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_codeforces_neg_all_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_codeforces_neg_all_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_codeforces_neg_all_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": 6.415454425086689e+17,
+    "train_loss": 0.5228371008650049,
+    "train_runtime": 8840.4399,
+    "train_samples_per_second": 2.502,
+    "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 sha256:7a3673f3fcdaa3cba59a5b0d76c5564283949c1a88f6c306917b7901ec37db21
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1560603a4c7dba0ac3c7c4fb9a4f30e1f5bd2424f3bd4c1af3a8bec46fedcf
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942d15ea65f308e1f1c25c70233c735e746fc7e5ce7423590a3cee64c641287c
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ba7bfbaa4ed8cd42d399f2c52fb4fc5b1e47d39ab316f4b7eedd3d899ff00c
+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_20-08-06_jpbot-001-18.jupiter.internal/events.out.tfevents.1745690924.jpbot-001-18.jupiter.internal.2521428.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287dc6191df95eee9177be8c577f78e769c40f5b9a9cb6bba5a445d7060a9bd9
+size 54205

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 20:08:06", "end_time": "2025-04-26 22:36:13"}

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": 6.415454425086689e+17,
+    "train_loss": 0.5228371008650049,
+    "train_runtime": 8840.4399,
+    "train_samples_per_second": 2.502,
+    "train_steps_per_second": 0.026
+}

trainer_log.jsonl

@@ -0,0 +1,232 @@
+{"current_steps": 1, "total_steps": 231, "loss": 1.0428, "lr": 8.333333333333333e-07, "epoch": 0.030303030303030304, "percentage": 0.43, "elapsed_time": "0:00:43", "remaining_time": "2:45:04"}
+{"current_steps": 2, "total_steps": 231, "loss": 1.0483, "lr": 1.6666666666666667e-06, "epoch": 0.06060606060606061, "percentage": 0.87, "elapsed_time": "0:01:21", "remaining_time": "2:36:12"}
+{"current_steps": 3, "total_steps": 231, "loss": 1.0076, "lr": 2.5e-06, "epoch": 0.09090909090909091, "percentage": 1.3, "elapsed_time": "0:01:56", "remaining_time": "2:27:28"}
+{"current_steps": 4, "total_steps": 231, "loss": 1.0567, "lr": 3.3333333333333333e-06, "epoch": 0.12121212121212122, "percentage": 1.73, "elapsed_time": "0:02:33", "remaining_time": "2:24:54"}
+{"current_steps": 5, "total_steps": 231, "loss": 1.0084, "lr": 4.166666666666667e-06, "epoch": 0.15151515151515152, "percentage": 2.16, "elapsed_time": "0:03:12", "remaining_time": "2:24:53"}
+{"current_steps": 6, "total_steps": 231, "loss": 0.965, "lr": 5e-06, "epoch": 0.18181818181818182, "percentage": 2.6, "elapsed_time": "0:03:52", "remaining_time": "2:25:36"}
+{"current_steps": 7, "total_steps": 231, "loss": 0.9429, "lr": 5.833333333333334e-06, "epoch": 0.21212121212121213, "percentage": 3.03, "elapsed_time": "0:04:30", "remaining_time": "2:24:21"}
+{"current_steps": 8, "total_steps": 231, "loss": 0.9282, "lr": 6.666666666666667e-06, "epoch": 0.24242424242424243, "percentage": 3.46, "elapsed_time": "0:05:08", "remaining_time": "2:23:09"}
+{"current_steps": 9, "total_steps": 231, "loss": 0.9393, "lr": 7.500000000000001e-06, "epoch": 0.2727272727272727, "percentage": 3.9, "elapsed_time": "0:05:46", "remaining_time": "2:22:36"}
+{"current_steps": 10, "total_steps": 231, "loss": 0.9139, "lr": 8.333333333333334e-06, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "0:06:24", "remaining_time": "2:21:36"}
+{"current_steps": 11, "total_steps": 231, "loss": 0.8747, "lr": 9.166666666666666e-06, "epoch": 0.3333333333333333, "percentage": 4.76, "elapsed_time": "0:07:02", "remaining_time": "2:20:52"}
+{"current_steps": 12, "total_steps": 231, "loss": 0.8748, "lr": 1e-05, "epoch": 0.36363636363636365, "percentage": 5.19, "elapsed_time": "0:07:38", "remaining_time": "2:19:25"}
+{"current_steps": 13, "total_steps": 231, "loss": 0.8607, "lr": 1.0833333333333334e-05, "epoch": 0.3939393939393939, "percentage": 5.63, "elapsed_time": "0:08:15", "remaining_time": "2:18:21"}
+{"current_steps": 14, "total_steps": 231, "loss": 0.8153, "lr": 1.1666666666666668e-05, "epoch": 0.42424242424242425, "percentage": 6.06, "elapsed_time": "0:08:50", "remaining_time": "2:16:56"}
+{"current_steps": 15, "total_steps": 231, "loss": 0.8089, "lr": 1.25e-05, "epoch": 0.45454545454545453, "percentage": 6.49, "elapsed_time": "0:09:28", "remaining_time": "2:16:22"}
+{"current_steps": 16, "total_steps": 231, "loss": 0.7918, "lr": 1.3333333333333333e-05, "epoch": 0.48484848484848486, "percentage": 6.93, "elapsed_time": "0:10:07", "remaining_time": "2:16:05"}
+{"current_steps": 17, "total_steps": 231, "loss": 0.7809, "lr": 1.416666666666667e-05, "epoch": 0.5151515151515151, "percentage": 7.36, "elapsed_time": "0:10:45", "remaining_time": "2:15:19"}
+{"current_steps": 18, "total_steps": 231, "loss": 0.7785, "lr": 1.5000000000000002e-05, "epoch": 0.5454545454545454, "percentage": 7.79, "elapsed_time": "0:11:21", "remaining_time": "2:14:20"}
+{"current_steps": 19, "total_steps": 231, "loss": 0.7742, "lr": 1.5833333333333333e-05, "epoch": 0.5757575757575758, "percentage": 8.23, "elapsed_time": "0:11:57", "remaining_time": "2:13:23"}
+{"current_steps": 20, "total_steps": 231, "loss": 0.7509, "lr": 1.6666666666666667e-05, "epoch": 0.6060606060606061, "percentage": 8.66, "elapsed_time": "0:12:33", "remaining_time": "2:12:24"}
+{"current_steps": 21, "total_steps": 231, "loss": 0.7512, "lr": 1.7500000000000002e-05, "epoch": 0.6363636363636364, "percentage": 9.09, "elapsed_time": "0:13:10", "remaining_time": "2:11:48"}
+{"current_steps": 22, "total_steps": 231, "loss": 0.7381, "lr": 1.8333333333333333e-05, "epoch": 0.6666666666666666, "percentage": 9.52, "elapsed_time": "0:13:48", "remaining_time": "2:11:13"}
+{"current_steps": 23, "total_steps": 231, "loss": 0.7335, "lr": 1.916666666666667e-05, "epoch": 0.696969696969697, "percentage": 9.96, "elapsed_time": "0:14:28", "remaining_time": "2:10:51"}
+{"current_steps": 24, "total_steps": 231, "loss": 0.7342, "lr": 2e-05, "epoch": 0.7272727272727273, "percentage": 10.39, "elapsed_time": "0:15:07", "remaining_time": "2:10:30"}
+{"current_steps": 25, "total_steps": 231, "loss": 0.7162, "lr": 1.999884834944106e-05, "epoch": 0.7575757575757576, "percentage": 10.82, "elapsed_time": "0:15:44", "remaining_time": "2:09:40"}
+{"current_steps": 26, "total_steps": 231, "loss": 0.7068, "lr": 1.9995393663024054e-05, "epoch": 0.7878787878787878, "percentage": 11.26, "elapsed_time": "0:16:17", "remaining_time": "2:08:29"}
+{"current_steps": 27, "total_steps": 231, "loss": 0.7179, "lr": 1.9989636736467278e-05, "epoch": 0.8181818181818182, "percentage": 11.69, "elapsed_time": "0:16:53", "remaining_time": "2:07:37"}
+{"current_steps": 28, "total_steps": 231, "loss": 0.6952, "lr": 1.9981578895764272e-05, "epoch": 0.8484848484848485, "percentage": 12.12, "elapsed_time": "0:17:31", "remaining_time": "2:07:02"}
+{"current_steps": 29, "total_steps": 231, "loss": 0.7062, "lr": 1.9971221996878395e-05, "epoch": 0.8787878787878788, "percentage": 12.55, "elapsed_time": "0:18:07", "remaining_time": "2:06:13"}
+{"current_steps": 30, "total_steps": 231, "loss": 0.6895, "lr": 1.9958568425315316e-05, "epoch": 0.9090909090909091, "percentage": 12.99, "elapsed_time": "0:18:44", "remaining_time": "2:05:36"}
+{"current_steps": 31, "total_steps": 231, "loss": 0.7066, "lr": 1.9943621095573588e-05, "epoch": 0.9393939393939394, "percentage": 13.42, "elapsed_time": "0:19:23", "remaining_time": "2:05:08"}
+{"current_steps": 32, "total_steps": 231, "loss": 0.6939, "lr": 1.9926383450473344e-05, "epoch": 0.9696969696969697, "percentage": 13.85, "elapsed_time": "0:20:01", "remaining_time": "2:04:31"}
+{"current_steps": 33, "total_steps": 231, "loss": 0.6849, "lr": 1.9906859460363307e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:20:38", "remaining_time": "2:03:49"}
+{"current_steps": 34, "total_steps": 231, "loss": 0.6666, "lr": 1.9885053622206305e-05, "epoch": 1.0303030303030303, "percentage": 14.72, "elapsed_time": "0:21:45", "remaining_time": "2:06:06"}
+{"current_steps": 35, "total_steps": 231, "loss": 0.6617, "lr": 1.986097095854347e-05, "epoch": 1.0606060606060606, "percentage": 15.15, "elapsed_time": "0:22:23", "remaining_time": "2:05:26"}
+{"current_steps": 36, "total_steps": 231, "loss": 0.6661, "lr": 1.9834617016337424e-05, "epoch": 1.0909090909090908, "percentage": 15.58, "elapsed_time": "0:23:03", "remaining_time": "2:04:51"}
+{"current_steps": 37, "total_steps": 231, "loss": 0.6541, "lr": 1.9805997865694616e-05, "epoch": 1.121212121212121, "percentage": 16.02, "elapsed_time": "0:23:40", "remaining_time": "2:04:09"}
+{"current_steps": 38, "total_steps": 231, "loss": 0.6482, "lr": 1.9775120098467212e-05, "epoch": 1.1515151515151516, "percentage": 16.45, "elapsed_time": "0:24:15", "remaining_time": "2:03:14"}
+{"current_steps": 39, "total_steps": 231, "loss": 0.6538, "lr": 1.9741990826734793e-05, "epoch": 1.1818181818181819, "percentage": 16.88, "elapsed_time": "0:24:54", "remaining_time": "2:02:37"}
+{"current_steps": 40, "total_steps": 231, "loss": 0.6636, "lr": 1.970661768116622e-05, "epoch": 1.2121212121212122, "percentage": 17.32, "elapsed_time": "0:25:28", "remaining_time": "2:01:39"}
+{"current_steps": 41, "total_steps": 231, "loss": 0.6434, "lr": 1.9669008809262064e-05, "epoch": 1.2424242424242424, "percentage": 17.75, "elapsed_time": "0:26:04", "remaining_time": "2:00:51"}
+{"current_steps": 42, "total_steps": 231, "loss": 0.653, "lr": 1.9629172873477995e-05, "epoch": 1.2727272727272727, "percentage": 18.18, "elapsed_time": "0:26:42", "remaining_time": "2:00:10"}
+{"current_steps": 43, "total_steps": 231, "loss": 0.6362, "lr": 1.9587119049229558e-05, "epoch": 1.303030303030303, "percentage": 18.61, "elapsed_time": "0:27:21", "remaining_time": "1:59:37"}
+{"current_steps": 44, "total_steps": 231, "loss": 0.6295, "lr": 1.954285702277879e-05, "epoch": 1.3333333333333333, "percentage": 19.05, "elapsed_time": "0:27:59", "remaining_time": "1:58:56"}
+{"current_steps": 45, "total_steps": 231, "loss": 0.6233, "lr": 1.9496396989003195e-05, "epoch": 1.3636363636363638, "percentage": 19.48, "elapsed_time": "0:28:35", "remaining_time": "1:58:11"}
+{"current_steps": 46, "total_steps": 231, "loss": 0.6275, "lr": 1.944774964904754e-05, "epoch": 1.393939393939394, "percentage": 19.91, "elapsed_time": "0:29:11", "remaining_time": "1:57:24"}
+{"current_steps": 47, "total_steps": 231, "loss": 0.6271, "lr": 1.9396926207859085e-05, "epoch": 1.4242424242424243, "percentage": 20.35, "elapsed_time": "0:29:47", "remaining_time": "1:56:38"}
