Hugging Face's logo

langgptai
/
qwen1.5-7b-chat-sa-v0.1

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
1
sci-m-wang commited on
Commit
1148b15
·
verified ·
1 Parent(s): a14de95

Upload 16 files

Browse files
Files changed (16) hide show
  1. README.md +59 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +5 -0
  5. all_results.json +8 -0
  6. merges.txt +0 -0
  7. running_log.txt +1357 -0
  8. special_tokens_map.json +20 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +44 -0
  11. train_results.json +8 -0
  12. trainer_config.yaml +28 -0
  13. trainer_log.jsonl +0 -0
  14. trainer_state.json +3761 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - llama-factory
6
+ - lora
7
+ - generated_from_trainer
8
+ base_model: Qwen/Qwen1.5-7B-Chat
9
+ model-index:
10
+ - name: Qwen1.5-7B-Chat
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Qwen1.5-7B-Chat
18
+
19
+ This model is a fine-tuned version of [/datas/huggingface/Qwen1.5-7B-Chat](https://huggingface.co//datas/huggingface/Qwen1.5-7B-Chat) on the LangGPT_community, the LangGPT_alpaca and the LangGPT_seed datasets.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - num_epochs: 5.0
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.10.0
56
+ - Transformers 4.40.2
57
+ - Pytorch 2.3.0+cu121
58
+ - Datasets 2.19.1
59
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen1.5-7B-Chat",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f381387fbe6cdce293105cfe56b4590d12558f167275ed3b2b39dae458dd85
3
+ size 16794200
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.9976558837318334,
3
+ "total_flos": 2.0317707214423327e+18,
4
+ "train_loss": 0.623453339492626,
5
+ "train_runtime": 36076.8467,
6
+ "train_samples_per_second": 1.182,
7
+ "train_steps_per_second": 0.074
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
running_log.txt ADDED
@@ -0,0 +1,1357 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 05/29/2024 23:00:05 - INFO - transformers.tokenization_utils_base - loading file vocab.json
2
+
3
+ 05/29/2024 23:00:05 - INFO - transformers.tokenization_utils_base - loading file merges.txt
4
+
5
+ 05/29/2024 23:00:05 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json
6
+
7
+ 05/29/2024 23:00:05 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json
8
+
9
+ 05/29/2024 23:00:05 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json
10
+
11
+ 05/29/2024 23:00:05 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json
12
+
13
+ 05/29/2024 23:00:05 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
14
+
15
+ 05/29/2024 23:00:05 - INFO - llmtuner.data.template - Replace eos token: <|im_end|>
16
+
17
+ 05/29/2024 23:00:05 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/LangGPT_community.jsonl...
18
+
19
+ 05/29/2024 23:00:05 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
20
+
21
+ 05/29/2024 23:00:06 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/langgpt_alpaca.jsonl...
22
+
23
+ 05/29/2024 23:00:06 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
24
+
25
+ 05/29/2024 23:00:08 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/langgpt_seed.jsonl...
26
+
27
+ 05/29/2024 23:00:08 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
28
+
29
+ 05/29/2024 23:00:27 - INFO - transformers.configuration_utils - loading configuration file /datas/huggingface/Qwen1.5-7B-Chat/config.json
30
+
31
+ 05/29/2024 23:00:27 - INFO - transformers.configuration_utils - Model config Qwen2Config {
32
+ "_name_or_path": "/datas/huggingface/Qwen1.5-7B-Chat",
33
+ "architectures": [
34
+ "Qwen2ForCausalLM"
35
+ ],
36
+ "attention_dropout": 0.0,
37
+ "bos_token_id": 151643,
38
+ "eos_token_id": 151645,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 4096,
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 11008,
43
+ "max_position_embeddings": 32768,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 32,
47
+ "num_hidden_layers": 32,
48
+ "num_key_value_heads": 32,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_theta": 1000000.0,
51
+ "sliding_window": 32768,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "bfloat16",
54
+ "transformers_version": "4.40.2",
55
+ "use_cache": true,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 151936
58
+ }
59
+
60
+
61
+ 05/29/2024 23:00:27 - INFO - transformers.modeling_utils - loading weights file /datas/huggingface/Qwen1.5-7B-Chat/model.safetensors.index.json
62
+
63
+ 05/29/2024 23:00:27 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.float16.
64
+
65
+ 05/29/2024 23:00:27 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
66
+ "bos_token_id": 151643,
67
+ "eos_token_id": 151645,
68
+ "use_cache": false
69
+ }
70
+
71
+
72
+ 05/29/2024 23:02:53 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing Qwen2ForCausalLM.
73
+
74
+
75
+ 05/29/2024 23:02:53 - INFO - transformers.modeling_utils - All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /datas/huggingface/Qwen1.5-7B-Chat.
76
+ If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
77
+
78
+ 05/29/2024 23:02:53 - INFO - transformers.generation.configuration_utils - loading configuration file /datas/huggingface/Qwen1.5-7B-Chat/generation_config.json
79
+
80
+ 05/29/2024 23:02:53 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
81
+ "bos_token_id": 151643,
82
+ "do_sample": true,
83
+ "eos_token_id": [
84
+ 151645,
85
+ 151643
86
+ ],
87
+ "pad_token_id": 151643,
88
+ "repetition_penalty": 1.05,
89
+ "temperature": 0.7,
90
+ "top_k": 20,
91
+ "top_p": 0.8
92
+ }
93
+
94
+
95
+ 05/29/2024 23:02:53 - INFO - llmtuner.model.utils.checkpointing - Gradient checkpointing enabled.
96
+
97
+ 05/29/2024 23:02:53 - INFO - llmtuner.model.utils.attention - Using torch SDPA for faster training and inference.
98
+
99
+ 05/29/2024 23:02:53 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
100
+
101
+ 05/29/2024 23:02:54 - INFO - llmtuner.model.loader - trainable params: 4194304 || all params: 7725518848 || trainable%: 0.0543
102
+
103
+ 05/29/2024 23:02:54 - INFO - transformers.trainer - Using auto half precision backend
104
+
105
+ 05/29/2024 23:02:54 - INFO - transformers.trainer - ***** Running training *****
106
+
107
+ 05/29/2024 23:02:54 - INFO - transformers.trainer - Num examples = 8,531
108
+
109
+ 05/29/2024 23:02:54 - INFO - transformers.trainer - Num Epochs = 5
110
+
111
+ 05/29/2024 23:02:54 - INFO - transformers.trainer - Instantaneous batch size per device = 2
112
+
113
+ 05/29/2024 23:02:54 - INFO - transformers.trainer - Total train batch size (w. parallel, distributed & accumulation) = 16
114
+
115
+ 05/29/2024 23:02:54 - INFO - transformers.trainer - Gradient Accumulation steps = 8
116
+
117
+ 05/29/2024 23:02:54 - INFO - transformers.trainer - Total optimization steps = 2,665
118
+
119
+ 05/29/2024 23:02:54 - INFO - transformers.trainer - Number of trainable parameters = 4,194,304
120
+
121
+ 05/29/2024 23:04:09 - INFO - llmtuner.extras.callbacks - {'loss': 1.2495, 'learning_rate': 5.0000e-05, 'epoch': 0.01}
122
+
123
+ 05/29/2024 23:05:14 - INFO - llmtuner.extras.callbacks - {'loss': 1.0913, 'learning_rate': 4.9998e-05, 'epoch': 0.02}
124
+
125
+ 05/29/2024 23:06:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.9163, 'learning_rate': 4.9996e-05, 'epoch': 0.03}
126
+
127
+ 05/29/2024 23:07:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.9189, 'learning_rate': 4.9993e-05, 'epoch': 0.04}
128
+
129
+ 05/29/2024 23:08:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.8406, 'learning_rate': 4.9989e-05, 'epoch': 0.05}
130
+
131
+ 05/29/2024 23:09:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7963, 'learning_rate': 4.9984e-05, 'epoch': 0.06}
132
+
133
+ 05/29/2024 23:10:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.8229, 'learning_rate': 4.9979e-05, 'epoch': 0.07}
134
+
135
+ 05/29/2024 23:11:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.8240, 'learning_rate': 4.9972e-05, 'epoch': 0.08}
136
+
137
+ 05/29/2024 23:13:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.8236, 'learning_rate': 4.9965e-05, 'epoch': 0.08}
138
+
139
+ 05/29/2024 23:14:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7696, 'learning_rate': 4.9957e-05, 'epoch': 0.09}
140
+
141
+ 05/29/2024 23:15:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.7585, 'learning_rate': 4.9947e-05, 'epoch': 0.10}
142
+
143
+ 05/29/2024 23:16:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7549, 'learning_rate': 4.9937e-05, 'epoch': 0.11}
144
+
145
+ 05/29/2024 23:17:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7345, 'learning_rate': 4.9927e-05, 'epoch': 0.12}
146
+
147
+ 05/29/2024 23:18:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7273, 'learning_rate': 4.9915e-05, 'epoch': 0.13}
148
+
149
+ 05/29/2024 23:19:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7803, 'learning_rate': 4.9902e-05, 'epoch': 0.14}
150
+
151
+ 05/29/2024 23:20:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6957, 'learning_rate': 4.9889e-05, 'epoch': 0.15}
152
+
153
+ 05/29/2024 23:22:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7076, 'learning_rate': 4.9875e-05, 'epoch': 0.16}
154
+
155
+ 05/29/2024 23:23:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7231, 'learning_rate': 4.9859e-05, 'epoch': 0.17}
156
+
157
+ 05/29/2024 23:24:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6879, 'learning_rate': 4.9843e-05, 'epoch': 0.18}
158
+
159
+ 05/29/2024 23:25:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6650, 'learning_rate': 4.9826e-05, 'epoch': 0.19}
160
+
161
+ 05/29/2024 23:25:23 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-100
162
+
163
+ 05/29/2024 23:25:23 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-100/tokenizer_config.json
164
+
165
+ 05/29/2024 23:25:23 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-100/special_tokens_map.json
166
+
167
+ 05/29/2024 23:26:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7560, 'learning_rate': 4.9809e-05, 'epoch': 0.20}
168
+
169
+ 05/29/2024 23:27:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6963, 'learning_rate': 4.9790e-05, 'epoch': 0.21}
170
+
171
+ 05/29/2024 23:28:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.7310, 'learning_rate': 4.9771e-05, 'epoch': 0.22}
172
+
173
+ 05/29/2024 23:29:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.7397, 'learning_rate': 4.9750e-05, 'epoch': 0.23}
174
+
175
+ 05/29/2024 23:31:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7006, 'learning_rate': 4.9729e-05, 'epoch': 0.23}
176
+
177
+ 05/29/2024 23:32:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7231, 'learning_rate': 4.9707e-05, 'epoch': 0.24}
178
+
179
+ 05/29/2024 23:33:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7323, 'learning_rate': 4.9684e-05, 'epoch': 0.25}
180
+
181
+ 05/29/2024 23:34:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6721, 'learning_rate': 4.9660e-05, 'epoch': 0.26}
182
+
183
+ 05/29/2024 23:35:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6722, 'learning_rate': 4.9636e-05, 'epoch': 0.27}
184
+
185
+ 05/29/2024 23:36:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7208, 'learning_rate': 4.9610e-05, 'epoch': 0.28}
186
+
187
+ 05/29/2024 23:37:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6621, 'learning_rate': 4.9584e-05, 'epoch': 0.29}
188
+
189
+ 05/29/2024 23:38:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.7114, 'learning_rate': 4.9557e-05, 'epoch': 0.30}
190
+
191
+ 05/29/2024 23:39:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7235, 'learning_rate': 4.9529e-05, 'epoch': 0.31}
192
+
193
+ 05/29/2024 23:41:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6993, 'learning_rate': 4.9500e-05, 'epoch': 0.32}
194
+
195
+ 05/29/2024 23:42:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7186, 'learning_rate': 4.9470e-05, 'epoch': 0.33}
196
+
197
+ 05/29/2024 23:43:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6867, 'learning_rate': 4.9439e-05, 'epoch': 0.34}
198
+
199
+ 05/29/2024 23:44:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6907, 'learning_rate': 4.9408e-05, 'epoch': 0.35}
200
+
201
+ 05/29/2024 23:45:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6693, 'learning_rate': 4.9376e-05, 'epoch': 0.36}
202
+
203
+ 05/29/2024 23:46:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7322, 'learning_rate': 4.9342e-05, 'epoch': 0.37}
204
+
205
+ 05/29/2024 23:48:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7351, 'learning_rate': 4.9308e-05, 'epoch': 0.38}
206
+
207
+ 05/29/2024 23:48:06 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-200
208
+
209
+ 05/29/2024 23:48:06 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-200/tokenizer_config.json
210
+
211
+ 05/29/2024 23:48:06 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-200/special_tokens_map.json
212
+
213
+ 05/29/2024 23:49:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6996, 'learning_rate': 4.9274e-05, 'epoch': 0.38}
214
+
215
+ 05/29/2024 23:50:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7124, 'learning_rate': 4.9238e-05, 'epoch': 0.39}
216
+
217
+ 05/29/2024 23:51:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6734, 'learning_rate': 4.9201e-05, 'epoch': 0.40}
218
+
219
+ 05/29/2024 23:52:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6914, 'learning_rate': 4.9164e-05, 'epoch': 0.41}
220
+
221
+ 05/29/2024 23:53:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6584, 'learning_rate': 4.9126e-05, 'epoch': 0.42}
222
+
223
+ 05/29/2024 23:55:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6326, 'learning_rate': 4.9087e-05, 'epoch': 0.43}
224
+
225
+ 05/29/2024 23:56:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6931, 'learning_rate': 4.9047e-05, 'epoch': 0.44}
226
+
227
+ 05/29/2024 23:57:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6769, 'learning_rate': 4.9006e-05, 'epoch': 0.45}
228
+
229
+ 05/29/2024 23:58:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6957, 'learning_rate': 4.8965e-05, 'epoch': 0.46}
230
+
231
+ 05/29/2024 23:59:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6949, 'learning_rate': 4.8922e-05, 'epoch': 0.47}
232
+
233
+ 05/30/2024 00:00:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.7084, 'learning_rate': 4.8879e-05, 'epoch': 0.48}
234
+
235
+ 05/30/2024 00:01:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6439, 'learning_rate': 4.8835e-05, 'epoch': 0.49}
236
+
237
+ 05/30/2024 00:02:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6540, 'learning_rate': 4.8790e-05, 'epoch': 0.50}
238
+
239
+ 05/30/2024 00:04:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6513, 'learning_rate': 4.8744e-05, 'epoch': 0.51}
240
+
241
+ 05/30/2024 00:05:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6406, 'learning_rate': 4.8698e-05, 'epoch': 0.52}
242
+
243
+ 05/30/2024 00:06:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6761, 'learning_rate': 4.8650e-05, 'epoch': 0.53}
244
+
245
+ 05/30/2024 00:07:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6440, 'learning_rate': 4.8602e-05, 'epoch': 0.53}
246
+
247
+ 05/30/2024 00:08:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6619, 'learning_rate': 4.8553e-05, 'epoch': 0.54}
248
+
249
+ 05/30/2024 00:09:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6855, 'learning_rate': 4.8503e-05, 'epoch': 0.55}
250
+
251
+ 05/30/2024 00:10:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6716, 'learning_rate': 4.8453e-05, 'epoch': 0.56}
252
+
253
+ 05/30/2024 00:10:44 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-300
254
+
255
+ 05/30/2024 00:10:44 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-300/tokenizer_config.json
256
+
257
+ 05/30/2024 00:10:44 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-300/special_tokens_map.json
258
+
259
+ 05/30/2024 00:11:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6784, 'learning_rate': 4.8401e-05, 'epoch': 0.57}
260
+
261
+ 05/30/2024 00:12:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6587, 'learning_rate': 4.8349e-05, 'epoch': 0.58}
262
+
263
+ 05/30/2024 00:14:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6411, 'learning_rate': 4.8296e-05, 'epoch': 0.59}
264
+
265
+ 05/30/2024 00:15:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7191, 'learning_rate': 4.8242e-05, 'epoch': 0.60}
266
+
267
+ 05/30/2024 00:16:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6679, 'learning_rate': 4.8188e-05, 'epoch': 0.61}
268
+
269
+ 05/30/2024 00:17:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6270, 'learning_rate': 4.8132e-05, 'epoch': 0.62}
270
+
271
+ 05/30/2024 00:18:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7084, 'learning_rate': 4.8076e-05, 'epoch': 0.63}
272
+
273
+ 05/30/2024 00:19:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6555, 'learning_rate': 4.8019e-05, 'epoch': 0.64}
274
+
275
+ 05/30/2024 00:20:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6865, 'learning_rate': 4.7961e-05, 'epoch': 0.65}
276
+
277
+ 05/30/2024 00:22:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6968, 'learning_rate': 4.7902e-05, 'epoch': 0.66}
278
+
279
+ 05/30/2024 00:23:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6370, 'learning_rate': 4.7843e-05, 'epoch': 0.67}
280
+
281
+ 05/30/2024 00:24:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6898, 'learning_rate': 4.7782e-05, 'epoch': 0.68}
282
+
283
+ 05/30/2024 00:25:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6258, 'learning_rate': 4.7721e-05, 'epoch': 0.68}
284
+
285
+ 05/30/2024 00:26:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6418, 'learning_rate': 4.7659e-05, 'epoch': 0.69}
286
+
287
+ 05/30/2024 00:27:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6957, 'learning_rate': 4.7597e-05, 'epoch': 0.70}
288
+
289
+ 05/30/2024 00:28:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6813, 'learning_rate': 4.7533e-05, 'epoch': 0.71}
290
+
291
+ 05/30/2024 00:29:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6565, 'learning_rate': 4.7469e-05, 'epoch': 0.72}
292
+
293
+ 05/30/2024 00:30:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6557, 'learning_rate': 4.7404e-05, 'epoch': 0.73}
294
+
295
+ 05/30/2024 00:32:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6715, 'learning_rate': 4.7338e-05, 'epoch': 0.74}
296
+
297
+ 05/30/2024 00:33:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6929, 'learning_rate': 4.7272e-05, 'epoch': 0.75}
298
+
299
+ 05/30/2024 00:33:08 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-400
300
+
301
+ 05/30/2024 00:33:08 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-400/tokenizer_config.json
302
+
303
+ 05/30/2024 00:33:08 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-400/special_tokens_map.json
304
+
305
+ 05/30/2024 00:34:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6474, 'learning_rate': 4.7204e-05, 'epoch': 0.76}
306
+
307
+ 05/30/2024 00:35:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6519, 'learning_rate': 4.7136e-05, 'epoch': 0.77}
308
+
309
+ 05/30/2024 00:36:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6600, 'learning_rate': 4.7068e-05, 'epoch': 0.78}
310
+
311
+ 05/30/2024 00:37:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.7041, 'learning_rate': 4.6998e-05, 'epoch': 0.79}
312
+
313
+ 05/30/2024 00:38:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6676, 'learning_rate': 4.6928e-05, 'epoch': 0.80}
314
+
315
+ 05/30/2024 00:39:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6382, 'learning_rate': 4.6856e-05, 'epoch': 0.81}
316
+
317
+ 05/30/2024 00:41:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5761, 'learning_rate': 4.6784e-05, 'epoch': 0.82}
318
+
319
+ 05/30/2024 00:42:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6149, 'learning_rate': 4.6712e-05, 'epoch': 0.83}
320
+
321
+ 05/30/2024 00:43:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6610, 'learning_rate': 4.6638e-05, 'epoch': 0.83}
322
+
323
+ 05/30/2024 00:44:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6477, 'learning_rate': 4.6564e-05, 'epoch': 0.84}
324
+
325
+ 05/30/2024 00:45:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6267, 'learning_rate': 4.6489e-05, 'epoch': 0.85}
326
+
327
+ 05/30/2024 00:46:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6776, 'learning_rate': 4.6414e-05, 'epoch': 0.86}
328
+
329
+ 05/30/2024 00:47:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6450, 'learning_rate': 4.6337e-05, 'epoch': 0.87}
330
+
331
+ 05/30/2024 00:48:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6486, 'learning_rate': 4.6260e-05, 'epoch': 0.88}
332
+
333
+ 05/30/2024 00:50:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6784, 'learning_rate': 4.6182e-05, 'epoch': 0.89}
334
+
335
+ 05/30/2024 00:51:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6595, 'learning_rate': 4.6103e-05, 'epoch': 0.90}
336
+
337
+ 05/30/2024 00:52:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6403, 'learning_rate': 4.6024e-05, 'epoch': 0.91}
338
+
339
+ 05/30/2024 00:53:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6334, 'learning_rate': 4.5944e-05, 'epoch': 0.92}
