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_16_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_16_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_16_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": 2.86943794002133e+17,
+    "train_loss": 0.2993284181159522,
+    "train_runtime": 12424.2407,
+    "train_samples_per_second": 1.78,
+    "train_steps_per_second": 0.018
+}

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 sha256:0542360e047e23898c2f31e302ef0c4d8c9015bce5608f96b1af6417324c33f8
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ecb8742c5e0f382808860d9ee6f1d21776994d4a787c4e70521ca0c7b748f0
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de48557d25d96257a65e1ddab0a9d7743a77d8b3f074822b7d962e886a226d8f
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0cc238ab40b63b46972b89c43459883ad4d3f88ad33a4b6b1e8179677d6b6d
+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_07-16-14_jpbot-001-03.jupiter.internal/events.out.tfevents.1745039794.jpbot-001-03.jupiter.internal.1268012.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de03e74705861ab2a1f17ec4e18716a50e14003945227687e7c02dc855bf94d
+size 52629

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 07:16:14", "end_time": "2025-04-19 10:43:49"}

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": 2.86943794002133e+17,
+    "train_loss": 0.2993284181159522,
+    "train_runtime": 12424.2407,
+    "train_samples_per_second": 1.78,
+    "train_steps_per_second": 0.018
+}

trainer_log.jsonl

@@ -0,0 +1,225 @@
+{"current_steps": 1, "total_steps": 224, "loss": 0.8862, "lr": 8.695652173913044e-07, "epoch": 0.030379746835443037, "percentage": 0.45, "elapsed_time": "0:00:48", "remaining_time": "3:01:19"}
+{"current_steps": 2, "total_steps": 224, "loss": 0.8348, "lr": 1.7391304347826088e-06, "epoch": 0.060759493670886074, "percentage": 0.89, "elapsed_time": "0:01:50", "remaining_time": "3:24:01"}
+{"current_steps": 3, "total_steps": 224, "loss": 0.8919, "lr": 2.6086956521739132e-06, "epoch": 0.09113924050632911, "percentage": 1.34, "elapsed_time": "0:02:50", "remaining_time": "3:29:04"}
+{"current_steps": 4, "total_steps": 224, "loss": 0.8317, "lr": 3.4782608695652175e-06, "epoch": 0.12151898734177215, "percentage": 1.79, "elapsed_time": "0:03:33", "remaining_time": "3:15:45"}
+{"current_steps": 5, "total_steps": 224, "loss": 0.8164, "lr": 4.347826086956522e-06, "epoch": 0.1518987341772152, "percentage": 2.23, "elapsed_time": "0:04:27", "remaining_time": "3:15:23"}
+{"current_steps": 6, "total_steps": 224, "loss": 0.7569, "lr": 5.2173913043478265e-06, "epoch": 0.18227848101265823, "percentage": 2.68, "elapsed_time": "0:05:21", "remaining_time": "3:14:54"}
+{"current_steps": 7, "total_steps": 224, "loss": 0.7122, "lr": 6.086956521739132e-06, "epoch": 0.21265822784810126, "percentage": 3.12, "elapsed_time": "0:06:20", "remaining_time": "3:16:38"}
+{"current_steps": 8, "total_steps": 224, "loss": 0.7835, "lr": 6.956521739130435e-06, "epoch": 0.2430379746835443, "percentage": 3.57, "elapsed_time": "0:07:08", "remaining_time": "3:13:00"}
+{"current_steps": 9, "total_steps": 224, "loss": 0.7065, "lr": 7.82608695652174e-06, "epoch": 0.27341772151898736, "percentage": 4.02, "elapsed_time": "0:07:56", "remaining_time": "3:09:36"}
+{"current_steps": 10, "total_steps": 224, "loss": 0.7161, "lr": 8.695652173913044e-06, "epoch": 0.3037974683544304, "percentage": 4.46, "elapsed_time": "0:08:36", "remaining_time": "3:04:16"}
+{"current_steps": 11, "total_steps": 224, "loss": 0.6817, "lr": 9.565217391304349e-06, "epoch": 0.3341772151898734, "percentage": 4.91, "elapsed_time": "0:09:26", "remaining_time": "3:02:56"}
+{"current_steps": 12, "total_steps": 224, "loss": 0.7038, "lr": 1.0434782608695653e-05, "epoch": 0.36455696202531646, "percentage": 5.36, "elapsed_time": "0:10:21", "remaining_time": "3:03:03"}
+{"current_steps": 13, "total_steps": 224, "loss": 0.6703, "lr": 1.1304347826086957e-05, "epoch": 0.3949367088607595, "percentage": 5.8, "elapsed_time": "0:11:14", "remaining_time": "3:02:29"}
+{"current_steps": 14, "total_steps": 224, "loss": 0.652, "lr": 1.2173913043478263e-05, "epoch": 0.4253164556962025, "percentage": 6.25, "elapsed_time": "0:12:03", "remaining_time": "3:00:52"}
+{"current_steps": 15, "total_steps": 224, "loss": 0.6597, "lr": 1.3043478260869566e-05, "epoch": 0.45569620253164556, "percentage": 6.7, "elapsed_time": "0:13:04", "remaining_time": "3:02:12"}
+{"current_steps": 16, "total_steps": 224, "loss": 0.5939, "lr": 1.391304347826087e-05, "epoch": 0.4860759493670886, "percentage": 7.14, "elapsed_time": "0:13:54", "remaining_time": "3:00:54"}
+{"current_steps": 17, "total_steps": 224, "loss": 0.6429, "lr": 1.4782608695652174e-05, "epoch": 0.5164556962025316, "percentage": 7.59, "elapsed_time": "0:14:42", "remaining_time": "2:59:10"}
+{"current_steps": 18, "total_steps": 224, "loss": 0.6238, "lr": 1.565217391304348e-05, "epoch": 0.5468354430379747, "percentage": 8.04, "elapsed_time": "0:15:38", "remaining_time": "2:59:03"}
+{"current_steps": 19, "total_steps": 224, "loss": 0.6051, "lr": 1.6521739130434785e-05, "epoch": 0.5772151898734177, "percentage": 8.48, "elapsed_time": "0:16:31", "remaining_time": "2:58:13"}
+{"current_steps": 20, "total_steps": 224, "loss": 0.5999, "lr": 1.739130434782609e-05, "epoch": 0.6075949367088608, "percentage": 8.93, "elapsed_time": "0:17:22", "remaining_time": "2:57:16"}
+{"current_steps": 21, "total_steps": 224, "loss": 0.5697, "lr": 1.8260869565217393e-05, "epoch": 0.6379746835443038, "percentage": 9.38, "elapsed_time": "0:18:16", "remaining_time": "2:56:35"}
+{"current_steps": 22, "total_steps": 224, "loss": 0.5683, "lr": 1.9130434782608697e-05, "epoch": 0.6683544303797468, "percentage": 9.82, "elapsed_time": "0:19:01", "remaining_time": "2:54:44"}
+{"current_steps": 23, "total_steps": 224, "loss": 0.597, "lr": 2e-05, "epoch": 0.6987341772151898, "percentage": 10.27, "elapsed_time": "0:20:01", "remaining_time": "2:54:57"}
+{"current_steps": 24, "total_steps": 224, "loss": 0.5507, "lr": 1.999877856940653e-05, "epoch": 0.7291139240506329, "percentage": 10.71, "elapsed_time": "0:20:54", "remaining_time": "2:54:10"}
+{"current_steps": 25, "total_steps": 224, "loss": 0.5784, "lr": 1.999511457600466e-05, "epoch": 0.759493670886076, "percentage": 11.16, "elapsed_time": "0:21:55", "remaining_time": "2:54:27"}
+{"current_steps": 26, "total_steps": 224, "loss": 0.5719, "lr": 1.9989008914857115e-05, "epoch": 0.789873417721519, "percentage": 11.61, "elapsed_time": "0:22:56", "remaining_time": "2:54:41"}
+{"current_steps": 27, "total_steps": 224, "loss": 0.5649, "lr": 1.998046307749216e-05, "epoch": 0.8202531645569621, "percentage": 12.05, "elapsed_time": "0:23:49", "remaining_time": "2:53:49"}
+{"current_steps": 28, "total_steps": 224, "loss": 0.55, "lr": 1.9969479151539238e-05, "epoch": 0.850632911392405, "percentage": 12.5, "elapsed_time": "0:24:49", "remaining_time": "2:53:47"}
+{"current_steps": 29, "total_steps": 224, "loss": 0.5935, "lr": 1.9956059820218982e-05, "epoch": 0.8810126582278481, "percentage": 12.95, "elapsed_time": "0:25:50", "remaining_time": "2:53:45"}
+{"current_steps": 30, "total_steps": 224, "loss": 0.5589, "lr": 1.9940208361687762e-05, "epoch": 0.9113924050632911, "percentage": 13.39, "elapsed_time": "0:26:41", "remaining_time": "2:52:38"}
+{"current_steps": 31, "total_steps": 224, "loss": 0.5388, "lr": 1.9921928648236855e-05, "epoch": 0.9417721518987342, "percentage": 13.84, "elapsed_time": "0:27:44", "remaining_time": "2:52:45"}
+{"current_steps": 32, "total_steps": 224, "loss": 0.5358, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "0:28:45", "remaining_time": "2:52:34"}
+{"current_steps": 33, "total_steps": 224, "loss": 0.7344, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "0:30:21", "remaining_time": "2:55:40"}
+{"current_steps": 34, "total_steps": 224, "loss": 0.4806, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "0:31:05", "remaining_time": "2:53:45"}
+{"current_steps": 35, "total_steps": 224, "loss": 0.4871, "lr": 1.982462542875576e-05, "epoch": 1.070886075949367, "percentage": 15.62, "elapsed_time": "0:31:56", "remaining_time": "2:52:26"}
+{"current_steps": 36, "total_steps": 224, "loss": 0.4807, "lr": 1.979428324547432e-05, "epoch": 1.1012658227848102, "percentage": 16.07, "elapsed_time": "0:32:44", "remaining_time": "2:51:00"}
+{"current_steps": 37, "total_steps": 224, "loss": 0.5233, "lr": 1.9761548454753455e-05, "epoch": 1.1316455696202532, "percentage": 16.52, "elapsed_time": "0:33:53", "remaining_time": "2:51:19"}
+{"current_steps": 38, "total_steps": 224, "loss": 0.4424, "lr": 1.972642905324813e-05, "epoch": 1.1620253164556962, "percentage": 16.96, "elapsed_time": "0:34:57", "remaining_time": "2:51:06"}
+{"current_steps": 39, "total_steps": 224, "loss": 0.4689, "lr": 1.9688933620140638e-05, "epoch": 1.1924050632911392, "percentage": 17.41, "elapsed_time": "0:35:45", "remaining_time": "2:49:39"}
+{"current_steps": 40, "total_steps": 224, "loss": 0.5329, "lr": 1.96490713150448e-05, "epoch": 1.2227848101265824, "percentage": 17.86, "elapsed_time": "0:36:47", "remaining_time": "2:49:16"}
+{"current_steps": 41, "total_steps": 224, "loss": 0.4655, "lr": 1.9606851875768404e-05, "epoch": 1.2531645569620253, "percentage": 18.3, "elapsed_time": "0:37:31", "remaining_time": "2:47:29"}
+{"current_steps": 42, "total_steps": 224, "loss": 0.4712, "lr": 1.956228561593441e-05, "epoch": 1.2835443037974683, "percentage": 18.75, "elapsed_time": "0:38:21", "remaining_time": "2:46:12"}
+{"current_steps": 43, "total_steps": 224, "loss": 0.5023, "lr": 1.9515383422461457e-05, "epoch": 1.3139240506329113, "percentage": 19.2, "elapsed_time": "0:39:10", "remaining_time": "2:44:55"}
+{"current_steps": 44, "total_steps": 224, "loss": 0.4177, "lr": 1.9466156752904344e-05, "epoch": 1.3443037974683545, "percentage": 19.64, "elapsed_time": "0:39:51", "remaining_time": "2:43:03"}
