, "loss": 0.2682, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "4:34:46", "remaining_time": "0:52:56"}
+{"current_steps": 328, "total_steps": 390, "loss": 0.2558, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "4:35:35", "remaining_time": "0:52:05"}
+{"current_steps": 329, "total_steps": 390, "loss": 0.2638, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "4:36:28", "remaining_time": "0:51:15"}
+{"current_steps": 330, "total_steps": 390, "loss": 0.2658, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "4:37:17", "remaining_time": "0:50:24"}
+{"current_steps": 331, "total_steps": 390, "loss": 0.2647, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "4:38:10", "remaining_time": "0:49:35"}
+{"current_steps": 332, "total_steps": 390, "loss": 0.2652, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "4:38:59", "remaining_time": "0:48:44"}
+{"current_steps": 333, "total_steps": 390, "loss": 0.2666, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "4:39:48", "remaining_time": "0:47:53"}
+{"current_steps": 334, "total_steps": 390, "loss": 0.2643, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "4:40:37", "remaining_time": "0:47:03"}
+{"current_steps": 335, "total_steps": 390, "loss": 0.2612, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "4:41:22", "remaining_time": "0:46:11"}
+{"current_steps": 336, "total_steps": 390, "loss": 0.2598, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "4:42:14", "remaining_time": "0:45:21"}
+{"current_steps": 337, "total_steps": 390, "loss": 0.2591, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "4:43:04", "remaining_time": "0:44:31"}
+{"current_steps": 338, "total_steps": 390, "loss": 0.2674, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "4:43:53", "remaining_time": "0:43:40"}
+{"current_steps": 339, "total_steps": 390, "loss": 0.255, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "4:44:40", "remaining_time": "0:42:49"}
+{"current_steps": 340, "total_steps": 390, "loss": 0.2665, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "4:45:29", "remaining_time": "0:41:59"}
+{"current_steps": 341, "total_steps": 390, "loss": 0.268, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "4:46:22", "remaining_time": "0:41:09"}
+{"current_steps": 342, "total_steps": 390, "loss": 0.2674, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "4:47:09", "remaining_time": "0:40:18"}
+{"current_steps": 343, "total_steps": 390, "loss": 0.2613, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "4:47:58", "remaining_time": "0:39:27"}
+{"current_steps": 344, "total_steps": 390, "loss": 0.2581, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "4:48:46", "remaining_time": "0:38:36"}
+{"current_steps": 345, "total_steps": 390, "loss": 0.2648, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "4:49:38", "remaining_time": "0:37:46"}
+{"current_steps": 346, "total_steps": 390, "loss": 0.263, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "4:50:28", "remaining_time": "0:36:56"}
+{"current_steps": 347, "total_steps": 390, "loss": 0.2595, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "4:51:14", "remaining_time": "0:36:05"}
+{"current_steps": 348, "total_steps": 390, "loss": 0.2705, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "4:52:06", "remaining_time": "0:35:15"}
+{"current_steps": 349, "total_steps": 390, "loss": 0.2648, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "4:52:55", "remaining_time": "0:34:24"}
+{"current_steps": 350, "total_steps": 390, "loss": 0.2664, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "4:53:47", "remaining_time": "0:33:34"}
+{"current_steps": 351, "total_steps": 390, "loss": 0.2693, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "4:54:38", "remaining_time": "0:32:44"}
+{"current_steps": 352, "total_steps": 390, "loss": 0.2689, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "4:55:24", "remaining_time": "0:31:53"}
+{"current_steps": 353, "total_steps": 390, "loss": 0.2545, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "4:56:14", "remaining_time": "0:31:03"}
+{"current_steps": 354, "total_steps": 390, "loss": 0.2728, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "4:57:05", "remaining_time": "0:30:12"}
+{"current_steps": 355, "total_steps": 390, "loss": 0.2742, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "4:57:57", "remaining_time": "0:29:22"}
+{"current_steps": 356, "total_steps": 390, "loss": 0.2654, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "4:58:48", "remaining_time": "0:28:32"}
+{"current_steps": 357, "total_steps": 390, "loss": 0.2623, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "4:59:39", "remaining_time": "0:27:41"}
+{"current_steps": 358, "total_steps": 390, "loss": 0.2666, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "5:00:29", "remaining_time": "0:26:51"}
+{"current_steps": 359, "total_steps": 390, "loss": 0.2727, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "5:01:19", "remaining_time": "0:26:01"}
+{"current_steps": 360, "total_steps": 390, "loss": 0.2565, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "5:02:08", "remaining_time": "0:25:10"}
+{"current_steps": 361, "total_steps": 390, "loss": 0.2616, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "5:02:57", "remaining_time": "0:24:20"}
+{"current_steps": 362, "total_steps": 390, "loss": 0.263, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "5:03:47", "remaining_time": "0:23:29"}
+{"current_steps": 363, "total_steps": 390, "loss": 0.2639, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "5:04:36", "remaining_time": "0:22:39"}
+{"current_steps": 364, "total_steps": 390, "loss": 0.2568, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "5:05:27", "remaining_time": "0:21:49"}
+{"current_steps": 365, "total_steps": 390, "loss": 0.2597, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "5:06:16", "remaining_time": "0:20:58"}
+{"current_steps": 366, "total_steps": 390, "loss": 0.2687, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "5:07:07", "remaining_time": "0:20:08"}
+{"current_steps": 367, "total_steps": 390, "loss": 0.2649, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "5:07:55", "remaining_time": "0:19:17"}
+{"current_steps": 368, "total_steps": 390, "loss": 0.2563, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "5:08:45", "remaining_time": "0:18:27"}
+{"current_steps": 369, "total_steps": 390, "loss": 0.2711, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "5:09:32", "remaining_time": "0:17:36"}
+{"current_steps": 370, "total_steps": 390, "loss": 0.2572, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "5:10:22", "remaining_time": "0:16:46"}
+{"current_steps": 371, "total_steps": 390, "loss": 0.2637, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "5:11:10", "remaining_time": "0:15:56"}
+{"current_steps": 372, "total_steps": 390, "loss": 0.2463, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "5:12:00", "remaining_time": "0:15:05"}
+{"current_steps": 373, "total_steps": 390, "loss": 0.265, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "5:12:50", "remaining_time": "0:14:15"}
+{"current_steps": 374, "total_steps": 390, "loss": 0.2659, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "5:13:40", "remaining_time": "0:13:25"}
+{"current_steps": 375, "total_steps": 390, "loss": 0.2572, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "5:14:30", "remaining_time": "0:12:34"}
+{"current_steps": 376, "total_steps": 390, "loss": 0.254, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "5:15:18", "remaining_time": "0:11:44"}
+{"current_steps": 377, "total_steps": 390, "loss": 0.2607, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "5:16:08", "remaining_time": "0:10:54"}
+{"current_steps": 378, "total_steps": 390, "loss": 0.2584, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "5:16:56", "remaining_time": "0:10:03"}
+{"current_steps": 379, "total_steps": 390, "loss": 0.2672, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "5:17:49", "remaining_time": "0:09:13"}
+{"current_steps": 380, "total_steps": 390, "loss": 0.2632, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "5:18:39", "remaining_time": "0:08:23"}
+{"current_steps": 381, "total_steps": 390, "loss": 0.2701, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "5:19:29", "remaining_time": "0:07:32"}
+{"current_steps": 382, "total_steps": 390, "loss": 0.259, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "5:20:20", "remaining_time": "0:06:42"}
+{"current_steps": 383, "total_steps": 390, "loss": 0.2526, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "5:21:12", "remaining_time": "0:05:52"}
+{"current_steps": 384, "total_steps": 390, "loss": 0.2686, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "5:22:03", "remaining_time": "0:05:01"}
+{"current_steps": 385, "total_steps": 390, "loss": 0.2618, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "5:22:49", "remaining_time": "0:04:11"}
+{"current_steps": 386, "total_steps": 390, "loss": 0.2675, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "5:23:39", "remaining_time": "0:03:21"}
+{"current_steps": 387, "total_steps": 390, "loss": 0.2592, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "5:24:30", "remaining_time": "0:02:30"}
+{"current_steps": 388, "total_steps": 390, "loss": 0.2755, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "5:25:21", "remaining_time": "0:01:40"}
+{"current_steps": 389, "total_steps": 390, "loss": 0.2595, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "5:26:13", "remaining_time": "0:00:50"}