+{"current_steps": 48, "total_steps": 231, "loss": 0.6125, "lr": 1.9343938371606714e-05, "epoch": 1.4545454545454546, "percentage": 20.78, "elapsed_time": "0:30:22", "remaining_time": "1:55:49"}
+{"current_steps": 49, "total_steps": 231, "loss": 0.6398, "lr": 1.9288798344984673e-05, "epoch": 1.4848484848484849, "percentage": 21.21, "elapsed_time": "0:31:00", "remaining_time": "1:55:11"}
+{"current_steps": 50, "total_steps": 231, "loss": 0.6255, "lr": 1.9231518828401458e-05, "epoch": 1.5151515151515151, "percentage": 21.65, "elapsed_time": "0:31:38", "remaining_time": "1:54:33"}
+{"current_steps": 51, "total_steps": 231, "loss": 0.6259, "lr": 1.917211301505453e-05, "epoch": 1.5454545454545454, "percentage": 22.08, "elapsed_time": "0:32:15", "remaining_time": "1:53:51"}
+{"current_steps": 52, "total_steps": 231, "loss": 0.6235, "lr": 1.911059458789152e-05, "epoch": 1.5757575757575757, "percentage": 22.51, "elapsed_time": "0:32:52", "remaining_time": "1:53:08"}
+{"current_steps": 53, "total_steps": 231, "loss": 0.6017, "lr": 1.9046977716458627e-05, "epoch": 1.606060606060606, "percentage": 22.94, "elapsed_time": "0:33:27", "remaining_time": "1:52:23"}
+{"current_steps": 54, "total_steps": 231, "loss": 0.6113, "lr": 1.8981277053636963e-05, "epoch": 1.6363636363636362, "percentage": 23.38, "elapsed_time": "0:34:03", "remaining_time": "1:51:36"}
+{"current_steps": 55, "total_steps": 231, "loss": 0.6267, "lr": 1.891350773226754e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "0:34:41", "remaining_time": "1:51:00"}
+{"current_steps": 56, "total_steps": 231, "loss": 0.6301, "lr": 1.8843685361665724e-05, "epoch": 1.696969696969697, "percentage": 24.24, "elapsed_time": "0:35:18", "remaining_time": "1:50:20"}
+{"current_steps": 57, "total_steps": 231, "loss": 0.6296, "lr": 1.8771826024025944e-05, "epoch": 1.7272727272727273, "percentage": 24.68, "elapsed_time": "0:35:53", "remaining_time": "1:49:35"}
+{"current_steps": 58, "total_steps": 231, "loss": 0.6242, "lr": 1.8697946270717468e-05, "epoch": 1.7575757575757576, "percentage": 25.11, "elapsed_time": "0:36:31", "remaining_time": "1:48:55"}
+{"current_steps": 59, "total_steps": 231, "loss": 0.6238, "lr": 1.8622063118472135e-05, "epoch": 1.7878787878787878, "percentage": 25.54, "elapsed_time": "0:37:09", "remaining_time": "1:48:19"}
+{"current_steps": 60, "total_steps": 231, "loss": 0.6159, "lr": 1.8544194045464888e-05, "epoch": 1.8181818181818183, "percentage": 25.97, "elapsed_time": "0:37:47", "remaining_time": "1:47:40"}
+{"current_steps": 61, "total_steps": 231, "loss": 0.608, "lr": 1.8464356987288012e-05, "epoch": 1.8484848484848486, "percentage": 26.41, "elapsed_time": "0:38:22", "remaining_time": "1:46:58"}
+{"current_steps": 62, "total_steps": 231, "loss": 0.616, "lr": 1.8382570332820045e-05, "epoch": 1.878787878787879, "percentage": 26.84, "elapsed_time": "0:39:01", "remaining_time": "1:46:23"}
+{"current_steps": 63, "total_steps": 231, "loss": 0.6191, "lr": 1.8298852919990254e-05, "epoch": 1.9090909090909092, "percentage": 27.27, "elapsed_time": "0:39:39", "remaining_time": "1:45:44"}
+{"current_steps": 64, "total_steps": 231, "loss": 0.6365, "lr": 1.821322403143969e-05, "epoch": 1.9393939393939394, "percentage": 27.71, "elapsed_time": "0:40:16", "remaining_time": "1:45:05"}
+{"current_steps": 65, "total_steps": 231, "loss": 0.6143, "lr": 1.812570339007983e-05, "epoch": 1.9696969696969697, "percentage": 28.14, "elapsed_time": "0:40:51", "remaining_time": "1:44:20"}
+{"current_steps": 66, "total_steps": 231, "loss": 0.6266, "lr": 1.8036311154549783e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "0:41:29", "remaining_time": "1:43:43"}
+{"current_steps": 67, "total_steps": 231, "loss": 0.5654, "lr": 1.7945067914573147e-05, "epoch": 2.0303030303030303, "percentage": 29.0, "elapsed_time": "0:42:38", "remaining_time": "1:44:23"}
+{"current_steps": 68, "total_steps": 231, "loss": 0.5782, "lr": 1.7851994686215592e-05, "epoch": 2.0606060606060606, "percentage": 29.44, "elapsed_time": "0:43:14", "remaining_time": "1:43:40"}
+{"current_steps": 69, "total_steps": 231, "loss": 0.5641, "lr": 1.77571129070442e-05, "epoch": 2.090909090909091, "percentage": 29.87, "elapsed_time": "0:43:52", "remaining_time": "1:43:00"}
+{"current_steps": 70, "total_steps": 231, "loss": 0.5633, "lr": 1.766044443118978e-05, "epoch": 2.121212121212121, "percentage": 30.3, "elapsed_time": "0:44:31", "remaining_time": "1:42:23"}
+{"current_steps": 71, "total_steps": 231, "loss": 0.5498, "lr": 1.7562011524313187e-05, "epoch": 2.1515151515151514, "percentage": 30.74, "elapsed_time": "0:45:08", "remaining_time": "1:41:44"}
+{"current_steps": 72, "total_steps": 231, "loss": 0.5583, "lr": 1.7461836858476858e-05, "epoch": 2.1818181818181817, "percentage": 31.17, "elapsed_time": "0:45:46", "remaining_time": "1:41:05"}
+{"current_steps": 73, "total_steps": 231, "loss": 0.558, "lr": 1.7359943506922775e-05, "epoch": 2.212121212121212, "percentage": 31.6, "elapsed_time": "0:46:23", "remaining_time": "1:40:24"}
+{"current_steps": 74, "total_steps": 231, "loss": 0.5502, "lr": 1.725635493875799e-05, "epoch": 2.242424242424242, "percentage": 32.03, "elapsed_time": "0:46:59", "remaining_time": "1:39:41"}
+{"current_steps": 75, "total_steps": 231, "loss": 0.5432, "lr": 1.7151095013548996e-05, "epoch": 2.2727272727272725, "percentage": 32.47, "elapsed_time": "0:47:36", "remaining_time": "1:39:00"}
+{"current_steps": 76, "total_steps": 231, "loss": 0.5341, "lr": 1.7044187975826126e-05, "epoch": 2.303030303030303, "percentage": 32.9, "elapsed_time": "0:48:12", "remaining_time": "1:38:18"}
+{"current_steps": 77, "total_steps": 231, "loss": 0.553, "lr": 1.693565844949933e-05, "epoch": 2.3333333333333335, "percentage": 33.33, "elapsed_time": "0:48:50", "remaining_time": "1:37:41"}
+{"current_steps": 78, "total_steps": 231, "loss": 0.5423, "lr": 1.6825531432186545e-05, "epoch": 2.3636363636363638, "percentage": 33.77, "elapsed_time": "0:49:24", "remaining_time": "1:36:54"}
+{"current_steps": 79, "total_steps": 231, "loss": 0.5507, "lr": 1.671383228945597e-05, "epoch": 2.393939393939394, "percentage": 34.2, "elapsed_time": "0:49:58", "remaining_time": "1:36:09"}
+{"current_steps": 80, "total_steps": 231, "loss": 0.5455, "lr": 1.6600586748983642e-05, "epoch": 2.4242424242424243, "percentage": 34.63, "elapsed_time": "0:50:37", "remaining_time": "1:35:33"}
+{"current_steps": 81, "total_steps": 231, "loss": 0.5592, "lr": 1.648582089462756e-05, "epoch": 2.4545454545454546, "percentage": 35.06, "elapsed_time": "0:51:15", "remaining_time": "1:34:55"}
+{"current_steps": 82, "total_steps": 231, "loss": 0.5533, "lr": 1.6369561160419783e-05, "epoch": 2.484848484848485, "percentage": 35.5, "elapsed_time": "0:51:52", "remaining_time": "1:34:15"}
+{"current_steps": 83, "total_steps": 231, "loss": 0.5527, "lr": 1.625183432447789e-05, "epoch": 2.515151515151515, "percentage": 35.93, "elapsed_time": "0:52:30", "remaining_time": "1:33:37"}
+{"current_steps": 84, "total_steps": 231, "loss": 0.5506, "lr": 1.6132667502837164e-05, "epoch": 2.5454545454545454, "percentage": 36.36, "elapsed_time": "0:53:07", "remaining_time": "1:32:57"}
+{"current_steps": 85, "total_steps": 231, "loss": 0.5718, "lr": 1.6012088143204953e-05, "epoch": 2.5757575757575757, "percentage": 36.8, "elapsed_time": "0:53:46", "remaining_time": "1:32:21"}
+{"current_steps": 86, "total_steps": 231, "loss": 0.5567, "lr": 1.589012401863864e-05, "epoch": 2.606060606060606, "percentage": 37.23, "elapsed_time": "0:54:22", "remaining_time": "1:31:40"}
+{"current_steps": 87, "total_steps": 231, "loss": 0.5429, "lr": 1.5766803221148676e-05, "epoch": 2.6363636363636362, "percentage": 37.66, "elapsed_time": "0:54:59", "remaining_time": "1:31:01"}
+{"current_steps": 88, "total_steps": 231, "loss": 0.55, "lr": 1.5642154155228124e-05, "epoch": 2.6666666666666665, "percentage": 38.1, "elapsed_time": "0:55:37", "remaining_time": "1:30:23"}
+{"current_steps": 89, "total_steps": 231, "loss": 0.5369, "lr": 1.5516205531310272e-05, "epoch": 2.6969696969696972, "percentage": 38.53, "elapsed_time": "0:56:14", "remaining_time": "1:29:44"}
+{"current_steps": 90, "total_steps": 231, "loss": 0.5514, "lr": 1.538898635915576e-05, "epoch": 2.7272727272727275, "percentage": 38.96, "elapsed_time": "0:56:52", "remaining_time": "1:29:06"}
+{"current_steps": 91, "total_steps": 231, "loss": 0.5428, "lr": 1.526052594117071e-05, "epoch": 2.757575757575758, "percentage": 39.39, "elapsed_time": "0:57:30", "remaining_time": "1:28:29"}
+{"current_steps": 92, "total_steps": 231, "loss": 0.5442, "lr": 1.513085386565758e-05, "epoch": 2.787878787878788, "percentage": 39.83, "elapsed_time": "0:58:08", "remaining_time": "1:27:51"}
+{"current_steps": 93, "total_steps": 231, "loss": 0.5629, "lr": 1.5000000000000002e-05, "epoch": 2.8181818181818183, "percentage": 40.26, "elapsed_time": "0:58:45", "remaining_time": "1:27:11"}
+{"current_steps": 94, "total_steps": 231, "loss": 0.5399, "lr": 1.4867994483783485e-05, "epoch": 2.8484848484848486, "percentage": 40.69, "elapsed_time": "0:59:22", "remaining_time": "1:26:32"}
+{"current_steps": 95, "total_steps": 231, "loss": 0.5388, "lr": 1.4734867721853341e-05, "epoch": 2.878787878787879, "percentage": 41.13, "elapsed_time": "1:00:00", "remaining_time": "1:25:53"}
+{"current_steps": 96, "total_steps": 231, "loss": 0.5412, "lr": 1.4600650377311523e-05, "epoch": 2.909090909090909, "percentage": 41.56, "elapsed_time": "1:00:38", "remaining_time": "1:25:17"}
+{"current_steps": 97, "total_steps": 231, "loss": 0.5496, "lr": 1.4465373364454001e-05, "epoch": 2.9393939393939394, "percentage": 41.99, "elapsed_time": "1:01:17", "remaining_time": "1:24:40"}
+{"current_steps": 98, "total_steps": 231, "loss": 0.5333, "lr": 1.4329067841650274e-05, "epoch": 2.9696969696969697, "percentage": 42.42, "elapsed_time": "1:01:56", "remaining_time": "1:24:04"}
+{"current_steps": 99, "total_steps": 231, "loss": 0.5419, "lr": 1.4191765204166643e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "1:02:35", "remaining_time": "1:23:27"}
+{"current_steps": 100, "total_steps": 231, "loss": 0.497, "lr": 1.4053497076934948e-05, "epoch": 3.0303030303030303, "percentage": 43.29, "elapsed_time": "1:03:44", "remaining_time": "1:23:30"}
+{"current_steps": 101, "total_steps": 231, "loss": 0.4843, "lr": 1.3914295307268396e-05, "epoch": 3.0606060606060606, "percentage": 43.72, "elapsed_time": "1:04:21", "remaining_time": "1:22:50"}