340
+
341
+ 05/30/2024 00:54:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7385, 'learning_rate': 4.5863e-05, 'epoch': 0.93}
342
+
343
+ 05/30/2024 00:55:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6463, 'learning_rate': 4.5782e-05, 'epoch': 0.94}
344
+
345
+ 05/30/2024 00:55:38 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-500
346
+
347
+ 05/30/2024 00:55:38 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-500/tokenizer_config.json
348
+
349
+ 05/30/2024 00:55:38 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-500/special_tokens_map.json
350
+
351
+ 05/30/2024 00:56:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6693, 'learning_rate': 4.5699e-05, 'epoch': 0.95}
352
+
353
+ 05/30/2024 00:57:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7034, 'learning_rate': 4.5616e-05, 'epoch': 0.96}
354
+
355
+ 05/30/2024 00:59:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6520, 'learning_rate': 4.5533e-05, 'epoch': 0.97}
356
+
357
+ 05/30/2024 01:00:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6399, 'learning_rate': 4.5448e-05, 'epoch': 0.98}
358
+
359
+ 05/30/2024 01:01:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6426, 'learning_rate': 4.5363e-05, 'epoch': 0.98}
360
+
361
+ 05/30/2024 01:02:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6600, 'learning_rate': 4.5277e-05, 'epoch': 0.99}
362
+
363
+ 05/30/2024 01:03:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6243, 'learning_rate': 4.5191e-05, 'epoch': 1.00}
364
+
365
+ 05/30/2024 01:04:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6001, 'learning_rate': 4.5103e-05, 'epoch': 1.01}
366
+
367
+ 05/30/2024 01:05:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6071, 'learning_rate': 4.5016e-05, 'epoch': 1.02}
368
+
369
+ 05/30/2024 01:07:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6617, 'learning_rate': 4.4927e-05, 'epoch': 1.03}
370
+
371
+ 05/30/2024 01:08:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6291, 'learning_rate': 4.4838e-05, 'epoch': 1.04}
372
+
373
+ 05/30/2024 01:09:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6011, 'learning_rate': 4.4748e-05, 'epoch': 1.05}
374
+
375
+ 05/30/2024 01:10:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6631, 'learning_rate': 4.4657e-05, 'epoch': 1.06}
376
+
377
+ 05/30/2024 01:11:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6544, 'learning_rate': 4.4565e-05, 'epoch': 1.07}
378
+
379
+ 05/30/2024 01:12:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6332, 'learning_rate': 4.4473e-05, 'epoch': 1.08}
380
+
381
+ 05/30/2024 01:14:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6426, 'learning_rate': 4.4381e-05, 'epoch': 1.09}
382
+
383
+ 05/30/2024 01:15:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6362, 'learning_rate': 4.4287e-05, 'epoch': 1.10}
384
+
385
+ 05/30/2024 01:16:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6136, 'learning_rate': 4.4193e-05, 'epoch': 1.11}
386
+
387
+ 05/30/2024 01:17:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6360, 'learning_rate': 4.4098e-05, 'epoch': 1.12}
388
+
389
+ 05/30/2024 01:18:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6253, 'learning_rate': 4.4003e-05, 'epoch': 1.13}
390
+
391
+ 05/30/2024 01:18:38 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-600
392
+
393
+ 05/30/2024 01:18:38 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-600/tokenizer_config.json
394
+
395
+ 05/30/2024 01:18:38 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-600/special_tokens_map.json
396
+
397
+ 05/30/2024 01:19:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6351, 'learning_rate': 4.3907e-05, 'epoch': 1.13}
398
+
399
+ 05/30/2024 01:20:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.5974, 'learning_rate': 4.3810e-05, 'epoch': 1.14}
400
+
401
+ 05/30/2024 01:21:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6023, 'learning_rate': 4.3713e-05, 'epoch': 1.15}
402
+
403
+ 05/30/2024 01:23:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6096, 'learning_rate': 4.3615e-05, 'epoch': 1.16}
404
+
405
+ 05/30/2024 01:24:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6156, 'learning_rate': 4.3516e-05, 'epoch': 1.17}
406
+
407
+ 05/30/2024 01:25:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6406, 'learning_rate': 4.3417e-05, 'epoch': 1.18}
408
+
409
+ 05/30/2024 01:26:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6224, 'learning_rate': 4.3317e-05, 'epoch': 1.19}
410
+
411
+ 05/30/2024 01:27:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6188, 'learning_rate': 4.3216e-05, 'epoch': 1.20}
412
+
413
+ 05/30/2024 01:28:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6088, 'learning_rate': 4.3115e-05, 'epoch': 1.21}
414
+
415
+ 05/30/2024 01:29:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6570, 'learning_rate': 4.3013e-05, 'epoch': 1.22}
416
+
417
+ 05/30/2024 01:30:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6417, 'learning_rate': 4.2911e-05, 'epoch': 1.23}
418
+
419
+ 05/30/2024 01:32:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6402, 'learning_rate': 4.2807e-05, 'epoch': 1.24}
420
+
421
+ 05/30/2024 01:33:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6393, 'learning_rate': 4.2704e-05, 'epoch': 1.25}
422
+
423
+ 05/30/2024 01:34:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7175, 'learning_rate': 4.2599e-05, 'epoch': 1.26}
424
+
425
+ 05/30/2024 01:35:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6800, 'learning_rate': 4.2494e-05, 'epoch': 1.27}
426
+
427
+ 05/30/2024 01:36:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5966, 'learning_rate': 4.2389e-05, 'epoch': 1.28}
428
+
429
+ 05/30/2024 01:37:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6432, 'learning_rate': 4.2283e-05, 'epoch': 1.28}
430
+
431
+ 05/30/2024 01:38:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6688, 'learning_rate': 4.2176e-05, 'epoch': 1.29}
432
+
433
+ 05/30/2024 01:40:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6407, 'learning_rate': 4.2069e-05, 'epoch': 1.30}
434
+
435
+ 05/30/2024 01:41:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6084, 'learning_rate': 4.1961e-05, 'epoch': 1.31}
436
+
437
+ 05/30/2024 01:41:05 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-700
438
+
439
+ 05/30/2024 01:41:05 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-700/tokenizer_config.json
440
+
441
+ 05/30/2024 01:41:05 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-700/special_tokens_map.json
442
+
443
+ 05/30/2024 01:42:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6407, 'learning_rate': 4.1852e-05, 'epoch': 1.32}
444
+
445
+ 05/30/2024 01:43:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6430, 'learning_rate': 4.1743e-05, 'epoch': 1.33}
446
+
447
+ 05/30/2024 01:44:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5899, 'learning_rate': 4.1633e-05, 'epoch': 1.34}
448
+
449
+ 05/30/2024 01:45:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6299, 'learning_rate': 4.1523e-05, 'epoch': 1.35}
450
+
451
+ 05/30/2024 01:46:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6462, 'learning_rate': 4.1412e-05, 'epoch': 1.36}
452
+
453
+ 05/30/2024 01:47:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6558, 'learning_rate': 4.1301e-05, 'epoch': 1.37}
454
+
455
+ 05/30/2024 01:48:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6316, 'learning_rate': 4.1189e-05, 'epoch': 1.38}
456
+
457
+ 05/30/2024 01:49:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6143, 'learning_rate': 4.1076e-05, 'epoch': 1.39}
458
+
459
+ 05/30/2024 01:51:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6358, 'learning_rate': 4.0963e-05, 'epoch': 1.40}
460
+
461
+ 05/30/2024 01:52:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6276, 'learning_rate': 4.0849e-05, 'epoch': 1.41}
462
+
463
+ 05/30/2024 01:53:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6238, 'learning_rate': 4.0735e-05, 'epoch': 1.42}
464
+
465
+ 05/30/2024 01:54:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6775, 'learning_rate': 4.0620e-05, 'epoch': 1.43}
466
+
467
+ 05/30/2024 01:55:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6330, 'learning_rate': 4.0505e-05, 'epoch': 1.43}
468
+
469
+ 05/30/2024 01:56:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6307, 'learning_rate': 4.0389e-05, 'epoch': 1.44}
470
+
471
+ 05/30/2024 01:57:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.5959, 'learning_rate': 4.0273e-05, 'epoch': 1.45}
472
+
473
+ 05/30/2024 01:58:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6334, 'learning_rate': 4.0156e-05, 'epoch': 1.46}
474
+
475
+ 05/30/2024 02:00:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6440, 'learning_rate': 4.0038e-05, 'epoch': 1.47}
476
+
477
+ 05/30/2024 02:01:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.7045, 'learning_rate': 3.9920e-05, 'epoch': 1.48}
478
+
479
+ 05/30/2024 02:02:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6335, 'learning_rate': 3.9802e-05, 'epoch': 1.49}
480
+
481
+ 05/30/2024 02:03:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6705, 'learning_rate': 3.9683e-05, 'epoch': 1.50}
482
+
483
+ 05/30/2024 02:03:25 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-800
484
+
485
+ 05/30/2024 02:03:25 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-800/tokenizer_config.json
486
+
487
+ 05/30/2024 02:03:25 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-800/special_tokens_map.json
488
+
489
+ 05/30/2024 02:04:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6219, 'learning_rate': 3.9563e-05, 'epoch': 1.51}
490
+
491
+ 05/30/2024 02:05:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6101, 'learning_rate': 3.9443e-05, 'epoch': 1.52}
492
+
493
+ 05/30/2024 02:06:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5930, 'learning_rate': 3.9323e-05, 'epoch': 1.53}
494
+
495
+ 05/30/2024 02:07:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6577, 'learning_rate': 3.9202e-05, 'epoch': 1.54}
496
+
497
+ 05/30/2024 02:09:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6369, 'learning_rate': 3.9080e-05, 'epoch': 1.55}
498
+
499
+ 05/30/2024 02:10:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6459, 'learning_rate': 3.8958e-05, 'epoch': 1.56}
500
+
501
+ 05/30/2024 02:11:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5747, 'learning_rate': 3.8836e-05, 'epoch': 1.57}
502
+
503
+ 05/30/2024 02:12:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6334, 'learning_rate': 3.8713e-05, 'epoch': 1.58}
504
+
505
+ 05/30/2024 02:13:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5922, 'learning_rate': 3.8589e-05, 'epoch': 1.58}
506
+
507
+ 05/30/2024 02:14:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6324, 'learning_rate': 3.8465e-05, 'epoch': 1.59}
508
+
509
+ 05/30/2024 02:15:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6397, 'learning_rate': 3.8341e-05, 'epoch': 1.60}
510
+
511
+ 05/30/2024 02:16:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6344, 'learning_rate': 3.8216e-05, 'epoch': 1.61}
512
+
513
+ 05/30/2024 02:17:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.5903, 'learning_rate': 3.8091e-05, 'epoch': 1.62}
514
+
515
+ 05/30/2024 02:19:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6362, 'learning_rate': 3.7965e-05, 'epoch': 1.63}
516
+
517
+ 05/30/2024 02:20:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6037, 'learning_rate': 3.7839e-05, 'epoch': 1.64}
518
+
519
+ 05/30/2024 02:21:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6131, 'learning_rate': 3.7712e-05, 'epoch': 1.65}
520
+
521
+ 05/30/2024 02:22:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6504, 'learning_rate': 3.7585e-05, 'epoch': 1.66}
522
+
523
+ 05/30/2024 02:23:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5784, 'learning_rate': 3.7457e-05, 'epoch': 1.67}
524
+
525
+ 05/30/2024 02:24:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6192, 'learning_rate': 3.7329e-05, 'epoch': 1.68}
526
+
527
+ 05/30/2024 02:25:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6849, 'learning_rate': 3.7201e-05, 'epoch': 1.69}
528
+
529
+ 05/30/2024 02:25:52 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-900
530
+
531
+ 05/30/2024 02:25:52 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-900/tokenizer_config.json
532
+
533
+ 05/30/2024 02:25:52 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-900/special_tokens_map.json
534
+
535
+ 05/30/2024 02:27:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6645, 'learning_rate': 3.7072e-05, 'epoch': 1.70}
536
+
537
+ 05/30/2024 02:28:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6728, 'learning_rate': 3.6943e-05, 'epoch': 1.71}
538
+
539
+ 05/30/2024 02:29:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6476, 'learning_rate': 3.6813e-05, 'epoch': 1.72}
540
+
541
+ 05/30/2024 02:30:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7412, 'learning_rate': 3.6683e-05, 'epoch': 1.73}
542
+
543
+ 05/30/2024 02:31:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6201, 'learning_rate': 3.6553e-05, 'epoch': 1.73}
544
+
545
+ 05/30/2024 02:32:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6296, 'learning_rate': 3.6422e-05, 'epoch': 1.74}
546
+
547
+ 05/30/2024 02:33:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6199, 'learning_rate': 3.6291e-05, 'epoch': 1.75}
548
+
549
+ 05/30/2024 02:35:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6726, 'learning_rate': 3.6159e-05, 'epoch': 1.76}
550
+
551
+ 05/30/2024 02:36:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6077, 'learning_rate': 3.6027e-05, 'epoch': 1.77}
552
+
553
+ 05/30/2024 02:37:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6546, 'learning_rate': 3.5894e-05, 'epoch': 1.78}
554
+
555
+ 05/30/2024 02:38:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6134, 'learning_rate': 3.5762e-05, 'epoch': 1.79}
556
+
557
+ 05/30/2024 02:39:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6833, 'learning_rate': 3.5628e-05, 'epoch': 1.80}
558
+
559
+ 05/30/2024 02:40:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6008, 'learning_rate': 3.5495e-05, 'epoch': 1.81}
560
+
561
+ 05/30/2024 02:41:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6444, 'learning_rate': 3.5361e-05, 'epoch': 1.82}
562
+
563
+ 05/30/2024 02:43:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5960, 'learning_rate': 3.5227e-05, 'epoch': 1.83}
564
+
565
+ 05/30/2024 02:44:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5834, 'learning_rate': 3.5092e-05, 'epoch': 1.84}
566
+
567
+ 05/30/2024 02:45:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6094, 'learning_rate': 3.4957e-05, 'epoch': 1.85}
568
+
569
+ 05/30/2024 02:46:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5964, 'learning_rate': 3.4822e-05, 'epoch': 1.86}
570
+
571
+ 05/30/2024 02:47:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6180, 'learning_rate': 3.4686e-05, 'epoch': 1.87}
572
+
573
+ 05/30/2024 02:48:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.5960, 'learning_rate': 3.4550e-05, 'epoch': 1.88}
574
+
575
+ 05/30/2024 02:48:50 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1000
576
+
577
+ 05/30/2024 02:48:50 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1000/tokenizer_config.json
578
+
579
+ 05/30/2024 02:48:50 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1000/special_tokens_map.json
580
+
581
+ 05/30/2024 02:49:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5774, 'learning_rate': 3.4414e-05, 'epoch': 1.88}
582
+
583
+ 05/30/2024 02:51:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5982, 'learning_rate': 3.4277e-05, 'epoch': 1.89}
584
+
585
+ 05/30/2024 02:52:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6422, 'learning_rate': 3.4140e-05, 'epoch': 1.90}
586
+
587
+ 05/30/2024 02:53:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6312, 'learning_rate': 3.4003e-05, 'epoch': 1.91}
588
+
589
+ 05/30/2024 02:54:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5998, 'learning_rate': 3.3865e-05, 'epoch': 1.92}
590
+
591
+ 05/30/2024 02:55:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6103, 'learning_rate': 3.3727e-05, 'epoch': 1.93}
592
+
593
+ 05/30/2024 02:56:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6074, 'learning_rate': 3.3589e-05, 'epoch': 1.94}
594
+
595
+ 05/30/2024 02:57:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6142, 'learning_rate': 3.3450e-05, 'epoch': 1.95}
596
+
597
+ 05/30/2024 02:58:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6366, 'learning_rate': 3.3312e-05, 'epoch': 1.96}
598
+
599
+ 05/30/2024 02:59:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5871, 'learning_rate': 3.3172e-05, 'epoch': 1.97}
600
+
601
+ 05/30/2024 03:01:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6010, 'learning_rate': 3.3033e-05, 'epoch': 1.98}
602
+
603
+ 05/30/2024 03:02:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5808, 'learning_rate': 3.2893e-05, 'epoch': 1.99}
604
+
605
+ 05/30/2024 03:03:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6152, 'learning_rate': 3.2753e-05, 'epoch': 2.00}
606
+
607
+ 05/30/2024 03:04:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5649, 'learning_rate': 3.2613e-05, 'epoch': 2.01}
608
+
609
+ 05/30/2024 03:05:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5623, 'learning_rate': 3.2473e-05, 'epoch': 2.02}
610
+
611
+ 05/30/2024 03:06:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6362, 'learning_rate': 3.2332e-05, 'epoch': 2.03}
612
+
613
+ 05/30/2024 03:08:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6060, 'learning_rate': 3.2191e-05, 'epoch': 2.03}
614
+
615
+ 05/30/2024 03:09:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6176, 'learning_rate': 3.2050e-05, 'epoch': 2.04}
616
+
617
+ 05/30/2024 03:10:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6362, 'learning_rate': 3.1908e-05, 'epoch': 2.05}
618
+
619
+ 05/30/2024 03:11:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5969, 'learning_rate': 3.1767e-05, 'epoch': 2.06}
620
+
621
+ 05/30/2024 03:11:26 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1100
622
+
623
+ 05/30/2024 03:11:26 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1100/tokenizer_config.json
624
+
625
+ 05/30/2024 03:11:26 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1100/special_tokens_map.json
626
+
627
+ 05/30/2024 03:12:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5587, 'learning_rate': 3.1625e-05, 'epoch': 2.07}
628
+
629
+ 05/30/2024 03:13:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5828, 'learning_rate': 3.1482e-05, 'epoch': 2.08}
630
+
631
+ 05/30/2024 03:14:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6010, 'learning_rate': 3.1340e-05, 'epoch': 2.09}
632
+
633
+ 05/30/2024 03:15:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6003, 'learning_rate': 3.1197e-05, 'epoch': 2.10}
634
+
635
+ 05/30/2024 03:17:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6198, 'learning_rate': 3.1054e-05, 'epoch': 2.11}
636
+
637
+ 05/30/2024 03:18:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6133, 'learning_rate': 3.0911e-05, 'epoch': 2.12}
638
+
639
+ 05/30/2024 03:19:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6002, 'learning_rate': 3.0768e-05, 'epoch': 2.13}
640
+
641
+ 05/30/2024 03:20:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6979, 'learning_rate': 3.0625e-05, 'epoch': 2.14}
642
+
643
+ 05/30/2024 03:21:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5819, 'learning_rate': 3.0481e-05, 'epoch': 2.15}
644
+
645
+ 05/30/2024 03:22:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.5804, 'learning_rate': 3.0337e-05, 'epoch': 2.16}
646
+
647
+ 05/30/2024 03:23:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5913, 'learning_rate': 3.0193e-05, 'epoch': 2.17}
648
+
649
+ 05/30/2024 03:25:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5993, 'learning_rate': 3.0049e-05, 'epoch': 2.18}
650
+
651
+ 05/30/2024 03:26:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6061, 'learning_rate': 2.9904e-05, 'epoch': 2.18}
652
+
653
+ 05/30/2024 03:27:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6630, 'learning_rate': 2.9760e-05, 'epoch': 2.19}
654
+
655
+ 05/30/2024 03:28:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6158, 'learning_rate': 2.9615e-05, 'epoch': 2.20}
656
+
657
+ 05/30/2024 03:29:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6348, 'learning_rate': 2.9470e-05, 'epoch': 2.21}
658
+
659
+ 05/30/2024 03:30:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6263, 'learning_rate': 2.9325e-05, 'epoch': 2.22}
660
+
661
+ 05/30/2024 03:31:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5918, 'learning_rate': 2.9180e-05, 'epoch': 2.23}
662
+
663
+ 05/30/2024 03:33:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5724, 'learning_rate': 2.9035e-05, 'epoch': 2.24}
664
+
665
+ 05/30/2024 03:34:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6142, 'learning_rate': 2.8889e-05, 'epoch': 2.25}
666
+
667