+{"current_steps": 390, "total_steps": 390, "loss": 0.2657, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "5:27:04", "remaining_time": "0:00:00"}
+{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "5:29:11", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2772 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.992,
+  "eval_steps": 500,
+  "global_step": 390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0128,
+      "grad_norm": 6.219960368061681,
+      "learning_rate": 1.0256410256410257e-06,
+      "loss": 0.8101,
+      "step": 1
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 6.255587230045647,
+      "learning_rate": 2.0512820512820513e-06,
+      "loss": 0.8184,
+      "step": 2
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 5.812583180263883,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.7754,
+      "step": 3
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 5.530199285053854,
+      "learning_rate": 4.102564102564103e-06,
+      "loss": 0.7871,
+      "step": 4
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 4.039710518300703,
+      "learning_rate": 5.128205128205128e-06,
+      "loss": 0.7527,
+      "step": 5
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 2.2466369696015103,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.7133,
+      "step": 6
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 2.1073418979367995,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 0.7011,
+      "step": 7
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 4.034393097464074,
+      "learning_rate": 8.205128205128205e-06,
+      "loss": 0.7398,
+      "step": 8
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 4.144401097982347,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.7094,
+      "step": 9
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 3.8695340817216914,
+      "learning_rate": 1.0256410256410256e-05,
+      "loss": 0.6714,
+      "step": 10
+    },
+    {
+      "epoch": 0.1408,
+      "grad_norm": 3.4446729988081484,
+      "learning_rate": 1.1282051282051283e-05,
+      "loss": 0.6735,
+      "step": 11
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 1.9143368701964922,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 0.6446,
+      "step": 12
+    },
+    {
+      "epoch": 0.1664,
+      "grad_norm": 1.5632792175236936,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6465,
+      "step": 13
+    },
+    {
+      "epoch": 0.1792,
+      "grad_norm": 2.090557483686497,
+      "learning_rate": 1.435897435897436e-05,
+      "loss": 0.6262,
+      "step": 14
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 1.4279661882786803,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.6068,
+      "step": 15
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 1.226067869994867,
+      "learning_rate": 1.641025641025641e-05,
+      "loss": 0.598,
+      "step": 16
+    },
+    {
+      "epoch": 0.2176,
+      "grad_norm": 1.0165564708836172,
+      "learning_rate": 1.7435897435897438e-05,
+      "loss": 0.5589,
+      "step": 17
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 1.0491928880215449,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.5617,
+      "step": 18
+    },
+    {
+      "epoch": 0.2432,
+      "grad_norm": 0.989476474713095,
+      "learning_rate": 1.9487179487179488e-05,
+      "loss": 0.5718,
+      "step": 19
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.7747709123954674,
+      "learning_rate": 2.0512820512820512e-05,
+      "loss": 0.5714,
+      "step": 20
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 0.9017229990416915,
+      "learning_rate": 2.153846153846154e-05,
+      "loss": 0.5418,
+      "step": 21
+    },
+    {
+      "epoch": 0.2816,
+      "grad_norm": 0.7326914793600917,
+      "learning_rate": 2.2564102564102566e-05,
+      "loss": 0.5234,
+      "step": 22
+    },
+    {
+      "epoch": 0.2944,
+      "grad_norm": 0.6957415259620942,
+      "learning_rate": 2.3589743589743593e-05,
+      "loss": 0.5356,
+      "step": 23
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 0.7539434604193752,
+      "learning_rate": 2.461538461538462e-05,
+      "loss": 0.5502,
+      "step": 24
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8906034389744679,
+      "learning_rate": 2.5641025641025646e-05,
+      "loss": 0.5439,
+      "step": 25
+    },
+    {
+      "epoch": 0.3328,
+      "grad_norm": 0.5342890646270876,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.5282,
+      "step": 26
+    },
+    {
+      "epoch": 0.3456,
+      "grad_norm": 0.7622179978471697,
+      "learning_rate": 2.7692307692307694e-05,
+      "loss": 0.5066,
+      "step": 27
+    },
+    {
+      "epoch": 0.3584,
+      "grad_norm": 0.6331707233908107,
+      "learning_rate": 2.871794871794872e-05,
+      "loss": 0.505,
+      "step": 28
+    },
+    {
+      "epoch": 0.3712,
+      "grad_norm": 0.6612848135954165,
+      "learning_rate": 2.9743589743589747e-05,
+      "loss": 0.5077,
+      "step": 29
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.7682267051668576,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.5305,
+      "step": 30
+    },
+    {
+      "epoch": 0.3968,
+      "grad_norm": 0.7520925871727904,
+      "learning_rate": 3.1794871794871795e-05,
+      "loss": 0.504,
+      "step": 31
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 0.653998799214937,
+      "learning_rate": 3.282051282051282e-05,
+      "loss": 0.5222,
+      "step": 32
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 0.6679867654461787,
+      "learning_rate": 3.384615384615385e-05,
+      "loss": 0.5176,
+      "step": 33
+    },
+    {
+      "epoch": 0.4352,
+      "grad_norm": 0.642486851645915,
+      "learning_rate": 3.4871794871794875e-05,
+      "loss": 0.5113,
+      "step": 34
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6871592500186298,
+      "learning_rate": 3.58974358974359e-05,
+      "loss": 0.4983,
+      "step": 35
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 0.7910986255637528,
+      "learning_rate": 3.692307692307693e-05,
+      "loss": 0.5051,
+      "step": 36
+    },
+    {
+      "epoch": 0.4736,
+      "grad_norm": 0.8080740629150058,
+      "learning_rate": 3.794871794871795e-05,
+      "loss": 0.4983,
+      "step": 37
+    },
+    {
+      "epoch": 0.4864,
+      "grad_norm": 0.9200078993378724,
+      "learning_rate": 3.8974358974358976e-05,
+      "loss": 0.4939,
+      "step": 38
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 0.8367426738033117,
+      "learning_rate": 4e-05,
+      "loss": 0.4896,
+      "step": 39
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.6713192992042779,
+      "learning_rate": 3.9999198907597046e-05,
+      "loss": 0.5069,
+      "step": 40
+    },
+    {
+      "epoch": 0.5248,
+      "grad_norm": 0.7662119700759862,
+      "learning_rate": 3.9996795694563096e-05,
+      "loss": 0.5082,
+      "step": 41
+    },
+    {
+      "epoch": 0.5376,
+      "grad_norm": 0.8669344109784791,
+      "learning_rate": 3.999279055341771e-05,
+      "loss": 0.4919,
+      "step": 42
+    },
+    {
+      "epoch": 0.5504,
+      "grad_norm": 0.8899512451163312,
+      "learning_rate": 3.998718380500971e-05,
+      "loss": 0.4875,
+      "step": 43
+    },
+    {
+      "epoch": 0.5632,
+      "grad_norm": 0.7563887486399409,
+      "learning_rate": 3.997997589849145e-05,
+      "loss": 0.4921,
+      "step": 44
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.7127142506461983,
+      "learning_rate": 3.9971167411282835e-05,
+      "loss": 0.48,
+      "step": 45
+    },
+    {
+      "epoch": 0.5888,
+      "grad_norm": 0.6656339174054332,
+      "learning_rate": 3.99607590490251e-05,
+      "loss": 0.483,
+      "step": 46
+    },
+    {
+      "epoch": 0.6016,
+      "grad_norm": 0.6318377185051762,
+      "learning_rate": 3.9948751645524235e-05,
+      "loss": 0.4832,
+      "step": 47
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 0.6778098859319694,
+      "learning_rate": 3.9935146162684206e-05,
+      "loss": 0.4853,
+      "step": 48
+    },
+    {
+      "epoch": 0.6272,
+      "grad_norm": 0.6885469806114507,
+      "learning_rate": 3.9919943690429906e-05,
+      "loss": 0.5057,
+      "step": 49
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.6325530323836207,
+      "learning_rate": 3.9903145446619837e-05,
+      "loss": 0.4802,
+      "step": 50
+    },
+    {
+      "epoch": 0.6528,
+      "grad_norm": 0.782547149645394,
+      "learning_rate": 3.9884752776948564e-05,
+      "loss": 0.4769,
+      "step": 51
+    },
+    {
+      "epoch": 0.6656,
+      "grad_norm": 0.6207695198782405,
+      "learning_rate": 3.9864767154838864e-05,
+      "loss": 0.4522,
+      "step": 52
+    },
+    {
+      "epoch": 0.6784,
+      "grad_norm": 0.5428851252081672,
+      "learning_rate": 3.9843190181323744e-05,
+      "loss": 0.4782,
+      "step": 53
+    },
+    {
+      "epoch": 0.6912,
+      "grad_norm": 0.7763049738206279,
+      "learning_rate": 3.982002358491817e-05,
+      "loss": 0.4712,
+      "step": 54
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.7325806554777012,
+      "learning_rate": 3.979526922148058e-05,
+      "loss": 0.4581,
+      "step": 55
+    },
+    {
+      "epoch": 0.7168,
+      "grad_norm": 0.5668478628549942,
+      "learning_rate": 3.9768929074064206e-05,
