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: b2_code_fasttext_pos_all_neg_sql_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. -->
+
+# b2_code_fasttext_pos_all_neg_sql_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/b2_code_fasttext_pos_all_neg_sql_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": 6.103710830103101e+17,
+    "train_loss": 0.5184378920695483,
+    "train_runtime": 8807.9751,
+    "train_samples_per_second": 2.511,
+    "train_steps_per_second": 0.026
+}

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 sha256:068f5892830a355c0179592f16d51c76d3ff3d41ba4d5cd032b75d095bbe477e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9eea9bae7e1f973762a02cdd48ad274080ab86736e6a5418cc7f03ceec10d7
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f4c5e9491d1331db3e81cd6ab3693443b5b237e73b46ba605b56a8bad01add
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1a0a5f4b25d09d827e4410be5362da87dc62017354b7cd6c0b53e90de8886a
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

runs/Apr26_18-28-38_jpbot-001-16.jupiter.internal/events.out.tfevents.1745684953.jpbot-001-16.jupiter.internal.1648139.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ff809c9fcdd45fa019bfb635a808e4d3bc875da7fc4290efce0398a5dd853d3
+size 54177

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-26 18:28:38", "end_time": "2025-04-26 20:56:09"}

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": 6.103710830103101e+17,
+    "train_loss": 0.5184378920695483,
+    "train_runtime": 8807.9751,
+    "train_samples_per_second": 2.511,
+    "train_steps_per_second": 0.026
+}

trainer_log.jsonl

@@ -0,0 +1,232 @@
+{"current_steps": 1, "total_steps": 231, "loss": 1.0455, "lr": 8.333333333333333e-07, "epoch": 0.030303030303030304, "percentage": 0.43, "elapsed_time": "0:00:53", "remaining_time": "3:24:08"}
+{"current_steps": 2, "total_steps": 231, "loss": 1.0538, "lr": 1.6666666666666667e-06, "epoch": 0.06060606060606061, "percentage": 0.87, "elapsed_time": "0:01:31", "remaining_time": "2:53:56"}
+{"current_steps": 3, "total_steps": 231, "loss": 1.0183, "lr": 2.5e-06, "epoch": 0.09090909090909091, "percentage": 1.3, "elapsed_time": "0:02:10", "remaining_time": "2:45:04"}
+{"current_steps": 4, "total_steps": 231, "loss": 1.0403, "lr": 3.3333333333333333e-06, "epoch": 0.12121212121212122, "percentage": 1.73, "elapsed_time": "0:02:44", "remaining_time": "2:35:40"}
+{"current_steps": 5, "total_steps": 231, "loss": 1.0087, "lr": 4.166666666666667e-06, "epoch": 0.15151515151515152, "percentage": 2.16, "elapsed_time": "0:03:25", "remaining_time": "2:34:56"}
+{"current_steps": 6, "total_steps": 231, "loss": 0.9609, "lr": 5e-06, "epoch": 0.18181818181818182, "percentage": 2.6, "elapsed_time": "0:04:04", "remaining_time": "2:32:33"}
+{"current_steps": 7, "total_steps": 231, "loss": 0.9351, "lr": 5.833333333333334e-06, "epoch": 0.21212121212121213, "percentage": 3.03, "elapsed_time": "0:04:40", "remaining_time": "2:29:29"}
+{"current_steps": 8, "total_steps": 231, "loss": 0.9216, "lr": 6.666666666666667e-06, "epoch": 0.24242424242424243, "percentage": 3.46, "elapsed_time": "0:05:18", "remaining_time": "2:27:45"}
+{"current_steps": 9, "total_steps": 231, "loss": 0.9455, "lr": 7.500000000000001e-06, "epoch": 0.2727272727272727, "percentage": 3.9, "elapsed_time": "0:05:57", "remaining_time": "2:27:05"}
+{"current_steps": 10, "total_steps": 231, "loss": 0.9028, "lr": 8.333333333333334e-06, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "0:06:39", "remaining_time": "2:27:14"}
+{"current_steps": 11, "total_steps": 231, "loss": 0.8936, "lr": 9.166666666666666e-06, "epoch": 0.3333333333333333, "percentage": 4.76, "elapsed_time": "0:07:19", "remaining_time": "2:26:26"}
+{"current_steps": 12, "total_steps": 231, "loss": 0.8668, "lr": 1e-05, "epoch": 0.36363636363636365, "percentage": 5.19, "elapsed_time": "0:07:57", "remaining_time": "2:25:06"}
+{"current_steps": 13, "total_steps": 231, "loss": 0.8486, "lr": 1.0833333333333334e-05, "epoch": 0.3939393939393939, "percentage": 5.63, "elapsed_time": "0:08:35", "remaining_time": "2:24:12"}
+{"current_steps": 14, "total_steps": 231, "loss": 0.8195, "lr": 1.1666666666666668e-05, "epoch": 0.42424242424242425, "percentage": 6.06, "elapsed_time": "0:09:09", "remaining_time": "2:21:58"}
+{"current_steps": 15, "total_steps": 231, "loss": 0.7993, "lr": 1.25e-05, "epoch": 0.45454545454545453, "percentage": 6.49, "elapsed_time": "0:09:44", "remaining_time": "2:20:12"}
+{"current_steps": 16, "total_steps": 231, "loss": 0.7693, "lr": 1.3333333333333333e-05, "epoch": 0.48484848484848486, "percentage": 6.93, "elapsed_time": "0:10:23", "remaining_time": "2:19:44"}
+{"current_steps": 17, "total_steps": 231, "loss": 0.7884, "lr": 1.416666666666667e-05, "epoch": 0.5151515151515151, "percentage": 7.36, "elapsed_time": "0:11:03", "remaining_time": "2:19:15"}
+{"current_steps": 18, "total_steps": 231, "loss": 0.7686, "lr": 1.5000000000000002e-05, "epoch": 0.5454545454545454, "percentage": 7.79, "elapsed_time": "0:11:43", "remaining_time": "2:18:49"}
+{"current_steps": 19, "total_steps": 231, "loss": 0.7386, "lr": 1.5833333333333333e-05, "epoch": 0.5757575757575758, "percentage": 8.23, "elapsed_time": "0:12:18", "remaining_time": "2:17:23"}
+{"current_steps": 20, "total_steps": 231, "loss": 0.759, "lr": 1.6666666666666667e-05, "epoch": 0.6060606060606061, "percentage": 8.66, "elapsed_time": "0:12:57", "remaining_time": "2:16:42"}
+{"current_steps": 21, "total_steps": 231, "loss": 0.7453, "lr": 1.7500000000000002e-05, "epoch": 0.6363636363636364, "percentage": 9.09, "elapsed_time": "0:13:31", "remaining_time": "2:15:12"}
+{"current_steps": 22, "total_steps": 231, "loss": 0.7493, "lr": 1.8333333333333333e-05, "epoch": 0.6666666666666666, "percentage": 9.52, "elapsed_time": "0:14:08", "remaining_time": "2:14:25"}
+{"current_steps": 23, "total_steps": 231, "loss": 0.7069, "lr": 1.916666666666667e-05, "epoch": 0.696969696969697, "percentage": 9.96, "elapsed_time": "0:14:46", "remaining_time": "2:13:37"}
+{"current_steps": 24, "total_steps": 231, "loss": 0.7274, "lr": 2e-05, "epoch": 0.7272727272727273, "percentage": 10.39, "elapsed_time": "0:15:24", "remaining_time": "2:12:50"}
+{"current_steps": 25, "total_steps": 231, "loss": 0.7113, "lr": 1.999884834944106e-05, "epoch": 0.7575757575757576, "percentage": 10.82, "elapsed_time": "0:15:59", "remaining_time": "2:11:44"}
+{"current_steps": 26, "total_steps": 231, "loss": 0.7339, "lr": 1.9995393663024054e-05, "epoch": 0.7878787878787878, "percentage": 11.26, "elapsed_time": "0:16:33", "remaining_time": "2:10:31"}
+{"current_steps": 27, "total_steps": 231, "loss": 0.7404, "lr": 1.9989636736467278e-05, "epoch": 0.8181818181818182, "percentage": 11.69, "elapsed_time": "0:17:07", "remaining_time": "2:09:25"}
+{"current_steps": 28, "total_steps": 231, "loss": 0.7325, "lr": 1.9981578895764272e-05, "epoch": 0.8484848484848485, "percentage": 12.12, "elapsed_time": "0:17:46", "remaining_time": "2:08:52"}
+{"current_steps": 29, "total_steps": 231, "loss": 0.698, "lr": 1.9971221996878395e-05, "epoch": 0.8787878787878788, "percentage": 12.55, "elapsed_time": "0:18:23", "remaining_time": "2:08:07"}
+{"current_steps": 30, "total_steps": 231, "loss": 0.7074, "lr": 1.9958568425315316e-05, "epoch": 0.9090909090909091, "percentage": 12.99, "elapsed_time": "0:18:56", "remaining_time": "2:06:56"}
+{"current_steps": 31, "total_steps": 231, "loss": 0.6983, "lr": 1.9943621095573588e-05, "epoch": 0.9393939393939394, "percentage": 13.42, "elapsed_time": "0:19:34", "remaining_time": "2:06:17"}
+{"current_steps": 32, "total_steps": 231, "loss": 0.7091, "lr": 1.9926383450473344e-05, "epoch": 0.9696969696969697, "percentage": 13.85, "elapsed_time": "0:20:13", "remaining_time": "2:05:49"}
+{"current_steps": 33, "total_steps": 231, "loss": 0.7099, "lr": 1.9906859460363307e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:20:51", "remaining_time": "2:05:09"}
+{"current_steps": 34, "total_steps": 231, "loss": 0.6775, "lr": 1.9885053622206305e-05, "epoch": 1.0303030303030303, "percentage": 14.72, "elapsed_time": "0:23:45", "remaining_time": "2:17:41"}
+{"current_steps": 35, "total_steps": 231, "loss": 0.6599, "lr": 1.986097095854347e-05, "epoch": 1.0606060606060606, "percentage": 15.15, "elapsed_time": "0:24:21", "remaining_time": "2:16:25"}
+{"current_steps": 36, "total_steps": 231, "loss": 0.6543, "lr": 1.9834617016337424e-05, "epoch": 1.0909090909090908, "percentage": 15.58, "elapsed_time": "0:24:57", "remaining_time": "2:15:10"}
+{"current_steps": 37, "total_steps": 231, "loss": 0.6522, "lr": 1.9805997865694616e-05, "epoch": 1.121212121212121, "percentage": 16.02, "elapsed_time": "0:25:36", "remaining_time": "2:14:15"}
+{"current_steps": 38, "total_steps": 231, "loss": 0.6342, "lr": 1.9775120098467212e-05, "epoch": 1.1515151515151516, "percentage": 16.45, "elapsed_time": "0:26:10", "remaining_time": "2:12:58"}
+{"current_steps": 39, "total_steps": 231, "loss": 0.6499, "lr": 1.9741990826734793e-05, "epoch": 1.1818181818181819, "percentage": 16.88, "elapsed_time": "0:26:47", "remaining_time": "2:11:52"}
+{"current_steps": 40, "total_steps": 231, "loss": 0.6368, "lr": 1.970661768116622e-05, "epoch": 1.2121212121212122, "percentage": 17.32, "elapsed_time": "0:27:23", "remaining_time": "2:10:47"}
+{"current_steps": 41, "total_steps": 231, "loss": 0.6359, "lr": 1.9669008809262064e-05, "epoch": 1.2424242424242424, "percentage": 17.75, "elapsed_time": "0:28:00", "remaining_time": "2:09:49"}
+{"current_steps": 42, "total_steps": 231, "loss": 0.6415, "lr": 1.9629172873477995e-05, "epoch": 1.2727272727272727, "percentage": 18.18, "elapsed_time": "0:28:36", "remaining_time": "2:08:46"}
+{"current_steps": 43, "total_steps": 231, "loss": 0.642, "lr": 1.9587119049229558e-05, "epoch": 1.303030303030303, "percentage": 18.61, "elapsed_time": "0:29:14", "remaining_time": "2:07:52"}
+{"current_steps": 44, "total_steps": 231, "loss": 0.6355, "lr": 1.954285702277879e-05, "epoch": 1.3333333333333333, "percentage": 19.05, "elapsed_time": "0:29:52", "remaining_time": "2:06:58"}
+{"current_steps": 45, "total_steps": 231, "loss": 0.6293, "lr": 1.9496396989003195e-05, "epoch": 1.3636363636363638, "percentage": 19.48, "elapsed_time": "0:30:29", "remaining_time": "2:06:00"}
+{"current_steps": 46, "total_steps": 231, "loss": 0.634, "lr": 1.944774964904754e-05, "epoch": 1.393939393939394, "percentage": 19.91, "elapsed_time": "0:31:05", "remaining_time": "2:05:01"}
