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: b1_math_top_8_3k
+  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. -->
+
+# b1_math_top_8_3k
+
+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/b1_math_top_8_3k 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 24
+- total_train_batch_size: 96
+- total_eval_batch_size: 32
+- 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: 7.0
+
+### 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": 6.850632911392405,
+    "total_flos": 3.4820098135320166e+17,
+    "train_loss": 0.32787186798772644,
+    "train_runtime": 15227.7577,
+    "train_samples_per_second": 1.453,
+    "train_steps_per_second": 0.015
+}

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 sha256:5ffd10b4c14f56466d61a2140c3f6785a00ff81ed4ee24f480e9777d3bbe5461
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590229b810a9ea2af0bf3d988278e3d240687b251b71a07aefbe337717d36701
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f823026349439da9638e8ec4f3be1f0de3406fef9d1edb2a68f50f28975474
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bf28f1d46a5d7a319f250ecf43e11706890d611bb373f32d66b51d8ca0bb27
+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/Apr19_06-26-51_jrc0912/events.out.tfevents.1745036842.jrc0912.3461994.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01d67bb6e2ec86241f09da260a38bc5b9261e51dfa21b7074bf7622de951462
+size 5492

runs/Apr19_07-16-07_jpbot-001-02.jupiter.internal/events.out.tfevents.1745039787.jpbot-001-02.jupiter.internal.1888603.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c36d833bc38510e07ac692b5a71bbf2f21608d66d9af3d667d8125fa1d4c80a
+size 52625

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": "2025-04-19 07:16:07", "end_time": "2025-04-19 11:30:21"}

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": 6.850632911392405,
+    "total_flos": 3.4820098135320166e+17,
+    "train_loss": 0.32787186798772644,
+    "train_runtime": 15227.7577,
+    "train_samples_per_second": 1.453,
+    "train_steps_per_second": 0.015
+}

trainer_log.jsonl

@@ -0,0 +1,225 @@
+{"current_steps": 1, "total_steps": 224, "loss": 0.8653, "lr": 8.695652173913044e-07, "epoch": 0.030379746835443037, "percentage": 0.45, "elapsed_time": "0:01:10", "remaining_time": "4:20:42"}
+{"current_steps": 2, "total_steps": 224, "loss": 0.8939, "lr": 1.7391304347826088e-06, "epoch": 0.060759493670886074, "percentage": 0.89, "elapsed_time": "0:02:21", "remaining_time": "4:21:24"}
+{"current_steps": 3, "total_steps": 224, "loss": 0.8222, "lr": 2.6086956521739132e-06, "epoch": 0.09113924050632911, "percentage": 1.34, "elapsed_time": "0:03:24", "remaining_time": "4:10:37"}
+{"current_steps": 4, "total_steps": 224, "loss": 0.861, "lr": 3.4782608695652175e-06, "epoch": 0.12151898734177215, "percentage": 1.79, "elapsed_time": "0:04:28", "remaining_time": "4:06:34"}
+{"current_steps": 5, "total_steps": 224, "loss": 0.8116, "lr": 4.347826086956522e-06, "epoch": 0.1518987341772152, "percentage": 2.23, "elapsed_time": "0:05:38", "remaining_time": "4:07:18"}
+{"current_steps": 6, "total_steps": 224, "loss": 0.7778, "lr": 5.2173913043478265e-06, "epoch": 0.18227848101265823, "percentage": 2.68, "elapsed_time": "0:06:51", "remaining_time": "4:08:58"}
+{"current_steps": 7, "total_steps": 224, "loss": 0.775, "lr": 6.086956521739132e-06, "epoch": 0.21265822784810126, "percentage": 3.12, "elapsed_time": "0:07:50", "remaining_time": "4:03:04"}
+{"current_steps": 8, "total_steps": 224, "loss": 0.7985, "lr": 6.956521739130435e-06, "epoch": 0.2430379746835443, "percentage": 3.57, "elapsed_time": "0:08:54", "remaining_time": "4:00:31"}
+{"current_steps": 9, "total_steps": 224, "loss": 0.7189, "lr": 7.82608695652174e-06, "epoch": 0.27341772151898736, "percentage": 4.02, "elapsed_time": "0:10:05", "remaining_time": "4:00:57"}
+{"current_steps": 10, "total_steps": 224, "loss": 0.7316, "lr": 8.695652173913044e-06, "epoch": 0.3037974683544304, "percentage": 4.46, "elapsed_time": "0:11:23", "remaining_time": "4:03:45"}
+{"current_steps": 11, "total_steps": 224, "loss": 0.7169, "lr": 9.565217391304349e-06, "epoch": 0.3341772151898734, "percentage": 4.91, "elapsed_time": "0:12:42", "remaining_time": "4:06:10"}
+{"current_steps": 12, "total_steps": 224, "loss": 0.6868, "lr": 1.0434782608695653e-05, "epoch": 0.36455696202531646, "percentage": 5.36, "elapsed_time": "0:13:53", "remaining_time": "4:05:31"}
+{"current_steps": 13, "total_steps": 224, "loss": 0.6444, "lr": 1.1304347826086957e-05, "epoch": 0.3949367088607595, "percentage": 5.8, "elapsed_time": "0:14:54", "remaining_time": "4:02:01"}
+{"current_steps": 14, "total_steps": 224, "loss": 0.65, "lr": 1.2173913043478263e-05, "epoch": 0.4253164556962025, "percentage": 6.25, "elapsed_time": "0:15:51", "remaining_time": "3:57:54"}
+{"current_steps": 15, "total_steps": 224, "loss": 0.6213, "lr": 1.3043478260869566e-05, "epoch": 0.45569620253164556, "percentage": 6.7, "elapsed_time": "0:17:03", "remaining_time": "3:57:36"}
+{"current_steps": 16, "total_steps": 224, "loss": 0.6337, "lr": 1.391304347826087e-05, "epoch": 0.4860759493670886, "percentage": 7.14, "elapsed_time": "0:18:06", "remaining_time": "3:55:24"}
+{"current_steps": 17, "total_steps": 224, "loss": 0.6227, "lr": 1.4782608695652174e-05, "epoch": 0.5164556962025316, "percentage": 7.59, "elapsed_time": "0:19:16", "remaining_time": "3:54:38"}
+{"current_steps": 18, "total_steps": 224, "loss": 0.6338, "lr": 1.565217391304348e-05, "epoch": 0.5468354430379747, "percentage": 8.04, "elapsed_time": "0:20:22", "remaining_time": "3:53:07"}
+{"current_steps": 19, "total_steps": 224, "loss": 0.6246, "lr": 1.6521739130434785e-05, "epoch": 0.5772151898734177, "percentage": 8.48, "elapsed_time": "0:21:32", "remaining_time": "3:52:29"}
+{"current_steps": 20, "total_steps": 224, "loss": 0.6125, "lr": 1.739130434782609e-05, "epoch": 0.6075949367088608, "percentage": 8.93, "elapsed_time": "0:22:49", "remaining_time": "3:52:49"}
+{"current_steps": 21, "total_steps": 224, "loss": 0.569, "lr": 1.8260869565217393e-05, "epoch": 0.6379746835443038, "percentage": 9.38, "elapsed_time": "0:23:56", "remaining_time": "3:51:24"}
+{"current_steps": 22, "total_steps": 224, "loss": 0.5777, "lr": 1.9130434782608697e-05, "epoch": 0.6683544303797468, "percentage": 9.82, "elapsed_time": "0:25:00", "remaining_time": "3:49:36"}
+{"current_steps": 23, "total_steps": 224, "loss": 0.6277, "lr": 2e-05, "epoch": 0.6987341772151898, "percentage": 10.27, "elapsed_time": "0:26:12", "remaining_time": "3:49:02"}
+{"current_steps": 24, "total_steps": 224, "loss": 0.5953, "lr": 1.999877856940653e-05, "epoch": 0.7291139240506329, "percentage": 10.71, "elapsed_time": "0:27:24", "remaining_time": "3:48:25"}
+{"current_steps": 25, "total_steps": 224, "loss": 0.6098, "lr": 1.999511457600466e-05, "epoch": 0.759493670886076, "percentage": 11.16, "elapsed_time": "0:28:15", "remaining_time": "3:44:53"}
+{"current_steps": 26, "total_steps": 224, "loss": 0.5633, "lr": 1.9989008914857115e-05, "epoch": 0.789873417721519, "percentage": 11.61, "elapsed_time": "0:29:14", "remaining_time": "3:42:41"}
+{"current_steps": 27, "total_steps": 224, "loss": 0.5583, "lr": 1.998046307749216e-05, "epoch": 0.8202531645569621, "percentage": 12.05, "elapsed_time": "0:30:01", "remaining_time": "3:39:01"}
+{"current_steps": 28, "total_steps": 224, "loss": 0.5541, "lr": 1.9969479151539238e-05, "epoch": 0.850632911392405, "percentage": 12.5, "elapsed_time": "0:30:57", "remaining_time": "3:36:40"}
+{"current_steps": 29, "total_steps": 224, "loss": 0.5612, "lr": 1.9956059820218982e-05, "epoch": 0.8810126582278481, "percentage": 12.95, "elapsed_time": "0:32:11", "remaining_time": "3:36:24"}
+{"current_steps": 30, "total_steps": 224, "loss": 0.5655, "lr": 1.9940208361687762e-05, "epoch": 0.9113924050632911, "percentage": 13.39, "elapsed_time": "0:33:12", "remaining_time": "3:34:45"}
+{"current_steps": 31, "total_steps": 224, "loss": 0.5887, "lr": 1.9921928648236855e-05, "epoch": 0.9417721518987342, "percentage": 13.84, "elapsed_time": "0:34:16", "remaining_time": "3:33:21"}
+{"current_steps": 32, "total_steps": 224, "loss": 0.5631, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "0:35:25", "remaining_time": "3:32:32"}
+{"current_steps": 33, "total_steps": 224, "loss": 0.6821, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "0:37:17", "remaining_time": "3:35:52"}
+{"current_steps": 34, "total_steps": 224, "loss": 0.5633, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "0:38:30", "remaining_time": "3:35:09"}
+{"current_steps": 35, "total_steps": 224, "loss": 0.4339, "lr": 1.982462542875576e-05, "epoch": 1.070886075949367, "percentage": 15.62, "elapsed_time": "0:39:39", "remaining_time": "3:34:08"}
+{"current_steps": 36, "total_steps": 224, "loss": 0.4979, "lr": 1.979428324547432e-05, "epoch": 1.1012658227848102, "percentage": 16.07, "elapsed_time": "0:40:56", "remaining_time": "3:33:48"}
+{"current_steps": 37, "total_steps": 224, "loss": 0.5448, "lr": 1.9761548454753455e-05, "epoch": 1.1316455696202532, "percentage": 16.52, "elapsed_time": "0:41:56", "remaining_time": "3:32:00"}
+{"current_steps": 38, "total_steps": 224, "loss": 0.4755, "lr": 1.972642905324813e-05, "epoch": 1.1620253164556962, "percentage": 16.96, "elapsed_time": "0:43:10", "remaining_time": "3:31:19"}
+{"current_steps": 39, "total_steps": 224, "loss": 0.449, "lr": 1.9688933620140638e-05, "epoch": 1.1924050632911392, "percentage": 17.41, "elapsed_time": "0:44:02", "remaining_time": "3:28:56"}
+{"current_steps": 40, "total_steps": 224, "loss": 0.517, "lr": 1.96490713150448e-05, "epoch": 1.2227848101265824, "percentage": 17.86, "elapsed_time": "0:45:06", "remaining_time": "3:27:30"}
+{"current_steps": 41, "total_steps": 224, "loss": 0.4576, "lr": 1.9606851875768404e-05, "epoch": 1.2531645569620253, "percentage": 18.3, "elapsed_time": "0:46:02", "remaining_time": "3:25:30"}
+{"current_steps": 42, "total_steps": 224, "loss": 0.4684, "lr": 1.956228561593441e-05, "epoch": 1.2835443037974683, "percentage": 18.75, "elapsed_time": "0:47:07", "remaining_time": "3:24:11"}