+{"current_steps": 102, "total_steps": 231, "loss": 0.4917, "lr": 1.3774191957526144e-05, "epoch": 3.090909090909091, "percentage": 44.16, "elapsed_time": "1:04:56", "remaining_time": "1:22:08"}
+{"current_steps": 103, "total_steps": 231, "loss": 0.5018, "lr": 1.3633219297728415e-05, "epoch": 3.121212121212121, "percentage": 44.59, "elapsed_time": "1:05:34", "remaining_time": "1:21:29"}
+{"current_steps": 104, "total_steps": 231, "loss": 0.4821, "lr": 1.3491409798123687e-05, "epoch": 3.1515151515151514, "percentage": 45.02, "elapsed_time": "1:06:09", "remaining_time": "1:20:47"}
+{"current_steps": 105, "total_steps": 231, "loss": 0.4955, "lr": 1.3348796121709862e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "1:06:48", "remaining_time": "1:20:10"}
+{"current_steps": 106, "total_steps": 231, "loss": 0.4774, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "1:07:23", "remaining_time": "1:19:28"}
+{"current_steps": 107, "total_steps": 231, "loss": 0.5004, "lr": 1.3061287809011243e-05, "epoch": 3.242424242424242, "percentage": 46.32, "elapsed_time": "1:08:03", "remaining_time": "1:18:51"}
+{"current_steps": 108, "total_steps": 231, "loss": 0.4782, "lr": 1.291645939454825e-05, "epoch": 3.2727272727272725, "percentage": 46.75, "elapsed_time": "1:08:38", "remaining_time": "1:18:10"}
+{"current_steps": 109, "total_steps": 231, "loss": 0.4872, "lr": 1.277095923166689e-05, "epoch": 3.303030303030303, "percentage": 47.19, "elapsed_time": "1:09:13", "remaining_time": "1:17:29"}
+{"current_steps": 110, "total_steps": 231, "loss": 0.4892, "lr": 1.2624820833435939e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "1:09:50", "remaining_time": "1:16:49"}
+{"current_steps": 111, "total_steps": 231, "loss": 0.4859, "lr": 1.2478077859929e-05, "epoch": 3.3636363636363638, "percentage": 48.05, "elapsed_time": "1:10:27", "remaining_time": "1:16:10"}
+{"current_steps": 112, "total_steps": 231, "loss": 0.4866, "lr": 1.2330764110471567e-05, "epoch": 3.393939393939394, "percentage": 48.48, "elapsed_time": "1:11:03", "remaining_time": "1:15:30"}
+{"current_steps": 113, "total_steps": 231, "loss": 0.4801, "lr": 1.2182913515856016e-05, "epoch": 3.4242424242424243, "percentage": 48.92, "elapsed_time": "1:11:41", "remaining_time": "1:14:51"}
+{"current_steps": 114, "total_steps": 231, "loss": 0.4867, "lr": 1.2034560130526341e-05, "epoch": 3.4545454545454546, "percentage": 49.35, "elapsed_time": "1:12:19", "remaining_time": "1:14:14"}
+{"current_steps": 115, "total_steps": 231, "loss": 0.4721, "lr": 1.1885738124734359e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "1:12:54", "remaining_time": "1:13:32"}
+{"current_steps": 116, "total_steps": 231, "loss": 0.4864, "lr": 1.1736481776669307e-05, "epoch": 3.515151515151515, "percentage": 50.22, "elapsed_time": "1:13:32", "remaining_time": "1:12:54"}
+{"current_steps": 117, "total_steps": 231, "loss": 0.4764, "lr": 1.1586825464562515e-05, "epoch": 3.5454545454545454, "percentage": 50.65, "elapsed_time": "1:14:09", "remaining_time": "1:12:15"}
+{"current_steps": 118, "total_steps": 231, "loss": 0.4949, "lr": 1.1436803658769082e-05, "epoch": 3.5757575757575757, "percentage": 51.08, "elapsed_time": "1:14:46", "remaining_time": "1:11:36"}
+{"current_steps": 119, "total_steps": 231, "loss": 0.4979, "lr": 1.1286450913828313e-05, "epoch": 3.606060606060606, "percentage": 51.52, "elapsed_time": "1:15:23", "remaining_time": "1:10:57"}
+{"current_steps": 120, "total_steps": 231, "loss": 0.4752, "lr": 1.113580186050475e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "1:15:55", "remaining_time": "1:10:14"}
+{"current_steps": 121, "total_steps": 231, "loss": 0.4753, "lr": 1.0984891197811686e-05, "epoch": 3.6666666666666665, "percentage": 52.38, "elapsed_time": "1:16:32", "remaining_time": "1:09:35"}
+{"current_steps": 122, "total_steps": 231, "loss": 0.4758, "lr": 1.0833753685018935e-05, "epoch": 3.6969696969696972, "percentage": 52.81, "elapsed_time": "1:17:10", "remaining_time": "1:08:56"}
+{"current_steps": 123, "total_steps": 231, "loss": 0.4852, "lr": 1.0682424133646712e-05, "epoch": 3.7272727272727275, "percentage": 53.25, "elapsed_time": "1:17:48", "remaining_time": "1:08:18"}
+{"current_steps": 124, "total_steps": 231, "loss": 0.4738, "lr": 1.0530937399447496e-05, "epoch": 3.757575757575758, "percentage": 53.68, "elapsed_time": "1:18:27", "remaining_time": "1:07:42"}
+{"current_steps": 125, "total_steps": 231, "loss": 0.4866, "lr": 1.0379328374377715e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "1:19:06", "remaining_time": "1:07:05"}
+{"current_steps": 126, "total_steps": 231, "loss": 0.4787, "lr": 1.0227631978561057e-05, "epoch": 3.8181818181818183, "percentage": 54.55, "elapsed_time": "1:19:44", "remaining_time": "1:06:26"}
+{"current_steps": 127, "total_steps": 231, "loss": 0.4798, "lr": 1.0075883152245334e-05, "epoch": 3.8484848484848486, "percentage": 54.98, "elapsed_time": "1:20:21", "remaining_time": "1:05:48"}
+{"current_steps": 128, "total_steps": 231, "loss": 0.4787, "lr": 9.92411684775467e-06, "epoch": 3.878787878787879, "percentage": 55.41, "elapsed_time": "1:21:00", "remaining_time": "1:05:11"}
+{"current_steps": 129, "total_steps": 231, "loss": 0.4862, "lr": 9.772368021438943e-06, "epoch": 3.909090909090909, "percentage": 55.84, "elapsed_time": "1:21:40", "remaining_time": "1:04:34"}
+{"current_steps": 130, "total_steps": 231, "loss": 0.4801, "lr": 9.620671625622287e-06, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "1:22:16", "remaining_time": "1:03:55"}
+{"current_steps": 131, "total_steps": 231, "loss": 0.4889, "lr": 9.469062600552509e-06, "epoch": 3.9696969696969697, "percentage": 56.71, "elapsed_time": "1:22:55", "remaining_time": "1:03:18"}
+{"current_steps": 132, "total_steps": 231, "loss": 0.4613, "lr": 9.317575866353293e-06, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "1:23:32", "remaining_time": "1:02:39"}
+{"current_steps": 133, "total_steps": 231, "loss": 0.4256, "lr": 9.166246314981066e-06, "epoch": 4.03030303030303, "percentage": 57.58, "elapsed_time": "1:24:44", "remaining_time": "1:02:26"}
+{"current_steps": 134, "total_steps": 231, "loss": 0.4333, "lr": 9.015108802188314e-06, "epoch": 4.0606060606060606, "percentage": 58.01, "elapsed_time": "1:25:20", "remaining_time": "1:01:46"}
+{"current_steps": 135, "total_steps": 231, "loss": 0.4265, "lr": 8.86419813949525e-06, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "1:25:58", "remaining_time": "1:01:08"}
+{"current_steps": 136, "total_steps": 231, "loss": 0.4209, "lr": 8.71354908617169e-06, "epoch": 4.121212121212121, "percentage": 58.87, "elapsed_time": "1:26:36", "remaining_time": "1:00:30"}
+{"current_steps": 137, "total_steps": 231, "loss": 0.4283, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "1:27:14", "remaining_time": "0:59:51"}
+{"current_steps": 138, "total_steps": 231, "loss": 0.4189, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "1:27:53", "remaining_time": "0:59:13"}
+{"current_steps": 139, "total_steps": 231, "loss": 0.4273, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "1:28:29", "remaining_time": "0:58:34"}
+{"current_steps": 140, "total_steps": 231, "loss": 0.428, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "1:29:05", "remaining_time": "0:57:54"}
+{"current_steps": 141, "total_steps": 231, "loss": 0.4232, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "1:29:42", "remaining_time": "0:57:15"}
+{"current_steps": 142, "total_steps": 231, "loss": 0.433, "lr": 7.817086484143987e-06, "epoch": 4.303030303030303, "percentage": 61.47, "elapsed_time": "1:30:21", "remaining_time": "0:56:38"}
+{"current_steps": 143, "total_steps": 231, "loss": 0.4196, "lr": 7.669235889528436e-06, "epoch": 4.333333333333333, "percentage": 61.9, "elapsed_time": "1:30:59", "remaining_time": "0:55:59"}
+{"current_steps": 144, "total_steps": 231, "loss": 0.4225, "lr": 7.521922140071003e-06, "epoch": 4.363636363636363, "percentage": 62.34, "elapsed_time": "1:31:38", "remaining_time": "0:55:22"}
+{"current_steps": 145, "total_steps": 231, "loss": 0.4231, "lr": 7.375179166564062e-06, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "1:32:15", "remaining_time": "0:54:43"}
+{"current_steps": 146, "total_steps": 231, "loss": 0.4206, "lr": 7.2290407683331154e-06, "epoch": 4.424242424242424, "percentage": 63.2, "elapsed_time": "1:32:50", "remaining_time": "0:54:03"}
+{"current_steps": 147, "total_steps": 231, "loss": 0.4261, "lr": 7.0835406054517505e-06, "epoch": 4.454545454545454, "percentage": 63.64, "elapsed_time": "1:33:24", "remaining_time": "0:53:22"}
+{"current_steps": 148, "total_steps": 231, "loss": 0.4203, "lr": 6.93871219098876e-06, "epoch": 4.484848484848484, "percentage": 64.07, "elapsed_time": "1:33:59", "remaining_time": "0:52:42"}
+{"current_steps": 149, "total_steps": 231, "loss": 0.4216, "lr": 6.79458888328903e-06, "epoch": 4.515151515151516, "percentage": 64.5, "elapsed_time": "1:34:38", "remaining_time": "0:52:05"}
+{"current_steps": 150, "total_steps": 231, "loss": 0.4265, "lr": 6.651203878290139e-06, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "1:35:16", "remaining_time": "0:51:26"}
+{"current_steps": 151, "total_steps": 231, "loss": 0.4179, "lr": 6.508590201876317e-06, "epoch": 4.575757575757576, "percentage": 65.37, "elapsed_time": "1:35:51", "remaining_time": "0:50:47"}
+{"current_steps": 152, "total_steps": 231, "loss": 0.4196, "lr": 6.366780702271589e-06, "epoch": 4.606060606060606, "percentage": 65.8, "elapsed_time": "1:36:26", "remaining_time": "0:50:07"}
+{"current_steps": 153, "total_steps": 231, "loss": 0.4309, "lr": 6.225808042473857e-06, "epoch": 4.636363636363637, "percentage": 66.23, "elapsed_time": "1:37:02", "remaining_time": "0:49:28"}
+{"current_steps": 154, "total_steps": 231, "loss": 0.4318, "lr": 6.085704692731609e-06, "epoch": 4.666666666666667, "percentage": 66.67, "elapsed_time": "1:37:41", "remaining_time": "0:48:50"}
+{"current_steps": 155, "total_steps": 231, "loss": 0.4474, "lr": 5.946502923065054e-06, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "1:38:19", "remaining_time": "0:48:12"}
+{"current_steps": 156, "total_steps": 231, "loss": 0.4195, "lr": 5.8082347958333625e-06, "epoch": 4.7272727272727275, "percentage": 67.53, "elapsed_time": "1:38:53", "remaining_time": "0:47:32"}
+{"current_steps": 157, "total_steps": 231, "loss": 0.4247, "lr": 5.670932158349732e-06, "epoch": 4.757575757575758, "percentage": 67.97, "elapsed_time": "1:39:27", "remaining_time": "0:46:52"}
