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: d1_science_gpt_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. -->
+
+# d1_science_gpt_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/d1_science_gpt_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: 16
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 96
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 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": 7.0,
+    "total_flos": 2.7774205071405875e+17,
+    "train_loss": 0.363200804404108,
+    "train_runtime": 5432.6588,
+    "train_samples_per_second": 4.072,
+    "train_steps_per_second": 0.043
+}

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:e4f202899c294740bda6541b8e6256dacfccffebdb508b2d02a4d1f117dfc4b0
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9ed23582d8faf49da4f1522a68edd8de544d9682cf851913362ebbe647a567
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb3d400e515802b8eb65091cc6eccf72ec982a7d0f9d43fa8cacccf7182cc9e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a493a02f6ba9d923ac7127fa7cee74db6b5a114342cec375eaf4f46fd5f78576
+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/Apr28_06-39-44_jpbot-001-43.jupiter.internal/events.out.tfevents.1745815237.jpbot-001-43.jupiter.internal.3489130.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5b9037d432e18d72ae2b290040689580fc6f5ca9af22d30debd96fd055e841
+size 54105

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": "2025-04-28 06:39:44", "end_time": "2025-04-28 08:11:17"}

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": 7.0,
+    "total_flos": 2.7774205071405875e+17,
+    "train_loss": 0.363200804404108,
+    "train_runtime": 5432.6588,
+    "train_samples_per_second": 4.072,
+    "train_steps_per_second": 0.043
+}

trainer_log.jsonl

@@ -0,0 +1,232 @@
+{"current_steps": 1, "total_steps": 231, "loss": 0.9743, "lr": 8.333333333333333e-07, "epoch": 0.030303030303030304, "percentage": 0.43, "elapsed_time": "0:00:31", "remaining_time": "1:59:42"}
+{"current_steps": 2, "total_steps": 231, "loss": 0.9824, "lr": 1.6666666666666667e-06, "epoch": 0.06060606060606061, "percentage": 0.87, "elapsed_time": "0:00:56", "remaining_time": "1:47:45"}
+{"current_steps": 3, "total_steps": 231, "loss": 0.9484, "lr": 2.5e-06, "epoch": 0.09090909090909091, "percentage": 1.3, "elapsed_time": "0:01:19", "remaining_time": "1:40:58"}
+{"current_steps": 4, "total_steps": 231, "loss": 0.9593, "lr": 3.3333333333333333e-06, "epoch": 0.12121212121212122, "percentage": 1.73, "elapsed_time": "0:01:45", "remaining_time": "1:39:41"}
+{"current_steps": 5, "total_steps": 231, "loss": 0.9806, "lr": 4.166666666666667e-06, "epoch": 0.15151515151515152, "percentage": 2.16, "elapsed_time": "0:02:10", "remaining_time": "1:38:12"}
+{"current_steps": 6, "total_steps": 231, "loss": 0.8577, "lr": 5e-06, "epoch": 0.18181818181818182, "percentage": 2.6, "elapsed_time": "0:02:33", "remaining_time": "1:36:02"}
+{"current_steps": 7, "total_steps": 231, "loss": 0.9069, "lr": 5.833333333333334e-06, "epoch": 0.21212121212121213, "percentage": 3.03, "elapsed_time": "0:02:52", "remaining_time": "1:31:56"}
+{"current_steps": 8, "total_steps": 231, "loss": 0.8973, "lr": 6.666666666666667e-06, "epoch": 0.24242424242424243, "percentage": 3.46, "elapsed_time": "0:03:18", "remaining_time": "1:32:19"}
+{"current_steps": 9, "total_steps": 231, "loss": 0.8624, "lr": 7.500000000000001e-06, "epoch": 0.2727272727272727, "percentage": 3.9, "elapsed_time": "0:03:45", "remaining_time": "1:32:54"}
+{"current_steps": 10, "total_steps": 231, "loss": 0.8693, "lr": 8.333333333333334e-06, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "0:04:07", "remaining_time": "1:31:15"}
+{"current_steps": 11, "total_steps": 231, "loss": 0.8402, "lr": 9.166666666666666e-06, "epoch": 0.3333333333333333, "percentage": 4.76, "elapsed_time": "0:04:30", "remaining_time": "1:30:04"}
+{"current_steps": 12, "total_steps": 231, "loss": 0.8399, "lr": 1e-05, "epoch": 0.36363636363636365, "percentage": 5.19, "elapsed_time": "0:04:57", "remaining_time": "1:30:25"}
+{"current_steps": 13, "total_steps": 231, "loss": 0.8324, "lr": 1.0833333333333334e-05, "epoch": 0.3939393939393939, "percentage": 5.63, "elapsed_time": "0:05:20", "remaining_time": "1:29:32"}
+{"current_steps": 14, "total_steps": 231, "loss": 0.7438, "lr": 1.1666666666666668e-05, "epoch": 0.42424242424242425, "percentage": 6.06, "elapsed_time": "0:05:40", "remaining_time": "1:27:59"}
+{"current_steps": 15, "total_steps": 231, "loss": 0.7935, "lr": 1.25e-05, "epoch": 0.45454545454545453, "percentage": 6.49, "elapsed_time": "0:06:04", "remaining_time": "1:27:30"}
+{"current_steps": 16, "total_steps": 231, "loss": 0.7764, "lr": 1.3333333333333333e-05, "epoch": 0.48484848484848486, "percentage": 6.93, "elapsed_time": "0:06:24", "remaining_time": "1:26:01"}
+{"current_steps": 17, "total_steps": 231, "loss": 0.7612, "lr": 1.416666666666667e-05, "epoch": 0.5151515151515151, "percentage": 7.36, "elapsed_time": "0:06:44", "remaining_time": "1:24:52"}
+{"current_steps": 18, "total_steps": 231, "loss": 0.7319, "lr": 1.5000000000000002e-05, "epoch": 0.5454545454545454, "percentage": 7.79, "elapsed_time": "0:07:07", "remaining_time": "1:24:21"}
+{"current_steps": 19, "total_steps": 231, "loss": 0.7525, "lr": 1.5833333333333333e-05, "epoch": 0.5757575757575758, "percentage": 8.23, "elapsed_time": "0:07:29", "remaining_time": "1:23:40"}
+{"current_steps": 20, "total_steps": 231, "loss": 0.7351, "lr": 1.6666666666666667e-05, "epoch": 0.6060606060606061, "percentage": 8.66, "elapsed_time": "0:07:57", "remaining_time": "1:24:00"}
+{"current_steps": 21, "total_steps": 231, "loss": 0.7023, "lr": 1.7500000000000002e-05, "epoch": 0.6363636363636364, "percentage": 9.09, "elapsed_time": "0:08:21", "remaining_time": "1:23:32"}
+{"current_steps": 22, "total_steps": 231, "loss": 0.7288, "lr": 1.8333333333333333e-05, "epoch": 0.6666666666666666, "percentage": 9.52, "elapsed_time": "0:08:44", "remaining_time": "1:22:59"}
+{"current_steps": 23, "total_steps": 231, "loss": 0.6977, "lr": 1.916666666666667e-05, "epoch": 0.696969696969697, "percentage": 9.96, "elapsed_time": "0:09:12", "remaining_time": "1:23:19"}
+{"current_steps": 24, "total_steps": 231, "loss": 0.6841, "lr": 2e-05, "epoch": 0.7272727272727273, "percentage": 10.39, "elapsed_time": "0:09:35", "remaining_time": "1:22:39"}
+{"current_steps": 25, "total_steps": 231, "loss": 0.708, "lr": 1.999884834944106e-05, "epoch": 0.7575757575757576, "percentage": 10.82, "elapsed_time": "0:09:55", "remaining_time": "1:21:49"}
+{"current_steps": 26, "total_steps": 231, "loss": 0.6761, "lr": 1.9995393663024054e-05, "epoch": 0.7878787878787878, "percentage": 11.26, "elapsed_time": "0:10:20", "remaining_time": "1:21:29"}
+{"current_steps": 27, "total_steps": 231, "loss": 0.6682, "lr": 1.9989636736467278e-05, "epoch": 0.8181818181818182, "percentage": 11.69, "elapsed_time": "0:10:42", "remaining_time": "1:20:56"}
+{"current_steps": 28, "total_steps": 231, "loss": 0.6939, "lr": 1.9981578895764272e-05, "epoch": 0.8484848484848485, "percentage": 12.12, "elapsed_time": "0:11:07", "remaining_time": "1:20:36"}
+{"current_steps": 29, "total_steps": 231, "loss": 0.6689, "lr": 1.9971221996878395e-05, "epoch": 0.8787878787878788, "percentage": 12.55, "elapsed_time": "0:11:34", "remaining_time": "1:20:36"}
+{"current_steps": 30, "total_steps": 231, "loss": 0.6889, "lr": 1.9958568425315316e-05, "epoch": 0.9090909090909091, "percentage": 12.99, "elapsed_time": "0:11:54", "remaining_time": "1:19:44"}
+{"current_steps": 31, "total_steps": 231, "loss": 0.6756, "lr": 1.9943621095573588e-05, "epoch": 0.9393939393939394, "percentage": 13.42, "elapsed_time": "0:12:18", "remaining_time": "1:19:27"}
+{"current_steps": 32, "total_steps": 231, "loss": 0.6801, "lr": 1.9926383450473344e-05, "epoch": 0.9696969696969697, "percentage": 13.85, "elapsed_time": "0:12:43", "remaining_time": "1:19:05"}
+{"current_steps": 33, "total_steps": 231, "loss": 0.6359, "lr": 1.9906859460363307e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:13:05", "remaining_time": "1:18:35"}
+{"current_steps": 34, "total_steps": 231, "loss": 0.664, "lr": 1.9885053622206305e-05, "epoch": 1.0303030303030303, "percentage": 14.72, "elapsed_time": "0:13:50", "remaining_time": "1:20:10"}
+{"current_steps": 35, "total_steps": 231, "loss": 0.5904, "lr": 1.986097095854347e-05, "epoch": 1.0606060606060606, "percentage": 15.15, "elapsed_time": "0:14:15", "remaining_time": "1:19:52"}
+{"current_steps": 36, "total_steps": 231, "loss": 0.6009, "lr": 1.9834617016337424e-05, "epoch": 1.0909090909090908, "percentage": 15.58, "elapsed_time": "0:14:41", "remaining_time": "1:19:37"}
+{"current_steps": 37, "total_steps": 231, "loss": 0.5919, "lr": 1.9805997865694616e-05, "epoch": 1.121212121212121, "percentage": 16.02, "elapsed_time": "0:15:03", "remaining_time": "1:18:56"}
+{"current_steps": 38, "total_steps": 231, "loss": 0.5933, "lr": 1.9775120098467212e-05, "epoch": 1.1515151515151516, "percentage": 16.45, "elapsed_time": "0:15:28", "remaining_time": "1:18:36"}
+{"current_steps": 39, "total_steps": 231, "loss": 0.6017, "lr": 1.9741990826734793e-05, "epoch": 1.1818181818181819, "percentage": 16.88, "elapsed_time": "0:15:49", "remaining_time": "1:17:52"}
+{"current_steps": 40, "total_steps": 231, "loss": 0.5851, "lr": 1.970661768116622e-05, "epoch": 1.2121212121212122, "percentage": 17.32, "elapsed_time": "0:16:13", "remaining_time": "1:17:28"}
+{"current_steps": 41, "total_steps": 231, "loss": 0.5649, "lr": 1.9669008809262064e-05, "epoch": 1.2424242424242424, "percentage": 17.75, "elapsed_time": "0:16:40", "remaining_time": "1:17:14"}
+{"current_steps": 42, "total_steps": 231, "loss": 0.5826, "lr": 1.9629172873477995e-05, "epoch": 1.2727272727272727, "percentage": 18.18, "elapsed_time": "0:17:03", "remaining_time": "1:16:44"}
+{"current_steps": 43, "total_steps": 231, "loss": 0.5733, "lr": 1.9587119049229558e-05, "epoch": 1.303030303030303, "percentage": 18.61, "elapsed_time": "0:17:24", "remaining_time": "1:16:07"}
+{"current_steps": 44, "total_steps": 231, "loss": 0.6049, "lr": 1.954285702277879e-05, "epoch": 1.3333333333333333, "percentage": 19.05, "elapsed_time": "0:17:47", "remaining_time": "1:15:37"}
+{"current_steps": 45, "total_steps": 231, "loss": 0.5601, "lr": 1.9496396989003195e-05, "epoch": 1.3636363636363638, "percentage": 19.48, "elapsed_time": "0:18:13", "remaining_time": "1:15:20"}
+{"current_steps": 46, "total_steps": 231, "loss": 0.6024, "lr": 1.944774964904754e-05, "epoch": 1.393939393939394, "percentage": 19.91, "elapsed_time": "0:18:33", "remaining_time": "1:14:39"}