+ 05/30/2024 03:34:08 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1200
668
+
669
+ 05/30/2024 03:34:08 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1200/tokenizer_config.json
670
+
671
+ 05/30/2024 03:34:08 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1200/special_tokens_map.json
672
+
673
+ 05/30/2024 03:35:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6048, 'learning_rate': 2.8743e-05, 'epoch': 2.26}
674
+
675
+ 05/30/2024 03:36:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6531, 'learning_rate': 2.8598e-05, 'epoch': 2.27}
676
+
677
+ 05/30/2024 03:37:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5875, 'learning_rate': 2.8452e-05, 'epoch': 2.28}
678
+
679
+ 05/30/2024 03:38:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5762, 'learning_rate': 2.8306e-05, 'epoch': 2.29}
680
+
681
+ 05/30/2024 03:39:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6074, 'learning_rate': 2.8160e-05, 'epoch': 2.30}
682
+
683
+ 05/30/2024 03:40:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.5865, 'learning_rate': 2.8013e-05, 'epoch': 2.31}
684
+
685
+ 05/30/2024 03:42:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6015, 'learning_rate': 2.7867e-05, 'epoch': 2.32}
686
+
687
+ 05/30/2024 03:43:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5973, 'learning_rate': 2.7721e-05, 'epoch': 2.33}
688
+
689
+ 05/30/2024 03:44:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6309, 'learning_rate': 2.7574e-05, 'epoch': 2.33}
690
+
691
+ 05/30/2024 03:45:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6291, 'learning_rate': 2.7428e-05, 'epoch': 2.34}
692
+
693
+ 05/30/2024 03:46:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6297, 'learning_rate': 2.7281e-05, 'epoch': 2.35}
694
+
695
+ 05/30/2024 03:47:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5846, 'learning_rate': 2.7134e-05, 'epoch': 2.36}
696
+
697
+ 05/30/2024 03:48:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6009, 'learning_rate': 2.6987e-05, 'epoch': 2.37}
698
+
699
+ 05/30/2024 03:49:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6807, 'learning_rate': 2.6840e-05, 'epoch': 2.38}
700
+
701
+ 05/30/2024 03:51:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.5976, 'learning_rate': 2.6693e-05, 'epoch': 2.39}
702
+
703
+ 05/30/2024 03:52:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6617, 'learning_rate': 2.6546e-05, 'epoch': 2.40}
704
+
705
+ 05/30/2024 03:53:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6327, 'learning_rate': 2.6399e-05, 'epoch': 2.41}
706
+
707
+ 05/30/2024 03:54:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6101, 'learning_rate': 2.6252e-05, 'epoch': 2.42}
708
+
709
+ 05/30/2024 03:55:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5672, 'learning_rate': 2.6105e-05, 'epoch': 2.43}
710
+
711
+ 05/30/2024 03:56:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6172, 'learning_rate': 2.5958e-05, 'epoch': 2.44}
712
+
713
+ 05/30/2024 03:56:45 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1300
714
+
715
+ 05/30/2024 03:56:45 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1300/tokenizer_config.json
716
+
717
+ 05/30/2024 03:56:45 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1300/special_tokens_map.json
718
+
719
+ 05/30/2024 03:57:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6848, 'learning_rate': 2.5810e-05, 'epoch': 2.45}
720
+
721
+ 05/30/2024 03:59:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6313, 'learning_rate': 2.5663e-05, 'epoch': 2.46}
722
+
723
+ 05/30/2024 04:00:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5976, 'learning_rate': 2.5516e-05, 'epoch': 2.47}
724
+
725
+ 05/30/2024 04:01:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5623, 'learning_rate': 2.5368e-05, 'epoch': 2.48}
726
+
727
+ 05/30/2024 04:02:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6274, 'learning_rate': 2.5221e-05, 'epoch': 2.48}
728
+
729
+ 05/30/2024 04:03:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5823, 'learning_rate': 2.5074e-05, 'epoch': 2.49}
730
+
731
+ 05/30/2024 04:04:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5900, 'learning_rate': 2.4926e-05, 'epoch': 2.50}
732
+
733
+ 05/30/2024 04:05:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6277, 'learning_rate': 2.4779e-05, 'epoch': 2.51}
734
+
735
+ 05/30/2024 04:06:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5809, 'learning_rate': 2.4632e-05, 'epoch': 2.52}
736
+
737
+ 05/30/2024 04:07:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.5756, 'learning_rate': 2.4484e-05, 'epoch': 2.53}
738
+
739
+ 05/30/2024 04:09:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6230, 'learning_rate': 2.4337e-05, 'epoch': 2.54}
740
+
741
+ 05/30/2024 04:10:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6328, 'learning_rate': 2.4190e-05, 'epoch': 2.55}
742
+
743
+ 05/30/2024 04:11:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.5745, 'learning_rate': 2.4042e-05, 'epoch': 2.56}
744
+
745
+ 05/30/2024 04:12:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5681, 'learning_rate': 2.3895e-05, 'epoch': 2.57}
746
+
747
+ 05/30/2024 04:13:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6243, 'learning_rate': 2.3748e-05, 'epoch': 2.58}
748
+
749
+ 05/30/2024 04:14:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6017, 'learning_rate': 2.3601e-05, 'epoch': 2.59}
750
+
751
+ 05/30/2024 04:16:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5900, 'learning_rate': 2.3454e-05, 'epoch': 2.60}
752
+
753
+ 05/30/2024 04:17:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5715, 'learning_rate': 2.3307e-05, 'epoch': 2.61}
754
+
755
+ 05/30/2024 04:18:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6479, 'learning_rate': 2.3160e-05, 'epoch': 2.62}
756
+
757
+ 05/30/2024 04:19:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6044, 'learning_rate': 2.3013e-05, 'epoch': 2.63}
758
+
759
+ 05/30/2024 04:19:23 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1400
760
+
761
+ 05/30/2024 04:19:23 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1400/tokenizer_config.json
762
+
763
+ 05/30/2024 04:19:23 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1400/special_tokens_map.json
764
+
765
+ 05/30/2024 04:20:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.5893, 'learning_rate': 2.2866e-05, 'epoch': 2.63}
766
+
767
+ 05/30/2024 04:21:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5733, 'learning_rate': 2.2719e-05, 'epoch': 2.64}
768
+
769
+ 05/30/2024 04:22:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5649, 'learning_rate': 2.2572e-05, 'epoch': 2.65}
770
+
771
+ 05/30/2024 04:23:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5842, 'learning_rate': 2.2426e-05, 'epoch': 2.66}
772
+
773
+ 05/30/2024 04:24:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.5905, 'learning_rate': 2.2279e-05, 'epoch': 2.67}
774
+
775
+ 05/30/2024 04:25:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6128, 'learning_rate': 2.2133e-05, 'epoch': 2.68}
776
+
777
+ 05/30/2024 04:27:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6135, 'learning_rate': 2.1987e-05, 'epoch': 2.69}
778
+
779
+ 05/30/2024 04:28:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5995, 'learning_rate': 2.1840e-05, 'epoch': 2.70}
780
+
781
+ 05/30/2024 04:29:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6354, 'learning_rate': 2.1694e-05, 'epoch': 2.71}
782
+
783
+ 05/30/2024 04:30:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6152, 'learning_rate': 2.1548e-05, 'epoch': 2.72}
784
+
785
+ 05/30/2024 04:31:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5884, 'learning_rate': 2.1402e-05, 'epoch': 2.73}
786
+
787
+ 05/30/2024 04:32:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5956, 'learning_rate': 2.1257e-05, 'epoch': 2.74}
788
+
789
+ 05/30/2024 04:33:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5954, 'learning_rate': 2.1111e-05, 'epoch': 2.75}
790
+
791
+ 05/30/2024 04:34:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6026, 'learning_rate': 2.0965e-05, 'epoch': 2.76}
792
+
793
+ 05/30/2024 04:35:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5849, 'learning_rate': 2.0820e-05, 'epoch': 2.77}
794
+
795
+ 05/30/2024 04:37:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5873, 'learning_rate': 2.0675e-05, 'epoch': 2.78}
796
+
797
+ 05/30/2024 04:38:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6195, 'learning_rate': 2.0530e-05, 'epoch': 2.78}
798
+
799
+ 05/30/2024 04:39:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6176, 'learning_rate': 2.0385e-05, 'epoch': 2.79}
800
+
801
+ 05/30/2024 04:40:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6364, 'learning_rate': 2.0240e-05, 'epoch': 2.80}
802
+
803
+ 05/30/2024 04:41:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5921, 'learning_rate': 2.0096e-05, 'epoch': 2.81}
804
+
805
+ 05/30/2024 04:41:35 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1500
806
+
807
+ 05/30/2024 04:41:35 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1500/tokenizer_config.json
808
+
809
+ 05/30/2024 04:41:35 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1500/special_tokens_map.json
810
+
811
+ 05/30/2024 04:42:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5787, 'learning_rate': 1.9951e-05, 'epoch': 2.82}
812
+
813
+ 05/30/2024 04:43:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5955, 'learning_rate': 1.9807e-05, 'epoch': 2.83}
814
+
815
+ 05/30/2024 04:44:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6349, 'learning_rate': 1.9663e-05, 'epoch': 2.84}
816
+
817
+ 05/30/2024 04:46:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5990, 'learning_rate': 1.9519e-05, 'epoch': 2.85}
818
+
819
+ 05/30/2024 04:47:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6072, 'learning_rate': 1.9375e-05, 'epoch': 2.86}
820
+
821
+ 05/30/2024 04:48:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5714, 'learning_rate': 1.9232e-05, 'epoch': 2.87}
822
+
823
+ 05/30/2024 04:49:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6001, 'learning_rate': 1.9089e-05, 'epoch': 2.88}
824
+
825
+ 05/30/2024 04:50:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5621, 'learning_rate': 1.8946e-05, 'epoch': 2.89}
826
+
827
+ 05/30/2024 04:51:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6401, 'learning_rate': 1.8803e-05, 'epoch': 2.90}
828
+
829
+ 05/30/2024 04:52:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.5987, 'learning_rate': 1.8660e-05, 'epoch': 2.91}
830
+
831
+ 05/30/2024 04:53:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5915, 'learning_rate': 1.8518e-05, 'epoch': 2.92}
832
+
833
+ 05/30/2024 04:55:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6210, 'learning_rate': 1.8375e-05, 'epoch': 2.93}
834
+
835
+ 05/30/2024 04:56:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6379, 'learning_rate': 1.8233e-05, 'epoch': 2.93}
836
+
837
+ 05/30/2024 04:57:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.5990, 'learning_rate': 1.8092e-05, 'epoch': 2.94}
838
+
839
+ 05/30/2024 04:58:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6333, 'learning_rate': 1.7950e-05, 'epoch': 2.95}
840
+
841
+ 05/30/2024 04:59:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6245, 'learning_rate': 1.7809e-05, 'epoch': 2.96}
842
+
843
+ 05/30/2024 05:00:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5750, 'learning_rate': 1.7668e-05, 'epoch': 2.97}
844
+
845
+ 05/30/2024 05:01:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6453, 'learning_rate': 1.7527e-05, 'epoch': 2.98}
846
+
847
+ 05/30/2024 05:02:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6524, 'learning_rate': 1.7387e-05, 'epoch': 2.99}
848
+
849
+ 05/30/2024 05:03:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5959, 'learning_rate': 1.7247e-05, 'epoch': 3.00}
850
+
851
+ 05/30/2024 05:03:55 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1600
852
+
853
+ 05/30/2024 05:03:55 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1600/tokenizer_config.json
854
+
855
+ 05/30/2024 05:03:55 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1600/special_tokens_map.json
856
+
857
+ 05/30/2024 05:05:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6342, 'learning_rate': 1.7107e-05, 'epoch': 3.01}
858
+
859
+ 05/30/2024 05:06:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5901, 'learning_rate': 1.6967e-05, 'epoch': 3.02}
860
+
861
+ 05/30/2024 05:07:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6125, 'learning_rate': 1.6828e-05, 'epoch': 3.03}
862
+
863
+ 05/30/2024 05:08:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6208, 'learning_rate': 1.6688e-05, 'epoch': 3.04}
864
+
865
+ 05/30/2024 05:09:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6135, 'learning_rate': 1.6550e-05, 'epoch': 3.05}
866
+
867
+ 05/30/2024 05:10:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5635, 'learning_rate': 1.6411e-05, 'epoch': 3.06}
868
+
869
+ 05/30/2024 05:11:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5519, 'learning_rate': 1.6273e-05, 'epoch': 3.07}
870
+
871
+ 05/30/2024 05:12:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6453, 'learning_rate': 1.6135e-05, 'epoch': 3.08}
872
+
873
+ 05/30/2024 05:14:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.5444, 'learning_rate': 1.5997e-05, 'epoch': 3.08}
874
+
875
+ 05/30/2024 05:15:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6103, 'learning_rate': 1.5860e-05, 'epoch': 3.09}
876
+
877
+ 05/30/2024 05:16:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6560, 'learning_rate': 1.5723e-05, 'epoch': 3.10}
878
+
879
+ 05/30/2024 05:17:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5887, 'learning_rate': 1.5586e-05, 'epoch': 3.11}
880
+
881
+ 05/30/2024 05:18:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5990, 'learning_rate': 1.5450e-05, 'epoch': 3.12}
882
+
883
+ 05/30/2024 05:19:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5677, 'learning_rate': 1.5314e-05, 'epoch': 3.13}
884
+
885
+ 05/30/2024 05:20:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5458, 'learning_rate': 1.5178e-05, 'epoch': 3.14}
886
+
887
+ 05/30/2024 05:21:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6356, 'learning_rate': 1.5043e-05, 'epoch': 3.15}
888
+
889
+ 05/30/2024 05:22:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.5678, 'learning_rate': 1.4908e-05, 'epoch': 3.16}
890
+
891
+ 05/30/2024 05:23:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5883, 'learning_rate': 1.4773e-05, 'epoch': 3.17}
892
+
893
+ 05/30/2024 05:25:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5643, 'learning_rate': 1.4639e-05, 'epoch': 3.18}
894
+
895
+ 05/30/2024 05:26:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5889, 'learning_rate': 1.4505e-05, 'epoch': 3.19}
896
+
897
+ 05/30/2024 05:26:13 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1700
898
+
899
+ 05/30/2024 05:26:13 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1700/tokenizer_config.json
900
+
901
+ 05/30/2024 05:26:13 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1700/special_tokens_map.json
902
+
903
+ 05/30/2024 05:27:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.5550, 'learning_rate': 1.4372e-05, 'epoch': 3.20}
904
+
905
+ 05/30/2024 05:28:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5856, 'learning_rate': 1.4238e-05, 'epoch': 3.21}
906
+
907
+ 05/30/2024 05:29:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6232, 'learning_rate': 1.4106e-05, 'epoch': 3.22}
908
+
909
+ 05/30/2024 05:30:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6432, 'learning_rate': 1.3973e-05, 'epoch': 3.23}
910
+
911
+ 05/30/2024 05:31:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5808, 'learning_rate': 1.3841e-05, 'epoch': 3.23}
912
+
913
+ 05/30/2024 05:32:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5563, 'learning_rate': 1.3709e-05, 'epoch': 3.24}
914
+
915
+ 05/30/2024 05:34:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.5474, 'learning_rate': 1.3578e-05, 'epoch': 3.25}
916
+
917
+ 05/30/2024 05:35:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6451, 'learning_rate': 1.3447e-05, 'epoch': 3.26}
918
+
919
+ 05/30/2024 05:36:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5905, 'learning_rate': 1.3317e-05, 'epoch': 3.27}
920
+
921
+ 05/30/2024 05:37:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5763, 'learning_rate': 1.3187e-05, 'epoch': 3.28}
922
+
923
+ 05/30/2024 05:38:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5873, 'learning_rate': 1.3057e-05, 'epoch': 3.29}
924
+
925
+ 05/30/2024 05:39:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5518, 'learning_rate': 1.2928e-05, 'epoch': 3.30}
926
+
927
+ 05/30/2024 05:40:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5584, 'learning_rate': 1.2799e-05, 'epoch': 3.31}
928
+
929
+ 05/30/2024 05:41:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5702, 'learning_rate': 1.2671e-05, 'epoch': 3.32}
930
+
931
+ 05/30/2024 05:43:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5774, 'learning_rate': 1.2543e-05, 'epoch': 3.33}
932
+
933
+ 05/30/2024 05:44:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6325, 'learning_rate': 1.2415e-05, 'epoch': 3.34}
934
+
935
+ 05/30/2024 05:45:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5764, 'learning_rate': 1.2288e-05, 'epoch': 3.35}
936
+
937
+ 05/30/2024 05:46:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6093, 'learning_rate': 1.2161e-05, 'epoch': 3.36}
938
+
939
+ 05/30/2024 05:47:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6254, 'learning_rate': 1.2035e-05, 'epoch': 3.37}
940
+
941
+ 05/30/2024 05:48:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5884, 'learning_rate': 1.1909e-05, 'epoch': 3.38}
942
+
943
+ 05/30/2024 05:48:34 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1800
944
+
945
+ 05/30/2024 05:48:34 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1800/tokenizer_config.json
946
+
947
+ 05/30/2024 05:48:34 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1800/special_tokens_map.json
948
+
949
+ 05/30/2024 05:49:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5836, 'learning_rate': 1.1784e-05, 'epoch': 3.38}
950
+
951
+ 05/30/2024 05:50:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6103, 'learning_rate': 1.1659e-05, 'epoch': 3.39}
952
+
953
+ 05/30/2024 05:51:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5888, 'learning_rate': 1.1535e-05, 'epoch': 3.40}
954
+
955
+ 05/30/2024 05:52:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6512, 'learning_rate': 1.1411e-05, 'epoch': 3.41}
956
+
957
+ 05/30/2024 05:54:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5910, 'learning_rate': 1.1287e-05, 'epoch': 3.42}
958
+
959
+ 05/30/2024 05:55:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5623, 'learning_rate': 1.1164e-05, 'epoch': 3.43}
960
+
961
+ 05/30/2024 05:56:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6128, 'learning_rate': 1.1042e-05, 'epoch': 3.44}
962
+
963
+ 05/30/2024 05:57:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.5260, 'learning_rate': 1.0920e-05, 'epoch': 3.45}
964
+
965
+ 05/30/2024 05:58:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5670, 'learning_rate': 1.0798e-05, 'epoch': 3.46}
966
+
967
+ 05/30/2024 06:00:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6084, 'learning_rate': 1.0677e-05, 'epoch': 3.47}
968
+
969
+ 05/30/2024 06:01:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5740, 'learning_rate': 1.0557e-05, 'epoch': 3.48}
970
+
971
+ 05/30/2024 06:02:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5817, 'learning_rate': 1.0437e-05, 'epoch': 3.49}
972
+
973
+ 05/30/2024 06:03:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5398, 'learning_rate': 1.0317e-05, 'epoch': 3.50}
974
+
975
+ 05/30/2024 06:04:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.5761, 'learning_rate': 1.0198e-05, 'epoch': 3.51}
976
+
977
+ 05/30/2024 06:05:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5762, 'learning_rate': 1.0080e-05, 'epoch': 3.52}
978
+
979
+ 05/30/2024 06:06:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5656, 'learning_rate': 9.9618e-06, 'epoch': 3.53}
980
+
981
+ 05/30/2024 06:07:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6402, 'learning_rate': 9.8444e-06, 'epoch': 3.53}
982
+
983
+ 05/30/2024 06:09:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5627, 'learning_rate': 9.7274e-06, 'epoch': 3.54}
984
+
985
+ 05/30/2024 06:10:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6265, 'learning_rate': 9.6110e-06, 'epoch': 3.55}
986
+
987
+ 05/30/2024 06:11:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5915, 'learning_rate': 9.4952e-06, 'epoch': 3.56}
988
+
989
+ 05/30/2024 06:11:18 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1900
990
+
991
+ 05/30/2024 06:11:18 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1900/tokenizer_config.json
992
+
993
+ 05/30/2024 06:11:18 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-1900/special_tokens_map.json
994
+
995