+{"current_steps": 43, "total_steps": 224, "loss": 0.4712, "lr": 1.9515383422461457e-05, "epoch": 1.3139240506329113, "percentage": 19.2, "elapsed_time": "0:48:06", "remaining_time": "3:22:29"}
+{"current_steps": 44, "total_steps": 224, "loss": 0.4912, "lr": 1.9466156752904344e-05, "epoch": 1.3443037974683545, "percentage": 19.64, "elapsed_time": "0:49:12", "remaining_time": "3:21:16"}
+{"current_steps": 45, "total_steps": 224, "loss": 0.5171, "lr": 1.9414617632655114e-05, "epoch": 1.3746835443037975, "percentage": 20.09, "elapsed_time": "0:50:25", "remaining_time": "3:20:33"}
+{"current_steps": 46, "total_steps": 224, "loss": 0.4755, "lr": 1.9360778652005416e-05, "epoch": 1.4050632911392404, "percentage": 20.54, "elapsed_time": "0:51:23", "remaining_time": "3:18:53"}
+{"current_steps": 47, "total_steps": 224, "loss": 0.5238, "lr": 1.9304652963070868e-05, "epoch": 1.4354430379746836, "percentage": 20.98, "elapsed_time": "0:52:32", "remaining_time": "3:17:50"}
+{"current_steps": 48, "total_steps": 224, "loss": 0.4681, "lr": 1.9246254276578175e-05, "epoch": 1.4658227848101266, "percentage": 21.43, "elapsed_time": "0:53:38", "remaining_time": "3:16:40"}
+{"current_steps": 49, "total_steps": 224, "loss": 0.4942, "lr": 1.9185596858515797e-05, "epoch": 1.4962025316455696, "percentage": 21.88, "elapsed_time": "0:54:47", "remaining_time": "3:15:39"}
+{"current_steps": 50, "total_steps": 224, "loss": 0.4346, "lr": 1.9122695526648968e-05, "epoch": 1.5265822784810128, "percentage": 22.32, "elapsed_time": "0:56:01", "remaining_time": "3:14:57"}
+{"current_steps": 51, "total_steps": 224, "loss": 0.551, "lr": 1.905756564689991e-05, "epoch": 1.5569620253164556, "percentage": 22.77, "elapsed_time": "0:57:10", "remaining_time": "3:13:58"}
+{"current_steps": 52, "total_steps": 224, "loss": 0.4564, "lr": 1.8990223129594146e-05, "epoch": 1.5873417721518988, "percentage": 23.21, "elapsed_time": "0:58:19", "remaining_time": "3:12:55"}
+{"current_steps": 53, "total_steps": 224, "loss": 0.5452, "lr": 1.8920684425573865e-05, "epoch": 1.6177215189873417, "percentage": 23.66, "elapsed_time": "0:59:29", "remaining_time": "3:11:57"}
+{"current_steps": 54, "total_steps": 224, "loss": 0.454, "lr": 1.884896652217917e-05, "epoch": 1.6481012658227847, "percentage": 24.11, "elapsed_time": "1:00:36", "remaining_time": "3:10:49"}
+{"current_steps": 55, "total_steps": 224, "loss": 0.4683, "lr": 1.877508693909831e-05, "epoch": 1.678481012658228, "percentage": 24.55, "elapsed_time": "1:01:43", "remaining_time": "3:09:38"}
+{"current_steps": 56, "total_steps": 224, "loss": 0.4536, "lr": 1.8699063724087905e-05, "epoch": 1.7088607594936709, "percentage": 25.0, "elapsed_time": "1:02:49", "remaining_time": "3:08:29"}
+{"current_steps": 57, "total_steps": 224, "loss": 0.4863, "lr": 1.862091544856407e-05, "epoch": 1.7392405063291139, "percentage": 25.45, "elapsed_time": "1:03:56", "remaining_time": "3:07:19"}
+{"current_steps": 58, "total_steps": 224, "loss": 0.4862, "lr": 1.854066120306571e-05, "epoch": 1.769620253164557, "percentage": 25.89, "elapsed_time": "1:05:05", "remaining_time": "3:06:17"}
+{"current_steps": 59, "total_steps": 224, "loss": 0.5069, "lr": 1.8458320592590976e-05, "epoch": 1.8, "percentage": 26.34, "elapsed_time": "1:06:21", "remaining_time": "3:05:34"}
+{"current_steps": 60, "total_steps": 224, "loss": 0.5135, "lr": 1.837391373180801e-05, "epoch": 1.830379746835443, "percentage": 26.79, "elapsed_time": "1:07:19", "remaining_time": "3:04:00"}
+{"current_steps": 61, "total_steps": 224, "loss": 0.4328, "lr": 1.8287461240141217e-05, "epoch": 1.8607594936708862, "percentage": 27.23, "elapsed_time": "1:08:17", "remaining_time": "3:02:28"}
+{"current_steps": 62, "total_steps": 224, "loss": 0.4992, "lr": 1.8198984236734246e-05, "epoch": 1.891139240506329, "percentage": 27.68, "elapsed_time": "1:09:20", "remaining_time": "3:01:12"}
+{"current_steps": 63, "total_steps": 224, "loss": 0.4924, "lr": 1.8108504335290852e-05, "epoch": 1.9215189873417722, "percentage": 28.12, "elapsed_time": "1:10:27", "remaining_time": "3:00:02"}
+{"current_steps": 64, "total_steps": 224, "loss": 0.4423, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "1:11:24", "remaining_time": "2:58:30"}
+{"current_steps": 65, "total_steps": 224, "loss": 0.5937, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "1:12:44", "remaining_time": "2:57:55"}
+{"current_steps": 66, "total_steps": 224, "loss": 0.4914, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "1:14:24", "remaining_time": "2:58:07"}
+{"current_steps": 67, "total_steps": 224, "loss": 0.384, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "1:15:30", "remaining_time": "2:56:56"}
+{"current_steps": 68, "total_steps": 224, "loss": 0.4095, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "1:16:28", "remaining_time": "2:55:27"}
+{"current_steps": 69, "total_steps": 224, "loss": 0.3975, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "1:17:38", "remaining_time": "2:54:23"}
+{"current_steps": 70, "total_steps": 224, "loss": 0.3921, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "1:18:52", "remaining_time": "2:53:30"}
+{"current_steps": 71, "total_steps": 224, "loss": 0.3463, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "1:19:48", "remaining_time": "2:51:59"}
+{"current_steps": 72, "total_steps": 224, "loss": 0.3745, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "1:21:04", "remaining_time": "2:51:09"}
+{"current_steps": 73, "total_steps": 224, "loss": 0.3469, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "1:22:02", "remaining_time": "2:49:42"}
+{"current_steps": 74, "total_steps": 224, "loss": 0.3958, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "1:23:17", "remaining_time": "2:48:49"}
+{"current_steps": 75, "total_steps": 224, "loss": 0.3908, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "1:24:23", "remaining_time": "2:47:40"}
+{"current_steps": 76, "total_steps": 224, "loss": 0.3618, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "1:25:29", "remaining_time": "2:46:29"}
+{"current_steps": 77, "total_steps": 224, "loss": 0.4001, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "1:26:36", "remaining_time": "2:45:21"}
+{"current_steps": 78, "total_steps": 224, "loss": 0.3697, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "1:27:42", "remaining_time": "2:44:10"}
+{"current_steps": 79, "total_steps": 224, "loss": 0.4042, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "1:28:56", "remaining_time": "2:43:14"}
+{"current_steps": 80, "total_steps": 224, "loss": 0.3748, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "1:30:09", "remaining_time": "2:42:16"}
+{"current_steps": 81, "total_steps": 224, "loss": 0.3272, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "1:31:09", "remaining_time": "2:40:56"}
+{"current_steps": 82, "total_steps": 224, "loss": 0.3984, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "1:32:34", "remaining_time": "2:40:18"}
+{"current_steps": 83, "total_steps": 224, "loss": 0.3488, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "1:33:38", "remaining_time": "2:39:04"}
+{"current_steps": 84, "total_steps": 224, "loss": 0.3743, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "1:34:48", "remaining_time": "2:38:00"}
+{"current_steps": 85, "total_steps": 224, "loss": 0.3499, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "1:35:52", "remaining_time": "2:36:46"}
+{"current_steps": 86, "total_steps": 224, "loss": 0.3749, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "1:37:06", "remaining_time": "2:35:49"}
+{"current_steps": 87, "total_steps": 224, "loss": 0.3782, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "1:38:11", "remaining_time": "2:34:36"}
+{"current_steps": 88, "total_steps": 224, "loss": 0.3816, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "1:39:13", "remaining_time": "2:33:20"}
+{"current_steps": 89, "total_steps": 224, "loss": 0.3854, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "1:40:19", "remaining_time": "2:32:10"}
+{"current_steps": 90, "total_steps": 224, "loss": 0.3318, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "1:41:19", "remaining_time": "2:30:51"}
+{"current_steps": 91, "total_steps": 224, "loss": 0.4053, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "1:42:25", "remaining_time": "2:29:42"}
+{"current_steps": 92, "total_steps": 224, "loss": 0.3331, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "1:43:15", "remaining_time": "2:28:09"}
+{"current_steps": 93, "total_steps": 224, "loss": 0.3269, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "1:44:12", "remaining_time": "2:26:47"}
+{"current_steps": 94, "total_steps": 224, "loss": 0.4065, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "1:45:23", "remaining_time": "2:25:45"}
+{"current_steps": 95, "total_steps": 224, "loss": 0.3782, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "1:46:32", "remaining_time": "2:24:40"}
+{"current_steps": 96, "total_steps": 224, "loss": 0.4034, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "1:47:40", "remaining_time": "2:23:33"}
+{"current_steps": 97, "total_steps": 224, "loss": 0.3235, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "1:48:32", "remaining_time": "2:22:06"}
+{"current_steps": 98, "total_steps": 224, "loss": 0.4883, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "1:49:50", "remaining_time": "2:21:13"}
+{"current_steps": 99, "total_steps": 224, "loss": 0.2912, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "1:51:24", "remaining_time": "2:20:40"}
+{"current_steps": 100, "total_steps": 224, "loss": 0.2993, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "1:52:49", "remaining_time": "2:19:53"}
+{"current_steps": 101, "total_steps": 224, "loss": 0.2829, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "1:53:56", "remaining_time": "2:18:45"}
+{"current_steps": 102, "total_steps": 224, "loss": 0.2862, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "1:55:11", "remaining_time": "2:17:46"}