+      "loss": 0.479,
+      "step": 56
+    },
+    {
+      "epoch": 0.7296,
+      "grad_norm": 0.6263294106173753,
+      "learning_rate": 3.9741005252758255e-05,
+      "loss": 0.4743,
+      "step": 57
+    },
+    {
+      "epoch": 0.7424,
+      "grad_norm": 0.5607969345769923,
+      "learning_rate": 3.971149999451886e-05,
+      "loss": 0.4823,
+      "step": 58
+    },
+    {
+      "epoch": 0.7552,
+      "grad_norm": 0.5136174452333186,
+      "learning_rate": 3.9680415662989806e-05,
+      "loss": 0.4679,
+      "step": 59
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.471032886614314,
+      "learning_rate": 3.9647754748313294e-05,
+      "loss": 0.4775,
+      "step": 60
+    },
+    {
+      "epoch": 0.7808,
+      "grad_norm": 0.45671725772240584,
+      "learning_rate": 3.96135198669304e-05,
+      "loss": 0.4578,
+      "step": 61
+    },
+    {
+      "epoch": 0.7936,
+      "grad_norm": 0.4721743365196963,
+      "learning_rate": 3.957771376137144e-05,
+      "loss": 0.4624,
+      "step": 62
+    },
+    {
+      "epoch": 0.8064,
+      "grad_norm": 0.3638376734754168,
+      "learning_rate": 3.954033930003634e-05,
+      "loss": 0.4623,
+      "step": 63
+    },
+    {
+      "epoch": 0.8192,
+      "grad_norm": 0.47142236191713693,
+      "learning_rate": 3.9501399476964806e-05,
+      "loss": 0.4698,
+      "step": 64
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.4483840131656804,
+      "learning_rate": 3.946089741159648e-05,
+      "loss": 0.4641,
+      "step": 65
+    },
+    {
+      "epoch": 0.8448,
+      "grad_norm": 0.48886663683590464,
+      "learning_rate": 3.9418836348521045e-05,
+      "loss": 0.458,
+      "step": 66
+    },
+    {
+      "epoch": 0.8576,
+      "grad_norm": 0.552125666602303,
+      "learning_rate": 3.937521965721831e-05,
+      "loss": 0.4732,
+      "step": 67
+    },
+    {
+      "epoch": 0.8704,
+      "grad_norm": 0.6603957595848559,
+      "learning_rate": 3.933005083178828e-05,
+      "loss": 0.4667,
+      "step": 68
+    },
+    {
+      "epoch": 0.8832,
+      "grad_norm": 0.7103390466059525,
+      "learning_rate": 3.928333349067125e-05,
+      "loss": 0.4756,
+      "step": 69
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.4843247302130666,
+      "learning_rate": 3.923507137635792e-05,
+      "loss": 0.4711,
+      "step": 70
+    },
+    {
+      "epoch": 0.9088,
+      "grad_norm": 0.4921206893241678,
+      "learning_rate": 3.9185268355089606e-05,
+      "loss": 0.4664,
+      "step": 71
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 0.3990742427137136,
+      "learning_rate": 3.913392841654851e-05,
+      "loss": 0.4708,
+      "step": 72
+    },
+    {
+      "epoch": 0.9344,
+      "grad_norm": 0.5575527605510985,
+      "learning_rate": 3.9081055673538093e-05,
+      "loss": 0.465,
+      "step": 73
+    },
+    {
+      "epoch": 0.9472,
+      "grad_norm": 0.49825122885831696,
+      "learning_rate": 3.902665436165364e-05,
+      "loss": 0.4645,
+      "step": 74
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.4260337681086415,
+      "learning_rate": 3.897072883894291e-05,
+      "loss": 0.4456,
+      "step": 75
+    },
+    {
+      "epoch": 0.9728,
+      "grad_norm": 0.36449224341953756,
+      "learning_rate": 3.8913283585557054e-05,
+      "loss": 0.4566,
+      "step": 76
+    },
+    {
+      "epoch": 0.9856,
+      "grad_norm": 0.4324858962044455,
+      "learning_rate": 3.885432320339167e-05,
+      "loss": 0.4743,
+      "step": 77
+    },
+    {
+      "epoch": 0.9984,
+      "grad_norm": 0.43359457503733184,
+      "learning_rate": 3.879385241571817e-05,
+      "loss": 0.4686,
+      "step": 78
+    },
+    {
+      "epoch": 1.0112,
+      "grad_norm": 1.0502585254063914,
+      "learning_rate": 3.873187606680543e-05,
+      "loss": 0.8511,
+      "step": 79
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 1.4627143223113306,
+      "learning_rate": 3.866839912153168e-05,
+      "loss": 0.4321,
+      "step": 80
+    },
+    {
+      "epoch": 1.0368,
+      "grad_norm": 0.7480690321547587,
+      "learning_rate": 3.860342666498677e-05,
+      "loss": 0.4286,
+      "step": 81
+    },
+    {
+      "epoch": 1.0496,
+      "grad_norm": 1.0679337626627332,
+      "learning_rate": 3.853696390206484e-05,
+      "loss": 0.436,
+      "step": 82
+    },
+    {
+      "epoch": 1.0624,
+      "grad_norm": 0.8322278186443296,
+      "learning_rate": 3.846901615704734e-05,
+      "loss": 0.4344,
+      "step": 83
+    },
+    {
+      "epoch": 1.0752,
+      "grad_norm": 0.8310740611172034,
+      "learning_rate": 3.839958887317649e-05,
+      "loss": 0.4135,
+      "step": 84
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7265084163301352,
+      "learning_rate": 3.832868761221926e-05,
+      "loss": 0.4383,
+      "step": 85
+    },
+    {
+      "epoch": 1.1008,
+      "grad_norm": 0.8432536460204655,
+      "learning_rate": 3.825631805402182e-05,
+      "loss": 0.4189,
+      "step": 86
+    },
+    {
+      "epoch": 1.1136,
+      "grad_norm": 0.5914223651226814,
+      "learning_rate": 3.818248599605448e-05,
+      "loss": 0.4287,
+      "step": 87
+    },
+    {
+      "epoch": 1.1264,
+      "grad_norm": 0.7758229261853449,
+      "learning_rate": 3.810719735294731e-05,
+      "loss": 0.4251,
+      "step": 88
+    },
+    {
+      "epoch": 1.1392,
+      "grad_norm": 0.5880230426542516,
+      "learning_rate": 3.8030458156016326e-05,
+      "loss": 0.4362,
+      "step": 89
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.582352185601103,
+      "learning_rate": 3.795227455278029e-05,
+      "loss": 0.4143,
+      "step": 90
+    },
+    {
+      "epoch": 1.1648,
+      "grad_norm": 0.5313469123938604,
+      "learning_rate": 3.787265280646825e-05,
+      "loss": 0.4194,
+      "step": 91
+    },
+    {
+      "epoch": 1.1776,
+      "grad_norm": 0.6318881329574421,
+      "learning_rate": 3.7791599295517825e-05,
+      "loss": 0.4272,
+      "step": 92
+    },
+    {
+      "epoch": 1.1904,
+      "grad_norm": 0.5615435888090177,
+      "learning_rate": 3.7709120513064196e-05,
+      "loss": 0.4174,
+      "step": 93
+    },
+    {
+      "epoch": 1.2032,
+      "grad_norm": 0.5159084360650437,
+      "learning_rate": 3.762522306641998e-05,
+      "loss": 0.4152,
+      "step": 94
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.4731566632934445,
+      "learning_rate": 3.7539913676545874e-05,
+      "loss": 0.4239,
+      "step": 95
+    },
+    {
+      "epoch": 1.2288000000000001,
+      "grad_norm": 0.49208237680350847,
+      "learning_rate": 3.745319917751229e-05,
+      "loss": 0.4216,
+      "step": 96
+    },
+    {
+      "epoch": 1.2416,
+      "grad_norm": 0.4998376104043881,
+      "learning_rate": 3.736508651595188e-05,
+      "loss": 0.4365,
+      "step": 97
+    },
+    {
+      "epoch": 1.2544,
+      "grad_norm": 0.4589678934170144,
+      "learning_rate": 3.727558275050301e-05,
+      "loss": 0.4124,
+      "step": 98
+    },
+    {
+      "epoch": 1.2671999999999999,
+      "grad_norm": 0.5191560318056777,
+      "learning_rate": 3.718469505124434e-05,
+      "loss": 0.4282,
+      "step": 99
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5123962286905679,
+      "learning_rate": 3.709243069912041e-05,
+      "loss": 0.4184,
+      "step": 100
+    },
+    {
+      "epoch": 1.2928,
+      "grad_norm": 0.4301206051843682,
+      "learning_rate": 3.699879708535838e-05,
+      "loss": 0.4099,
+      "step": 101
+    },
+    {
+      "epoch": 1.3056,
+      "grad_norm": 0.4980931015846837,
+      "learning_rate": 3.69038017108759e-05,
+      "loss": 0.4285,
+      "step": 102
+    },
+    {
+      "epoch": 1.3184,
+      "grad_norm": 0.41922427101233256,
+      "learning_rate": 3.680745218568026e-05,
+      "loss": 0.4214,
+      "step": 103
+    },
+    {
+      "epoch": 1.3312,
+      "grad_norm": 0.4210197599229585,
+      "learning_rate": 3.6709756228258735e-05,
+      "loss": 0.41,
+      "step": 104
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.33044370672997886,
+      "learning_rate": 3.6610721664960236e-05,
+      "loss": 0.4133,
+      "step": 105
+    },
+    {
+      "epoch": 1.3568,
+      "grad_norm": 0.46036392068195386,
+      "learning_rate": 3.65103564293684e-05,
+      "loss": 0.4142,
+      "step": 106
+    },
+    {
+      "epoch": 1.3696,
+      "grad_norm": 0.5197079194705977,
+      "learning_rate": 3.640866856166601e-05,
+      "loss": 0.4241,
+      "step": 107
+    },
+    {
+      "epoch": 1.3824,
+      "grad_norm": 0.5735931578875425,
+      "learning_rate": 3.6305666207990886e-05,
+      "loss": 0.4134,
+      "step": 108
+    },
+    {
+      "epoch": 1.3952,
+      "grad_norm": 0.34967134539280176,
+      "learning_rate": 3.6201357619783336e-05,
+      "loss": 0.4156,
+      "step": 109
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6184740233792955,
+      "learning_rate": 3.609575115312511e-05,
+      "loss": 0.4162,
+      "step": 110
+    },
+    {
+      "epoch": 1.4208,
+      "grad_norm": 0.39886032959277895,
+      "learning_rate": 3.598885526807003e-05,
+      "loss": 0.4065,
+      "step": 111
+    },
+    {
+      "epoch": 1.4336,
+      "grad_norm": 0.5232061639818978,
+      "learning_rate": 3.5880678527966224e-05,
+      "loss": 0.426,
+      "step": 112
+    },
+    {
+      "epoch": 1.4464000000000001,
+      "grad_norm": 0.5392396167721961,