+{"current_steps": 45, "total_steps": 224, "loss": 0.5141, "lr": 1.9414617632655114e-05, "epoch": 1.3746835443037975, "percentage": 20.09, "elapsed_time": "0:40:59", "remaining_time": "2:43:05"}
+{"current_steps": 46, "total_steps": 224, "loss": 0.4599, "lr": 1.9360778652005416e-05, "epoch": 1.4050632911392404, "percentage": 20.54, "elapsed_time": "0:41:51", "remaining_time": "2:42:00"}
+{"current_steps": 47, "total_steps": 224, "loss": 0.4406, "lr": 1.9304652963070868e-05, "epoch": 1.4354430379746836, "percentage": 20.98, "elapsed_time": "0:42:43", "remaining_time": "2:40:53"}
+{"current_steps": 48, "total_steps": 224, "loss": 0.5134, "lr": 1.9246254276578175e-05, "epoch": 1.4658227848101266, "percentage": 21.43, "elapsed_time": "0:43:35", "remaining_time": "2:39:51"}
+{"current_steps": 49, "total_steps": 224, "loss": 0.444, "lr": 1.9185596858515797e-05, "epoch": 1.4962025316455696, "percentage": 21.88, "elapsed_time": "0:44:25", "remaining_time": "2:38:38"}
+{"current_steps": 50, "total_steps": 224, "loss": 0.3933, "lr": 1.9122695526648968e-05, "epoch": 1.5265822784810128, "percentage": 22.32, "elapsed_time": "0:45:09", "remaining_time": "2:37:07"}
+{"current_steps": 51, "total_steps": 224, "loss": 0.4488, "lr": 1.905756564689991e-05, "epoch": 1.5569620253164556, "percentage": 22.77, "elapsed_time": "0:45:55", "remaining_time": "2:35:47"}
+{"current_steps": 52, "total_steps": 224, "loss": 0.5049, "lr": 1.8990223129594146e-05, "epoch": 1.5873417721518988, "percentage": 23.21, "elapsed_time": "0:47:00", "remaining_time": "2:35:29"}
+{"current_steps": 53, "total_steps": 224, "loss": 0.4713, "lr": 1.8920684425573865e-05, "epoch": 1.6177215189873417, "percentage": 23.66, "elapsed_time": "0:47:42", "remaining_time": "2:33:54"}
+{"current_steps": 54, "total_steps": 224, "loss": 0.44, "lr": 1.884896652217917e-05, "epoch": 1.6481012658227847, "percentage": 24.11, "elapsed_time": "0:48:30", "remaining_time": "2:32:42"}
+{"current_steps": 55, "total_steps": 224, "loss": 0.4619, "lr": 1.877508693909831e-05, "epoch": 1.678481012658228, "percentage": 24.55, "elapsed_time": "0:49:25", "remaining_time": "2:31:51"}
+{"current_steps": 56, "total_steps": 224, "loss": 0.4267, "lr": 1.8699063724087905e-05, "epoch": 1.7088607594936709, "percentage": 25.0, "elapsed_time": "0:50:18", "remaining_time": "2:30:56"}
+{"current_steps": 57, "total_steps": 224, "loss": 0.4761, "lr": 1.862091544856407e-05, "epoch": 1.7392405063291139, "percentage": 25.45, "elapsed_time": "0:51:12", "remaining_time": "2:30:01"}
+{"current_steps": 58, "total_steps": 224, "loss": 0.4637, "lr": 1.854066120306571e-05, "epoch": 1.769620253164557, "percentage": 25.89, "elapsed_time": "0:52:14", "remaining_time": "2:29:31"}
+{"current_steps": 59, "total_steps": 224, "loss": 0.4436, "lr": 1.8458320592590976e-05, "epoch": 1.8, "percentage": 26.34, "elapsed_time": "0:53:24", "remaining_time": "2:29:22"}
+{"current_steps": 60, "total_steps": 224, "loss": 0.4885, "lr": 1.837391373180801e-05, "epoch": 1.830379746835443, "percentage": 26.79, "elapsed_time": "0:54:30", "remaining_time": "2:28:58"}
+{"current_steps": 61, "total_steps": 224, "loss": 0.4367, "lr": 1.8287461240141217e-05, "epoch": 1.8607594936708862, "percentage": 27.23, "elapsed_time": "0:55:26", "remaining_time": "2:28:09"}
+{"current_steps": 62, "total_steps": 224, "loss": 0.4405, "lr": 1.8198984236734246e-05, "epoch": 1.891139240506329, "percentage": 27.68, "elapsed_time": "0:56:20", "remaining_time": "2:27:13"}
+{"current_steps": 63, "total_steps": 224, "loss": 0.4269, "lr": 1.8108504335290852e-05, "epoch": 1.9215189873417722, "percentage": 28.12, "elapsed_time": "0:57:02", "remaining_time": "2:25:46"}
+{"current_steps": 64, "total_steps": 224, "loss": 0.4215, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "0:57:58", "remaining_time": "2:24:55"}
+{"current_steps": 65, "total_steps": 224, "loss": 0.5136, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "0:58:52", "remaining_time": "2:24:01"}
+{"current_steps": 66, "total_steps": 224, "loss": 0.5217, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "1:00:34", "remaining_time": "2:25:01"}
+{"current_steps": 67, "total_steps": 224, "loss": 0.3458, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "1:01:26", "remaining_time": "2:23:58"}
+{"current_steps": 68, "total_steps": 224, "loss": 0.3504, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "1:02:13", "remaining_time": "2:22:46"}
+{"current_steps": 69, "total_steps": 224, "loss": 0.3902, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "1:03:20", "remaining_time": "2:22:17"}
+{"current_steps": 70, "total_steps": 224, "loss": 0.3084, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "1:03:57", "remaining_time": "2:20:42"}
+{"current_steps": 71, "total_steps": 224, "loss": 0.4264, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "1:04:56", "remaining_time": "2:19:56"}
+{"current_steps": 72, "total_steps": 224, "loss": 0.3048, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "1:05:52", "remaining_time": "2:19:04"}
+{"current_steps": 73, "total_steps": 224, "loss": 0.3685, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "1:07:02", "remaining_time": "2:18:39"}
+{"current_steps": 74, "total_steps": 224, "loss": 0.3297, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "1:07:53", "remaining_time": "2:17:36"}
+{"current_steps": 75, "total_steps": 224, "loss": 0.3494, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "1:08:38", "remaining_time": "2:16:22"}
+{"current_steps": 76, "total_steps": 224, "loss": 0.3359, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "1:09:35", "remaining_time": "2:15:32"}
+{"current_steps": 77, "total_steps": 224, "loss": 0.3738, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "1:10:38", "remaining_time": "2:14:52"}
+{"current_steps": 78, "total_steps": 224, "loss": 0.3256, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "1:11:44", "remaining_time": "2:14:16"}
+{"current_steps": 79, "total_steps": 224, "loss": 0.3154, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "1:12:34", "remaining_time": "2:13:12"}
+{"current_steps": 80, "total_steps": 224, "loss": 0.3466, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "1:13:26", "remaining_time": "2:12:11"}
+{"current_steps": 81, "total_steps": 224, "loss": 0.3428, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "1:14:28", "remaining_time": "2:11:29"}
+{"current_steps": 82, "total_steps": 224, "loss": 0.3096, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "1:15:17", "remaining_time": "2:10:22"}
+{"current_steps": 83, "total_steps": 224, "loss": 0.3437, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "1:16:12", "remaining_time": "2:09:28"}
+{"current_steps": 84, "total_steps": 224, "loss": 0.3118, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "1:16:57", "remaining_time": "2:08:16"}
+{"current_steps": 85, "total_steps": 224, "loss": 0.3807, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "1:18:01", "remaining_time": "2:07:35"}
+{"current_steps": 86, "total_steps": 224, "loss": 0.3003, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "1:18:45", "remaining_time": "2:06:22"}
+{"current_steps": 87, "total_steps": 224, "loss": 0.3883, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "1:19:39", "remaining_time": "2:05:26"}
+{"current_steps": 88, "total_steps": 224, "loss": 0.304, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "1:20:19", "remaining_time": "2:04:08"}
+{"current_steps": 89, "total_steps": 224, "loss": 0.3603, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "1:21:06", "remaining_time": "2:03:01"}
+{"current_steps": 90, "total_steps": 224, "loss": 0.2964, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "1:21:48", "remaining_time": "2:01:48"}
+{"current_steps": 91, "total_steps": 224, "loss": 0.3442, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "1:22:46", "remaining_time": "2:00:58"}
+{"current_steps": 92, "total_steps": 224, "loss": 0.3446, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "1:23:41", "remaining_time": "2:00:04"}
+{"current_steps": 93, "total_steps": 224, "loss": 0.3397, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "1:24:30", "remaining_time": "1:59:02"}
+{"current_steps": 94, "total_steps": 224, "loss": 0.3069, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "1:25:28", "remaining_time": "1:58:12"}
+{"current_steps": 95, "total_steps": 224, "loss": 0.3638, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "1:26:26", "remaining_time": "1:57:22"}
+{"current_steps": 96, "total_steps": 224, "loss": 0.3712, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "1:27:17", "remaining_time": "1:56:23"}
+{"current_steps": 97, "total_steps": 224, "loss": 0.3542, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "1:28:15", "remaining_time": "1:55:33"}
+{"current_steps": 98, "total_steps": 224, "loss": 0.4107, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "1:29:14", "remaining_time": "1:54:44"}
+{"current_steps": 99, "total_steps": 224, "loss": 0.2537, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "1:30:35", "remaining_time": "1:54:22"}
+{"current_steps": 100, "total_steps": 224, "loss": 0.2451, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "1:31:37", "remaining_time": "1:53:36"}
+{"current_steps": 101, "total_steps": 224, "loss": 0.2225, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "1:32:32", "remaining_time": "1:52:42"}
+{"current_steps": 102, "total_steps": 224, "loss": 0.2686, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "1:33:23", "remaining_time": "1:51:42"}
+{"current_steps": 103, "total_steps": 224, "loss": 0.2613, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "1:34:24", "remaining_time": "1:50:54"}
+{"current_steps": 104, "total_steps": 224, "loss": 0.2346, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "1:35:23", "remaining_time": "1:50:03"}