+{"current_steps": 47, "total_steps": 231, "loss": 0.5467, "lr": 1.9396926207859085e-05, "epoch": 1.4242424242424243, "percentage": 20.35, "elapsed_time": "0:18:52", "remaining_time": "1:13:51"}
+{"current_steps": 48, "total_steps": 231, "loss": 0.5808, "lr": 1.9343938371606714e-05, "epoch": 1.4545454545454546, "percentage": 20.78, "elapsed_time": "0:19:10", "remaining_time": "1:13:05"}
+{"current_steps": 49, "total_steps": 231, "loss": 0.5406, "lr": 1.9288798344984673e-05, "epoch": 1.4848484848484849, "percentage": 21.21, "elapsed_time": "0:19:31", "remaining_time": "1:12:29"}
+{"current_steps": 50, "total_steps": 231, "loss": 0.5592, "lr": 1.9231518828401458e-05, "epoch": 1.5151515151515151, "percentage": 21.65, "elapsed_time": "0:19:50", "remaining_time": "1:11:50"}
+{"current_steps": 51, "total_steps": 231, "loss": 0.6109, "lr": 1.917211301505453e-05, "epoch": 1.5454545454545454, "percentage": 22.08, "elapsed_time": "0:20:17", "remaining_time": "1:11:37"}
+{"current_steps": 52, "total_steps": 231, "loss": 0.5306, "lr": 1.911059458789152e-05, "epoch": 1.5757575757575757, "percentage": 22.51, "elapsed_time": "0:20:40", "remaining_time": "1:11:11"}
+{"current_steps": 53, "total_steps": 231, "loss": 0.5892, "lr": 1.9046977716458627e-05, "epoch": 1.606060606060606, "percentage": 22.94, "elapsed_time": "0:21:03", "remaining_time": "1:10:41"}
+{"current_steps": 54, "total_steps": 231, "loss": 0.5784, "lr": 1.8981277053636963e-05, "epoch": 1.6363636363636362, "percentage": 23.38, "elapsed_time": "0:21:26", "remaining_time": "1:10:17"}
+{"current_steps": 55, "total_steps": 231, "loss": 0.5433, "lr": 1.891350773226754e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "0:21:50", "remaining_time": "1:09:52"}
+{"current_steps": 56, "total_steps": 231, "loss": 0.5797, "lr": 1.8843685361665724e-05, "epoch": 1.696969696969697, "percentage": 24.24, "elapsed_time": "0:22:09", "remaining_time": "1:09:15"}
+{"current_steps": 57, "total_steps": 231, "loss": 0.5882, "lr": 1.8771826024025944e-05, "epoch": 1.7272727272727273, "percentage": 24.68, "elapsed_time": "0:22:31", "remaining_time": "1:08:44"}
+{"current_steps": 58, "total_steps": 231, "loss": 0.5888, "lr": 1.8697946270717468e-05, "epoch": 1.7575757575757576, "percentage": 25.11, "elapsed_time": "0:22:59", "remaining_time": "1:08:33"}
+{"current_steps": 59, "total_steps": 231, "loss": 0.5415, "lr": 1.8622063118472135e-05, "epoch": 1.7878787878787878, "percentage": 25.54, "elapsed_time": "0:23:24", "remaining_time": "1:08:14"}
+{"current_steps": 60, "total_steps": 231, "loss": 0.5745, "lr": 1.8544194045464888e-05, "epoch": 1.8181818181818183, "percentage": 25.97, "elapsed_time": "0:23:45", "remaining_time": "1:07:42"}
+{"current_steps": 61, "total_steps": 231, "loss": 0.5236, "lr": 1.8464356987288012e-05, "epoch": 1.8484848484848486, "percentage": 26.41, "elapsed_time": "0:24:10", "remaining_time": "1:07:23"}
+{"current_steps": 62, "total_steps": 231, "loss": 0.5252, "lr": 1.8382570332820045e-05, "epoch": 1.878787878787879, "percentage": 26.84, "elapsed_time": "0:24:33", "remaining_time": "1:06:56"}
+{"current_steps": 63, "total_steps": 231, "loss": 0.5607, "lr": 1.8298852919990254e-05, "epoch": 1.9090909090909092, "percentage": 27.27, "elapsed_time": "0:24:52", "remaining_time": "1:06:20"}
+{"current_steps": 64, "total_steps": 231, "loss": 0.5631, "lr": 1.821322403143969e-05, "epoch": 1.9393939393939394, "percentage": 27.71, "elapsed_time": "0:25:17", "remaining_time": "1:06:00"}
+{"current_steps": 65, "total_steps": 231, "loss": 0.5809, "lr": 1.812570339007983e-05, "epoch": 1.9696969696969697, "percentage": 28.14, "elapsed_time": "0:25:40", "remaining_time": "1:05:34"}
+{"current_steps": 66, "total_steps": 231, "loss": 0.578, "lr": 1.8036311154549783e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "0:26:05", "remaining_time": "1:05:14"}
+{"current_steps": 67, "total_steps": 231, "loss": 0.451, "lr": 1.7945067914573147e-05, "epoch": 2.0303030303030303, "percentage": 29.0, "elapsed_time": "0:26:45", "remaining_time": "1:05:29"}
+{"current_steps": 68, "total_steps": 231, "loss": 0.4404, "lr": 1.7851994686215592e-05, "epoch": 2.0606060606060606, "percentage": 29.44, "elapsed_time": "0:27:08", "remaining_time": "1:05:02"}
+{"current_steps": 69, "total_steps": 231, "loss": 0.4581, "lr": 1.77571129070442e-05, "epoch": 2.090909090909091, "percentage": 29.87, "elapsed_time": "0:27:29", "remaining_time": "1:04:33"}
+{"current_steps": 70, "total_steps": 231, "loss": 0.4509, "lr": 1.766044443118978e-05, "epoch": 2.121212121212121, "percentage": 30.3, "elapsed_time": "0:27:56", "remaining_time": "1:04:14"}
+{"current_steps": 71, "total_steps": 231, "loss": 0.4417, "lr": 1.7562011524313187e-05, "epoch": 2.1515151515151514, "percentage": 30.74, "elapsed_time": "0:28:23", "remaining_time": "1:03:59"}
+{"current_steps": 72, "total_steps": 231, "loss": 0.4315, "lr": 1.7461836858476858e-05, "epoch": 2.1818181818181817, "percentage": 31.17, "elapsed_time": "0:28:48", "remaining_time": "1:03:36"}
+{"current_steps": 73, "total_steps": 231, "loss": 0.4357, "lr": 1.7359943506922775e-05, "epoch": 2.212121212121212, "percentage": 31.6, "elapsed_time": "0:29:07", "remaining_time": "1:03:02"}
+{"current_steps": 74, "total_steps": 231, "loss": 0.4155, "lr": 1.725635493875799e-05, "epoch": 2.242424242424242, "percentage": 32.03, "elapsed_time": "0:29:32", "remaining_time": "1:02:41"}
+{"current_steps": 75, "total_steps": 231, "loss": 0.4294, "lr": 1.7151095013548996e-05, "epoch": 2.2727272727272725, "percentage": 32.47, "elapsed_time": "0:29:59", "remaining_time": "1:02:22"}
+{"current_steps": 76, "total_steps": 231, "loss": 0.4133, "lr": 1.7044187975826126e-05, "epoch": 2.303030303030303, "percentage": 32.9, "elapsed_time": "0:30:22", "remaining_time": "1:01:57"}
+{"current_steps": 77, "total_steps": 231, "loss": 0.4255, "lr": 1.693565844949933e-05, "epoch": 2.3333333333333335, "percentage": 33.33, "elapsed_time": "0:30:46", "remaining_time": "1:01:33"}
+{"current_steps": 78, "total_steps": 231, "loss": 0.438, "lr": 1.6825531432186545e-05, "epoch": 2.3636363636363638, "percentage": 33.77, "elapsed_time": "0:31:04", "remaining_time": "1:00:57"}
+{"current_steps": 79, "total_steps": 231, "loss": 0.398, "lr": 1.671383228945597e-05, "epoch": 2.393939393939394, "percentage": 34.2, "elapsed_time": "0:31:27", "remaining_time": "1:00:32"}
+{"current_steps": 80, "total_steps": 231, "loss": 0.4236, "lr": 1.6600586748983642e-05, "epoch": 2.4242424242424243, "percentage": 34.63, "elapsed_time": "0:31:50", "remaining_time": "1:00:05"}
+{"current_steps": 81, "total_steps": 231, "loss": 0.4369, "lr": 1.648582089462756e-05, "epoch": 2.4545454545454546, "percentage": 35.06, "elapsed_time": "0:32:12", "remaining_time": "0:59:38"}
+{"current_steps": 82, "total_steps": 231, "loss": 0.4092, "lr": 1.6369561160419783e-05, "epoch": 2.484848484848485, "percentage": 35.5, "elapsed_time": "0:32:37", "remaining_time": "0:59:17"}
+{"current_steps": 83, "total_steps": 231, "loss": 0.4197, "lr": 1.625183432447789e-05, "epoch": 2.515151515151515, "percentage": 35.93, "elapsed_time": "0:32:57", "remaining_time": "0:58:46"}
+{"current_steps": 84, "total_steps": 231, "loss": 0.4242, "lr": 1.6132667502837164e-05, "epoch": 2.5454545454545454, "percentage": 36.36, "elapsed_time": "0:33:17", "remaining_time": "0:58:14"}
+{"current_steps": 85, "total_steps": 231, "loss": 0.4235, "lr": 1.6012088143204953e-05, "epoch": 2.5757575757575757, "percentage": 36.8, "elapsed_time": "0:33:39", "remaining_time": "0:57:49"}
+{"current_steps": 86, "total_steps": 231, "loss": 0.4213, "lr": 1.589012401863864e-05, "epoch": 2.606060606060606, "percentage": 37.23, "elapsed_time": "0:33:57", "remaining_time": "0:57:15"}
+{"current_steps": 87, "total_steps": 231, "loss": 0.4057, "lr": 1.5766803221148676e-05, "epoch": 2.6363636363636362, "percentage": 37.66, "elapsed_time": "0:34:20", "remaining_time": "0:56:51"}
+{"current_steps": 88, "total_steps": 231, "loss": 0.419, "lr": 1.5642154155228124e-05, "epoch": 2.6666666666666665, "percentage": 38.1, "elapsed_time": "0:34:38", "remaining_time": "0:56:17"}
+{"current_steps": 89, "total_steps": 231, "loss": 0.4093, "lr": 1.5516205531310272e-05, "epoch": 2.6969696969696972, "percentage": 38.53, "elapsed_time": "0:35:01", "remaining_time": "0:55:53"}
+{"current_steps": 90, "total_steps": 231, "loss": 0.4106, "lr": 1.538898635915576e-05, "epoch": 2.7272727272727275, "percentage": 38.96, "elapsed_time": "0:35:29", "remaining_time": "0:55:35"}
+{"current_steps": 91, "total_steps": 231, "loss": 0.4227, "lr": 1.526052594117071e-05, "epoch": 2.757575757575758, "percentage": 39.39, "elapsed_time": "0:35:49", "remaining_time": "0:55:07"}
+{"current_steps": 92, "total_steps": 231, "loss": 0.4253, "lr": 1.513085386565758e-05, "epoch": 2.787878787878788, "percentage": 39.83, "elapsed_time": "0:36:16", "remaining_time": "0:54:48"}
+{"current_steps": 93, "total_steps": 231, "loss": 0.4025, "lr": 1.5000000000000002e-05, "epoch": 2.8181818181818183, "percentage": 40.26, "elapsed_time": "0:36:36", "remaining_time": "0:54:19"}
+{"current_steps": 94, "total_steps": 231, "loss": 0.4332, "lr": 1.4867994483783485e-05, "epoch": 2.8484848484848486, "percentage": 40.69, "elapsed_time": "0:36:56", "remaining_time": "0:53:50"}
+{"current_steps": 95, "total_steps": 231, "loss": 0.4296, "lr": 1.4734867721853341e-05, "epoch": 2.878787878787879, "percentage": 41.13, "elapsed_time": "0:37:17", "remaining_time": "0:53:22"}
+{"current_steps": 96, "total_steps": 231, "loss": 0.4095, "lr": 1.4600650377311523e-05, "epoch": 2.909090909090909, "percentage": 41.56, "elapsed_time": "0:37:45", "remaining_time": "0:53:06"}
+{"current_steps": 97, "total_steps": 231, "loss": 0.4375, "lr": 1.4465373364454001e-05, "epoch": 2.9393939393939394, "percentage": 41.99, "elapsed_time": "0:38:07", "remaining_time": "0:52:39"}
+{"current_steps": 98, "total_steps": 231, "loss": 0.4412, "lr": 1.4329067841650274e-05, "epoch": 2.9696969696969697, "percentage": 42.42, "elapsed_time": "0:38:29", "remaining_time": "0:52:14"}
+{"current_steps": 99, "total_steps": 231, "loss": 0.4179, "lr": 1.4191765204166643e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "0:38:58", "remaining_time": "0:51:57"}
+{"current_steps": 100, "total_steps": 231, "loss": 0.3316, "lr": 1.4053497076934948e-05, "epoch": 3.0303030303030303, "percentage": 43.29, "elapsed_time": "0:39:32", "remaining_time": "0:51:47"}