+{"current_steps": 103, "total_steps": 224, "loss": 0.3082, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "1:56:06", "remaining_time": "2:16:23"}
+{"current_steps": 104, "total_steps": 224, "loss": 0.2775, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "1:57:02", "remaining_time": "2:15:02"}
+{"current_steps": 105, "total_steps": 224, "loss": 0.2484, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "1:58:00", "remaining_time": "2:13:44"}
+{"current_steps": 106, "total_steps": 224, "loss": 0.2713, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "1:59:07", "remaining_time": "2:12:36"}
+{"current_steps": 107, "total_steps": 224, "loss": 0.2809, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "2:00:07", "remaining_time": "2:11:20"}
+{"current_steps": 108, "total_steps": 224, "loss": 0.2771, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "2:01:15", "remaining_time": "2:10:13"}
+{"current_steps": 109, "total_steps": 224, "loss": 0.2785, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "2:02:26", "remaining_time": "2:09:10"}
+{"current_steps": 110, "total_steps": 224, "loss": 0.2655, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "2:03:32", "remaining_time": "2:08:01"}
+{"current_steps": 111, "total_steps": 224, "loss": 0.2876, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "2:04:50", "remaining_time": "2:07:05"}
+{"current_steps": 112, "total_steps": 224, "loss": 0.2645, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "2:06:06", "remaining_time": "2:06:06"}
+{"current_steps": 113, "total_steps": 224, "loss": 0.2843, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "2:07:07", "remaining_time": "2:04:52"}
+{"current_steps": 114, "total_steps": 224, "loss": 0.2705, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "2:08:13", "remaining_time": "2:03:43"}
+{"current_steps": 115, "total_steps": 224, "loss": 0.2405, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "2:09:01", "remaining_time": "2:02:18"}
+{"current_steps": 116, "total_steps": 224, "loss": 0.2874, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "2:10:12", "remaining_time": "2:01:14"}
+{"current_steps": 117, "total_steps": 224, "loss": 0.2722, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "2:11:21", "remaining_time": "2:00:07"}
+{"current_steps": 118, "total_steps": 224, "loss": 0.2606, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "2:12:22", "remaining_time": "1:58:55"}
+{"current_steps": 119, "total_steps": 224, "loss": 0.2627, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "2:13:35", "remaining_time": "1:57:52"}
+{"current_steps": 120, "total_steps": 224, "loss": 0.2778, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "2:14:32", "remaining_time": "1:56:36"}
+{"current_steps": 121, "total_steps": 224, "loss": 0.2782, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "2:15:48", "remaining_time": "1:55:36"}
+{"current_steps": 122, "total_steps": 224, "loss": 0.2822, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "2:16:41", "remaining_time": "1:54:17"}
+{"current_steps": 123, "total_steps": 224, "loss": 0.2624, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "2:17:28", "remaining_time": "1:52:52"}
+{"current_steps": 124, "total_steps": 224, "loss": 0.2518, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "2:18:31", "remaining_time": "1:51:43"}
+{"current_steps": 125, "total_steps": 224, "loss": 0.2679, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "2:19:50", "remaining_time": "1:50:44"}
+{"current_steps": 126, "total_steps": 224, "loss": 0.2617, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "2:20:55", "remaining_time": "1:49:36"}
+{"current_steps": 127, "total_steps": 224, "loss": 0.2857, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "2:22:06", "remaining_time": "1:48:32"}
+{"current_steps": 128, "total_steps": 224, "loss": 0.2676, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "2:23:30", "remaining_time": "1:47:38"}
+{"current_steps": 129, "total_steps": 224, "loss": 0.2743, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "2:24:33", "remaining_time": "1:46:27"}
+{"current_steps": 130, "total_steps": 224, "loss": 0.2827, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "2:25:39", "remaining_time": "1:45:19"}
+{"current_steps": 131, "total_steps": 224, "loss": 0.3169, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "2:27:24", "remaining_time": "1:44:38"}
+{"current_steps": 132, "total_steps": 224, "loss": 0.2049, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "2:28:23", "remaining_time": "1:43:25"}
+{"current_steps": 133, "total_steps": 224, "loss": 0.2082, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "2:29:28", "remaining_time": "1:42:16"}
+{"current_steps": 134, "total_steps": 224, "loss": 0.1795, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "2:30:26", "remaining_time": "1:41:02"}
+{"current_steps": 135, "total_steps": 224, "loss": 0.2008, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "2:31:37", "remaining_time": "1:39:57"}
+{"current_steps": 136, "total_steps": 224, "loss": 0.2018, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "2:32:50", "remaining_time": "1:38:53"}
+{"current_steps": 137, "total_steps": 224, "loss": 0.1703, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "2:33:46", "remaining_time": "1:37:39"}
+{"current_steps": 138, "total_steps": 224, "loss": 0.2185, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "2:35:00", "remaining_time": "1:36:35"}
+{"current_steps": 139, "total_steps": 224, "loss": 0.1862, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "2:36:06", "remaining_time": "1:35:27"}
+{"current_steps": 140, "total_steps": 224, "loss": 0.1989, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "2:37:11", "remaining_time": "1:34:18"}
+{"current_steps": 141, "total_steps": 224, "loss": 0.2267, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "2:38:15", "remaining_time": "1:33:09"}
+{"current_steps": 142, "total_steps": 224, "loss": 0.1753, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "2:39:17", "remaining_time": "1:31:59"}
+{"current_steps": 143, "total_steps": 224, "loss": 0.2041, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "2:40:38", "remaining_time": "1:30:59"}
+{"current_steps": 144, "total_steps": 224, "loss": 0.1844, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "2:41:44", "remaining_time": "1:29:51"}
+{"current_steps": 145, "total_steps": 224, "loss": 0.1676, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "2:42:42", "remaining_time": "1:28:39"}
+{"current_steps": 146, "total_steps": 224, "loss": 0.2021, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "2:43:57", "remaining_time": "1:27:35"}
+{"current_steps": 147, "total_steps": 224, "loss": 0.1892, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "2:45:10", "remaining_time": "1:26:31"}
+{"current_steps": 148, "total_steps": 224, "loss": 0.185, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "2:46:17", "remaining_time": "1:25:23"}
+{"current_steps": 149, "total_steps": 224, "loss": 0.2135, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "2:47:38", "remaining_time": "1:24:23"}
+{"current_steps": 150, "total_steps": 224, "loss": 0.1744, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "2:48:30", "remaining_time": "1:23:07"}
+{"current_steps": 151, "total_steps": 224, "loss": 0.179, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "2:49:30", "remaining_time": "1:21:56"}
+{"current_steps": 152, "total_steps": 224, "loss": 0.1736, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "2:50:38", "remaining_time": "1:20:49"}
+{"current_steps": 153, "total_steps": 224, "loss": 0.1883, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "2:51:47", "remaining_time": "1:19:43"}
+{"current_steps": 154, "total_steps": 224, "loss": 0.2123, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "2:53:02", "remaining_time": "1:18:39"}
+{"current_steps": 155, "total_steps": 224, "loss": 0.1899, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "2:54:04", "remaining_time": "1:17:29"}
+{"current_steps": 156, "total_steps": 224, "loss": 0.1847, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "2:54:58", "remaining_time": "1:16:16"}
+{"current_steps": 157, "total_steps": 224, "loss": 0.174, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "2:56:05", "remaining_time": "1:15:08"}
+{"current_steps": 158, "total_steps": 224, "loss": 0.1667, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "2:57:07", "remaining_time": "1:13:59"}
+{"current_steps": 159, "total_steps": 224, "loss": 0.2158, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "2:58:19", "remaining_time": "1:12:53"}
+{"current_steps": 160, "total_steps": 224, "loss": 0.1846, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "2:59:18", "remaining_time": "1:11:43"}
+{"current_steps": 161, "total_steps": 224, "loss": 0.1956, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "3:00:20", "remaining_time": "1:10:34"}
+{"current_steps": 162, "total_steps": 224, "loss": 0.202, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "3:01:32", "remaining_time": "1:09:28"}
+{"current_steps": 163, "total_steps": 224, "loss": 0.2082, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "3:02:47", "remaining_time": "1:08:24"}
+{"current_steps": 164, "total_steps": 224, "loss": 0.2131, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "3:04:33", "remaining_time": "1:07:31"}
+{"current_steps": 165, "total_steps": 224, "loss": 0.1501, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "3:05:48", "remaining_time": "1:06:26"}
+{"current_steps": 166, "total_steps": 224, "loss": 0.1489, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "3:06:51", "remaining_time": "1:05:17"}
+{"current_steps": 167, "total_steps": 224, "loss": 0.1308, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "3:07:50", "remaining_time": "1:04:06"}
+{"current_steps": 168, "total_steps": 224, "loss": 0.1345, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "3:09:01", "remaining_time": "1:03:00"}