+ 05/30/2024 06:12:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6192, 'learning_rate': 9.3799e-06, 'epoch': 3.57}
996
+
997
+ 05/30/2024 06:13:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6139, 'learning_rate': 9.2651e-06, 'epoch': 3.58}
998
+
999
+ 05/30/2024 06:14:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5788, 'learning_rate': 9.1508e-06, 'epoch': 3.59}
1000
+
1001
+ 05/30/2024 06:15:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5967, 'learning_rate': 9.0372e-06, 'epoch': 3.60}
1002
+
1003
+ 05/30/2024 06:16:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.5525, 'learning_rate': 8.9240e-06, 'epoch': 3.61}
1004
+
1005
+ 05/30/2024 06:18:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6459, 'learning_rate': 8.8115e-06, 'epoch': 3.62}
1006
+
1007
+ 05/30/2024 06:19:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6542, 'learning_rate': 8.6995e-06, 'epoch': 3.63}
1008
+
1009
+ 05/30/2024 06:20:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6144, 'learning_rate': 8.5880e-06, 'epoch': 3.64}
1010
+
1011
+ 05/30/2024 06:21:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6243, 'learning_rate': 8.4772e-06, 'epoch': 3.65}
1012
+
1013
+ 05/30/2024 06:22:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6097, 'learning_rate': 8.3669e-06, 'epoch': 3.66}
1014
+
1015
+ 05/30/2024 06:23:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5890, 'learning_rate': 8.2571e-06, 'epoch': 3.67}
1016
+
1017
+ 05/30/2024 06:24:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6196, 'learning_rate': 8.1480e-06, 'epoch': 3.68}
1018
+
1019
+ 05/30/2024 06:25:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5785, 'learning_rate': 8.0395e-06, 'epoch': 3.68}
1020
+
1021
+ 05/30/2024 06:27:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6941, 'learning_rate': 7.9315e-06, 'epoch': 3.69}
1022
+
1023
+ 05/30/2024 06:28:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5711, 'learning_rate': 7.8241e-06, 'epoch': 3.70}
1024
+
1025
+ 05/30/2024 06:29:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5851, 'learning_rate': 7.7173e-06, 'epoch': 3.71}
1026
+
1027
+ 05/30/2024 06:30:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5877, 'learning_rate': 7.6112e-06, 'epoch': 3.72}
1028
+
1029
+ 05/30/2024 06:31:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5841, 'learning_rate': 7.5056e-06, 'epoch': 3.73}
1030
+
1031
+ 05/30/2024 06:33:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6185, 'learning_rate': 7.4006e-06, 'epoch': 3.74}
1032
+
1033
+ 05/30/2024 06:34:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6278, 'learning_rate': 7.2963e-06, 'epoch': 3.75}
1034
+
1035
+ 05/30/2024 06:34:15 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2000
1036
+
1037
+ 05/30/2024 06:34:15 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2000/tokenizer_config.json
1038
+
1039
+ 05/30/2024 06:34:15 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2000/special_tokens_map.json
1040
+
1041
+ 05/30/2024 06:35:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6518, 'learning_rate': 7.1926e-06, 'epoch': 3.76}
1042
+
1043
+ 05/30/2024 06:36:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.5290, 'learning_rate': 7.0895e-06, 'epoch': 3.77}
1044
+
1045
+ 05/30/2024 06:37:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5540, 'learning_rate': 6.9870e-06, 'epoch': 3.78}
1046
+
1047
+ 05/30/2024 06:38:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.5859, 'learning_rate': 6.8851e-06, 'epoch': 3.79}
1048
+
1049
+ 05/30/2024 06:40:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5853, 'learning_rate': 6.7839e-06, 'epoch': 3.80}
1050
+
1051
+ 05/30/2024 06:41:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5972, 'learning_rate': 6.6833e-06, 'epoch': 3.81}
1052
+
1053
+ 05/30/2024 06:42:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6114, 'learning_rate': 6.5833e-06, 'epoch': 3.82}
1054
+
1055
+ 05/30/2024 06:43:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5638, 'learning_rate': 6.4840e-06, 'epoch': 3.83}
1056
+
1057
+ 05/30/2024 06:44:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6113, 'learning_rate': 6.3853e-06, 'epoch': 3.83}
1058
+
1059
+ 05/30/2024 06:45:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5559, 'learning_rate': 6.2872e-06, 'epoch': 3.84}
1060
+
1061
+ 05/30/2024 06:46:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6219, 'learning_rate': 6.1898e-06, 'epoch': 3.85}
1062
+
1063
+ 05/30/2024 06:47:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.5907, 'learning_rate': 6.0931e-06, 'epoch': 3.86}
1064
+
1065
+ 05/30/2024 06:48:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5563, 'learning_rate': 5.9970e-06, 'epoch': 3.87}
1066
+
1067
+ 05/30/2024 06:50:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6009, 'learning_rate': 5.9016e-06, 'epoch': 3.88}
1068
+
1069
+ 05/30/2024 06:51:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6581, 'learning_rate': 5.8069e-06, 'epoch': 3.89}
1070
+
1071
+ 05/30/2024 06:52:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.5945, 'learning_rate': 5.7128e-06, 'epoch': 3.90}
1072
+
1073
+ 05/30/2024 06:53:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5586, 'learning_rate': 5.6194e-06, 'epoch': 3.91}
1074
+
1075
+ 05/30/2024 06:54:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.5624, 'learning_rate': 5.5266e-06, 'epoch': 3.92}
1076
+
1077
+ 05/30/2024 06:55:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6261, 'learning_rate': 5.4345e-06, 'epoch': 3.93}
1078
+
1079
+ 05/30/2024 06:56:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6223, 'learning_rate': 5.3432e-06, 'epoch': 3.94}
1080
+
1081
+ 05/30/2024 06:56:44 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2100
1082
+
1083
+ 05/30/2024 06:56:44 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2100/tokenizer_config.json
1084
+
1085
+ 05/30/2024 06:56:44 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2100/special_tokens_map.json
1086
+
1087
+ 05/30/2024 06:57:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5724, 'learning_rate': 5.2524e-06, 'epoch': 3.95}
1088
+
1089
+ 05/30/2024 06:59:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5976, 'learning_rate': 5.1624e-06, 'epoch': 3.96}
1090
+
1091
+ 05/30/2024 07:00:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5715, 'learning_rate': 5.0731e-06, 'epoch': 3.97}
1092
+
1093
+ 05/30/2024 07:01:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6233, 'learning_rate': 4.9845e-06, 'epoch': 3.98}
1094
+
1095
+ 05/30/2024 07:02:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5740, 'learning_rate': 4.8965e-06, 'epoch': 3.98}
1096
+
1097
+ 05/30/2024 07:03:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5929, 'learning_rate': 4.8093e-06, 'epoch': 3.99}
1098
+
1099
+ 05/30/2024 07:04:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.5920, 'learning_rate': 4.7227e-06, 'epoch': 4.00}
1100
+
1101
+ 05/30/2024 07:05:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6445, 'learning_rate': 4.6369e-06, 'epoch': 4.01}
1102
+
1103
+ 05/30/2024 07:06:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5722, 'learning_rate': 4.5518e-06, 'epoch': 4.02}
1104
+
1105
+ 05/30/2024 07:08:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6088, 'learning_rate': 4.4673e-06, 'epoch': 4.03}
1106
+
1107
+ 05/30/2024 07:09:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5924, 'learning_rate': 4.3836e-06, 'epoch': 4.04}
1108
+
1109
+ 05/30/2024 07:10:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5758, 'learning_rate': 4.3006e-06, 'epoch': 4.05}
1110
+
1111
+ 05/30/2024 07:11:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5952, 'learning_rate': 4.2184e-06, 'epoch': 4.06}
1112
+
1113
+ 05/30/2024 07:12:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6040, 'learning_rate': 4.1368e-06, 'epoch': 4.07}
1114
+
1115
+ 05/30/2024 07:13:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5906, 'learning_rate': 4.0560e-06, 'epoch': 4.08}
1116
+
1117
+ 05/30/2024 07:14:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5407, 'learning_rate': 3.9759e-06, 'epoch': 4.09}
1118
+
1119
+ 05/30/2024 07:15:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.5633, 'learning_rate': 3.8965e-06, 'epoch': 4.10}
1120
+
1121
+ 05/30/2024 07:16:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5990, 'learning_rate': 3.8179e-06, 'epoch': 4.11}
1122
+
1123
+ 05/30/2024 07:18:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5879, 'learning_rate': 3.7400e-06, 'epoch': 4.12}
1124
+
1125
+ 05/30/2024 07:19:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5620, 'learning_rate': 3.6629e-06, 'epoch': 4.13}
1126
+
1127
+ 05/30/2024 07:19:15 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2200
1128
+
1129
+ 05/30/2024 07:19:15 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2200/tokenizer_config.json
1130
+
1131
+ 05/30/2024 07:19:15 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2200/special_tokens_map.json
1132
+
1133
+ 05/30/2024 07:20:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5675, 'learning_rate': 3.5864e-06, 'epoch': 4.14}
1134
+
1135
+ 05/30/2024 07:21:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5573, 'learning_rate': 3.5108e-06, 'epoch': 4.14}
1136
+
1137
+ 05/30/2024 07:22:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5788, 'learning_rate': 3.4358e-06, 'epoch': 4.15}
1138
+
1139
+ 05/30/2024 07:23:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5877, 'learning_rate': 3.3617e-06, 'epoch': 4.16}
1140
+
1141
+ 05/30/2024 07:24:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5661, 'learning_rate': 3.2882e-06, 'epoch': 4.17}
1142
+
1143
+ 05/30/2024 07:25:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6241, 'learning_rate': 3.2156e-06, 'epoch': 4.18}
1144
+
1145
+ 05/30/2024 07:27:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5932, 'learning_rate': 3.1436e-06, 'epoch': 4.19}
1146
+
1147
+ 05/30/2024 07:28:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6129, 'learning_rate': 3.0725e-06, 'epoch': 4.20}
1148
+
1149
+ 05/30/2024 07:29:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5467, 'learning_rate': 3.0021e-06, 'epoch': 4.21}
1150
+
1151
+ 05/30/2024 07:30:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6347, 'learning_rate': 2.9325e-06, 'epoch': 4.22}
1152
+
1153
+ 05/30/2024 07:31:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5657, 'learning_rate': 2.8636e-06, 'epoch': 4.23}
1154
+
1155
+ 05/30/2024 07:32:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5562, 'learning_rate': 2.7955e-06, 'epoch': 4.24}
1156
+
1157
+ 05/30/2024 07:33:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5954, 'learning_rate': 2.7282e-06, 'epoch': 4.25}
1158
+
1159
+ 05/30/2024 07:34:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6499, 'learning_rate': 2.6616e-06, 'epoch': 4.26}
1160
+
1161
+ 05/30/2024 07:36:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5835, 'learning_rate': 2.5959e-06, 'epoch': 4.27}
1162
+
1163
+ 05/30/2024 07:37:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5804, 'learning_rate': 2.5309e-06, 'epoch': 4.28}
1164
+
1165
+ 05/30/2024 07:38:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.5838, 'learning_rate': 2.4667e-06, 'epoch': 4.29}
1166
+
1167
+ 05/30/2024 07:39:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6163, 'learning_rate': 2.4032e-06, 'epoch': 4.29}
1168
+
1169
+ 05/30/2024 07:40:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5561, 'learning_rate': 2.3406e-06, 'epoch': 4.30}
1170
+
1171
+ 05/30/2024 07:41:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5709, 'learning_rate': 2.2787e-06, 'epoch': 4.31}
1172
+
1173
+ 05/30/2024 07:41:37 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2300
1174
+
1175
+ 05/30/2024 07:41:37 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2300/tokenizer_config.json
1176
+
1177
+ 05/30/2024 07:41:37 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2300/special_tokens_map.json
1178
+
1179
+ 05/30/2024 07:42:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5357, 'learning_rate': 2.2176e-06, 'epoch': 4.32}
1180
+
1181
+ 05/30/2024 07:43:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.5840, 'learning_rate': 2.1574e-06, 'epoch': 4.33}
1182
+
1183
+ 05/30/2024 07:44:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5967, 'learning_rate': 2.0979e-06, 'epoch': 4.34}
1184
+
1185
+ 05/30/2024 07:46:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5506, 'learning_rate': 2.0392e-06, 'epoch': 4.35}
1186
+
1187
+ 05/30/2024 07:47:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5686, 'learning_rate': 1.9813e-06, 'epoch': 4.36}
1188
+
1189
+ 05/30/2024 07:48:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5544, 'learning_rate': 1.9242e-06, 'epoch': 4.37}
1190
+
1191
+ 05/30/2024 07:49:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.5756, 'learning_rate': 1.8679e-06, 'epoch': 4.38}
1192
+
1193
+ 05/30/2024 07:50:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5522, 'learning_rate': 1.8124e-06, 'epoch': 4.39}
1194
+
1195
+ 05/30/2024 07:51:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5979, 'learning_rate': 1.7578e-06, 'epoch': 4.40}
1196
+
1197
+ 05/30/2024 07:52:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5762, 'learning_rate': 1.7039e-06, 'epoch': 4.41}
1198
+
1199
+ 05/30/2024 07:53:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6322, 'learning_rate': 1.6508e-06, 'epoch': 4.42}
1200
+
1201
+ 05/30/2024 07:55:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5814, 'learning_rate': 1.5986e-06, 'epoch': 4.43}
1202
+
1203
+ 05/30/2024 07:56:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6210, 'learning_rate': 1.5471e-06, 'epoch': 4.44}
1204
+
1205
+ 05/30/2024 07:57:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5462, 'learning_rate': 1.4965e-06, 'epoch': 4.44}
1206
+
1207
+ 05/30/2024 07:58:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5868, 'learning_rate': 1.4467e-06, 'epoch': 4.45}
1208
+
1209
+ 05/30/2024 07:59:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.5820, 'learning_rate': 1.3977e-06, 'epoch': 4.46}
1210
+
1211
+ 05/30/2024 08:00:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5764, 'learning_rate': 1.3495e-06, 'epoch': 4.47}
1212
+
1213
+ 05/30/2024 08:01:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5745, 'learning_rate': 1.3022e-06, 'epoch': 4.48}
1214
+
1215
+ 05/30/2024 08:03:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6206, 'learning_rate': 1.2557e-06, 'epoch': 4.49}
1216
+
1217
+ 05/30/2024 08:04:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5657, 'learning_rate': 1.2100e-06, 'epoch': 4.50}
1218
+
1219
+ 05/30/2024 08:04:12 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2400
1220
+
1221
+ 05/30/2024 08:04:12 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2400/tokenizer_config.json
1222
+
1223
+ 05/30/2024 08:04:12 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2400/special_tokens_map.json
1224
+
1225
+ 05/30/2024 08:05:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.5487, 'learning_rate': 1.1651e-06, 'epoch': 4.51}
1226
+
1227
+ 05/30/2024 08:06:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6923, 'learning_rate': 1.1210e-06, 'epoch': 4.52}
1228
+
1229
+ 05/30/2024 08:07:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5588, 'learning_rate': 1.0778e-06, 'epoch': 4.53}
1230
+
1231
+ 05/30/2024 08:08:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5588, 'learning_rate': 1.0354e-06, 'epoch': 4.54}
1232
+
1233
+ 05/30/2024 08:09:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5864, 'learning_rate': 9.9389e-07, 'epoch': 4.55}
1234
+
1235
+ 05/30/2024 08:10:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5896, 'learning_rate': 9.5317e-07, 'epoch': 4.56}
1236
+
1237
+ 05/30/2024 08:11:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6555, 'learning_rate': 9.1329e-07, 'epoch': 4.57}
1238
+
1239
+ 05/30/2024 08:13:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5814, 'learning_rate': 8.7424e-07, 'epoch': 4.58}
1240
+
1241
+ 05/30/2024 08:14:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5837, 'learning_rate': 8.3604e-07, 'epoch': 4.59}
1242
+
1243
+ 05/30/2024 08:15:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6351, 'learning_rate': 7.9867e-07, 'epoch': 4.59}
1244
+
1245
+ 05/30/2024 08:16:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6131, 'learning_rate': 7.6214e-07, 'epoch': 4.60}
1246
+
1247
+ 05/30/2024 08:17:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5549, 'learning_rate': 7.2645e-07, 'epoch': 4.61}
1248
+
1249
+ 05/30/2024 08:18:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5807, 'learning_rate': 6.9161e-07, 'epoch': 4.62}
1250
+
1251
+ 05/30/2024 08:19:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6375, 'learning_rate': 6.5761e-07, 'epoch': 4.63}
1252
+
1253
+ 05/30/2024 08:21:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5800, 'learning_rate': 6.2446e-07, 'epoch': 4.64}
1254
+
1255
+ 05/30/2024 08:22:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6019, 'learning_rate': 5.9216e-07, 'epoch': 4.65}
1256
+
1257
+ 05/30/2024 08:23:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5911, 'learning_rate': 5.6070e-07, 'epoch': 4.66}
1258
+
1259
+ 05/30/2024 08:24:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5959, 'learning_rate': 5.3009e-07, 'epoch': 4.67}
1260
+
1261
+ 05/30/2024 08:25:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5758, 'learning_rate': 5.0033e-07, 'epoch': 4.68}
1262
+
1263
+ 05/30/2024 08:26:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6281, 'learning_rate': 4.7143e-07, 'epoch': 4.69}
1264
+
1265
+ 05/30/2024 08:26:40 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2500
1266
+
1267
+ 05/30/2024 08:26:40 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2500/tokenizer_config.json
1268
+
1269
+ 05/30/2024 08:26:40 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2500/special_tokens_map.json
1270
+
1271
+ 05/30/2024 08:27:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5875, 'learning_rate': 4.4337e-07, 'epoch': 4.70}
1272
+
1273
+ 05/30/2024 08:28:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6487, 'learning_rate': 4.1617e-07, 'epoch': 4.71}
1274
+
1275
+ 05/30/2024 08:30:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5580, 'learning_rate': 3.8982e-07, 'epoch': 4.72}
1276
+
1277
+ 05/30/2024 08:31:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6207, 'learning_rate': 3.6433e-07, 'epoch': 4.73}
1278
+
1279
+ 05/30/2024 08:32:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5592, 'learning_rate': 3.3969e-07, 'epoch': 4.74}
1280
+
1281
+ 05/30/2024 08:33:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.5857, 'learning_rate': 3.1591e-07, 'epoch': 4.74}
1282
+
1283
+ 05/30/2024 08:34:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5805, 'learning_rate': 2.9299e-07, 'epoch': 4.75}
1284
+
1285
+ 05/30/2024 08:35:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5519, 'learning_rate': 2.7093e-07, 'epoch': 4.76}
1286
+
1287
+ 05/30/2024 08:36:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6442, 'learning_rate': 2.4972e-07, 'epoch': 4.77}
1288
+
1289
+ 05/30/2024 08:38:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5744, 'learning_rate': 2.2937e-07, 'epoch': 4.78}
1290
+
1291
+ 05/30/2024 08:39:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6113, 'learning_rate': 2.0989e-07, 'epoch': 4.79}
1292
+
1293
+ 05/30/2024 08:40:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6187, 'learning_rate': 1.9127e-07, 'epoch': 4.80}
1294
+
1295
+ 05/30/2024 08:41:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5540, 'learning_rate': 1.7351e-07, 'epoch': 4.81}
1296
+
1297
+ 05/30/2024 08:42:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5647, 'learning_rate': 1.5661e-07, 'epoch': 4.82}
1298
+
1299
+ 05/30/2024 08:43:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6173, 'learning_rate': 1.4057e-07, 'epoch': 4.83}
1300
+
1301
+ 05/30/2024 08:44:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.5928, 'learning_rate': 1.2540e-07, 'epoch': 4.84}
1302
+
1303
+ 05/30/2024 08:46:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5262, 'learning_rate': 1.1109e-07, 'epoch': 4.85}
1304
+
1305
+ 05/30/2024 08:47:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5449, 'learning_rate': 9.7646e-08, 'epoch': 4.86}
1306
+
1307
+ 05/30/2024 08:48:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5811, 'learning_rate': 8.5068e-08, 'epoch': 4.87}
1308
+
1309
+ 05/30/2024 08:49:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.5818, 'learning_rate': 7.3355e-08, 'epoch': 4.88}
1310
+
1311
+ 05/30/2024 08:49:17 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2600
1312
+
1313
+ 05/30/2024 08:49:17 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2600/tokenizer_config.json
1314
+
1315
+ 05/30/2024 08:49:17 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/checkpoint-2600/special_tokens_map.json