+{"current_steps": 101, "total_steps": 231, "loss": 0.2961, "lr": 1.3914295307268396e-05, "epoch": 3.0606060606060606, "percentage": 43.72, "elapsed_time": "0:39:51", "remaining_time": "0:51:18"}
+{"current_steps": 102, "total_steps": 231, "loss": 0.3223, "lr": 1.3774191957526144e-05, "epoch": 3.090909090909091, "percentage": 44.16, "elapsed_time": "0:40:18", "remaining_time": "0:50:58"}
+{"current_steps": 103, "total_steps": 231, "loss": 0.3014, "lr": 1.3633219297728415e-05, "epoch": 3.121212121212121, "percentage": 44.59, "elapsed_time": "0:40:42", "remaining_time": "0:50:34"}
+{"current_steps": 104, "total_steps": 231, "loss": 0.3173, "lr": 1.3491409798123687e-05, "epoch": 3.1515151515151514, "percentage": 45.02, "elapsed_time": "0:41:10", "remaining_time": "0:50:17"}
+{"current_steps": 105, "total_steps": 231, "loss": 0.3068, "lr": 1.3348796121709862e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "0:41:37", "remaining_time": "0:49:57"}
+{"current_steps": 106, "total_steps": 231, "loss": 0.3075, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "0:42:01", "remaining_time": "0:49:33"}
+{"current_steps": 107, "total_steps": 231, "loss": 0.3061, "lr": 1.3061287809011243e-05, "epoch": 3.242424242424242, "percentage": 46.32, "elapsed_time": "0:42:25", "remaining_time": "0:49:09"}
+{"current_steps": 108, "total_steps": 231, "loss": 0.3259, "lr": 1.291645939454825e-05, "epoch": 3.2727272727272725, "percentage": 46.75, "elapsed_time": "0:42:56", "remaining_time": "0:48:53"}
+{"current_steps": 109, "total_steps": 231, "loss": 0.305, "lr": 1.277095923166689e-05, "epoch": 3.303030303030303, "percentage": 47.19, "elapsed_time": "0:43:15", "remaining_time": "0:48:24"}
+{"current_steps": 110, "total_steps": 231, "loss": 0.2969, "lr": 1.2624820833435939e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "0:43:39", "remaining_time": "0:48:01"}
+{"current_steps": 111, "total_steps": 231, "loss": 0.2983, "lr": 1.2478077859929e-05, "epoch": 3.3636363636363638, "percentage": 48.05, "elapsed_time": "0:44:00", "remaining_time": "0:47:34"}
+{"current_steps": 112, "total_steps": 231, "loss": 0.3005, "lr": 1.2330764110471567e-05, "epoch": 3.393939393939394, "percentage": 48.48, "elapsed_time": "0:44:16", "remaining_time": "0:47:02"}
+{"current_steps": 113, "total_steps": 231, "loss": 0.3187, "lr": 1.2182913515856016e-05, "epoch": 3.4242424242424243, "percentage": 48.92, "elapsed_time": "0:44:35", "remaining_time": "0:46:33"}
+{"current_steps": 114, "total_steps": 231, "loss": 0.296, "lr": 1.2034560130526341e-05, "epoch": 3.4545454545454546, "percentage": 49.35, "elapsed_time": "0:45:03", "remaining_time": "0:46:14"}
+{"current_steps": 115, "total_steps": 231, "loss": 0.3096, "lr": 1.1885738124734359e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "0:45:24", "remaining_time": "0:45:48"}
+{"current_steps": 116, "total_steps": 231, "loss": 0.2866, "lr": 1.1736481776669307e-05, "epoch": 3.515151515151515, "percentage": 50.22, "elapsed_time": "0:45:40", "remaining_time": "0:45:17"}
+{"current_steps": 117, "total_steps": 231, "loss": 0.2986, "lr": 1.1586825464562515e-05, "epoch": 3.5454545454545454, "percentage": 50.65, "elapsed_time": "0:46:06", "remaining_time": "0:44:55"}
+{"current_steps": 118, "total_steps": 231, "loss": 0.2984, "lr": 1.1436803658769082e-05, "epoch": 3.5757575757575757, "percentage": 51.08, "elapsed_time": "0:46:32", "remaining_time": "0:44:33"}
+{"current_steps": 119, "total_steps": 231, "loss": 0.2898, "lr": 1.1286450913828313e-05, "epoch": 3.606060606060606, "percentage": 51.52, "elapsed_time": "0:46:53", "remaining_time": "0:44:08"}
+{"current_steps": 120, "total_steps": 231, "loss": 0.2976, "lr": 1.113580186050475e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "0:47:17", "remaining_time": "0:43:44"}
+{"current_steps": 121, "total_steps": 231, "loss": 0.3019, "lr": 1.0984891197811686e-05, "epoch": 3.6666666666666665, "percentage": 52.38, "elapsed_time": "0:47:43", "remaining_time": "0:43:23"}
+{"current_steps": 122, "total_steps": 231, "loss": 0.287, "lr": 1.0833753685018935e-05, "epoch": 3.6969696969696972, "percentage": 52.81, "elapsed_time": "0:48:10", "remaining_time": "0:43:02"}
+{"current_steps": 123, "total_steps": 231, "loss": 0.301, "lr": 1.0682424133646712e-05, "epoch": 3.7272727272727275, "percentage": 53.25, "elapsed_time": "0:48:31", "remaining_time": "0:42:36"}
+{"current_steps": 124, "total_steps": 231, "loss": 0.3142, "lr": 1.0530937399447496e-05, "epoch": 3.757575757575758, "percentage": 53.68, "elapsed_time": "0:48:54", "remaining_time": "0:42:12"}
+{"current_steps": 125, "total_steps": 231, "loss": 0.2854, "lr": 1.0379328374377715e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "0:49:18", "remaining_time": "0:41:49"}
+{"current_steps": 126, "total_steps": 231, "loss": 0.2826, "lr": 1.0227631978561057e-05, "epoch": 3.8181818181818183, "percentage": 54.55, "elapsed_time": "0:49:38", "remaining_time": "0:41:22"}
+{"current_steps": 127, "total_steps": 231, "loss": 0.2737, "lr": 1.0075883152245334e-05, "epoch": 3.8484848484848486, "percentage": 54.98, "elapsed_time": "0:50:01", "remaining_time": "0:40:57"}
+{"current_steps": 128, "total_steps": 231, "loss": 0.3052, "lr": 9.92411684775467e-06, "epoch": 3.878787878787879, "percentage": 55.41, "elapsed_time": "0:50:29", "remaining_time": "0:40:37"}
+{"current_steps": 129, "total_steps": 231, "loss": 0.3027, "lr": 9.772368021438943e-06, "epoch": 3.909090909090909, "percentage": 55.84, "elapsed_time": "0:50:54", "remaining_time": "0:40:15"}
+{"current_steps": 130, "total_steps": 231, "loss": 0.2916, "lr": 9.620671625622287e-06, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "0:51:17", "remaining_time": "0:39:50"}
+{"current_steps": 131, "total_steps": 231, "loss": 0.3132, "lr": 9.469062600552509e-06, "epoch": 3.9696969696969697, "percentage": 56.71, "elapsed_time": "0:51:40", "remaining_time": "0:39:26"}
+{"current_steps": 132, "total_steps": 231, "loss": 0.2724, "lr": 9.317575866353293e-06, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "0:52:00", "remaining_time": "0:39:00"}
+{"current_steps": 133, "total_steps": 231, "loss": 0.2173, "lr": 9.166246314981066e-06, "epoch": 4.03030303030303, "percentage": 57.58, "elapsed_time": "0:52:33", "remaining_time": "0:38:43"}
+{"current_steps": 134, "total_steps": 231, "loss": 0.2279, "lr": 9.015108802188314e-06, "epoch": 4.0606060606060606, "percentage": 58.01, "elapsed_time": "0:53:00", "remaining_time": "0:38:22"}
+{"current_steps": 135, "total_steps": 231, "loss": 0.2097, "lr": 8.86419813949525e-06, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "0:53:19", "remaining_time": "0:37:55"}
+{"current_steps": 136, "total_steps": 231, "loss": 0.2114, "lr": 8.71354908617169e-06, "epoch": 4.121212121212121, "percentage": 58.87, "elapsed_time": "0:53:41", "remaining_time": "0:37:30"}
+{"current_steps": 137, "total_steps": 231, "loss": 0.2211, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "0:54:04", "remaining_time": "0:37:06"}
+{"current_steps": 138, "total_steps": 231, "loss": 0.2046, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "0:54:29", "remaining_time": "0:36:43"}
+{"current_steps": 139, "total_steps": 231, "loss": 0.2059, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "0:54:50", "remaining_time": "0:36:18"}
+{"current_steps": 140, "total_steps": 231, "loss": 0.1994, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "0:55:17", "remaining_time": "0:35:56"}
+{"current_steps": 141, "total_steps": 231, "loss": 0.2242, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "0:55:40", "remaining_time": "0:35:31"}
+{"current_steps": 142, "total_steps": 231, "loss": 0.198, "lr": 7.817086484143987e-06, "epoch": 4.303030303030303, "percentage": 61.47, "elapsed_time": "0:55:57", "remaining_time": "0:35:04"}
+{"current_steps": 143, "total_steps": 231, "loss": 0.2016, "lr": 7.669235889528436e-06, "epoch": 4.333333333333333, "percentage": 61.9, "elapsed_time": "0:56:16", "remaining_time": "0:34:38"}
+{"current_steps": 144, "total_steps": 231, "loss": 0.227, "lr": 7.521922140071003e-06, "epoch": 4.363636363636363, "percentage": 62.34, "elapsed_time": "0:56:44", "remaining_time": "0:34:17"}
+{"current_steps": 145, "total_steps": 231, "loss": 0.2037, "lr": 7.375179166564062e-06, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "0:57:10", "remaining_time": "0:33:54"}
+{"current_steps": 146, "total_steps": 231, "loss": 0.1998, "lr": 7.2290407683331154e-06, "epoch": 4.424242424242424, "percentage": 63.2, "elapsed_time": "0:57:34", "remaining_time": "0:33:31"}
+{"current_steps": 147, "total_steps": 231, "loss": 0.1984, "lr": 7.0835406054517505e-06, "epoch": 4.454545454545454, "percentage": 63.64, "elapsed_time": "0:57:55", "remaining_time": "0:33:06"}
+{"current_steps": 148, "total_steps": 231, "loss": 0.1884, "lr": 6.93871219098876e-06, "epoch": 4.484848484848484, "percentage": 64.07, "elapsed_time": "0:58:14", "remaining_time": "0:32:39"}
+{"current_steps": 149, "total_steps": 231, "loss": 0.2031, "lr": 6.79458888328903e-06, "epoch": 4.515151515151516, "percentage": 64.5, "elapsed_time": "0:58:36", "remaining_time": "0:32:15"}
+{"current_steps": 150, "total_steps": 231, "loss": 0.1959, "lr": 6.651203878290139e-06, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "0:58:49", "remaining_time": "0:31:46"}
+{"current_steps": 151, "total_steps": 231, "loss": 0.2005, "lr": 6.508590201876317e-06, "epoch": 4.575757575757576, "percentage": 65.37, "elapsed_time": "0:59:11", "remaining_time": "0:31:21"}
+{"current_steps": 152, "total_steps": 231, "loss": 0.1928, "lr": 6.366780702271589e-06, "epoch": 4.606060606060606, "percentage": 65.8, "elapsed_time": "0:59:35", "remaining_time": "0:30:58"}
+{"current_steps": 153, "total_steps": 231, "loss": 0.1977, "lr": 6.225808042473857e-06, "epoch": 4.636363636363637, "percentage": 66.23, "elapsed_time": "0:59:55", "remaining_time": "0:30:32"}
+{"current_steps": 154, "total_steps": 231, "loss": 0.1988, "lr": 6.085704692731609e-06, "epoch": 4.666666666666667, "percentage": 66.67, "elapsed_time": "1:00:15", "remaining_time": "0:30:07"}
+{"current_steps": 155, "total_steps": 231, "loss": 0.2107, "lr": 5.946502923065054e-06, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "1:00:38", "remaining_time": "0:29:44"}
+{"current_steps": 156, "total_steps": 231, "loss": 0.2251, "lr": 5.8082347958333625e-06, "epoch": 4.7272727272727275, "percentage": 67.53, "elapsed_time": "1:01:03", "remaining_time": "0:29:21"}
+{"current_steps": 157, "total_steps": 231, "loss": 0.1868, "lr": 5.670932158349732e-06, "epoch": 4.757575757575758, "percentage": 67.97, "elapsed_time": "1:01:27", "remaining_time": "0:28:57"}