+      "learning_rate": 3.577122959877017e-05,
+      "loss": 0.4058,
+      "step": 113
+    },
+    {
+      "epoch": 1.4592,
+      "grad_norm": 0.39738094371187505,
+      "learning_rate": 3.566051724835245e-05,
+      "loss": 0.4117,
+      "step": 114
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.43114668450905597,
+      "learning_rate": 3.554855034579532e-05,
+      "loss": 0.4233,
+      "step": 115
+    },
+    {
+      "epoch": 1.4848,
+      "grad_norm": 0.44432873781066573,
+      "learning_rate": 3.5435337860682304e-05,
+      "loss": 0.3932,
+      "step": 116
+    },
+    {
+      "epoch": 1.4976,
+      "grad_norm": 0.40254748431088544,
+      "learning_rate": 3.532088886237956e-05,
+      "loss": 0.4104,
+      "step": 117
+    },
+    {
+      "epoch": 1.5104,
+      "grad_norm": 0.4356093648467301,
+      "learning_rate": 3.520521251930941e-05,
+      "loss": 0.4311,
+      "step": 118
+    },
+    {
+      "epoch": 1.5232,
+      "grad_norm": 0.3598813494896981,
+      "learning_rate": 3.5088318098215805e-05,
+      "loss": 0.3961,
+      "step": 119
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.36312680014273024,
+      "learning_rate": 3.497021496342203e-05,
+      "loss": 0.4145,
+      "step": 120
+    },
+    {
+      "epoch": 1.5488,
+      "grad_norm": 0.44939906912663474,
+      "learning_rate": 3.485091257608047e-05,
+      "loss": 0.4176,
+      "step": 121
+    },
+    {
+      "epoch": 1.5615999999999999,
+      "grad_norm": 0.44711667575178554,
+      "learning_rate": 3.473042049341474e-05,
+      "loss": 0.4267,
+      "step": 122
+    },
+    {
+      "epoch": 1.5744,
+      "grad_norm": 0.39673670743660033,
+      "learning_rate": 3.4608748367954064e-05,
+      "loss": 0.4094,
+      "step": 123
+    },
+    {
+      "epoch": 1.5872000000000002,
+      "grad_norm": 0.5130143641085764,
+      "learning_rate": 3.4485905946759965e-05,
+      "loss": 0.4258,
+      "step": 124
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.4847123994711865,
+      "learning_rate": 3.4361903070645484e-05,
+      "loss": 0.4215,
+      "step": 125
+    },
+    {
+      "epoch": 1.6128,
+      "grad_norm": 0.34497157500964715,
+      "learning_rate": 3.423674967338681e-05,
+      "loss": 0.3974,
+      "step": 126
+    },
+    {
+      "epoch": 1.6256,
+      "grad_norm": 0.5418950563871423,
+      "learning_rate": 3.411045578092754e-05,
+      "loss": 0.4052,
+      "step": 127
+    },
+    {
+      "epoch": 1.6383999999999999,
+      "grad_norm": 0.5457922313342711,
+      "learning_rate": 3.398303151057543e-05,
+      "loss": 0.4034,
+      "step": 128
+    },
+    {
+      "epoch": 1.6512,
+      "grad_norm": 0.3161412930452751,
+      "learning_rate": 3.385448707019199e-05,
+      "loss": 0.4123,
+      "step": 129
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.5233565454343642,
+      "learning_rate": 3.372483275737468e-05,
+      "loss": 0.4078,
+      "step": 130
+    },
+    {
+      "epoch": 1.6768,
+      "grad_norm": 0.4227025929662532,
+      "learning_rate": 3.359407895863199e-05,
+      "loss": 0.4159,
+      "step": 131
+    },
+    {
+      "epoch": 1.6896,
+      "grad_norm": 0.3350150395065374,
+      "learning_rate": 3.34622361485514e-05,
+      "loss": 0.4161,
+      "step": 132
+    },
+    {
+      "epoch": 1.7024,
+      "grad_norm": 0.4788031151576321,
+      "learning_rate": 3.332931488896029e-05,
+      "loss": 0.4053,
+      "step": 133
+    },
+    {
+      "epoch": 1.7151999999999998,
+      "grad_norm": 0.44064149123425755,
+      "learning_rate": 3.319532582807977e-05,
+      "loss": 0.423,
+      "step": 134
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.3579153381760676,
+      "learning_rate": 3.30602796996717e-05,
+      "loss": 0.4131,
+      "step": 135
+    },
+    {
+      "epoch": 1.7408000000000001,
+      "grad_norm": 0.4431422410986477,
+      "learning_rate": 3.2924187322178865e-05,
+      "loss": 0.4098,
+      "step": 136
+    },
+    {
+      "epoch": 1.7536,
+      "grad_norm": 0.3237836795334074,
+      "learning_rate": 3.278705959785821e-05,
+      "loss": 0.4018,
+      "step": 137
+    },
+    {
+      "epoch": 1.7664,
+      "grad_norm": 0.43921889103638523,
+      "learning_rate": 3.2648907511907544e-05,
+      "loss": 0.4194,
+      "step": 138
+    },
+    {
+      "epoch": 1.7792,
+      "grad_norm": 0.38476175122380096,
+      "learning_rate": 3.250974213158555e-05,
+      "loss": 0.4087,
+      "step": 139
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.29254420648683577,
+      "learning_rate": 3.23695746053251e-05,
+      "loss": 0.4213,
+      "step": 140
+    },
+    {
+      "epoch": 1.8048,
+      "grad_norm": 0.4261387699145811,
+      "learning_rate": 3.222841616184025e-05,
+      "loss": 0.4124,
+      "step": 141
+    },
+    {
+      "epoch": 1.8176,
+      "grad_norm": 0.3886411273932464,
+      "learning_rate": 3.208627810922665e-05,
+      "loss": 0.411,
+      "step": 142
+    },
+    {
+      "epoch": 1.8304,
+      "grad_norm": 0.3979518371673893,
+      "learning_rate": 3.194317183405573e-05,
+      "loss": 0.4093,
+      "step": 143
+    },
+    {
+      "epoch": 1.8432,
+      "grad_norm": 0.3999045260658046,
+      "learning_rate": 3.1799108800462466e-05,
+      "loss": 0.4213,
+      "step": 144
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.3760337630105005,
+      "learning_rate": 3.1654100549227024e-05,
+      "loss": 0.4219,
+      "step": 145
+    },
+    {
+      "epoch": 1.8688,
+      "grad_norm": 0.4686479438292246,
+      "learning_rate": 3.1508158696850275e-05,
+      "loss": 0.3926,
+      "step": 146
+    },
+    {
+      "epoch": 1.8816000000000002,
+      "grad_norm": 0.34949867790932876,
+      "learning_rate": 3.136129493462312e-05,
+      "loss": 0.4096,
+      "step": 147
+    },
+    {
+      "epoch": 1.8944,
+      "grad_norm": 0.3821103543970302,
+      "learning_rate": 3.121352102768998e-05,
+      "loss": 0.4177,
+      "step": 148
+    },
+    {
+      "epoch": 1.9072,
+      "grad_norm": 0.35807291233095556,
+      "learning_rate": 3.106484881410628e-05,
+      "loss": 0.4055,
+      "step": 149
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.36639865137433913,
+      "learning_rate": 3.091529020389009e-05,
+      "loss": 0.4236,
+      "step": 150
+    },
+    {
+      "epoch": 1.9327999999999999,
+      "grad_norm": 0.3227686276164447,
+      "learning_rate": 3.076485717806808e-05,
+      "loss": 0.4006,
+      "step": 151
+    },
+    {
+      "epoch": 1.9456,
+      "grad_norm": 0.35808948671887775,
+      "learning_rate": 3.061356178771564e-05,
+      "loss": 0.402,
+      "step": 152
+    },
+    {
+      "epoch": 1.9584000000000001,
+      "grad_norm": 0.3457066902452974,
+      "learning_rate": 3.0461416152991555e-05,
+      "loss": 0.421,
+      "step": 153
+    },
+    {
+      "epoch": 1.9712,
+      "grad_norm": 0.3475253542398459,
+      "learning_rate": 3.0308432462167045e-05,
+      "loss": 0.3982,
+      "step": 154
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.3205588619302455,
+      "learning_rate": 3.015462297064936e-05,
+      "loss": 0.4026,
+      "step": 155
+    },
+    {
+      "epoch": 1.9968,
+      "grad_norm": 0.3901439997813586,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 0.4276,
+      "step": 156
+    },
+    {
+      "epoch": 2.0096,
+      "grad_norm": 0.8738457584981104,
+      "learning_rate": 2.98445759369477e-05,
+      "loss": 0.7805,
+      "step": 157
+    },
+    {
+      "epoch": 2.0224,
+      "grad_norm": 0.7480515761787411,
+      "learning_rate": 2.9688363232396056e-05,
+      "loss": 0.3596,
+      "step": 158
+    },
+    {
+      "epoch": 2.0352,
+      "grad_norm": 0.5640866303523602,
+      "learning_rate": 2.9531374400426158e-05,
+      "loss": 0.3473,
+      "step": 159
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.602382092551675,
+      "learning_rate": 2.9373622017294075e-05,
+      "loss": 0.3838,
+      "step": 160
+    },
+    {
+      "epoch": 2.0608,
+      "grad_norm": 0.6638274726754934,
+      "learning_rate": 2.9215118720423375e-05,
+      "loss": 0.3502,
+      "step": 161
+    },
+    {
+      "epoch": 2.0736,
+      "grad_norm": 0.5438404133170176,
+      "learning_rate": 2.9055877207392752e-05,
+      "loss": 0.3758,
+      "step": 162
+    },
+    {
+      "epoch": 2.0864,
+      "grad_norm": 0.5905460081915943,
+      "learning_rate": 2.8895910234918828e-05,
+      "loss": 0.3532,
+      "step": 163
+    },
+    {
+      "epoch": 2.0992,
+      "grad_norm": 6.8823160810813455,
+      "learning_rate": 2.873523061783426e-05,
+      "loss": 0.3581,
+      "step": 164
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 1.0105876318902012,
+      "learning_rate": 2.8573851228061084e-05,
+      "loss": 0.3688,
+      "step": 165
+    },
+    {
+      "epoch": 2.1248,
+      "grad_norm": 1.0020339014576163,
+      "learning_rate": 2.8411784993579633e-05,
+      "loss": 0.375,
+      "step": 166
+    },
+    {
+      "epoch": 2.1376,
+      "grad_norm": 0.7483800946597154,
+      "learning_rate": 2.8249044897392814e-05,
+      "loss": 0.3646,
+      "step": 167
+    },
+    {
+      "epoch": 2.1504,
+      "grad_norm": 0.7939656840141626,
+      "learning_rate": 2.80856439764861e-05,
+      "loss": 0.3531,
+      "step": 168
+    },
+    {
+      "epoch": 2.1632,
+      "grad_norm": 0.7448259060057426,