+{"current_steps": 158, "total_steps": 231, "loss": 0.4328, "lr": 5.534626635546e-06, "epoch": 4.787878787878788, "percentage": 68.4, "elapsed_time": "1:40:02", "remaining_time": "0:46:13"}
+{"current_steps": 159, "total_steps": 231, "loss": 0.4291, "lr": 5.399349622688479e-06, "epoch": 4.818181818181818, "percentage": 68.83, "elapsed_time": "1:40:40", "remaining_time": "0:45:35"}
+{"current_steps": 160, "total_steps": 231, "loss": 0.4338, "lr": 5.2651322781466606e-06, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "1:41:19", "remaining_time": "0:44:57"}
+{"current_steps": 161, "total_steps": 231, "loss": 0.4129, "lr": 5.132005516216512e-06, "epoch": 4.878787878787879, "percentage": 69.7, "elapsed_time": "1:41:53", "remaining_time": "0:44:18"}
+{"current_steps": 162, "total_steps": 231, "loss": 0.4238, "lr": 5.000000000000003e-06, "epoch": 4.909090909090909, "percentage": 70.13, "elapsed_time": "1:42:29", "remaining_time": "0:43:39"}
+{"current_steps": 163, "total_steps": 231, "loss": 0.4307, "lr": 4.869146134342426e-06, "epoch": 4.9393939393939394, "percentage": 70.56, "elapsed_time": "1:43:09", "remaining_time": "0:43:01"}
+{"current_steps": 164, "total_steps": 231, "loss": 0.4196, "lr": 4.739474058829288e-06, "epoch": 4.96969696969697, "percentage": 71.0, "elapsed_time": "1:43:44", "remaining_time": "0:42:23"}
+{"current_steps": 165, "total_steps": 231, "loss": 0.4253, "lr": 4.611013640844245e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:44:21", "remaining_time": "0:41:44"}
+{"current_steps": 166, "total_steps": 231, "loss": 0.3872, "lr": 4.483794468689728e-06, "epoch": 5.03030303030303, "percentage": 71.86, "elapsed_time": "1:45:28", "remaining_time": "0:41:18"}
+{"current_steps": 167, "total_steps": 231, "loss": 0.3822, "lr": 4.357845844771881e-06, "epoch": 5.0606060606060606, "percentage": 72.29, "elapsed_time": "1:46:08", "remaining_time": "0:40:40"}
+{"current_steps": 168, "total_steps": 231, "loss": 0.3778, "lr": 4.2331967788513295e-06, "epoch": 5.090909090909091, "percentage": 72.73, "elapsed_time": "1:46:45", "remaining_time": "0:40:02"}
+{"current_steps": 169, "total_steps": 231, "loss": 0.3863, "lr": 4.109875981361363e-06, "epoch": 5.121212121212121, "percentage": 73.16, "elapsed_time": "1:47:22", "remaining_time": "0:39:23"}
+{"current_steps": 170, "total_steps": 231, "loss": 0.3793, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:48:00", "remaining_time": "0:38:45"}
+{"current_steps": 171, "total_steps": 231, "loss": 0.3765, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:48:37", "remaining_time": "0:38:06"}
+{"current_steps": 172, "total_steps": 231, "loss": 0.3809, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:49:14", "remaining_time": "0:37:28"}
+{"current_steps": 173, "total_steps": 231, "loss": 0.3858, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:49:52", "remaining_time": "0:36:50"}
+{"current_steps": 174, "total_steps": 231, "loss": 0.38, "lr": 3.5141791053724405e-06, "epoch": 5.2727272727272725, "percentage": 75.32, "elapsed_time": "1:50:28", "remaining_time": "0:36:11"}
+{"current_steps": 175, "total_steps": 231, "loss": 0.3745, "lr": 3.399413251016359e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:51:07", "remaining_time": "0:35:33"}
+{"current_steps": 176, "total_steps": 231, "loss": 0.3728, "lr": 3.2861677105440335e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "1:51:44", "remaining_time": "0:34:55"}
+{"current_steps": 177, "total_steps": 231, "loss": 0.3706, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "1:52:20", "remaining_time": "0:34:16"}
+{"current_steps": 178, "total_steps": 231, "loss": 0.3814, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "1:52:56", "remaining_time": "0:33:37"}
+{"current_steps": 179, "total_steps": 231, "loss": 0.3639, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "1:53:34", "remaining_time": "0:32:59"}
+{"current_steps": 180, "total_steps": 231, "loss": 0.3807, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:54:12", "remaining_time": "0:32:21"}
+{"current_steps": 181, "total_steps": 231, "loss": 0.3798, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "1:54:50", "remaining_time": "0:31:43"}
+{"current_steps": 182, "total_steps": 231, "loss": 0.3881, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "1:55:28", "remaining_time": "0:31:05"}
+{"current_steps": 183, "total_steps": 231, "loss": 0.3847, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "1:56:07", "remaining_time": "0:30:27"}
+{"current_steps": 184, "total_steps": 231, "loss": 0.3719, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "1:56:44", "remaining_time": "0:29:49"}
+{"current_steps": 185, "total_steps": 231, "loss": 0.3977, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:57:20", "remaining_time": "0:29:10"}
+{"current_steps": 186, "total_steps": 231, "loss": 0.3835, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "1:57:54", "remaining_time": "0:28:31"}
+{"current_steps": 187, "total_steps": 231, "loss": 0.3852, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "1:58:30", "remaining_time": "0:27:53"}
+{"current_steps": 188, "total_steps": 231, "loss": 0.3858, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "1:59:08", "remaining_time": "0:27:14"}
+{"current_steps": 189, "total_steps": 231, "loss": 0.3876, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "1:59:45", "remaining_time": "0:26:36"}
+{"current_steps": 190, "total_steps": 231, "loss": 0.3715, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "2:00:23", "remaining_time": "0:25:58"}
+{"current_steps": 191, "total_steps": 231, "loss": 0.3797, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "2:00:59", "remaining_time": "0:25:20"}
+{"current_steps": 192, "total_steps": 231, "loss": 0.3922, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "2:01:36", "remaining_time": "0:24:42"}
+{"current_steps": 193, "total_steps": 231, "loss": 0.3737, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "2:02:11", "remaining_time": "0:24:03"}
+{"current_steps": 194, "total_steps": 231, "loss": 0.3838, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "2:02:50", "remaining_time": "0:23:25"}
+{"current_steps": 195, "total_steps": 231, "loss": 0.375, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "2:03:29", "remaining_time": "0:22:47"}
+{"current_steps": 196, "total_steps": 231, "loss": 0.3841, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "2:04:07", "remaining_time": "0:22:09"}
+{"current_steps": 197, "total_steps": 231, "loss": 0.3955, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "2:04:44", "remaining_time": "0:21:31"}
+{"current_steps": 198, "total_steps": 231, "loss": 0.3862, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "2:05:19", "remaining_time": "0:20:53"}
+{"current_steps": 199, "total_steps": 231, "loss": 0.3559, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "2:06:33", "remaining_time": "0:20:21"}
+{"current_steps": 200, "total_steps": 231, "loss": 0.3621, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "2:07:09", "remaining_time": "0:19:42"}
+{"current_steps": 201, "total_steps": 231, "loss": 0.3664, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "2:07:44", "remaining_time": "0:19:03"}
+{"current_steps": 202, "total_steps": 231, "loss": 0.3701, "lr": 9.530222835413739e-07, "epoch": 6.121212121212121, "percentage": 87.45, "elapsed_time": "2:08:20", "remaining_time": "0:18:25"}
+{"current_steps": 203, "total_steps": 231, "loss": 0.3594, "lr": 8.894054121084839e-07, "epoch": 6.151515151515151, "percentage": 87.88, "elapsed_time": "2:08:57", "remaining_time": "0:17:47"}
+{"current_steps": 204, "total_steps": 231, "loss": 0.3478, "lr": 8.278869849454718e-07, "epoch": 6.181818181818182, "percentage": 88.31, "elapsed_time": "2:09:32", "remaining_time": "0:17:08"}
+{"current_steps": 205, "total_steps": 231, "loss": 0.3601, "lr": 7.684811715985429e-07, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "2:10:10", "remaining_time": "0:16:30"}
+{"current_steps": 206, "total_steps": 231, "loss": 0.357, "lr": 7.1120165501533e-07, "epoch": 6.242424242424242, "percentage": 89.18, "elapsed_time": "2:10:46", "remaining_time": "0:15:52"}
+{"current_steps": 207, "total_steps": 231, "loss": 0.3621, "lr": 6.560616283932897e-07, "epoch": 6.2727272727272725, "percentage": 89.61, "elapsed_time": "2:11:25", "remaining_time": "0:15:14"}
+{"current_steps": 208, "total_steps": 231, "loss": 0.3553, "lr": 6.030737921409169e-07, "epoch": 6.303030303030303, "percentage": 90.04, "elapsed_time": "2:12:02", "remaining_time": "0:14:36"}
+{"current_steps": 209, "total_steps": 231, "loss": 0.3624, "lr": 5.522503509524591e-07, "epoch": 6.333333333333333, "percentage": 90.48, "elapsed_time": "2:12:40", "remaining_time": "0:13:57"}
+{"current_steps": 210, "total_steps": 231, "loss": 0.3728, "lr": 5.036030109968082e-07, "epoch": 6.363636363636363, "percentage": 90.91, "elapsed_time": "2:13:18", "remaining_time": "0:13:19"}
+{"current_steps": 211, "total_steps": 231, "loss": 0.3594, "lr": 4.5714297722121105e-07, "epoch": 6.393939393939394, "percentage": 91.34, "elapsed_time": "2:13:55", "remaining_time": "0:12:41"}
+{"current_steps": 212, "total_steps": 231, "loss": 0.3534, "lr": 4.128809507704445e-07, "epoch": 6.424242424242424, "percentage": 91.77, "elapsed_time": "2:14:29", "remaining_time": "0:12:03"}
+{"current_steps": 213, "total_steps": 231, "loss": 0.3545, "lr": 3.708271265220087e-07, "epoch": 6.454545454545454, "percentage": 92.21, "elapsed_time": "2:15:06", "remaining_time": "0:11:25"}
+{"current_steps": 214, "total_steps": 231, "loss": 0.368, "lr": 3.309911907379393e-07, "epoch": 6.484848484848484, "percentage": 92.64, "elapsed_time": "2:15:44", "remaining_time": "0:10:47"}
+{"current_steps": 215, "total_steps": 231, "loss": 0.3614, "lr": 2.9338231883378365e-07, "epoch": 6.515151515151516, "percentage": 93.07, "elapsed_time": "2:16:23", "remaining_time": "0:10:08"}
+{"current_steps": 216, "total_steps": 231, "loss": 0.3576, "lr": 2.5800917326521013e-07, "epoch": 6.545454545454545, "percentage": 93.51, "elapsed_time": "2:17:00", "remaining_time": "0:09:30"}
+{"current_steps": 217, "total_steps": 231, "loss": 0.3552, "lr": 2.248799015327907e-07, "epoch": 6.575757575757576, "percentage": 93.94, "elapsed_time": "2:17:36", "remaining_time": "0:08:52"}
+{"current_steps": 218, "total_steps": 231, "loss": 0.3474, "lr": 1.9400213430538773e-07, "epoch": 6.606060606060606, "percentage": 94.37, "elapsed_time": "2:18:10", "remaining_time": "0:08:14"}