+{"current_steps": 158, "total_steps": 231, "loss": 0.1788, "lr": 5.534626635546e-06, "epoch": 4.787878787878788, "percentage": 68.4, "elapsed_time": "1:01:43", "remaining_time": "0:28:31"}
+{"current_steps": 159, "total_steps": 231, "loss": 0.1982, "lr": 5.399349622688479e-06, "epoch": 4.818181818181818, "percentage": 68.83, "elapsed_time": "1:02:06", "remaining_time": "0:28:07"}
+{"current_steps": 160, "total_steps": 231, "loss": 0.2075, "lr": 5.2651322781466606e-06, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "1:02:25", "remaining_time": "0:27:42"}
+{"current_steps": 161, "total_steps": 231, "loss": 0.1988, "lr": 5.132005516216512e-06, "epoch": 4.878787878787879, "percentage": 69.7, "elapsed_time": "1:02:53", "remaining_time": "0:27:20"}
+{"current_steps": 162, "total_steps": 231, "loss": 0.1958, "lr": 5.000000000000003e-06, "epoch": 4.909090909090909, "percentage": 70.13, "elapsed_time": "1:03:16", "remaining_time": "0:26:57"}
+{"current_steps": 163, "total_steps": 231, "loss": 0.1899, "lr": 4.869146134342426e-06, "epoch": 4.9393939393939394, "percentage": 70.56, "elapsed_time": "1:03:42", "remaining_time": "0:26:34"}
+{"current_steps": 164, "total_steps": 231, "loss": 0.1931, "lr": 4.739474058829288e-06, "epoch": 4.96969696969697, "percentage": 71.0, "elapsed_time": "1:04:05", "remaining_time": "0:26:11"}
+{"current_steps": 165, "total_steps": 231, "loss": 0.1958, "lr": 4.611013640844245e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:04:32", "remaining_time": "0:25:49"}
+{"current_steps": 166, "total_steps": 231, "loss": 0.1634, "lr": 4.483794468689728e-06, "epoch": 5.03030303030303, "percentage": 71.86, "elapsed_time": "1:05:12", "remaining_time": "0:25:31"}
+{"current_steps": 167, "total_steps": 231, "loss": 0.1484, "lr": 4.357845844771881e-06, "epoch": 5.0606060606060606, "percentage": 72.29, "elapsed_time": "1:05:34", "remaining_time": "0:25:07"}
+{"current_steps": 168, "total_steps": 231, "loss": 0.1422, "lr": 4.2331967788513295e-06, "epoch": 5.090909090909091, "percentage": 72.73, "elapsed_time": "1:05:54", "remaining_time": "0:24:42"}
+{"current_steps": 169, "total_steps": 231, "loss": 0.1326, "lr": 4.109875981361363e-06, "epoch": 5.121212121212121, "percentage": 73.16, "elapsed_time": "1:06:10", "remaining_time": "0:24:16"}
+{"current_steps": 170, "total_steps": 231, "loss": 0.1453, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:06:29", "remaining_time": "0:23:51"}
+{"current_steps": 171, "total_steps": 231, "loss": 0.1398, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:06:50", "remaining_time": "0:23:27"}
+{"current_steps": 172, "total_steps": 231, "loss": 0.1392, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:07:15", "remaining_time": "0:23:04"}
+{"current_steps": 173, "total_steps": 231, "loss": 0.1397, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:07:33", "remaining_time": "0:22:39"}
+{"current_steps": 174, "total_steps": 231, "loss": 0.1414, "lr": 3.5141791053724405e-06, "epoch": 5.2727272727272725, "percentage": 75.32, "elapsed_time": "1:07:55", "remaining_time": "0:22:15"}
+{"current_steps": 175, "total_steps": 231, "loss": 0.1363, "lr": 3.399413251016359e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:08:19", "remaining_time": "0:21:51"}
+{"current_steps": 176, "total_steps": 231, "loss": 0.1379, "lr": 3.2861677105440335e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "1:08:41", "remaining_time": "0:21:27"}
+{"current_steps": 177, "total_steps": 231, "loss": 0.1326, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "1:09:09", "remaining_time": "0:21:05"}
+{"current_steps": 178, "total_steps": 231, "loss": 0.1295, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "1:09:34", "remaining_time": "0:20:42"}
+{"current_steps": 179, "total_steps": 231, "loss": 0.1283, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "1:09:59", "remaining_time": "0:20:19"}
+{"current_steps": 180, "total_steps": 231, "loss": 0.1466, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:10:26", "remaining_time": "0:19:57"}
+{"current_steps": 181, "total_steps": 231, "loss": 0.1517, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "1:10:54", "remaining_time": "0:19:35"}
+{"current_steps": 182, "total_steps": 231, "loss": 0.1292, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "1:11:18", "remaining_time": "0:19:11"}
+{"current_steps": 183, "total_steps": 231, "loss": 0.1299, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "1:11:36", "remaining_time": "0:18:46"}
+{"current_steps": 184, "total_steps": 231, "loss": 0.136, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "1:11:56", "remaining_time": "0:18:22"}
+{"current_steps": 185, "total_steps": 231, "loss": 0.1297, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:12:14", "remaining_time": "0:17:57"}
+{"current_steps": 186, "total_steps": 231, "loss": 0.1311, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "1:12:34", "remaining_time": "0:17:33"}
+{"current_steps": 187, "total_steps": 231, "loss": 0.1414, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "1:12:56", "remaining_time": "0:17:09"}
+{"current_steps": 188, "total_steps": 231, "loss": 0.1407, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "1:13:21", "remaining_time": "0:16:46"}
+{"current_steps": 189, "total_steps": 231, "loss": 0.1422, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "1:13:48", "remaining_time": "0:16:24"}
+{"current_steps": 190, "total_steps": 231, "loss": 0.136, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "1:14:07", "remaining_time": "0:15:59"}
+{"current_steps": 191, "total_steps": 231, "loss": 0.1571, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "1:14:36", "remaining_time": "0:15:37"}
+{"current_steps": 192, "total_steps": 231, "loss": 0.1258, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "1:15:01", "remaining_time": "0:15:14"}
+{"current_steps": 193, "total_steps": 231, "loss": 0.1233, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "1:15:23", "remaining_time": "0:14:50"}
+{"current_steps": 194, "total_steps": 231, "loss": 0.1328, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "1:15:44", "remaining_time": "0:14:26"}
+{"current_steps": 195, "total_steps": 231, "loss": 0.1373, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "1:16:10", "remaining_time": "0:14:03"}
+{"current_steps": 196, "total_steps": 231, "loss": 0.1378, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "1:16:34", "remaining_time": "0:13:40"}
+{"current_steps": 197, "total_steps": 231, "loss": 0.1366, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "1:16:58", "remaining_time": "0:13:17"}
+{"current_steps": 198, "total_steps": 231, "loss": 0.1365, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "1:17:15", "remaining_time": "0:12:52"}
+{"current_steps": 199, "total_steps": 231, "loss": 0.1209, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "1:17:50", "remaining_time": "0:12:31"}
+{"current_steps": 200, "total_steps": 231, "loss": 0.1189, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "1:18:14", "remaining_time": "0:12:07"}
+{"current_steps": 201, "total_steps": 231, "loss": 0.108, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "1:18:38", "remaining_time": "0:11:44"}
+{"current_steps": 202, "total_steps": 231, "loss": 0.1067, "lr": 9.530222835413739e-07, "epoch": 6.121212121212121, "percentage": 87.45, "elapsed_time": "1:19:02", "remaining_time": "0:11:20"}
+{"current_steps": 203, "total_steps": 231, "loss": 0.1154, "lr": 8.894054121084839e-07, "epoch": 6.151515151515151, "percentage": 87.88, "elapsed_time": "1:19:25", "remaining_time": "0:10:57"}
+{"current_steps": 204, "total_steps": 231, "loss": 0.1106, "lr": 8.278869849454718e-07, "epoch": 6.181818181818182, "percentage": 88.31, "elapsed_time": "1:19:52", "remaining_time": "0:10:34"}
+{"current_steps": 205, "total_steps": 231, "loss": 0.1059, "lr": 7.684811715985429e-07, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "1:20:13", "remaining_time": "0:10:10"}
+{"current_steps": 206, "total_steps": 231, "loss": 0.1035, "lr": 7.1120165501533e-07, "epoch": 6.242424242424242, "percentage": 89.18, "elapsed_time": "1:20:36", "remaining_time": "0:09:46"}
+{"current_steps": 207, "total_steps": 231, "loss": 0.1095, "lr": 6.560616283932897e-07, "epoch": 6.2727272727272725, "percentage": 89.61, "elapsed_time": "1:21:01", "remaining_time": "0:09:23"}
+{"current_steps": 208, "total_steps": 231, "loss": 0.1, "lr": 6.030737921409169e-07, "epoch": 6.303030303030303, "percentage": 90.04, "elapsed_time": "1:21:17", "remaining_time": "0:08:59"}
+{"current_steps": 209, "total_steps": 231, "loss": 0.1064, "lr": 5.522503509524591e-07, "epoch": 6.333333333333333, "percentage": 90.48, "elapsed_time": "1:21:39", "remaining_time": "0:08:35"}
+{"current_steps": 210, "total_steps": 231, "loss": 0.1172, "lr": 5.036030109968082e-07, "epoch": 6.363636363636363, "percentage": 90.91, "elapsed_time": "1:22:01", "remaining_time": "0:08:12"}
+{"current_steps": 211, "total_steps": 231, "loss": 0.1123, "lr": 4.5714297722121105e-07, "epoch": 6.393939393939394, "percentage": 91.34, "elapsed_time": "1:22:28", "remaining_time": "0:07:49"}
+{"current_steps": 212, "total_steps": 231, "loss": 0.1197, "lr": 4.128809507704445e-07, "epoch": 6.424242424242424, "percentage": 91.77, "elapsed_time": "1:22:46", "remaining_time": "0:07:25"}
+{"current_steps": 213, "total_steps": 231, "loss": 0.1144, "lr": 3.708271265220087e-07, "epoch": 6.454545454545454, "percentage": 92.21, "elapsed_time": "1:23:11", "remaining_time": "0:07:01"}
+{"current_steps": 214, "total_steps": 231, "loss": 0.1255, "lr": 3.309911907379393e-07, "epoch": 6.484848484848484, "percentage": 92.64, "elapsed_time": "1:23:36", "remaining_time": "0:06:38"}
+{"current_steps": 215, "total_steps": 231, "loss": 0.1204, "lr": 2.9338231883378365e-07, "epoch": 6.515151515151516, "percentage": 93.07, "elapsed_time": "1:23:57", "remaining_time": "0:06:14"}
+{"current_steps": 216, "total_steps": 231, "loss": 0.1042, "lr": 2.5800917326521013e-07, "epoch": 6.545454545454545, "percentage": 93.51, "elapsed_time": "1:24:14", "remaining_time": "0:05:51"}
+{"current_steps": 217, "total_steps": 231, "loss": 0.1104, "lr": 2.248799015327907e-07, "epoch": 6.575757575757576, "percentage": 93.94, "elapsed_time": "1:24:39", "remaining_time": "0:05:27"}
+{"current_steps": 218, "total_steps": 231, "loss": 0.1165, "lr": 1.9400213430538773e-07, "epoch": 6.606060606060606, "percentage": 94.37, "elapsed_time": "1:25:01", "remaining_time": "0:05:04"}