+{"current_steps": 105, "total_steps": 224, "loss": 0.2366, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "1:36:18", "remaining_time": "1:49:08"}
+{"current_steps": 106, "total_steps": 224, "loss": 0.2357, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "1:37:14", "remaining_time": "1:48:14"}
+{"current_steps": 107, "total_steps": 224, "loss": 0.2537, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "1:38:03", "remaining_time": "1:47:13"}
+{"current_steps": 108, "total_steps": 224, "loss": 0.2325, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "1:38:47", "remaining_time": "1:46:07"}
+{"current_steps": 109, "total_steps": 224, "loss": 0.2302, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "1:39:41", "remaining_time": "1:45:10"}
+{"current_steps": 110, "total_steps": 224, "loss": 0.2379, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "1:40:35", "remaining_time": "1:44:14"}
+{"current_steps": 111, "total_steps": 224, "loss": 0.2196, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "1:41:22", "remaining_time": "1:43:11"}
+{"current_steps": 112, "total_steps": 224, "loss": 0.2417, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "1:42:21", "remaining_time": "1:42:21"}
+{"current_steps": 113, "total_steps": 224, "loss": 0.2462, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "1:43:21", "remaining_time": "1:41:31"}
+{"current_steps": 114, "total_steps": 224, "loss": 0.2291, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "1:44:03", "remaining_time": "1:40:24"}
+{"current_steps": 115, "total_steps": 224, "loss": 0.2374, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "1:44:58", "remaining_time": "1:39:29"}
+{"current_steps": 116, "total_steps": 224, "loss": 0.2376, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "1:46:06", "remaining_time": "1:38:47"}
+{"current_steps": 117, "total_steps": 224, "loss": 0.242, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "1:46:59", "remaining_time": "1:37:50"}
+{"current_steps": 118, "total_steps": 224, "loss": 0.2476, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "1:47:59", "remaining_time": "1:37:00"}
+{"current_steps": 119, "total_steps": 224, "loss": 0.2364, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "1:49:05", "remaining_time": "1:36:15"}
+{"current_steps": 120, "total_steps": 224, "loss": 0.2354, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "1:50:10", "remaining_time": "1:35:29"}
+{"current_steps": 121, "total_steps": 224, "loss": 0.2284, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "1:50:55", "remaining_time": "1:34:25"}
+{"current_steps": 122, "total_steps": 224, "loss": 0.2413, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "1:51:53", "remaining_time": "1:33:32"}
+{"current_steps": 123, "total_steps": 224, "loss": 0.2467, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "1:52:49", "remaining_time": "1:32:38"}
+{"current_steps": 124, "total_steps": 224, "loss": 0.213, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "1:53:43", "remaining_time": "1:31:42"}
+{"current_steps": 125, "total_steps": 224, "loss": 0.244, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "1:54:39", "remaining_time": "1:30:48"}
+{"current_steps": 126, "total_steps": 224, "loss": 0.2324, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "1:55:31", "remaining_time": "1:29:51"}
+{"current_steps": 127, "total_steps": 224, "loss": 0.2338, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "1:56:25", "remaining_time": "1:28:55"}
+{"current_steps": 128, "total_steps": 224, "loss": 0.2551, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "1:57:22", "remaining_time": "1:28:01"}
+{"current_steps": 129, "total_steps": 224, "loss": 0.2134, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "1:58:06", "remaining_time": "1:26:58"}
+{"current_steps": 130, "total_steps": 224, "loss": 0.2247, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "1:59:03", "remaining_time": "1:26:05"}
+{"current_steps": 131, "total_steps": 224, "loss": 0.3163, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "2:00:27", "remaining_time": "1:25:31"}
+{"current_steps": 132, "total_steps": 224, "loss": 0.2007, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "2:01:19", "remaining_time": "1:24:33"}
+{"current_steps": 133, "total_steps": 224, "loss": 0.1541, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "2:02:15", "remaining_time": "1:23:39"}
+{"current_steps": 134, "total_steps": 224, "loss": 0.1569, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "2:03:08", "remaining_time": "1:22:42"}
+{"current_steps": 135, "total_steps": 224, "loss": 0.1675, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "2:04:11", "remaining_time": "1:21:52"}
+{"current_steps": 136, "total_steps": 224, "loss": 0.1713, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "2:05:04", "remaining_time": "1:20:55"}
+{"current_steps": 137, "total_steps": 224, "loss": 0.1529, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "2:05:58", "remaining_time": "1:19:59"}
+{"current_steps": 138, "total_steps": 224, "loss": 0.1629, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "2:06:54", "remaining_time": "1:19:05"}
+{"current_steps": 139, "total_steps": 224, "loss": 0.1496, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "2:07:46", "remaining_time": "1:18:08"}
+{"current_steps": 140, "total_steps": 224, "loss": 0.147, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "2:08:41", "remaining_time": "1:17:12"}
+{"current_steps": 141, "total_steps": 224, "loss": 0.1713, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "2:09:31", "remaining_time": "1:16:14"}
+{"current_steps": 142, "total_steps": 224, "loss": 0.1422, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "2:10:15", "remaining_time": "1:15:13"}
+{"current_steps": 143, "total_steps": 224, "loss": 0.1547, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "2:11:00", "remaining_time": "1:14:12"}
+{"current_steps": 144, "total_steps": 224, "loss": 0.163, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "2:12:04", "remaining_time": "1:13:22"}
+{"current_steps": 145, "total_steps": 224, "loss": 0.1362, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "2:12:51", "remaining_time": "1:12:23"}
+{"current_steps": 146, "total_steps": 224, "loss": 0.1605, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "2:13:52", "remaining_time": "1:11:31"}
+{"current_steps": 147, "total_steps": 224, "loss": 0.1657, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "2:14:53", "remaining_time": "1:10:39"}
+{"current_steps": 148, "total_steps": 224, "loss": 0.1417, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "2:15:45", "remaining_time": "1:09:42"}
+{"current_steps": 149, "total_steps": 224, "loss": 0.1598, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "2:16:37", "remaining_time": "1:08:46"}
+{"current_steps": 150, "total_steps": 224, "loss": 0.1659, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "2:17:25", "remaining_time": "1:07:47"}
+{"current_steps": 151, "total_steps": 224, "loss": 0.1232, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "2:18:08", "remaining_time": "1:06:47"}
+{"current_steps": 152, "total_steps": 224, "loss": 0.1407, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "2:18:46", "remaining_time": "1:05:44"}
+{"current_steps": 153, "total_steps": 224, "loss": 0.188, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "2:19:53", "remaining_time": "1:04:54"}
+{"current_steps": 154, "total_steps": 224, "loss": 0.139, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "2:20:58", "remaining_time": "1:04:04"}
+{"current_steps": 155, "total_steps": 224, "loss": 0.1642, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "2:21:54", "remaining_time": "1:03:10"}
+{"current_steps": 156, "total_steps": 224, "loss": 0.1471, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "2:22:49", "remaining_time": "1:02:15"}
+{"current_steps": 157, "total_steps": 224, "loss": 0.1367, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "2:23:42", "remaining_time": "1:01:19"}
+{"current_steps": 158, "total_steps": 224, "loss": 0.1452, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "2:24:43", "remaining_time": "1:00:27"}
+{"current_steps": 159, "total_steps": 224, "loss": 0.1428, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "2:25:38", "remaining_time": "0:59:32"}
+{"current_steps": 160, "total_steps": 224, "loss": 0.1564, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "2:26:33", "remaining_time": "0:58:37"}
+{"current_steps": 161, "total_steps": 224, "loss": 0.1586, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "2:27:45", "remaining_time": "0:57:49"}
+{"current_steps": 162, "total_steps": 224, "loss": 0.1401, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "2:28:32", "remaining_time": "0:56:50"}
+{"current_steps": 163, "total_steps": 224, "loss": 0.1777, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "2:29:18", "remaining_time": "0:55:52"}
+{"current_steps": 164, "total_steps": 224, "loss": 0.1548, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "2:31:01", "remaining_time": "0:55:15"}
+{"current_steps": 165, "total_steps": 224, "loss": 0.1256, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "2:32:09", "remaining_time": "0:54:24"}
+{"current_steps": 166, "total_steps": 224, "loss": 0.0947, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "2:32:59", "remaining_time": "0:53:27"}
+{"current_steps": 167, "total_steps": 224, "loss": 0.0933, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "2:33:49", "remaining_time": "0:52:30"}
+{"current_steps": 168, "total_steps": 224, "loss": 0.122, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "2:34:54", "remaining_time": "0:51:38"}
+{"current_steps": 169, "total_steps": 224, "loss": 0.0971, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "2:35:46", "remaining_time": "0:50:41"}
+{"current_steps": 170, "total_steps": 224, "loss": 0.1095, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "2:36:41", "remaining_time": "0:49:46"}