1316
+
1317
+ 05/30/2024 08:50:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6438, 'learning_rate': 6.2508e-08, 'epoch': 4.89}
1318
+
1319
+ 05/30/2024 08:51:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5808, 'learning_rate': 5.2528e-08, 'epoch': 4.89}
1320
+
1321
+ 05/30/2024 08:52:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5931, 'learning_rate': 4.3414e-08, 'epoch': 4.90}
1322
+
1323
+ 05/30/2024 08:53:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5510, 'learning_rate': 3.5167e-08, 'epoch': 4.91}
1324
+
1325
+ 05/30/2024 08:54:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5414, 'learning_rate': 2.7788e-08, 'epoch': 4.92}
1326
+
1327
+ 05/30/2024 08:56:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6081, 'learning_rate': 2.1276e-08, 'epoch': 4.93}
1328
+
1329
+ 05/30/2024 08:57:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6069, 'learning_rate': 1.5632e-08, 'epoch': 4.94}
1330
+
1331
+ 05/30/2024 08:58:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5897, 'learning_rate': 1.0856e-08, 'epoch': 4.95}
1332
+
1333
+ 05/30/2024 08:59:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.5580, 'learning_rate': 6.9479e-09, 'epoch': 4.96}
1334
+
1335
+ 05/30/2024 09:00:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5617, 'learning_rate': 3.9083e-09, 'epoch': 4.97}
1336
+
1337
+ 05/30/2024 09:01:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6366, 'learning_rate': 1.7370e-09, 'epoch': 4.98}
1338
+
1339
+ 05/30/2024 09:03:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5921, 'learning_rate': 4.3426e-10, 'epoch': 4.99}
1340
+
1341
+ 05/30/2024 09:04:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.5838, 'learning_rate': 0.0000e+00, 'epoch': 5.00}
1342
+
1343
+ 05/30/2024 09:04:11 - INFO - transformers.trainer -
1344
+
1345
+ Training completed. Do not forget to share your model on huggingface.co/models =)
1346
+
1347
+
1348
+
1349
+ 05/30/2024 09:04:11 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat
1350
+
1351
+ 05/30/2024 09:04:11 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/tokenizer_config.json
1352
+
1353
+ 05/30/2024 09:04:11 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat/special_tokens_map.json
1354
+
1355
+ 05/30/2024 09:04:11 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields:
1356
+ {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
1357
+
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.9976558837318334,
3
+ "total_flos": 2.0317707214423327e+18,
4
+ "train_loss": 0.623453339492626,
5
+ "train_runtime": 36076.8467,
6
+ "train_samples_per_second": 1.182,
7
+ "train_steps_per_second": 0.074
8
+ }
trainer_config.yaml ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ cutoff_len: 4096
2
+ dataset: LangGPT_community,LangGPT_alpaca,LangGPT_seed
3
+ dataset_dir: /datas/wangm/LLM4LangGPT
4
+ do_train: true
5
+ finetuning_type: lora
6
+ flash_attn: auto
7
+ fp16: true
8
+ gradient_accumulation_steps: 8
9
+ learning_rate: 5.0e-05
10
+ logging_steps: 5
11
+ lora_alpha: 16
12
+ lora_dropout: 0
13
+ lora_rank: 8
14
+ lora_target: q_proj,v_proj
15
+ lr_scheduler_type: cosine
16
+ max_grad_norm: 1.0
17
+ max_samples: 100000
18
+ model_name_or_path: Qwen/Qwen1.5-7B-Chat
19
+ num_train_epochs: 5.0
20
+ optim: adamw_torch
21
+ output_dir: /datas/wangm/LLM4LangGPT/output/Qwen1.5-7B-Chat
22
+ packing: false
23
+ per_device_train_batch_size: 2
24
+ report_to: none
25
+ save_steps: 100
26
+ stage: sft
27
+ template: qwen
28
+ warmup_steps: 0
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,3761 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.9976558837318334,
5
+ "eval_steps": 500,
6
+ "global_step": 2665,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009376465072667605,
13
+ "grad_norm": 1.043060064315796,
14
+ "learning_rate": 4.999956573574533e-05,
15
+ "loss": 1.2495,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.01875293014533521,
20
+ "grad_norm": 1.0880073308944702,
21
+ "learning_rate": 4.999826295806815e-05,
22
+ "loss": 1.0913,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.02812939521800281,
27
+ "grad_norm": 0.6108205914497375,
28
+ "learning_rate": 4.999609171222846e-05,
29
+ "loss": 0.9163,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.03750586029067042,
34
+ "grad_norm": 0.5320619344711304,
35
+ "learning_rate": 4.99930520736578e-05,
36
+ "loss": 0.9189,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.04688232536333802,
41
+ "grad_norm": 0.47798001766204834,
42
+ "learning_rate": 4.998914414795668e-05,
43
+ "loss": 0.8406,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.05625879043600562,
48
+ "grad_norm": 0.4477296769618988,
49
+ "learning_rate": 4.99843680708909e-05,
50
+ "loss": 0.7963,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.06563525550867323,
55
+ "grad_norm": 0.527661919593811,
56
+ "learning_rate": 4.997872400838682e-05,
57
+ "loss": 0.8229,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.07501172058134084,
62
+ "grad_norm": 0.4180678725242615,
63
+ "learning_rate": 4.997221215652562e-05,
64
+ "loss": 0.824,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.08438818565400844,
69
+ "grad_norm": 0.33111363649368286,
70
+ "learning_rate": 4.9964832741536444e-05,
71
+ "loss": 0.8236,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.09376465072667604,
76
+ "grad_norm": 0.29713910818099976,
77
+ "learning_rate": 4.9956586019788584e-05,
78
+ "loss": 0.7696,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.10314111579934365,
83
+ "grad_norm": 0.34906554222106934,
84
+ "learning_rate": 4.9947472277782584e-05,
85
+ "loss": 0.7585,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.11251758087201125,
90
+ "grad_norm": 0.447453111410141,
91
+ "learning_rate": 4.993749183214021e-05,
92
+ "loss": 0.7549,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.12189404594467886,
97
+ "grad_norm": 0.34558868408203125,
98
+ "learning_rate": 4.992664502959351e-05,
99
+ "loss": 0.7345,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.13127051101734646,
104
+ "grad_norm": 0.3259447515010834,
105
+ "learning_rate": 4.991493224697281e-05,
106
+ "loss": 0.7273,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.14064697609001406,
111
+ "grad_norm": 0.39191028475761414,
112
+ "learning_rate": 4.990235389119352e-05,
113
+ "loss": 0.7803,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.15002344116268168,
118
+ "grad_norm": 0.3894421458244324,
119
+ "learning_rate": 4.9888910399242065e-05,
120
+ "loss": 0.6957,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.15939990623534928,
125
+ "grad_norm": 0.40983864665031433,
126
+ "learning_rate": 4.987460223816067e-05,
127
+ "loss": 0.7076,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.16877637130801687,
132
+ "grad_norm": 0.4191415011882782,
133
+ "learning_rate": 4.985942990503119e-05,
134
+ "loss": 0.7231,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.1781528363806845,
139
+ "grad_norm": 0.41286033391952515,
140
+ "learning_rate": 4.984339392695777e-05,
141
+ "loss": 0.6879,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.1875293014533521,
146
+ "grad_norm": 0.40984493494033813,
147
+ "learning_rate": 4.9826494861048576e-05,
148
+ "loss": 0.665,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.19690576652601968,
153
+ "grad_norm": 0.45545095205307007,
154
+ "learning_rate": 4.980873329439644e-05,
155
+ "loss": 0.756,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 0.2062822315986873,
160
+ "grad_norm": 0.3807056248188019,
161
+ "learning_rate": 4.979010984405842e-05,
162
+ "loss": 0.6963,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 0.2156586966713549,
167
+ "grad_norm": 0.4047029912471771,
168
+ "learning_rate": 4.9770625157034436e-05,
169
+ "loss": 0.731,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 0.2250351617440225,
174
+ "grad_norm": 0.4204094409942627,
175
+ "learning_rate": 4.975027991024473e-05,
176
+ "loss": 0.7397,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 0.23441162681669012,
181
+ "grad_norm": 0.4436323344707489,
182
+ "learning_rate": 4.972907481050637e-05,
183
+ "loss": 0.7006,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 0.2437880918893577,
188
+ "grad_norm": 0.5543025732040405,
189
+ "learning_rate": 4.970701059450872e-05,
190
+ "loss": 0.7231,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 0.25316455696202533,
195
+ "grad_norm": 0.3950710594654083,
196
+ "learning_rate": 4.968408802878778e-05,
197
+ "loss": 0.7323,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 0.26254102203469293,
202
+ "grad_norm": 0.4335172772407532,
203
+ "learning_rate": 4.9660307909699645e-05,
204
+ "loss": 0.6721,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 0.2719174871073605,
209
+ "grad_norm": 0.37986621260643005,
210
+ "learning_rate": 4.963567106339276e-05,
211
+ "loss": 0.6722,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 0.2812939521800281,
216
+ "grad_norm": 0.49829936027526855,
217
+ "learning_rate": 4.961017834577927e-05,
218
+ "loss": 0.7208,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 0.2906704172526957,
223
+ "grad_norm": 0.466081827878952,
224
+ "learning_rate": 4.958383064250525e-05,
225
+ "loss": 0.6621,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 0.30004688232536336,
230
+ "grad_norm": 0.5066991448402405,
231
+ "learning_rate": 4.955662886891995e-05,
232
+ "loss": 0.7114,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 0.30942334739803096,
237
+ "grad_norm": 0.43918004631996155,
238
+ "learning_rate": 4.952857397004401e-05,
239
+ "loss": 0.7235,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 0.31879981247069855,
244
+ "grad_norm": 0.4280238747596741,
245
+ "learning_rate": 4.949966692053663e-05,
246
+ "loss": 0.6993,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 0.32817627754336615,
251
+ "grad_norm": 0.36493420600891113,
252
+ "learning_rate": 4.946990872466164e-05,
253
+ "loss": 0.7186,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 0.33755274261603374,
258
+ "grad_norm": 0.4803766906261444,
259
+ "learning_rate": 4.943930041625272e-05,
260
+ "loss": 0.6867,
261
+ "step": 180
262
+ },
263
+ {
264
+ "epoch": 0.34692920768870134,
265
+ "grad_norm": 0.43526196479797363,
266
+ "learning_rate": 4.940784305867741e-05,
267
+ "loss": 0.6907,
268
+ "step": 185
269
+ },
270
+ {
271
+ "epoch": 0.356305672761369,
272
+ "grad_norm": 0.4661521315574646,
273
+ "learning_rate": 4.937553774480018e-05,
274
+ "loss": 0.6693,
275
+ "step": 190
276
+ },
277
+ {
278
+ "epoch": 0.3656821378340366,
279
+ "grad_norm": 0.5094730257987976,
280
+ "learning_rate": 4.934238559694448e-05,
281
+ "loss": 0.7322,
282
+ "step": 195
283
+ },
284
+ {
285
+ "epoch": 0.3750586029067042,
286
+ "grad_norm": 0.47885701060295105,
287
+ "learning_rate": 4.9308387766853725e-05,
288
+ "loss": 0.7351,
289
+ "step": 200
290
+ },
291
+ {
292
+ "epoch": 0.38443506797937177,
293
+ "grad_norm": 0.475460022687912,
294
+ "learning_rate": 4.92735454356513e-05,
295
+ "loss": 0.6996,
296
+ "step": 205
297
+ },
298
+ {
299
+ "epoch": 0.39381153305203936,
300
+ "grad_norm": 0.46198564767837524,
301
+ "learning_rate": 4.9237859813799535e-05,
302
+ "loss": 0.7124,
303
+ "step": 210
304
+ },
305
+ {
306
+ "epoch": 0.40318799812470696,
307
+ "grad_norm": 0.5559020042419434,
308
+ "learning_rate": 4.9201332141057623e-05,
309
+ "loss": 0.6734,
310
+ "step": 215
311
+ },
312
+ {
313
+ "epoch": 0.4125644631973746,
314
+ "grad_norm": 0.5716303586959839,
315
+ "learning_rate": 4.9163963686438575e-05,
316
+ "loss": 0.6914,
317
+ "step": 220
318
+ },
319
+ {
320
+ "epoch": 0.4219409282700422,
321
+ "grad_norm": 0.4577886760234833,
322
+ "learning_rate": 4.912575574816511e-05,
323
+ "loss": 0.6584,
324
+ "step": 225
325
+ },
326
+ {
327
+ "epoch": 0.4313173933427098,
328
+ "grad_norm": 0.565101683139801,
329
+ "learning_rate": 4.908670965362457e-05,
330
+ "loss": 0.6326,
331
+ "step": 230
332
+ },
333
+ {
334
+ "epoch": 0.4406938584153774,
335
+ "grad_norm": 0.4204961657524109,
336
+ "learning_rate": 4.9046826759322825e-05,
337
+ "loss": 0.6931,
338
+ "step": 235
339
+ },
340
+ {
341
+ "epoch": 0.450070323488045,
342
+ "grad_norm": 0.6228139996528625,
343
+ "learning_rate": 4.9006108450837095e-05,
344
+ "loss": 0.6769,
345
+ "step": 240
346
+ },
347
+ {
348
+ "epoch": 0.45944678856071264,
349
+ "grad_norm": 0.4805678725242615,
350
+ "learning_rate": 4.8964556142767845e-05,
351
+ "loss": 0.6957,
352
+ "step": 245
353
+ },
354
+ {
355
+ "epoch": 0.46882325363338023,
356
+ "grad_norm": 0.5143615007400513,
357
+ "learning_rate": 4.892217127868965e-05,
358
+ "loss": 0.6949,
359
+ "step": 250
360
+ },
361
+ {
362
+ "epoch": 0.4781997187060478,
363
+ "grad_norm": 0.5050625205039978,
364
+ "learning_rate": 4.8878955331101026e-05,
365
+ "loss": 0.7084,
366
+ "step": 255
367
+ },
368
+ {
369
+ "epoch": 0.4875761837787154,
370
+ "grad_norm": 0.5915749669075012,
371
+ "learning_rate": 4.8834909801373264e-05,
372
+ "loss": 0.6439,
373
+ "step": 260
374
+ },
375
+ {
376
+ "epoch": 0.496952648851383,
377
+ "grad_norm": 0.5936545133590698,
378
+ "learning_rate": 4.879003621969831e-05,
379
+ "loss": 0.654,
380
+ "step": 265
381
+ },
382
+ {
383
+ "epoch": 0.5063291139240507,
384
+ "grad_norm": 0.575564980506897,
385
+ "learning_rate": 4.874433614503554e-05,
386
+ "loss": 0.6513,
387
+ "step": 270
388
+ },
389
+ {
390
+ "epoch": 0.5157055789967182,
391
+ "grad_norm": 0.4369766414165497,
392
+ "learning_rate": 4.869781116505768e-05,
393
+ "loss": 0.6406,
394
+ "step": 275
395
+ },
396
+ {
397
+ "epoch": 0.5250820440693859,
398
+ "grad_norm": 0.5553178787231445,
399
+ "learning_rate": 4.8650462896095597e-05,
400
+ "loss": 0.6761,
401
+ "step": 280
402
+ },
403
+ {
404
+ "epoch": 0.5344585091420534,
405
+ "grad_norm": 0.4776481091976166,
406
+ "learning_rate": 4.860229298308213e-05,
407
+ "loss": 0.644,
408
+ "step": 285
409
+ },
410
+ {
411
+ "epoch": 0.543834974214721,
412
+ "grad_norm": 0.5263465046882629,
413
+ "learning_rate": 4.8553303099495e-05,
414
+ "loss": 0.6619,
415
+ "step": 290
416
+ },
417
+ {
418
+ "epoch": 0.5532114392873887,
419
+ "grad_norm": 0.5093105435371399,
420
+ "learning_rate": 4.8503494947298634e-05,
421
+ "loss": 0.6855,
422
+ "step": 295
423
+ },
424
+ {
425
+ "epoch": 0.5625879043600562,
426
+ "grad_norm": 0.504751980304718,
427
+ "learning_rate": 4.845287025688503e-05,
428
+ "loss": 0.6716,
429
+ "step": 300
430
+ },
431
+ {
432
+ "epoch": 0.5719643694327239,
433
+ "grad_norm": 0.48812317848205566,
434
+ "learning_rate": 4.8401430787013666e-05,
435
+ "loss": 0.6784,
436
+ "step": 305
437
+ },
438
+ {
439
+ "epoch": 0.5813408345053914,
440
+ "grad_norm": 0.4794219136238098,
441
+ "learning_rate": 4.8349178324750387e-05,
442
+ "loss": 0.6587,
443
+ "step": 310
444
+ },
445
+ {
446
+ "epoch": 0.5907172995780591,
447
+ "grad_norm": 0.5530505180358887,
448
+ "learning_rate": 4.8296114685405324e-05,
449
+ "loss": 0.6411,
450
+ "step": 315
451
+ },
452
+ {
453
+ "epoch": 0.6000937646507267,
454
+ "grad_norm": 0.5403686165809631,
455
+ "learning_rate": 4.824224171246981e-05,
456
+ "loss": 0.7191,
457
+ "step": 320
458
+ },
459
+ {
460
+ "epoch": 0.6094702297233943,
461
+ "grad_norm": 0.5672193765640259,
462
+ "learning_rate": 4.8187561277552374e-05,
463
+ "loss": 0.6679,
464
+ "step": 325
465
+ },
466
+ {
467
+ "epoch": 0.6188466947960619,
468
+ "grad_norm": 0.5467439889907837,
469
+ "learning_rate": 4.813207528031366e-05,
470
+ "loss": 0.627,
471
+ "step": 330
472
+ },
473
+ {
474
+ "epoch": 0.6282231598687295,
475
+ "grad_norm": 0.5209377408027649,
476
+ "learning_rate": 4.807578564840051e-05,
477
+ "loss": 0.7084,
478
+ "step": 335
479
+ },
480
+ {
481
+ "epoch": 0.6375996249413971,
482
+ "grad_norm": 0.5048089623451233,
483
+ "learning_rate": 4.801869433737891e-05,
484
+ "loss": 0.6555,
485
+ "step": 340
486
+ },
487
+ {
488
+ "epoch": 0.6469760900140648,
489
+ "grad_norm": 0.5744394659996033,
490
+ "learning_rate": 4.796080333066613e-05,
491
+ "loss": 0.6865,
492
+ "step": 345
493
+ },
494
+ {
495
+ "epoch": 0.6563525550867323,
496
+ "grad_norm": 0.5384623408317566,
497
+ "learning_rate": 4.790211463946174e-05,
498
+ "loss": 0.6968,
499
+ "step": 350
500
+ },
501
+ {
502
+ "epoch": 0.6657290201593999,
503
+ "grad_norm": 0.591351330280304,
504
+ "learning_rate": 4.784263030267781e-05,
505
+ "loss": 0.637,
506
+ "step": 355
507
+ },
508
+ {
509
+ "epoch": 0.6751054852320675,
510
+ "grad_norm": 0.5314144492149353,
511
+ "learning_rate": 4.7782352386868035e-05,
512
+ "loss": 0.6898,
513
+ "step": 360
514
+ },
515
+ {
516
+ "epoch": 0.6844819503047351,
517
+ "grad_norm": 0.5192554593086243,
518
+ "learning_rate": 4.7721282986155945e-05,
519
+ "loss": 0.6258,
520
+ "step": 365
521
+ },
522
+ {
523
+ "epoch": 0.6938584153774027,
524
+ "grad_norm": 0.625133216381073,
525
+ "learning_rate": 4.7659424222162165e-05,
526
+ "loss": 0.6418,
527
+ "step": 370
528
+ },
529
+ {
530
+ "epoch": 0.7032348804500703,
531
+ "grad_norm": 0.5590410232543945,
532
+ "learning_rate": 4.7596778243930694e-05,
533
+ "loss": 0.6957,
534
+ "step": 375
535
+ },
536
+ {
537
+ "epoch": 0.712611345522738,
538
+ "grad_norm": 0.55343097448349,
539
+ "learning_rate": 4.7533347227854265e-05,
540
+ "loss": 0.6813,
541
+ "step": 380
542
+ },
543
+ {
544
+ "epoch": 0.7219878105954055,
545
+ "grad_norm": 0.6247820258140564,
546
+ "learning_rate": 4.7469133377598695e-05,
547
+ "loss": 0.6565,
548
+ "step": 385
549
+ },
550
+ {
551
+ "epoch": 0.7313642756680732,
552
+ "grad_norm": 0.6145781874656677,
553
+ "learning_rate": 4.740413892402639e-05,
554
+ "loss": 0.6557,
555
+ "step": 390
556
+ },
557
+ {
558
+ "epoch": 0.7407407407407407,
559
+ "grad_norm": 0.6102336645126343,
560
+ "learning_rate": 4.7338366125118775e-05,
561
+ "loss": 0.6715,
562
+ "step": 395
563
+ },
564
+ {
565
+ "epoch": 0.7501172058134083,
566
+ "grad_norm": 0.6142327189445496,
567
+ "learning_rate": 4.727181726589789e-05,
568
+ "loss": 0.6929,
569
+ "step": 400
570
+ },
571
+ {
572
+ "epoch": 0.759493670886076,
573
+ "grad_norm": 0.6012890934944153,
574
+ "learning_rate": 4.7204494658346996e-05,
575
+ "loss": 0.6474,
576
+ "step": 405
577
+ },
578
+ {
579
+ "epoch": 0.7688701359587435,
580
+ "grad_norm": 0.588411808013916,
581
+ "learning_rate": 4.713640064133025e-05,
582
+ "loss": 0.6519,
583
+ "step": 410
584
+ },
585
+ {
586
+ "epoch": 0.7782466010314112,
587
+ "grad_norm": 0.5341905951499939,
588
+ "learning_rate": 4.706753758051145e-05,
589
+ "loss": 0.66,
590
+ "step": 415
591
+ },
592
+ {
593
+ "epoch": 0.7876230661040787,
594
+ "grad_norm": 0.5620007514953613,
595
+ "learning_rate": 4.699790786827188e-05,
596
+ "loss": 0.7041,
597
+ "step": 420
598
+ },
599
+ {
600
+ "epoch": 0.7969995311767464,
601
+ "grad_norm": 0.6584540605545044,
602
+ "learning_rate": 4.6927513923627124e-05,
603
+ "loss": 0.6676,
604
+ "step": 425
605
+ },
606
+ {
607
+ "epoch": 0.8063759962494139,
608
+ "grad_norm": 0.5691075325012207,
609
+ "learning_rate": 4.68563581921431e-05,
610
+ "loss": 0.6382,
611
+ "step": 430
612
+ },
613
+ {
614
+ "epoch": 0.8157524613220816,
615
+ "grad_norm": 0.6462568640708923,
616
+ "learning_rate": 4.6784443145851074e-05,
617
+ "loss": 0.5761,
618
+ "step": 435
619
+ },
620
+ {
621
+ "epoch": 0.8251289263947492,
622
+ "grad_norm": 0.5838071703910828,
623
+ "learning_rate": 4.671177128316176e-05,
624
+ "loss": 0.6149,
625
+ "step": 440
626
+ },
627
+ {
628
+ "epoch": 0.8345053914674168,
629
+ "grad_norm": 0.5983990430831909,
630
+ "learning_rate": 4.663834512877853e-05,
631
+ "loss": 0.661,
632
+ "step": 445
633
+ },
634
+ {
635
+ "epoch": 0.8438818565400844,
636
+ "grad_norm": 0.6623389720916748,
637
+ "learning_rate": 4.6564167233609736e-05,
638
+ "loss": 0.6477,
639
+ "step": 450
640
+ },
641
+ {
642
+ "epoch": 0.853258321612752,
643
+ "grad_norm": 0.5716333389282227,
644
+ "learning_rate": 4.648924017468003e-05,
645
+ "loss": 0.6267,
646
+ "step": 455
647
+ },
648
+ {
649
+ "epoch": 0.8626347866854196,
650
+ "grad_norm": 0.6834291815757751,
651
+ "learning_rate": 4.6413566555040896e-05,
652
+ "loss": 0.6776,
653
+ "step": 460
654
+ },
655
+ {
656
+ "epoch": 0.8720112517580872,
657
+ "grad_norm": 0.6510602235794067,
658
+ "learning_rate": 4.633714900368018e-05,
659
+ "loss": 0.645,
660
+ "step": 465
661
+ },
662
+ {
663
+ "epoch": 0.8813877168307548,
664
+ "grad_norm": 0.5720119476318359,
665
+ "learning_rate": 4.625999017543075e-05,
666
+ "loss": 0.6486,
667
+ "step": 470
668
+ },
669
+ {
670
+ "epoch": 0.8907641819034224,
671
+ "grad_norm": 0.6245366930961609,
672
+ "learning_rate": 4.618209275087829e-05,
673
+ "loss": 0.6784,
674
+ "step": 475
675
+ },
676
+ {
677
+ "epoch": 0.90014064697609,
678
+ "grad_norm": 0.6153048276901245,
679
+ "learning_rate": 4.610345943626817e-05,
680
+ "loss": 0.6595,
681
+ "step": 480
682
+ },
683
+ {
684
+ "epoch": 0.9095171120487576,
685
+ "grad_norm": 0.573347270488739,
686
+ "learning_rate": 4.602409296341141e-05,
687
+ "loss": 0.6403,
688
+ "step": 485
689
+ },
690
+ {
691
+ "epoch": 0.9188935771214253,
692