+{"current_steps": 47, "total_steps": 231, "loss": 0.6254, "lr": 1.9396926207859085e-05, "epoch": 1.4242424242424243, "percentage": 20.35, "elapsed_time": "0:31:46", "remaining_time": "2:04:24"}
+{"current_steps": 48, "total_steps": 231, "loss": 0.6221, "lr": 1.9343938371606714e-05, "epoch": 1.4545454545454546, "percentage": 20.78, "elapsed_time": "0:32:20", "remaining_time": "2:03:18"}
+{"current_steps": 49, "total_steps": 231, "loss": 0.6386, "lr": 1.9288798344984673e-05, "epoch": 1.4848484848484849, "percentage": 21.21, "elapsed_time": "0:33:01", "remaining_time": "2:02:38"}
+{"current_steps": 50, "total_steps": 231, "loss": 0.629, "lr": 1.9231518828401458e-05, "epoch": 1.5151515151515151, "percentage": 21.65, "elapsed_time": "0:33:40", "remaining_time": "2:01:55"}
+{"current_steps": 51, "total_steps": 231, "loss": 0.6266, "lr": 1.917211301505453e-05, "epoch": 1.5454545454545454, "percentage": 22.08, "elapsed_time": "0:34:14", "remaining_time": "2:00:51"}
+{"current_steps": 52, "total_steps": 231, "loss": 0.6237, "lr": 1.911059458789152e-05, "epoch": 1.5757575757575757, "percentage": 22.51, "elapsed_time": "0:34:50", "remaining_time": "1:59:54"}
+{"current_steps": 53, "total_steps": 231, "loss": 0.6219, "lr": 1.9046977716458627e-05, "epoch": 1.606060606060606, "percentage": 22.94, "elapsed_time": "0:35:26", "remaining_time": "1:59:02"}
+{"current_steps": 54, "total_steps": 231, "loss": 0.6221, "lr": 1.8981277053636963e-05, "epoch": 1.6363636363636362, "percentage": 23.38, "elapsed_time": "0:36:04", "remaining_time": "1:58:14"}
+{"current_steps": 55, "total_steps": 231, "loss": 0.628, "lr": 1.891350773226754e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "0:36:42", "remaining_time": "1:57:27"}
+{"current_steps": 56, "total_steps": 231, "loss": 0.6181, "lr": 1.8843685361665724e-05, "epoch": 1.696969696969697, "percentage": 24.24, "elapsed_time": "0:37:18", "remaining_time": "1:56:34"}
+{"current_steps": 57, "total_steps": 231, "loss": 0.6269, "lr": 1.8771826024025944e-05, "epoch": 1.7272727272727273, "percentage": 24.68, "elapsed_time": "0:37:56", "remaining_time": "1:55:48"}
+{"current_steps": 58, "total_steps": 231, "loss": 0.6265, "lr": 1.8697946270717468e-05, "epoch": 1.7575757575757576, "percentage": 25.11, "elapsed_time": "0:38:33", "remaining_time": "1:55:00"}
+{"current_steps": 59, "total_steps": 231, "loss": 0.6516, "lr": 1.8622063118472135e-05, "epoch": 1.7878787878787878, "percentage": 25.54, "elapsed_time": "0:39:12", "remaining_time": "1:54:17"}
+{"current_steps": 60, "total_steps": 231, "loss": 0.6098, "lr": 1.8544194045464888e-05, "epoch": 1.8181818181818183, "percentage": 25.97, "elapsed_time": "0:39:49", "remaining_time": "1:53:28"}
+{"current_steps": 61, "total_steps": 231, "loss": 0.6041, "lr": 1.8464356987288012e-05, "epoch": 1.8484848484848486, "percentage": 26.41, "elapsed_time": "0:40:26", "remaining_time": "1:52:43"}
+{"current_steps": 62, "total_steps": 231, "loss": 0.6145, "lr": 1.8382570332820045e-05, "epoch": 1.878787878787879, "percentage": 26.84, "elapsed_time": "0:41:04", "remaining_time": "1:51:57"}
+{"current_steps": 63, "total_steps": 231, "loss": 0.6163, "lr": 1.8298852919990254e-05, "epoch": 1.9090909090909092, "percentage": 27.27, "elapsed_time": "0:41:41", "remaining_time": "1:51:11"}
+{"current_steps": 64, "total_steps": 231, "loss": 0.6242, "lr": 1.821322403143969e-05, "epoch": 1.9393939393939394, "percentage": 27.71, "elapsed_time": "0:42:15", "remaining_time": "1:50:16"}
+{"current_steps": 65, "total_steps": 231, "loss": 0.6178, "lr": 1.812570339007983e-05, "epoch": 1.9696969696969697, "percentage": 28.14, "elapsed_time": "0:42:52", "remaining_time": "1:49:30"}
+{"current_steps": 66, "total_steps": 231, "loss": 0.6288, "lr": 1.8036311154549783e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "0:43:30", "remaining_time": "1:48:47"}
+{"current_steps": 67, "total_steps": 231, "loss": 0.5725, "lr": 1.7945067914573147e-05, "epoch": 2.0303030303030303, "percentage": 29.0, "elapsed_time": "0:44:19", "remaining_time": "1:48:28"}
+{"current_steps": 68, "total_steps": 231, "loss": 0.5746, "lr": 1.7851994686215592e-05, "epoch": 2.0606060606060606, "percentage": 29.44, "elapsed_time": "0:44:57", "remaining_time": "1:47:46"}
+{"current_steps": 69, "total_steps": 231, "loss": 0.5565, "lr": 1.77571129070442e-05, "epoch": 2.090909090909091, "percentage": 29.87, "elapsed_time": "0:45:34", "remaining_time": "1:47:00"}
+{"current_steps": 70, "total_steps": 231, "loss": 0.5548, "lr": 1.766044443118978e-05, "epoch": 2.121212121212121, "percentage": 30.3, "elapsed_time": "0:46:10", "remaining_time": "1:46:12"}
+{"current_steps": 71, "total_steps": 231, "loss": 0.561, "lr": 1.7562011524313187e-05, "epoch": 2.1515151515151514, "percentage": 30.74, "elapsed_time": "0:46:45", "remaining_time": "1:45:23"}
+{"current_steps": 72, "total_steps": 231, "loss": 0.564, "lr": 1.7461836858476858e-05, "epoch": 2.1818181818181817, "percentage": 31.17, "elapsed_time": "0:47:18", "remaining_time": "1:44:29"}
+{"current_steps": 73, "total_steps": 231, "loss": 0.564, "lr": 1.7359943506922775e-05, "epoch": 2.212121212121212, "percentage": 31.6, "elapsed_time": "0:47:57", "remaining_time": "1:43:47"}
+{"current_steps": 74, "total_steps": 231, "loss": 0.5297, "lr": 1.725635493875799e-05, "epoch": 2.242424242424242, "percentage": 32.03, "elapsed_time": "0:48:35", "remaining_time": "1:43:05"}
+{"current_steps": 75, "total_steps": 231, "loss": 0.551, "lr": 1.7151095013548996e-05, "epoch": 2.2727272727272725, "percentage": 32.47, "elapsed_time": "0:49:13", "remaining_time": "1:42:23"}
+{"current_steps": 76, "total_steps": 231, "loss": 0.5455, "lr": 1.7044187975826126e-05, "epoch": 2.303030303030303, "percentage": 32.9, "elapsed_time": "0:49:50", "remaining_time": "1:41:39"}
+{"current_steps": 77, "total_steps": 231, "loss": 0.5364, "lr": 1.693565844949933e-05, "epoch": 2.3333333333333335, "percentage": 33.33, "elapsed_time": "0:50:23", "remaining_time": "1:40:47"}
+{"current_steps": 78, "total_steps": 231, "loss": 0.5404, "lr": 1.6825531432186545e-05, "epoch": 2.3636363636363638, "percentage": 33.77, "elapsed_time": "0:51:01", "remaining_time": "1:40:05"}
+{"current_steps": 79, "total_steps": 231, "loss": 0.5349, "lr": 1.671383228945597e-05, "epoch": 2.393939393939394, "percentage": 34.2, "elapsed_time": "0:51:37", "remaining_time": "1:39:19"}
+{"current_steps": 80, "total_steps": 231, "loss": 0.5378, "lr": 1.6600586748983642e-05, "epoch": 2.4242424242424243, "percentage": 34.63, "elapsed_time": "0:52:15", "remaining_time": "1:38:38"}
+{"current_steps": 81, "total_steps": 231, "loss": 0.5573, "lr": 1.648582089462756e-05, "epoch": 2.4545454545454546, "percentage": 35.06, "elapsed_time": "0:52:51", "remaining_time": "1:37:53"}
+{"current_steps": 82, "total_steps": 231, "loss": 0.5474, "lr": 1.6369561160419783e-05, "epoch": 2.484848484848485, "percentage": 35.5, "elapsed_time": "0:53:28", "remaining_time": "1:37:10"}
+{"current_steps": 83, "total_steps": 231, "loss": 0.548, "lr": 1.625183432447789e-05, "epoch": 2.515151515151515, "percentage": 35.93, "elapsed_time": "0:54:05", "remaining_time": "1:36:26"}
+{"current_steps": 84, "total_steps": 231, "loss": 0.5573, "lr": 1.6132667502837164e-05, "epoch": 2.5454545454545454, "percentage": 36.36, "elapsed_time": "0:54:43", "remaining_time": "1:35:45"}
+{"current_steps": 85, "total_steps": 231, "loss": 0.5383, "lr": 1.6012088143204953e-05, "epoch": 2.5757575757575757, "percentage": 36.8, "elapsed_time": "0:55:19", "remaining_time": "1:35:02"}
+{"current_steps": 86, "total_steps": 231, "loss": 0.5431, "lr": 1.589012401863864e-05, "epoch": 2.606060606060606, "percentage": 37.23, "elapsed_time": "0:55:54", "remaining_time": "1:34:15"}
+{"current_steps": 87, "total_steps": 231, "loss": 0.5516, "lr": 1.5766803221148676e-05, "epoch": 2.6363636363636362, "percentage": 37.66, "elapsed_time": "0:56:30", "remaining_time": "1:33:32"}
+{"current_steps": 88, "total_steps": 231, "loss": 0.5284, "lr": 1.5642154155228124e-05, "epoch": 2.6666666666666665, "percentage": 38.1, "elapsed_time": "0:57:07", "remaining_time": "1:32:50"}
+{"current_steps": 89, "total_steps": 231, "loss": 0.5537, "lr": 1.5516205531310272e-05, "epoch": 2.6969696969696972, "percentage": 38.53, "elapsed_time": "0:57:43", "remaining_time": "1:32:05"}
+{"current_steps": 90, "total_steps": 231, "loss": 0.5486, "lr": 1.538898635915576e-05, "epoch": 2.7272727272727275, "percentage": 38.96, "elapsed_time": "0:58:19", "remaining_time": "1:31:22"}
+{"current_steps": 91, "total_steps": 231, "loss": 0.5453, "lr": 1.526052594117071e-05, "epoch": 2.757575757575758, "percentage": 39.39, "elapsed_time": "0:58:55", "remaining_time": "1:30:38"}
+{"current_steps": 92, "total_steps": 231, "loss": 0.5546, "lr": 1.513085386565758e-05, "epoch": 2.787878787878788, "percentage": 39.83, "elapsed_time": "0:59:32", "remaining_time": "1:29:56"}
+{"current_steps": 93, "total_steps": 231, "loss": 0.5382, "lr": 1.5000000000000002e-05, "epoch": 2.8181818181818183, "percentage": 40.26, "elapsed_time": "1:00:09", "remaining_time": "1:29:16"}
+{"current_steps": 94, "total_steps": 231, "loss": 0.5484, "lr": 1.4867994483783485e-05, "epoch": 2.8484848484848486, "percentage": 40.69, "elapsed_time": "1:00:46", "remaining_time": "1:28:34"}
+{"current_steps": 95, "total_steps": 231, "loss": 0.5417, "lr": 1.4734867721853341e-05, "epoch": 2.878787878787879, "percentage": 41.13, "elapsed_time": "1:01:24", "remaining_time": "1:27:54"}
+{"current_steps": 96, "total_steps": 231, "loss": 0.55, "lr": 1.4600650377311523e-05, "epoch": 2.909090909090909, "percentage": 41.56, "elapsed_time": "1:02:00", "remaining_time": "1:27:12"}
+{"current_steps": 97, "total_steps": 231, "loss": 0.5603, "lr": 1.4465373364454001e-05, "epoch": 2.9393939393939394, "percentage": 41.99, "elapsed_time": "1:02:39", "remaining_time": "1:26:34"}
+{"current_steps": 98, "total_steps": 231, "loss": 0.537, "lr": 1.4329067841650274e-05, "epoch": 2.9696969696969697, "percentage": 42.42, "elapsed_time": "1:03:15", "remaining_time": "1:25:51"}
+{"current_steps": 99, "total_steps": 231, "loss": 0.545, "lr": 1.4191765204166643e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "1:03:53", "remaining_time": "1:25:11"}
+{"current_steps": 100, "total_steps": 231, "loss": 0.4968, "lr": 1.4053497076934948e-05, "epoch": 3.0303030303030303, "percentage": 43.29, "elapsed_time": "1:04:48", "remaining_time": "1:24:53"}
+{"current_steps": 101, "total_steps": 231, "loss": 0.4974, "lr": 1.3914295307268396e-05, "epoch": 3.0606060606060606, "percentage": 43.72, "elapsed_time": "1:05:24", "remaining_time": "1:24:11"}