+{"current_steps": 169, "total_steps": 224, "loss": 0.1396, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "3:10:10", "remaining_time": "1:01:53"}
+{"current_steps": 170, "total_steps": 224, "loss": 0.1526, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "3:11:14", "remaining_time": "1:00:44"}
+{"current_steps": 171, "total_steps": 224, "loss": 0.1288, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "3:12:12", "remaining_time": "0:59:34"}
+{"current_steps": 172, "total_steps": 224, "loss": 0.1357, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "3:13:09", "remaining_time": "0:58:23"}
+{"current_steps": 173, "total_steps": 224, "loss": 0.1524, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "3:14:15", "remaining_time": "0:57:15"}
+{"current_steps": 174, "total_steps": 224, "loss": 0.1346, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "3:15:07", "remaining_time": "0:56:04"}
+{"current_steps": 175, "total_steps": 224, "loss": 0.1364, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "3:16:21", "remaining_time": "0:54:58"}
+{"current_steps": 176, "total_steps": 224, "loss": 0.1445, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "3:17:30", "remaining_time": "0:53:51"}
+{"current_steps": 177, "total_steps": 224, "loss": 0.1362, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "3:18:37", "remaining_time": "0:52:44"}
+{"current_steps": 178, "total_steps": 224, "loss": 0.1338, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "3:19:46", "remaining_time": "0:51:37"}
+{"current_steps": 179, "total_steps": 224, "loss": 0.1388, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "3:20:54", "remaining_time": "0:50:30"}
+{"current_steps": 180, "total_steps": 224, "loss": 0.1252, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "3:21:52", "remaining_time": "0:49:20"}
+{"current_steps": 181, "total_steps": 224, "loss": 0.1262, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "3:22:56", "remaining_time": "0:48:12"}
+{"current_steps": 182, "total_steps": 224, "loss": 0.1337, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "3:24:17", "remaining_time": "0:47:08"}
+{"current_steps": 183, "total_steps": 224, "loss": 0.129, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "3:25:19", "remaining_time": "0:46:00"}
+{"current_steps": 184, "total_steps": 224, "loss": 0.1116, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "3:26:10", "remaining_time": "0:44:49"}
+{"current_steps": 185, "total_steps": 224, "loss": 0.1354, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "3:27:24", "remaining_time": "0:43:43"}
+{"current_steps": 186, "total_steps": 224, "loss": 0.1379, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "3:28:43", "remaining_time": "0:42:38"}
+{"current_steps": 187, "total_steps": 224, "loss": 0.1279, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "3:29:43", "remaining_time": "0:41:29"}
+{"current_steps": 188, "total_steps": 224, "loss": 0.1413, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "3:31:03", "remaining_time": "0:40:24"}
+{"current_steps": 189, "total_steps": 224, "loss": 0.1226, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "3:32:13", "remaining_time": "0:39:17"}
+{"current_steps": 190, "total_steps": 224, "loss": 0.1554, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "3:33:18", "remaining_time": "0:38:10"}
+{"current_steps": 191, "total_steps": 224, "loss": 0.1255, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "3:34:17", "remaining_time": "0:37:01"}
+{"current_steps": 192, "total_steps": 224, "loss": 0.1379, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "3:35:32", "remaining_time": "0:35:55"}
+{"current_steps": 193, "total_steps": 224, "loss": 0.1385, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "3:36:56", "remaining_time": "0:34:50"}
+{"current_steps": 194, "total_steps": 224, "loss": 0.1212, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "3:37:59", "remaining_time": "0:33:42"}
+{"current_steps": 195, "total_steps": 224, "loss": 0.1412, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "3:39:11", "remaining_time": "0:32:35"}
+{"current_steps": 196, "total_steps": 224, "loss": 0.1821, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "3:40:18", "remaining_time": "0:31:28"}
+{"current_steps": 197, "total_steps": 224, "loss": 0.121, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "3:41:56", "remaining_time": "0:30:25"}
+{"current_steps": 198, "total_steps": 224, "loss": 0.1205, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "3:43:25", "remaining_time": "0:29:20"}
+{"current_steps": 199, "total_steps": 224, "loss": 0.1134, "lr": 7.537457234218271e-07, "epoch": 6.091139240506329, "percentage": 88.84, "elapsed_time": "3:44:15", "remaining_time": "0:28:10"}
+{"current_steps": 200, "total_steps": 224, "loss": 0.106, "lr": 6.953470369291349e-07, "epoch": 6.121518987341772, "percentage": 89.29, "elapsed_time": "3:45:29", "remaining_time": "0:27:03"}
+{"current_steps": 201, "total_steps": 224, "loss": 0.1162, "lr": 6.392213479945852e-07, "epoch": 6.151898734177215, "percentage": 89.73, "elapsed_time": "3:46:30", "remaining_time": "0:25:55"}
+{"current_steps": 202, "total_steps": 224, "loss": 0.1104, "lr": 5.853823673448877e-07, "epoch": 6.182278481012658, "percentage": 90.18, "elapsed_time": "3:47:44", "remaining_time": "0:24:48"}
+{"current_steps": 203, "total_steps": 224, "loss": 0.1214, "lr": 5.33843247095659e-07, "epoch": 6.2126582278481015, "percentage": 90.62, "elapsed_time": "3:48:43", "remaining_time": "0:23:39"}
+{"current_steps": 204, "total_steps": 224, "loss": 0.1189, "lr": 4.846165775385459e-07, "epoch": 6.243037974683545, "percentage": 91.07, "elapsed_time": "3:49:49", "remaining_time": "0:22:31"}
+{"current_steps": 205, "total_steps": 224, "loss": 0.1058, "lr": 4.3771438406559173e-07, "epoch": 6.273417721518987, "percentage": 91.52, "elapsed_time": "3:50:54", "remaining_time": "0:21:24"}
+{"current_steps": 206, "total_steps": 224, "loss": 0.1234, "lr": 3.931481242315993e-07, "epoch": 6.30379746835443, "percentage": 91.96, "elapsed_time": "3:52:09", "remaining_time": "0:20:17"}
+{"current_steps": 207, "total_steps": 224, "loss": 0.1149, "lr": 3.5092868495520294e-07, "epoch": 6.334177215189873, "percentage": 92.41, "elapsed_time": "3:53:22", "remaining_time": "0:19:09"}
+{"current_steps": 208, "total_steps": 224, "loss": 0.1202, "lr": 3.110663798593616e-07, "epoch": 6.364556962025317, "percentage": 92.86, "elapsed_time": "3:54:33", "remaining_time": "0:18:02"}
+{"current_steps": 209, "total_steps": 224, "loss": 0.1146, "lr": 2.735709467518699e-07, "epoch": 6.39493670886076, "percentage": 93.3, "elapsed_time": "3:55:48", "remaining_time": "0:16:55"}
+{"current_steps": 210, "total_steps": 224, "loss": 0.1197, "lr": 2.384515452465475e-07, "epoch": 6.425316455696202, "percentage": 93.75, "elapsed_time": "3:56:48", "remaining_time": "0:15:47"}
+{"current_steps": 211, "total_steps": 224, "loss": 0.1069, "lr": 2.0571675452567997e-07, "epoch": 6.455696202531645, "percentage": 94.2, "elapsed_time": "3:58:10", "remaining_time": "0:14:40"}
+{"current_steps": 212, "total_steps": 224, "loss": 0.1216, "lr": 1.7537457124423896e-07, "epoch": 6.4860759493670885, "percentage": 94.64, "elapsed_time": "3:59:27", "remaining_time": "0:13:33"}
+{"current_steps": 213, "total_steps": 224, "loss": 0.1204, "lr": 1.474324075764111e-07, "epoch": 6.516455696202532, "percentage": 95.09, "elapsed_time": "4:00:30", "remaining_time": "0:12:25"}
+{"current_steps": 214, "total_steps": 224, "loss": 0.1142, "lr": 1.2189708940490653e-07, "epoch": 6.546835443037975, "percentage": 95.54, "elapsed_time": "4:01:29", "remaining_time": "0:11:17"}
+{"current_steps": 215, "total_steps": 224, "loss": 0.1234, "lr": 9.877485465349057e-08, "epoch": 6.577215189873417, "percentage": 95.98, "elapsed_time": "4:02:48", "remaining_time": "0:10:09"}
+{"current_steps": 216, "total_steps": 224, "loss": 0.1045, "lr": 7.807135176314707e-08, "epoch": 6.6075949367088604, "percentage": 96.43, "elapsed_time": "4:03:59", "remaining_time": "0:09:02"}
+{"current_steps": 217, "total_steps": 224, "loss": 0.1066, "lr": 5.979163831223988e-08, "epoch": 6.637974683544304, "percentage": 96.88, "elapsed_time": "4:05:06", "remaining_time": "0:07:54"}
+{"current_steps": 218, "total_steps": 224, "loss": 0.1123, "lr": 4.394017978101905e-08, "epoch": 6.668354430379747, "percentage": 97.32, "elapsed_time": "4:06:15", "remaining_time": "0:06:46"}
+{"current_steps": 219, "total_steps": 224, "loss": 0.1164, "lr": 3.0520848460765525e-08, "epoch": 6.69873417721519, "percentage": 97.77, "elapsed_time": "4:07:05", "remaining_time": "0:05:38"}
+{"current_steps": 220, "total_steps": 224, "loss": 0.1156, "lr": 1.9536922507841227e-08, "epoch": 6.729113924050633, "percentage": 98.21, "elapsed_time": "4:08:22", "remaining_time": "0:04:30"}
+{"current_steps": 221, "total_steps": 224, "loss": 0.1174, "lr": 1.099108514288627e-08, "epoch": 6.759493670886076, "percentage": 98.66, "elapsed_time": "4:09:26", "remaining_time": "0:03:23"}
+{"current_steps": 222, "total_steps": 224, "loss": 0.1079, "lr": 4.885423995341088e-09, "epoch": 6.789873417721519, "percentage": 99.11, "elapsed_time": "4:10:29", "remaining_time": "0:02:15"}
+{"current_steps": 223, "total_steps": 224, "loss": 0.1184, "lr": 1.2214305934699078e-09, "epoch": 6.820253164556962, "percentage": 99.55, "elapsed_time": "4:11:32", "remaining_time": "0:01:07"}
+{"current_steps": 224, "total_steps": 224, "loss": 0.1176, "lr": 0.0, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "4:12:38", "remaining_time": "0:00:00"}
+{"current_steps": 224, "total_steps": 224, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "4:13:46", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1610 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.850632911392405,
+  "eval_steps": 500,
+  "global_step": 224,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030379746835443037,