+{"current_steps": 219, "total_steps": 231, "loss": 0.3589, "lr": 1.6538298366257975e-07, "epoch": 6.636363636363637, "percentage": 94.81, "elapsed_time": "2:18:48", "remaining_time": "0:07:36"}
+{"current_steps": 220, "total_steps": 231, "loss": 0.3627, "lr": 1.3902904145653094e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "2:19:23", "remaining_time": "0:06:58"}
+{"current_steps": 221, "total_steps": 231, "loss": 0.3625, "lr": 1.1494637779369766e-07, "epoch": 6.696969696969697, "percentage": 95.67, "elapsed_time": "2:20:02", "remaining_time": "0:06:20"}
+{"current_steps": 222, "total_steps": 231, "loss": 0.3597, "lr": 9.314053963669245e-08, "epoch": 6.7272727272727275, "percentage": 96.1, "elapsed_time": "2:20:39", "remaining_time": "0:05:42"}
+{"current_steps": 223, "total_steps": 231, "loss": 0.3674, "lr": 7.361654952665608e-08, "epoch": 6.757575757575758, "percentage": 96.54, "elapsed_time": "2:21:17", "remaining_time": "0:05:04"}
+{"current_steps": 224, "total_steps": 231, "loss": 0.3565, "lr": 5.637890442641403e-08, "epoch": 6.787878787878788, "percentage": 96.97, "elapsed_time": "2:21:53", "remaining_time": "0:04:26"}
+{"current_steps": 225, "total_steps": 231, "loss": 0.3538, "lr": 4.143157468468717e-08, "epoch": 6.818181818181818, "percentage": 97.4, "elapsed_time": "2:22:30", "remaining_time": "0:03:48"}
+{"current_steps": 226, "total_steps": 231, "loss": 0.3784, "lr": 2.8778003121607834e-08, "epoch": 6.848484848484849, "percentage": 97.84, "elapsed_time": "2:23:09", "remaining_time": "0:03:10"}
+{"current_steps": 227, "total_steps": 231, "loss": 0.3586, "lr": 1.8421104235727406e-08, "epoch": 6.878787878787879, "percentage": 98.27, "elapsed_time": "2:23:46", "remaining_time": "0:02:32"}
+{"current_steps": 228, "total_steps": 231, "loss": 0.3749, "lr": 1.0363263532724433e-08, "epoch": 6.909090909090909, "percentage": 98.7, "elapsed_time": "2:24:24", "remaining_time": "0:01:54"}
+{"current_steps": 229, "total_steps": 231, "loss": 0.3569, "lr": 4.606336975948589e-09, "epoch": 6.9393939393939394, "percentage": 99.13, "elapsed_time": "2:25:00", "remaining_time": "0:01:15"}
+{"current_steps": 230, "total_steps": 231, "loss": 0.3542, "lr": 1.1516505589381777e-09, "epoch": 6.96969696969697, "percentage": 99.57, "elapsed_time": "2:25:37", "remaining_time": "0:00:37"}
+{"current_steps": 231, "total_steps": 231, "loss": 0.3549, "lr": 0.0, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:26:13", "remaining_time": "0:00:00"}
+{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:27:19", "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": 6.563540926047164,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.0428,
+      "step": 1
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 6.580449611407564,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.0483,
+      "step": 2
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 6.210885833052012,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0076,
+      "step": 3
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 6.036397259814275,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0567,
+      "step": 4
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 4.603774097681534,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.0084,
+      "step": 5
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.737755371478083,
+      "learning_rate": 5e-06,
+      "loss": 0.965,
+      "step": 6
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 2.5619445574428448,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.9429,
+      "step": 7
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 3.8525147643115134,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9282,
+      "step": 8
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 4.209095398851915,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.9393,
+      "step": 9
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 3.800581953224376,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.9139,
+      "step": 10
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.476621176143793,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.8747,
+      "step": 11
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 2.9503268969909007,
+      "learning_rate": 1e-05,
+      "loss": 0.8748,
+      "step": 12
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 2.153814926870141,
+      "learning_rate": 1.0833333333333334e-05,
+      "loss": 0.8607,
+      "step": 13
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 1.4726286662048231,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.8153,
+      "step": 14
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.5827019390839245,
+      "learning_rate": 1.25e-05,
+      "loss": 0.8089,
+      "step": 15
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 1.370989555312634,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7918,
+      "step": 16
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 1.0938787558192071,
+      "learning_rate": 1.416666666666667e-05,
+      "loss": 0.7809,
+      "step": 17
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.1189356582259942,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7785,
+      "step": 18
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 0.9962255721627962,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.7742,
+      "step": 19
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 1.044035841940071,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.7509,
+      "step": 20
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 0.9721149401473398,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.7512,
+      "step": 21
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.8933857358288726,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.7381,
+      "step": 22
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 0.9947922049252935,
+      "learning_rate": 1.916666666666667e-05,
+      "loss": 0.7335,
+      "step": 23
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.8824730582284096,
+      "learning_rate": 2e-05,
+      "loss": 0.7342,
+      "step": 24
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 0.9463986654416301,
+      "learning_rate": 1.999884834944106e-05,
+      "loss": 0.7162,
+      "step": 25
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.8632572070636885,
+      "learning_rate": 1.9995393663024054e-05,
+      "loss": 0.7068,
+      "step": 26
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.706944869585806,
+      "learning_rate": 1.9989636736467278e-05,
+      "loss": 0.7179,
+      "step": 27
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.71187796312837,
+      "learning_rate": 1.9981578895764272e-05,
+      "loss": 0.6952,
+      "step": 28
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 0.7235082612231346,
+      "learning_rate": 1.9971221996878395e-05,
+      "loss": 0.7062,
+      "step": 29
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.687345657184883,
+      "learning_rate": 1.9958568425315316e-05,
+      "loss": 0.6895,
+      "step": 30
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.637332917341387,
+      "learning_rate": 1.9943621095573588e-05,
+      "loss": 0.7066,
+      "step": 31
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.8211307421728865,
+      "learning_rate": 1.9926383450473344e-05,
+      "loss": 0.6939,
+      "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6568867965417567,
+      "learning_rate": 1.9906859460363307e-05,
+      "loss": 0.6849,
+      "step": 33
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 0.6316770232176342,
+      "learning_rate": 1.9885053622206305e-05,
+      "loss": 0.6666,
+      "step": 34
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.598548781481323,
+      "learning_rate": 1.986097095854347e-05,
+      "loss": 0.6617,
+      "step": 35
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.541888329561449,
+      "learning_rate": 1.9834617016337424e-05,
+      "loss": 0.6661,
+      "step": 36
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.548704296621704,
+      "learning_rate": 1.9805997865694616e-05,
+      "loss": 0.6541,
+      "step": 37
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 0.7232814085495041,
+      "learning_rate": 1.9775120098467212e-05,
+      "loss": 0.6482,
+      "step": 38
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.517966369427666,
+      "learning_rate": 1.9741990826734793e-05,
+      "loss": 0.6538,
+      "step": 39
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.6716665600989004,
+      "learning_rate": 1.970661768116622e-05,
+      "loss": 0.6636,
+      "step": 40
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 0.6847972723529687,
+      "learning_rate": 1.9669008809262064e-05,
+      "loss": 0.6434,
+      "step": 41
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.5804576446224823,
+      "learning_rate": 1.9629172873477995e-05,
+      "loss": 0.653,
+      "step": 42
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 0.6500106007023674,
+      "learning_rate": 1.9587119049229558e-05,
+      "loss": 0.6362,
+      "step": 43
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.694521890601108,
+      "learning_rate": 1.954285702277879e-05,
+      "loss": 0.6295,
+      "step": 44
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.6074904864106893,
+      "learning_rate": 1.9496396989003195e-05,
+      "loss": 0.6233,
+      "step": 45
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 0.7774754447607893,
+      "learning_rate": 1.944774964904754e-05,
+      "loss": 0.6275,
+      "step": 46
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 0.6113642022042228,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.6271,
+      "step": 47
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.6760030831909414,
+      "learning_rate": 1.9343938371606714e-05,
+      "loss": 0.6125,
+      "step": 48
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 0.6651014861881179,
+      "learning_rate": 1.9288798344984673e-05,
+      "loss": 0.6398,
+      "step": 49
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.8828627870381741,
+      "learning_rate": 1.9231518828401458e-05,
+      "loss": 0.6255,
+      "step": 50
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.759276830653897,
+      "learning_rate": 1.917211301505453e-05,
+      "loss": 0.6259,
+      "step": 51
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 0.5517216460140265,