+{"current_steps": 102, "total_steps": 231, "loss": 0.4824, "lr": 1.3774191957526144e-05, "epoch": 3.090909090909091, "percentage": 44.16, "elapsed_time": "1:06:00", "remaining_time": "1:23:28"}
+{"current_steps": 103, "total_steps": 231, "loss": 0.4825, "lr": 1.3633219297728415e-05, "epoch": 3.121212121212121, "percentage": 44.59, "elapsed_time": "1:06:35", "remaining_time": "1:22:45"}
+{"current_steps": 104, "total_steps": 231, "loss": 0.4787, "lr": 1.3491409798123687e-05, "epoch": 3.1515151515151514, "percentage": 45.02, "elapsed_time": "1:07:14", "remaining_time": "1:22:06"}
+{"current_steps": 105, "total_steps": 231, "loss": 0.4878, "lr": 1.3348796121709862e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "1:07:53", "remaining_time": "1:21:27"}
+{"current_steps": 106, "total_steps": 231, "loss": 0.4722, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "1:08:30", "remaining_time": "1:20:46"}
+{"current_steps": 107, "total_steps": 231, "loss": 0.4791, "lr": 1.3061287809011243e-05, "epoch": 3.242424242424242, "percentage": 46.32, "elapsed_time": "1:09:08", "remaining_time": "1:20:07"}
+{"current_steps": 108, "total_steps": 231, "loss": 0.4789, "lr": 1.291645939454825e-05, "epoch": 3.2727272727272725, "percentage": 46.75, "elapsed_time": "1:09:44", "remaining_time": "1:19:25"}
+{"current_steps": 109, "total_steps": 231, "loss": 0.478, "lr": 1.277095923166689e-05, "epoch": 3.303030303030303, "percentage": 47.19, "elapsed_time": "1:10:21", "remaining_time": "1:18:44"}
+{"current_steps": 110, "total_steps": 231, "loss": 0.473, "lr": 1.2624820833435939e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "1:10:58", "remaining_time": "1:18:04"}
+{"current_steps": 111, "total_steps": 231, "loss": 0.4672, "lr": 1.2478077859929e-05, "epoch": 3.3636363636363638, "percentage": 48.05, "elapsed_time": "1:11:35", "remaining_time": "1:17:24"}
+{"current_steps": 112, "total_steps": 231, "loss": 0.4831, "lr": 1.2330764110471567e-05, "epoch": 3.393939393939394, "percentage": 48.48, "elapsed_time": "1:12:14", "remaining_time": "1:16:45"}
+{"current_steps": 113, "total_steps": 231, "loss": 0.4793, "lr": 1.2182913515856016e-05, "epoch": 3.4242424242424243, "percentage": 48.92, "elapsed_time": "1:12:52", "remaining_time": "1:16:06"}
+{"current_steps": 114, "total_steps": 231, "loss": 0.4806, "lr": 1.2034560130526341e-05, "epoch": 3.4545454545454546, "percentage": 49.35, "elapsed_time": "1:13:28", "remaining_time": "1:15:24"}
+{"current_steps": 115, "total_steps": 231, "loss": 0.4818, "lr": 1.1885738124734359e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "1:14:04", "remaining_time": "1:14:42"}
+{"current_steps": 116, "total_steps": 231, "loss": 0.4796, "lr": 1.1736481776669307e-05, "epoch": 3.515151515151515, "percentage": 50.22, "elapsed_time": "1:14:42", "remaining_time": "1:14:03"}
+{"current_steps": 117, "total_steps": 231, "loss": 0.4765, "lr": 1.1586825464562515e-05, "epoch": 3.5454545454545454, "percentage": 50.65, "elapsed_time": "1:15:17", "remaining_time": "1:13:22"}
+{"current_steps": 118, "total_steps": 231, "loss": 0.494, "lr": 1.1436803658769082e-05, "epoch": 3.5757575757575757, "percentage": 51.08, "elapsed_time": "1:15:55", "remaining_time": "1:12:42"}
+{"current_steps": 119, "total_steps": 231, "loss": 0.4917, "lr": 1.1286450913828313e-05, "epoch": 3.606060606060606, "percentage": 51.52, "elapsed_time": "1:16:31", "remaining_time": "1:12:01"}
+{"current_steps": 120, "total_steps": 231, "loss": 0.4814, "lr": 1.113580186050475e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "1:17:09", "remaining_time": "1:11:22"}
+{"current_steps": 121, "total_steps": 231, "loss": 0.4721, "lr": 1.0984891197811686e-05, "epoch": 3.6666666666666665, "percentage": 52.38, "elapsed_time": "1:17:48", "remaining_time": "1:10:43"}
+{"current_steps": 122, "total_steps": 231, "loss": 0.4732, "lr": 1.0833753685018935e-05, "epoch": 3.6969696969696972, "percentage": 52.81, "elapsed_time": "1:18:23", "remaining_time": "1:10:02"}
+{"current_steps": 123, "total_steps": 231, "loss": 0.4734, "lr": 1.0682424133646712e-05, "epoch": 3.7272727272727275, "percentage": 53.25, "elapsed_time": "1:18:56", "remaining_time": "1:09:19"}
+{"current_steps": 124, "total_steps": 231, "loss": 0.4874, "lr": 1.0530937399447496e-05, "epoch": 3.757575757575758, "percentage": 53.68, "elapsed_time": "1:19:33", "remaining_time": "1:08:39"}
+{"current_steps": 125, "total_steps": 231, "loss": 0.4815, "lr": 1.0379328374377715e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "1:20:13", "remaining_time": "1:08:01"}
+{"current_steps": 126, "total_steps": 231, "loss": 0.4756, "lr": 1.0227631978561057e-05, "epoch": 3.8181818181818183, "percentage": 54.55, "elapsed_time": "1:20:50", "remaining_time": "1:07:21"}
+{"current_steps": 127, "total_steps": 231, "loss": 0.4741, "lr": 1.0075883152245334e-05, "epoch": 3.8484848484848486, "percentage": 54.98, "elapsed_time": "1:21:28", "remaining_time": "1:06:42"}
+{"current_steps": 128, "total_steps": 231, "loss": 0.4875, "lr": 9.92411684775467e-06, "epoch": 3.878787878787879, "percentage": 55.41, "elapsed_time": "1:22:04", "remaining_time": "1:06:02"}
+{"current_steps": 129, "total_steps": 231, "loss": 0.4724, "lr": 9.772368021438943e-06, "epoch": 3.909090909090909, "percentage": 55.84, "elapsed_time": "1:22:41", "remaining_time": "1:05:23"}
+{"current_steps": 130, "total_steps": 231, "loss": 0.4768, "lr": 9.620671625622287e-06, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "1:23:19", "remaining_time": "1:04:44"}
+{"current_steps": 131, "total_steps": 231, "loss": 0.4714, "lr": 9.469062600552509e-06, "epoch": 3.9696969696969697, "percentage": 56.71, "elapsed_time": "1:23:57", "remaining_time": "1:04:05"}
+{"current_steps": 132, "total_steps": 231, "loss": 0.4713, "lr": 9.317575866353293e-06, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "1:24:34", "remaining_time": "1:03:25"}
+{"current_steps": 133, "total_steps": 231, "loss": 0.4255, "lr": 9.166246314981066e-06, "epoch": 4.03030303030303, "percentage": 57.58, "elapsed_time": "1:25:30", "remaining_time": "1:03:00"}
+{"current_steps": 134, "total_steps": 231, "loss": 0.4365, "lr": 9.015108802188314e-06, "epoch": 4.0606060606060606, "percentage": 58.01, "elapsed_time": "1:26:08", "remaining_time": "1:02:21"}
+{"current_steps": 135, "total_steps": 231, "loss": 0.418, "lr": 8.86419813949525e-06, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "1:26:47", "remaining_time": "1:01:42"}
+{"current_steps": 136, "total_steps": 231, "loss": 0.4052, "lr": 8.71354908617169e-06, "epoch": 4.121212121212121, "percentage": 58.87, "elapsed_time": "1:27:25", "remaining_time": "1:01:04"}
+{"current_steps": 137, "total_steps": 231, "loss": 0.4292, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "1:28:03", "remaining_time": "1:00:24"}
+{"current_steps": 138, "total_steps": 231, "loss": 0.4173, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "1:28:38", "remaining_time": "0:59:44"}
+{"current_steps": 139, "total_steps": 231, "loss": 0.4198, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "1:29:16", "remaining_time": "0:59:05"}
+{"current_steps": 140, "total_steps": 231, "loss": 0.4049, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "1:29:53", "remaining_time": "0:58:25"}
+{"current_steps": 141, "total_steps": 231, "loss": 0.4244, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "1:30:28", "remaining_time": "0:57:45"}
+{"current_steps": 142, "total_steps": 231, "loss": 0.4143, "lr": 7.817086484143987e-06, "epoch": 4.303030303030303, "percentage": 61.47, "elapsed_time": "1:31:06", "remaining_time": "0:57:06"}
+{"current_steps": 143, "total_steps": 231, "loss": 0.4216, "lr": 7.669235889528436e-06, "epoch": 4.333333333333333, "percentage": 61.9, "elapsed_time": "1:31:44", "remaining_time": "0:56:27"}
+{"current_steps": 144, "total_steps": 231, "loss": 0.409, "lr": 7.521922140071003e-06, "epoch": 4.363636363636363, "percentage": 62.34, "elapsed_time": "1:32:19", "remaining_time": "0:55:46"}
+{"current_steps": 145, "total_steps": 231, "loss": 0.4159, "lr": 7.375179166564062e-06, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "1:32:56", "remaining_time": "0:55:07"}
+{"current_steps": 146, "total_steps": 231, "loss": 0.4256, "lr": 7.2290407683331154e-06, "epoch": 4.424242424242424, "percentage": 63.2, "elapsed_time": "1:33:33", "remaining_time": "0:54:27"}
+{"current_steps": 147, "total_steps": 231, "loss": 0.4163, "lr": 7.0835406054517505e-06, "epoch": 4.454545454545454, "percentage": 63.64, "elapsed_time": "1:34:09", "remaining_time": "0:53:48"}
+{"current_steps": 148, "total_steps": 231, "loss": 0.4221, "lr": 6.93871219098876e-06, "epoch": 4.484848484848484, "percentage": 64.07, "elapsed_time": "1:34:46", "remaining_time": "0:53:08"}
+{"current_steps": 149, "total_steps": 231, "loss": 0.4244, "lr": 6.79458888328903e-06, "epoch": 4.515151515151516, "percentage": 64.5, "elapsed_time": "1:35:24", "remaining_time": "0:52:30"}
+{"current_steps": 150, "total_steps": 231, "loss": 0.4215, "lr": 6.651203878290139e-06, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "1:36:02", "remaining_time": "0:51:51"}
+{"current_steps": 151, "total_steps": 231, "loss": 0.4051, "lr": 6.508590201876317e-06, "epoch": 4.575757575757576, "percentage": 65.37, "elapsed_time": "1:36:40", "remaining_time": "0:51:13"}
+{"current_steps": 152, "total_steps": 231, "loss": 0.4069, "lr": 6.366780702271589e-06, "epoch": 4.606060606060606, "percentage": 65.8, "elapsed_time": "1:37:17", "remaining_time": "0:50:34"}
+{"current_steps": 153, "total_steps": 231, "loss": 0.4348, "lr": 6.225808042473857e-06, "epoch": 4.636363636363637, "percentage": 66.23, "elapsed_time": "1:37:56", "remaining_time": "0:49:55"}
+{"current_steps": 154, "total_steps": 231, "loss": 0.4225, "lr": 6.085704692731609e-06, "epoch": 4.666666666666667, "percentage": 66.67, "elapsed_time": "1:38:33", "remaining_time": "0:49:16"}
+{"current_steps": 155, "total_steps": 231, "loss": 0.4085, "lr": 5.946502923065054e-06, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "1:39:08", "remaining_time": "0:48:36"}
+{"current_steps": 156, "total_steps": 231, "loss": 0.4122, "lr": 5.8082347958333625e-06, "epoch": 4.7272727272727275, "percentage": 67.53, "elapsed_time": "1:39:44", "remaining_time": "0:47:57"}
+{"current_steps": 157, "total_steps": 231, "loss": 0.4227, "lr": 5.670932158349732e-06, "epoch": 4.757575757575758, "percentage": 67.97, "elapsed_time": "1:40:23", "remaining_time": "0:47:18"}