+{"current_steps": 219, "total_steps": 231, "loss": 0.1262, "lr": 1.6538298366257975e-07, "epoch": 6.636363636363637, "percentage": 94.81, "elapsed_time": "1:25:28", "remaining_time": "0:04:41"}
+{"current_steps": 220, "total_steps": 231, "loss": 0.1175, "lr": 1.3902904145653094e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "1:25:51", "remaining_time": "0:04:17"}
+{"current_steps": 221, "total_steps": 231, "loss": 0.0973, "lr": 1.1494637779369766e-07, "epoch": 6.696969696969697, "percentage": 95.67, "elapsed_time": "1:26:14", "remaining_time": "0:03:54"}
+{"current_steps": 222, "total_steps": 231, "loss": 0.1053, "lr": 9.314053963669245e-08, "epoch": 6.7272727272727275, "percentage": 96.1, "elapsed_time": "1:26:38", "remaining_time": "0:03:30"}
+{"current_steps": 223, "total_steps": 231, "loss": 0.1035, "lr": 7.361654952665608e-08, "epoch": 6.757575757575758, "percentage": 96.54, "elapsed_time": "1:26:57", "remaining_time": "0:03:07"}
+{"current_steps": 224, "total_steps": 231, "loss": 0.1115, "lr": 5.637890442641403e-08, "epoch": 6.787878787878788, "percentage": 96.97, "elapsed_time": "1:27:21", "remaining_time": "0:02:43"}
+{"current_steps": 225, "total_steps": 231, "loss": 0.1065, "lr": 4.143157468468717e-08, "epoch": 6.818181818181818, "percentage": 97.4, "elapsed_time": "1:27:43", "remaining_time": "0:02:20"}
+{"current_steps": 226, "total_steps": 231, "loss": 0.119, "lr": 2.8778003121607834e-08, "epoch": 6.848484848484849, "percentage": 97.84, "elapsed_time": "1:28:10", "remaining_time": "0:01:57"}
+{"current_steps": 227, "total_steps": 231, "loss": 0.1187, "lr": 1.8421104235727406e-08, "epoch": 6.878787878787879, "percentage": 98.27, "elapsed_time": "1:28:29", "remaining_time": "0:01:33"}
+{"current_steps": 228, "total_steps": 231, "loss": 0.1111, "lr": 1.0363263532724433e-08, "epoch": 6.909090909090909, "percentage": 98.7, "elapsed_time": "1:28:53", "remaining_time": "0:01:10"}
+{"current_steps": 229, "total_steps": 231, "loss": 0.103, "lr": 4.606336975948589e-09, "epoch": 6.9393939393939394, "percentage": 99.13, "elapsed_time": "1:29:13", "remaining_time": "0:00:46"}
+{"current_steps": 230, "total_steps": 231, "loss": 0.1124, "lr": 1.1516505589381777e-09, "epoch": 6.96969696969697, "percentage": 99.57, "elapsed_time": "1:29:38", "remaining_time": "0:00:23"}
+{"current_steps": 231, "total_steps": 231, "loss": 0.1079, "lr": 0.0, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:30:01", "remaining_time": "0:00:00"}
+{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:30:31", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1659 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 231,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 6.082164551143029,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.9743,
+      "step": 1
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 6.199864643639447,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.9824,
+      "step": 2
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 5.933068581509626,
+      "learning_rate": 2.5e-06,
+      "loss": 0.9484,
+      "step": 3
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 5.48489512774313,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.9593,
+      "step": 4
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 4.733804820154826,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.9806,
+      "step": 5
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.453251004082805,
+      "learning_rate": 5e-06,
+      "loss": 0.8577,
+      "step": 6
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 2.194692816987401,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.9069,
+      "step": 7
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 4.169693041546917,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8973,
+      "step": 8
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 4.339203281212194,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.8624,
+      "step": 9
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 4.492627160157046,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.8693,
+      "step": 10
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.775232800961184,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.8402,
+      "step": 11
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 3.7624865252490447,
+      "learning_rate": 1e-05,
+      "loss": 0.8399,
+      "step": 12
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 3.030257151028533,
+      "learning_rate": 1.0833333333333334e-05,
+      "loss": 0.8324,
+      "step": 13
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 2.1045530995893955,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.7438,
+      "step": 14
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 2.529529609047169,
+      "learning_rate": 1.25e-05,
+      "loss": 0.7935,
+      "step": 15
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 2.3960493789409814,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7764,
+      "step": 16
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 2.3405459822246595,
+      "learning_rate": 1.416666666666667e-05,
+      "loss": 0.7612,
+      "step": 17
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.780242375804455,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7319,
+      "step": 18
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 1.8376558126663334,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.7525,
+      "step": 19
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 1.7841155986438049,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.7351,
+      "step": 20
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 1.4363844990323147,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.7023,
+      "step": 21
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.157085510392974,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.7288,
+      "step": 22
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 1.2534692241749141,
+      "learning_rate": 1.916666666666667e-05,
+      "loss": 0.6977,
+      "step": 23
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 1.2306556966026905,
+      "learning_rate": 2e-05,
+      "loss": 0.6841,
+      "step": 24
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 0.8716110203881019,
+      "learning_rate": 1.999884834944106e-05,
+      "loss": 0.708,
+      "step": 25
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 1.0877065969299742,
+      "learning_rate": 1.9995393663024054e-05,
+      "loss": 0.6761,
+      "step": 26
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.9671933925061544,
+      "learning_rate": 1.9989636736467278e-05,
+      "loss": 0.6682,
+      "step": 27
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.9251271064814989,
+      "learning_rate": 1.9981578895764272e-05,
+      "loss": 0.6939,
+      "step": 28
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 0.9021303013268445,
+      "learning_rate": 1.9971221996878395e-05,
+      "loss": 0.6689,
+      "step": 29
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.8563239151908998,
+      "learning_rate": 1.9958568425315316e-05,
+      "loss": 0.6889,
+      "step": 30
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.8264877357726544,
+      "learning_rate": 1.9943621095573588e-05,
+      "loss": 0.6756,
+      "step": 31
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.7549070294670714,
+      "learning_rate": 1.9926383450473344e-05,
+      "loss": 0.6801,
+      "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7528386178645887,
+      "learning_rate": 1.9906859460363307e-05,
+      "loss": 0.6359,
+      "step": 33
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 0.9479487314552061,
+      "learning_rate": 1.9885053622206305e-05,
+      "loss": 0.664,
+      "step": 34
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.5579551117644118,
+      "learning_rate": 1.986097095854347e-05,
+      "loss": 0.5904,
+      "step": 35
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.8784414158397916,
+      "learning_rate": 1.9834617016337424e-05,
+      "loss": 0.6009,
+      "step": 36
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.6911146133507795,
+      "learning_rate": 1.9805997865694616e-05,
+      "loss": 0.5919,
+      "step": 37
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 0.6893506149596769,
+      "learning_rate": 1.9775120098467212e-05,
+      "loss": 0.5933,
+      "step": 38
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.7255162316422783,
+      "learning_rate": 1.9741990826734793e-05,
+      "loss": 0.6017,
+      "step": 39
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.8471072586967952,
+      "learning_rate": 1.970661768116622e-05,
+      "loss": 0.5851,
+      "step": 40
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 0.6529361337239672,
+      "learning_rate": 1.9669008809262064e-05,
+      "loss": 0.5649,
+      "step": 41
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.6838430467037275,
+      "learning_rate": 1.9629172873477995e-05,
+      "loss": 0.5826,
+      "step": 42
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 0.6558124450536883,
+      "learning_rate": 1.9587119049229558e-05,
+      "loss": 0.5733,
+      "step": 43
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.7075844976370234,
+      "learning_rate": 1.954285702277879e-05,
+      "loss": 0.6049,
+      "step": 44
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.6741474451437296,
+      "learning_rate": 1.9496396989003195e-05,
+      "loss": 0.5601,
+      "step": 45
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 0.7554795068670029,
+      "learning_rate": 1.944774964904754e-05,
+      "loss": 0.6024,
+      "step": 46
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 0.830944144168637,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.5467,
+      "step": 47
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.7147180115547055,
+      "learning_rate": 1.9343938371606714e-05,
+      "loss": 0.5808,
+      "step": 48
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 0.6752142559980884,
+      "learning_rate": 1.9288798344984673e-05,
+      "loss": 0.5406,
+      "step": 49
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.806800173109227,
+      "learning_rate": 1.9231518828401458e-05,
+      "loss": 0.5592,
+      "step": 50
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.6786507591993622,
+      "learning_rate": 1.917211301505453e-05,