+      "grad_norm": 6.264223837447837,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 0.8653,
+      "step": 1
+    },
+    {
+      "epoch": 0.060759493670886074,
+      "grad_norm": 6.411256699697074,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.8939,
+      "step": 2
+    },
+    {
+      "epoch": 0.09113924050632911,
+      "grad_norm": 6.027212861227225,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.8222,
+      "step": 3
+    },
+    {
+      "epoch": 0.12151898734177215,
+      "grad_norm": 6.094770717952796,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.861,
+      "step": 4
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 4.446971159716574,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.8116,
+      "step": 5
+    },
+    {
+      "epoch": 0.18227848101265823,
+      "grad_norm": 2.500530798923617,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.7778,
+      "step": 6
+    },
+    {
+      "epoch": 0.21265822784810126,
+      "grad_norm": 2.097234677116947,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.775,
+      "step": 7
+    },
+    {
+      "epoch": 0.2430379746835443,
+      "grad_norm": 4.3091575269309015,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.7985,
+      "step": 8
+    },
+    {
+      "epoch": 0.27341772151898736,
+      "grad_norm": 3.821872023621295,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.7189,
+      "step": 9
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 4.036132029196842,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.7316,
+      "step": 10
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "grad_norm": 4.168552688043994,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.7169,
+      "step": 11
+    },
+    {
+      "epoch": 0.36455696202531646,
+      "grad_norm": 3.5725797832099504,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.6868,
+      "step": 12
+    },
+    {
+      "epoch": 0.3949367088607595,
+      "grad_norm": 2.3271747887261998,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.6444,
+      "step": 13
+    },
+    {
+      "epoch": 0.4253164556962025,
+      "grad_norm": 1.853858851417222,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.65,
+      "step": 14
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 2.3237928410153996,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.6213,
+      "step": 15
+    },
+    {
+      "epoch": 0.4860759493670886,
+      "grad_norm": 2.2891143923566757,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.6337,
+      "step": 16
+    },
+    {
+      "epoch": 0.5164556962025316,
+      "grad_norm": 1.2966845135592888,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.6227,
+      "step": 17
+    },
+    {
+      "epoch": 0.5468354430379747,
+      "grad_norm": 1.1578792077581719,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.6338,
+      "step": 18
+    },
+    {
+      "epoch": 0.5772151898734177,
+      "grad_norm": 1.3234419656554235,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.6246,
+      "step": 19
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.8655919173667078,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.6125,
+      "step": 20
+    },
+    {
+      "epoch": 0.6379746835443038,
+      "grad_norm": 0.8165889585109629,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.569,
+      "step": 21
+    },
+    {
+      "epoch": 0.6683544303797468,
+      "grad_norm": 1.1115583068811594,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.5777,
+      "step": 22
+    },
+    {
+      "epoch": 0.6987341772151898,
+      "grad_norm": 0.7628757493964801,
+      "learning_rate": 2e-05,
+      "loss": 0.6277,
+      "step": 23
+    },
+    {
+      "epoch": 0.7291139240506329,
+      "grad_norm": 1.0411028517271135,
+      "learning_rate": 1.999877856940653e-05,
+      "loss": 0.5953,
+      "step": 24
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.6804270776946826,
+      "learning_rate": 1.999511457600466e-05,
+      "loss": 0.6098,
+      "step": 25
+    },
+    {
+      "epoch": 0.789873417721519,
+      "grad_norm": 0.7025164734168877,
+      "learning_rate": 1.9989008914857115e-05,
+      "loss": 0.5633,
+      "step": 26
+    },
+    {
+      "epoch": 0.8202531645569621,
+      "grad_norm": 0.8802100886304541,
+      "learning_rate": 1.998046307749216e-05,
+      "loss": 0.5583,
+      "step": 27
+    },
+    {
+      "epoch": 0.850632911392405,
+      "grad_norm": 0.6163862927237143,
+      "learning_rate": 1.9969479151539238e-05,
+      "loss": 0.5541,
+      "step": 28
+    },
+    {
+      "epoch": 0.8810126582278481,
+      "grad_norm": 0.6849997287254687,
+      "learning_rate": 1.9956059820218982e-05,
+      "loss": 0.5612,
+      "step": 29
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.6298641549528552,
+      "learning_rate": 1.9940208361687762e-05,
+      "loss": 0.5655,
+      "step": 30
+    },
+    {
+      "epoch": 0.9417721518987342,
+      "grad_norm": 0.7004684552037466,
+      "learning_rate": 1.9921928648236855e-05,
+      "loss": 0.5887,
+      "step": 31
+    },
+    {
+      "epoch": 0.9721518987341772,
+      "grad_norm": 0.7253351732744092,
+      "learning_rate": 1.990122514534651e-05,
+      "loss": 0.5631,
+      "step": 32
+    },
+    {
+      "epoch": 1.010126582278481,
+      "grad_norm": 0.7406575180088495,
+      "learning_rate": 1.9878102910595097e-05,
+      "loss": 0.6821,
+      "step": 33
+    },
+    {
+      "epoch": 1.040506329113924,
+      "grad_norm": 0.6795309366762818,
+      "learning_rate": 1.985256759242359e-05,
+      "loss": 0.5633,
+      "step": 34
+    },
+    {
+      "epoch": 1.070886075949367,
+      "grad_norm": 0.5300947378258845,
+      "learning_rate": 1.982462542875576e-05,
+      "loss": 0.4339,
+      "step": 35
+    },
+    {
+      "epoch": 1.1012658227848102,
+      "grad_norm": 0.6948218294926742,
+      "learning_rate": 1.979428324547432e-05,
+      "loss": 0.4979,
+      "step": 36
+    },
+    {
+      "epoch": 1.1316455696202532,
+      "grad_norm": 0.6383161268526382,
+      "learning_rate": 1.9761548454753455e-05,
+      "loss": 0.5448,
+      "step": 37
+    },
+    {
+      "epoch": 1.1620253164556962,
+      "grad_norm": 0.5796574691977027,
+      "learning_rate": 1.972642905324813e-05,
+      "loss": 0.4755,
+      "step": 38
+    },
+    {
+      "epoch": 1.1924050632911392,
+      "grad_norm": 0.5205301553697834,
+      "learning_rate": 1.9688933620140638e-05,
+      "loss": 0.449,
+      "step": 39
+    },
+    {
+      "epoch": 1.2227848101265824,
+      "grad_norm": 0.6020646847574486,
+      "learning_rate": 1.96490713150448e-05,
+      "loss": 0.517,
+      "step": 40
+    },
+    {
+      "epoch": 1.2531645569620253,
+      "grad_norm": 0.6959773135755725,
+      "learning_rate": 1.9606851875768404e-05,
+      "loss": 0.4576,
+      "step": 41
+    },
+    {
+      "epoch": 1.2835443037974683,
+      "grad_norm": 0.6088235512117044,
+      "learning_rate": 1.956228561593441e-05,
+      "loss": 0.4684,
+      "step": 42
+    },
+    {
+      "epoch": 1.3139240506329113,
+      "grad_norm": 0.6766258484200818,
+      "learning_rate": 1.9515383422461457e-05,
+      "loss": 0.4712,
+      "step": 43
+    },
+    {
+      "epoch": 1.3443037974683545,
+      "grad_norm": 0.6249409834640268,
+      "learning_rate": 1.9466156752904344e-05,
+      "loss": 0.4912,
+      "step": 44
+    },
+    {
+      "epoch": 1.3746835443037975,
+      "grad_norm": 0.6980550037797275,
+      "learning_rate": 1.9414617632655114e-05,
+      "loss": 0.5171,
+      "step": 45
+    },
+    {
+      "epoch": 1.4050632911392404,
+      "grad_norm": 0.4823728113030638,
+      "learning_rate": 1.9360778652005416e-05,
+      "loss": 0.4755,
+      "step": 46
+    },
+    {
+      "epoch": 1.4354430379746836,
+      "grad_norm": 0.7178649227814365,
+      "learning_rate": 1.9304652963070868e-05,
+      "loss": 0.5238,
+      "step": 47
+    },
+    {
+      "epoch": 1.4658227848101266,
+      "grad_norm": 0.47742338433152715,
+      "learning_rate": 1.9246254276578175e-05,
+      "loss": 0.4681,
+      "step": 48
+    },
+    {
+      "epoch": 1.4962025316455696,
+      "grad_norm": 0.627334443689055,
+      "learning_rate": 1.9185596858515797e-05,
+      "loss": 0.4942,
+      "step": 49
+    },
+    {
+      "epoch": 1.5265822784810128,
+      "grad_norm": 0.47781725246848783,
+      "learning_rate": 1.9122695526648968e-05,
+      "loss": 0.4346,
+      "step": 50
+    },
+    {
+      "epoch": 1.5569620253164556,
+      "grad_norm": 0.6931187000064182,
+      "learning_rate": 1.905756564689991e-05,
+      "loss": 0.551,
+      "step": 51
+    },
+    {
+      "epoch": 1.5873417721518988,
+      "grad_norm": 0.5185073569252794,
+      "learning_rate": 1.8990223129594146e-05,
+      "loss": 0.4564,
+      "step": 52
+    },
+    {
+      "epoch": 1.6177215189873417,
+      "grad_norm": 0.6348042347292179,
+      "learning_rate": 1.8920684425573865e-05,
+      "loss": 0.5452,
+      "step": 53
+    },
+    {
+      "epoch": 1.6481012658227847,
+      "grad_norm": 0.6054361749046828,
+      "learning_rate": 1.884896652217917e-05,
+      "loss": 0.454,
+      "step": 54
+    },
+    {
+      "epoch": 1.678481012658228,
+      "grad_norm": 0.5450009949395281,
+      "learning_rate": 1.877508693909831e-05,
+      "loss": 0.4683,
+      "step": 55
+    },
+    {
+      "epoch": 1.7088607594936709,
+      "grad_norm": 0.61123856404764,
+      "learning_rate": 1.8699063724087905e-05,
+      "loss": 0.4536,
+      "step": 56
+    },
+    {
+      "epoch": 1.7392405063291139,
+      "grad_norm": 0.5906938867185233,
+      "learning_rate": 1.862091544856407e-05,
+      "loss": 0.4863,
+      "step": 57
+    },
+    {
+      "epoch": 1.769620253164557,
+      "grad_norm": 0.6213213252204924,
+      "learning_rate": 1.854066120306571e-05,
+      "loss": 0.4862,
+      "step": 58
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.5836327926282957,