+{"current_steps": 158, "total_steps": 231, "loss": 0.4203, "lr": 5.534626635546e-06, "epoch": 4.787878787878788, "percentage": 68.4, "elapsed_time": "1:40:59", "remaining_time": "0:46:39"}
+{"current_steps": 159, "total_steps": 231, "loss": 0.4176, "lr": 5.399349622688479e-06, "epoch": 4.818181818181818, "percentage": 68.83, "elapsed_time": "1:41:38", "remaining_time": "0:46:01"}
+{"current_steps": 160, "total_steps": 231, "loss": 0.4161, "lr": 5.2651322781466606e-06, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "1:42:12", "remaining_time": "0:45:21"}
+{"current_steps": 161, "total_steps": 231, "loss": 0.4154, "lr": 5.132005516216512e-06, "epoch": 4.878787878787879, "percentage": 69.7, "elapsed_time": "1:42:49", "remaining_time": "0:44:42"}
+{"current_steps": 162, "total_steps": 231, "loss": 0.4169, "lr": 5.000000000000003e-06, "epoch": 4.909090909090909, "percentage": 70.13, "elapsed_time": "1:43:25", "remaining_time": "0:44:03"}
+{"current_steps": 163, "total_steps": 231, "loss": 0.4209, "lr": 4.869146134342426e-06, "epoch": 4.9393939393939394, "percentage": 70.56, "elapsed_time": "1:44:02", "remaining_time": "0:43:24"}
+{"current_steps": 164, "total_steps": 231, "loss": 0.419, "lr": 4.739474058829288e-06, "epoch": 4.96969696969697, "percentage": 71.0, "elapsed_time": "1:44:38", "remaining_time": "0:42:44"}
+{"current_steps": 165, "total_steps": 231, "loss": 0.4143, "lr": 4.611013640844245e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:45:13", "remaining_time": "0:42:05"}
+{"current_steps": 166, "total_steps": 231, "loss": 0.382, "lr": 4.483794468689728e-06, "epoch": 5.03030303030303, "percentage": 71.86, "elapsed_time": "1:46:09", "remaining_time": "0:41:33"}
+{"current_steps": 167, "total_steps": 231, "loss": 0.3721, "lr": 4.357845844771881e-06, "epoch": 5.0606060606060606, "percentage": 72.29, "elapsed_time": "1:46:41", "remaining_time": "0:40:53"}
+{"current_steps": 168, "total_steps": 231, "loss": 0.3705, "lr": 4.2331967788513295e-06, "epoch": 5.090909090909091, "percentage": 72.73, "elapsed_time": "1:47:20", "remaining_time": "0:40:15"}
+{"current_steps": 169, "total_steps": 231, "loss": 0.3817, "lr": 4.109875981361363e-06, "epoch": 5.121212121212121, "percentage": 73.16, "elapsed_time": "1:47:57", "remaining_time": "0:39:36"}
+{"current_steps": 170, "total_steps": 231, "loss": 0.3864, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:48:34", "remaining_time": "0:38:57"}
+{"current_steps": 171, "total_steps": 231, "loss": 0.3863, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:49:11", "remaining_time": "0:38:18"}
+{"current_steps": 172, "total_steps": 231, "loss": 0.3716, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:49:49", "remaining_time": "0:37:40"}
+{"current_steps": 173, "total_steps": 231, "loss": 0.366, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:50:25", "remaining_time": "0:37:01"}
+{"current_steps": 174, "total_steps": 231, "loss": 0.362, "lr": 3.5141791053724405e-06, "epoch": 5.2727272727272725, "percentage": 75.32, "elapsed_time": "1:51:02", "remaining_time": "0:36:22"}
+{"current_steps": 175, "total_steps": 231, "loss": 0.3841, "lr": 3.399413251016359e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:51:39", "remaining_time": "0:35:43"}
+{"current_steps": 176, "total_steps": 231, "loss": 0.3759, "lr": 3.2861677105440335e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "1:52:16", "remaining_time": "0:35:05"}
+{"current_steps": 177, "total_steps": 231, "loss": 0.3592, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "1:52:53", "remaining_time": "0:34:26"}
+{"current_steps": 178, "total_steps": 231, "loss": 0.3725, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "1:53:28", "remaining_time": "0:33:47"}
+{"current_steps": 179, "total_steps": 231, "loss": 0.377, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "1:54:05", "remaining_time": "0:33:08"}
+{"current_steps": 180, "total_steps": 231, "loss": 0.3648, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:54:41", "remaining_time": "0:32:29"}
+{"current_steps": 181, "total_steps": 231, "loss": 0.3746, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "1:55:18", "remaining_time": "0:31:51"}
+{"current_steps": 182, "total_steps": 231, "loss": 0.3716, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "1:55:53", "remaining_time": "0:31:12"}
+{"current_steps": 183, "total_steps": 231, "loss": 0.3817, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "1:56:32", "remaining_time": "0:30:34"}
+{"current_steps": 184, "total_steps": 231, "loss": 0.3671, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "1:57:07", "remaining_time": "0:29:54"}
+{"current_steps": 185, "total_steps": 231, "loss": 0.3816, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:57:43", "remaining_time": "0:29:16"}
+{"current_steps": 186, "total_steps": 231, "loss": 0.3672, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "1:58:21", "remaining_time": "0:28:38"}
+{"current_steps": 187, "total_steps": 231, "loss": 0.3712, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "1:58:56", "remaining_time": "0:27:59"}
+{"current_steps": 188, "total_steps": 231, "loss": 0.3797, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "1:59:32", "remaining_time": "0:27:20"}
+{"current_steps": 189, "total_steps": 231, "loss": 0.3582, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "2:00:11", "remaining_time": "0:26:42"}
+{"current_steps": 190, "total_steps": 231, "loss": 0.3692, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "2:00:50", "remaining_time": "0:26:04"}
+{"current_steps": 191, "total_steps": 231, "loss": 0.3709, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "2:01:26", "remaining_time": "0:25:25"}
+{"current_steps": 192, "total_steps": 231, "loss": 0.3823, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "2:02:04", "remaining_time": "0:24:47"}
+{"current_steps": 193, "total_steps": 231, "loss": 0.3683, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "2:02:42", "remaining_time": "0:24:09"}
+{"current_steps": 194, "total_steps": 231, "loss": 0.3752, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "2:03:19", "remaining_time": "0:23:31"}
+{"current_steps": 195, "total_steps": 231, "loss": 0.3658, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "2:03:56", "remaining_time": "0:22:52"}
+{"current_steps": 196, "total_steps": 231, "loss": 0.3635, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "2:04:33", "remaining_time": "0:22:14"}
+{"current_steps": 197, "total_steps": 231, "loss": 0.3679, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "2:05:10", "remaining_time": "0:21:36"}
+{"current_steps": 198, "total_steps": 231, "loss": 0.3767, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "2:05:50", "remaining_time": "0:20:58"}
+{"current_steps": 199, "total_steps": 231, "loss": 0.3407, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "2:06:46", "remaining_time": "0:20:23"}
+{"current_steps": 200, "total_steps": 231, "loss": 0.3591, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "2:07:22", "remaining_time": "0:19:44"}
+{"current_steps": 201, "total_steps": 231, "loss": 0.3483, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "2:07:58", "remaining_time": "0:19:06"}
+{"current_steps": 202, "total_steps": 231, "loss": 0.3508, "lr": 9.530222835413739e-07, "epoch": 6.121212121212121, "percentage": 87.45, "elapsed_time": "2:08:32", "remaining_time": "0:18:27"}
+{"current_steps": 203, "total_steps": 231, "loss": 0.3446, "lr": 8.894054121084839e-07, "epoch": 6.151515151515151, "percentage": 87.88, "elapsed_time": "2:09:06", "remaining_time": "0:17:48"}
+{"current_steps": 204, "total_steps": 231, "loss": 0.3476, "lr": 8.278869849454718e-07, "epoch": 6.181818181818182, "percentage": 88.31, "elapsed_time": "2:09:44", "remaining_time": "0:17:10"}
+{"current_steps": 205, "total_steps": 231, "loss": 0.3543, "lr": 7.684811715985429e-07, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "2:10:20", "remaining_time": "0:16:31"}
+{"current_steps": 206, "total_steps": 231, "loss": 0.3575, "lr": 7.1120165501533e-07, "epoch": 6.242424242424242, "percentage": 89.18, "elapsed_time": "2:10:58", "remaining_time": "0:15:53"}
+{"current_steps": 207, "total_steps": 231, "loss": 0.3483, "lr": 6.560616283932897e-07, "epoch": 6.2727272727272725, "percentage": 89.61, "elapsed_time": "2:11:35", "remaining_time": "0:15:15"}
+{"current_steps": 208, "total_steps": 231, "loss": 0.3615, "lr": 6.030737921409169e-07, "epoch": 6.303030303030303, "percentage": 90.04, "elapsed_time": "2:12:11", "remaining_time": "0:14:37"}
+{"current_steps": 209, "total_steps": 231, "loss": 0.3553, "lr": 5.522503509524591e-07, "epoch": 6.333333333333333, "percentage": 90.48, "elapsed_time": "2:12:48", "remaining_time": "0:13:58"}
+{"current_steps": 210, "total_steps": 231, "loss": 0.3525, "lr": 5.036030109968082e-07, "epoch": 6.363636363636363, "percentage": 90.91, "elapsed_time": "2:13:24", "remaining_time": "0:13:20"}
+{"current_steps": 211, "total_steps": 231, "loss": 0.3586, "lr": 4.5714297722121105e-07, "epoch": 6.393939393939394, "percentage": 91.34, "elapsed_time": "2:13:59", "remaining_time": "0:12:42"}
+{"current_steps": 212, "total_steps": 231, "loss": 0.371, "lr": 4.128809507704445e-07, "epoch": 6.424242424242424, "percentage": 91.77, "elapsed_time": "2:14:36", "remaining_time": "0:12:03"}
+{"current_steps": 213, "total_steps": 231, "loss": 0.3369, "lr": 3.708271265220087e-07, "epoch": 6.454545454545454, "percentage": 92.21, "elapsed_time": "2:15:12", "remaining_time": "0:11:25"}
+{"current_steps": 214, "total_steps": 231, "loss": 0.3441, "lr": 3.309911907379393e-07, "epoch": 6.484848484848484, "percentage": 92.64, "elapsed_time": "2:15:50", "remaining_time": "0:10:47"}
+{"current_steps": 215, "total_steps": 231, "loss": 0.343, "lr": 2.9338231883378365e-07, "epoch": 6.515151515151516, "percentage": 93.07, "elapsed_time": "2:16:26", "remaining_time": "0:10:09"}
+{"current_steps": 216, "total_steps": 231, "loss": 0.3446, "lr": 2.5800917326521013e-07, "epoch": 6.545454545454545, "percentage": 93.51, "elapsed_time": "2:17:01", "remaining_time": "0:09:30"}
+{"current_steps": 217, "total_steps": 231, "loss": 0.3559, "lr": 2.248799015327907e-07, "epoch": 6.575757575757576, "percentage": 93.94, "elapsed_time": "2:17:37", "remaining_time": "0:08:52"}
+{"current_steps": 218, "total_steps": 231, "loss": 0.347, "lr": 1.9400213430538773e-07, "epoch": 6.606060606060606, "percentage": 94.37, "elapsed_time": "2:18:14", "remaining_time": "0:08:14"}