+      "loss": 0.6109,
+      "step": 51
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 0.6341107562740883,
+      "learning_rate": 1.911059458789152e-05,
+      "loss": 0.5306,
+      "step": 52
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 0.6568745519323503,
+      "learning_rate": 1.9046977716458627e-05,
+      "loss": 0.5892,
+      "step": 53
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.6852239165890293,
+      "learning_rate": 1.8981277053636963e-05,
+      "loss": 0.5784,
+      "step": 54
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.700488857549085,
+      "learning_rate": 1.891350773226754e-05,
+      "loss": 0.5433,
+      "step": 55
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 0.7945441088005711,
+      "learning_rate": 1.8843685361665724e-05,
+      "loss": 0.5797,
+      "step": 56
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.7276040007844824,
+      "learning_rate": 1.8771826024025944e-05,
+      "loss": 0.5882,
+      "step": 57
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 0.8596171576630897,
+      "learning_rate": 1.8697946270717468e-05,
+      "loss": 0.5888,
+      "step": 58
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 0.6610138494716133,
+      "learning_rate": 1.8622063118472135e-05,
+      "loss": 0.5415,
+      "step": 59
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.8106095732614276,
+      "learning_rate": 1.8544194045464888e-05,
+      "loss": 0.5745,
+      "step": 60
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.6102717823967825,
+      "learning_rate": 1.8464356987288012e-05,
+      "loss": 0.5236,
+      "step": 61
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 0.794138487374143,
+      "learning_rate": 1.8382570332820045e-05,
+      "loss": 0.5252,
+      "step": 62
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.5854426107859853,
+      "learning_rate": 1.8298852919990254e-05,
+      "loss": 0.5607,
+      "step": 63
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 0.7441208793477079,
+      "learning_rate": 1.821322403143969e-05,
+      "loss": 0.5631,
+      "step": 64
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.6307361361127832,
+      "learning_rate": 1.812570339007983e-05,
+      "loss": 0.5809,
+      "step": 65
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6386005422389703,
+      "learning_rate": 1.8036311154549783e-05,
+      "loss": 0.578,
+      "step": 66
+    },
+    {
+      "epoch": 2.0303030303030303,
+      "grad_norm": 0.7787329060681482,
+      "learning_rate": 1.7945067914573147e-05,
+      "loss": 0.451,
+      "step": 67
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 0.6567460397548995,
+      "learning_rate": 1.7851994686215592e-05,
+      "loss": 0.4404,
+      "step": 68
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 0.8241315933972604,
+      "learning_rate": 1.77571129070442e-05,
+      "loss": 0.4581,
+      "step": 69
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 0.7534370019747573,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.4509,
+      "step": 70
+    },
+    {
+      "epoch": 2.1515151515151514,
+      "grad_norm": 0.6872313509214591,
+      "learning_rate": 1.7562011524313187e-05,
+      "loss": 0.4417,
+      "step": 71
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.8003750790780567,
+      "learning_rate": 1.7461836858476858e-05,
+      "loss": 0.4315,
+      "step": 72
+    },
+    {
+      "epoch": 2.212121212121212,
+      "grad_norm": 0.6885114529551459,
+      "learning_rate": 1.7359943506922775e-05,
+      "loss": 0.4357,
+      "step": 73
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 0.622922312481805,
+      "learning_rate": 1.725635493875799e-05,
+      "loss": 0.4155,
+      "step": 74
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.6659684133395284,
+      "learning_rate": 1.7151095013548996e-05,
+      "loss": 0.4294,
+      "step": 75
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 0.6355696728345942,
+      "learning_rate": 1.7044187975826126e-05,
+      "loss": 0.4133,
+      "step": 76
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.6567767598814616,
+      "learning_rate": 1.693565844949933e-05,
+      "loss": 0.4255,
+      "step": 77
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.6933746677111999,
+      "learning_rate": 1.6825531432186545e-05,
+      "loss": 0.438,
+      "step": 78
+    },
+    {
+      "epoch": 2.393939393939394,
+      "grad_norm": 0.6056847026397173,
+      "learning_rate": 1.671383228945597e-05,
+      "loss": 0.398,
+      "step": 79
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.6597086578872607,
+      "learning_rate": 1.6600586748983642e-05,
+      "loss": 0.4236,
+      "step": 80
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.5548480457025179,
+      "learning_rate": 1.648582089462756e-05,
+      "loss": 0.4369,
+      "step": 81
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 0.5878138584407185,
+      "learning_rate": 1.6369561160419783e-05,
+      "loss": 0.4092,
+      "step": 82
+    },
+    {
+      "epoch": 2.515151515151515,
+      "grad_norm": 0.5865809429691052,
+      "learning_rate": 1.625183432447789e-05,
+      "loss": 0.4197,
+      "step": 83
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.6044346276756262,
+      "learning_rate": 1.6132667502837164e-05,
+      "loss": 0.4242,
+      "step": 84
+    },
+    {
+      "epoch": 2.5757575757575757,
+      "grad_norm": 0.6368164236990473,
+      "learning_rate": 1.6012088143204953e-05,
+      "loss": 0.4235,
+      "step": 85
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 0.5519239137142832,
+      "learning_rate": 1.589012401863864e-05,
+      "loss": 0.4213,
+      "step": 86
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 0.600599957336867,
+      "learning_rate": 1.5766803221148676e-05,
+      "loss": 0.4057,
+      "step": 87
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.6039341293280637,
+      "learning_rate": 1.5642154155228124e-05,
+      "loss": 0.419,
+      "step": 88
+    },
+    {
+      "epoch": 2.6969696969696972,
+      "grad_norm": 0.5580092804048937,
+      "learning_rate": 1.5516205531310272e-05,
+      "loss": 0.4093,
+      "step": 89
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.6116420692274311,
+      "learning_rate": 1.538898635915576e-05,
+      "loss": 0.4106,
+      "step": 90
+    },
+    {
+      "epoch": 2.757575757575758,
+      "grad_norm": 0.48991663926802204,
+      "learning_rate": 1.526052594117071e-05,
+      "loss": 0.4227,
+      "step": 91
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 0.6560670019285071,
+      "learning_rate": 1.513085386565758e-05,
+      "loss": 0.4253,
+      "step": 92
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.5300396641790873,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.4025,
+      "step": 93
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 0.5434375934212474,
+      "learning_rate": 1.4867994483783485e-05,
+      "loss": 0.4332,
+      "step": 94
+    },
+    {
+      "epoch": 2.878787878787879,
+      "grad_norm": 0.5828297559054213,
+      "learning_rate": 1.4734867721853341e-05,
+      "loss": 0.4296,
+      "step": 95
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.539521181319008,
+      "learning_rate": 1.4600650377311523e-05,
+      "loss": 0.4095,
+      "step": 96
+    },
+    {
+      "epoch": 2.9393939393939394,
+      "grad_norm": 0.5408066308418242,
+      "learning_rate": 1.4465373364454001e-05,
+      "loss": 0.4375,
+      "step": 97
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 0.5153917595894786,
+      "learning_rate": 1.4329067841650274e-05,
+      "loss": 0.4412,
+      "step": 98
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5086632643785411,
+      "learning_rate": 1.4191765204166643e-05,
+      "loss": 0.4179,
+      "step": 99
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 0.8397857310579694,
+      "learning_rate": 1.4053497076934948e-05,
+      "loss": 0.3316,
+      "step": 100
+    },
+    {
+      "epoch": 3.0606060606060606,
+      "grad_norm": 0.6169887350063111,
+      "learning_rate": 1.3914295307268396e-05,
+      "loss": 0.2961,
+      "step": 101
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 0.7373719556030066,
+      "learning_rate": 1.3774191957526144e-05,
+      "loss": 0.3223,
+      "step": 102
+    },
+    {
+      "epoch": 3.121212121212121,
+      "grad_norm": 0.9689178088933306,
+      "learning_rate": 1.3633219297728415e-05,
+      "loss": 0.3014,
+      "step": 103
+    },
+    {
+      "epoch": 3.1515151515151514,
+      "grad_norm": 0.65450824052187,
+      "learning_rate": 1.3491409798123687e-05,
+      "loss": 0.3173,
+      "step": 104
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.6379328128026068,
+      "learning_rate": 1.3348796121709862e-05,
+      "loss": 0.3068,
+      "step": 105
+    },
+    {
+      "epoch": 3.212121212121212,
+      "grad_norm": 0.6941873237026441,
+      "learning_rate": 1.3205411116710973e-05,
+      "loss": 0.3075,
+      "step": 106
+    },
+    {
+      "epoch": 3.242424242424242,
+      "grad_norm": 0.6163483028866464,
+      "learning_rate": 1.3061287809011243e-05,
+      "loss": 0.3061,
+      "step": 107
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 0.6393176916923681,
+      "learning_rate": 1.291645939454825e-05,
+      "loss": 0.3259,
+      "step": 108
+    },
+    {
+      "epoch": 3.303030303030303,
+      "grad_norm": 0.5507965203981176,
+      "learning_rate": 1.277095923166689e-05,
+      "loss": 0.305,
+      "step": 109
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.617267947967507,
+      "learning_rate": 1.2624820833435939e-05,
+      "loss": 0.2969,
+      "step": 110
+    },
+    {
+      "epoch": 3.3636363636363638,
+      "grad_norm": 0.6909455689002703,
+      "learning_rate": 1.2478077859929e-05,
+      "loss": 0.2983,
+      "step": 111
+    },
+    {
+      "epoch": 3.393939393939394,
+      "grad_norm": 0.5328958418698717,
+      "learning_rate": 1.2330764110471567e-05,
+      "loss": 0.3005,
+      "step": 112
+    },
+    {
+      "epoch": 3.4242424242424243,
+      "grad_norm": 0.7520834074743395,
+      "learning_rate": 1.2182913515856016e-05,
+      "loss": 0.3187,
+      "step": 113
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 0.6416314170295463,
+      "learning_rate": 1.2034560130526341e-05,
+      "loss": 0.296,
+      "step": 114
+    },
+    {