+      "learning_rate": 1.8458320592590976e-05,
+      "loss": 0.5069,
+      "step": 59
+    },
+    {
+      "epoch": 1.830379746835443,
+      "grad_norm": 0.7548796429456727,
+      "learning_rate": 1.837391373180801e-05,
+      "loss": 0.5135,
+      "step": 60
+    },
+    {
+      "epoch": 1.8607594936708862,
+      "grad_norm": 0.5254706157464364,
+      "learning_rate": 1.8287461240141217e-05,
+      "loss": 0.4328,
+      "step": 61
+    },
+    {
+      "epoch": 1.891139240506329,
+      "grad_norm": 0.713641729007418,
+      "learning_rate": 1.8198984236734246e-05,
+      "loss": 0.4992,
+      "step": 62
+    },
+    {
+      "epoch": 1.9215189873417722,
+      "grad_norm": 0.5992458896946319,
+      "learning_rate": 1.8108504335290852e-05,
+      "loss": 0.4924,
+      "step": 63
+    },
+    {
+      "epoch": 1.9518987341772152,
+      "grad_norm": 0.48363149755605384,
+      "learning_rate": 1.8016043638794975e-05,
+      "loss": 0.4423,
+      "step": 64
+    },
+    {
+      "epoch": 1.9822784810126581,
+      "grad_norm": 0.6984801529973972,
+      "learning_rate": 1.7921624734111292e-05,
+      "loss": 0.5937,
+      "step": 65
+    },
+    {
+      "epoch": 2.020253164556962,
+      "grad_norm": 0.6540653957913342,
+      "learning_rate": 1.7825270686467567e-05,
+      "loss": 0.4914,
+      "step": 66
+    },
+    {
+      "epoch": 2.050632911392405,
+      "grad_norm": 0.5546741099568598,
+      "learning_rate": 1.7727005033820117e-05,
+      "loss": 0.384,
+      "step": 67
+    },
+    {
+      "epoch": 2.081012658227848,
+      "grad_norm": 0.5533344104756105,
+      "learning_rate": 1.762685178110382e-05,
+      "loss": 0.4095,
+      "step": 68
+    },
+    {
+      "epoch": 2.1113924050632913,
+      "grad_norm": 0.6644968396867378,
+      "learning_rate": 1.752483539436807e-05,
+      "loss": 0.3975,
+      "step": 69
+    },
+    {
+      "epoch": 2.141772151898734,
+      "grad_norm": 0.5747849644459087,
+      "learning_rate": 1.7420980794800013e-05,
+      "loss": 0.3921,
+      "step": 70
+    },
+    {
+      "epoch": 2.1721518987341772,
+      "grad_norm": 0.5504373978876771,
+      "learning_rate": 1.731531335263669e-05,
+      "loss": 0.3463,
+      "step": 71
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.6175640089869175,
+      "learning_rate": 1.720785888096743e-05,
+      "loss": 0.3745,
+      "step": 72
+    },
+    {
+      "epoch": 2.232911392405063,
+      "grad_norm": 0.5572138976873671,
+      "learning_rate": 1.7098643629428035e-05,
+      "loss": 0.3469,
+      "step": 73
+    },
+    {
+      "epoch": 2.2632911392405064,
+      "grad_norm": 0.6164348928133362,
+      "learning_rate": 1.698769427778842e-05,
+      "loss": 0.3958,
+      "step": 74
+    },
+    {
+      "epoch": 2.293670886075949,
+      "grad_norm": 0.5796998598785476,
+      "learning_rate": 1.687503792943506e-05,
+      "loss": 0.3908,
+      "step": 75
+    },
+    {
+      "epoch": 2.3240506329113924,
+      "grad_norm": 0.6116690415189946,
+      "learning_rate": 1.6760702104750046e-05,
+      "loss": 0.3618,
+      "step": 76
+    },
+    {
+      "epoch": 2.3544303797468356,
+      "grad_norm": 0.5839247234024287,
+      "learning_rate": 1.664471473438822e-05,
+      "loss": 0.4001,
+      "step": 77
+    },
+    {
+      "epoch": 2.3848101265822783,
+      "grad_norm": 0.5648198606713947,
+      "learning_rate": 1.6527104152454096e-05,
+      "loss": 0.3697,
+      "step": 78
+    },
+    {
+      "epoch": 2.4151898734177215,
+      "grad_norm": 0.47424698774743923,
+      "learning_rate": 1.6407899089580263e-05,
+      "loss": 0.4042,
+      "step": 79
+    },
+    {
+      "epoch": 2.4455696202531647,
+      "grad_norm": 0.526491138441173,
+      "learning_rate": 1.628712866590885e-05,
+      "loss": 0.3748,
+      "step": 80
+    },
+    {
+      "epoch": 2.4759493670886075,
+      "grad_norm": 0.45913538596337083,
+      "learning_rate": 1.6164822383977912e-05,
+      "loss": 0.3272,
+      "step": 81
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 0.5245789145036932,
+      "learning_rate": 1.604101012151436e-05,
+      "loss": 0.3984,
+      "step": 82
+    },
+    {
+      "epoch": 2.536708860759494,
+      "grad_norm": 0.4564535629632483,
+      "learning_rate": 1.5915722124135227e-05,
+      "loss": 0.3488,
+      "step": 83
+    },
+    {
+      "epoch": 2.5670886075949366,
+      "grad_norm": 0.4439029401487793,
+      "learning_rate": 1.5788988997959115e-05,
+      "loss": 0.3743,
+      "step": 84
+    },
+    {
+      "epoch": 2.59746835443038,
+      "grad_norm": 0.45157043394592816,
+      "learning_rate": 1.5660841702129533e-05,
+      "loss": 0.3499,
+      "step": 85
+    },
+    {
+      "epoch": 2.6278481012658226,
+      "grad_norm": 0.47118805349317777,
+      "learning_rate": 1.5531311541251995e-05,
+      "loss": 0.3749,
+      "step": 86
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.4991151007339554,
+      "learning_rate": 1.540043015774676e-05,
+      "loss": 0.3782,
+      "step": 87
+    },
+    {
+      "epoch": 2.688607594936709,
+      "grad_norm": 0.5070045648686803,
+      "learning_rate": 1.5268229524119007e-05,
+      "loss": 0.3816,
+      "step": 88
+    },
+    {
+      "epoch": 2.7189873417721517,
+      "grad_norm": 0.5283211062424125,
+      "learning_rate": 1.513474193514842e-05,
+      "loss": 0.3854,
+      "step": 89
+    },
+    {
+      "epoch": 2.749367088607595,
+      "grad_norm": 0.49967849508328893,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.3318,
+      "step": 90
+    },
+    {
+      "epoch": 2.779746835443038,
+      "grad_norm": 0.5761824799913082,
+      "learning_rate": 1.4864036634258112e-05,
+      "loss": 0.4053,
+      "step": 91
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.457027992926431,
+      "learning_rate": 1.4726885051885654e-05,
+      "loss": 0.3331,
+      "step": 92
+    },
+    {
+      "epoch": 2.840506329113924,
+      "grad_norm": 0.5439180987165674,
+      "learning_rate": 1.4588578757110359e-05,
+      "loss": 0.3269,
+      "step": 93
+    },
+    {
+      "epoch": 2.8708860759493673,
+      "grad_norm": 0.5321339617362203,
+      "learning_rate": 1.4449151536240167e-05,
+      "loss": 0.4065,
+      "step": 94
+    },
+    {
+      "epoch": 2.90126582278481,
+      "grad_norm": 0.45872333749508787,
+      "learning_rate": 1.4308637449409705e-05,
+      "loss": 0.3782,
+      "step": 95
+    },
+    {
+      "epoch": 2.9316455696202532,
+      "grad_norm": 0.6685263430601783,
+      "learning_rate": 1.4167070822259868e-05,
+      "loss": 0.4034,
+      "step": 96
+    },
+    {
+      "epoch": 2.962025316455696,
+      "grad_norm": 0.4244383332703259,
+      "learning_rate": 1.402448623755254e-05,
+      "loss": 0.3235,
+      "step": 97
+    },
+    {
+      "epoch": 2.992405063291139,
+      "grad_norm": 0.7804195707932797,
+      "learning_rate": 1.3880918526722497e-05,
+      "loss": 0.4883,
+      "step": 98
+    },
+    {
+      "epoch": 3.030379746835443,
+      "grad_norm": 0.6898289222972395,
+      "learning_rate": 1.3736402761368597e-05,
+      "loss": 0.2912,
+      "step": 99
+    },
+    {
+      "epoch": 3.060759493670886,
+      "grad_norm": 0.6526461198800771,
+      "learning_rate": 1.3590974244686248e-05,
+      "loss": 0.2993,
+      "step": 100
+    },
+    {
+      "epoch": 3.091139240506329,
+      "grad_norm": 0.6109871722734659,
+      "learning_rate": 1.344466850284333e-05,
+      "loss": 0.2829,
+      "step": 101
+    },
+    {
+      "epoch": 3.1215189873417724,
+      "grad_norm": 0.8726587547995472,
+      "learning_rate": 1.3297521276301666e-05,
+      "loss": 0.2862,
+      "step": 102
+    },
+    {
+      "epoch": 3.151898734177215,
+      "grad_norm": 0.5915965883830315,
+      "learning_rate": 1.3149568511086104e-05,
+      "loss": 0.3082,
+      "step": 103
+    },
+    {
+      "epoch": 3.1822784810126583,
+      "grad_norm": 0.7018059359740425,
+      "learning_rate": 1.300084635000341e-05,
+      "loss": 0.2775,
+      "step": 104
+    },
+    {
+      "epoch": 3.212658227848101,
+      "grad_norm": 0.5648020640782025,
+      "learning_rate": 1.2851391123813075e-05,
+      "loss": 0.2484,
+      "step": 105
+    },
+    {
+      "epoch": 3.2430379746835443,
+      "grad_norm": 0.5491041130301101,
+      "learning_rate": 1.2701239342352223e-05,
+      "loss": 0.2713,
+      "step": 106
+    },
+    {
+      "epoch": 3.2734177215189875,
+      "grad_norm": 0.542398015518937,
+      "learning_rate": 1.2550427685616767e-05,
+      "loss": 0.2809,
+      "step": 107
+    },
+    {
+      "epoch": 3.3037974683544302,
+      "grad_norm": 0.5673079398195483,
+      "learning_rate": 1.239899299480098e-05,
+      "loss": 0.2771,
+      "step": 108
+    },
+    {
+      "epoch": 3.3341772151898734,
+      "grad_norm": 0.5560061684468235,
+      "learning_rate": 1.2246972263297718e-05,
+      "loss": 0.2785,
+      "step": 109
+    },
+    {
+      "epoch": 3.3645569620253166,
+      "grad_norm": 0.5142315215324735,
+      "learning_rate": 1.2094402627661447e-05,
+      "loss": 0.2655,
+      "step": 110
+    },
+    {
+      "epoch": 3.3949367088607594,
+      "grad_norm": 0.508027635053969,
+      "learning_rate": 1.1941321358536278e-05,
+      "loss": 0.2876,
+      "step": 111
+    },
+    {
+      "epoch": 3.4253164556962026,
+      "grad_norm": 0.5207943414533546,
+      "learning_rate": 1.1787765851551296e-05,
+      "loss": 0.2645,
+      "step": 112
+    },
+    {
+      "epoch": 3.4556962025316453,
+      "grad_norm": 0.4794185965888677,
+      "learning_rate": 1.1633773618185302e-05,
+      "loss": 0.2843,
+      "step": 113
+    },
+    {
+      "epoch": 3.4860759493670885,
+      "grad_norm": 0.5216131678174822,
+      "learning_rate": 1.14793822766033e-05,
+      "loss": 0.2705,
+      "step": 114
+    },
+    {
+      "epoch": 3.5164556962025317,
+      "grad_norm": 0.4362210510365554,
+      "learning_rate": 1.132462954246688e-05,