+      "learning_rate": 1.911059458789152e-05,
+      "loss": 0.6235,
+      "step": 52
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 0.7568131950239245,
+      "learning_rate": 1.9046977716458627e-05,
+      "loss": 0.6017,
+      "step": 53
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.6210935288846776,
+      "learning_rate": 1.8981277053636963e-05,
+      "loss": 0.6113,
+      "step": 54
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.529751177762721,
+      "learning_rate": 1.891350773226754e-05,
+      "loss": 0.6267,
+      "step": 55
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 0.6804806242920128,
+      "learning_rate": 1.8843685361665724e-05,
+      "loss": 0.6301,
+      "step": 56
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.5234947176657136,
+      "learning_rate": 1.8771826024025944e-05,
+      "loss": 0.6296,
+      "step": 57
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 0.630989209194213,
+      "learning_rate": 1.8697946270717468e-05,
+      "loss": 0.6242,
+      "step": 58
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 0.5781907314015904,
+      "learning_rate": 1.8622063118472135e-05,
+      "loss": 0.6238,
+      "step": 59
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5200010563062794,
+      "learning_rate": 1.8544194045464888e-05,
+      "loss": 0.6159,
+      "step": 60
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.5319459955427939,
+      "learning_rate": 1.8464356987288012e-05,
+      "loss": 0.608,
+      "step": 61
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 0.5163593309425878,
+      "learning_rate": 1.8382570332820045e-05,
+      "loss": 0.616,
+      "step": 62
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.5585332117774429,
+      "learning_rate": 1.8298852919990254e-05,
+      "loss": 0.6191,
+      "step": 63
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 0.5974666940232033,
+      "learning_rate": 1.821322403143969e-05,
+      "loss": 0.6365,
+      "step": 64
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.7254714115326361,
+      "learning_rate": 1.812570339007983e-05,
+      "loss": 0.6143,
+      "step": 65
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6048682162832721,
+      "learning_rate": 1.8036311154549783e-05,
+      "loss": 0.6266,
+      "step": 66
+    },
+    {
+      "epoch": 2.0303030303030303,
+      "grad_norm": 0.5811332386679446,
+      "learning_rate": 1.7945067914573147e-05,
+      "loss": 0.5654,
+      "step": 67
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 0.7078463221059967,
+      "learning_rate": 1.7851994686215592e-05,
+      "loss": 0.5782,
+      "step": 68
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 0.6467886516514096,
+      "learning_rate": 1.77571129070442e-05,
+      "loss": 0.5641,
+      "step": 69
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 0.8327454008647746,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.5633,
+      "step": 70
+    },
+    {
+      "epoch": 2.1515151515151514,
+      "grad_norm": 0.914036765125269,
+      "learning_rate": 1.7562011524313187e-05,
+      "loss": 0.5498,
+      "step": 71
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.7579034291454978,
+      "learning_rate": 1.7461836858476858e-05,
+      "loss": 0.5583,
+      "step": 72
+    },
+    {
+      "epoch": 2.212121212121212,
+      "grad_norm": 0.5951617380041966,
+      "learning_rate": 1.7359943506922775e-05,
+      "loss": 0.558,
+      "step": 73
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 0.6656364633288391,
+      "learning_rate": 1.725635493875799e-05,
+      "loss": 0.5502,
+      "step": 74
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.5498251841183976,
+      "learning_rate": 1.7151095013548996e-05,
+      "loss": 0.5432,
+      "step": 75
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 0.5181474131631552,
+      "learning_rate": 1.7044187975826126e-05,
+      "loss": 0.5341,
+      "step": 76
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.6056649893501447,
+      "learning_rate": 1.693565844949933e-05,
+      "loss": 0.553,
+      "step": 77
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.5505110256865079,
+      "learning_rate": 1.6825531432186545e-05,
+      "loss": 0.5423,
+      "step": 78
+    },
+    {
+      "epoch": 2.393939393939394,
+      "grad_norm": 0.5420722140172576,
+      "learning_rate": 1.671383228945597e-05,
+      "loss": 0.5507,
+      "step": 79
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.6144593157841388,
+      "learning_rate": 1.6600586748983642e-05,
+      "loss": 0.5455,
+      "step": 80
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.6164703057994342,
+      "learning_rate": 1.648582089462756e-05,
+      "loss": 0.5592,
+      "step": 81
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 0.5526863546676946,
+      "learning_rate": 1.6369561160419783e-05,
+      "loss": 0.5533,
+      "step": 82
+    },
+    {
+      "epoch": 2.515151515151515,
+      "grad_norm": 0.6382238950572803,
+      "learning_rate": 1.625183432447789e-05,
+      "loss": 0.5527,
+      "step": 83
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.4457817952252059,
+      "learning_rate": 1.6132667502837164e-05,
+      "loss": 0.5506,
+      "step": 84
+    },
+    {
+      "epoch": 2.5757575757575757,
+      "grad_norm": 0.5262250955813433,
+      "learning_rate": 1.6012088143204953e-05,
+      "loss": 0.5718,
+      "step": 85
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 0.4829041397558836,
+      "learning_rate": 1.589012401863864e-05,
+      "loss": 0.5567,
+      "step": 86
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 0.43069510677405,
+      "learning_rate": 1.5766803221148676e-05,
+      "loss": 0.5429,
+      "step": 87
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.5992851670087732,
+      "learning_rate": 1.5642154155228124e-05,
+      "loss": 0.55,
+      "step": 88
+    },
+    {
+      "epoch": 2.6969696969696972,
+      "grad_norm": 0.48987744304682884,
+      "learning_rate": 1.5516205531310272e-05,
+      "loss": 0.5369,
+      "step": 89
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.49423593619418865,
+      "learning_rate": 1.538898635915576e-05,
+      "loss": 0.5514,
+      "step": 90
+    },
+    {
+      "epoch": 2.757575757575758,
+      "grad_norm": 0.38480659724740207,
+      "learning_rate": 1.526052594117071e-05,
+      "loss": 0.5428,
+      "step": 91
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 0.4631999660083842,
+      "learning_rate": 1.513085386565758e-05,
+      "loss": 0.5442,
+      "step": 92
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.43383032995287757,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5629,
+      "step": 93
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 0.4930078476777237,
+      "learning_rate": 1.4867994483783485e-05,
+      "loss": 0.5399,
+      "step": 94
+    },
+    {
+      "epoch": 2.878787878787879,
+      "grad_norm": 0.38813626716680266,
+      "learning_rate": 1.4734867721853341e-05,
+      "loss": 0.5388,
+      "step": 95
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.4163833019799601,
+      "learning_rate": 1.4600650377311523e-05,
+      "loss": 0.5412,
+      "step": 96
+    },
+    {
+      "epoch": 2.9393939393939394,
+      "grad_norm": 0.46066144305840756,
+      "learning_rate": 1.4465373364454001e-05,
+      "loss": 0.5496,
+      "step": 97
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 0.3898310359926936,
+      "learning_rate": 1.4329067841650274e-05,
+      "loss": 0.5333,
+      "step": 98
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5066752775101956,
+      "learning_rate": 1.4191765204166643e-05,
+      "loss": 0.5419,
+      "step": 99
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 0.5474043513124414,
+      "learning_rate": 1.4053497076934948e-05,
+      "loss": 0.497,
+      "step": 100
+    },
+    {
+      "epoch": 3.0606060606060606,
+      "grad_norm": 0.49901750517264826,
+      "learning_rate": 1.3914295307268396e-05,
+      "loss": 0.4843,
+      "step": 101
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 0.5068420885440028,
+      "learning_rate": 1.3774191957526144e-05,
+      "loss": 0.4917,
+      "step": 102
+    },
+    {
+      "epoch": 3.121212121212121,
+      "grad_norm": 0.5572281263009282,
+      "learning_rate": 1.3633219297728415e-05,
+      "loss": 0.5018,
+      "step": 103
+    },
+    {
+      "epoch": 3.1515151515151514,
+      "grad_norm": 0.43663824894920084,
+      "learning_rate": 1.3491409798123687e-05,
+      "loss": 0.4821,
+      "step": 104
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.5393537880378538,
+      "learning_rate": 1.3348796121709862e-05,
+      "loss": 0.4955,
+      "step": 105
+    },
+    {
+      "epoch": 3.212121212121212,
+      "grad_norm": 0.5387099450604667,
+      "learning_rate": 1.3205411116710973e-05,
+      "loss": 0.4774,
+      "step": 106
+    },
+    {
+      "epoch": 3.242424242424242,
+      "grad_norm": 0.5054134734775204,
+      "learning_rate": 1.3061287809011243e-05,
+      "loss": 0.5004,
+      "step": 107
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 0.5514702124191662,
+      "learning_rate": 1.291645939454825e-05,
+      "loss": 0.4782,
+      "step": 108
+    },
+    {
+      "epoch": 3.303030303030303,
+      "grad_norm": 0.5001894829891724,
+      "learning_rate": 1.277095923166689e-05,
+      "loss": 0.4872,
+      "step": 109
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.5400539892428468,
+      "learning_rate": 1.2624820833435939e-05,
+      "loss": 0.4892,
+      "step": 110
+    },
+    {
+      "epoch": 3.3636363636363638,
+      "grad_norm": 0.5145544328425247,
+      "learning_rate": 1.2478077859929e-05,
+      "loss": 0.4859,
+      "step": 111
+    },
+    {
+      "epoch": 3.393939393939394,
+      "grad_norm": 0.4110011582979585,
+      "learning_rate": 1.2330764110471567e-05,
+      "loss": 0.4866,
+      "step": 112
+    },
+    {
+      "epoch": 3.4242424242424243,
+      "grad_norm": 0.5040490080891203,
+      "learning_rate": 1.2182913515856016e-05,
+      "loss": 0.4801,
+      "step": 113
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 0.460311106110748,
+      "learning_rate": 1.2034560130526341e-05,
+      "loss": 0.4867,
+      "step": 114
+    },
+    {
+      "epoch": 3.484848484848485,
+      "grad_norm": 0.4950344381182238,