+      "epoch": 3.484848484848485,
+      "grad_norm": 0.5565966816209027,
+      "learning_rate": 1.1885738124734359e-05,
+      "loss": 0.3096,
+      "step": 115
+    },
+    {
+      "epoch": 3.515151515151515,
+      "grad_norm": 0.6505365256952365,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.2866,
+      "step": 116
+    },
+    {
+      "epoch": 3.5454545454545454,
+      "grad_norm": 0.5028288108042958,
+      "learning_rate": 1.1586825464562515e-05,
+      "loss": 0.2986,
+      "step": 117
+    },
+    {
+      "epoch": 3.5757575757575757,
+      "grad_norm": 0.5560879755249306,
+      "learning_rate": 1.1436803658769082e-05,
+      "loss": 0.2984,
+      "step": 118
+    },
+    {
+      "epoch": 3.606060606060606,
+      "grad_norm": 0.561674570380799,
+      "learning_rate": 1.1286450913828313e-05,
+      "loss": 0.2898,
+      "step": 119
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.47347423026956065,
+      "learning_rate": 1.113580186050475e-05,
+      "loss": 0.2976,
+      "step": 120
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.5127687105759521,
+      "learning_rate": 1.0984891197811686e-05,
+      "loss": 0.3019,
+      "step": 121
+    },
+    {
+      "epoch": 3.6969696969696972,
+      "grad_norm": 0.5236365734999248,
+      "learning_rate": 1.0833753685018935e-05,
+      "loss": 0.287,
+      "step": 122
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 0.4811598328453427,
+      "learning_rate": 1.0682424133646712e-05,
+      "loss": 0.301,
+      "step": 123
+    },
+    {
+      "epoch": 3.757575757575758,
+      "grad_norm": 0.4964461036072366,
+      "learning_rate": 1.0530937399447496e-05,
+      "loss": 0.3142,
+      "step": 124
+    },
+    {
+      "epoch": 3.787878787878788,
+      "grad_norm": 0.542572482795018,
+      "learning_rate": 1.0379328374377715e-05,
+      "loss": 0.2854,
+      "step": 125
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 0.49529270879602094,
+      "learning_rate": 1.0227631978561057e-05,
+      "loss": 0.2826,
+      "step": 126
+    },
+    {
+      "epoch": 3.8484848484848486,
+      "grad_norm": 0.4825419630192013,
+      "learning_rate": 1.0075883152245334e-05,
+      "loss": 0.2737,
+      "step": 127
+    },
+    {
+      "epoch": 3.878787878787879,
+      "grad_norm": 0.5369360705017022,
+      "learning_rate": 9.92411684775467e-06,
+      "loss": 0.3052,
+      "step": 128
+    },
+    {
+      "epoch": 3.909090909090909,
+      "grad_norm": 0.49405796903698684,
+      "learning_rate": 9.772368021438943e-06,
+      "loss": 0.3027,
+      "step": 129
+    },
+    {
+      "epoch": 3.9393939393939394,
+      "grad_norm": 0.48724290865126735,
+      "learning_rate": 9.620671625622287e-06,
+      "loss": 0.2916,
+      "step": 130
+    },
+    {
+      "epoch": 3.9696969696969697,
+      "grad_norm": 0.5459544698031724,
+      "learning_rate": 9.469062600552509e-06,
+      "loss": 0.3132,
+      "step": 131
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5039711265231206,
+      "learning_rate": 9.317575866353293e-06,
+      "loss": 0.2724,
+      "step": 132
+    },
+    {
+      "epoch": 4.03030303030303,
+      "grad_norm": 0.7277166782918293,
+      "learning_rate": 9.166246314981066e-06,
+      "loss": 0.2173,
+      "step": 133
+    },
+    {
+      "epoch": 4.0606060606060606,
+      "grad_norm": 0.5882472305139107,
+      "learning_rate": 9.015108802188314e-06,
+      "loss": 0.2279,
+      "step": 134
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.5298145162290456,
+      "learning_rate": 8.86419813949525e-06,
+      "loss": 0.2097,
+      "step": 135
+    },
+    {
+      "epoch": 4.121212121212121,
+      "grad_norm": 0.7622376401983684,
+      "learning_rate": 8.71354908617169e-06,
+      "loss": 0.2114,
+      "step": 136
+    },
+    {
+      "epoch": 4.151515151515151,
+      "grad_norm": 0.8091106259564409,
+      "learning_rate": 8.56319634123092e-06,
+      "loss": 0.2211,
+      "step": 137
+    },
+    {
+      "epoch": 4.181818181818182,
+      "grad_norm": 0.552735676904124,
+      "learning_rate": 8.413174535437486e-06,
+      "loss": 0.2046,
+      "step": 138
+    },
+    {
+      "epoch": 4.212121212121212,
+      "grad_norm": 0.5619974706460401,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.2059,
+      "step": 139
+    },
+    {
+      "epoch": 4.242424242424242,
+      "grad_norm": 0.6022642886123147,
+      "learning_rate": 8.114261875265643e-06,
+      "loss": 0.1994,
+      "step": 140
+    },
+    {
+      "epoch": 4.2727272727272725,
+      "grad_norm": 0.5702540230632025,
+      "learning_rate": 7.965439869473664e-06,
+      "loss": 0.2242,
+      "step": 141
+    },
+    {
+      "epoch": 4.303030303030303,
+      "grad_norm": 0.5722229410713374,
+      "learning_rate": 7.817086484143987e-06,
+      "loss": 0.198,
+      "step": 142
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.5411390812679117,
+      "learning_rate": 7.669235889528436e-06,
+      "loss": 0.2016,
+      "step": 143
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 0.5898502091121667,
+      "learning_rate": 7.521922140071003e-06,
+      "loss": 0.227,
+      "step": 144
+    },
+    {
+      "epoch": 4.393939393939394,
+      "grad_norm": 0.5419999988005103,
+      "learning_rate": 7.375179166564062e-06,
+      "loss": 0.2037,
+      "step": 145
+    },
+    {
+      "epoch": 4.424242424242424,
+      "grad_norm": 0.5255083099684936,
+      "learning_rate": 7.2290407683331154e-06,
+      "loss": 0.1998,
+      "step": 146
+    },
+    {
+      "epoch": 4.454545454545454,
+      "grad_norm": 0.4997836198066876,
+      "learning_rate": 7.0835406054517505e-06,
+      "loss": 0.1984,
+      "step": 147
+    },
+    {
+      "epoch": 4.484848484848484,
+      "grad_norm": 0.5153790148750838,
+      "learning_rate": 6.93871219098876e-06,
+      "loss": 0.1884,
+      "step": 148
+    },
+    {
+      "epoch": 4.515151515151516,
+      "grad_norm": 0.48931878967443426,
+      "learning_rate": 6.79458888328903e-06,
+      "loss": 0.2031,
+      "step": 149
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.5277305274168856,
+      "learning_rate": 6.651203878290139e-06,
+      "loss": 0.1959,
+      "step": 150
+    },
+    {
+      "epoch": 4.575757575757576,
+      "grad_norm": 0.46438939206102664,
+      "learning_rate": 6.508590201876317e-06,
+      "loss": 0.2005,
+      "step": 151
+    },
+    {
+      "epoch": 4.606060606060606,
+      "grad_norm": 0.46881918533467243,
+      "learning_rate": 6.366780702271589e-06,
+      "loss": 0.1928,
+      "step": 152
+    },
+    {
+      "epoch": 4.636363636363637,
+      "grad_norm": 0.4764736017188973,
+      "learning_rate": 6.225808042473857e-06,
+      "loss": 0.1977,
+      "step": 153
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.47046144151353025,
+      "learning_rate": 6.085704692731609e-06,
+      "loss": 0.1988,
+      "step": 154
+    },
+    {
+      "epoch": 4.696969696969697,
+      "grad_norm": 0.4855529970086327,
+      "learning_rate": 5.946502923065054e-06,
+      "loss": 0.2107,
+      "step": 155
+    },
+    {
+      "epoch": 4.7272727272727275,
+      "grad_norm": 0.46000018432335865,
+      "learning_rate": 5.8082347958333625e-06,
+      "loss": 0.2251,
+      "step": 156
+    },
+    {
+      "epoch": 4.757575757575758,
+      "grad_norm": 0.46395250190385995,
+      "learning_rate": 5.670932158349732e-06,
+      "loss": 0.1868,
+      "step": 157
+    },
+    {
+      "epoch": 4.787878787878788,
+      "grad_norm": 0.5087778457525394,
+      "learning_rate": 5.534626635546e-06,
+      "loss": 0.1788,
+      "step": 158
+    },
+    {
+      "epoch": 4.818181818181818,
+      "grad_norm": 0.4795841560481975,
+      "learning_rate": 5.399349622688479e-06,
+      "loss": 0.1982,
+      "step": 159
+    },
+    {
+      "epoch": 4.848484848484849,
+      "grad_norm": 0.4370991242352397,
+      "learning_rate": 5.2651322781466606e-06,
+      "loss": 0.2075,
+      "step": 160
+    },
+    {
+      "epoch": 4.878787878787879,
+      "grad_norm": 0.4293123093795792,
+      "learning_rate": 5.132005516216512e-06,
+      "loss": 0.1988,
+      "step": 161
+    },
+    {
+      "epoch": 4.909090909090909,
+      "grad_norm": 0.5787382975004897,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.1958,
+      "step": 162
+    },
+    {
+      "epoch": 4.9393939393939394,
+      "grad_norm": 0.4574130412997006,
+      "learning_rate": 4.869146134342426e-06,
+      "loss": 0.1899,
+      "step": 163
+    },
+    {
+      "epoch": 4.96969696969697,
+      "grad_norm": 0.4380726185982083,
+      "learning_rate": 4.739474058829288e-06,
+      "loss": 0.1931,
+      "step": 164
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.4539513661465005,
+      "learning_rate": 4.611013640844245e-06,
+      "loss": 0.1958,
+      "step": 165
+    },
+    {
+      "epoch": 5.03030303030303,
+      "grad_norm": 0.5975706051263661,
+      "learning_rate": 4.483794468689728e-06,
+      "loss": 0.1634,
+      "step": 166
+    },
+    {
+      "epoch": 5.0606060606060606,
+      "grad_norm": 0.5308345825385193,
+      "learning_rate": 4.357845844771881e-06,
+      "loss": 0.1484,
+      "step": 167
+    },
+    {
+      "epoch": 5.090909090909091,
+      "grad_norm": 0.4306605521264556,
+      "learning_rate": 4.2331967788513295e-06,
+      "loss": 0.1422,
+      "step": 168
+    },
+    {
+      "epoch": 5.121212121212121,
+      "grad_norm": 0.44799985389855046,
+      "learning_rate": 4.109875981361363e-06,
+      "loss": 0.1326,
+      "step": 169
+    },
+    {
+      "epoch": 5.151515151515151,
+      "grad_norm": 0.5396573031305413,
+      "learning_rate": 3.987911856795047e-06,
+      "loss": 0.1453,
+      "step": 170
+    },
+    {
+      "epoch": 5.181818181818182,
+      "grad_norm": 0.6258082214119879,
+      "learning_rate": 3.867332497162836e-06,
+      "loss": 0.1398,
+      "step": 171
+    },
+    {
+      "epoch": 5.212121212121212,
+      "grad_norm": 0.6066507081440136,
+      "learning_rate": 3.748165675522113e-06,
+      "loss": 0.1392,
+      "step": 172
+    },
+    {
+      "epoch": 5.242424242424242,
+      "grad_norm": 0.5232848536220339,
+      "learning_rate": 3.630438839580217e-06,
+      "loss": 0.1397,
+      "step": 173
+    },
+    {
+      "epoch": 5.2727272727272725,
+      "grad_norm": 0.4720769063490613,
+      "learning_rate": 3.5141791053724405e-06,
+      "loss": 0.1414,
+      "step": 174
+    },
+    {
+      "epoch": 5.303030303030303,