+      "learning_rate": 2.792159532078314e-05,
+      "loss": 0.3694,
+      "step": 169
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.6514266801940611,
+      "learning_rate": 2.77569120720971e-05,
+      "loss": 0.3507,
+      "step": 170
+    },
+    {
+      "epoch": 2.1888,
+      "grad_norm": 0.649242399425495,
+      "learning_rate": 2.7591607423077932e-05,
+      "loss": 0.3602,
+      "step": 171
+    },
+    {
+      "epoch": 2.2016,
+      "grad_norm": 0.4576587081331995,
+      "learning_rate": 2.7425694616155474e-05,
+      "loss": 0.3565,
+      "step": 172
+    },
+    {
+      "epoch": 2.2144,
+      "grad_norm": 0.6604918457009642,
+      "learning_rate": 2.7259186942478656e-05,
+      "loss": 0.3689,
+      "step": 173
+    },
+    {
+      "epoch": 2.2272,
+      "grad_norm": 0.4397911958064353,
+      "learning_rate": 2.7092097740850712e-05,
+      "loss": 0.3569,
+      "step": 174
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.49943864796444065,
+      "learning_rate": 2.692444039666066e-05,
+      "loss": 0.3627,
+      "step": 175
+    },
+    {
+      "epoch": 2.2528,
+      "grad_norm": 0.5184404200513918,
+      "learning_rate": 2.6756228340810946e-05,
+      "loss": 0.3625,
+      "step": 176
+    },
+    {
+      "epoch": 2.2656,
+      "grad_norm": 0.4027625188275841,
+      "learning_rate": 2.6587475048641596e-05,
+      "loss": 0.3495,
+      "step": 177
+    },
+    {
+      "epoch": 2.2784,
+      "grad_norm": 0.4913910574951981,
+      "learning_rate": 2.6418194038850634e-05,
+      "loss": 0.3499,
+      "step": 178
+    },
+    {
+      "epoch": 2.2912,
+      "grad_norm": 1.3061725116256797,
+      "learning_rate": 2.624839887241115e-05,
+      "loss": 0.3718,
+      "step": 179
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.4734015911963579,
+      "learning_rate": 2.607810315148494e-05,
+      "loss": 0.3462,
+      "step": 180
+    },
+    {
+      "epoch": 2.3168,
+      "grad_norm": 0.3512087638097743,
+      "learning_rate": 2.5907320518332827e-05,
+      "loss": 0.362,
+      "step": 181
+    },
+    {
+      "epoch": 2.3296,
+      "grad_norm": 0.3938674946237412,
+      "learning_rate": 2.5736064654221808e-05,
+      "loss": 0.3488,
+      "step": 182
+    },
+    {
+      "epoch": 2.3424,
+      "grad_norm": 0.37929820735277997,
+      "learning_rate": 2.5564349278329056e-05,
+      "loss": 0.3574,
+      "step": 183
+    },
+    {
+      "epoch": 2.3552,
+      "grad_norm": 0.3907990222810365,
+      "learning_rate": 2.539218814664288e-05,
+      "loss": 0.339,
+      "step": 184
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.36895671598541147,
+      "learning_rate": 2.521959505086075e-05,
+      "loss": 0.3541,
+      "step": 185
+    },
+    {
+      "epoch": 2.3808,
+      "grad_norm": 0.4217604958853726,
+      "learning_rate": 2.5046583817284437e-05,
+      "loss": 0.355,
+      "step": 186
+    },
+    {
+      "epoch": 2.3936,
+      "grad_norm": 0.34984768175904685,
+      "learning_rate": 2.487316830571244e-05,
+      "loss": 0.3391,
+      "step": 187
+    },
+    {
+      "epoch": 2.4064,
+      "grad_norm": 0.35143695803310604,
+      "learning_rate": 2.4699362408329646e-05,
+      "loss": 0.3687,
+      "step": 188
+    },
+    {
+      "epoch": 2.4192,
+      "grad_norm": 0.30181277781268995,
+      "learning_rate": 2.4525180048594452e-05,
+      "loss": 0.3417,
+      "step": 189
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.3179670439617093,
+      "learning_rate": 2.435063518012335e-05,
+      "loss": 0.3563,
+      "step": 190
+    },
+    {
+      "epoch": 2.4448,
+      "grad_norm": 0.3434455104718644,
+      "learning_rate": 2.4175741785573177e-05,
+      "loss": 0.3542,
+      "step": 191
+    },
+    {
+      "epoch": 2.4576000000000002,
+      "grad_norm": 0.32562672855847785,
+      "learning_rate": 2.4000513875520892e-05,
+      "loss": 0.3671,
+      "step": 192
+    },
+    {
+      "epoch": 2.4704,
+      "grad_norm": 0.30331805437000403,
+      "learning_rate": 2.3824965487341247e-05,
+      "loss": 0.3586,
+      "step": 193
+    },
+    {
+      "epoch": 2.4832,
+      "grad_norm": 0.3271268259739871,
+      "learning_rate": 2.3649110684082258e-05,
+      "loss": 0.3437,
+      "step": 194
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.28596308241097534,
+      "learning_rate": 2.3472963553338614e-05,
+      "loss": 0.3555,
+      "step": 195
+    },
+    {
+      "epoch": 2.5088,
+      "grad_norm": 0.35364437300722873,
+      "learning_rate": 2.3296538206123134e-05,
+      "loss": 0.3462,
+      "step": 196
+    },
+    {
+      "epoch": 2.5216,
+      "grad_norm": 0.3691401958363945,
+      "learning_rate": 2.311984877573636e-05,
+      "loss": 0.3551,
+      "step": 197
+    },
+    {
+      "epoch": 2.5343999999999998,
+      "grad_norm": 0.34958767039747213,
+      "learning_rate": 2.2942909416634326e-05,
+      "loss": 0.3642,
+      "step": 198
+    },
+    {
+      "epoch": 2.5472,
+      "grad_norm": 0.347179387105894,
+      "learning_rate": 2.2765734303294666e-05,
+      "loss": 0.3478,
+      "step": 199
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.29055667713456323,
+      "learning_rate": 2.2588337629081107e-05,
+      "loss": 0.3601,
+      "step": 200
+    },
+    {
+      "epoch": 2.5728,
+      "grad_norm": 0.2957415258779927,
+      "learning_rate": 2.2410733605106462e-05,
+      "loss": 0.3635,
+      "step": 201
+    },
+    {
+      "epoch": 2.5856,
+      "grad_norm": 0.3163595463392172,
+      "learning_rate": 2.2232936459094158e-05,
+      "loss": 0.3498,
+      "step": 202
+    },
+    {
+      "epoch": 2.5984,
+      "grad_norm": 0.24606892407899797,
+      "learning_rate": 2.205496043423849e-05,
+      "loss": 0.3544,
+      "step": 203
+    },
+    {
+      "epoch": 2.6112,
+      "grad_norm": 0.29863764447592844,
+      "learning_rate": 2.1876819788063586e-05,
+      "loss": 0.3425,
+      "step": 204
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.2817341903784844,
+      "learning_rate": 2.16985287912813e-05,
+      "loss": 0.3563,
+      "step": 205
+    },
+    {
+      "epoch": 2.6368,
+      "grad_norm": 0.2847194177003871,
+      "learning_rate": 2.1520101726647922e-05,
+      "loss": 0.3729,
+      "step": 206
+    },
+    {
+      "epoch": 2.6496,
+      "grad_norm": 0.2805248067283957,
+      "learning_rate": 2.1341552887820048e-05,
+      "loss": 0.3619,
+      "step": 207
+    },
+    {
+      "epoch": 2.6624,
+      "grad_norm": 0.2682651776470791,
+      "learning_rate": 2.1162896578209517e-05,
+      "loss": 0.361,
+      "step": 208
+    },
+    {
+      "epoch": 2.6752000000000002,
+      "grad_norm": 0.26872536211596487,
+      "learning_rate": 2.0984147109837564e-05,
+      "loss": 0.3456,
+      "step": 209
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.2423078332853935,
+      "learning_rate": 2.0805318802188307e-05,
+      "loss": 0.3603,
+      "step": 210
+    },
+    {
+      "epoch": 2.7008,
+      "grad_norm": 0.2660821971082229,
+      "learning_rate": 2.0626425981061608e-05,
+      "loss": 0.3602,
+      "step": 211
+    },
+    {
+      "epoch": 2.7136,
+      "grad_norm": 0.2310883269089652,
+      "learning_rate": 2.0447482977425465e-05,
+      "loss": 0.3531,
+      "step": 212
+    },
+    {
+      "epoch": 2.7264,
+      "grad_norm": 0.27424614026821437,
+      "learning_rate": 2.0268504126267952e-05,
+      "loss": 0.361,
+      "step": 213
+    },
+    {
+      "epoch": 2.7392,
+      "grad_norm": 0.2250758562888674,
+      "learning_rate": 2.008950376544887e-05,
+      "loss": 0.3344,
+      "step": 214
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.30101916956153363,
+      "learning_rate": 1.9910496234551132e-05,
+      "loss": 0.365,
+      "step": 215
+    },
+    {
+      "epoch": 2.7648,
+      "grad_norm": 0.2246784009965487,
+      "learning_rate": 1.9731495873732055e-05,
+      "loss": 0.3591,
+      "step": 216
+    },
+    {
+      "epoch": 2.7776,
+      "grad_norm": 0.25711526147618635,
+      "learning_rate": 1.9552517022574542e-05,
+      "loss": 0.3625,
+      "step": 217
+    },
+    {
+      "epoch": 2.7904,
+      "grad_norm": 0.2536199289770775,
+      "learning_rate": 1.93735740189384e-05,
+      "loss": 0.3493,
+      "step": 218
+    },
+    {
+      "epoch": 2.8032,
+      "grad_norm": 0.25698296364674106,
+      "learning_rate": 1.9194681197811703e-05,
+      "loss": 0.3583,
+      "step": 219
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.26263935450286985,
+      "learning_rate": 1.901585289016244e-05,
+      "loss": 0.3605,
+      "step": 220
+    },
+    {
+      "epoch": 2.8288,
+      "grad_norm": 0.25202721644314985,
+      "learning_rate": 1.8837103421790486e-05,
+      "loss": 0.3464,
+      "step": 221
+    },
+    {
+      "epoch": 2.8416,
+      "grad_norm": 0.27102511660060785,
+      "learning_rate": 1.8658447112179952e-05,
+      "loss": 0.3703,
+      "step": 222
+    },
+    {
+      "epoch": 2.8544,
+      "grad_norm": 0.26129491255528986,
+      "learning_rate": 1.8479898273352084e-05,
+      "loss": 0.3502,
+      "step": 223
+    },
+    {
+      "epoch": 2.8672,
+      "grad_norm": 0.26114263983712904,
+      "learning_rate": 1.83014712087187e-05,
+      "loss": 0.3573,
+      "step": 224
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.25417622140863766,
+      "learning_rate": 1.8123180211936417e-05,
+      "loss": 0.342,