+      "loss": 0.2405,
+      "step": 115
+    },
+    {
+      "epoch": 3.546835443037975,
+      "grad_norm": 0.5484752284700704,
+      "learning_rate": 1.1169553219720828e-05,
+      "loss": 0.2874,
+      "step": 116
+    },
+    {
+      "epoch": 3.5772151898734177,
+      "grad_norm": 0.44411698682566847,
+      "learning_rate": 1.1014191191358118e-05,
+      "loss": 0.2722,
+      "step": 117
+    },
+    {
+      "epoch": 3.607594936708861,
+      "grad_norm": 0.4256453593025832,
+      "learning_rate": 1.085858141016566e-05,
+      "loss": 0.2606,
+      "step": 118
+    },
+    {
+      "epoch": 3.6379746835443036,
+      "grad_norm": 0.4840576533102752,
+      "learning_rate": 1.070276188945293e-05,
+      "loss": 0.2627,
+      "step": 119
+    },
+    {
+      "epoch": 3.668354430379747,
+      "grad_norm": 0.4763344324363398,
+      "learning_rate": 1.0546770693765859e-05,
+      "loss": 0.2778,
+      "step": 120
+    },
+    {
+      "epoch": 3.69873417721519,
+      "grad_norm": 0.4520353656979555,
+      "learning_rate": 1.0390645929588197e-05,
+      "loss": 0.2782,
+      "step": 121
+    },
+    {
+      "epoch": 3.729113924050633,
+      "grad_norm": 0.484359088787161,
+      "learning_rate": 1.0234425736032607e-05,
+      "loss": 0.2822,
+      "step": 122
+    },
+    {
+      "epoch": 3.759493670886076,
+      "grad_norm": 0.5122783646022456,
+      "learning_rate": 1.007814827552384e-05,
+      "loss": 0.2624,
+      "step": 123
+    },
+    {
+      "epoch": 3.7898734177215188,
+      "grad_norm": 0.4497907628730785,
+      "learning_rate": 9.92185172447616e-06,
+      "loss": 0.2518,
+      "step": 124
+    },
+    {
+      "epoch": 3.820253164556962,
+      "grad_norm": 0.4376125761126391,
+      "learning_rate": 9.765574263967397e-06,
+      "loss": 0.2679,
+      "step": 125
+    },
+    {
+      "epoch": 3.850632911392405,
+      "grad_norm": 0.45266135210460645,
+      "learning_rate": 9.609354070411807e-06,
+      "loss": 0.2617,
+      "step": 126
+    },
+    {
+      "epoch": 3.8810126582278484,
+      "grad_norm": 0.4286208278697542,
+      "learning_rate": 9.453229306234143e-06,
+      "loss": 0.2857,
+      "step": 127
+    },
+    {
+      "epoch": 3.911392405063291,
+      "grad_norm": 0.4164821744132408,
+      "learning_rate": 9.297238110547075e-06,
+      "loss": 0.2676,
+      "step": 128
+    },
+    {
+      "epoch": 3.9417721518987343,
+      "grad_norm": 0.42463497579882714,
+      "learning_rate": 9.14141858983434e-06,
+      "loss": 0.2743,
+      "step": 129
+    },
+    {
+      "epoch": 3.972151898734177,
+      "grad_norm": 0.45143201821249485,
+      "learning_rate": 8.985808808641883e-06,
+      "loss": 0.2827,
+      "step": 130
+    },
+    {
+      "epoch": 4.010126582278481,
+      "grad_norm": 0.5178904309434295,
+      "learning_rate": 8.830446780279175e-06,
+      "loss": 0.3169,
+      "step": 131
+    },
+    {
+      "epoch": 4.040506329113924,
+      "grad_norm": 0.6255008822350463,
+      "learning_rate": 8.675370457533122e-06,
+      "loss": 0.2049,
+      "step": 132
+    },
+    {
+      "epoch": 4.0708860759493675,
+      "grad_norm": 0.4663360072666728,
+      "learning_rate": 8.520617723396702e-06,
+      "loss": 0.2082,
+      "step": 133
+    },
+    {
+      "epoch": 4.10126582278481,
+      "grad_norm": 0.5525690051399497,
+      "learning_rate": 8.366226381814698e-06,
+      "loss": 0.1795,
+      "step": 134
+    },
+    {
+      "epoch": 4.131645569620253,
+      "grad_norm": 0.7424606332536962,
+      "learning_rate": 8.212234148448708e-06,
+      "loss": 0.2008,
+      "step": 135
+    },
+    {
+      "epoch": 4.162025316455696,
+      "grad_norm": 0.5745096218393714,
+      "learning_rate": 8.058678641463724e-06,
+      "loss": 0.2018,
+      "step": 136
+    },
+    {
+      "epoch": 4.192405063291139,
+      "grad_norm": 0.4702614444346243,
+      "learning_rate": 7.905597372338558e-06,
+      "loss": 0.1703,
+      "step": 137
+    },
+    {
+      "epoch": 4.222784810126583,
+      "grad_norm": 0.6390290266050745,
+      "learning_rate": 7.753027736702283e-06,
+      "loss": 0.2185,
+      "step": 138
+    },
+    {
+      "epoch": 4.253164556962025,
+      "grad_norm": 0.4628581214262268,
+      "learning_rate": 7.601007005199022e-06,
+      "loss": 0.1862,
+      "step": 139
+    },
+    {
+      "epoch": 4.283544303797468,
+      "grad_norm": 0.5399100867642865,
+      "learning_rate": 7.449572314383237e-06,
+      "loss": 0.1989,
+      "step": 140
+    },
+    {
+      "epoch": 4.313924050632911,
+      "grad_norm": 0.574931790699253,
+      "learning_rate": 7.298760657647779e-06,
+      "loss": 0.2267,
+      "step": 141
+    },
+    {
+      "epoch": 4.3443037974683545,
+      "grad_norm": 0.4439955496878499,
+      "learning_rate": 7.148608876186931e-06,
+      "loss": 0.1753,
+      "step": 142
+    },
+    {
+      "epoch": 4.374683544303798,
+      "grad_norm": 0.5047861912578576,
+      "learning_rate": 6.999153649996595e-06,
+      "loss": 0.2041,
+      "step": 143
+    },
+    {
+      "epoch": 4.405063291139241,
+      "grad_norm": 0.43821876188470377,
+      "learning_rate": 6.8504314889138956e-06,
+      "loss": 0.1844,
+      "step": 144
+    },
+    {
+      "epoch": 4.435443037974683,
+      "grad_norm": 0.450828883558137,
+      "learning_rate": 6.702478723698336e-06,
+      "loss": 0.1676,
+      "step": 145
+    },
+    {
+      "epoch": 4.465822784810126,
+      "grad_norm": 0.47294294676149884,
+      "learning_rate": 6.555331497156671e-06,
+      "loss": 0.2021,
+      "step": 146
+    },
+    {
+      "epoch": 4.49620253164557,
+      "grad_norm": 0.4116079904869393,
+      "learning_rate": 6.4090257553137566e-06,
+      "loss": 0.1892,
+      "step": 147
+    },
+    {
+      "epoch": 4.526582278481013,
+      "grad_norm": 0.44665415136996167,
+      "learning_rate": 6.263597238631405e-06,
+      "loss": 0.185,
+      "step": 148
+    },
+    {
+      "epoch": 4.556962025316456,
+      "grad_norm": 0.45228880304893426,
+      "learning_rate": 6.119081473277502e-06,
+      "loss": 0.2135,
+      "step": 149
+    },
+    {
+      "epoch": 4.587341772151898,
+      "grad_norm": 0.4211840314348762,
+      "learning_rate": 5.975513762447465e-06,
+      "loss": 0.1744,
+      "step": 150
+    },
+    {
+      "epoch": 4.6177215189873415,
+      "grad_norm": 0.42731254775297467,
+      "learning_rate": 5.832929177740134e-06,
+      "loss": 0.179,
+      "step": 151
+    },
+    {
+      "epoch": 4.648101265822785,
+      "grad_norm": 0.4114726369883331,
+      "learning_rate": 5.6913625505902966e-06,
+      "loss": 0.1736,
+      "step": 152
+    },
+    {
+      "epoch": 4.678481012658228,
+      "grad_norm": 0.41713312191238006,
+      "learning_rate": 5.550848463759835e-06,
+      "loss": 0.1883,
+      "step": 153
+    },
+    {
+      "epoch": 4.708860759493671,
+      "grad_norm": 0.4441935778969085,
+      "learning_rate": 5.411421242889643e-06,
+      "loss": 0.2123,
+      "step": 154
+    },
+    {
+      "epoch": 4.739240506329114,
+      "grad_norm": 0.41563812394315813,
+      "learning_rate": 5.273114948114346e-06,
+      "loss": 0.1899,
+      "step": 155
+    },
+    {
+      "epoch": 4.769620253164557,
+      "grad_norm": 0.4362364289458295,
+      "learning_rate": 5.135963365741892e-06,
+      "loss": 0.1847,
+      "step": 156
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.40794185942171385,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.174,
+      "step": 157
+    },
+    {
+      "epoch": 4.830379746835443,
+      "grad_norm": 0.38071092887816593,
+      "learning_rate": 4.865258064851579e-06,
+      "loss": 0.1667,
+      "step": 158
+    },
+    {
+      "epoch": 4.860759493670886,
+      "grad_norm": 0.46842208821628495,
+      "learning_rate": 4.731770475880995e-06,
+      "loss": 0.2158,
+      "step": 159
+    },
+    {
+      "epoch": 4.891139240506329,
+      "grad_norm": 0.40121416255265785,
+      "learning_rate": 4.599569842253244e-06,
+      "loss": 0.1846,
+      "step": 160
+    },
+    {
+      "epoch": 4.921518987341772,
+      "grad_norm": 0.42931887950953884,
+      "learning_rate": 4.468688458748006e-06,
+      "loss": 0.1956,
+      "step": 161
+    },
+    {
+      "epoch": 4.951898734177215,
+      "grad_norm": 0.4122318318707383,
+      "learning_rate": 4.339158297870469e-06,
+      "loss": 0.202,
+      "step": 162
+    },
+    {
+      "epoch": 4.982278481012658,
+      "grad_norm": 0.49075311327954135,
+      "learning_rate": 4.211011002040885e-06,
+      "loss": 0.2082,
+      "step": 163
+    },
+    {
+      "epoch": 5.020253164556962,
+      "grad_norm": 0.6212796674101548,
+      "learning_rate": 4.084277875864776e-06,
+      "loss": 0.2131,
+      "step": 164
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 0.5462254440984692,
+      "learning_rate": 3.958989878485644e-06,
+      "loss": 0.1501,
+      "step": 165
+    },
+    {
+      "epoch": 5.0810126582278485,
+      "grad_norm": 0.42302184153770833,
+      "learning_rate": 3.83517761602209e-06,
+      "loss": 0.1489,
+      "step": 166
+    },
+    {
+      "epoch": 5.111392405063291,
+      "grad_norm": 0.3469584459655291,
+      "learning_rate": 3.712871334091154e-06,
+      "loss": 0.1308,
+      "step": 167
+    },
+    {
+      "epoch": 5.141772151898734,
+      "grad_norm": 0.43320219632040574,
+      "learning_rate": 3.592100910419738e-06,
+      "loss": 0.1345,
+      "step": 168
+    },
+    {
+      "epoch": 5.172151898734177,
+      "grad_norm": 0.5578330333033935,
+      "learning_rate": 3.4728958475459052e-06,
+      "loss": 0.1396,
+      "step": 169
+    },
+    {
+      "epoch": 5.2025316455696204,
+      "grad_norm": 0.640178109725764,
+      "learning_rate": 3.355285265611784e-06,
+      "loss": 0.1526,
+      "step": 170
+    },
+    {
+      "epoch": 5.232911392405064,
+      "grad_norm": 0.4415130114149953,
+      "learning_rate": 3.2392978952499553e-06,