+{"current_steps": 171, "total_steps": 224, "loss": 0.113, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "2:37:29", "remaining_time": "0:48:48"}
+{"current_steps": 172, "total_steps": 224, "loss": 0.1125, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "2:38:29", "remaining_time": "0:47:54"}
+{"current_steps": 173, "total_steps": 224, "loss": 0.1058, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "2:39:23", "remaining_time": "0:46:59"}
+{"current_steps": 174, "total_steps": 224, "loss": 0.0954, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "2:40:16", "remaining_time": "0:46:03"}
+{"current_steps": 175, "total_steps": 224, "loss": 0.106, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "2:41:07", "remaining_time": "0:45:07"}
+{"current_steps": 176, "total_steps": 224, "loss": 0.0931, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "2:42:00", "remaining_time": "0:44:10"}
+{"current_steps": 177, "total_steps": 224, "loss": 0.0908, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "2:43:03", "remaining_time": "0:43:17"}
+{"current_steps": 178, "total_steps": 224, "loss": 0.1057, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "2:44:04", "remaining_time": "0:42:24"}
+{"current_steps": 179, "total_steps": 224, "loss": 0.0986, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "2:44:48", "remaining_time": "0:41:26"}
+{"current_steps": 180, "total_steps": 224, "loss": 0.0877, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "2:45:41", "remaining_time": "0:40:30"}
+{"current_steps": 181, "total_steps": 224, "loss": 0.099, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "2:46:35", "remaining_time": "0:39:34"}
+{"current_steps": 182, "total_steps": 224, "loss": 0.0958, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "2:47:38", "remaining_time": "0:38:41"}
+{"current_steps": 183, "total_steps": 224, "loss": 0.1123, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "2:48:40", "remaining_time": "0:37:47"}
+{"current_steps": 184, "total_steps": 224, "loss": 0.0934, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "2:49:36", "remaining_time": "0:36:52"}
+{"current_steps": 185, "total_steps": 224, "loss": 0.1252, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "2:50:33", "remaining_time": "0:35:57"}
+{"current_steps": 186, "total_steps": 224, "loss": 0.0801, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "2:51:15", "remaining_time": "0:34:59"}
+{"current_steps": 187, "total_steps": 224, "loss": 0.0998, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "2:52:04", "remaining_time": "0:34:02"}
+{"current_steps": 188, "total_steps": 224, "loss": 0.1002, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "2:52:58", "remaining_time": "0:33:07"}
+{"current_steps": 189, "total_steps": 224, "loss": 0.1115, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "2:53:50", "remaining_time": "0:32:11"}
+{"current_steps": 190, "total_steps": 224, "loss": 0.0986, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "2:54:30", "remaining_time": "0:31:13"}
+{"current_steps": 191, "total_steps": 224, "loss": 0.108, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "2:55:22", "remaining_time": "0:30:18"}
+{"current_steps": 192, "total_steps": 224, "loss": 0.0913, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "2:56:11", "remaining_time": "0:29:21"}
+{"current_steps": 193, "total_steps": 224, "loss": 0.1042, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "2:57:03", "remaining_time": "0:28:26"}
+{"current_steps": 194, "total_steps": 224, "loss": 0.1083, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "2:57:58", "remaining_time": "0:27:31"}
+{"current_steps": 195, "total_steps": 224, "loss": 0.1117, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "2:58:53", "remaining_time": "0:26:36"}
+{"current_steps": 196, "total_steps": 224, "loss": 0.1091, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "2:59:36", "remaining_time": "0:25:39"}
+{"current_steps": 197, "total_steps": 224, "loss": 0.0816, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "3:00:55", "remaining_time": "0:24:47"}
+{"current_steps": 198, "total_steps": 224, "loss": 0.0799, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "3:01:59", "remaining_time": "0:23:53"}
+{"current_steps": 199, "total_steps": 224, "loss": 0.0739, "lr": 7.537457234218271e-07, "epoch": 6.091139240506329, "percentage": 88.84, "elapsed_time": "3:02:49", "remaining_time": "0:22:58"}
+{"current_steps": 200, "total_steps": 224, "loss": 0.0758, "lr": 6.953470369291349e-07, "epoch": 6.121518987341772, "percentage": 89.29, "elapsed_time": "3:03:49", "remaining_time": "0:22:03"}
+{"current_steps": 201, "total_steps": 224, "loss": 0.0949, "lr": 6.392213479945852e-07, "epoch": 6.151898734177215, "percentage": 89.73, "elapsed_time": "3:04:49", "remaining_time": "0:21:08"}
+{"current_steps": 202, "total_steps": 224, "loss": 0.0876, "lr": 5.853823673448877e-07, "epoch": 6.182278481012658, "percentage": 90.18, "elapsed_time": "3:05:59", "remaining_time": "0:20:15"}
+{"current_steps": 203, "total_steps": 224, "loss": 0.087, "lr": 5.33843247095659e-07, "epoch": 6.2126582278481015, "percentage": 90.62, "elapsed_time": "3:06:55", "remaining_time": "0:19:20"}
+{"current_steps": 204, "total_steps": 224, "loss": 0.0895, "lr": 4.846165775385459e-07, "epoch": 6.243037974683545, "percentage": 91.07, "elapsed_time": "3:07:50", "remaining_time": "0:18:24"}
+{"current_steps": 205, "total_steps": 224, "loss": 0.0889, "lr": 4.3771438406559173e-07, "epoch": 6.273417721518987, "percentage": 91.52, "elapsed_time": "3:08:51", "remaining_time": "0:17:30"}
+{"current_steps": 206, "total_steps": 224, "loss": 0.0703, "lr": 3.931481242315993e-07, "epoch": 6.30379746835443, "percentage": 91.96, "elapsed_time": "3:09:37", "remaining_time": "0:16:34"}
+{"current_steps": 207, "total_steps": 224, "loss": 0.0796, "lr": 3.5092868495520294e-07, "epoch": 6.334177215189873, "percentage": 92.41, "elapsed_time": "3:10:45", "remaining_time": "0:15:39"}
+{"current_steps": 208, "total_steps": 224, "loss": 0.0968, "lr": 3.110663798593616e-07, "epoch": 6.364556962025317, "percentage": 92.86, "elapsed_time": "3:11:34", "remaining_time": "0:14:44"}
+{"current_steps": 209, "total_steps": 224, "loss": 0.0825, "lr": 2.735709467518699e-07, "epoch": 6.39493670886076, "percentage": 93.3, "elapsed_time": "3:12:25", "remaining_time": "0:13:48"}
+{"current_steps": 210, "total_steps": 224, "loss": 0.0887, "lr": 2.384515452465475e-07, "epoch": 6.425316455696202, "percentage": 93.75, "elapsed_time": "3:13:32", "remaining_time": "0:12:54"}
+{"current_steps": 211, "total_steps": 224, "loss": 0.0764, "lr": 2.0571675452567997e-07, "epoch": 6.455696202531645, "percentage": 94.2, "elapsed_time": "3:14:25", "remaining_time": "0:11:58"}
+{"current_steps": 212, "total_steps": 224, "loss": 0.0887, "lr": 1.7537457124423896e-07, "epoch": 6.4860759493670885, "percentage": 94.64, "elapsed_time": "3:15:27", "remaining_time": "0:11:03"}
+{"current_steps": 213, "total_steps": 224, "loss": 0.0806, "lr": 1.474324075764111e-07, "epoch": 6.516455696202532, "percentage": 95.09, "elapsed_time": "3:16:29", "remaining_time": "0:10:08"}
+{"current_steps": 214, "total_steps": 224, "loss": 0.0864, "lr": 1.2189708940490653e-07, "epoch": 6.546835443037975, "percentage": 95.54, "elapsed_time": "3:17:10", "remaining_time": "0:09:12"}
+{"current_steps": 215, "total_steps": 224, "loss": 0.0867, "lr": 9.877485465349057e-08, "epoch": 6.577215189873417, "percentage": 95.98, "elapsed_time": "3:18:14", "remaining_time": "0:08:17"}
+{"current_steps": 216, "total_steps": 224, "loss": 0.0833, "lr": 7.807135176314707e-08, "epoch": 6.6075949367088604, "percentage": 96.43, "elapsed_time": "3:19:01", "remaining_time": "0:07:22"}
+{"current_steps": 217, "total_steps": 224, "loss": 0.0833, "lr": 5.979163831223988e-08, "epoch": 6.637974683544304, "percentage": 96.88, "elapsed_time": "3:19:56", "remaining_time": "0:06:26"}
+{"current_steps": 218, "total_steps": 224, "loss": 0.073, "lr": 4.394017978101905e-08, "epoch": 6.668354430379747, "percentage": 97.32, "elapsed_time": "3:20:53", "remaining_time": "0:05:31"}
+{"current_steps": 219, "total_steps": 224, "loss": 0.0851, "lr": 3.0520848460765525e-08, "epoch": 6.69873417721519, "percentage": 97.77, "elapsed_time": "3:21:49", "remaining_time": "0:04:36"}
+{"current_steps": 220, "total_steps": 224, "loss": 0.0793, "lr": 1.9536922507841227e-08, "epoch": 6.729113924050633, "percentage": 98.21, "elapsed_time": "3:22:33", "remaining_time": "0:03:40"}
+{"current_steps": 221, "total_steps": 224, "loss": 0.0734, "lr": 1.099108514288627e-08, "epoch": 6.759493670886076, "percentage": 98.66, "elapsed_time": "3:23:23", "remaining_time": "0:02:45"}
+{"current_steps": 222, "total_steps": 224, "loss": 0.0939, "lr": 4.885423995341088e-09, "epoch": 6.789873417721519, "percentage": 99.11, "elapsed_time": "3:24:15", "remaining_time": "0:01:50"}
+{"current_steps": 223, "total_steps": 224, "loss": 0.0796, "lr": 1.2214305934699078e-09, "epoch": 6.820253164556962, "percentage": 99.55, "elapsed_time": "3:25:06", "remaining_time": "0:00:55"}
+{"current_steps": 224, "total_steps": 224, "loss": 0.0811, "lr": 0.0, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "3:25:53", "remaining_time": "0:00:00"}
+{"current_steps": 224, "total_steps": 224, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "3:27:02", "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": 6.293833826007159,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 0.8862,
+      "step": 1
+    },
+    {
+      "epoch": 0.060759493670886074,
+      "grad_norm": 6.06683060242767,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 0.8348,
+      "step": 2
+    },
+    {
+      "epoch": 0.09113924050632911,
+      "grad_norm": 6.085593029855262,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.8919,