+{"current_steps": 219, "total_steps": 231, "loss": 0.3496, "lr": 1.6538298366257975e-07, "epoch": 6.636363636363637, "percentage": 94.81, "elapsed_time": "2:18:51", "remaining_time": "0:07:36"}
+{"current_steps": 220, "total_steps": 231, "loss": 0.3466, "lr": 1.3902904145653094e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "2:19:24", "remaining_time": "0:06:58"}
+{"current_steps": 221, "total_steps": 231, "loss": 0.3533, "lr": 1.1494637779369766e-07, "epoch": 6.696969696969697, "percentage": 95.67, "elapsed_time": "2:20:03", "remaining_time": "0:06:20"}
+{"current_steps": 222, "total_steps": 231, "loss": 0.3477, "lr": 9.314053963669245e-08, "epoch": 6.7272727272727275, "percentage": 96.1, "elapsed_time": "2:20:40", "remaining_time": "0:05:42"}
+{"current_steps": 223, "total_steps": 231, "loss": 0.3512, "lr": 7.361654952665608e-08, "epoch": 6.757575757575758, "percentage": 96.54, "elapsed_time": "2:21:18", "remaining_time": "0:05:04"}
+{"current_steps": 224, "total_steps": 231, "loss": 0.3547, "lr": 5.637890442641403e-08, "epoch": 6.787878787878788, "percentage": 96.97, "elapsed_time": "2:21:57", "remaining_time": "0:04:26"}
+{"current_steps": 225, "total_steps": 231, "loss": 0.3648, "lr": 4.143157468468717e-08, "epoch": 6.818181818181818, "percentage": 97.4, "elapsed_time": "2:22:33", "remaining_time": "0:03:48"}
+{"current_steps": 226, "total_steps": 231, "loss": 0.354, "lr": 2.8778003121607834e-08, "epoch": 6.848484848484849, "percentage": 97.84, "elapsed_time": "2:23:08", "remaining_time": "0:03:10"}
+{"current_steps": 227, "total_steps": 231, "loss": 0.3475, "lr": 1.8421104235727406e-08, "epoch": 6.878787878787879, "percentage": 98.27, "elapsed_time": "2:23:45", "remaining_time": "0:02:31"}
+{"current_steps": 228, "total_steps": 231, "loss": 0.3526, "lr": 1.0363263532724433e-08, "epoch": 6.909090909090909, "percentage": 98.7, "elapsed_time": "2:24:23", "remaining_time": "0:01:53"}
+{"current_steps": 229, "total_steps": 231, "loss": 0.3469, "lr": 4.606336975948589e-09, "epoch": 6.9393939393939394, "percentage": 99.13, "elapsed_time": "2:24:58", "remaining_time": "0:01:15"}
+{"current_steps": 230, "total_steps": 231, "loss": 0.3435, "lr": 1.1516505589381777e-09, "epoch": 6.96969696969697, "percentage": 99.57, "elapsed_time": "2:25:36", "remaining_time": "0:00:37"}
+{"current_steps": 231, "total_steps": 231, "loss": 0.3469, "lr": 0.0, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:26:11", "remaining_time": "0:00:00"}
+{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:26:46", "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": 6.517928735676965,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.0455,
+      "step": 1
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 6.5772655527337225,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.0538,
+      "step": 2
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 6.234913448864819,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0183,
+      "step": 3
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 6.028555631511048,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0403,
+      "step": 4
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 4.614248102967521,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.0087,
+      "step": 5
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.8093652372056996,
+      "learning_rate": 5e-06,
+      "loss": 0.9609,
+      "step": 6
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 2.531229757877748,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.9351,
+      "step": 7
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 3.954820632458033,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9216,
+      "step": 8
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 4.349233683778192,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.9455,
+      "step": 9
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 3.9434657814129603,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.9028,
+      "step": 10
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.319039548252818,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.8936,
+      "step": 11
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 2.9062149806353275,
+      "learning_rate": 1e-05,
+      "loss": 0.8668,
+      "step": 12
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 2.1578300199262115,
+      "learning_rate": 1.0833333333333334e-05,
+      "loss": 0.8486,
+      "step": 13
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 1.3909657883291664,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.8195,
+      "step": 14
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.524438571353993,
+      "learning_rate": 1.25e-05,
+      "loss": 0.7993,
+      "step": 15
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 1.3007009517951573,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7693,
+      "step": 16
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 1.1840573751827055,
+      "learning_rate": 1.416666666666667e-05,
+      "loss": 0.7884,
+      "step": 17
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.072242504675073,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7686,
+      "step": 18
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 1.0713373045598065,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.7386,
+      "step": 19
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 1.0077579984518008,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.759,
+      "step": 20
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 0.9558690379004416,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.7453,
+      "step": 21
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.9329162555700646,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.7493,
+      "step": 22
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 0.9683964184874808,
+      "learning_rate": 1.916666666666667e-05,
+      "loss": 0.7069,
+      "step": 23
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.8805496812777832,
+      "learning_rate": 2e-05,
+      "loss": 0.7274,
+      "step": 24
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 1.1577430567000497,
+      "learning_rate": 1.999884834944106e-05,
+      "loss": 0.7113,
+      "step": 25
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.820818250052884,
+      "learning_rate": 1.9995393663024054e-05,
+      "loss": 0.7339,
+      "step": 26
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 1.026572847248684,
+      "learning_rate": 1.9989636736467278e-05,
+      "loss": 0.7404,
+      "step": 27
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.8949030890717823,
+      "learning_rate": 1.9981578895764272e-05,
+      "loss": 0.7325,
+      "step": 28
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 0.6612521991913959,
+      "learning_rate": 1.9971221996878395e-05,
+      "loss": 0.698,
+      "step": 29
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.893505399104731,
+      "learning_rate": 1.9958568425315316e-05,
+      "loss": 0.7074,
+      "step": 30
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.8127090262942633,
+      "learning_rate": 1.9943621095573588e-05,
+      "loss": 0.6983,
+      "step": 31
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.6426688453837587,
+      "learning_rate": 1.9926383450473344e-05,
+      "loss": 0.7091,
+      "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7643160321623741,
+      "learning_rate": 1.9906859460363307e-05,
+      "loss": 0.7099,
+      "step": 33
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 0.7663374263559303,
+      "learning_rate": 1.9885053622206305e-05,
+      "loss": 0.6775,
+      "step": 34
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.5721050329168993,
+      "learning_rate": 1.986097095854347e-05,
+      "loss": 0.6599,
+      "step": 35
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.6381280372319813,
+      "learning_rate": 1.9834617016337424e-05,
+      "loss": 0.6543,
+      "step": 36
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.589157622166952,
+      "learning_rate": 1.9805997865694616e-05,
+      "loss": 0.6522,
+      "step": 37
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 0.4955649866020235,
+      "learning_rate": 1.9775120098467212e-05,
+      "loss": 0.6342,
+      "step": 38
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.6041664505696033,
+      "learning_rate": 1.9741990826734793e-05,
+      "loss": 0.6499,
+      "step": 39
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.5417305039931442,
+      "learning_rate": 1.970661768116622e-05,
+      "loss": 0.6368,
+      "step": 40
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 0.5479708269864506,
+      "learning_rate": 1.9669008809262064e-05,
+      "loss": 0.6359,
+      "step": 41
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.5822279252934454,
+      "learning_rate": 1.9629172873477995e-05,
+      "loss": 0.6415,
+      "step": 42
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 0.6394116074964873,
+      "learning_rate": 1.9587119049229558e-05,
+      "loss": 0.642,
+      "step": 43
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.5849806700810495,
+      "learning_rate": 1.954285702277879e-05,
+      "loss": 0.6355,
+      "step": 44
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.5747917658467485,
+      "learning_rate": 1.9496396989003195e-05,
+      "loss": 0.6293,
+      "step": 45
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 0.6951246814835008,
+      "learning_rate": 1.944774964904754e-05,
+      "loss": 0.634,
+      "step": 46
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 0.49648204546835345,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.6254,
+      "step": 47
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.690453417629691,
+      "learning_rate": 1.9343938371606714e-05,
+      "loss": 0.6221,
+      "step": 48
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 0.5951412266996973,
+      "learning_rate": 1.9288798344984673e-05,
+      "loss": 0.6386,
+      "step": 49
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.6617890971401159,
+      "learning_rate": 1.9231518828401458e-05,
+      "loss": 0.629,
+      "step": 50
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.5430380521759081,
+      "learning_rate": 1.917211301505453e-05,
+      "loss": 0.6266,
+      "step": 51