+ "grad_norm": 0.5834039449691772,
693
+ "learning_rate": 4.5943996089589775e-05,
694
+ "loss": 0.6334,
695
+ "step": 490
696
+ },
697
+ {
698
+ "epoch": 0.9282700421940928,
699
+ "grad_norm": 0.6009634137153625,
700
+ "learning_rate": 4.586317159746001e-05,
701
+ "loss": 0.7385,
702
+ "step": 495
703
+ },
704
+ {
705
+ "epoch": 0.9376465072667605,
706
+ "grad_norm": 0.6226871013641357,
707
+ "learning_rate": 4.5781622294957136e-05,
708
+ "loss": 0.6463,
709
+ "step": 500
710
+ },
711
+ {
712
+ "epoch": 0.947022972339428,
713
+ "grad_norm": 0.5742005109786987,
714
+ "learning_rate": 4.569935101519692e-05,
715
+ "loss": 0.6693,
716
+ "step": 505
717
+ },
718
+ {
719
+ "epoch": 0.9563994374120957,
720
+ "grad_norm": 0.5679554343223572,
721
+ "learning_rate": 4.561636061637745e-05,
722
+ "loss": 0.7034,
723
+ "step": 510
724
+ },
725
+ {
726
+ "epoch": 0.9657759024847632,
727
+ "grad_norm": 0.5975098013877869,
728
+ "learning_rate": 4.553265398167981e-05,
729
+ "loss": 0.652,
730
+ "step": 515
731
+ },
732
+ {
733
+ "epoch": 0.9751523675574308,
734
+ "grad_norm": 0.5988393425941467,
735
+ "learning_rate": 4.5448234019167945e-05,
736
+ "loss": 0.6399,
737
+ "step": 520
738
+ },
739
+ {
740
+ "epoch": 0.9845288326300985,
741
+ "grad_norm": 0.6314676403999329,
742
+ "learning_rate": 4.536310366168763e-05,
743
+ "loss": 0.6426,
744
+ "step": 525
745
+ },
746
+ {
747
+ "epoch": 0.993905297702766,
748
+ "grad_norm": 0.5880908370018005,
749
+ "learning_rate": 4.5277265866764565e-05,
750
+ "loss": 0.66,
751
+ "step": 530
752
+ },
753
+ {
754
+ "epoch": 1.0032817627754336,
755
+ "grad_norm": 0.6495065093040466,
756
+ "learning_rate": 4.519072361650163e-05,
757
+ "loss": 0.6243,
758
+ "step": 535
759
+ },
760
+ {
761
+ "epoch": 1.0126582278481013,
762
+ "grad_norm": 0.661907970905304,
763
+ "learning_rate": 4.5103479917475286e-05,
764
+ "loss": 0.6001,
765
+ "step": 540
766
+ },
767
+ {
768
+ "epoch": 1.0220346929207689,
769
+ "grad_norm": 0.7230183482170105,
770
+ "learning_rate": 4.501553780063113e-05,
771
+ "loss": 0.6071,
772
+ "step": 545
773
+ },
774
+ {
775
+ "epoch": 1.0314111579934364,
776
+ "grad_norm": 0.5441235303878784,
777
+ "learning_rate": 4.4926900321178595e-05,
778
+ "loss": 0.6617,
779
+ "step": 550
780
+ },
781
+ {
782
+ "epoch": 1.0407876230661042,
783
+ "grad_norm": 0.6352370381355286,
784
+ "learning_rate": 4.483757055848479e-05,
785
+ "loss": 0.6291,
786
+ "step": 555
787
+ },
788
+ {
789
+ "epoch": 1.0501640881387717,
790
+ "grad_norm": 0.6081958413124084,
791
+ "learning_rate": 4.4747551615967534e-05,
792
+ "loss": 0.6011,
793
+ "step": 560
794
+ },
795
+ {
796
+ "epoch": 1.0595405532114393,
797
+ "grad_norm": 0.662145733833313,
798
+ "learning_rate": 4.4656846620987557e-05,
799
+ "loss": 0.6631,
800
+ "step": 565
801
+ },
802
+ {
803
+ "epoch": 1.0689170182841068,
804
+ "grad_norm": 0.6905146241188049,
805
+ "learning_rate": 4.4565458724739825e-05,
806
+ "loss": 0.6544,
807
+ "step": 570
808
+ },
809
+ {
810
+ "epoch": 1.0782934833567746,
811
+ "grad_norm": 0.6696512699127197,
812
+ "learning_rate": 4.447339110214405e-05,
813
+ "loss": 0.6332,
814
+ "step": 575
815
+ },
816
+ {
817
+ "epoch": 1.087669948429442,
818
+ "grad_norm": 0.6640881896018982,
819
+ "learning_rate": 4.438064695173446e-05,
820
+ "loss": 0.6426,
821
+ "step": 580
822
+ },
823
+ {
824
+ "epoch": 1.0970464135021096,
825
+ "grad_norm": 0.7038636803627014,
826
+ "learning_rate": 4.428722949554857e-05,
827
+ "loss": 0.6362,
828
+ "step": 585
829
+ },
830
+ {
831
+ "epoch": 1.1064228785747774,
832
+ "grad_norm": 0.6065195202827454,
833
+ "learning_rate": 4.419314197901537e-05,
834
+ "loss": 0.6136,
835
+ "step": 590
836
+ },
837
+ {
838
+ "epoch": 1.115799343647445,
839
+ "grad_norm": 0.6090584397315979,
840
+ "learning_rate": 4.4098387670842466e-05,
841
+ "loss": 0.636,
842
+ "step": 595
843
+ },
844
+ {
845
+ "epoch": 1.1251758087201125,
846
+ "grad_norm": 0.6664246320724487,
847
+ "learning_rate": 4.400296986290258e-05,
848
+ "loss": 0.6253,
849
+ "step": 600
850
+ },
851
+ {
852
+ "epoch": 1.1345522737927802,
853
+ "grad_norm": 0.7402456998825073,
854
+ "learning_rate": 4.390689187011917e-05,
855
+ "loss": 0.6351,
856
+ "step": 605
857
+ },
858
+ {
859
+ "epoch": 1.1439287388654478,
860
+ "grad_norm": 0.6655504107475281,
861
+ "learning_rate": 4.3810157030351276e-05,
862
+ "loss": 0.5974,
863
+ "step": 610
864
+ },
865
+ {
866
+ "epoch": 1.1533052039381153,
867
+ "grad_norm": 0.6735255122184753,
868
+ "learning_rate": 4.371276870427753e-05,
869
+ "loss": 0.6023,
870
+ "step": 615
871
+ },
872
+ {
873
+ "epoch": 1.1626816690107828,
874
+ "grad_norm": 0.6369088888168335,
875
+ "learning_rate": 4.3614730275279457e-05,
876
+ "loss": 0.6096,
877
+ "step": 620
878
+ },
879
+ {
880
+ "epoch": 1.1720581340834506,
881
+ "grad_norm": 0.7166373133659363,
882
+ "learning_rate": 4.351604514932387e-05,
883
+ "loss": 0.6156,
884
+ "step": 625
885
+ },
886
+ {
887
+ "epoch": 1.1814345991561181,
888
+ "grad_norm": 0.6789242029190063,
889
+ "learning_rate": 4.341671675484459e-05,
890
+ "loss": 0.6406,
891
+ "step": 630
892
+ },
893
+ {
894
+ "epoch": 1.1908110642287857,
895
+ "grad_norm": 0.5939568877220154,
896
+ "learning_rate": 4.331674854262331e-05,
897
+ "loss": 0.6224,
898
+ "step": 635
899
+ },
900
+ {
901
+ "epoch": 1.2001875293014534,
902
+ "grad_norm": 0.6717362403869629,
903
+ "learning_rate": 4.321614398566972e-05,
904
+ "loss": 0.6188,
905
+ "step": 640
906
+ },
907
+ {
908
+ "epoch": 1.209563994374121,
909
+ "grad_norm": 0.668659508228302,
910
+ "learning_rate": 4.3114906579100853e-05,
911
+ "loss": 0.6088,
912
+ "step": 645
913
+ },
914
+ {
915
+ "epoch": 1.2189404594467885,
916
+ "grad_norm": 0.6963931322097778,
917
+ "learning_rate": 4.301303984001967e-05,
918
+ "loss": 0.657,
919
+ "step": 650
920
+ },
921
+ {
922
+ "epoch": 1.228316924519456,
923
+ "grad_norm": 0.7464931607246399,
924
+ "learning_rate": 4.291054730739286e-05,
925
+ "loss": 0.6417,
926
+ "step": 655
927
+ },
928
+ {
929
+ "epoch": 1.2376933895921238,
930
+ "grad_norm": 0.6999815702438354,
931
+ "learning_rate": 4.2807432541927865e-05,
932
+ "loss": 0.6402,
933
+ "step": 660
934
+ },
935
+ {
936
+ "epoch": 1.2470698546647914,
937
+ "grad_norm": 0.7735899686813354,
938
+ "learning_rate": 4.2703699125949245e-05,
939
+ "loss": 0.6393,
940
+ "step": 665
941
+ },
942
+ {
943
+ "epoch": 1.256446319737459,
944
+ "grad_norm": 0.7408654093742371,
945
+ "learning_rate": 4.259935066327415e-05,
946
+ "loss": 0.7175,
947
+ "step": 670
948
+ },
949
+ {
950
+ "epoch": 1.2658227848101267,
951
+ "grad_norm": 0.5848163962364197,
952
+ "learning_rate": 4.2494390779087187e-05,
953
+ "loss": 0.68,
954
+ "step": 675
955
+ },
956
+ {
957
+ "epoch": 1.2751992498827942,
958
+ "grad_norm": 0.6354319453239441,
959
+ "learning_rate": 4.238882311981441e-05,
960
+ "loss": 0.5966,
961
+ "step": 680
962
+ },
963
+ {
964
+ "epoch": 1.2845757149554617,
965
+ "grad_norm": 0.6874629259109497,
966
+ "learning_rate": 4.228265135299669e-05,
967
+ "loss": 0.6432,
968
+ "step": 685
969
+ },
970
+ {
971
+ "epoch": 1.2939521800281293,
972
+ "grad_norm": 0.6156244874000549,
973
+ "learning_rate": 4.2175879167162304e-05,
974
+ "loss": 0.6688,
975
+ "step": 690
976
+ },
977
+ {
978
+ "epoch": 1.303328645100797,
979
+ "grad_norm": 0.6476886868476868,
980
+ "learning_rate": 4.206851027169871e-05,
981
+ "loss": 0.6407,
982
+ "step": 695
983
+ },
984
+ {
985
+ "epoch": 1.3127051101734646,
986
+ "grad_norm": 0.6186336874961853,
987
+ "learning_rate": 4.196054839672382e-05,
988
+ "loss": 0.6084,
989
+ "step": 700
990
+ },
991
+ {
992
+ "epoch": 1.3220815752461323,
993
+ "grad_norm": 0.566964328289032,
994
+ "learning_rate": 4.1851997292956255e-05,
995
+ "loss": 0.6407,
996
+ "step": 705
997
+ },
998
+ {
999
+ "epoch": 1.3314580403187999,
1000
+ "grad_norm": 0.6484958529472351,
1001
+ "learning_rate": 4.174286073158516e-05,
1002
+ "loss": 0.643,
1003
+ "step": 710
1004
+ },
1005
+ {
1006
+ "epoch": 1.3408345053914674,
1007
+ "grad_norm": 0.6172962784767151,
1008
+ "learning_rate": 4.163314250413913e-05,
1009
+ "loss": 0.5899,
1010
+ "step": 715
1011
+ },
1012
+ {
1013
+ "epoch": 1.350210970464135,
1014
+ "grad_norm": 0.6747507452964783,
1015
+ "learning_rate": 4.152284642235452e-05,
1016
+ "loss": 0.6299,
1017
+ "step": 720
1018
+ },
1019
+ {
1020
+ "epoch": 1.3595874355368025,
1021
+ "grad_norm": 0.7099136710166931,
1022
+ "learning_rate": 4.141197631804298e-05,
1023
+ "loss": 0.6462,
1024
+ "step": 725
1025
+ },
1026
+ {
1027
+ "epoch": 1.3689639006094703,
1028
+ "grad_norm": 0.6501842141151428,
1029
+ "learning_rate": 4.1300536042958354e-05,
1030
+ "loss": 0.6558,
1031
+ "step": 730
1032
+ },
1033
+ {
1034
+ "epoch": 1.3783403656821378,
1035
+ "grad_norm": 0.6962847113609314,
1036
+ "learning_rate": 4.118852946866291e-05,
1037
+ "loss": 0.6316,
1038
+ "step": 735
1039
+ },
1040
+ {
1041
+ "epoch": 1.3877168307548056,
1042
+ "grad_norm": 0.7128638029098511,
1043
+ "learning_rate": 4.107596048639274e-05,
1044
+ "loss": 0.6143,
1045
+ "step": 740
1046
+ },
1047
+ {
1048
+ "epoch": 1.397093295827473,
1049
+ "grad_norm": 0.6980453729629517,
1050
+ "learning_rate": 4.0962833006922675e-05,
1051
+ "loss": 0.6358,
1052
+ "step": 745
1053
+ },
1054
+ {
1055
+ "epoch": 1.4064697609001406,
1056
+ "grad_norm": 0.6058886051177979,
1057
+ "learning_rate": 4.0849150960430356e-05,
1058
+ "loss": 0.6276,
1059
+ "step": 750
1060
+ },
1061
+ {
1062
+ "epoch": 1.4158462259728082,
1063
+ "grad_norm": 0.6673750281333923,
1064
+ "learning_rate": 4.0734918296359716e-05,
1065
+ "loss": 0.6238,
1066
+ "step": 755
1067
+ },
1068
+ {
1069
+ "epoch": 1.4252226910454757,
1070
+ "grad_norm": 0.6338385343551636,
1071
+ "learning_rate": 4.0620138983283785e-05,
1072
+ "loss": 0.6775,
1073
+ "step": 760
1074
+ },
1075
+ {
1076
+ "epoch": 1.4345991561181435,
1077
+ "grad_norm": 0.6448456645011902,
1078
+ "learning_rate": 4.050481700876677e-05,
1079
+ "loss": 0.633,
1080
+ "step": 765
1081
+ },
1082
+ {
1083
+ "epoch": 1.443975621190811,
1084
+ "grad_norm": 0.7474460005760193,
1085
+ "learning_rate": 4.038895637922559e-05,
1086
+ "loss": 0.6307,
1087
+ "step": 770
1088
+ },
1089
+ {
1090
+ "epoch": 1.4533520862634788,
1091
+ "grad_norm": 0.7345675230026245,
1092
+ "learning_rate": 4.027256111979063e-05,
1093
+ "loss": 0.5959,
1094
+ "step": 775
1095
+ },
1096
+ {
1097
+ "epoch": 1.4627285513361463,
1098
+ "grad_norm": 0.6653993725776672,
1099
+ "learning_rate": 4.015563527416595e-05,
1100
+ "loss": 0.6334,
1101
+ "step": 780
1102
+ },
1103
+ {
1104
+ "epoch": 1.4721050164088139,
1105
+ "grad_norm": 0.652690052986145,
1106
+ "learning_rate": 4.003818290448876e-05,
1107
+ "loss": 0.644,
1108
+ "step": 785
1109
+ },
1110
+ {
1111
+ "epoch": 1.4814814814814814,
1112
+ "grad_norm": 0.624614953994751,
1113
+ "learning_rate": 3.992020809118832e-05,
1114
+ "loss": 0.7045,
1115
+ "step": 790
1116
+ },
1117
+ {
1118
+ "epoch": 1.4908579465541492,
1119
+ "grad_norm": 0.6916288137435913,
1120
+ "learning_rate": 3.980171493284418e-05,
1121
+ "loss": 0.6335,
1122
+ "step": 795
1123
+ },
1124
+ {
1125
+ "epoch": 1.5002344116268167,
1126
+ "grad_norm": 0.6975934505462646,
1127
+ "learning_rate": 3.9682707546043785e-05,
1128
+ "loss": 0.6705,
1129
+ "step": 800
1130
+ },
1131
+ {
1132
+ "epoch": 1.5096108766994845,
1133
+ "grad_norm": 0.7178190350532532,
1134
+ "learning_rate": 3.9563190065239474e-05,
1135
+ "loss": 0.6219,
1136
+ "step": 805
1137
+ },
1138
+ {
1139
+ "epoch": 1.518987341772152,
1140
+ "grad_norm": 0.711218535900116,
1141
+ "learning_rate": 3.9443166642604814e-05,
1142
+ "loss": 0.6101,
1143
+ "step": 810
1144
+ },
1145
+ {
1146
+ "epoch": 1.5283638068448195,
1147
+ "grad_norm": 0.5779418349266052,
1148
+ "learning_rate": 3.932264144789038e-05,
1149
+ "loss": 0.593,
1150
+ "step": 815
1151
+ },
1152
+ {
1153
+ "epoch": 1.537740271917487,
1154
+ "grad_norm": 0.6230177879333496,
1155
+ "learning_rate": 3.920161866827889e-05,
1156
+ "loss": 0.6577,
1157
+ "step": 820
1158
+ },
1159
+ {
1160
+ "epoch": 1.5471167369901546,
1161
+ "grad_norm": 0.7051926851272583,
1162
+ "learning_rate": 3.908010250823972e-05,
1163
+ "loss": 0.6369,
1164
+ "step": 825
1165
+ },
1166
+ {
1167
+ "epoch": 1.5564932020628222,
1168
+ "grad_norm": 0.7006888389587402,
1169
+ "learning_rate": 3.895809718938283e-05,
1170
+ "loss": 0.6459,
1171
+ "step": 830
1172
+ },
1173
+ {
1174
+ "epoch": 1.56586966713549,
1175
+ "grad_norm": 0.6218993067741394,
1176
+ "learning_rate": 3.883560695031213e-05,
1177
+ "loss": 0.5747,
1178
+ "step": 835
1179
+ },
1180
+ {
1181
+ "epoch": 1.5752461322081577,
1182
+ "grad_norm": 0.656377911567688,
1183
+ "learning_rate": 3.871263604647822e-05,
1184
+ "loss": 0.6334,
1185
+ "step": 840
1186
+ },
1187
+ {
1188
+ "epoch": 1.5846225972808252,
1189
+ "grad_norm": 0.6752548813819885,
1190
+ "learning_rate": 3.858918875003053e-05,
1191
+ "loss": 0.5922,
1192
+ "step": 845
1193
+ },
1194
+ {
1195
+ "epoch": 1.5939990623534928,
1196
+ "grad_norm": 0.7023399472236633,
1197
+ "learning_rate": 3.846526934966891e-05,
1198
+ "loss": 0.6324,
1199
+ "step": 850
1200
+ },
1201
+ {
1202
+ "epoch": 1.6033755274261603,
1203
+ "grad_norm": 0.7364317774772644,
1204
+ "learning_rate": 3.834088215049464e-05,
1205
+ "loss": 0.6397,
1206
+ "step": 855
1207
+ },
1208
+ {
1209
+ "epoch": 1.6127519924988278,
1210
+ "grad_norm": 0.7179546356201172,
1211
+ "learning_rate": 3.821603147386088e-05,
1212
+ "loss": 0.6344,
1213
+ "step": 860
1214
+ },
1215
+ {
1216
+ "epoch": 1.6221284575714956,
1217
+ "grad_norm": 0.6943954825401306,
1218
+ "learning_rate": 3.80907216572225e-05,
1219
+ "loss": 0.5903,
1220
+ "step": 865
1221
+ },
1222
+ {
1223
+ "epoch": 1.6315049226441631,
1224
+ "grad_norm": 0.7795728445053101,
1225
+ "learning_rate": 3.796495705398544e-05,
1226
+ "loss": 0.6362,
1227
+ "step": 870
1228
+ },
1229
+ {
1230
+ "epoch": 1.640881387716831,
1231
+ "grad_norm": 0.6673624515533447,
1232
+ "learning_rate": 3.783874203335542e-05,
1233
+ "loss": 0.6037,
1234
+ "step": 875
1235
+ },
1236
+ {
1237
+ "epoch": 1.6502578527894984,
1238
+ "grad_norm": 0.7244172096252441,
1239
+ "learning_rate": 3.77120809801862e-05,
1240
+ "loss": 0.6131,
1241
+ "step": 880
1242
+ },
1243
+ {
1244
+ "epoch": 1.659634317862166,
1245
+ "grad_norm": 0.587921679019928,
1246
+ "learning_rate": 3.758497829482721e-05,
1247
+ "loss": 0.6504,
1248
+ "step": 885
1249
+ },
1250
+ {
1251
+ "epoch": 1.6690107829348335,
1252
+ "grad_norm": 0.6311667561531067,
1253
+ "learning_rate": 3.7457438392970686e-05,
1254
+ "loss": 0.5784,
1255
+ "step": 890
1256
+ },
1257
+ {
1258
+ "epoch": 1.678387248007501,
1259
+ "grad_norm": 0.7019160985946655,
1260
+ "learning_rate": 3.732946570549825e-05,
1261
+ "loss": 0.6192,
1262
+ "step": 895
1263
+ },
1264
+ {
1265
+ "epoch": 1.6877637130801688,
1266
+ "grad_norm": 0.7296169996261597,
1267
+ "learning_rate": 3.720106467832701e-05,
1268
+ "loss": 0.6849,
1269
+ "step": 900
1270
+ },
1271
+ {
1272
+ "epoch": 1.6971401781528364,
1273
+ "grad_norm": 0.6518985033035278,
1274
+ "learning_rate": 3.707223977225507e-05,
1275
+ "loss": 0.6645,
1276
+ "step": 905
1277
+ },
1278
+ {
1279
+ "epoch": 1.7065166432255041,
1280
+ "grad_norm": 0.629097044467926,
1281
+ "learning_rate": 3.694299546280657e-05,
1282
+ "loss": 0.6728,
1283
+ "step": 910
1284
+ },
1285
+ {
1286
+ "epoch": 1.7158931082981717,
1287
+ "grad_norm": 0.7138874530792236,
1288
+ "learning_rate": 3.681333624007623e-05,
1289
+ "loss": 0.6476,
1290
+ "step": 915
1291
+ },
1292
+ {
1293
+ "epoch": 1.7252695733708392,
1294
+ "grad_norm": 0.69582200050354,
1295
+ "learning_rate": 3.6683266608573286e-05,
1296
+ "loss": 0.7412,
1297
+ "step": 920
1298
+ },
1299
+ {
1300
+ "epoch": 1.7346460384435067,
1301
+ "grad_norm": 0.7621073722839355,
1302
+ "learning_rate": 3.6552791087065075e-05,
1303
+ "loss": 0.6201,
1304
+ "step": 925
1305
+ },
1306
+ {
1307
+ "epoch": 1.7440225035161743,
1308
+ "grad_norm": 0.6894713044166565,
1309
+ "learning_rate": 3.642191420842e-05,
1310
+ "loss": 0.6296,
1311
+ "step": 930
1312
+ },
1313
+ {
1314
+ "epoch": 1.753398968588842,
1315
+ "grad_norm": 0.7036609649658203,
1316
+ "learning_rate": 3.6290640519450074e-05,
1317
+ "loss": 0.6199,
1318
+ "step": 935
1319
+ },
1320
+ {
1321
+ "epoch": 1.7627754336615096,
1322
+ "grad_norm": 0.7221242189407349,
1323
+ "learning_rate": 3.6158974580752954e-05,
1324
+ "loss": 0.6726,
1325
+ "step": 940
1326
+ },
1327
+ {
1328
+ "epoch": 1.7721518987341773,
1329
+ "grad_norm": 0.7487791180610657,
1330
+ "learning_rate": 3.60269209665535e-05,
1331
+ "loss": 0.6077,
1332
+ "step": 945
1333
+ },
1334
+ {
1335
+ "epoch": 1.7815283638068449,
1336
+ "grad_norm": 0.7120531797409058,
1337
+ "learning_rate": 3.589448426454486e-05,
1338
+ "loss": 0.6546,
1339
+ "step": 950
1340
+ },
1341
+ {
1342
+ "epoch": 1.7909048288795124,
1343
+ "grad_norm": 0.7374992966651917,
1344
+ "learning_rate": 3.5761669075729084e-05,
1345
+ "loss": 0.6134,
1346
+ "step": 955
1347
+ },
1348
+ {
1349
+ "epoch": 1.80028129395218,
1350
+ "grad_norm": 0.7404727339744568,
1351
+ "learning_rate": 3.562848001425729e-05,
1352
+ "loss": 0.6833,
1353
+ "step": 960
1354
+ },
1355
+ {
1356
+ "epoch": 1.8096577590248475,
1357
+ "grad_norm": 0.6800241470336914,
1358
+ "learning_rate": 3.549492170726937e-05,
1359
+ "loss": 0.6008,
1360
+ "step": 965
1361
+ },
1362
+ {
1363
+ "epoch": 1.8190342240975153,
1364
+ "grad_norm": 0.736266016960144,
1365
+ "learning_rate": 3.53609987947332e-05,
1366
+ "loss": 0.6444,
1367
+ "step": 970
1368
+ },
1369
+ {
1370
+ "epoch": 1.8284106891701828,
1371
+ "grad_norm": 0.6644765734672546,
1372
+ "learning_rate": 3.5226715929283506e-05,
1373
+ "loss": 0.596,
1374
+ "step": 975
1375
+ },
1376
+ {
1377
+ "epoch": 1.8377871542428506,
1378
+ "grad_norm": 0.6540014147758484,
1379
+ "learning_rate": 3.509207777606013e-05,
1380
+ "loss": 0.5834,
1381
+ "step": 980
1382
+ },
1383
+ {
1384
+ "epoch": 1.847163619315518,
1385
+ "grad_norm": 0.7583248615264893,
1386
+ "learning_rate": 3.49570890125461e-05,
1387
+ "loss": 0.6094,
1388
+ "step": 985
1389
+ },
1390
+ {
1391
+ "epoch": 1.8565400843881856,
1392
+ "grad_norm": 0.6199962496757507,
1393
+ "learning_rate": 3.482175432840495e-05,
1394
+ "loss": 0.5964,
1395
+ "step": 990
1396
+ },
1397
+ {
1398
+ "epoch": 1.8659165494608532,
1399
+ "grad_norm": 0.7292067408561707,
1400
+ "learning_rate": 3.468607842531797e-05,
1401
+ "loss": 0.618,
1402
+ "step": 995
1403
+ },
1404
+ {
1405
+ "epoch": 1.8752930145335207,
1406
+ "grad_norm": 0.7406108379364014,
1407
+ "learning_rate": 3.455006601682075e-05,
1408
+ "loss": 0.596,
1409
+ "step": 1000
1410
+ },
1411
+ {
1412
+ "epoch": 1.8846694796061885,
1413
+ "grad_norm": 0.6806167364120483,
1414
+ "learning_rate": 3.441372182813946e-05,
1415
+ "loss": 0.5774,
1416
+ "step": 1005
1417
+ },
1418
+ {
1419
+ "epoch": 1.8940459446788562,
1420
+ "grad_norm": 0.6825852990150452,
1421
+ "learning_rate": 3.427705059602671e-05,
1422
+ "loss": 0.5982,
1423
+ "step": 1010
1424
+ },
1425
+ {
1426
+ "epoch": 1.9034224097515238,
1427
+ "grad_norm": 0.7001626491546631,
1428
+ "learning_rate": 3.414005706859693e-05,
1429
+ "loss": 0.6422,
1430
+ "step": 1015
1431
+ },
1432
+ {
1433
+ "epoch": 1.9127988748241913,
1434
+ "grad_norm": 0.6993778944015503,
1435
+ "learning_rate": 3.400274600516152e-05,
1436
+ "loss": 0.6312,
1437
+ "step": 1020
1438
+ },
1439
+ {
1440
+ "epoch": 1.9221753398968588,
1441
+ "grad_norm": 0.6194260716438293,
1442
+ "learning_rate": 3.386512217606339e-05,
1443
+ "loss": 0.5998,
1444
+ "step": 1025
1445
+ },
1446
+ {
1447
+ "epoch": 1.9315518049695264,
1448
+ "grad_norm": 0.7205774188041687,
1449
+ "learning_rate": 3.372719036251132e-05,
1450
+ "loss": 0.6103,
1451
+ "step": 1030
1452
+ },
1453
+ {
1454
+ "epoch": 1.9409282700421941,
1455
+ "grad_norm": 0.6409869194030762,
1456
+ "learning_rate": 3.3588955356413795e-05,
1457
+ "loss": 0.6074,
1458
+ "step": 1035
1459
+ },
1460
+ {
1461
+ "epoch": 1.9503047351148617,
1462
+ "grad_norm": 0.7475089430809021,
1463
+ "learning_rate": 3.3450421960212566e-05,
1464
+ "loss": 0.6142,
1465
+ "step": 1040
1466
+ },
1467
+ {
1468
+ "epoch": 1.9596812001875294,
1469
+ "grad_norm": 0.6921798586845398,
1470
+ "learning_rate": 3.3311594986715814e-05,
1471
+ "loss": 0.6366,
1472
+ "step": 1045
1473
+ },
1474
+ {
1475
+ "epoch": 1.969057665260197,
1476
+ "grad_norm": 0.7049899697303772,
1477
+ "learning_rate": 3.317247925893089e-05,
1478
+ "loss": 0.5871,
1479
+ "step": 1050
1480
+ },
1481
+ {
1482
+ "epoch": 1.9784341303328645,
1483
+ "grad_norm": 0.7039067149162292,
1484
+ "learning_rate": 3.3033079609896834e-05,
1485
+ "loss": 0.601,
1486
+ "step": 1055
1487
+ },
1488
+ {
1489
+ "epoch": 1.987810595405532,
1490
+ "grad_norm": 0.7747904062271118,
1491
+ "learning_rate": 3.289340088251642e-05,
1492
+ "loss": 0.5808,
1493
+ "step": 1060
1494
+ },
1495
+ {
1496
+ "epoch": 1.9971870604781996,
1497
+ "grad_norm": 0.6818182468414307,
1498
+ "learning_rate": 3.275344792938791e-05,
1499
+ "loss": 0.6152,
1500
+ "step": 1065
1501
+ },
1502
+ {
1503
+ "epoch": 2.006563525550867,
1504