+      "learning_rate": 1.1885738124734359e-05,
+      "loss": 0.4721,
+      "step": 115
+    },
+    {
+      "epoch": 3.515151515151515,
+      "grad_norm": 0.4636731269112049,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.4864,
+      "step": 116
+    },
+    {
+      "epoch": 3.5454545454545454,
+      "grad_norm": 0.39781010318904547,
+      "learning_rate": 1.1586825464562515e-05,
+      "loss": 0.4764,
+      "step": 117
+    },
+    {
+      "epoch": 3.5757575757575757,
+      "grad_norm": 0.47344015190765665,
+      "learning_rate": 1.1436803658769082e-05,
+      "loss": 0.4949,
+      "step": 118
+    },
+    {
+      "epoch": 3.606060606060606,
+      "grad_norm": 0.45748213076954986,
+      "learning_rate": 1.1286450913828313e-05,
+      "loss": 0.4979,
+      "step": 119
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.4543919473808373,
+      "learning_rate": 1.113580186050475e-05,
+      "loss": 0.4752,
+      "step": 120
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.41379006149200803,
+      "learning_rate": 1.0984891197811686e-05,
+      "loss": 0.4753,
+      "step": 121
+    },
+    {
+      "epoch": 3.6969696969696972,
+      "grad_norm": 0.43943952235155676,
+      "learning_rate": 1.0833753685018935e-05,
+      "loss": 0.4758,
+      "step": 122
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 0.3985989707644989,
+      "learning_rate": 1.0682424133646712e-05,
+      "loss": 0.4852,
+      "step": 123
+    },
+    {
+      "epoch": 3.757575757575758,
+      "grad_norm": 0.37866491127879987,
+      "learning_rate": 1.0530937399447496e-05,
+      "loss": 0.4738,
+      "step": 124
+    },
+    {
+      "epoch": 3.787878787878788,
+      "grad_norm": 0.391346474863689,
+      "learning_rate": 1.0379328374377715e-05,
+      "loss": 0.4866,
+      "step": 125
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 0.3625474315447914,
+      "learning_rate": 1.0227631978561057e-05,
+      "loss": 0.4787,
+      "step": 126
+    },
+    {
+      "epoch": 3.8484848484848486,
+      "grad_norm": 0.3845329743925931,
+      "learning_rate": 1.0075883152245334e-05,
+      "loss": 0.4798,
+      "step": 127
+    },
+    {
+      "epoch": 3.878787878787879,
+      "grad_norm": 0.383433574379574,
+      "learning_rate": 9.92411684775467e-06,
+      "loss": 0.4787,
+      "step": 128
+    },
+    {
+      "epoch": 3.909090909090909,
+      "grad_norm": 0.4115392188921613,
+      "learning_rate": 9.772368021438943e-06,
+      "loss": 0.4862,
+      "step": 129
+    },
+    {
+      "epoch": 3.9393939393939394,
+      "grad_norm": 0.389354832046105,
+      "learning_rate": 9.620671625622287e-06,
+      "loss": 0.4801,
+      "step": 130
+    },
+    {
+      "epoch": 3.9696969696969697,
+      "grad_norm": 0.4485920448439754,
+      "learning_rate": 9.469062600552509e-06,
+      "loss": 0.4889,
+      "step": 131
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.35020551865579047,
+      "learning_rate": 9.317575866353293e-06,
+      "loss": 0.4613,
+      "step": 132
+    },
+    {
+      "epoch": 4.03030303030303,
+      "grad_norm": 0.5607546876543795,
+      "learning_rate": 9.166246314981066e-06,
+      "loss": 0.4256,
+      "step": 133
+    },
+    {
+      "epoch": 4.0606060606060606,
+      "grad_norm": 0.4557755084880889,
+      "learning_rate": 9.015108802188314e-06,
+      "loss": 0.4333,
+      "step": 134
+    },
+    {
+      "epoch": 4.090909090909091,
+      "grad_norm": 0.4725633025186906,
+      "learning_rate": 8.86419813949525e-06,
+      "loss": 0.4265,
+      "step": 135
+    },
+    {
+      "epoch": 4.121212121212121,
+      "grad_norm": 0.573363372087563,
+      "learning_rate": 8.71354908617169e-06,
+      "loss": 0.4209,
+      "step": 136
+    },
+    {
+      "epoch": 4.151515151515151,
+      "grad_norm": 0.46044001223143577,
+      "learning_rate": 8.56319634123092e-06,
+      "loss": 0.4283,
+      "step": 137
+    },
+    {
+      "epoch": 4.181818181818182,
+      "grad_norm": 0.4467152469171767,
+      "learning_rate": 8.413174535437486e-06,
+      "loss": 0.4189,
+      "step": 138
+    },
+    {
+      "epoch": 4.212121212121212,
+      "grad_norm": 0.4867813595382334,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.4273,
+      "step": 139
+    },
+    {
+      "epoch": 4.242424242424242,
+      "grad_norm": 0.4177932775745287,
+      "learning_rate": 8.114261875265643e-06,
+      "loss": 0.428,
+      "step": 140
+    },
+    {
+      "epoch": 4.2727272727272725,
+      "grad_norm": 0.411671150540731,
+      "learning_rate": 7.965439869473664e-06,
+      "loss": 0.4232,
+      "step": 141
+    },
+    {
+      "epoch": 4.303030303030303,
+      "grad_norm": 0.47085390143038414,
+      "learning_rate": 7.817086484143987e-06,
+      "loss": 0.433,
+      "step": 142
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.3958790763883933,
+      "learning_rate": 7.669235889528436e-06,
+      "loss": 0.4196,
+      "step": 143
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 0.41826411109606854,
+      "learning_rate": 7.521922140071003e-06,
+      "loss": 0.4225,
+      "step": 144
+    },
+    {
+      "epoch": 4.393939393939394,
+      "grad_norm": 0.40191901886516435,
+      "learning_rate": 7.375179166564062e-06,
+      "loss": 0.4231,
+      "step": 145
+    },
+    {
+      "epoch": 4.424242424242424,
+      "grad_norm": 0.4269248963055479,
+      "learning_rate": 7.2290407683331154e-06,
+      "loss": 0.4206,
+      "step": 146
+    },
+    {
+      "epoch": 4.454545454545454,
+      "grad_norm": 0.42115014136542406,
+      "learning_rate": 7.0835406054517505e-06,
+      "loss": 0.4261,
+      "step": 147
+    },
+    {
+      "epoch": 4.484848484848484,
+      "grad_norm": 0.39326005037866735,
+      "learning_rate": 6.93871219098876e-06,
+      "loss": 0.4203,
+      "step": 148
+    },
+    {
+      "epoch": 4.515151515151516,
+      "grad_norm": 0.39609232779775183,
+      "learning_rate": 6.79458888328903e-06,
+      "loss": 0.4216,
+      "step": 149
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.3712986313940363,
+      "learning_rate": 6.651203878290139e-06,
+      "loss": 0.4265,
+      "step": 150
+    },
+    {
+      "epoch": 4.575757575757576,
+      "grad_norm": 0.392633527257338,
+      "learning_rate": 6.508590201876317e-06,
+      "loss": 0.4179,
+      "step": 151
+    },
+    {
+      "epoch": 4.606060606060606,
+      "grad_norm": 0.37590428954350047,
+      "learning_rate": 6.366780702271589e-06,
+      "loss": 0.4196,
+      "step": 152
+    },
+    {
+      "epoch": 4.636363636363637,
+      "grad_norm": 0.37092433982418843,
+      "learning_rate": 6.225808042473857e-06,
+      "loss": 0.4309,
+      "step": 153
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.3787184593441365,
+      "learning_rate": 6.085704692731609e-06,
+      "loss": 0.4318,
+      "step": 154
+    },
+    {
+      "epoch": 4.696969696969697,
+      "grad_norm": 0.7699843144622641,
+      "learning_rate": 5.946502923065054e-06,
+      "loss": 0.4474,
+      "step": 155
+    },
+    {
+      "epoch": 4.7272727272727275,
+      "grad_norm": 0.35041173464519193,
+      "learning_rate": 5.8082347958333625e-06,
+      "loss": 0.4195,
+      "step": 156
+    },
+    {
+      "epoch": 4.757575757575758,
+      "grad_norm": 0.37410267572131256,
+      "learning_rate": 5.670932158349732e-06,
+      "loss": 0.4247,
+      "step": 157
+    },
+    {
+      "epoch": 4.787878787878788,
+      "grad_norm": 0.34432142617929,
+      "learning_rate": 5.534626635546e-06,
+      "loss": 0.4328,
+      "step": 158
+    },
+    {
+      "epoch": 4.818181818181818,
+      "grad_norm": 0.3466828538594678,
+      "learning_rate": 5.399349622688479e-06,
+      "loss": 0.4291,
+      "step": 159
+    },
+    {
+      "epoch": 4.848484848484849,
+      "grad_norm": 0.3550750415579987,
+      "learning_rate": 5.2651322781466606e-06,
+      "loss": 0.4338,
+      "step": 160
+    },
+    {
+      "epoch": 4.878787878787879,
+      "grad_norm": 0.3444707493311806,
+      "learning_rate": 5.132005516216512e-06,
+      "loss": 0.4129,
+      "step": 161
+    },
+    {
+      "epoch": 4.909090909090909,
+      "grad_norm": 0.32768268988127786,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.4238,
+      "step": 162
+    },
+    {
+      "epoch": 4.9393939393939394,
+      "grad_norm": 0.34960894126683545,
+      "learning_rate": 4.869146134342426e-06,
+      "loss": 0.4307,
+      "step": 163
+    },
+    {
+      "epoch": 4.96969696969697,
+      "grad_norm": 0.330195615528033,
+      "learning_rate": 4.739474058829288e-06,
+      "loss": 0.4196,
+      "step": 164
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.3459410278415265,
+      "learning_rate": 4.611013640844245e-06,
+      "loss": 0.4253,
+      "step": 165
+    },
+    {
+      "epoch": 5.03030303030303,
+      "grad_norm": 0.48189255968384775,
+      "learning_rate": 4.483794468689728e-06,
+      "loss": 0.3872,
+      "step": 166
+    },
+    {
+      "epoch": 5.0606060606060606,
+      "grad_norm": 0.4069317192144402,
+      "learning_rate": 4.357845844771881e-06,
+      "loss": 0.3822,
+      "step": 167
+    },
+    {
+      "epoch": 5.090909090909091,
+      "grad_norm": 0.3381651303644385,
+      "learning_rate": 4.2331967788513295e-06,
+      "loss": 0.3778,
+      "step": 168
+    },
+    {
+      "epoch": 5.121212121212121,
+      "grad_norm": 0.476940791131885,
+      "learning_rate": 4.109875981361363e-06,
+      "loss": 0.3863,
+      "step": 169
+    },
+    {
+      "epoch": 5.151515151515151,
+      "grad_norm": 0.5094452924087921,
+      "learning_rate": 3.987911856795047e-06,
+      "loss": 0.3793,
+      "step": 170
+    },
+    {
+      "epoch": 5.181818181818182,
+      "grad_norm": 0.3661104380813191,
+      "learning_rate": 3.867332497162836e-06,
+      "loss": 0.3765,
+      "step": 171
+    },
+    {
+      "epoch": 5.212121212121212,
+      "grad_norm": 0.3393190292607263,
+      "learning_rate": 3.748165675522113e-06,
+      "loss": 0.3809,
+      "step": 172
+    },
+    {
+      "epoch": 5.242424242424242,
+      "grad_norm": 0.3566253442002397,
+      "learning_rate": 3.630438839580217e-06,
+      "loss": 0.3858,
+      "step": 173
+    },
+    {
+      "epoch": 5.2727272727272725,
+      "grad_norm": 0.38325860340550916,
+      "learning_rate": 3.5141791053724405e-06,
+      "loss": 0.38,
+      "step": 174
+    },
+    {
+      "epoch": 5.303030303030303,