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 0.6603764327836058,
+      "learning_rate": 1.911059458789152e-05,
+      "loss": 0.6237,
+      "step": 52
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 0.5418638187576439,
+      "learning_rate": 1.9046977716458627e-05,
+      "loss": 0.6219,
+      "step": 53
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.5945041110356534,
+      "learning_rate": 1.8981277053636963e-05,
+      "loss": 0.6221,
+      "step": 54
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5690684623748405,
+      "learning_rate": 1.891350773226754e-05,
+      "loss": 0.628,
+      "step": 55
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 0.6631928877862863,
+      "learning_rate": 1.8843685361665724e-05,
+      "loss": 0.6181,
+      "step": 56
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.6689566033883234,
+      "learning_rate": 1.8771826024025944e-05,
+      "loss": 0.6269,
+      "step": 57
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 0.7066091560013505,
+      "learning_rate": 1.8697946270717468e-05,
+      "loss": 0.6265,
+      "step": 58
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 0.5811635487093934,
+      "learning_rate": 1.8622063118472135e-05,
+      "loss": 0.6516,
+      "step": 59
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.7488418345694374,
+      "learning_rate": 1.8544194045464888e-05,
+      "loss": 0.6098,
+      "step": 60
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.5457353046046373,
+      "learning_rate": 1.8464356987288012e-05,
+      "loss": 0.6041,
+      "step": 61
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 0.6736333769853714,
+      "learning_rate": 1.8382570332820045e-05,
+      "loss": 0.6145,
+      "step": 62
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.6469957663674077,
+      "learning_rate": 1.8298852919990254e-05,
+      "loss": 0.6163,
+      "step": 63
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 0.6803830814584926,
+      "learning_rate": 1.821322403143969e-05,
+      "loss": 0.6242,
+      "step": 64
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.5663508233607352,
+      "learning_rate": 1.812570339007983e-05,
+      "loss": 0.6178,
+      "step": 65
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.551652751302577,
+      "learning_rate": 1.8036311154549783e-05,
+      "loss": 0.6288,
+      "step": 66
+    },
+    {
+      "epoch": 2.0303030303030303,
+      "grad_norm": 0.7771647721010193,
+      "learning_rate": 1.7945067914573147e-05,
+      "loss": 0.5725,
+      "step": 67
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 0.564899996509134,
+      "learning_rate": 1.7851994686215592e-05,
+      "loss": 0.5746,
+      "step": 68
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 0.618249122036095,
+      "learning_rate": 1.77571129070442e-05,
+      "loss": 0.5565,
+      "step": 69
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 0.5944500659793406,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.5548,
+      "step": 70
+    },
+    {
+      "epoch": 2.1515151515151514,
+      "grad_norm": 0.6128159952824492,
+      "learning_rate": 1.7562011524313187e-05,
+      "loss": 0.561,
+      "step": 71
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.5327494294178395,
+      "learning_rate": 1.7461836858476858e-05,
+      "loss": 0.564,
+      "step": 72
+    },
+    {
+      "epoch": 2.212121212121212,
+      "grad_norm": 0.6082360705069719,
+      "learning_rate": 1.7359943506922775e-05,
+      "loss": 0.564,
+      "step": 73
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 0.5671302488950932,
+      "learning_rate": 1.725635493875799e-05,
+      "loss": 0.5297,
+      "step": 74
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.5915509386240322,
+      "learning_rate": 1.7151095013548996e-05,
+      "loss": 0.551,
+      "step": 75
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 0.6660479034674898,
+      "learning_rate": 1.7044187975826126e-05,
+      "loss": 0.5455,
+      "step": 76
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.5266660301477659,
+      "learning_rate": 1.693565844949933e-05,
+      "loss": 0.5364,
+      "step": 77
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.6247338879059353,
+      "learning_rate": 1.6825531432186545e-05,
+      "loss": 0.5404,
+      "step": 78
+    },
+    {
+      "epoch": 2.393939393939394,
+      "grad_norm": 0.6222629637099215,
+      "learning_rate": 1.671383228945597e-05,
+      "loss": 0.5349,
+      "step": 79
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.6189555444712931,
+      "learning_rate": 1.6600586748983642e-05,
+      "loss": 0.5378,
+      "step": 80
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.802497560917399,
+      "learning_rate": 1.648582089462756e-05,
+      "loss": 0.5573,
+      "step": 81
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 0.6793514991600532,
+      "learning_rate": 1.6369561160419783e-05,
+      "loss": 0.5474,
+      "step": 82
+    },
+    {
+      "epoch": 2.515151515151515,
+      "grad_norm": 0.6645605435800442,
+      "learning_rate": 1.625183432447789e-05,
+      "loss": 0.548,
+      "step": 83
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.697403221351068,
+      "learning_rate": 1.6132667502837164e-05,
+      "loss": 0.5573,
+      "step": 84
+    },
+    {
+      "epoch": 2.5757575757575757,
+      "grad_norm": 0.6119028025068409,
+      "learning_rate": 1.6012088143204953e-05,
+      "loss": 0.5383,
+      "step": 85
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 0.5185634339277824,
+      "learning_rate": 1.589012401863864e-05,
+      "loss": 0.5431,
+      "step": 86
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 0.6140765208748267,
+      "learning_rate": 1.5766803221148676e-05,
+      "loss": 0.5516,
+      "step": 87
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.4340062681908139,
+      "learning_rate": 1.5642154155228124e-05,
+      "loss": 0.5284,
+      "step": 88
+    },
+    {
+      "epoch": 2.6969696969696972,
+      "grad_norm": 0.5424528614752664,
+      "learning_rate": 1.5516205531310272e-05,
+      "loss": 0.5537,
+      "step": 89
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.5595676031125654,
+      "learning_rate": 1.538898635915576e-05,
+      "loss": 0.5486,
+      "step": 90
+    },
+    {
+      "epoch": 2.757575757575758,
+      "grad_norm": 0.49369623901247756,
+      "learning_rate": 1.526052594117071e-05,
+      "loss": 0.5453,
+      "step": 91
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 0.5697187256144819,
+      "learning_rate": 1.513085386565758e-05,
+      "loss": 0.5546,
+      "step": 92
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.4382602815757698,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5382,
+      "step": 93
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 0.725931420202846,
+      "learning_rate": 1.4867994483783485e-05,
+      "loss": 0.5484,
+      "step": 94
+    },
+    {
+      "epoch": 2.878787878787879,
+      "grad_norm": 0.5526464700652515,
+      "learning_rate": 1.4734867721853341e-05,
+      "loss": 0.5417,
+      "step": 95
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.5197731640521036,
+      "learning_rate": 1.4600650377311523e-05,
+      "loss": 0.55,
+      "step": 96
+    },
+    {
+      "epoch": 2.9393939393939394,
+      "grad_norm": 0.5682826825760908,
+      "learning_rate": 1.4465373364454001e-05,
+      "loss": 0.5603,
+      "step": 97
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 0.466275094156658,
+      "learning_rate": 1.4329067841650274e-05,
+      "loss": 0.537,
+      "step": 98
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6352363204388607,
+      "learning_rate": 1.4191765204166643e-05,
+      "loss": 0.545,
+      "step": 99
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 0.5776585338313645,
+      "learning_rate": 1.4053497076934948e-05,
+      "loss": 0.4968,
+      "step": 100
+    },
+    {
+      "epoch": 3.0606060606060606,
+      "grad_norm": 0.4771059248611455,
+      "learning_rate": 1.3914295307268396e-05,
+      "loss": 0.4974,
+      "step": 101
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 0.5605350362601154,
+      "learning_rate": 1.3774191957526144e-05,
+      "loss": 0.4824,
+      "step": 102
+    },
+    {
+      "epoch": 3.121212121212121,
+      "grad_norm": 0.48093206214966144,
+      "learning_rate": 1.3633219297728415e-05,
+      "loss": 0.4825,
+      "step": 103
+    },
+    {
+      "epoch": 3.1515151515151514,
+      "grad_norm": 0.5695727515540727,
+      "learning_rate": 1.3491409798123687e-05,
+      "loss": 0.4787,
+      "step": 104
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.552164375832746,
+      "learning_rate": 1.3348796121709862e-05,
+      "loss": 0.4878,
+      "step": 105
+    },
+    {
+      "epoch": 3.212121212121212,
+      "grad_norm": 0.5159675769861567,
+      "learning_rate": 1.3205411116710973e-05,
+      "loss": 0.4722,
+      "step": 106
+    },
+    {
+      "epoch": 3.242424242424242,
+      "grad_norm": 0.46240380219363764,
+      "learning_rate": 1.3061287809011243e-05,
+      "loss": 0.4791,
+      "step": 107
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 0.5231843366499154,
+      "learning_rate": 1.291645939454825e-05,
+      "loss": 0.4789,
+      "step": 108
+    },
+    {
+      "epoch": 3.303030303030303,
+      "grad_norm": 0.43961723636777644,
+      "learning_rate": 1.277095923166689e-05,
+      "loss": 0.478,
+      "step": 109
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.4721485286866721,
+      "learning_rate": 1.2624820833435939e-05,
+      "loss": 0.473,
+      "step": 110
+    },
+    {
+      "epoch": 3.3636363636363638,
+      "grad_norm": 0.5443639503195921,
+      "learning_rate": 1.2478077859929e-05,
+      "loss": 0.4672,
+      "step": 111
+    },
+    {
+      "epoch": 3.393939393939394,
+      "grad_norm": 0.4662242306518608,
+      "learning_rate": 1.2330764110471567e-05,
+      "loss": 0.4831,
+      "step": 112
+    },
+    {
+      "epoch": 3.4242424242424243,
+      "grad_norm": 0.5388879388421665,
+      "learning_rate": 1.2182913515856016e-05,
+      "loss": 0.4793,
+      "step": 113
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 0.4907864746109935,
+      "learning_rate": 1.2034560130526341e-05,
+      "loss": 0.4806,
+      "step": 114
+    },
+    {
+      "epoch": 3.484848484848485,