+      "grad_norm": 0.4592538846411448,
+      "learning_rate": 3.399413251016359e-06,
+      "loss": 0.1363,
+      "step": 175
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.4314115482649703,
+      "learning_rate": 3.2861677105440335e-06,
+      "loss": 0.1379,
+      "step": 176
+    },
+    {
+      "epoch": 5.363636363636363,
+      "grad_norm": 0.4183800342884364,
+      "learning_rate": 3.174468567813461e-06,
+      "loss": 0.1326,
+      "step": 177
+    },
+    {
+      "epoch": 5.393939393939394,
+      "grad_norm": 0.43272870332998015,
+      "learning_rate": 3.0643415505006733e-06,
+      "loss": 0.1295,
+      "step": 178
+    },
+    {
+      "epoch": 5.424242424242424,
+      "grad_norm": 0.4318367293901279,
+      "learning_rate": 2.9558120241738786e-06,
+      "loss": 0.1283,
+      "step": 179
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.44965374722824286,
+      "learning_rate": 2.8489049864510053e-06,
+      "loss": 0.1466,
+      "step": 180
+    },
+    {
+      "epoch": 5.484848484848484,
+      "grad_norm": 0.4069977439485942,
+      "learning_rate": 2.7436450612420098e-06,
+      "loss": 0.1517,
+      "step": 181
+    },
+    {
+      "epoch": 5.515151515151516,
+      "grad_norm": 0.39337556446353444,
+      "learning_rate": 2.640056493077231e-06,
+      "loss": 0.1292,
+      "step": 182
+    },
+    {
+      "epoch": 5.545454545454545,
+      "grad_norm": 0.4207085912362768,
+      "learning_rate": 2.5381631415231455e-06,
+      "loss": 0.1299,
+      "step": 183
+    },
+    {
+      "epoch": 5.575757575757576,
+      "grad_norm": 0.4592367809245842,
+      "learning_rate": 2.4379884756868167e-06,
+      "loss": 0.136,
+      "step": 184
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 0.4292783238689395,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.1297,
+      "step": 185
+    },
+    {
+      "epoch": 5.636363636363637,
+      "grad_norm": 0.4369252482459367,
+      "learning_rate": 2.2428870929558012e-06,
+      "loss": 0.1311,
+      "step": 186
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 0.4298607160404583,
+      "learning_rate": 2.1480053137844115e-06,
+      "loss": 0.1414,
+      "step": 187
+    },
+    {
+      "epoch": 5.696969696969697,
+      "grad_norm": 0.44145537137502966,
+      "learning_rate": 2.054932085426856e-06,
+      "loss": 0.1407,
+      "step": 188
+    },
+    {
+      "epoch": 5.7272727272727275,
+      "grad_norm": 0.3968739541513693,
+      "learning_rate": 1.963688845450218e-06,
+      "loss": 0.1422,
+      "step": 189
+    },
+    {
+      "epoch": 5.757575757575758,
+      "grad_norm": 0.41925298626523944,
+      "learning_rate": 1.8742966099201699e-06,
+      "loss": 0.136,
+      "step": 190
+    },
+    {
+      "epoch": 5.787878787878788,
+      "grad_norm": 0.4084034837164202,
+      "learning_rate": 1.7867759685603115e-06,
+      "loss": 0.1571,
+      "step": 191
+    },
+    {
+      "epoch": 5.818181818181818,
+      "grad_norm": 0.37618501943941296,
+      "learning_rate": 1.7011470800097496e-06,
+      "loss": 0.1258,
+      "step": 192
+    },
+    {
+      "epoch": 5.848484848484849,
+      "grad_norm": 0.39252498544081876,
+      "learning_rate": 1.6174296671799571e-06,
+      "loss": 0.1233,
+      "step": 193
+    },
+    {
+      "epoch": 5.878787878787879,
+      "grad_norm": 0.40389203534972906,
+      "learning_rate": 1.5356430127119915e-06,
+      "loss": 0.1328,
+      "step": 194
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 0.40549008704684514,
+      "learning_rate": 1.4558059545351144e-06,
+      "loss": 0.1373,
+      "step": 195
+    },
+    {
+      "epoch": 5.9393939393939394,
+      "grad_norm": 0.3999848448814429,
+      "learning_rate": 1.3779368815278648e-06,
+      "loss": 0.1378,
+      "step": 196
+    },
+    {
+      "epoch": 5.96969696969697,
+      "grad_norm": 0.4161486440331444,
+      "learning_rate": 1.302053729282533e-06,
+      "loss": 0.1366,
+      "step": 197
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.4114995630693783,
+      "learning_rate": 1.2281739759740575e-06,
+      "loss": 0.1365,
+      "step": 198
+    },
+    {
+      "epoch": 6.03030303030303,
+      "grad_norm": 0.432622913410847,
+      "learning_rate": 1.156314638334277e-06,
+      "loss": 0.1209,
+      "step": 199
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "grad_norm": 0.44266928378283915,
+      "learning_rate": 1.086492267732462e-06,
+      "loss": 0.1189,
+      "step": 200
+    },
+    {
+      "epoch": 6.090909090909091,
+      "grad_norm": 0.40020191270495875,
+      "learning_rate": 1.01872294636304e-06,
+      "loss": 0.108,
+      "step": 201
+    },
+    {
+      "epoch": 6.121212121212121,
+      "grad_norm": 0.40940444298781203,
+      "learning_rate": 9.530222835413739e-07,
+      "loss": 0.1067,
+      "step": 202
+    },
+    {
+      "epoch": 6.151515151515151,
+      "grad_norm": 0.3694176417338478,
+      "learning_rate": 8.894054121084839e-07,
+      "loss": 0.1154,
+      "step": 203
+    },
+    {
+      "epoch": 6.181818181818182,
+      "grad_norm": 0.3512238164978757,
+      "learning_rate": 8.278869849454718e-07,
+      "loss": 0.1106,
+      "step": 204
+    },
+    {
+      "epoch": 6.212121212121212,
+      "grad_norm": 0.3572165347480285,
+      "learning_rate": 7.684811715985429e-07,
+      "loss": 0.1059,
+      "step": 205
+    },
+    {
+      "epoch": 6.242424242424242,
+      "grad_norm": 0.34746945972713617,
+      "learning_rate": 7.1120165501533e-07,
+      "loss": 0.1035,
+      "step": 206
+    },
+    {
+      "epoch": 6.2727272727272725,
+      "grad_norm": 0.331349142326655,
+      "learning_rate": 6.560616283932897e-07,
+      "loss": 0.1095,
+      "step": 207
+    },
+    {
+      "epoch": 6.303030303030303,
+      "grad_norm": 0.41627031545081433,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.1,
+      "step": 208
+    },
+    {
+      "epoch": 6.333333333333333,
+      "grad_norm": 0.3703896686565648,
+      "learning_rate": 5.522503509524591e-07,
+      "loss": 0.1064,
+      "step": 209
+    },
+    {
+      "epoch": 6.363636363636363,
+      "grad_norm": 0.39260491910249645,
+      "learning_rate": 5.036030109968082e-07,
+      "loss": 0.1172,
+      "step": 210
+    },
+    {
+      "epoch": 6.393939393939394,
+      "grad_norm": 0.37440287555335755,
+      "learning_rate": 4.5714297722121105e-07,
+      "loss": 0.1123,
+      "step": 211
+    },
+    {
+      "epoch": 6.424242424242424,
+      "grad_norm": 0.4282474761319765,
+      "learning_rate": 4.128809507704445e-07,
+      "loss": 0.1197,
+      "step": 212
+    },
+    {
+      "epoch": 6.454545454545454,
+      "grad_norm": 0.3633684114874979,
+      "learning_rate": 3.708271265220087e-07,
+      "loss": 0.1144,
+      "step": 213
+    },
+    {
+      "epoch": 6.484848484848484,
+      "grad_norm": 0.38411665635234393,
+      "learning_rate": 3.309911907379393e-07,
+      "loss": 0.1255,
+      "step": 214
+    },
+    {
+      "epoch": 6.515151515151516,
+      "grad_norm": 0.374091633669975,
+      "learning_rate": 2.9338231883378365e-07,
+      "loss": 0.1204,
+      "step": 215
+    },
+    {
+      "epoch": 6.545454545454545,
+      "grad_norm": 0.37109340802594226,
+      "learning_rate": 2.5800917326521013e-07,
+      "loss": 0.1042,
+      "step": 216
+    },
+    {
+      "epoch": 6.575757575757576,
+      "grad_norm": 0.35478388580467535,
+      "learning_rate": 2.248799015327907e-07,
+      "loss": 0.1104,
+      "step": 217
+    },
+    {
+      "epoch": 6.606060606060606,
+      "grad_norm": 0.3885722436279484,
+      "learning_rate": 1.9400213430538773e-07,
+      "loss": 0.1165,
+      "step": 218
+    },
+    {
+      "epoch": 6.636363636363637,
+      "grad_norm": 0.37371970260395854,
+      "learning_rate": 1.6538298366257975e-07,
+      "loss": 0.1262,
+      "step": 219
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.3903538774663792,
+      "learning_rate": 1.3902904145653094e-07,
+      "loss": 0.1175,
+      "step": 220
+    },
+    {
+      "epoch": 6.696969696969697,
+      "grad_norm": 0.3610511715229448,
+      "learning_rate": 1.1494637779369766e-07,
+      "loss": 0.0973,
+      "step": 221
+    },
+    {
+      "epoch": 6.7272727272727275,
+      "grad_norm": 0.3628989645199989,
+      "learning_rate": 9.314053963669245e-08,
+      "loss": 0.1053,
+      "step": 222
+    },
+    {
+      "epoch": 6.757575757575758,
+      "grad_norm": 0.34183166951991567,
+      "learning_rate": 7.361654952665608e-08,
+      "loss": 0.1035,
+      "step": 223
+    },
+    {
+      "epoch": 6.787878787878788,
+      "grad_norm": 0.34550763956865527,
+      "learning_rate": 5.637890442641403e-08,
+      "loss": 0.1115,
+      "step": 224
+    },
+    {
+      "epoch": 6.818181818181818,
+      "grad_norm": 0.3560200973058206,
+      "learning_rate": 4.143157468468717e-08,
+      "loss": 0.1065,
+      "step": 225
+    },
+    {
+      "epoch": 6.848484848484849,
+      "grad_norm": 0.3700351136531262,
+      "learning_rate": 2.8778003121607834e-08,
+      "loss": 0.119,
+      "step": 226
+    },
+    {
+      "epoch": 6.878787878787879,
+      "grad_norm": 0.38171282360266545,
+      "learning_rate": 1.8421104235727406e-08,
+      "loss": 0.1187,
+      "step": 227
+    },
+    {
+      "epoch": 6.909090909090909,
+      "grad_norm": 0.3571610695253175,
+      "learning_rate": 1.0363263532724433e-08,
+      "loss": 0.1111,
+      "step": 228
+    },
+    {
+      "epoch": 6.9393939393939394,
+      "grad_norm": 0.36033729473264947,
+      "learning_rate": 4.606336975948589e-09,
+      "loss": 0.103,
+      "step": 229
+    },
+    {
+      "epoch": 6.96969696969697,
+      "grad_norm": 0.3348421864242949,
+      "learning_rate": 1.1516505589381777e-09,
+      "loss": 0.1124,
+      "step": 230
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.32938291762287747,
+      "learning_rate": 0.0,
+      "loss": 0.1079,
+      "step": 231
+    },
+    {
+      "epoch": 7.0,
+      "step": 231,
+      "total_flos": 2.7774205071405875e+17,
+      "train_loss": 0.363200804404108,
+      "train_runtime": 5432.6588,
+      "train_samples_per_second": 4.072,
+      "train_steps_per_second": 0.043
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 231,
+  "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": 2.7774205071405875e+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 sha256:2e5fb0c0ddf7cfb4e615ef8333eddf26c4c7842e352c79dd3eb61ad83809460b
+size 7352