+      "step": 225
+    },
+    {
+      "epoch": 2.8928000000000003,
+      "grad_norm": 0.24525939867506674,
+      "learning_rate": 1.794503956576152e-05,
+      "loss": 0.355,
+      "step": 226
+    },
+    {
+      "epoch": 2.9055999999999997,
+      "grad_norm": 0.2715219261209413,
+      "learning_rate": 1.776706354090585e-05,
+      "loss": 0.3335,
+      "step": 227
+    },
+    {
+      "epoch": 2.9184,
+      "grad_norm": 0.2528857012917834,
+      "learning_rate": 1.758926639489354e-05,
+      "loss": 0.349,
+      "step": 228
+    },
+    {
+      "epoch": 2.9312,
+      "grad_norm": 0.33211410752890635,
+      "learning_rate": 1.7411662370918893e-05,
+      "loss": 0.3525,
+      "step": 229
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.23775360683138613,
+      "learning_rate": 1.7234265696705344e-05,
+      "loss": 0.3291,
+      "step": 230
+    },
+    {
+      "epoch": 2.9568,
+      "grad_norm": 0.348373721814402,
+      "learning_rate": 1.7057090583365678e-05,
+      "loss": 0.3561,
+      "step": 231
+    },
+    {
+      "epoch": 2.9696,
+      "grad_norm": 0.2989919443310957,
+      "learning_rate": 1.6880151224263646e-05,
+      "loss": 0.3548,
+      "step": 232
+    },
+    {
+      "epoch": 2.9824,
+      "grad_norm": 0.19813119471007232,
+      "learning_rate": 1.6703461793876876e-05,
+      "loss": 0.3594,
+      "step": 233
+    },
+    {
+      "epoch": 2.9952,
+      "grad_norm": 0.2630566786008279,
+      "learning_rate": 1.6527036446661396e-05,
+      "loss": 0.3589,
+      "step": 234
+    },
+    {
+      "epoch": 3.008,
+      "grad_norm": 0.6997028145200225,
+      "learning_rate": 1.635088931591775e-05,
+      "loss": 0.6686,
+      "step": 235
+    },
+    {
+      "epoch": 3.0208,
+      "grad_norm": 0.34104002600696753,
+      "learning_rate": 1.6175034512658753e-05,
+      "loss": 0.297,
+      "step": 236
+    },
+    {
+      "epoch": 3.0336,
+      "grad_norm": 0.41087129393573824,
+      "learning_rate": 1.5999486124479115e-05,
+      "loss": 0.2975,
+      "step": 237
+    },
+    {
+      "epoch": 3.0464,
+      "grad_norm": 0.4050458221374504,
+      "learning_rate": 1.5824258214426833e-05,
+      "loss": 0.3079,
+      "step": 238
+    },
+    {
+      "epoch": 3.0592,
+      "grad_norm": 0.34000028015287853,
+      "learning_rate": 1.5649364819876655e-05,
+      "loss": 0.2912,
+      "step": 239
+    },
+    {
+      "epoch": 3.072,
+      "grad_norm": 0.360253753275954,
+      "learning_rate": 1.547481995140556e-05,
+      "loss": 0.3029,
+      "step": 240
+    },
+    {
+      "epoch": 3.0848,
+      "grad_norm": 0.32772700785145326,
+      "learning_rate": 1.5300637591670357e-05,
+      "loss": 0.2984,
+      "step": 241
+    },
+    {
+      "epoch": 3.0976,
+      "grad_norm": 0.28162362643559274,
+      "learning_rate": 1.5126831694287564e-05,
+      "loss": 0.3022,
+      "step": 242
+    },
+    {
+      "epoch": 3.1104,
+      "grad_norm": 0.3132619916446047,
+      "learning_rate": 1.4953416182715566e-05,
+      "loss": 0.3022,
+      "step": 243
+    },
+    {
+      "epoch": 3.1232,
+      "grad_norm": 0.28284420914160613,
+      "learning_rate": 1.478040494913926e-05,
+      "loss": 0.3007,
+      "step": 244
+    },
+    {
+      "epoch": 3.136,
+      "grad_norm": 0.28599876556564563,
+      "learning_rate": 1.460781185335713e-05,
+      "loss": 0.3009,
+      "step": 245
+    },
+    {
+      "epoch": 3.1488,
+      "grad_norm": 0.25097124897824297,
+      "learning_rate": 1.443565072167095e-05,
+      "loss": 0.293,
+      "step": 246
+    },
+    {
+      "epoch": 3.1616,
+      "grad_norm": 0.2691028583537877,
+      "learning_rate": 1.4263935345778202e-05,
+      "loss": 0.2941,
+      "step": 247
+    },
+    {
+      "epoch": 3.1744,
+      "grad_norm": 0.2845304868532452,
+      "learning_rate": 1.409267948166718e-05,
+      "loss": 0.3075,
+      "step": 248
+    },
+    {
+      "epoch": 3.1872,
+      "grad_norm": 0.2662058110191505,
+      "learning_rate": 1.3921896848515064e-05,
+      "loss": 0.3057,
+      "step": 249
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.23910464481296942,
+      "learning_rate": 1.3751601127588849e-05,
+      "loss": 0.2841,
+      "step": 250
+    },
+    {
+      "epoch": 3.2128,
+      "grad_norm": 0.27147343006641145,
+      "learning_rate": 1.3581805961149371e-05,
+      "loss": 0.3005,
+      "step": 251
+    },
+    {
+      "epoch": 3.2256,
+      "grad_norm": 0.24373274572443954,
+      "learning_rate": 1.341252495135841e-05,
+      "loss": 0.2963,
+      "step": 252
+    },
+    {
+      "epoch": 3.2384,
+      "grad_norm": 0.2661521544403677,
+      "learning_rate": 1.324377165918906e-05,
+      "loss": 0.3163,
+      "step": 253
+    },
+    {
+      "epoch": 3.2512,
+      "grad_norm": 0.245342801299721,
+      "learning_rate": 1.3075559603339354e-05,
+      "loss": 0.3098,
+      "step": 254
+    },
+    {
+      "epoch": 3.2640000000000002,
+      "grad_norm": 0.24745784876539328,
+      "learning_rate": 1.2907902259149287e-05,
+      "loss": 0.3036,
+      "step": 255
+    },
+    {
+      "epoch": 3.2768,
+      "grad_norm": 0.24962742030451818,
+      "learning_rate": 1.274081305752135e-05,
+      "loss": 0.3097,
+      "step": 256
+    },
+    {
+      "epoch": 3.2896,
+      "grad_norm": 0.23813922999200066,
+      "learning_rate": 1.2574305383844528e-05,
+      "loss": 0.2943,
+      "step": 257
+    },
+    {
+      "epoch": 3.3024,
+      "grad_norm": 0.23222023271235778,
+      "learning_rate": 1.2408392576922075e-05,
+      "loss": 0.2975,
+      "step": 258
+    },
+    {
+      "epoch": 3.3152,
+      "grad_norm": 0.23588041850396957,
+      "learning_rate": 1.2243087927902905e-05,
+      "loss": 0.2985,
+      "step": 259
+    },
+    {
+      "epoch": 3.328,
+      "grad_norm": 0.23695273659822808,
+      "learning_rate": 1.2078404679216864e-05,
+      "loss": 0.3193,
+      "step": 260
+    },
+    {
+      "epoch": 3.3407999999999998,
+      "grad_norm": 0.22384129800841113,
+      "learning_rate": 1.1914356023513904e-05,
+      "loss": 0.2978,
+      "step": 261
+    },
+    {
+      "epoch": 3.3536,
+      "grad_norm": 0.22293737482158904,
+      "learning_rate": 1.1750955102607193e-05,
+      "loss": 0.2993,
+      "step": 262
+    },
+    {
+      "epoch": 3.3664,
+      "grad_norm": 0.255784638985407,
+      "learning_rate": 1.1588215006420374e-05,
+      "loss": 0.301,
+      "step": 263
+    },
+    {
+      "epoch": 3.3792,
+      "grad_norm": 0.22130509730837458,
+      "learning_rate": 1.1426148771938915e-05,
+      "loss": 0.2919,
+      "step": 264
+    },
+    {
+      "epoch": 3.392,
+      "grad_norm": 0.23243980161708455,
+      "learning_rate": 1.1264769382165748e-05,
+      "loss": 0.2917,
+      "step": 265
+    },
+    {
+      "epoch": 3.4048,
+      "grad_norm": 0.23212703810901136,
+      "learning_rate": 1.110408976508118e-05,
+      "loss": 0.3012,
+      "step": 266
+    },
+    {
+      "epoch": 3.4176,
+      "grad_norm": 0.20831796458613283,
+      "learning_rate": 1.094412279260726e-05,
+      "loss": 0.2919,
+      "step": 267
+    },
+    {
+      "epoch": 3.4304,
+      "grad_norm": 0.2240756219438419,
+      "learning_rate": 1.0784881279576635e-05,
+      "loss": 0.3048,
+      "step": 268
+    },
+    {
+      "epoch": 3.4432,
+      "grad_norm": 0.2207706005685621,
+      "learning_rate": 1.0626377982705929e-05,
+      "loss": 0.2888,
+      "step": 269
+    },
+    {
+      "epoch": 3.456,
+      "grad_norm": 0.23616169619311528,
+      "learning_rate": 1.0468625599573842e-05,
+      "loss": 0.3008,
+      "step": 270
+    },
+    {
+      "epoch": 3.4688,
+      "grad_norm": 0.21443123274049505,
+      "learning_rate": 1.0311636767603952e-05,
+      "loss": 0.3117,
+      "step": 271
+    },
+    {
+      "epoch": 3.4816,
+      "grad_norm": 0.2084241121958855,
+      "learning_rate": 1.0155424063052306e-05,
+      "loss": 0.2978,
+      "step": 272
+    },
+    {
+      "epoch": 3.4944,
+      "grad_norm": 0.2296631500405593,
+      "learning_rate": 1.0000000000000006e-05,
+      "loss": 0.3022,
+      "step": 273
+    },
+    {
+      "epoch": 3.5072,
+      "grad_norm": 0.20559856655631023,
+      "learning_rate": 9.84537702935065e-06,
+      "loss": 0.2898,
+      "step": 274
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 0.2135162571558101,
+      "learning_rate": 9.691567537832964e-06,
+      "loss": 0.299,
+      "step": 275
+    },
+    {
+      "epoch": 3.5328,
+      "grad_norm": 0.18261613701429247,
+      "learning_rate": 9.538583847008452e-06,
+      "loss": 0.2992,
+      "step": 276
+    },
+    {
+      "epoch": 3.5456,
+      "grad_norm": 0.22197145750478148,
+      "learning_rate": 9.386438212284372e-06,
+      "loss": 0.3204,
+      "step": 277
+    },
+    {
+      "epoch": 3.5584,
+      "grad_norm": 0.19997724440354603,
+      "learning_rate": 9.235142821931928e-06,
+      "loss": 0.3043,
+      "step": 278
+    },
+    {
+      "epoch": 3.5712,
+      "grad_norm": 0.19930148388659957,
+      "learning_rate": 9.084709796109907e-06,
+      "loss": 0.2974,
+      "step": 279
+    },
+    {
+      "epoch": 3.584,
+      "grad_norm": 0.19306872791743596,
+      "learning_rate": 8.93515118589373e-06,
+      "loss": 0.3005,
+      "step": 280
+    },
+    {
+      "epoch": 3.5968,
+      "grad_norm": 0.21911971090499133,
+      "learning_rate": 8.786478972310023e-06,