+      "step": 3
+    },
+    {
+      "epoch": 0.12151898734177215,
+      "grad_norm": 5.760576316404554,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.8317,
+      "step": 4
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 4.5955604298294395,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.8164,
+      "step": 5
+    },
+    {
+      "epoch": 0.18227848101265823,
+      "grad_norm": 2.4241910432702802,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.7569,
+      "step": 6
+    },
+    {
+      "epoch": 0.21265822784810126,
+      "grad_norm": 2.0775478325962156,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.7122,
+      "step": 7
+    },
+    {
+      "epoch": 0.2430379746835443,
+      "grad_norm": 3.9008746772989573,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.7835,
+      "step": 8
+    },
+    {
+      "epoch": 0.27341772151898736,
+      "grad_norm": 3.6499637096171424,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.7065,
+      "step": 9
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 3.897621871094942,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.7161,
+      "step": 10
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "grad_norm": 4.108219669394765,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.6817,
+      "step": 11
+    },
+    {
+      "epoch": 0.36455696202531646,
+      "grad_norm": 4.05540403379258,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 0.7038,
+      "step": 12
+    },
+    {
+      "epoch": 0.3949367088607595,
+      "grad_norm": 2.568474560061959,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 0.6703,
+      "step": 13
+    },
+    {
+      "epoch": 0.4253164556962025,
+      "grad_norm": 1.9544696940564121,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 0.652,
+      "step": 14
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 2.6134105187686236,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.6597,
+      "step": 15
+    },
+    {
+      "epoch": 0.4860759493670886,
+      "grad_norm": 2.2342699291974677,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.5939,
+      "step": 16
+    },
+    {
+      "epoch": 0.5164556962025316,
+      "grad_norm": 1.7411085903434311,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.6429,
+      "step": 17
+    },
+    {
+      "epoch": 0.5468354430379747,
+      "grad_norm": 1.2430514639056482,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.6238,
+      "step": 18
+    },
+    {
+      "epoch": 0.5772151898734177,
+      "grad_norm": 1.310646421522415,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.6051,
+      "step": 19
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 1.1362663542854012,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.5999,
+      "step": 20
+    },
+    {
+      "epoch": 0.6379746835443038,
+      "grad_norm": 0.8889327202115898,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.5697,
+      "step": 21
+    },
+    {
+      "epoch": 0.6683544303797468,
+      "grad_norm": 1.0712088916619098,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.5683,
+      "step": 22
+    },
+    {
+      "epoch": 0.6987341772151898,
+      "grad_norm": 1.0078969637180104,
+      "learning_rate": 2e-05,
+      "loss": 0.597,
+      "step": 23
+    },
+    {
+      "epoch": 0.7291139240506329,
+      "grad_norm": 0.9422799824806541,
+      "learning_rate": 1.999877856940653e-05,
+      "loss": 0.5507,
+      "step": 24
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.9698330597252763,
+      "learning_rate": 1.999511457600466e-05,
+      "loss": 0.5784,
+      "step": 25
+    },
+    {
+      "epoch": 0.789873417721519,
+      "grad_norm": 0.7221079971222841,
+      "learning_rate": 1.9989008914857115e-05,
+      "loss": 0.5719,
+      "step": 26
+    },
+    {
+      "epoch": 0.8202531645569621,
+      "grad_norm": 0.7014980135419222,
+      "learning_rate": 1.998046307749216e-05,
+      "loss": 0.5649,
+      "step": 27
+    },
+    {
+      "epoch": 0.850632911392405,
+      "grad_norm": 0.7633701425527275,
+      "learning_rate": 1.9969479151539238e-05,
+      "loss": 0.55,
+      "step": 28
+    },
+    {
+      "epoch": 0.8810126582278481,
+      "grad_norm": 0.6417825074207438,
+      "learning_rate": 1.9956059820218982e-05,
+      "loss": 0.5935,
+      "step": 29
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.708037799601626,
+      "learning_rate": 1.9940208361687762e-05,
+      "loss": 0.5589,
+      "step": 30
+    },
+    {
+      "epoch": 0.9417721518987342,
+      "grad_norm": 0.7491076050282107,
+      "learning_rate": 1.9921928648236855e-05,
+      "loss": 0.5388,
+      "step": 31
+    },
+    {
+      "epoch": 0.9721518987341772,
+      "grad_norm": 0.5804329603861615,
+      "learning_rate": 1.990122514534651e-05,
+      "loss": 0.5358,
+      "step": 32
+    },
+    {
+      "epoch": 1.010126582278481,
+      "grad_norm": 1.0995232109558182,
+      "learning_rate": 1.9878102910595097e-05,
+      "loss": 0.7344,
+      "step": 33
+    },
+    {
+      "epoch": 1.040506329113924,
+      "grad_norm": 0.5842012161050123,
+      "learning_rate": 1.985256759242359e-05,
+      "loss": 0.4806,
+      "step": 34
+    },
+    {
+      "epoch": 1.070886075949367,
+      "grad_norm": 0.704739789920105,
+      "learning_rate": 1.982462542875576e-05,
+      "loss": 0.4871,
+      "step": 35
+    },
+    {
+      "epoch": 1.1012658227848102,
+      "grad_norm": 0.736623351275328,
+      "learning_rate": 1.979428324547432e-05,
+      "loss": 0.4807,
+      "step": 36
+    },
+    {
+      "epoch": 1.1316455696202532,
+      "grad_norm": 0.6253908809510927,
+      "learning_rate": 1.9761548454753455e-05,
+      "loss": 0.5233,
+      "step": 37
+    },
+    {
+      "epoch": 1.1620253164556962,
+      "grad_norm": 0.6182900601597383,
+      "learning_rate": 1.972642905324813e-05,
+      "loss": 0.4424,
+      "step": 38
+    },
+    {
+      "epoch": 1.1924050632911392,
+      "grad_norm": 0.6681235591120583,
+      "learning_rate": 1.9688933620140638e-05,
+      "loss": 0.4689,
+      "step": 39
+    },
+    {
+      "epoch": 1.2227848101265824,
+      "grad_norm": 0.6373323329321743,
+      "learning_rate": 1.96490713150448e-05,
+      "loss": 0.5329,
+      "step": 40
+    },
+    {
+      "epoch": 1.2531645569620253,
+      "grad_norm": 0.7047275034593882,
+      "learning_rate": 1.9606851875768404e-05,
+      "loss": 0.4655,
+      "step": 41
+    },
+    {
+      "epoch": 1.2835443037974683,
+      "grad_norm": 0.6246515542250495,
+      "learning_rate": 1.956228561593441e-05,
+      "loss": 0.4712,
+      "step": 42
+    },
+    {
+      "epoch": 1.3139240506329113,
+      "grad_norm": 0.5856508173641957,
+      "learning_rate": 1.9515383422461457e-05,
+      "loss": 0.5023,
+      "step": 43
+    },
+    {
+      "epoch": 1.3443037974683545,
+      "grad_norm": 0.5962967705046875,
+      "learning_rate": 1.9466156752904344e-05,
+      "loss": 0.4177,
+      "step": 44
+    },
+    {
+      "epoch": 1.3746835443037975,
+      "grad_norm": 0.7806001779998398,
+      "learning_rate": 1.9414617632655114e-05,
+      "loss": 0.5141,
+      "step": 45
+    },
+    {
+      "epoch": 1.4050632911392404,
+      "grad_norm": 0.622043734959372,
+      "learning_rate": 1.9360778652005416e-05,
+      "loss": 0.4599,
+      "step": 46
+    },
+    {
+      "epoch": 1.4354430379746836,
+      "grad_norm": 0.7121168891261236,
+      "learning_rate": 1.9304652963070868e-05,
+      "loss": 0.4406,
+      "step": 47
+    },
+    {
+      "epoch": 1.4658227848101266,
+      "grad_norm": 0.6488634345123712,
+      "learning_rate": 1.9246254276578175e-05,
+      "loss": 0.5134,
+      "step": 48
+    },
+    {
+      "epoch": 1.4962025316455696,
+      "grad_norm": 0.520746079921578,
+      "learning_rate": 1.9185596858515797e-05,
+      "loss": 0.444,
+      "step": 49
+    },
+    {
+      "epoch": 1.5265822784810128,
+      "grad_norm": 0.6045948242543929,
+      "learning_rate": 1.9122695526648968e-05,
+      "loss": 0.3933,
+      "step": 50
+    },
+    {
+      "epoch": 1.5569620253164556,
+      "grad_norm": 0.5254642849482244,
+      "learning_rate": 1.905756564689991e-05,
+      "loss": 0.4488,
+      "step": 51
+    },
+    {
+      "epoch": 1.5873417721518988,
+      "grad_norm": 0.6157649648460861,
+      "learning_rate": 1.8990223129594146e-05,
+      "loss": 0.5049,
+      "step": 52
+    },
+    {
+      "epoch": 1.6177215189873417,
+      "grad_norm": 0.5631831213957198,
+      "learning_rate": 1.8920684425573865e-05,
+      "loss": 0.4713,
+      "step": 53
+    },
+    {
+      "epoch": 1.6481012658227847,
+      "grad_norm": 0.5602537302229734,
+      "learning_rate": 1.884896652217917e-05,
+      "loss": 0.44,
+      "step": 54
+    },
+    {
+      "epoch": 1.678481012658228,
+      "grad_norm": 0.5914581257872572,
+      "learning_rate": 1.877508693909831e-05,
+      "loss": 0.4619,
+      "step": 55
+    },
+    {
+      "epoch": 1.7088607594936709,
+      "grad_norm": 0.549463095796092,
+      "learning_rate": 1.8699063724087905e-05,
+      "loss": 0.4267,
+      "step": 56
+    },
+    {
+      "epoch": 1.7392405063291139,
+      "grad_norm": 0.5340178679294976,
+      "learning_rate": 1.862091544856407e-05,
+      "loss": 0.4761,
+      "step": 57
+    },
+    {
+      "epoch": 1.769620253164557,
+      "grad_norm": 0.5808152206830257,
+      "learning_rate": 1.854066120306571e-05,
+      "loss": 0.4637,
+      "step": 58
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.4902800171092904,
+      "learning_rate": 1.8458320592590976e-05,
+      "loss": 0.4436,
+      "step": 59
+    },
+    {
+      "epoch": 1.830379746835443,
+      "grad_norm": 0.5390313052443518,
+      "learning_rate": 1.837391373180801e-05,
+      "loss": 0.4885,
+      "step": 60
+    },
+    {
+      "epoch": 1.8607594936708862,