+ "grad_norm": 0.6767409443855286,
1505
+ "learning_rate": 3.2613225612636525e-05,
1506
+ "loss": 0.5649,
1507
+ "step": 1070
1508
+ },
1509
+ {
1510
+ "epoch": 2.015939990623535,
1511
+ "grad_norm": 0.6562533378601074,
1512
+ "learning_rate": 3.247273880374542e-05,
1513
+ "loss": 0.5623,
1514
+ "step": 1075
1515
+ },
1516
+ {
1517
+ "epoch": 2.0253164556962027,
1518
+ "grad_norm": 0.7730954885482788,
1519
+ "learning_rate": 3.2331992383386566e-05,
1520
+ "loss": 0.6362,
1521
+ "step": 1080
1522
+ },
1523
+ {
1524
+ "epoch": 2.03469292076887,
1525
+ "grad_norm": 0.6370785236358643,
1526
+ "learning_rate": 3.21909912412511e-05,
1527
+ "loss": 0.606,
1528
+ "step": 1085
1529
+ },
1530
+ {
1531
+ "epoch": 2.0440693858415377,
1532
+ "grad_norm": 0.6823928952217102,
1533
+ "learning_rate": 3.2049740275879493e-05,
1534
+ "loss": 0.6176,
1535
+ "step": 1090
1536
+ },
1537
+ {
1538
+ "epoch": 2.0534458509142053,
1539
+ "grad_norm": 0.705295205116272,
1540
+ "learning_rate": 3.190824439449137e-05,
1541
+ "loss": 0.6362,
1542
+ "step": 1095
1543
+ },
1544
+ {
1545
+ "epoch": 2.062822315986873,
1546
+ "grad_norm": 0.7424062490463257,
1547
+ "learning_rate": 3.176650851281499e-05,
1548
+ "loss": 0.5969,
1549
+ "step": 1100
1550
+ },
1551
+ {
1552
+ "epoch": 2.0721987810595404,
1553
+ "grad_norm": 0.7166156768798828,
1554
+ "learning_rate": 3.162453755491655e-05,
1555
+ "loss": 0.5587,
1556
+ "step": 1105
1557
+ },
1558
+ {
1559
+ "epoch": 2.0815752461322083,
1560
+ "grad_norm": 0.6642809510231018,
1561
+ "learning_rate": 3.1482336453028986e-05,
1562
+ "loss": 0.5828,
1563
+ "step": 1110
1564
+ },
1565
+ {
1566
+ "epoch": 2.090951711204876,
1567
+ "grad_norm": 0.7335144877433777,
1568
+ "learning_rate": 3.133991014738076e-05,
1569
+ "loss": 0.601,
1570
+ "step": 1115
1571
+ },
1572
+ {
1573
+ "epoch": 2.1003281762775434,
1574
+ "grad_norm": 0.6921694874763489,
1575
+ "learning_rate": 3.1197263586024155e-05,
1576
+ "loss": 0.6003,
1577
+ "step": 1120
1578
+ },
1579
+ {
1580
+ "epoch": 2.109704641350211,
1581
+ "grad_norm": 0.8270456194877625,
1582
+ "learning_rate": 3.105440172466337e-05,
1583
+ "loss": 0.6198,
1584
+ "step": 1125
1585
+ },
1586
+ {
1587
+ "epoch": 2.1190811064228785,
1588
+ "grad_norm": 0.8127502799034119,
1589
+ "learning_rate": 3.09113295264824e-05,
1590
+ "loss": 0.6133,
1591
+ "step": 1130
1592
+ },
1593
+ {
1594
+ "epoch": 2.128457571495546,
1595
+ "grad_norm": 0.7760539650917053,
1596
+ "learning_rate": 3.076805196197255e-05,
1597
+ "loss": 0.6002,
1598
+ "step": 1135
1599
+ },
1600
+ {
1601
+ "epoch": 2.1378340365682136,
1602
+ "grad_norm": 0.8686167597770691,
1603
+ "learning_rate": 3.0624574008759805e-05,
1604
+ "loss": 0.6979,
1605
+ "step": 1140
1606
+ },
1607
+ {
1608
+ "epoch": 2.1472105016408816,
1609
+ "grad_norm": 0.8145749568939209,
1610
+ "learning_rate": 3.0480900651431876e-05,
1611
+ "loss": 0.5819,
1612
+ "step": 1145
1613
+ },
1614
+ {
1615
+ "epoch": 2.156586966713549,
1616
+ "grad_norm": 0.7867200970649719,
1617
+ "learning_rate": 3.0337036881365045e-05,
1618
+ "loss": 0.5804,
1619
+ "step": 1150
1620
+ },
1621
+ {
1622
+ "epoch": 2.1659634317862166,
1623
+ "grad_norm": 0.7709445953369141,
1624
+ "learning_rate": 3.0192987696550746e-05,
1625
+ "loss": 0.5913,
1626
+ "step": 1155
1627
+ },
1628
+ {
1629
+ "epoch": 2.175339896858884,
1630
+ "grad_norm": 0.7718144059181213,
1631
+ "learning_rate": 3.0048758101421914e-05,
1632
+ "loss": 0.5993,
1633
+ "step": 1160
1634
+ },
1635
+ {
1636
+ "epoch": 2.1847163619315517,
1637
+ "grad_norm": 0.7650019526481628,
1638
+ "learning_rate": 2.9904353106679178e-05,
1639
+ "loss": 0.6061,
1640
+ "step": 1165
1641
+ },
1642
+ {
1643
+ "epoch": 2.1940928270042193,
1644
+ "grad_norm": 0.6802553534507751,
1645
+ "learning_rate": 2.975977772911671e-05,
1646
+ "loss": 0.663,
1647
+ "step": 1170
1648
+ },
1649
+ {
1650
+ "epoch": 2.2034692920768872,
1651
+ "grad_norm": 0.8476700186729431,
1652
+ "learning_rate": 2.9615036991448015e-05,
1653
+ "loss": 0.6158,
1654
+ "step": 1175
1655
+ },
1656
+ {
1657
+ "epoch": 2.212845757149555,
1658
+ "grad_norm": 0.7697311639785767,
1659
+ "learning_rate": 2.947013592213137e-05,
1660
+ "loss": 0.6348,
1661
+ "step": 1180
1662
+ },
1663
+ {
1664
+ "epoch": 2.2222222222222223,
1665
+ "grad_norm": 0.7111309170722961,
1666
+ "learning_rate": 2.9325079555195163e-05,
1667
+ "loss": 0.6263,
1668
+ "step": 1185
1669
+ },
1670
+ {
1671
+ "epoch": 2.23159868729489,
1672
+ "grad_norm": 0.8301457166671753,
1673
+ "learning_rate": 2.9179872930063e-05,
1674
+ "loss": 0.5918,
1675
+ "step": 1190
1676
+ },
1677
+ {
1678
+ "epoch": 2.2409751523675574,
1679
+ "grad_norm": 0.7816576957702637,
1680
+ "learning_rate": 2.9034521091378635e-05,
1681
+ "loss": 0.5724,
1682
+ "step": 1195
1683
+ },
1684
+ {
1685
+ "epoch": 2.250351617440225,
1686
+ "grad_norm": 0.798967182636261,
1687
+ "learning_rate": 2.8889029088830686e-05,
1688
+ "loss": 0.6142,
1689
+ "step": 1200
1690
+ },
1691
+ {
1692
+ "epoch": 2.2597280825128925,
1693
+ "grad_norm": 0.7511455416679382,
1694
+ "learning_rate": 2.8743401976977257e-05,
1695
+ "loss": 0.6048,
1696
+ "step": 1205
1697
+ },
1698
+ {
1699
+ "epoch": 2.2691045475855605,
1700
+ "grad_norm": 0.6589820981025696,
1701
+ "learning_rate": 2.8597644815070263e-05,
1702
+ "loss": 0.6531,
1703
+ "step": 1210
1704
+ },
1705
+ {
1706
+ "epoch": 2.278481012658228,
1707
+ "grad_norm": 0.755199670791626,
1708
+ "learning_rate": 2.845176266687974e-05,
1709
+ "loss": 0.5875,
1710
+ "step": 1215
1711
+ },
1712
+ {
1713
+ "epoch": 2.2878574777308955,
1714
+ "grad_norm": 0.8146589398384094,
1715
+ "learning_rate": 2.8305760600517862e-05,
1716
+ "loss": 0.5762,
1717
+ "step": 1220
1718
+ },
1719
+ {
1720
+ "epoch": 2.297233942803563,
1721
+ "grad_norm": 0.7374768853187561,
1722
+ "learning_rate": 2.815964368826292e-05,
1723
+ "loss": 0.6074,
1724
+ "step": 1225
1725
+ },
1726
+ {
1727
+ "epoch": 2.3066104078762306,
1728
+ "grad_norm": 0.8007232546806335,
1729
+ "learning_rate": 2.8013417006383076e-05,
1730
+ "loss": 0.5865,
1731
+ "step": 1230
1732
+ },
1733
+ {
1734
+ "epoch": 2.315986872948898,
1735
+ "grad_norm": 0.7976067662239075,
1736
+ "learning_rate": 2.7867085634960016e-05,
1737
+ "loss": 0.6015,
1738
+ "step": 1235
1739
+ },
1740
+ {
1741
+ "epoch": 2.3253633380215657,
1742
+ "grad_norm": 0.7782787084579468,
1743
+ "learning_rate": 2.772065465771244e-05,
1744
+ "loss": 0.5973,
1745
+ "step": 1240
1746
+ },
1747
+ {
1748
+ "epoch": 2.3347398030942337,
1749
+ "grad_norm": 0.8809172511100769,
1750
+ "learning_rate": 2.7574129161819495e-05,
1751
+ "loss": 0.6309,
1752
+ "step": 1245
1753
+ },
1754
+ {
1755
+ "epoch": 2.344116268166901,
1756
+ "grad_norm": 0.7300681471824646,
1757
+ "learning_rate": 2.7427514237744e-05,
1758
+ "loss": 0.6291,
1759
+ "step": 1250
1760
+ },
1761
+ {
1762
+ "epoch": 2.3534927332395688,
1763
+ "grad_norm": 0.7953155636787415,
1764
+ "learning_rate": 2.7280814979055612e-05,
1765
+ "loss": 0.6297,
1766
+ "step": 1255
1767
+ },
1768
+ {
1769
+ "epoch": 2.3628691983122363,
1770
+ "grad_norm": 0.6899072527885437,
1771
+ "learning_rate": 2.713403648225388e-05,
1772
+ "loss": 0.5846,
1773
+ "step": 1260
1774
+ },
1775
+ {
1776
+ "epoch": 2.372245663384904,
1777
+ "grad_norm": 0.7751972079277039,
1778
+ "learning_rate": 2.698718384659114e-05,
1779
+ "loss": 0.6009,
1780
+ "step": 1265
1781
+ },
1782
+ {
1783
+ "epoch": 2.3816221284575714,
1784
+ "grad_norm": 0.831641674041748,
1785
+ "learning_rate": 2.684026217389544e-05,
1786
+ "loss": 0.6807,
1787
+ "step": 1270
1788
+ },
1789
+ {
1790
+ "epoch": 2.390998593530239,
1791
+ "grad_norm": 0.7829850912094116,
1792
+ "learning_rate": 2.6693276568393245e-05,
1793
+ "loss": 0.5976,
1794
+ "step": 1275
1795
+ },
1796
+ {
1797
+ "epoch": 2.400375058602907,
1798
+ "grad_norm": 0.7054941058158875,
1799
+ "learning_rate": 2.6546232136532083e-05,
1800
+ "loss": 0.6617,
1801
+ "step": 1280
1802
+ },
1803
+ {
1804
+ "epoch": 2.4097515236755744,
1805
+ "grad_norm": 0.7278191447257996,
1806
+ "learning_rate": 2.639913398680322e-05,
1807
+ "loss": 0.6327,
1808
+ "step": 1285
1809
+ },
1810
+ {
1811
+ "epoch": 2.419127988748242,
1812
+ "grad_norm": 0.6977508068084717,
1813
+ "learning_rate": 2.6251987229564123e-05,
1814
+ "loss": 0.6101,
1815
+ "step": 1290
1816
+ },
1817
+ {
1818
+ "epoch": 2.4285044538209095,
1819
+ "grad_norm": 0.7802432775497437,
1820
+ "learning_rate": 2.610479697686093e-05,
1821
+ "loss": 0.5672,
1822
+ "step": 1295
1823
+ },
1824
+ {
1825
+ "epoch": 2.437880918893577,
1826
+ "grad_norm": 0.8246661424636841,
1827
+ "learning_rate": 2.595756834225089e-05,
1828
+ "loss": 0.6172,
1829
+ "step": 1300
1830
+ },
1831
+ {
1832
+ "epoch": 2.4472573839662446,
1833
+ "grad_norm": 0.8327619433403015,
1834
+ "learning_rate": 2.5810306440624644e-05,
1835
+ "loss": 0.6848,
1836
+ "step": 1305
1837
+ },
1838
+ {
1839
+ "epoch": 2.456633849038912,
1840
+ "grad_norm": 0.8517838716506958,
1841
+ "learning_rate": 2.566301638802861e-05,
1842
+ "loss": 0.6313,
1843
+ "step": 1310
1844
+ },
1845
+ {
1846
+ "epoch": 2.46601031411158,
1847
+ "grad_norm": 0.8053081035614014,
1848
+ "learning_rate": 2.551570330148716e-05,
1849
+ "loss": 0.5976,
1850
+ "step": 1315
1851
+ },
1852
+ {
1853
+ "epoch": 2.4753867791842477,
1854
+ "grad_norm": 0.821284830570221,
1855
+ "learning_rate": 2.5368372298824922e-05,
1856
+ "loss": 0.5623,
1857
+ "step": 1320
1858
+ },
1859
+ {
1860
+ "epoch": 2.484763244256915,
1861
+ "grad_norm": 0.8210687041282654,
1862
+ "learning_rate": 2.5221028498488947e-05,
1863
+ "loss": 0.6274,
1864
+ "step": 1325
1865
+ },
1866
+ {
1867
+ "epoch": 2.4941397093295827,
1868
+ "grad_norm": 0.8597337603569031,
1869
+ "learning_rate": 2.507367701937087e-05,
1870
+ "loss": 0.5823,
1871
+ "step": 1330
1872
+ },
1873
+ {
1874
+ "epoch": 2.5035161744022503,
1875
+ "grad_norm": 0.7325977087020874,
1876
+ "learning_rate": 2.492632298062913e-05,
1877
+ "loss": 0.59,
1878
+ "step": 1335
1879
+ },
1880
+ {
1881
+ "epoch": 2.512892639474918,
1882
+ "grad_norm": 0.8166496157646179,
1883
+ "learning_rate": 2.4778971501511063e-05,
1884
+ "loss": 0.6277,
1885
+ "step": 1340
1886
+ },
1887
+ {
1888
+ "epoch": 2.5222691045475853,
1889
+ "grad_norm": 0.8390632271766663,
1890
+ "learning_rate": 2.4631627701175084e-05,
1891
+ "loss": 0.5809,
1892
+ "step": 1345
1893
+ },
1894
+ {
1895
+ "epoch": 2.5316455696202533,
1896
+ "grad_norm": 0.8438106775283813,
1897
+ "learning_rate": 2.448429669851285e-05,
1898
+ "loss": 0.5756,
1899
+ "step": 1350
1900
+ },
1901
+ {
1902
+ "epoch": 2.541022034692921,
1903
+ "grad_norm": 0.8104760646820068,
1904
+ "learning_rate": 2.43369836119714e-05,
1905
+ "loss": 0.623,
1906
+ "step": 1355
1907
+ },
1908
+ {
1909
+ "epoch": 2.5503984997655884,
1910
+ "grad_norm": 0.7337835431098938,
1911
+ "learning_rate": 2.4189693559375365e-05,
1912
+ "loss": 0.6328,
1913
+ "step": 1360
1914
+ },
1915
+ {
1916
+ "epoch": 2.559774964838256,
1917
+ "grad_norm": 0.8129787445068359,
1918
+ "learning_rate": 2.4042431657749117e-05,
1919
+ "loss": 0.5745,
1920
+ "step": 1365
1921
+ },
1922
+ {
1923
+ "epoch": 2.5691514299109235,
1924
+ "grad_norm": 0.8080322742462158,
1925
+ "learning_rate": 2.3895203023139073e-05,
1926
+ "loss": 0.5681,
1927
+ "step": 1370
1928
+ },
1929
+ {
1930
+ "epoch": 2.578527894983591,
1931
+ "grad_norm": 0.7477867603302002,
1932
+ "learning_rate": 2.3748012770435883e-05,
1933
+ "loss": 0.6243,
1934
+ "step": 1375
1935
+ },
1936
+ {
1937
+ "epoch": 2.5879043600562586,
1938
+ "grad_norm": 0.7538096308708191,
1939
+ "learning_rate": 2.3600866013196787e-05,
1940
+ "loss": 0.6017,
1941
+ "step": 1380
1942
+ },
1943
+ {
1944
+ "epoch": 2.5972808251289266,
1945
+ "grad_norm": 0.7187966704368591,
1946
+ "learning_rate": 2.3453767863467923e-05,
1947
+ "loss": 0.59,
1948
+ "step": 1385
1949
+ },
1950
+ {
1951
+ "epoch": 2.606657290201594,
1952
+ "grad_norm": 0.7694785594940186,
1953
+ "learning_rate": 2.3306723431606758e-05,
1954
+ "loss": 0.5715,
1955
+ "step": 1390
1956
+ },
1957
+ {
1958
+ "epoch": 2.6160337552742616,
1959
+ "grad_norm": 0.7553474307060242,
1960
+ "learning_rate": 2.3159737826104565e-05,
1961
+ "loss": 0.6479,
1962
+ "step": 1395
1963
+ },
1964
+ {
1965
+ "epoch": 2.625410220346929,
1966
+ "grad_norm": 0.7968561053276062,
1967
+ "learning_rate": 2.3012816153408863e-05,
1968
+ "loss": 0.6044,
1969
+ "step": 1400
1970
+ },
1971
+ {
1972
+ "epoch": 2.6347866854195967,
1973
+ "grad_norm": 0.7905867099761963,
1974
+ "learning_rate": 2.286596351774613e-05,
1975
+ "loss": 0.5893,
1976
+ "step": 1405
1977
+ },
1978
+ {
1979
+ "epoch": 2.6441631504922647,
1980
+ "grad_norm": 0.8002238869667053,
1981
+ "learning_rate": 2.271918502094439e-05,
1982
+ "loss": 0.5733,
1983
+ "step": 1410
1984
+ },
1985
+ {
1986
+ "epoch": 2.653539615564932,
1987
+ "grad_norm": 0.7693070769309998,
1988
+ "learning_rate": 2.2572485762256005e-05,
1989
+ "loss": 0.5649,
1990
+ "step": 1415
1991
+ },
1992
+ {
1993
+ "epoch": 2.6629160806375998,
1994
+ "grad_norm": 0.8900006413459778,
1995
+ "learning_rate": 2.2425870838180507e-05,
1996
+ "loss": 0.5842,
1997
+ "step": 1420
1998
+ },
1999
+ {
2000
+ "epoch": 2.6722925457102673,
2001
+ "grad_norm": 0.7960033416748047,
2002
+ "learning_rate": 2.2279345342287567e-05,
2003
+ "loss": 0.5905,
2004
+ "step": 1425
2005
+ },
2006
+ {
2007
+ "epoch": 2.681669010782935,
2008
+ "grad_norm": 0.7953693270683289,
2009
+ "learning_rate": 2.2132914365039993e-05,
2010
+ "loss": 0.6128,
2011
+ "step": 1430
2012
+ },
2013
+ {
2014
+ "epoch": 2.6910454758556024,
2015
+ "grad_norm": 0.8477721214294434,
2016
+ "learning_rate": 2.1986582993616926e-05,
2017
+ "loss": 0.6135,
2018
+ "step": 1435
2019
+ },
2020
+ {
2021
+ "epoch": 2.70042194092827,
2022
+ "grad_norm": 0.7555422782897949,
2023
+ "learning_rate": 2.1840356311737084e-05,
2024
+ "loss": 0.5995,
2025
+ "step": 1440
2026
+ },
2027
+ {
2028
+ "epoch": 2.709798406000938,
2029
+ "grad_norm": 0.74222731590271,
2030
+ "learning_rate": 2.169423939948215e-05,
2031
+ "loss": 0.6354,
2032
+ "step": 1445
2033
+ },
2034
+ {
2035
+ "epoch": 2.719174871073605,
2036
+ "grad_norm": 0.8535959124565125,
2037
+ "learning_rate": 2.154823733312027e-05,
2038
+ "loss": 0.6152,
2039
+ "step": 1450
2040
+ },
2041
+ {
2042
+ "epoch": 2.728551336146273,
2043
+ "grad_norm": 0.8919956684112549,
2044
+ "learning_rate": 2.140235518492975e-05,
2045
+ "loss": 0.5884,
2046
+ "step": 1455
2047
+ },
2048
+ {
2049
+ "epoch": 2.7379278012189405,
2050
+ "grad_norm": 0.8774855732917786,
2051
+ "learning_rate": 2.125659802302275e-05,
2052
+ "loss": 0.5956,
2053
+ "step": 1460
2054
+ },
2055
+ {
2056
+ "epoch": 2.747304266291608,
2057
+ "grad_norm": 0.6897487044334412,
2058
+ "learning_rate": 2.1110970911169316e-05,
2059
+ "loss": 0.5954,
2060
+ "step": 1465
2061
+ },
2062
+ {
2063
+ "epoch": 2.7566807313642756,
2064
+ "grad_norm": 0.714082658290863,
2065
+ "learning_rate": 2.096547890862137e-05,
2066
+ "loss": 0.6026,
2067
+ "step": 1470
2068
+ },
2069
+ {
2070
+ "epoch": 2.766057196436943,
2071
+ "grad_norm": 0.890238881111145,
2072
+ "learning_rate": 2.0820127069937008e-05,
2073
+ "loss": 0.5849,
2074
+ "step": 1475
2075
+ },
2076
+ {
2077
+ "epoch": 2.775433661509611,
2078
+ "grad_norm": 0.8606293201446533,
2079
+ "learning_rate": 2.0674920444804847e-05,
2080
+ "loss": 0.5873,
2081
+ "step": 1480
2082
+ },
2083
+ {
2084
+ "epoch": 2.7848101265822782,
2085
+ "grad_norm": 0.8042623996734619,
2086
+ "learning_rate": 2.0529864077868643e-05,
2087
+ "loss": 0.6195,
2088
+ "step": 1485
2089
+ },
2090
+ {
2091
+ "epoch": 2.794186591654946,
2092
+ "grad_norm": 0.8238710761070251,
2093
+ "learning_rate": 2.0384963008551995e-05,
2094
+ "loss": 0.6176,
2095
+ "step": 1490
2096
+ },
2097
+ {
2098
+ "epoch": 2.8035630567276137,
2099
+ "grad_norm": 0.7856019139289856,
2100
+ "learning_rate": 2.0240222270883288e-05,
2101
+ "loss": 0.6364,
2102
+ "step": 1495
2103
+ },
2104
+ {
2105
+ "epoch": 2.8129395218002813,
2106
+ "grad_norm": 0.8265510201454163,
2107
+ "learning_rate": 2.0095646893320828e-05,
2108
+ "loss": 0.5921,
2109
+ "step": 1500
2110
+ },
2111
+ {
2112
+ "epoch": 2.822315986872949,
2113
+ "grad_norm": 0.7399757504463196,
2114
+ "learning_rate": 1.9951241898578085e-05,
2115
+ "loss": 0.5787,
2116
+ "step": 1505
2117
+ },
2118
+ {
2119
+ "epoch": 2.8316924519456164,
2120
+ "grad_norm": 0.7769511938095093,
2121
+ "learning_rate": 1.980701230344926e-05,
2122
+ "loss": 0.5955,
2123
+ "step": 1510
2124
+ },
2125
+ {
2126
+ "epoch": 2.8410689170182843,
2127
+ "grad_norm": 0.7197275757789612,
2128
+ "learning_rate": 1.9662963118634954e-05,
2129
+ "loss": 0.6349,
2130
+ "step": 1515
2131
+ },
2132
+ {
2133
+ "epoch": 2.8504453820909514,
2134
+ "grad_norm": 0.844546914100647,
2135
+ "learning_rate": 1.9519099348568127e-05,
2136
+ "loss": 0.599,
2137
+ "step": 1520
2138
+ },
2139
+ {
2140
+ "epoch": 2.8598218471636194,
2141
+ "grad_norm": 0.799412727355957,
2142
+ "learning_rate": 1.93754259912402e-05,
2143
+ "loss": 0.6072,
2144
+ "step": 1525
2145
+ },
2146
+ {
2147
+ "epoch": 2.869198312236287,
2148
+ "grad_norm": 0.7316399216651917,
2149
+ "learning_rate": 1.9231948038027462e-05,
2150
+ "loss": 0.5714,
2151
+ "step": 1530
2152
+ },
2153
+ {
2154
+ "epoch": 2.8785747773089545,
2155
+ "grad_norm": 0.7330530285835266,
2156
+ "learning_rate": 1.9088670473517605e-05,
2157
+ "loss": 0.6001,
2158
+ "step": 1535
2159
+ },
2160
+ {
2161
+ "epoch": 2.887951242381622,
2162
+ "grad_norm": 0.7442522048950195,
2163
+ "learning_rate": 1.8945598275336633e-05,
2164
+ "loss": 0.5621,
2165
+ "step": 1540
2166
+ },
2167
+ {
2168
+ "epoch": 2.8973277074542896,
2169
+ "grad_norm": 0.8327356576919556,
2170
+ "learning_rate": 1.8802736413975844e-05,
2171
+ "loss": 0.6401,
2172
+ "step": 1545
2173
+ },
2174
+ {
2175
+ "epoch": 2.9067041725269576,
2176
+ "grad_norm": 0.8828593492507935,
2177
+ "learning_rate": 1.866008985261924e-05,
2178
+ "loss": 0.5987,
2179
+ "step": 1550
2180
+ },
2181
+ {
2182
+ "epoch": 2.916080637599625,
2183
+ "grad_norm": 0.79734867811203,
2184
+ "learning_rate": 1.8517663546971013e-05,
2185
+ "loss": 0.5915,
2186
+ "step": 1555
2187
+ },
2188
+ {
2189
+ "epoch": 2.9254571026722926,
2190
+ "grad_norm": 0.8401964902877808,
2191
+ "learning_rate": 1.8375462445083464e-05,
2192
+ "loss": 0.621,
2193
+ "step": 1560
2194
+ },
2195
+ {
2196
+ "epoch": 2.93483356774496,
2197
+ "grad_norm": 0.7760779857635498,
2198
+ "learning_rate": 1.8233491487185006e-05,
2199
+ "loss": 0.6379,
2200
+ "step": 1565
2201
+ },
2202
+ {
2203
+ "epoch": 2.9442100328176277,
2204
+ "grad_norm": 0.7567408084869385,
2205
+ "learning_rate": 1.8091755605508643e-05,
2206
+ "loss": 0.599,
2207
+ "step": 1570
2208
+ },
2209
+ {
2210
+ "epoch": 2.9535864978902953,
2211
+ "grad_norm": 0.8464756608009338,
2212
+ "learning_rate": 1.7950259724120512e-05,
2213
+ "loss": 0.6333,
2214
+ "step": 1575
2215
+ },
2216
+ {
2217
+ "epoch": 2.962962962962963,
2218
+ "grad_norm": 0.8063556551933289,
2219
+ "learning_rate": 1.7809008758748913e-05,
2220
+ "loss": 0.6245,
2221
+ "step": 1580
2222
+ },
2223
+ {
2224
+ "epoch": 2.972339428035631,
2225
+ "grad_norm": 0.8217030167579651,
2226
+ "learning_rate": 1.766800761661344e-05,
2227
+ "loss": 0.575,
2228
+ "step": 1585
2229
+ },
2230
+ {
2231
+ "epoch": 2.9817158931082983,
2232
+ "grad_norm": 0.9118950366973877,
2233
+ "learning_rate": 1.752726119625459e-05,
2234
+ "loss": 0.6453,
2235
+ "step": 1590
2236
+ },
2237
+ {
2238
+ "epoch": 2.991092358180966,
2239
+ "grad_norm": 0.7912649512290955,
2240
+ "learning_rate": 1.7386774387363484e-05,
2241
+ "loss": 0.6524,
2242
+ "step": 1595
2243
+ },
2244
+ {
2245
+ "epoch": 3.0004688232536334,
2246
+ "grad_norm": 0.8924903869628906,
2247
+ "learning_rate": 1.724655207061209e-05,
2248
+ "loss": 0.5959,
2249
+ "step": 1600
2250
+ },
2251
+ {
2252
+ "epoch": 3.009845288326301,
2253
+ "grad_norm": 0.8312458992004395,
2254
+ "learning_rate": 1.710659911748359e-05,
2255
+ "loss": 0.6342,
2256
+ "step": 1605
2257
+ },
2258
+ {
2259
+ "epoch": 3.0192217533989685,
2260
+ "grad_norm": 0.8554635047912598,
2261
+ "learning_rate": 1.696692039010317e-05,
2262
+ "loss": 0.5901,
2263
+ "step": 1610
2264
+ },
2265
+ {
2266
+ "epoch": 3.028598218471636,
2267
+ "grad_norm": 0.8181942701339722,
2268
+ "learning_rate": 1.6827520741069118e-05,
2269
+ "loss": 0.6125,
2270
+ "step": 1615
2271
+ },
2272
+ {
2273
+ "epoch": 3.037974683544304,
2274
+ "grad_norm": 0.8597581386566162,
2275
+ "learning_rate": 1.6688405013284192e-05,
2276
+ "loss": 0.6208,
2277
+ "step": 1620
2278
+ },
2279
+ {
2280
+ "epoch": 3.0473511486169715,
2281
+ "grad_norm": 0.7262174487113953,
2282
+ "learning_rate": 1.6549578039787436e-05,
2283
+ "loss": 0.6135,
2284
+ "step": 1625
2285
+ },
2286
+ {
2287
+ "epoch": 3.056727613689639,
2288
+ "grad_norm": 0.8130325675010681,
2289
+ "learning_rate": 1.6411044643586204e-05,
2290
+ "loss": 0.5635,
2291
+ "step": 1630
2292
+ },
2293
+ {
2294
+ "epoch": 3.0661040787623066,
2295
+ "grad_norm": 0.8838590383529663,
2296
+ "learning_rate": 1.627280963748869e-05,
2297
+ "loss": 0.5519,
2298
+ "step": 1635
2299
+ },