+      "grad_norm": 0.34337264051552197,
+      "learning_rate": 3.399413251016359e-06,
+      "loss": 0.3745,
+      "step": 175
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.33113896425624495,
+      "learning_rate": 3.2861677105440335e-06,
+      "loss": 0.3728,
+      "step": 176
+    },
+    {
+      "epoch": 5.363636363636363,
+      "grad_norm": 0.35482288831996844,
+      "learning_rate": 3.174468567813461e-06,
+      "loss": 0.3706,
+      "step": 177
+    },
+    {
+      "epoch": 5.393939393939394,
+      "grad_norm": 0.5621907966741517,
+      "learning_rate": 3.0643415505006733e-06,
+      "loss": 0.3814,
+      "step": 178
+    },
+    {
+      "epoch": 5.424242424242424,
+      "grad_norm": 0.33758999301051723,
+      "learning_rate": 2.9558120241738786e-06,
+      "loss": 0.3639,
+      "step": 179
+    },
+    {
+      "epoch": 5.454545454545454,
+      "grad_norm": 0.34667774663189316,
+      "learning_rate": 2.8489049864510053e-06,
+      "loss": 0.3807,
+      "step": 180
+    },
+    {
+      "epoch": 5.484848484848484,
+      "grad_norm": 0.3132018666400906,
+      "learning_rate": 2.7436450612420098e-06,
+      "loss": 0.3798,
+      "step": 181
+    },
+    {
+      "epoch": 5.515151515151516,
+      "grad_norm": 0.3371484635436534,
+      "learning_rate": 2.640056493077231e-06,
+      "loss": 0.3881,
+      "step": 182
+    },
+    {
+      "epoch": 5.545454545454545,
+      "grad_norm": 0.3105879958077527,
+      "learning_rate": 2.5381631415231455e-06,
+      "loss": 0.3847,
+      "step": 183
+    },
+    {
+      "epoch": 5.575757575757576,
+      "grad_norm": 0.3343505128008297,
+      "learning_rate": 2.4379884756868167e-06,
+      "loss": 0.3719,
+      "step": 184
+    },
+    {
+      "epoch": 5.606060606060606,
+      "grad_norm": 0.33297737666263527,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.3977,
+      "step": 185
+    },
+    {
+      "epoch": 5.636363636363637,
+      "grad_norm": 0.31346210814602987,
+      "learning_rate": 2.2428870929558012e-06,
+      "loss": 0.3835,
+      "step": 186
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 0.3268734785098672,
+      "learning_rate": 2.1480053137844115e-06,
+      "loss": 0.3852,
+      "step": 187
+    },
+    {
+      "epoch": 5.696969696969697,
+      "grad_norm": 0.31547113405684213,
+      "learning_rate": 2.054932085426856e-06,
+      "loss": 0.3858,
+      "step": 188
+    },
+    {
+      "epoch": 5.7272727272727275,
+      "grad_norm": 0.30699942166401356,
+      "learning_rate": 1.963688845450218e-06,
+      "loss": 0.3876,
+      "step": 189
+    },
+    {
+      "epoch": 5.757575757575758,
+      "grad_norm": 0.3004604356148264,
+      "learning_rate": 1.8742966099201699e-06,
+      "loss": 0.3715,
+      "step": 190
+    },
+    {
+      "epoch": 5.787878787878788,
+      "grad_norm": 0.30110377420404033,
+      "learning_rate": 1.7867759685603115e-06,
+      "loss": 0.3797,
+      "step": 191
+    },
+    {
+      "epoch": 5.818181818181818,
+      "grad_norm": 0.3020524997749085,
+      "learning_rate": 1.7011470800097496e-06,
+      "loss": 0.3922,
+      "step": 192
+    },
+    {
+      "epoch": 5.848484848484849,
+      "grad_norm": 0.30549617753019875,
+      "learning_rate": 1.6174296671799571e-06,
+      "loss": 0.3737,
+      "step": 193
+    },
+    {
+      "epoch": 5.878787878787879,
+      "grad_norm": 0.37524600057770147,
+      "learning_rate": 1.5356430127119915e-06,
+      "loss": 0.3838,
+      "step": 194
+    },
+    {
+      "epoch": 5.909090909090909,
+      "grad_norm": 0.3042161760921001,
+      "learning_rate": 1.4558059545351144e-06,
+      "loss": 0.375,
+      "step": 195
+    },
+    {
+      "epoch": 5.9393939393939394,
+      "grad_norm": 0.30041972160383384,
+      "learning_rate": 1.3779368815278648e-06,
+      "loss": 0.3841,
+      "step": 196
+    },
+    {
+      "epoch": 5.96969696969697,
+      "grad_norm": 0.29667721012490295,
+      "learning_rate": 1.302053729282533e-06,
+      "loss": 0.3955,
+      "step": 197
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.29460086955248166,
+      "learning_rate": 1.2281739759740575e-06,
+      "loss": 0.3862,
+      "step": 198
+    },
+    {
+      "epoch": 6.03030303030303,
+      "grad_norm": 0.39066495345577096,
+      "learning_rate": 1.156314638334277e-06,
+      "loss": 0.3559,
+      "step": 199
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "grad_norm": 0.3297082732903188,
+      "learning_rate": 1.086492267732462e-06,
+      "loss": 0.3621,
+      "step": 200
+    },
+    {
+      "epoch": 6.090909090909091,
+      "grad_norm": 0.3218756416031739,
+      "learning_rate": 1.01872294636304e-06,
+      "loss": 0.3664,
+      "step": 201
+    },
+    {
+      "epoch": 6.121212121212121,
+      "grad_norm": 0.29542877990945426,
+      "learning_rate": 9.530222835413739e-07,
+      "loss": 0.3701,
+      "step": 202
+    },
+    {
+      "epoch": 6.151515151515151,
+      "grad_norm": 0.3226379281831477,
+      "learning_rate": 8.894054121084839e-07,
+      "loss": 0.3594,
+      "step": 203
+    },
+    {
+      "epoch": 6.181818181818182,
+      "grad_norm": 0.29876651406377464,
+      "learning_rate": 8.278869849454718e-07,
+      "loss": 0.3478,
+      "step": 204
+    },
+    {
+      "epoch": 6.212121212121212,
+      "grad_norm": 0.31595442268640583,
+      "learning_rate": 7.684811715985429e-07,
+      "loss": 0.3601,
+      "step": 205
+    },
+    {
+      "epoch": 6.242424242424242,
+      "grad_norm": 0.3327410989346359,
+      "learning_rate": 7.1120165501533e-07,
+      "loss": 0.357,
+      "step": 206
+    },
+    {
+      "epoch": 6.2727272727272725,
+      "grad_norm": 0.33021799323368684,
+      "learning_rate": 6.560616283932897e-07,
+      "loss": 0.3621,
+      "step": 207
+    },
+    {
+      "epoch": 6.303030303030303,
+      "grad_norm": 0.3369077443848601,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.3553,
+      "step": 208
+    },
+    {
+      "epoch": 6.333333333333333,
+      "grad_norm": 0.3402979609634558,
+      "learning_rate": 5.522503509524591e-07,
+      "loss": 0.3624,
+      "step": 209
+    },
+    {
+      "epoch": 6.363636363636363,
+      "grad_norm": 0.32636505512382785,
+      "learning_rate": 5.036030109968082e-07,
+      "loss": 0.3728,
+      "step": 210
+    },
+    {
+      "epoch": 6.393939393939394,
+      "grad_norm": 0.31061296784676257,
+      "learning_rate": 4.5714297722121105e-07,
+      "loss": 0.3594,
+      "step": 211
+    },
+    {
+      "epoch": 6.424242424242424,
+      "grad_norm": 0.29914957991433055,
+      "learning_rate": 4.128809507704445e-07,
+      "loss": 0.3534,
+      "step": 212
+    },
+    {
+      "epoch": 6.454545454545454,
+      "grad_norm": 0.3188455054527916,
+      "learning_rate": 3.708271265220087e-07,
+      "loss": 0.3545,
+      "step": 213
+    },
+    {
+      "epoch": 6.484848484848484,
+      "grad_norm": 0.28950522233899323,
+      "learning_rate": 3.309911907379393e-07,
+      "loss": 0.368,
+      "step": 214
+    },
+    {
+      "epoch": 6.515151515151516,
+      "grad_norm": 0.3069425529194652,
+      "learning_rate": 2.9338231883378365e-07,
+      "loss": 0.3614,
+      "step": 215
+    },
+    {
+      "epoch": 6.545454545454545,
+      "grad_norm": 0.3003951738033514,
+      "learning_rate": 2.5800917326521013e-07,
+      "loss": 0.3576,
+      "step": 216
+    },
+    {
+      "epoch": 6.575757575757576,
+      "grad_norm": 0.27217818372962993,
+      "learning_rate": 2.248799015327907e-07,
+      "loss": 0.3552,
+      "step": 217
+    },
+    {
+      "epoch": 6.606060606060606,
+      "grad_norm": 0.29692820758872923,
+      "learning_rate": 1.9400213430538773e-07,
+      "loss": 0.3474,
+      "step": 218
+    },
+    {
+      "epoch": 6.636363636363637,
+      "grad_norm": 0.29355347763625134,
+      "learning_rate": 1.6538298366257975e-07,
+      "loss": 0.3589,
+      "step": 219
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.2905088604483449,
+      "learning_rate": 1.3902904145653094e-07,
+      "loss": 0.3627,
+      "step": 220
+    },
+    {
+      "epoch": 6.696969696969697,
+      "grad_norm": 0.28660185842852404,
+      "learning_rate": 1.1494637779369766e-07,
+      "loss": 0.3625,
+      "step": 221
+    },
+    {
+      "epoch": 6.7272727272727275,
+      "grad_norm": 0.2813520036309213,
+      "learning_rate": 9.314053963669245e-08,
+      "loss": 0.3597,
+      "step": 222
+    },
+    {
+      "epoch": 6.757575757575758,
+      "grad_norm": 0.28485100572086103,
+      "learning_rate": 7.361654952665608e-08,
+      "loss": 0.3674,
+      "step": 223
+    },
+    {
+      "epoch": 6.787878787878788,
+      "grad_norm": 0.2919101968416061,
+      "learning_rate": 5.637890442641403e-08,
+      "loss": 0.3565,
+      "step": 224
+    },
+    {
+      "epoch": 6.818181818181818,
+      "grad_norm": 0.2881055002821337,
+      "learning_rate": 4.143157468468717e-08,
+      "loss": 0.3538,
+      "step": 225
+    },
+    {
+      "epoch": 6.848484848484849,
+      "grad_norm": 0.2801943229513225,
+      "learning_rate": 2.8778003121607834e-08,
+      "loss": 0.3784,
+      "step": 226
+    },
+    {
+      "epoch": 6.878787878787879,
+      "grad_norm": 0.2867035584776558,
+      "learning_rate": 1.8421104235727406e-08,
+      "loss": 0.3586,
+      "step": 227
+    },
+    {
+      "epoch": 6.909090909090909,
+      "grad_norm": 0.27538587725464836,
+      "learning_rate": 1.0363263532724433e-08,
+      "loss": 0.3749,
+      "step": 228
+    },
+    {
+      "epoch": 6.9393939393939394,
+      "grad_norm": 0.2861165909576405,
+      "learning_rate": 4.606336975948589e-09,
+      "loss": 0.3569,
+      "step": 229
+    },
+    {
+      "epoch": 6.96969696969697,
+      "grad_norm": 0.2809624315847679,
+      "learning_rate": 1.1516505589381777e-09,
+      "loss": 0.3542,
+      "step": 230
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.28930700143285026,
+      "learning_rate": 0.0,
+      "loss": 0.3549,
+      "step": 231
+    },
+    {
+      "epoch": 7.0,
+      "step": 231,
+      "total_flos": 6.415454425086689e+17,
+      "train_loss": 0.5228371008650049,
+      "train_runtime": 8840.4399,
+      "train_samples_per_second": 2.502,
+      "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": 6.415454425086689e+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 sha256:231f99dbce7edd581c3b695e30bc82a9b3f2774ac29d744b3c457dcc97dd87f5
+size 7416