+      "grad_norm": 0.5121936867897753,
+      "learning_rate": 1.8287461240141217e-05,
+      "loss": 0.4367,
+      "step": 61
+    },
+    {
+      "epoch": 1.891139240506329,
+      "grad_norm": 0.5500363533706862,
+      "learning_rate": 1.8198984236734246e-05,
+      "loss": 0.4405,
+      "step": 62
+    },
+    {
+      "epoch": 1.9215189873417722,
+      "grad_norm": 0.5172272256314452,
+      "learning_rate": 1.8108504335290852e-05,
+      "loss": 0.4269,
+      "step": 63
+    },
+    {
+      "epoch": 1.9518987341772152,
+      "grad_norm": 0.5483248813247145,
+      "learning_rate": 1.8016043638794975e-05,
+      "loss": 0.4215,
+      "step": 64
+    },
+    {
+      "epoch": 1.9822784810126581,
+      "grad_norm": 0.59195187727915,
+      "learning_rate": 1.7921624734111292e-05,
+      "loss": 0.5136,
+      "step": 65
+    },
+    {
+      "epoch": 2.020253164556962,
+      "grad_norm": 0.6987707813692844,
+      "learning_rate": 1.7825270686467567e-05,
+      "loss": 0.5217,
+      "step": 66
+    },
+    {
+      "epoch": 2.050632911392405,
+      "grad_norm": 0.6335148697025192,
+      "learning_rate": 1.7727005033820117e-05,
+      "loss": 0.3458,
+      "step": 67
+    },
+    {
+      "epoch": 2.081012658227848,
+      "grad_norm": 0.5630324718459703,
+      "learning_rate": 1.762685178110382e-05,
+      "loss": 0.3504,
+      "step": 68
+    },
+    {
+      "epoch": 2.1113924050632913,
+      "grad_norm": 0.8028572217234614,
+      "learning_rate": 1.752483539436807e-05,
+      "loss": 0.3902,
+      "step": 69
+    },
+    {
+      "epoch": 2.141772151898734,
+      "grad_norm": 0.5670381413787162,
+      "learning_rate": 1.7420980794800013e-05,
+      "loss": 0.3084,
+      "step": 70
+    },
+    {
+      "epoch": 2.1721518987341772,
+      "grad_norm": 0.8122168290341552,
+      "learning_rate": 1.731531335263669e-05,
+      "loss": 0.4264,
+      "step": 71
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.4741214258962823,
+      "learning_rate": 1.720785888096743e-05,
+      "loss": 0.3048,
+      "step": 72
+    },
+    {
+      "epoch": 2.232911392405063,
+      "grad_norm": 0.6586253722411579,
+      "learning_rate": 1.7098643629428035e-05,
+      "loss": 0.3685,
+      "step": 73
+    },
+    {
+      "epoch": 2.2632911392405064,
+      "grad_norm": 0.561869536718334,
+      "learning_rate": 1.698769427778842e-05,
+      "loss": 0.3297,
+      "step": 74
+    },
+    {
+      "epoch": 2.293670886075949,
+      "grad_norm": 0.6767692478813152,
+      "learning_rate": 1.687503792943506e-05,
+      "loss": 0.3494,
+      "step": 75
+    },
+    {
+      "epoch": 2.3240506329113924,
+      "grad_norm": 0.5928821569905506,
+      "learning_rate": 1.6760702104750046e-05,
+      "loss": 0.3359,
+      "step": 76
+    },
+    {
+      "epoch": 2.3544303797468356,
+      "grad_norm": 0.8164378937491322,
+      "learning_rate": 1.664471473438822e-05,
+      "loss": 0.3738,
+      "step": 77
+    },
+    {
+      "epoch": 2.3848101265822783,
+      "grad_norm": 0.5572591269430051,
+      "learning_rate": 1.6527104152454096e-05,
+      "loss": 0.3256,
+      "step": 78
+    },
+    {
+      "epoch": 2.4151898734177215,
+      "grad_norm": 0.6300653290697507,
+      "learning_rate": 1.6407899089580263e-05,
+      "loss": 0.3154,
+      "step": 79
+    },
+    {
+      "epoch": 2.4455696202531647,
+      "grad_norm": 0.6162777886076989,
+      "learning_rate": 1.628712866590885e-05,
+      "loss": 0.3466,
+      "step": 80
+    },
+    {
+      "epoch": 2.4759493670886075,
+      "grad_norm": 0.6058053919206401,
+      "learning_rate": 1.6164822383977912e-05,
+      "loss": 0.3428,
+      "step": 81
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 0.560153372409703,
+      "learning_rate": 1.604101012151436e-05,
+      "loss": 0.3096,
+      "step": 82
+    },
+    {
+      "epoch": 2.536708860759494,
+      "grad_norm": 0.6087346002273554,
+      "learning_rate": 1.5915722124135227e-05,
+      "loss": 0.3437,
+      "step": 83
+    },
+    {
+      "epoch": 2.5670886075949366,
+      "grad_norm": 0.4955198786766178,
+      "learning_rate": 1.5788988997959115e-05,
+      "loss": 0.3118,
+      "step": 84
+    },
+    {
+      "epoch": 2.59746835443038,
+      "grad_norm": 0.5789844176944846,
+      "learning_rate": 1.5660841702129533e-05,
+      "loss": 0.3807,
+      "step": 85
+    },
+    {
+      "epoch": 2.6278481012658226,
+      "grad_norm": 0.5309509336643291,
+      "learning_rate": 1.5531311541251995e-05,
+      "loss": 0.3003,
+      "step": 86
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.6719031837507913,
+      "learning_rate": 1.540043015774676e-05,
+      "loss": 0.3883,
+      "step": 87
+    },
+    {
+      "epoch": 2.688607594936709,
+      "grad_norm": 0.5005442690624767,
+      "learning_rate": 1.5268229524119007e-05,
+      "loss": 0.304,
+      "step": 88
+    },
+    {
+      "epoch": 2.7189873417721517,
+      "grad_norm": 0.688837206554437,
+      "learning_rate": 1.513474193514842e-05,
+      "loss": 0.3603,
+      "step": 89
+    },
+    {
+      "epoch": 2.749367088607595,
+      "grad_norm": 0.5394782699862007,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2964,
+      "step": 90
+    },
+    {
+      "epoch": 2.779746835443038,
+      "grad_norm": 0.5148588742942368,
+      "learning_rate": 1.4864036634258112e-05,
+      "loss": 0.3442,
+      "step": 91
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.5817362125441904,
+      "learning_rate": 1.4726885051885654e-05,
+      "loss": 0.3446,
+      "step": 92
+    },
+    {
+      "epoch": 2.840506329113924,
+      "grad_norm": 0.5148990671834646,
+      "learning_rate": 1.4588578757110359e-05,
+      "loss": 0.3397,
+      "step": 93
+    },
+    {
+      "epoch": 2.8708860759493673,
+      "grad_norm": 0.5485534320777181,
+      "learning_rate": 1.4449151536240167e-05,
+      "loss": 0.3069,
+      "step": 94
+    },
+    {
+      "epoch": 2.90126582278481,
+      "grad_norm": 0.5302264458421836,
+      "learning_rate": 1.4308637449409705e-05,
+      "loss": 0.3638,
+      "step": 95
+    },
+    {
+      "epoch": 2.9316455696202532,
+      "grad_norm": 0.49405999684903523,
+      "learning_rate": 1.4167070822259868e-05,
+      "loss": 0.3712,
+      "step": 96
+    },
+    {
+      "epoch": 2.962025316455696,
+      "grad_norm": 0.5096202744829424,
+      "learning_rate": 1.402448623755254e-05,
+      "loss": 0.3542,
+      "step": 97
+    },
+    {
+      "epoch": 2.992405063291139,
+      "grad_norm": 0.5620601845699008,
+      "learning_rate": 1.3880918526722497e-05,
+      "loss": 0.4107,
+      "step": 98
+    },
+    {
+      "epoch": 3.030379746835443,
+      "grad_norm": 0.6845312065128214,
+      "learning_rate": 1.3736402761368597e-05,
+      "loss": 0.2537,
+      "step": 99
+    },
+    {
+      "epoch": 3.060759493670886,
+      "grad_norm": 0.5683322678824294,
+      "learning_rate": 1.3590974244686248e-05,
+      "loss": 0.2451,
+      "step": 100
+    },
+    {
+      "epoch": 3.091139240506329,
+      "grad_norm": 0.5792932670782358,
+      "learning_rate": 1.344466850284333e-05,
+      "loss": 0.2225,
+      "step": 101
+    },
+    {
+      "epoch": 3.1215189873417724,
+      "grad_norm": 0.9628768359244015,
+      "learning_rate": 1.3297521276301666e-05,
+      "loss": 0.2686,
+      "step": 102
+    },
+    {
+      "epoch": 3.151898734177215,
+      "grad_norm": 0.6337138487225528,
+      "learning_rate": 1.3149568511086104e-05,
+      "loss": 0.2613,
+      "step": 103
+    },
+    {
+      "epoch": 3.1822784810126583,
+      "grad_norm": 0.6632556801107956,
+      "learning_rate": 1.300084635000341e-05,
+      "loss": 0.2346,
+      "step": 104
+    },
+    {
+      "epoch": 3.212658227848101,
+      "grad_norm": 0.577840594366836,
+      "learning_rate": 1.2851391123813075e-05,
+      "loss": 0.2366,
+      "step": 105
+    },
+    {
+      "epoch": 3.2430379746835443,
+      "grad_norm": 0.5967042560307922,
+      "learning_rate": 1.2701239342352223e-05,
+      "loss": 0.2357,
+      "step": 106
+    },
+    {
+      "epoch": 3.2734177215189875,
+      "grad_norm": 0.6052889150964138,
+      "learning_rate": 1.2550427685616767e-05,
+      "loss": 0.2537,
+      "step": 107
+    },
+    {
+      "epoch": 3.3037974683544302,
+      "grad_norm": 0.5526256136083812,
+      "learning_rate": 1.239899299480098e-05,
+      "loss": 0.2325,
+      "step": 108
+    },
+    {
+      "epoch": 3.3341772151898734,
+      "grad_norm": 0.5783020114883667,
+      "learning_rate": 1.2246972263297718e-05,
+      "loss": 0.2302,
+      "step": 109
+    },
+    {
+      "epoch": 3.3645569620253166,
+      "grad_norm": 0.5151150904654107,
+      "learning_rate": 1.2094402627661447e-05,
+      "loss": 0.2379,
+      "step": 110
+    },
+    {
+      "epoch": 3.3949367088607594,
+      "grad_norm": 0.5840124872421842,
+      "learning_rate": 1.1941321358536278e-05,
+      "loss": 0.2196,
+      "step": 111
+    },
+    {
+      "epoch": 3.4253164556962026,
+      "grad_norm": 0.5575638981914616,
+      "learning_rate": 1.1787765851551296e-05,
+      "loss": 0.2417,
+      "step": 112
+    },
+    {
+      "epoch": 3.4556962025316453,
+      "grad_norm": 0.5676673745339996,
+      "learning_rate": 1.1633773618185302e-05,
+      "loss": 0.2462,
+      "step": 113
+    },
+    {
+      "epoch": 3.4860759493670885,
+      "grad_norm": 0.5488291523193319,
+      "learning_rate": 1.14793822766033e-05,
+      "loss": 0.2291,
+      "step": 114
+    },
+    {
+      "epoch": 3.5164556962025317,
+      "grad_norm": 0.5704098450792927,
+      "learning_rate": 1.132462954246688e-05,
+      "loss": 0.2374,
+      "step": 115
+    },
+    {
+      "epoch": 3.546835443037975,
+      "grad_norm": 0.4867272584844033,
+      "learning_rate": 1.1169553219720828e-05,
+      "loss": 0.2376,
+      "step": 116
+    },