+      "loss": 0.1288,
+      "step": 171
+    },
+    {
+      "epoch": 5.263291139240506,
+      "grad_norm": 0.37477185848963257,
+      "learning_rate": 3.1249620705649417e-06,
+      "loss": 0.1357,
+      "step": 172
+    },
+    {
+      "epoch": 5.293670886075949,
+      "grad_norm": 0.4454771530728319,
+      "learning_rate": 3.0123057222115835e-06,
+      "loss": 0.1524,
+      "step": 173
+    },
+    {
+      "epoch": 5.324050632911392,
+      "grad_norm": 0.45252662088706425,
+      "learning_rate": 2.9013563705719673e-06,
+      "loss": 0.1346,
+      "step": 174
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 0.40446738836683316,
+      "learning_rate": 2.7921411190325753e-06,
+      "loss": 0.1364,
+      "step": 175
+    },
+    {
+      "epoch": 5.384810126582279,
+      "grad_norm": 0.4168074072408946,
+      "learning_rate": 2.6846866473633126e-06,
+      "loss": 0.1445,
+      "step": 176
+    },
+    {
+      "epoch": 5.415189873417722,
+      "grad_norm": 0.3896504523888332,
+      "learning_rate": 2.579019205199992e-06,
+      "loss": 0.1362,
+      "step": 177
+    },
+    {
+      "epoch": 5.445569620253164,
+      "grad_norm": 0.3589228993693732,
+      "learning_rate": 2.4751646056319334e-06,
+      "loss": 0.1338,
+      "step": 178
+    },
+    {
+      "epoch": 5.4759493670886075,
+      "grad_norm": 0.4002822744684675,
+      "learning_rate": 2.373148218896182e-06,
+      "loss": 0.1388,
+      "step": 179
+    },
+    {
+      "epoch": 5.506329113924051,
+      "grad_norm": 0.3722210390601156,
+      "learning_rate": 2.2729949661798876e-06,
+      "loss": 0.1252,
+      "step": 180
+    },
+    {
+      "epoch": 5.536708860759494,
+      "grad_norm": 0.36402491121876285,
+      "learning_rate": 2.174729313532433e-06,
+      "loss": 0.1262,
+      "step": 181
+    },
+    {
+      "epoch": 5.567088607594937,
+      "grad_norm": 0.3694016510988465,
+      "learning_rate": 2.078375265888707e-06,
+      "loss": 0.1337,
+      "step": 182
+    },
+    {
+      "epoch": 5.597468354430379,
+      "grad_norm": 0.37537279604979884,
+      "learning_rate": 1.9839563612050273e-06,
+      "loss": 0.129,
+      "step": 183
+    },
+    {
+      "epoch": 5.627848101265823,
+      "grad_norm": 0.33440167755873895,
+      "learning_rate": 1.8914956647091497e-06,
+      "loss": 0.1116,
+      "step": 184
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 0.3757913764404746,
+      "learning_rate": 1.8010157632657544e-06,
+      "loss": 0.1354,
+      "step": 185
+    },
+    {
+      "epoch": 5.688607594936709,
+      "grad_norm": 0.34216379773242095,
+      "learning_rate": 1.7125387598587862e-06,
+      "loss": 0.1379,
+      "step": 186
+    },
+    {
+      "epoch": 5.718987341772152,
+      "grad_norm": 0.33803173864730923,
+      "learning_rate": 1.6260862681919965e-06,
+      "loss": 0.1279,
+      "step": 187
+    },
+    {
+      "epoch": 5.749367088607595,
+      "grad_norm": 0.3654303753984185,
+      "learning_rate": 1.5416794074090258e-06,
+      "loss": 0.1413,
+      "step": 188
+    },
+    {
+      "epoch": 5.779746835443038,
+      "grad_norm": 0.32221649213877057,
+      "learning_rate": 1.459338796934293e-06,
+      "loss": 0.1226,
+      "step": 189
+    },
+    {
+      "epoch": 5.810126582278481,
+      "grad_norm": 0.3810213863554794,
+      "learning_rate": 1.3790845514359363e-06,
+      "loss": 0.1554,
+      "step": 190
+    },
+    {
+      "epoch": 5.840506329113924,
+      "grad_norm": 0.3391070109677399,
+      "learning_rate": 1.300936275912098e-06,
+      "loss": 0.1255,
+      "step": 191
+    },
+    {
+      "epoch": 5.870886075949367,
+      "grad_norm": 0.34691646635131895,
+      "learning_rate": 1.224913060901688e-06,
+      "loss": 0.1379,
+      "step": 192
+    },
+    {
+      "epoch": 5.9012658227848105,
+      "grad_norm": 0.3342692915245725,
+      "learning_rate": 1.1510334778208332e-06,
+      "loss": 0.1385,
+      "step": 193
+    },
+    {
+      "epoch": 5.931645569620253,
+      "grad_norm": 0.3335059460429094,
+      "learning_rate": 1.0793155744261352e-06,
+      "loss": 0.1212,
+      "step": 194
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 0.3607583058461707,
+      "learning_rate": 1.0097768704058542e-06,
+      "loss": 0.1412,
+      "step": 195
+    },
+    {
+      "epoch": 5.992405063291139,
+      "grad_norm": 0.4698491102661422,
+      "learning_rate": 9.424343531000968e-07,
+      "loss": 0.1821,
+      "step": 196
+    },
+    {
+      "epoch": 6.030379746835443,
+      "grad_norm": 0.40763370914111263,
+      "learning_rate": 8.773044733510338e-07,
+      "loss": 0.121,
+      "step": 197
+    },
+    {
+      "epoch": 6.060759493670886,
+      "grad_norm": 0.33102756087066815,
+      "learning_rate": 8.144031414842012e-07,
+      "loss": 0.1205,
+      "step": 198
+    },
+    {
+      "epoch": 6.091139240506329,
+      "grad_norm": 0.40115234371354197,
+      "learning_rate": 7.537457234218271e-07,
+      "loss": 0.1134,
+      "step": 199
+    },
+    {
+      "epoch": 6.121518987341772,
+      "grad_norm": 0.33971191739567935,
+      "learning_rate": 6.953470369291349e-07,
+      "loss": 0.106,
+      "step": 200
+    },
+    {
+      "epoch": 6.151898734177215,
+      "grad_norm": 0.34076051053215356,
+      "learning_rate": 6.392213479945852e-07,
+      "loss": 0.1162,
+      "step": 201
+    },
+    {
+      "epoch": 6.182278481012658,
+      "grad_norm": 0.30163529551377666,
+      "learning_rate": 5.853823673448877e-07,
+      "loss": 0.1104,
+      "step": 202
+    },
+    {
+      "epoch": 6.2126582278481015,
+      "grad_norm": 0.30486309486129837,
+      "learning_rate": 5.33843247095659e-07,
+      "loss": 0.1214,
+      "step": 203
+    },
+    {
+      "epoch": 6.243037974683545,
+      "grad_norm": 0.37329930860455734,
+      "learning_rate": 4.846165775385459e-07,
+      "loss": 0.1189,
+      "step": 204
+    },
+    {
+      "epoch": 6.273417721518987,
+      "grad_norm": 0.30478576584706973,
+      "learning_rate": 4.3771438406559173e-07,
+      "loss": 0.1058,
+      "step": 205
+    },
+    {
+      "epoch": 6.30379746835443,
+      "grad_norm": 0.32163190636375755,
+      "learning_rate": 3.931481242315993e-07,
+      "loss": 0.1234,
+      "step": 206
+    },
+    {
+      "epoch": 6.334177215189873,
+      "grad_norm": 0.35511722030237625,
+      "learning_rate": 3.5092868495520294e-07,
+      "loss": 0.1149,
+      "step": 207
+    },
+    {
+      "epoch": 6.364556962025317,
+      "grad_norm": 0.3457462845239258,
+      "learning_rate": 3.110663798593616e-07,
+      "loss": 0.1202,
+      "step": 208
+    },
+    {
+      "epoch": 6.39493670886076,
+      "grad_norm": 0.3107686645474473,
+      "learning_rate": 2.735709467518699e-07,
+      "loss": 0.1146,
+      "step": 209
+    },
+    {
+      "epoch": 6.425316455696202,
+      "grad_norm": 0.3369894507843882,
+      "learning_rate": 2.384515452465475e-07,
+      "loss": 0.1197,
+      "step": 210
+    },
+    {
+      "epoch": 6.455696202531645,
+      "grad_norm": 0.2958490695117549,
+      "learning_rate": 2.0571675452567997e-07,
+      "loss": 0.1069,
+      "step": 211
+    },
+    {
+      "epoch": 6.4860759493670885,
+      "grad_norm": 0.32195825943174333,
+      "learning_rate": 1.7537457124423896e-07,
+      "loss": 0.1216,
+      "step": 212
+    },
+    {
+      "epoch": 6.516455696202532,
+      "grad_norm": 0.3252260869537387,
+      "learning_rate": 1.474324075764111e-07,
+      "loss": 0.1204,
+      "step": 213
+    },
+    {
+      "epoch": 6.546835443037975,
+      "grad_norm": 0.328999581616471,
+      "learning_rate": 1.2189708940490653e-07,
+      "loss": 0.1142,
+      "step": 214
+    },
+    {
+      "epoch": 6.577215189873417,
+      "grad_norm": 0.3131690743268465,
+      "learning_rate": 9.877485465349057e-08,
+      "loss": 0.1234,
+      "step": 215
+    },
+    {
+      "epoch": 6.6075949367088604,
+      "grad_norm": 0.2999294804387676,
+      "learning_rate": 7.807135176314707e-08,
+      "loss": 0.1045,
+      "step": 216
+    },
+    {
+      "epoch": 6.637974683544304,
+      "grad_norm": 0.3069573676918086,
+      "learning_rate": 5.979163831223988e-08,
+      "loss": 0.1066,
+      "step": 217
+    },
+    {
+      "epoch": 6.668354430379747,
+      "grad_norm": 0.30918289682126204,
+      "learning_rate": 4.394017978101905e-08,
+      "loss": 0.1123,
+      "step": 218
+    },
+    {
+      "epoch": 6.69873417721519,
+      "grad_norm": 0.3421838237906003,
+      "learning_rate": 3.0520848460765525e-08,
+      "loss": 0.1164,
+      "step": 219
+    },
+    {
+      "epoch": 6.729113924050633,
+      "grad_norm": 0.32110695428743896,
+      "learning_rate": 1.9536922507841227e-08,
+      "loss": 0.1156,
+      "step": 220
+    },
+    {
+      "epoch": 6.759493670886076,
+      "grad_norm": 0.33797817117104373,
+      "learning_rate": 1.099108514288627e-08,
+      "loss": 0.1174,
+      "step": 221
+    },
+    {
+      "epoch": 6.789873417721519,
+      "grad_norm": 0.31898372133563707,
+      "learning_rate": 4.885423995341088e-09,
+      "loss": 0.1079,
+      "step": 222
+    },
+    {
+      "epoch": 6.820253164556962,
+      "grad_norm": 0.31465044834388256,
+      "learning_rate": 1.2214305934699078e-09,
+      "loss": 0.1184,
+      "step": 223
+    },
+    {
+      "epoch": 6.850632911392405,
+      "grad_norm": 0.3182540685603932,
+      "learning_rate": 0.0,
+      "loss": 0.1176,
+      "step": 224
+    },
+    {
+      "epoch": 6.850632911392405,
+      "step": 224,
+      "total_flos": 3.4820098135320166e+17,
+      "train_loss": 0.32787186798772644,
+      "train_runtime": 15227.7577,
+      "train_samples_per_second": 1.453,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 224,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 3.4820098135320166e+17,
+  "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:b2e640533c7b6b1bb3e0d0fff11eabd7eeff1de037b808a08361b70c965de609
+size 7352