+      "loss": 0.3011,
+      "step": 281
+    },
+    {
+      "epoch": 3.6096,
+      "grad_norm": 0.20630961825525088,
+      "learning_rate": 8.638705065376887e-06,
+      "loss": 0.3023,
+      "step": 282
+    },
+    {
+      "epoch": 3.6224,
+      "grad_norm": 0.21637030841896499,
+      "learning_rate": 8.491841303149728e-06,
+      "loss": 0.2984,
+      "step": 283
+    },
+    {
+      "epoch": 3.6352,
+      "grad_norm": 0.2029316798557108,
+      "learning_rate": 8.345899450772975e-06,
+      "loss": 0.3003,
+      "step": 284
+    },
+    {
+      "epoch": 3.648,
+      "grad_norm": 0.193975360078272,
+      "learning_rate": 8.200891199537549e-06,
+      "loss": 0.3051,
+      "step": 285
+    },
+    {
+      "epoch": 3.6608,
+      "grad_norm": 0.20986849026320764,
+      "learning_rate": 8.056828165944282e-06,
+      "loss": 0.288,
+      "step": 286
+    },
+    {
+      "epoch": 3.6736,
+      "grad_norm": 0.2186914964309987,
+      "learning_rate": 7.913721890773354e-06,
+      "loss": 0.2992,
+      "step": 287
+    },
+    {
+      "epoch": 3.6864,
+      "grad_norm": 0.19236272379122993,
+      "learning_rate": 7.771583838159756e-06,
+      "loss": 0.3007,
+      "step": 288
+    },
+    {
+      "epoch": 3.6992000000000003,
+      "grad_norm": 0.21218510109020924,
+      "learning_rate": 7.630425394674903e-06,
+      "loss": 0.2986,
+      "step": 289
+    },
+    {
+      "epoch": 3.7119999999999997,
+      "grad_norm": 0.20346088237367663,
+      "learning_rate": 7.49025786841445e-06,
+      "loss": 0.2961,
+      "step": 290
+    },
+    {
+      "epoch": 3.7248,
+      "grad_norm": 0.2171416113355265,
+      "learning_rate": 7.3510924880924575e-06,
+      "loss": 0.3115,
+      "step": 291
+    },
+    {
+      "epoch": 3.7376,
+      "grad_norm": 0.2044087272447511,
+      "learning_rate": 7.212940402141808e-06,
+      "loss": 0.2981,
+      "step": 292
+    },
+    {
+      "epoch": 3.7504,
+      "grad_norm": 0.2305755913982547,
+      "learning_rate": 7.075812677821145e-06,
+      "loss": 0.2912,
+      "step": 293
+    },
+    {
+      "epoch": 3.7632,
+      "grad_norm": 0.1900301156856817,
+      "learning_rate": 6.939720300328303e-06,
+      "loss": 0.298,
+      "step": 294
+    },
+    {
+      "epoch": 3.776,
+      "grad_norm": 0.1946712044676471,
+      "learning_rate": 6.8046741719202385e-06,
+      "loss": 0.2956,
+      "step": 295
+    },
+    {
+      "epoch": 3.7888,
+      "grad_norm": 0.22310892194889975,
+      "learning_rate": 6.67068511103971e-06,
+      "loss": 0.3166,
+      "step": 296
+    },
+    {
+      "epoch": 3.8016,
+      "grad_norm": 0.1928986764225647,
+      "learning_rate": 6.537763851448593e-06,
+      "loss": 0.2968,
+      "step": 297
+    },
+    {
+      "epoch": 3.8144,
+      "grad_norm": 0.19989130193404223,
+      "learning_rate": 6.4059210413680175e-06,
+      "loss": 0.3072,
+      "step": 298
+    },
+    {
+      "epoch": 3.8272,
+      "grad_norm": 0.19104881596589784,
+      "learning_rate": 6.275167242625331e-06,
+      "loss": 0.2936,
+      "step": 299
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.19946395829690933,
+      "learning_rate": 6.145512929808013e-06,
+      "loss": 0.3086,
+      "step": 300
+    },
+    {
+      "epoch": 3.8528000000000002,
+      "grad_norm": 0.18747864622727894,
+      "learning_rate": 6.016968489424572e-06,
+      "loss": 0.2963,
+      "step": 301
+    },
+    {
+      "epoch": 3.8656,
+      "grad_norm": 0.1918720455331222,
+      "learning_rate": 5.889544219072465e-06,
+      "loss": 0.289,
+      "step": 302
+    },
+    {
+      "epoch": 3.8784,
+      "grad_norm": 0.18224359274518848,
+      "learning_rate": 5.7632503266131925e-06,
+      "loss": 0.2941,
+      "step": 303
+    },
+    {
+      "epoch": 3.8912,
+      "grad_norm": 0.1847216276283363,
+      "learning_rate": 5.638096929354522e-06,
+      "loss": 0.2986,
+      "step": 304
+    },
+    {
+      "epoch": 3.904,
+      "grad_norm": 0.20415713904772567,
+      "learning_rate": 5.514094053240035e-06,
+      "loss": 0.3042,
+      "step": 305
+    },
+    {
+      "epoch": 3.9168,
+      "grad_norm": 0.19803624174264708,
+      "learning_rate": 5.39125163204594e-06,
+      "loss": 0.2986,
+      "step": 306
+    },
+    {
+      "epoch": 3.9295999999999998,
+      "grad_norm": 0.1927102447499531,
+      "learning_rate": 5.269579506585259e-06,
+      "loss": 0.3106,
+      "step": 307
+    },
+    {
+      "epoch": 3.9424,
+      "grad_norm": 0.18312573653875455,
+      "learning_rate": 5.149087423919541e-06,
+      "loss": 0.291,
+      "step": 308
+    },
+    {
+      "epoch": 3.9552,
+      "grad_norm": 0.20080495844344906,
+      "learning_rate": 5.029785036577976e-06,
+      "loss": 0.2992,
+      "step": 309
+    },
+    {
+      "epoch": 3.968,
+      "grad_norm": 0.18852217229459217,
+      "learning_rate": 4.911681901784198e-06,
+      "loss": 0.2946,
+      "step": 310
+    },
+    {
+      "epoch": 3.9808,
+      "grad_norm": 0.1971870511076327,
+      "learning_rate": 4.794787480690597e-06,
+      "loss": 0.3105,
+      "step": 311
+    },
+    {
+      "epoch": 3.9936,
+      "grad_norm": 0.1846546580876203,
+      "learning_rate": 4.679111137620442e-06,
+      "loss": 0.3029,
+      "step": 312
+    },
+    {
+      "epoch": 4.0064,
+      "grad_norm": 0.5396691917025843,
+      "learning_rate": 4.5646621393177e-06,
+      "loss": 0.5375,
+      "step": 313
+    },
+    {
+      "epoch": 4.0192,
+      "grad_norm": 0.2890536087215895,
+      "learning_rate": 4.451449654204685e-06,
+      "loss": 0.2642,
+      "step": 314
+    },
+    {
+      "epoch": 4.032,
+      "grad_norm": 0.2640547862683752,
+      "learning_rate": 4.339482751647557e-06,
+      "loss": 0.2618,
+      "step": 315
+    },
+    {
+      "epoch": 4.0448,
+      "grad_norm": 0.22180229697520343,
+      "learning_rate": 4.228770401229824e-06,
+      "loss": 0.2759,
+      "step": 316
+    },
+    {
+      "epoch": 4.0576,
+      "grad_norm": 0.2609043014637818,
+      "learning_rate": 4.119321472033779e-06,
+      "loss": 0.2715,
+      "step": 317
+    },
+    {
+      "epoch": 4.0704,
+      "grad_norm": 0.30990208719376133,
+      "learning_rate": 4.011144731929981e-06,
+      "loss": 0.2681,
+      "step": 318
+    },
+    {
+      "epoch": 4.0832,
+      "grad_norm": 0.2898580293118983,
+      "learning_rate": 3.904248846874894e-06,
+      "loss": 0.2664,
+      "step": 319
+    },
+    {
+      "epoch": 4.096,
+      "grad_norm": 0.28007198851452264,
+      "learning_rate": 3.7986423802166705e-06,
+      "loss": 0.2768,
+      "step": 320
+    },
+    {
+      "epoch": 4.1088,
+      "grad_norm": 0.24381392643980318,
+      "learning_rate": 3.694333792009115e-06,
+      "loss": 0.2815,
+      "step": 321
+    },
+    {
+      "epoch": 4.1216,
+      "grad_norm": 0.23568735740011512,
+      "learning_rate": 3.5913314383339937e-06,
+      "loss": 0.2606,
+      "step": 322
+    },
+    {
+      "epoch": 4.1344,
+      "grad_norm": 0.2360334696648068,
+      "learning_rate": 3.4896435706316e-06,
+      "loss": 0.2614,
+      "step": 323
+    },
+    {
+      "epoch": 4.1472,
+      "grad_norm": 0.2403488922021054,
+      "learning_rate": 3.3892783350397675e-06,
+      "loss": 0.2695,
+      "step": 324
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.2240701082175525,
+      "learning_rate": 3.290243771741275e-06,
+      "loss": 0.2759,
+      "step": 325
+    },
+    {
+      "epoch": 4.1728,
+      "grad_norm": 0.214724683311387,
+      "learning_rate": 3.1925478143197418e-06,
+      "loss": 0.2562,
+      "step": 326
+    },
+    {
+      "epoch": 4.1856,
+      "grad_norm": 0.2041350595950632,
+      "learning_rate": 3.0961982891241083e-06,
+      "loss": 0.2682,
+      "step": 327
+    },
+    {
+      "epoch": 4.1984,
+      "grad_norm": 0.20224503187585574,
+      "learning_rate": 3.001202914641628e-06,
+      "loss": 0.2558,
+      "step": 328
+    },
+    {
+      "epoch": 4.2112,
+      "grad_norm": 0.20380994571218028,
+      "learning_rate": 2.907569300879596e-06,
+      "loss": 0.2638,
+      "step": 329
+    },
+    {
+      "epoch": 4.224,
+      "grad_norm": 0.20778818288979672,
+      "learning_rate": 2.815304948755664e-06,
+      "loss": 0.2658,
+      "step": 330
+    },
+    {
+      "epoch": 4.2368,
+      "grad_norm": 0.20668185213261822,
+      "learning_rate": 2.7244172494969978e-06,
+      "loss": 0.2647,
+      "step": 331
+    },
+    {
+      "epoch": 4.2496,
+      "grad_norm": 0.19166925436015203,
+      "learning_rate": 2.6349134840481294e-06,
+      "loss": 0.2652,
+      "step": 332
+    },
+    {
+      "epoch": 4.2624,
+      "grad_norm": 0.20958472909910286,
+      "learning_rate": 2.546800822487714e-06,
+      "loss": 0.2666,
+      "step": 333
+    },
+    {
+      "epoch": 4.2752,
+      "grad_norm": 0.18966665260048096,
+      "learning_rate": 2.4600863234541338e-06,
+      "loss": 0.2643,
+      "step": 334
+    },
+    {
+      "epoch": 4.288,
+      "grad_norm": 0.19021310568530453,
+      "learning_rate": 2.374776933580025e-06,
+      "loss": 0.2612,
+      "step": 335
+    },
+    {
+      "epoch": 4.3008,
+      "grad_norm": 0.1937889584861872,
+      "learning_rate": 2.2908794869358044e-06,
+      "loss": 0.2598,
+      "step": 336
+    },
+    {
+      "epoch": 4.3136,
+      "grad_norm": 0.18804445094292152,
+      "learning_rate": 2.2084007044821764e-06,