+    {
+      "epoch": 3.5772151898734177,
+      "grad_norm": 0.5529530918394492,
+      "learning_rate": 1.1014191191358118e-05,
+      "loss": 0.242,
+      "step": 117
+    },
+    {
+      "epoch": 3.607594936708861,
+      "grad_norm": 0.5192190664599996,
+      "learning_rate": 1.085858141016566e-05,
+      "loss": 0.2476,
+      "step": 118
+    },
+    {
+      "epoch": 3.6379746835443036,
+      "grad_norm": 0.45987096851195997,
+      "learning_rate": 1.070276188945293e-05,
+      "loss": 0.2364,
+      "step": 119
+    },
+    {
+      "epoch": 3.668354430379747,
+      "grad_norm": 0.4956300338006397,
+      "learning_rate": 1.0546770693765859e-05,
+      "loss": 0.2354,
+      "step": 120
+    },
+    {
+      "epoch": 3.69873417721519,
+      "grad_norm": 0.5040046760144843,
+      "learning_rate": 1.0390645929588197e-05,
+      "loss": 0.2284,
+      "step": 121
+    },
+    {
+      "epoch": 3.729113924050633,
+      "grad_norm": 0.48330329822327217,
+      "learning_rate": 1.0234425736032607e-05,
+      "loss": 0.2413,
+      "step": 122
+    },
+    {
+      "epoch": 3.759493670886076,
+      "grad_norm": 0.45658137067510934,
+      "learning_rate": 1.007814827552384e-05,
+      "loss": 0.2467,
+      "step": 123
+    },
+    {
+      "epoch": 3.7898734177215188,
+      "grad_norm": 0.4734591767237467,
+      "learning_rate": 9.92185172447616e-06,
+      "loss": 0.213,
+      "step": 124
+    },
+    {
+      "epoch": 3.820253164556962,
+      "grad_norm": 0.505360568959351,
+      "learning_rate": 9.765574263967397e-06,
+      "loss": 0.244,
+      "step": 125
+    },
+    {
+      "epoch": 3.850632911392405,
+      "grad_norm": 0.42730450106912954,
+      "learning_rate": 9.609354070411807e-06,
+      "loss": 0.2324,
+      "step": 126
+    },
+    {
+      "epoch": 3.8810126582278484,
+      "grad_norm": 0.44477229642302935,
+      "learning_rate": 9.453229306234143e-06,
+      "loss": 0.2338,
+      "step": 127
+    },
+    {
+      "epoch": 3.911392405063291,
+      "grad_norm": 0.5032262389671527,
+      "learning_rate": 9.297238110547075e-06,
+      "loss": 0.2551,
+      "step": 128
+    },
+    {
+      "epoch": 3.9417721518987343,
+      "grad_norm": 0.4353746960923058,
+      "learning_rate": 9.14141858983434e-06,
+      "loss": 0.2134,
+      "step": 129
+    },
+    {
+      "epoch": 3.972151898734177,
+      "grad_norm": 0.4647540232924408,
+      "learning_rate": 8.985808808641883e-06,
+      "loss": 0.2247,
+      "step": 130
+    },
+    {
+      "epoch": 4.010126582278481,
+      "grad_norm": 0.6339386720042828,
+      "learning_rate": 8.830446780279175e-06,
+      "loss": 0.3163,
+      "step": 131
+    },
+    {
+      "epoch": 4.040506329113924,
+      "grad_norm": 0.6530531217301823,
+      "learning_rate": 8.675370457533122e-06,
+      "loss": 0.2007,
+      "step": 132
+    },
+    {
+      "epoch": 4.0708860759493675,
+      "grad_norm": 0.43875095031695605,
+      "learning_rate": 8.520617723396702e-06,
+      "loss": 0.1541,
+      "step": 133
+    },
+    {
+      "epoch": 4.10126582278481,
+      "grad_norm": 0.5625986310025605,
+      "learning_rate": 8.366226381814698e-06,
+      "loss": 0.1569,
+      "step": 134
+    },
+    {
+      "epoch": 4.131645569620253,
+      "grad_norm": 0.758344673638472,
+      "learning_rate": 8.212234148448708e-06,
+      "loss": 0.1675,
+      "step": 135
+    },
+    {
+      "epoch": 4.162025316455696,
+      "grad_norm": 0.5742624637188126,
+      "learning_rate": 8.058678641463724e-06,
+      "loss": 0.1713,
+      "step": 136
+    },
+    {
+      "epoch": 4.192405063291139,
+      "grad_norm": 0.47306195670055207,
+      "learning_rate": 7.905597372338558e-06,
+      "loss": 0.1529,
+      "step": 137
+    },
+    {
+      "epoch": 4.222784810126583,
+      "grad_norm": 0.5082834459351141,
+      "learning_rate": 7.753027736702283e-06,
+      "loss": 0.1629,
+      "step": 138
+    },
+    {
+      "epoch": 4.253164556962025,
+      "grad_norm": 0.5149170887831235,
+      "learning_rate": 7.601007005199022e-06,
+      "loss": 0.1496,
+      "step": 139
+    },
+    {
+      "epoch": 4.283544303797468,
+      "grad_norm": 0.5396696154356401,
+      "learning_rate": 7.449572314383237e-06,
+      "loss": 0.147,
+      "step": 140
+    },
+    {
+      "epoch": 4.313924050632911,
+      "grad_norm": 0.4639127622235571,
+      "learning_rate": 7.298760657647779e-06,
+      "loss": 0.1713,
+      "step": 141
+    },
+    {
+      "epoch": 4.3443037974683545,
+      "grad_norm": 0.4642291200280393,
+      "learning_rate": 7.148608876186931e-06,
+      "loss": 0.1422,
+      "step": 142
+    },
+    {
+      "epoch": 4.374683544303798,
+      "grad_norm": 0.5277818211438168,
+      "learning_rate": 6.999153649996595e-06,
+      "loss": 0.1547,
+      "step": 143
+    },
+    {
+      "epoch": 4.405063291139241,
+      "grad_norm": 0.5011866251927994,
+      "learning_rate": 6.8504314889138956e-06,
+      "loss": 0.163,
+      "step": 144
+    },
+    {
+      "epoch": 4.435443037974683,
+      "grad_norm": 0.42343022420856047,
+      "learning_rate": 6.702478723698336e-06,
+      "loss": 0.1362,
+      "step": 145
+    },
+    {
+      "epoch": 4.465822784810126,
+      "grad_norm": 0.4787131077725175,
+      "learning_rate": 6.555331497156671e-06,
+      "loss": 0.1605,
+      "step": 146
+    },
+    {
+      "epoch": 4.49620253164557,
+      "grad_norm": 0.46626711693552353,
+      "learning_rate": 6.4090257553137566e-06,
+      "loss": 0.1657,
+      "step": 147
+    },
+    {
+      "epoch": 4.526582278481013,
+      "grad_norm": 0.4198237310944781,
+      "learning_rate": 6.263597238631405e-06,
+      "loss": 0.1417,
+      "step": 148
+    },
+    {
+      "epoch": 4.556962025316456,
+      "grad_norm": 0.4538075285568228,
+      "learning_rate": 6.119081473277502e-06,
+      "loss": 0.1598,
+      "step": 149
+    },
+    {
+      "epoch": 4.587341772151898,
+      "grad_norm": 0.4496647677446296,
+      "learning_rate": 5.975513762447465e-06,
+      "loss": 0.1659,
+      "step": 150
+    },
+    {
+      "epoch": 4.6177215189873415,
+      "grad_norm": 0.37645967832153626,
+      "learning_rate": 5.832929177740134e-06,
+      "loss": 0.1232,
+      "step": 151
+    },
+    {
+      "epoch": 4.648101265822785,
+      "grad_norm": 0.4483913968217151,
+      "learning_rate": 5.6913625505902966e-06,
+      "loss": 0.1407,
+      "step": 152
+    },
+    {
+      "epoch": 4.678481012658228,
+      "grad_norm": 0.48675690589639076,
+      "learning_rate": 5.550848463759835e-06,
+      "loss": 0.188,
+      "step": 153
+    },
+    {
+      "epoch": 4.708860759493671,
+      "grad_norm": 0.40360767268137376,
+      "learning_rate": 5.411421242889643e-06,
+      "loss": 0.139,
+      "step": 154
+    },
+    {
+      "epoch": 4.739240506329114,
+      "grad_norm": 0.41779812899318686,
+      "learning_rate": 5.273114948114346e-06,
+      "loss": 0.1642,
+      "step": 155
+    },
+    {
+      "epoch": 4.769620253164557,
+      "grad_norm": 0.3961846709703568,
+      "learning_rate": 5.135963365741892e-06,
+      "loss": 0.1471,
+      "step": 156
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.40133842476598025,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.1367,
+      "step": 157
+    },
+    {
+      "epoch": 4.830379746835443,
+      "grad_norm": 0.43745906466801676,
+      "learning_rate": 4.865258064851579e-06,
+      "loss": 0.1452,
+      "step": 158
+    },
+    {
+      "epoch": 4.860759493670886,
+      "grad_norm": 0.41254691993311743,
+      "learning_rate": 4.731770475880995e-06,
+      "loss": 0.1428,
+      "step": 159
+    },
+    {
+      "epoch": 4.891139240506329,
+      "grad_norm": 0.3992517987662612,
+      "learning_rate": 4.599569842253244e-06,
+      "loss": 0.1564,
+      "step": 160
+    },
+    {
+      "epoch": 4.921518987341772,
+      "grad_norm": 0.42501443450592047,
+      "learning_rate": 4.468688458748006e-06,
+      "loss": 0.1586,
+      "step": 161
+    },
+    {
+      "epoch": 4.951898734177215,
+      "grad_norm": 0.421487348641718,
+      "learning_rate": 4.339158297870469e-06,
+      "loss": 0.1401,
+      "step": 162
+    },
+    {
+      "epoch": 4.982278481012658,
+      "grad_norm": 0.48888887508046985,
+      "learning_rate": 4.211011002040885e-06,
+      "loss": 0.1777,
+      "step": 163
+    },
+    {
+      "epoch": 5.020253164556962,
+      "grad_norm": 0.532368006164555,
+      "learning_rate": 4.084277875864776e-06,
+      "loss": 0.1548,
+      "step": 164
+    },
+    {
+      "epoch": 5.050632911392405,
+      "grad_norm": 0.5126184772174526,
+      "learning_rate": 3.958989878485644e-06,
+      "loss": 0.1256,
+      "step": 165
+    },
+    {
+      "epoch": 5.0810126582278485,
+      "grad_norm": 0.42535194636650964,
+      "learning_rate": 3.83517761602209e-06,
+      "loss": 0.0947,
+      "step": 166
+    },
+    {
+      "epoch": 5.111392405063291,
+      "grad_norm": 0.3771851719739927,
+      "learning_rate": 3.712871334091154e-06,
+      "loss": 0.0933,
+      "step": 167
+    },
+    {
+      "epoch": 5.141772151898734,
+      "grad_norm": 0.45196639950573986,
+      "learning_rate": 3.592100910419738e-06,
+      "loss": 0.122,
+      "step": 168
+    },
+    {
+      "epoch": 5.172151898734177,
+      "grad_norm": 0.45157600306964624,
+      "learning_rate": 3.4728958475459052e-06,
+      "loss": 0.0971,
+      "step": 169
+    },
+    {
+      "epoch": 5.2025316455696204,
+      "grad_norm": 0.5169697816786871,
+      "learning_rate": 3.355285265611784e-06,
+      "loss": 0.1095,
+      "step": 170
+    },
+    {
+      "epoch": 5.232911392405064,
+      "grad_norm": 0.5431066086388939,
+      "learning_rate": 3.2392978952499553e-06,
+      "loss": 0.113,
+      "step": 171
+    },
+    {
+      "epoch": 5.263291139240506,
+      "grad_norm": 0.4731235647267685,