+      "grad_norm": 0.5382786784782878,
+      "learning_rate": 1.1885738124734359e-05,
+      "loss": 0.4818,
+      "step": 115
+    },
+    {
+      "epoch": 3.515151515151515,
+      "grad_norm": 0.4325648604370947,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.4796,
+      "step": 116
+    },
+    {
+      "epoch": 3.5454545454545454,
+      "grad_norm": 0.4914914905055827,
+      "learning_rate": 1.1586825464562515e-05,
+      "loss": 0.4765,
+      "step": 117
+    },
+    {
+      "epoch": 3.5757575757575757,
+      "grad_norm": 0.44194107125135146,
+      "learning_rate": 1.1436803658769082e-05,
+      "loss": 0.494,
+      "step": 118
+    },
+    {
+      "epoch": 3.606060606060606,
+      "grad_norm": 0.4192917180919241,
+      "learning_rate": 1.1286450913828313e-05,
+      "loss": 0.4917,
+      "step": 119
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.4610644445088454,
+      "learning_rate": 1.113580186050475e-05,
+      "loss": 0.4814,
+      "step": 120
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.3902931908900223,
+      "learning_rate": 1.0984891197811686e-05,
+      "loss": 0.4721,
+      "step": 121
+    },
+    {
+      "epoch": 3.6969696969696972,
+      "grad_norm": 0.4140702518302563,
+      "learning_rate": 1.0833753685018935e-05,
+      "loss": 0.4732,
+      "step": 122
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 0.4101357605462889,
+      "learning_rate": 1.0682424133646712e-05,
+      "loss": 0.4734,
+      "step": 123
+    },
+    {
+      "epoch": 3.757575757575758,
+      "grad_norm": 0.44911020645751626,
+      "learning_rate": 1.0530937399447496e-05,
+      "loss": 0.4874,
+      "step": 124
+    },
+    {
+      "epoch": 3.787878787878788,
+      "grad_norm": 0.3818119445654494,
+      "learning_rate": 1.0379328374377715e-05,
+      "loss": 0.4815,
+      "step": 125
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 0.5580474214383856,
+      "learning_rate": 1.0227631978561057e-05,
+      "loss": 0.4756,
+      "step": 126
+    },
+    {
+      "epoch": 3.8484848484848486,
+      "grad_norm": 0.4116446618071981,
+      "learning_rate": 1.0075883152245334e-05,
+      "loss": 0.4741,
+      "step": 127
+    },
+    {
+      "epoch": 3.878787878787879,
+      "grad_norm": 0.4943120264299029,
+      "learning_rate": 9.92411684775467e-06,
+      "loss": 0.4875,
+      "step": 128
+    },
+    {
+      "epoch": 3.909090909090909,
+      "grad_norm": 0.4180939845391508,
+      "learning_rate": 9.772368021438943e-06,
+      "loss": 0.4724,
+      "step": 129
+    },
+    {
+      "epoch": 3.9393939393939394,
+      "grad_norm": 0.4769942870235733,
+      "learning_rate": 9.620671625622287e-06,
+      "loss": 0.4768,
+      "step": 130
+    },
+    {
+      "epoch": 3.9696969696969697,
+      "grad_norm": 0.453817923016501,
+      "learning_rate": 9.469062600552509e-06,
+      "loss": 0.4714,
+      "step": 131
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.39927065617614704,
+      "learning_rate": 9.317575866353293e-06,
+      "loss": 0.4713,
+      "step": 132
+    },
+    {
+      "epoch": 4.03030303030303,
+      "grad_norm": 0.5987689057987375,
+      "learning_rate": 9.166246314981066e-06,
+      "loss": 0.4255,
+      "step": 133
+    },
+    {
+      "epoch": 4.0606060606060606,
+      "grad_norm": 0.4790300942770665,
+      "learning_rate": 9.015108802188314e-06,
+      "loss": 0.4365,
+      "step": 134
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.48980998436066,
+      "learning_rate": 8.86419813949525e-06,
+      "loss": 0.418,
+      "step": 135
+    },
+    {
+      "epoch": 4.121212121212121,
+      "grad_norm": 0.599569588363402,
+      "learning_rate": 8.71354908617169e-06,
+      "loss": 0.4052,
+      "step": 136
+    },
+    {
+      "epoch": 4.151515151515151,
+      "grad_norm": 0.5585790964609069,
+      "learning_rate": 8.56319634123092e-06,
+      "loss": 0.4292,
+      "step": 137
+    },
+    {
+      "epoch": 4.181818181818182,
+      "grad_norm": 0.5102739750207342,
+      "learning_rate": 8.413174535437486e-06,
+      "loss": 0.4173,
+      "step": 138
+    },
+    {
+      "epoch": 4.212121212121212,
+      "grad_norm": 0.5175867828824035,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.4198,
+      "step": 139
+    },
+    {
+      "epoch": 4.242424242424242,
+      "grad_norm": 0.5196144980105121,
+      "learning_rate": 8.114261875265643e-06,
+      "loss": 0.4049,
+      "step": 140
+    },
+    {
+      "epoch": 4.2727272727272725,
+      "grad_norm": 0.4870940451465083,
+      "learning_rate": 7.965439869473664e-06,
+      "loss": 0.4244,
+      "step": 141
+    },
+    {
+      "epoch": 4.303030303030303,
+      "grad_norm": 0.46255414067156897,
+      "learning_rate": 7.817086484143987e-06,
+      "loss": 0.4143,
+      "step": 142
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.5286334558089502,
+      "learning_rate": 7.669235889528436e-06,
+      "loss": 0.4216,
+      "step": 143
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 0.462928845467462,
+      "learning_rate": 7.521922140071003e-06,
+      "loss": 0.409,
+      "step": 144
+    },
+    {
+      "epoch": 4.393939393939394,
+      "grad_norm": 0.42566600796425524,
+      "learning_rate": 7.375179166564062e-06,
+      "loss": 0.4159,
+      "step": 145
+    },
+    {
+      "epoch": 4.424242424242424,
+      "grad_norm": 0.4171665568759143,
+      "learning_rate": 7.2290407683331154e-06,
+      "loss": 0.4256,
+      "step": 146
+    },
+    {
+      "epoch": 4.454545454545454,
+      "grad_norm": 0.46595276831246435,
+      "learning_rate": 7.0835406054517505e-06,
+      "loss": 0.4163,
+      "step": 147
+    },
+    {
+      "epoch": 4.484848484848484,
+      "grad_norm": 0.3851926386621285,
+      "learning_rate": 6.93871219098876e-06,
+      "loss": 0.4221,
+      "step": 148
+    },
+    {
+      "epoch": 4.515151515151516,
+      "grad_norm": 0.3900923201698187,
+      "learning_rate": 6.79458888328903e-06,
+      "loss": 0.4244,
+      "step": 149
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.4034534199650892,
+      "learning_rate": 6.651203878290139e-06,
+      "loss": 0.4215,
+      "step": 150
+    },
+    {
+      "epoch": 4.575757575757576,
+      "grad_norm": 0.3799715262816614,
+      "learning_rate": 6.508590201876317e-06,
+      "loss": 0.4051,
+      "step": 151
+    },
+    {
+      "epoch": 4.606060606060606,
+      "grad_norm": 0.371365785193263,
+      "learning_rate": 6.366780702271589e-06,
+      "loss": 0.4069,
+      "step": 152
+    },
+    {
+      "epoch": 4.636363636363637,
+      "grad_norm": 0.3706688070478696,
+      "learning_rate": 6.225808042473857e-06,
+      "loss": 0.4348,
+      "step": 153
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.3667995438450157,
+      "learning_rate": 6.085704692731609e-06,
+      "loss": 0.4225,
+      "step": 154
+    },
+    {
+      "epoch": 4.696969696969697,
+      "grad_norm": 0.394320750379463,
+      "learning_rate": 5.946502923065054e-06,
+      "loss": 0.4085,
+      "step": 155
+    },
+    {
+      "epoch": 4.7272727272727275,
+      "grad_norm": 0.3476113946267737,
+      "learning_rate": 5.8082347958333625e-06,
+      "loss": 0.4122,
+      "step": 156
+    },
+    {
+      "epoch": 4.757575757575758,
+      "grad_norm": 0.384396711169214,
+      "learning_rate": 5.670932158349732e-06,
+      "loss": 0.4227,
+      "step": 157
+    },
+    {
+      "epoch": 4.787878787878788,
+      "grad_norm": 0.3792106407811517,
+      "learning_rate": 5.534626635546e-06,
+      "loss": 0.4203,
+      "step": 158
+    },
+    {
+      "epoch": 4.818181818181818,
+      "grad_norm": 0.3556912896979165,
+      "learning_rate": 5.399349622688479e-06,
+      "loss": 0.4176,
+      "step": 159
+    },
+    {
+      "epoch": 4.848484848484849,
+      "grad_norm": 0.35611015173815613,
+      "learning_rate": 5.2651322781466606e-06,
+      "loss": 0.4161,
+      "step": 160
+    },
+    {
+      "epoch": 4.878787878787879,
+      "grad_norm": 0.3747879122931635,
+      "learning_rate": 5.132005516216512e-06,
+      "loss": 0.4154,
+      "step": 161
+    },
+    {
+      "epoch": 4.909090909090909,
+      "grad_norm": 0.34767749347685095,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.4169,
+      "step": 162
+    },
+    {
+      "epoch": 4.9393939393939394,
+      "grad_norm": 0.32095751420570984,
+      "learning_rate": 4.869146134342426e-06,
+      "loss": 0.4209,
+      "step": 163
+    },
+    {
+      "epoch": 4.96969696969697,
+      "grad_norm": 0.34456110661136463,
+      "learning_rate": 4.739474058829288e-06,
+      "loss": 0.419,
+      "step": 164
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.353567015392029,
+      "learning_rate": 4.611013640844245e-06,
+      "loss": 0.4143,
+      "step": 165
+    },
+    {
+      "epoch": 5.03030303030303,
+      "grad_norm": 0.5382318520401967,
+      "learning_rate": 4.483794468689728e-06,
+      "loss": 0.382,
+      "step": 166
+    },
+    {
+      "epoch": 5.0606060606060606,
+      "grad_norm": 0.39983247500309826,
+      "learning_rate": 4.357845844771881e-06,
+      "loss": 0.3721,
+      "step": 167
+    },
+    {
+      "epoch": 5.090909090909091,
+      "grad_norm": 0.3475018833963907,
+      "learning_rate": 4.2331967788513295e-06,
+      "loss": 0.3705,
+      "step": 168
+    },
+    {
+      "epoch": 5.121212121212121,
+      "grad_norm": 0.5189815394990832,
+      "learning_rate": 4.109875981361363e-06,
+      "loss": 0.3817,
+      "step": 169
+    },
+    {
+      "epoch": 5.151515151515151,
+      "grad_norm": 0.554522540829979,
+      "learning_rate": 3.987911856795047e-06,
+      "loss": 0.3864,
+      "step": 170
+    },
+    {
+      "epoch": 5.181818181818182,
+      "grad_norm": 0.41688108911198396,
+      "learning_rate": 3.867332497162836e-06,
+      "loss": 0.3863,
+      "step": 171
+    },
+    {
+      "epoch": 5.212121212121212,
+      "grad_norm": 0.4027653897797602,
+      "learning_rate": 3.748165675522113e-06,
+      "loss": 0.3716,
+      "step": 172
+    },
+    {
+      "epoch": 5.242424242424242,
+      "grad_norm": 0.41406725572850883,
+      "learning_rate": 3.630438839580217e-06,
+      "loss": 0.366,
+      "step": 173
+    },
+    {
+      "epoch": 5.2727272727272725,
+      "grad_norm": 0.4079762390454095,
+      "learning_rate": 3.5141791053724405e-06,
+      "loss": 0.362,
+      "step": 174
+    },
+    {