+      "loss": 0.2591,
+      "step": 337
+    },
+    {
+      "epoch": 4.3264,
+      "grad_norm": 0.18776160962683494,
+      "learning_rate": 2.127347193531757e-06,
+      "loss": 0.2674,
+      "step": 338
+    },
+    {
+      "epoch": 4.3392,
+      "grad_norm": 0.18117126201806483,
+      "learning_rate": 2.0477254472197237e-06,
+      "loss": 0.255,
+      "step": 339
+    },
+    {
+      "epoch": 4.352,
+      "grad_norm": 0.18618073145377165,
+      "learning_rate": 1.96954184398368e-06,
+      "loss": 0.2665,
+      "step": 340
+    },
+    {
+      "epoch": 4.3648,
+      "grad_norm": 0.17928312558621964,
+      "learning_rate": 1.8928026470526917e-06,
+      "loss": 0.268,
+      "step": 341
+    },
+    {
+      "epoch": 4.3776,
+      "grad_norm": 0.18504920323383642,
+      "learning_rate": 1.817514003945524e-06,
+      "loss": 0.2674,
+      "step": 342
+    },
+    {
+      "epoch": 4.3904,
+      "grad_norm": 0.18199455479077112,
+      "learning_rate": 1.743681945978184e-06,
+      "loss": 0.2613,
+      "step": 343
+    },
+    {
+      "epoch": 4.4032,
+      "grad_norm": 0.19175828594233651,
+      "learning_rate": 1.6713123877807413e-06,
+      "loss": 0.2581,
+      "step": 344
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 0.1863128522851686,
+      "learning_rate": 1.6004111268235156e-06,
+      "loss": 0.2648,
+      "step": 345
+    },
+    {
+      "epoch": 4.4288,
+      "grad_norm": 0.17774694064747787,
+      "learning_rate": 1.5309838429526714e-06,
+      "loss": 0.263,
+      "step": 346
+    },
+    {
+      "epoch": 4.4416,
+      "grad_norm": 0.1782659108979163,
+      "learning_rate": 1.4630360979351644e-06,
+      "loss": 0.2595,
+      "step": 347
+    },
+    {
+      "epoch": 4.4544,
+      "grad_norm": 0.18485815260648936,
+      "learning_rate": 1.396573335013236e-06,
+      "loss": 0.2705,
+      "step": 348
+    },
+    {
+      "epoch": 4.4672,
+      "grad_norm": 0.178378794238484,
+      "learning_rate": 1.3316008784683265e-06,
+      "loss": 0.2648,
+      "step": 349
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.1923571033693555,
+      "learning_rate": 1.2681239331945695e-06,
+      "loss": 0.2664,
+      "step": 350
+    },
+    {
+      "epoch": 4.4928,
+      "grad_norm": 0.18706802997289357,
+      "learning_rate": 1.2061475842818337e-06,
+      "loss": 0.2693,
+      "step": 351
+    },
+    {
+      "epoch": 4.5056,
+      "grad_norm": 0.18057336658799308,
+      "learning_rate": 1.1456767966083393e-06,
+      "loss": 0.2689,
+      "step": 352
+    },
+    {
+      "epoch": 4.5184,
+      "grad_norm": 0.16993427340804612,
+      "learning_rate": 1.086716414442952e-06,
+      "loss": 0.2545,
+      "step": 353
+    },
+    {
+      "epoch": 4.5312,
+      "grad_norm": 0.17978667488327493,
+      "learning_rate": 1.0292711610570904e-06,
+      "loss": 0.2728,
+      "step": 354
+    },
+    {
+      "epoch": 4.5440000000000005,
+      "grad_norm": 0.1759031439220219,
+      "learning_rate": 9.733456383463658e-07,
+      "loss": 0.2742,
+      "step": 355
+    },
+    {
+      "epoch": 4.5568,
+      "grad_norm": 0.16819019314255032,
+      "learning_rate": 9.189443264619102e-07,
+      "loss": 0.2654,
+      "step": 356
+    },
+    {
+      "epoch": 4.5696,
+      "grad_norm": 0.17684706017433846,
+      "learning_rate": 8.660715834514977e-07,
+      "loss": 0.2623,
+      "step": 357
+    },
+    {
+      "epoch": 4.5824,
+      "grad_norm": 0.1780885287188612,
+      "learning_rate": 8.147316449103959e-07,
+      "loss": 0.2666,
+      "step": 358
+    },
+    {
+      "epoch": 4.5952,
+      "grad_norm": 0.17505138984335916,
+      "learning_rate": 7.649286236420806e-07,
+      "loss": 0.2727,
+      "step": 359
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 0.16994562099187394,
+      "learning_rate": 7.166665093287539e-07,
+      "loss": 0.2565,
+      "step": 360
+    },
+    {
+      "epoch": 4.6208,
+      "grad_norm": 0.16967779918455525,
+      "learning_rate": 6.69949168211721e-07,
+      "loss": 0.2616,
+      "step": 361
+    },
+    {
+      "epoch": 4.6336,
+      "grad_norm": 0.17202986180718627,
+      "learning_rate": 6.247803427816945e-07,
+      "loss": 0.263,
+      "step": 362
+    },
+    {
+      "epoch": 4.6464,
+      "grad_norm": 0.17110436252240552,
+      "learning_rate": 5.811636514789598e-07,
+      "loss": 0.2639,
+      "step": 363
+    },
+    {
+      "epoch": 4.6592,
+      "grad_norm": 0.17182100115105445,
+      "learning_rate": 5.391025884035239e-07,
+      "loss": 0.2568,
+      "step": 364
+    },
+    {
+      "epoch": 4.672,
+      "grad_norm": 0.16502389754333371,
+      "learning_rate": 4.986005230351954e-07,
+      "loss": 0.2597,
+      "step": 365
+    },
+    {
+      "epoch": 4.6848,
+      "grad_norm": 0.173198753106447,
+      "learning_rate": 4.5966069996365993e-07,
+      "loss": 0.2687,
+      "step": 366
+    },
+    {
+      "epoch": 4.6975999999999996,
+      "grad_norm": 0.16925658628130652,
+      "learning_rate": 4.22286238628562e-07,
+      "loss": 0.2649,
+      "step": 367
+    },
+    {
+      "epoch": 4.7104,
+      "grad_norm": 0.1694579169583432,
+      "learning_rate": 3.8648013306960664e-07,
+      "loss": 0.2563,
+      "step": 368
+    },
+    {
+      "epoch": 4.7232,
+      "grad_norm": 0.17179795829254527,
+      "learning_rate": 3.522452516867048e-07,
+      "loss": 0.2711,
+      "step": 369
+    },
+    {
+      "epoch": 4.736,
+      "grad_norm": 0.16687608279205143,
+      "learning_rate": 3.1958433701019697e-07,
+      "loss": 0.2572,
+      "step": 370
+    },
+    {
+      "epoch": 4.7488,
+      "grad_norm": 0.16976180283763298,
+      "learning_rate": 2.8850000548115155e-07,
+      "loss": 0.2637,
+      "step": 371
+    },
+    {
+      "epoch": 4.7616,
+      "grad_norm": 0.16604126148098586,
+      "learning_rate": 2.5899474724174313e-07,
+      "loss": 0.2463,
+      "step": 372
+    },
+    {
+      "epoch": 4.7744,
+      "grad_norm": 0.1715658554432001,
+      "learning_rate": 2.3107092593579905e-07,
+      "loss": 0.265,
+      "step": 373
+    },
+    {
+      "epoch": 4.7872,
+      "grad_norm": 0.1739506001586336,
+      "learning_rate": 2.0473077851942858e-07,
+      "loss": 0.2659,
+      "step": 374
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.17018709058523263,
+      "learning_rate": 1.799764150818306e-07,
+      "loss": 0.2572,
+      "step": 375
+    },
+    {
+      "epoch": 4.8128,
+      "grad_norm": 0.16785428847738693,
+      "learning_rate": 1.5680981867625566e-07,
+      "loss": 0.254,
+      "step": 376
+    },
+    {
+      "epoch": 4.8256,
+      "grad_norm": 0.16831813887980965,
+      "learning_rate": 1.3523284516113955e-07,
+      "loss": 0.2607,
+      "step": 377
+    },
+    {
+      "epoch": 4.8384,
+      "grad_norm": 0.1723003598800097,
+      "learning_rate": 1.1524722305144231e-07,
+      "loss": 0.2584,
+      "step": 378
+    },
+    {
+      "epoch": 4.8512,
+      "grad_norm": 0.17539264327127366,
+      "learning_rate": 9.685455338016347e-08,
+      "loss": 0.2672,
+      "step": 379
+    },
+    {
+      "epoch": 4.864,
+      "grad_norm": 0.1713708427354091,
+      "learning_rate": 8.005630957010014e-08,
+      "loss": 0.2632,
+      "step": 380
+    },
+    {
+      "epoch": 4.8768,
+      "grad_norm": 0.1685673876803162,
+      "learning_rate": 6.485383731580142e-08,
+      "loss": 0.2701,
+      "step": 381
+    },
+    {
+      "epoch": 4.8896,
+      "grad_norm": 0.166606338953714,
+      "learning_rate": 5.1248354475768034e-08,
+      "loss": 0.259,
+      "step": 382
+    },
+    {
+      "epoch": 4.9024,
+      "grad_norm": 0.16731443926355397,
+      "learning_rate": 3.924095097489922e-08,
+      "loss": 0.2526,
+      "step": 383
+    },
+    {
+      "epoch": 4.9152000000000005,
+      "grad_norm": 0.1685044586685876,
+      "learning_rate": 2.8832588717164766e-08,
+      "loss": 0.2686,
+      "step": 384
+    },
+    {
+      "epoch": 4.928,
+      "grad_norm": 0.16691305854993616,
+      "learning_rate": 2.0024101508555604e-08,
+      "loss": 0.2618,
+      "step": 385
+    },
+    {
+      "epoch": 4.9408,
+      "grad_norm": 0.1684797201052588,
+      "learning_rate": 1.281619499029274e-08,
+      "loss": 0.2675,
+      "step": 386
+    },
+    {
+      "epoch": 4.9536,
+      "grad_norm": 0.1861012245822086,
+      "learning_rate": 7.209446582292501e-09,
+      "loss": 0.2592,
+      "step": 387
+    },
+    {
+      "epoch": 4.9664,
+      "grad_norm": 0.17484645168594473,
+      "learning_rate": 3.2043054369057523e-09,
+      "loss": 0.2755,
+      "step": 388
+    },
+    {
+      "epoch": 4.9792,
+      "grad_norm": 0.16579922216192233,
+      "learning_rate": 8.010924029533406e-10,
+      "loss": 0.2595,
+      "step": 389
+    },
+    {
+      "epoch": 4.992,
+      "grad_norm": 0.16627934732470429,
+      "learning_rate": 0.0,
+      "loss": 0.2657,
+      "step": 390
+    },
+    {
+      "epoch": 4.992,
+      "step": 390,
+      "total_flos": 1.878482348849234e+18,
+      "train_loss": 0.37849522767922816,
+      "train_runtime": 19752.9737,
+      "train_samples_per_second": 2.531,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 390,
+  "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": 1.878482348849234e+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 sha256:00d9f6e8322db62b37766df5a5dc07171ad87f0b9a581285e8244fe8911d6e52
+size 7352