+      "learning_rate": 3.1249620705649417e-06,
+      "loss": 0.1125,
+      "step": 172
+    },
+    {
+      "epoch": 5.293670886075949,
+      "grad_norm": 0.38763624259915713,
+      "learning_rate": 3.0123057222115835e-06,
+      "loss": 0.1058,
+      "step": 173
+    },
+    {
+      "epoch": 5.324050632911392,
+      "grad_norm": 0.38932153933623975,
+      "learning_rate": 2.9013563705719673e-06,
+      "loss": 0.0954,
+      "step": 174
+    },
+    {
+      "epoch": 5.3544303797468356,
+      "grad_norm": 0.3958162438015379,
+      "learning_rate": 2.7921411190325753e-06,
+      "loss": 0.106,
+      "step": 175
+    },
+    {
+      "epoch": 5.384810126582279,
+      "grad_norm": 0.37217291947862674,
+      "learning_rate": 2.6846866473633126e-06,
+      "loss": 0.0931,
+      "step": 176
+    },
+    {
+      "epoch": 5.415189873417722,
+      "grad_norm": 0.3789283664630874,
+      "learning_rate": 2.579019205199992e-06,
+      "loss": 0.0908,
+      "step": 177
+    },
+    {
+      "epoch": 5.445569620253164,
+      "grad_norm": 0.3664134539407824,
+      "learning_rate": 2.4751646056319334e-06,
+      "loss": 0.1057,
+      "step": 178
+    },
+    {
+      "epoch": 5.4759493670886075,
+      "grad_norm": 0.35771266382078304,
+      "learning_rate": 2.373148218896182e-06,
+      "loss": 0.0986,
+      "step": 179
+    },
+    {
+      "epoch": 5.506329113924051,
+      "grad_norm": 0.3472703082619096,
+      "learning_rate": 2.2729949661798876e-06,
+      "loss": 0.0877,
+      "step": 180
+    },
+    {
+      "epoch": 5.536708860759494,
+      "grad_norm": 0.3515962152406197,
+      "learning_rate": 2.174729313532433e-06,
+      "loss": 0.099,
+      "step": 181
+    },
+    {
+      "epoch": 5.567088607594937,
+      "grad_norm": 0.34854961186427696,
+      "learning_rate": 2.078375265888707e-06,
+      "loss": 0.0958,
+      "step": 182
+    },
+    {
+      "epoch": 5.597468354430379,
+      "grad_norm": 0.40154731325881876,
+      "learning_rate": 1.9839563612050273e-06,
+      "loss": 0.1123,
+      "step": 183
+    },
+    {
+      "epoch": 5.627848101265823,
+      "grad_norm": 0.36183221654182146,
+      "learning_rate": 1.8914956647091497e-06,
+      "loss": 0.0934,
+      "step": 184
+    },
+    {
+      "epoch": 5.658227848101266,
+      "grad_norm": 0.4295934552136442,
+      "learning_rate": 1.8010157632657544e-06,
+      "loss": 0.1252,
+      "step": 185
+    },
+    {
+      "epoch": 5.688607594936709,
+      "grad_norm": 0.32970138402708415,
+      "learning_rate": 1.7125387598587862e-06,
+      "loss": 0.0801,
+      "step": 186
+    },
+    {
+      "epoch": 5.718987341772152,
+      "grad_norm": 0.3695821342065737,
+      "learning_rate": 1.6260862681919965e-06,
+      "loss": 0.0998,
+      "step": 187
+    },
+    {
+      "epoch": 5.749367088607595,
+      "grad_norm": 0.3672619778582091,
+      "learning_rate": 1.5416794074090258e-06,
+      "loss": 0.1002,
+      "step": 188
+    },
+    {
+      "epoch": 5.779746835443038,
+      "grad_norm": 0.41056065686731014,
+      "learning_rate": 1.459338796934293e-06,
+      "loss": 0.1115,
+      "step": 189
+    },
+    {
+      "epoch": 5.810126582278481,
+      "grad_norm": 0.35028287274755804,
+      "learning_rate": 1.3790845514359363e-06,
+      "loss": 0.0986,
+      "step": 190
+    },
+    {
+      "epoch": 5.840506329113924,
+      "grad_norm": 0.35138499534126416,
+      "learning_rate": 1.300936275912098e-06,
+      "loss": 0.108,
+      "step": 191
+    },
+    {
+      "epoch": 5.870886075949367,
+      "grad_norm": 0.3464988655002844,
+      "learning_rate": 1.224913060901688e-06,
+      "loss": 0.0913,
+      "step": 192
+    },
+    {
+      "epoch": 5.9012658227848105,
+      "grad_norm": 0.36519734216811445,
+      "learning_rate": 1.1510334778208332e-06,
+      "loss": 0.1042,
+      "step": 193
+    },
+    {
+      "epoch": 5.931645569620253,
+      "grad_norm": 0.33907718375369833,
+      "learning_rate": 1.0793155744261352e-06,
+      "loss": 0.1083,
+      "step": 194
+    },
+    {
+      "epoch": 5.962025316455696,
+      "grad_norm": 0.3385410561678952,
+      "learning_rate": 1.0097768704058542e-06,
+      "loss": 0.1117,
+      "step": 195
+    },
+    {
+      "epoch": 5.992405063291139,
+      "grad_norm": 0.4671555068109887,
+      "learning_rate": 9.424343531000968e-07,
+      "loss": 0.1091,
+      "step": 196
+    },
+    {
+      "epoch": 6.030379746835443,
+      "grad_norm": 0.41214886246914095,
+      "learning_rate": 8.773044733510338e-07,
+      "loss": 0.0816,
+      "step": 197
+    },
+    {
+      "epoch": 6.060759493670886,
+      "grad_norm": 0.39539527834164195,
+      "learning_rate": 8.144031414842012e-07,
+      "loss": 0.0799,
+      "step": 198
+    },
+    {
+      "epoch": 6.091139240506329,
+      "grad_norm": 0.36386501874919946,
+      "learning_rate": 7.537457234218271e-07,
+      "loss": 0.0739,
+      "step": 199
+    },
+    {
+      "epoch": 6.121518987341772,
+      "grad_norm": 0.31706993387029775,
+      "learning_rate": 6.953470369291349e-07,
+      "loss": 0.0758,
+      "step": 200
+    },
+    {
+      "epoch": 6.151898734177215,
+      "grad_norm": 0.34669274298668185,
+      "learning_rate": 6.392213479945852e-07,
+      "loss": 0.0949,
+      "step": 201
+    },
+    {
+      "epoch": 6.182278481012658,
+      "grad_norm": 0.31834158848784283,
+      "learning_rate": 5.853823673448877e-07,
+      "loss": 0.0876,
+      "step": 202
+    },
+    {
+      "epoch": 6.2126582278481015,
+      "grad_norm": 0.29201858105248085,
+      "learning_rate": 5.33843247095659e-07,
+      "loss": 0.087,
+      "step": 203
+    },
+    {
+      "epoch": 6.243037974683545,
+      "grad_norm": 0.32292934350297237,
+      "learning_rate": 4.846165775385459e-07,
+      "loss": 0.0895,
+      "step": 204
+    },
+    {
+      "epoch": 6.273417721518987,
+      "grad_norm": 0.28146694255115595,
+      "learning_rate": 4.3771438406559173e-07,
+      "loss": 0.0889,
+      "step": 205
+    },
+    {
+      "epoch": 6.30379746835443,
+      "grad_norm": 0.2900228526044847,
+      "learning_rate": 3.931481242315993e-07,
+      "loss": 0.0703,
+      "step": 206
+    },
+    {
+      "epoch": 6.334177215189873,
+      "grad_norm": 0.2920659823821498,
+      "learning_rate": 3.5092868495520294e-07,
+      "loss": 0.0796,
+      "step": 207
+    },
+    {
+      "epoch": 6.364556962025317,
+      "grad_norm": 0.35055198081769356,
+      "learning_rate": 3.110663798593616e-07,
+      "loss": 0.0968,
+      "step": 208
+    },
+    {
+      "epoch": 6.39493670886076,
+      "grad_norm": 0.3152896231902338,
+      "learning_rate": 2.735709467518699e-07,
+      "loss": 0.0825,
+      "step": 209
+    },
+    {
+      "epoch": 6.425316455696202,
+      "grad_norm": 0.31340595951494493,
+      "learning_rate": 2.384515452465475e-07,
+      "loss": 0.0887,
+      "step": 210
+    },
+    {
+      "epoch": 6.455696202531645,
+      "grad_norm": 0.3060587528938938,
+      "learning_rate": 2.0571675452567997e-07,
+      "loss": 0.0764,
+      "step": 211
+    },
+    {
+      "epoch": 6.4860759493670885,
+      "grad_norm": 0.31527091622895953,
+      "learning_rate": 1.7537457124423896e-07,
+      "loss": 0.0887,
+      "step": 212
+    },
+    {
+      "epoch": 6.516455696202532,
+      "grad_norm": 0.3202497921531981,
+      "learning_rate": 1.474324075764111e-07,
+      "loss": 0.0806,
+      "step": 213
+    },
+    {
+      "epoch": 6.546835443037975,
+      "grad_norm": 0.34033534010942323,
+      "learning_rate": 1.2189708940490653e-07,
+      "loss": 0.0864,
+      "step": 214
+    },
+    {
+      "epoch": 6.577215189873417,
+      "grad_norm": 0.31351196332151854,
+      "learning_rate": 9.877485465349057e-08,
+      "loss": 0.0867,
+      "step": 215
+    },
+    {
+      "epoch": 6.6075949367088604,
+      "grad_norm": 0.3245746897018996,
+      "learning_rate": 7.807135176314707e-08,
+      "loss": 0.0833,
+      "step": 216
+    },
+    {
+      "epoch": 6.637974683544304,
+      "grad_norm": 0.3159564900300316,
+      "learning_rate": 5.979163831223988e-08,
+      "loss": 0.0833,
+      "step": 217
+    },
+    {
+      "epoch": 6.668354430379747,
+      "grad_norm": 0.2692316727079578,
+      "learning_rate": 4.394017978101905e-08,
+      "loss": 0.073,
+      "step": 218
+    },
+    {
+      "epoch": 6.69873417721519,
+      "grad_norm": 0.3240983350991465,
+      "learning_rate": 3.0520848460765525e-08,
+      "loss": 0.0851,
+      "step": 219
+    },
+    {
+      "epoch": 6.729113924050633,
+      "grad_norm": 0.3080977226597638,
+      "learning_rate": 1.9536922507841227e-08,
+      "loss": 0.0793,
+      "step": 220
+    },
+    {
+      "epoch": 6.759493670886076,
+      "grad_norm": 0.2963952964292608,
+      "learning_rate": 1.099108514288627e-08,
+      "loss": 0.0734,
+      "step": 221
+    },
+    {
+      "epoch": 6.789873417721519,
+      "grad_norm": 0.3343021300081363,
+      "learning_rate": 4.885423995341088e-09,
+      "loss": 0.0939,
+      "step": 222
+    },
+    {
+      "epoch": 6.820253164556962,
+      "grad_norm": 0.3065995855334038,
+      "learning_rate": 1.2214305934699078e-09,
+      "loss": 0.0796,
+      "step": 223
+    },
+    {
+      "epoch": 6.850632911392405,
+      "grad_norm": 0.31520626619705966,
+      "learning_rate": 0.0,
+      "loss": 0.0811,
+      "step": 224
+    },
+    {
+      "epoch": 6.850632911392405,
+      "step": 224,
+      "total_flos": 2.86943794002133e+17,
+      "train_loss": 0.2993284181159522,
+      "train_runtime": 12424.2407,
+      "train_samples_per_second": 1.78,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "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": 2.86943794002133e+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:f0cd23a4aa9dc56874676a3ff18dfc2bf33a4ff1d6feacc9b1ddbd210e15c6c7
+size 7352