+      "epoch": 5.303030303030303,
+      "grad_norm": 0.3766526825355298,
+      "learning_rate": 3.399413251016359e-06,
+      "loss": 0.3841,
+      "step": 175
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.37011491054019086,
+      "learning_rate": 3.2861677105440335e-06,
+      "loss": 0.3759,
+      "step": 176
+    },
+    {
+      "epoch": 5.363636363636363,
+      "grad_norm": 0.3838011792978329,
+      "learning_rate": 3.174468567813461e-06,
+      "loss": 0.3592,
+      "step": 177
+    },
+    {
+      "epoch": 5.393939393939394,
+      "grad_norm": 0.39870925113344313,
+      "learning_rate": 3.0643415505006733e-06,
+      "loss": 0.3725,
+      "step": 178
+    },
+    {
+      "epoch": 5.424242424242424,
+      "grad_norm": 0.3741463586176945,
+      "learning_rate": 2.9558120241738786e-06,
+      "loss": 0.377,
+      "step": 179
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.35712527597315996,
+      "learning_rate": 2.8489049864510053e-06,
+      "loss": 0.3648,
+      "step": 180
+    },
+    {
+      "epoch": 5.484848484848484,
+      "grad_norm": 0.37516801168343306,
+      "learning_rate": 2.7436450612420098e-06,
+      "loss": 0.3746,
+      "step": 181
+    },
+    {
+      "epoch": 5.515151515151516,
+      "grad_norm": 0.33612195811172774,
+      "learning_rate": 2.640056493077231e-06,
+      "loss": 0.3716,
+      "step": 182
+    },
+    {
+      "epoch": 5.545454545454545,
+      "grad_norm": 0.36328449670893154,
+      "learning_rate": 2.5381631415231455e-06,
+      "loss": 0.3817,
+      "step": 183
+    },
+    {
+      "epoch": 5.575757575757576,
+      "grad_norm": 0.3703073744878245,
+      "learning_rate": 2.4379884756868167e-06,
+      "loss": 0.3671,
+      "step": 184
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 0.3427111752725232,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.3816,
+      "step": 185
+    },
+    {
+      "epoch": 5.636363636363637,
+      "grad_norm": 0.3496215218548327,
+      "learning_rate": 2.2428870929558012e-06,
+      "loss": 0.3672,
+      "step": 186
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 0.329336790888063,
+      "learning_rate": 2.1480053137844115e-06,
+      "loss": 0.3712,
+      "step": 187
+    },
+    {
+      "epoch": 5.696969696969697,
+      "grad_norm": 0.3310711965914957,
+      "learning_rate": 2.054932085426856e-06,
+      "loss": 0.3797,
+      "step": 188
+    },
+    {
+      "epoch": 5.7272727272727275,
+      "grad_norm": 0.3370368521698809,
+      "learning_rate": 1.963688845450218e-06,
+      "loss": 0.3582,
+      "step": 189
+    },
+    {
+      "epoch": 5.757575757575758,
+      "grad_norm": 0.33096560047160006,
+      "learning_rate": 1.8742966099201699e-06,
+      "loss": 0.3692,
+      "step": 190
+    },
+    {
+      "epoch": 5.787878787878788,
+      "grad_norm": 0.3010735438457465,
+      "learning_rate": 1.7867759685603115e-06,
+      "loss": 0.3709,
+      "step": 191
+    },
+    {
+      "epoch": 5.818181818181818,
+      "grad_norm": 0.3126661813863104,
+      "learning_rate": 1.7011470800097496e-06,
+      "loss": 0.3823,
+      "step": 192
+    },
+    {
+      "epoch": 5.848484848484849,
+      "grad_norm": 0.3175598268657734,
+      "learning_rate": 1.6174296671799571e-06,
+      "loss": 0.3683,
+      "step": 193
+    },
+    {
+      "epoch": 5.878787878787879,
+      "grad_norm": 0.3236261627206911,
+      "learning_rate": 1.5356430127119915e-06,
+      "loss": 0.3752,
+      "step": 194
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 0.3332425708602334,
+      "learning_rate": 1.4558059545351144e-06,
+      "loss": 0.3658,
+      "step": 195
+    },
+    {
+      "epoch": 5.9393939393939394,
+      "grad_norm": 0.3152879170071617,
+      "learning_rate": 1.3779368815278648e-06,
+      "loss": 0.3635,
+      "step": 196
+    },
+    {
+      "epoch": 5.96969696969697,
+      "grad_norm": 0.30008582946052875,
+      "learning_rate": 1.302053729282533e-06,
+      "loss": 0.3679,
+      "step": 197
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.2977174824295516,
+      "learning_rate": 1.2281739759740575e-06,
+      "loss": 0.3767,
+      "step": 198
+    },
+    {
+      "epoch": 6.03030303030303,
+      "grad_norm": 0.3879029800082202,
+      "learning_rate": 1.156314638334277e-06,
+      "loss": 0.3407,
+      "step": 199
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "grad_norm": 0.3271155972576399,
+      "learning_rate": 1.086492267732462e-06,
+      "loss": 0.3591,
+      "step": 200
+    },
+    {
+      "epoch": 6.090909090909091,
+      "grad_norm": 0.34645313121663107,
+      "learning_rate": 1.01872294636304e-06,
+      "loss": 0.3483,
+      "step": 201
+    },
+    {
+      "epoch": 6.121212121212121,
+      "grad_norm": 0.28743262379825385,
+      "learning_rate": 9.530222835413739e-07,
+      "loss": 0.3508,
+      "step": 202
+    },
+    {
+      "epoch": 6.151515151515151,
+      "grad_norm": 0.29565754895347895,
+      "learning_rate": 8.894054121084839e-07,
+      "loss": 0.3446,
+      "step": 203
+    },
+    {
+      "epoch": 6.181818181818182,
+      "grad_norm": 0.30250529576379726,
+      "learning_rate": 8.278869849454718e-07,
+      "loss": 0.3476,
+      "step": 204
+    },
+    {
+      "epoch": 6.212121212121212,
+      "grad_norm": 0.3163060170935283,
+      "learning_rate": 7.684811715985429e-07,
+      "loss": 0.3543,
+      "step": 205
+    },
+    {
+      "epoch": 6.242424242424242,
+      "grad_norm": 0.3283811226544294,
+      "learning_rate": 7.1120165501533e-07,
+      "loss": 0.3575,
+      "step": 206
+    },
+    {
+      "epoch": 6.2727272727272725,
+      "grad_norm": 0.29942592377487787,
+      "learning_rate": 6.560616283932897e-07,
+      "loss": 0.3483,
+      "step": 207
+    },
+    {
+      "epoch": 6.303030303030303,
+      "grad_norm": 0.36862485605365164,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.3615,
+      "step": 208
+    },
+    {
+      "epoch": 6.333333333333333,
+      "grad_norm": 0.2949393074036796,
+      "learning_rate": 5.522503509524591e-07,
+      "loss": 0.3553,
+      "step": 209
+    },
+    {
+      "epoch": 6.363636363636363,
+      "grad_norm": 0.318252977076404,
+      "learning_rate": 5.036030109968082e-07,
+      "loss": 0.3525,
+      "step": 210
+    },
+    {
+      "epoch": 6.393939393939394,
+      "grad_norm": 0.3017808653775596,
+      "learning_rate": 4.5714297722121105e-07,
+      "loss": 0.3586,
+      "step": 211
+    },
+    {
+      "epoch": 6.424242424242424,
+      "grad_norm": 0.31274706811092523,
+      "learning_rate": 4.128809507704445e-07,
+      "loss": 0.371,
+      "step": 212
+    },
+    {
+      "epoch": 6.454545454545454,
+      "grad_norm": 0.2982929444465025,
+      "learning_rate": 3.708271265220087e-07,
+      "loss": 0.3369,
+      "step": 213
+    },
+    {
+      "epoch": 6.484848484848484,
+      "grad_norm": 0.2856931805359614,
+      "learning_rate": 3.309911907379393e-07,
+      "loss": 0.3441,
+      "step": 214
+    },
+    {
+      "epoch": 6.515151515151516,
+      "grad_norm": 0.295130199159678,
+      "learning_rate": 2.9338231883378365e-07,
+      "loss": 0.343,
+      "step": 215
+    },
+    {
+      "epoch": 6.545454545454545,
+      "grad_norm": 0.30638944417414304,
+      "learning_rate": 2.5800917326521013e-07,
+      "loss": 0.3446,
+      "step": 216
+    },
+    {
+      "epoch": 6.575757575757576,
+      "grad_norm": 0.2957235766685017,
+      "learning_rate": 2.248799015327907e-07,
+      "loss": 0.3559,
+      "step": 217
+    },
+    {
+      "epoch": 6.606060606060606,
+      "grad_norm": 0.303702542574936,
+      "learning_rate": 1.9400213430538773e-07,
+      "loss": 0.347,
+      "step": 218
+    },
+    {
+      "epoch": 6.636363636363637,
+      "grad_norm": 0.2851016218651606,
+      "learning_rate": 1.6538298366257975e-07,
+      "loss": 0.3496,
+      "step": 219
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.3034112904525307,
+      "learning_rate": 1.3902904145653094e-07,
+      "loss": 0.3466,
+      "step": 220
+    },
+    {
+      "epoch": 6.696969696969697,
+      "grad_norm": 0.29969234719385984,
+      "learning_rate": 1.1494637779369766e-07,
+      "loss": 0.3533,
+      "step": 221
+    },
+    {
+      "epoch": 6.7272727272727275,
+      "grad_norm": 0.2907347327578063,
+      "learning_rate": 9.314053963669245e-08,
+      "loss": 0.3477,
+      "step": 222
+    },
+    {
+      "epoch": 6.757575757575758,
+      "grad_norm": 0.27725605270722475,
+      "learning_rate": 7.361654952665608e-08,
+      "loss": 0.3512,
+      "step": 223
+    },
+    {
+      "epoch": 6.787878787878788,
+      "grad_norm": 0.2983284815250133,
+      "learning_rate": 5.637890442641403e-08,
+      "loss": 0.3547,
+      "step": 224
+    },
+    {
+      "epoch": 6.818181818181818,
+      "grad_norm": 0.29664319153122787,
+      "learning_rate": 4.143157468468717e-08,
+      "loss": 0.3648,
+      "step": 225
+    },
+    {
+      "epoch": 6.848484848484849,
+      "grad_norm": 0.291300393043478,
+      "learning_rate": 2.8778003121607834e-08,
+      "loss": 0.354,
+      "step": 226
+    },
+    {
+      "epoch": 6.878787878787879,
+      "grad_norm": 0.28479952634254985,
+      "learning_rate": 1.8421104235727406e-08,
+      "loss": 0.3475,
+      "step": 227
+    },
+    {
+      "epoch": 6.909090909090909,
+      "grad_norm": 0.30549072336004507,
+      "learning_rate": 1.0363263532724433e-08,
+      "loss": 0.3526,
+      "step": 228
+    },
+    {
+      "epoch": 6.9393939393939394,
+      "grad_norm": 0.28929693249167693,
+      "learning_rate": 4.606336975948589e-09,
+      "loss": 0.3469,
+      "step": 229
+    },
+    {
+      "epoch": 6.96969696969697,
+      "grad_norm": 0.2867666386627962,
+      "learning_rate": 1.1516505589381777e-09,
+      "loss": 0.3435,
+      "step": 230
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.30195503222447084,
+      "learning_rate": 0.0,
+      "loss": 0.3469,
+      "step": 231
+    },
+    {
+      "epoch": 7.0,
+      "step": 231,
+      "total_flos": 6.103710830103101e+17,
+      "train_loss": 0.5184378920695483,
+      "train_runtime": 8807.9751,
+      "train_samples_per_second": 2.511,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "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": 6.103710830103101e+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 sha256:332a567fea816c406a0d021d5f172946d3dd83e5c7a1f4085768728d861241d4
+size 7416