2300
+ {
2301
+ "epoch": 3.075480543834974,
2302
+ "grad_norm": 0.73687344789505,
2303
+ "learning_rate": 1.613487782393661e-05,
2304
+ "loss": 0.6453,
2305
+ "step": 1640
2306
+ },
2307
+ {
2308
+ "epoch": 3.0848570089076417,
2309
+ "grad_norm": 0.8523545265197754,
2310
+ "learning_rate": 1.5997253994838484e-05,
2311
+ "loss": 0.5444,
2312
+ "step": 1645
2313
+ },
2314
+ {
2315
+ "epoch": 3.0942334739803092,
2316
+ "grad_norm": 0.9110212922096252,
2317
+ "learning_rate": 1.5859942931403072e-05,
2318
+ "loss": 0.6103,
2319
+ "step": 1650
2320
+ },
2321
+ {
2322
+ "epoch": 3.103609939052977,
2323
+ "grad_norm": 0.867031991481781,
2324
+ "learning_rate": 1.5722949403973308e-05,
2325
+ "loss": 0.656,
2326
+ "step": 1655
2327
+ },
2328
+ {
2329
+ "epoch": 3.1129864041256448,
2330
+ "grad_norm": 0.9489920735359192,
2331
+ "learning_rate": 1.5586278171860546e-05,
2332
+ "loss": 0.5887,
2333
+ "step": 1660
2334
+ },
2335
+ {
2336
+ "epoch": 3.1223628691983123,
2337
+ "grad_norm": 0.8050504326820374,
2338
+ "learning_rate": 1.5449933983179256e-05,
2339
+ "loss": 0.599,
2340
+ "step": 1665
2341
+ },
2342
+ {
2343
+ "epoch": 3.13173933427098,
2344
+ "grad_norm": 0.8593913316726685,
2345
+ "learning_rate": 1.5313921574682032e-05,
2346
+ "loss": 0.5677,
2347
+ "step": 1670
2348
+ },
2349
+ {
2350
+ "epoch": 3.1411157993436474,
2351
+ "grad_norm": 0.8273171782493591,
2352
+ "learning_rate": 1.517824567159506e-05,
2353
+ "loss": 0.5458,
2354
+ "step": 1675
2355
+ },
2356
+ {
2357
+ "epoch": 3.150492264416315,
2358
+ "grad_norm": 0.9210759997367859,
2359
+ "learning_rate": 1.5042910987453909e-05,
2360
+ "loss": 0.6356,
2361
+ "step": 1680
2362
+ },
2363
+ {
2364
+ "epoch": 3.1598687294889825,
2365
+ "grad_norm": 0.8576172590255737,
2366
+ "learning_rate": 1.4907922223939874e-05,
2367
+ "loss": 0.5678,
2368
+ "step": 1685
2369
+ },
2370
+ {
2371
+ "epoch": 3.1692451945616504,
2372
+ "grad_norm": 0.838844358921051,
2373
+ "learning_rate": 1.4773284070716503e-05,
2374
+ "loss": 0.5883,
2375
+ "step": 1690
2376
+ },
2377
+ {
2378
+ "epoch": 3.178621659634318,
2379
+ "grad_norm": 0.846047043800354,
2380
+ "learning_rate": 1.4639001205266803e-05,
2381
+ "loss": 0.5643,
2382
+ "step": 1695
2383
+ },
2384
+ {
2385
+ "epoch": 3.1879981247069855,
2386
+ "grad_norm": 0.7580421566963196,
2387
+ "learning_rate": 1.4505078292730632e-05,
2388
+ "loss": 0.5889,
2389
+ "step": 1700
2390
+ },
2391
+ {
2392
+ "epoch": 3.197374589779653,
2393
+ "grad_norm": 0.8859914541244507,
2394
+ "learning_rate": 1.4371519985742715e-05,
2395
+ "loss": 0.555,
2396
+ "step": 1705
2397
+ },
2398
+ {
2399
+ "epoch": 3.2067510548523206,
2400
+ "grad_norm": 0.8607549071311951,
2401
+ "learning_rate": 1.4238330924270927e-05,
2402
+ "loss": 0.5856,
2403
+ "step": 1710
2404
+ },
2405
+ {
2406
+ "epoch": 3.216127519924988,
2407
+ "grad_norm": 0.8387409448623657,
2408
+ "learning_rate": 1.4105515735455149e-05,
2409
+ "loss": 0.6232,
2410
+ "step": 1715
2411
+ },
2412
+ {
2413
+ "epoch": 3.2255039849976557,
2414
+ "grad_norm": 0.8116487860679626,
2415
+ "learning_rate": 1.3973079033446501e-05,
2416
+ "loss": 0.6432,
2417
+ "step": 1720
2418
+ },
2419
+ {
2420
+ "epoch": 3.2348804500703237,
2421
+ "grad_norm": 0.9285030364990234,
2422
+ "learning_rate": 1.3841025419247045e-05,
2423
+ "loss": 0.5808,
2424
+ "step": 1725
2425
+ },
2426
+ {
2427
+ "epoch": 3.244256915142991,
2428
+ "grad_norm": 0.9143246412277222,
2429
+ "learning_rate": 1.3709359480549932e-05,
2430
+ "loss": 0.5563,
2431
+ "step": 1730
2432
+ },
2433
+ {
2434
+ "epoch": 3.2536333802156587,
2435
+ "grad_norm": 0.8626976013183594,
2436
+ "learning_rate": 1.3578085791580008e-05,
2437
+ "loss": 0.5474,
2438
+ "step": 1735
2439
+ },
2440
+ {
2441
+ "epoch": 3.2630098452883263,
2442
+ "grad_norm": 0.8373091220855713,
2443
+ "learning_rate": 1.3447208912934927e-05,
2444
+ "loss": 0.6451,
2445
+ "step": 1740
2446
+ },
2447
+ {
2448
+ "epoch": 3.272386310360994,
2449
+ "grad_norm": 0.9622659087181091,
2450
+ "learning_rate": 1.3316733391426716e-05,
2451
+ "loss": 0.5905,
2452
+ "step": 1745
2453
+ },
2454
+ {
2455
+ "epoch": 3.2817627754336613,
2456
+ "grad_norm": 0.8686250448226929,
2457
+ "learning_rate": 1.3186663759923782e-05,
2458
+ "loss": 0.5763,
2459
+ "step": 1750
2460
+ },
2461
+ {
2462
+ "epoch": 3.291139240506329,
2463
+ "grad_norm": 0.8520202040672302,
2464
+ "learning_rate": 1.3057004537193423e-05,
2465
+ "loss": 0.5873,
2466
+ "step": 1755
2467
+ },
2468
+ {
2469
+ "epoch": 3.300515705578997,
2470
+ "grad_norm": 0.8578153252601624,
2471
+ "learning_rate": 1.2927760227744943e-05,
2472
+ "loss": 0.5518,
2473
+ "step": 1760
2474
+ },
2475
+ {
2476
+ "epoch": 3.3098921706516644,
2477
+ "grad_norm": 0.9105794429779053,
2478
+ "learning_rate": 1.2798935321673e-05,
2479
+ "loss": 0.5584,
2480
+ "step": 1765
2481
+ },
2482
+ {
2483
+ "epoch": 3.319268635724332,
2484
+ "grad_norm": 0.7702586650848389,
2485
+ "learning_rate": 1.2670534294501756e-05,
2486
+ "loss": 0.5702,
2487
+ "step": 1770
2488
+ },
2489
+ {
2490
+ "epoch": 3.3286451007969995,
2491
+ "grad_norm": 0.910254716873169,
2492
+ "learning_rate": 1.2542561607029322e-05,
2493
+ "loss": 0.5774,
2494
+ "step": 1775
2495
+ },
2496
+ {
2497
+ "epoch": 3.338021565869667,
2498
+ "grad_norm": 0.8458461761474609,
2499
+ "learning_rate": 1.2415021705172799e-05,
2500
+ "loss": 0.6325,
2501
+ "step": 1780
2502
+ },
2503
+ {
2504
+ "epoch": 3.3473980309423346,
2505
+ "grad_norm": 0.8077149987220764,
2506
+ "learning_rate": 1.2287919019813807e-05,
2507
+ "loss": 0.5764,
2508
+ "step": 1785
2509
+ },
2510
+ {
2511
+ "epoch": 3.356774496015002,
2512
+ "grad_norm": 0.954138457775116,
2513
+ "learning_rate": 1.2161257966644588e-05,
2514
+ "loss": 0.6093,
2515
+ "step": 1790
2516
+ },
2517
+ {
2518
+ "epoch": 3.36615096108767,
2519
+ "grad_norm": 0.8187435865402222,
2520
+ "learning_rate": 1.2035042946014572e-05,
2521
+ "loss": 0.6254,
2522
+ "step": 1795
2523
+ },
2524
+ {
2525
+ "epoch": 3.3755274261603376,
2526
+ "grad_norm": 0.9092109799385071,
2527
+ "learning_rate": 1.1909278342777513e-05,
2528
+ "loss": 0.5884,
2529
+ "step": 1800
2530
+ },
2531
+ {
2532
+ "epoch": 3.384903891233005,
2533
+ "grad_norm": 0.7966195940971375,
2534
+ "learning_rate": 1.1783968526139121e-05,
2535
+ "loss": 0.5836,
2536
+ "step": 1805
2537
+ },
2538
+ {
2539
+ "epoch": 3.3942803563056727,
2540
+ "grad_norm": 0.9109008312225342,
2541
+ "learning_rate": 1.1659117849505367e-05,
2542
+ "loss": 0.6103,
2543
+ "step": 1810
2544
+ },
2545
+ {
2546
+ "epoch": 3.4036568213783402,
2547
+ "grad_norm": 0.8773274421691895,
2548
+ "learning_rate": 1.1534730650331096e-05,
2549
+ "loss": 0.5888,
2550
+ "step": 1815
2551
+ },
2552
+ {
2553
+ "epoch": 3.413033286451008,
2554
+ "grad_norm": 0.8986825346946716,
2555
+ "learning_rate": 1.1410811249969475e-05,
2556
+ "loss": 0.6512,
2557
+ "step": 1820
2558
+ },
2559
+ {
2560
+ "epoch": 3.4224097515236753,
2561
+ "grad_norm": 0.8653113842010498,
2562
+ "learning_rate": 1.1287363953521779e-05,
2563
+ "loss": 0.591,
2564
+ "step": 1825
2565
+ },
2566
+ {
2567
+ "epoch": 3.4317862165963433,
2568
+ "grad_norm": 0.8190916776657104,
2569
+ "learning_rate": 1.1164393049687868e-05,
2570
+ "loss": 0.5623,
2571
+ "step": 1830
2572
+ },
2573
+ {
2574
+ "epoch": 3.441162681669011,
2575
+ "grad_norm": 0.7718261480331421,
2576
+ "learning_rate": 1.104190281061718e-05,
2577
+ "loss": 0.6128,
2578
+ "step": 1835
2579
+ },
2580
+ {
2581
+ "epoch": 3.4505391467416784,
2582
+ "grad_norm": 0.8960718512535095,
2583
+ "learning_rate": 1.0919897491760279e-05,
2584
+ "loss": 0.526,
2585
+ "step": 1840
2586
+ },
2587
+ {
2588
+ "epoch": 3.459915611814346,
2589
+ "grad_norm": 0.8175593614578247,
2590
+ "learning_rate": 1.0798381331721109e-05,
2591
+ "loss": 0.567,
2592
+ "step": 1845
2593
+ },
2594
+ {
2595
+ "epoch": 3.4692920768870135,
2596
+ "grad_norm": 0.7988520860671997,
2597
+ "learning_rate": 1.0677358552109618e-05,
2598
+ "loss": 0.6084,
2599
+ "step": 1850
2600
+ },
2601
+ {
2602
+ "epoch": 3.4786685419596814,
2603
+ "grad_norm": 0.7820413112640381,
2604
+ "learning_rate": 1.0556833357395188e-05,
2605
+ "loss": 0.574,
2606
+ "step": 1855
2607
+ },
2608
+ {
2609
+ "epoch": 3.488045007032349,
2610
+ "grad_norm": 0.8565638661384583,
2611
+ "learning_rate": 1.0436809934760527e-05,
2612
+ "loss": 0.5817,
2613
+ "step": 1860
2614
+ },
2615
+ {
2616
+ "epoch": 3.4974214721050165,
2617
+ "grad_norm": 0.8797834515571594,
2618
+ "learning_rate": 1.031729245395622e-05,
2619
+ "loss": 0.5398,
2620
+ "step": 1865
2621
+ },
2622
+ {
2623
+ "epoch": 3.506797937177684,
2624
+ "grad_norm": 0.9399333000183105,
2625
+ "learning_rate": 1.0198285067155827e-05,
2626
+ "loss": 0.5761,
2627
+ "step": 1870
2628
+ },
2629
+ {
2630
+ "epoch": 3.5161744022503516,
2631
+ "grad_norm": 0.8871551752090454,
2632
+ "learning_rate": 1.0079791908811683e-05,
2633
+ "loss": 0.5762,
2634
+ "step": 1875
2635
+ },
2636
+ {
2637
+ "epoch": 3.525550867323019,
2638
+ "grad_norm": 0.8348819613456726,
2639
+ "learning_rate": 9.961817095511242e-06,
2640
+ "loss": 0.5656,
2641
+ "step": 1880
2642
+ },
2643
+ {
2644
+ "epoch": 3.5349273323956867,
2645
+ "grad_norm": 0.7780579924583435,
2646
+ "learning_rate": 9.844364725834057e-06,
2647
+ "loss": 0.6402,
2648
+ "step": 1885
2649
+ },
2650
+ {
2651
+ "epoch": 3.5443037974683547,
2652
+ "grad_norm": 1.0246992111206055,
2653
+ "learning_rate": 9.727438880209366e-06,
2654
+ "loss": 0.5627,
2655
+ "step": 1890
2656
+ },
2657
+ {
2658
+ "epoch": 3.5536802625410218,
2659
+ "grad_norm": 0.9967918395996094,
2660
+ "learning_rate": 9.611043620774419e-06,
2661
+ "loss": 0.6265,
2662
+ "step": 1895
2663
+ },
2664
+ {
2665
+ "epoch": 3.5630567276136897,
2666
+ "grad_norm": 0.803693413734436,
2667
+ "learning_rate": 9.495182991233236e-06,
2668
+ "loss": 0.5915,
2669
+ "step": 1900
2670
+ },
2671
+ {
2672
+ "epoch": 3.5724331926863573,
2673
+ "grad_norm": 0.8501057028770447,
2674
+ "learning_rate": 9.379861016716224e-06,
2675
+ "loss": 0.6192,
2676
+ "step": 1905
2677
+ },
2678
+ {
2679
+ "epoch": 3.581809657759025,
2680
+ "grad_norm": 0.8275097012519836,
2681
+ "learning_rate": 9.265081703640285e-06,
2682
+ "loss": 0.6139,
2683
+ "step": 1910
2684
+ },
2685
+ {
2686
+ "epoch": 3.5911861228316924,
2687
+ "grad_norm": 0.863562822341919,
2688
+ "learning_rate": 9.150849039569655e-06,
2689
+ "loss": 0.5788,
2690
+ "step": 1915
2691
+ },
2692
+ {
2693
+ "epoch": 3.60056258790436,
2694
+ "grad_norm": 0.777866005897522,
2695
+ "learning_rate": 9.037166993077337e-06,
2696
+ "loss": 0.5967,
2697
+ "step": 1920
2698
+ },
2699
+ {
2700
+ "epoch": 3.609939052977028,
2701
+ "grad_norm": 0.8494200110435486,
2702
+ "learning_rate": 8.92403951360726e-06,
2703
+ "loss": 0.5525,
2704
+ "step": 1925
2705
+ },
2706
+ {
2707
+ "epoch": 3.6193155180496954,
2708
+ "grad_norm": 0.7887282967567444,
2709
+ "learning_rate": 8.811470531337102e-06,
2710
+ "loss": 0.6459,
2711
+ "step": 1930
2712
+ },
2713
+ {
2714
+ "epoch": 3.628691983122363,
2715
+ "grad_norm": 0.8828495144844055,
2716
+ "learning_rate": 8.699463957041649e-06,
2717
+ "loss": 0.6542,
2718
+ "step": 1935
2719
+ },
2720
+ {
2721
+ "epoch": 3.6380684481950305,
2722
+ "grad_norm": 0.8919112682342529,
2723
+ "learning_rate": 8.588023681957028e-06,
2724
+ "loss": 0.6144,
2725
+ "step": 1940
2726
+ },
2727
+ {
2728
+ "epoch": 3.647444913267698,
2729
+ "grad_norm": 0.9850883483886719,
2730
+ "learning_rate": 8.477153577645481e-06,
2731
+ "loss": 0.6243,
2732
+ "step": 1945
2733
+ },
2734
+ {
2735
+ "epoch": 3.6568213783403656,
2736
+ "grad_norm": 0.7918851375579834,
2737
+ "learning_rate": 8.36685749586087e-06,
2738
+ "loss": 0.6097,
2739
+ "step": 1950
2740
+ },
2741
+ {
2742
+ "epoch": 3.666197843413033,
2743
+ "grad_norm": 0.9201750159263611,
2744
+ "learning_rate": 8.257139268414844e-06,
2745
+ "loss": 0.589,
2746
+ "step": 1955
2747
+ },
2748
+ {
2749
+ "epoch": 3.675574308485701,
2750
+ "grad_norm": 0.8442370891571045,
2751
+ "learning_rate": 8.14800270704375e-06,
2752
+ "loss": 0.6196,
2753
+ "step": 1960
2754
+ },
2755
+ {
2756
+ "epoch": 3.6849507735583686,
2757
+ "grad_norm": 0.8792855143547058,
2758
+ "learning_rate": 8.039451603276185e-06,
2759
+ "loss": 0.5785,
2760
+ "step": 1965
2761
+ },
2762
+ {
2763
+ "epoch": 3.694327238631036,
2764
+ "grad_norm": 0.760504424571991,
2765
+ "learning_rate": 7.931489728301292e-06,
2766
+ "loss": 0.6941,
2767
+ "step": 1970
2768
+ },
2769
+ {
2770
+ "epoch": 3.7037037037037037,
2771
+ "grad_norm": 0.9026913046836853,
2772
+ "learning_rate": 7.8241208328377e-06,
2773
+ "loss": 0.5711,
2774
+ "step": 1975
2775
+ },
2776
+ {
2777
+ "epoch": 3.7130801687763713,
2778
+ "grad_norm": 0.7041096687316895,
2779
+ "learning_rate": 7.71734864700331e-06,
2780
+ "loss": 0.5851,
2781
+ "step": 1980
2782
+ },
2783
+ {
2784
+ "epoch": 3.722456633849039,
2785
+ "grad_norm": 0.8825089335441589,
2786
+ "learning_rate": 7.611176880185597e-06,
2787
+ "loss": 0.5877,
2788
+ "step": 1985
2789
+ },
2790
+ {
2791
+ "epoch": 3.7318330989217063,
2792
+ "grad_norm": 0.8271408677101135,
2793
+ "learning_rate": 7.505609220912821e-06,
2794
+ "loss": 0.5841,
2795
+ "step": 1990
2796
+ },
2797
+ {
2798
+ "epoch": 3.7412095639943743,
2799
+ "grad_norm": 0.8782235980033875,
2800
+ "learning_rate": 7.4006493367258515e-06,
2801
+ "loss": 0.6185,
2802
+ "step": 1995
2803
+ },
2804
+ {
2805
+ "epoch": 3.750586029067042,
2806
+ "grad_norm": 0.9581049084663391,
2807
+ "learning_rate": 7.2963008740507656e-06,
2808
+ "loss": 0.6278,
2809
+ "step": 2000
2810
+ },
2811
+ {
2812
+ "epoch": 3.7599624941397094,
2813
+ "grad_norm": 0.8480396270751953,
2814
+ "learning_rate": 7.192567458072138e-06,
2815
+ "loss": 0.6518,
2816
+ "step": 2005
2817
+ },
2818
+ {
2819
+ "epoch": 3.769338959212377,
2820
+ "grad_norm": 0.8499250411987305,
2821
+ "learning_rate": 7.089452692607146e-06,
2822
+ "loss": 0.529,
2823
+ "step": 2010
2824
+ },
2825
+ {
2826
+ "epoch": 3.7787154242850445,
2827
+ "grad_norm": 0.9328426122665405,
2828
+ "learning_rate": 6.986960159980327e-06,
2829
+ "loss": 0.554,
2830
+ "step": 2015
2831
+ },
2832
+ {
2833
+ "epoch": 3.788091889357712,
2834
+ "grad_norm": 0.7562410831451416,
2835
+ "learning_rate": 6.885093420899152e-06,
2836
+ "loss": 0.5859,
2837
+ "step": 2020
2838
+ },
2839
+ {
2840
+ "epoch": 3.7974683544303796,
2841
+ "grad_norm": 0.8860601186752319,
2842
+ "learning_rate": 6.783856014330281e-06,
2843
+ "loss": 0.5853,
2844
+ "step": 2025
2845
+ },
2846
+ {
2847
+ "epoch": 3.8068448195030475,
2848
+ "grad_norm": 0.8630738258361816,
2849
+ "learning_rate": 6.68325145737669e-06,
2850
+ "loss": 0.5972,
2851
+ "step": 2030
2852
+ },
2853
+ {
2854
+ "epoch": 3.816221284575715,
2855
+ "grad_norm": 0.8959819674491882,
2856
+ "learning_rate": 6.583283245155414e-06,
2857
+ "loss": 0.6114,
2858
+ "step": 2035
2859
+ },
2860
+ {
2861
+ "epoch": 3.8255977496483826,
2862
+ "grad_norm": 1.036385178565979,
2863
+ "learning_rate": 6.483954850676133e-06,
2864
+ "loss": 0.5638,
2865
+ "step": 2040
2866
+ },
2867
+ {
2868
+ "epoch": 3.83497421472105,
2869
+ "grad_norm": 0.830777645111084,
2870
+ "learning_rate": 6.385269724720547e-06,
2871
+ "loss": 0.6113,
2872
+ "step": 2045
2873
+ },
2874
+ {
2875
+ "epoch": 3.8443506797937177,
2876
+ "grad_norm": 0.9295665621757507,
2877
+ "learning_rate": 6.28723129572247e-06,
2878
+ "loss": 0.5559,
2879
+ "step": 2050
2880
+ },
2881
+ {
2882
+ "epoch": 3.8537271448663852,
2883
+ "grad_norm": 0.9256186485290527,
2884
+ "learning_rate": 6.189842969648737e-06,
2885
+ "loss": 0.6219,
2886
+ "step": 2055
2887
+ },
2888
+ {
2889
+ "epoch": 3.8631036099390528,
2890
+ "grad_norm": 0.8613486289978027,
2891
+ "learning_rate": 6.0931081298808316e-06,
2892
+ "loss": 0.5907,
2893
+ "step": 2060
2894
+ },
2895
+ {
2896
+ "epoch": 3.8724800750117208,
2897
+ "grad_norm": 0.8655708432197571,
2898
+ "learning_rate": 5.997030137097426e-06,
2899
+ "loss": 0.5563,
2900
+ "step": 2065
2901
+ },
2902
+ {
2903
+ "epoch": 3.8818565400843883,
2904
+ "grad_norm": 0.864285409450531,
2905
+ "learning_rate": 5.901612329157535e-06,
2906
+ "loss": 0.6009,
2907
+ "step": 2070
2908
+ },
2909
+ {
2910
+ "epoch": 3.891233005157056,
2911
+ "grad_norm": 0.819516122341156,
2912
+ "learning_rate": 5.806858020984629e-06,
2913
+ "loss": 0.6581,
2914
+ "step": 2075
2915
+ },
2916
+ {
2917
+ "epoch": 3.9006094702297234,
2918
+ "grad_norm": 0.9411301016807556,
2919
+ "learning_rate": 5.712770504451426e-06,
2920
+ "loss": 0.5945,
2921
+ "step": 2080
2922
+ },
2923
+ {
2924
+ "epoch": 3.909985935302391,
2925
+ "grad_norm": 0.8822996020317078,
2926
+ "learning_rate": 5.619353048265552e-06,
2927
+ "loss": 0.5586,
2928
+ "step": 2085
2929
+ },
2930
+ {
2931
+ "epoch": 3.9193624003750585,
2932
+ "grad_norm": 0.8772969245910645,
2933
+ "learning_rate": 5.526608897855953e-06,
2934
+ "loss": 0.5624,
2935
+ "step": 2090
2936
+ },
2937
+ {
2938
+ "epoch": 3.928738865447726,
2939
+ "grad_norm": 0.8968551754951477,
2940
+ "learning_rate": 5.434541275260182e-06,
2941
+ "loss": 0.6261,
2942
+ "step": 2095
2943
+ },
2944
+ {
2945
+ "epoch": 3.938115330520394,
2946
+ "grad_norm": 0.8807035088539124,
2947
+ "learning_rate": 5.343153379012444e-06,
2948
+ "loss": 0.6223,
2949
+ "step": 2100
2950
+ },
2951
+ {
2952
+ "epoch": 3.9474917955930615,
2953
+ "grad_norm": 0.8569791316986084,
2954
+ "learning_rate": 5.252448384032471e-06,
2955
+ "loss": 0.5724,
2956
+ "step": 2105
2957
+ },
2958
+ {
2959
+ "epoch": 3.956868260665729,
2960
+ "grad_norm": 0.8825068473815918,
2961
+ "learning_rate": 5.162429441515221e-06,
2962
+ "loss": 0.5976,
2963
+ "step": 2110
2964
+ },
2965
+ {
2966
+ "epoch": 3.9662447257383966,
2967
+ "grad_norm": 0.8981527090072632,
2968
+ "learning_rate": 5.073099678821413e-06,
2969
+ "loss": 0.5715,
2970
+ "step": 2115
2971
+ },
2972
+ {
2973
+ "epoch": 3.975621190811064,
2974
+ "grad_norm": 0.8927028775215149,
2975
+ "learning_rate": 4.984462199368872e-06,
2976
+ "loss": 0.6233,
2977
+ "step": 2120
2978
+ },
2979
+ {
2980
+ "epoch": 3.9849976558837317,
2981
+ "grad_norm": 0.8970484137535095,
2982
+ "learning_rate": 4.8965200825247245e-06,
2983
+ "loss": 0.574,
2984
+ "step": 2125
2985
+ },
2986
+ {
2987
+ "epoch": 3.994374120956399,
2988
+ "grad_norm": 0.8048734664916992,
2989
+ "learning_rate": 4.809276383498376e-06,
2990
+ "loss": 0.5929,
2991
+ "step": 2130
2992
+ },
2993
+ {
2994
+ "epoch": 4.003750586029067,
2995
+ "grad_norm": 0.8596838116645813,
2996
+ "learning_rate": 4.722734133235438e-06,
2997
+ "loss": 0.592,
2998
+ "step": 2135
2999
+ },
3000
+ {
3001
+ "epoch": 4.013127051101734,
3002
+ "grad_norm": 0.8907204866409302,
3003
+ "learning_rate": 4.636896338312374e-06,
3004
+ "loss": 0.6445,
3005
+ "step": 2140
3006
+ },
3007
+ {
3008
+ "epoch": 4.022503516174402,
3009
+ "grad_norm": 0.8903965353965759,
3010
+ "learning_rate": 4.551765980832059e-06,
3011
+ "loss": 0.5722,
3012
+ "step": 2145
3013
+ },
3014
+ {
3015
+ "epoch": 4.03187998124707,
3016
+ "grad_norm": 0.9628483057022095,
3017
+ "learning_rate": 4.467346018320198e-06,
3018
+ "loss": 0.6088,
3019
+ "step": 2150
3020
+ },
3021
+ {
3022
+ "epoch": 4.041256446319737,
3023
+ "grad_norm": 0.8551229238510132,
3024
+ "learning_rate": 4.383639383622557e-06,
3025
+ "loss": 0.5924,
3026
+ "step": 2155
3027
+ },
3028
+ {
3029
+ "epoch": 4.050632911392405,
3030
+ "grad_norm": 0.9129508137702942,
3031
+ "learning_rate": 4.300648984803085e-06,
3032
+ "loss": 0.5758,
3033
+ "step": 2160
3034
+ },
3035
+ {
3036
+ "epoch": 4.060009376465072,
3037
+ "grad_norm": 0.7754344940185547,
3038
+ "learning_rate": 4.218377705042867e-06,
3039
+ "loss": 0.5952,
3040
+ "step": 2165
3041
+ },
3042
+ {
3043
+ "epoch": 4.06938584153774,
3044
+ "grad_norm": 0.8496968746185303,
3045
+ "learning_rate": 4.1368284025399965e-06,
3046
+ "loss": 0.604,
3047
+ "step": 2170
3048
+ },
3049
+ {
3050
+ "epoch": 4.0787623066104075,
3051
+ "grad_norm": 0.7441787719726562,
3052
+ "learning_rate": 4.0560039104102305e-06,
3053
+ "loss": 0.5906,
3054
+ "step": 2175
3055
+ },
3056
+ {
3057
+ "epoch": 4.0881387716830755,
3058
+ "grad_norm": 0.782251238822937,
3059
+ "learning_rate": 3.975907036588594e-06,
3060
+ "loss": 0.5407,
3061
+ "step": 2180
3062
+ },
3063
+ {
3064
+ "epoch": 4.0975152367557435,
3065
+ "grad_norm": 0.9450968503952026,
3066
+ "learning_rate": 3.8965405637318294e-06,
3067
+ "loss": 0.5633,
3068
+ "step": 2185
3069
+ },
3070
+ {
3071
+ "epoch": 4.106891701828411,
3072
+ "grad_norm": 0.9217153787612915,
3073
+ "learning_rate": 3.817907249121713e-06,
3074
+ "loss": 0.599,
3075
+ "step": 2190
3076
+ },
3077
+ {
3078
+ "epoch": 4.1162681669010786,
3079
+ "grad_norm": 0.8987939953804016,
3080
+ "learning_rate": 3.7400098245692572e-06,
3081
+ "loss": 0.5879,
3082
+ "step": 2195
3083
+ },
3084
+ {
3085
+ "epoch": 4.125644631973746,
3086
+ "grad_norm": 0.8248675465583801,
3087
+ "learning_rate": 3.662850996319825e-06,
3088
+ "loss": 0.562,
3089
+ "step": 2200
3090
+ },
3091
+ {
3092
+ "epoch": 4.135021097046414,
3093
+ "grad_norm": 0.9806444644927979,
3094
+ "learning_rate": 3.586433444959103e-06,
3095
+ "loss": 0.5675,
3096
+ "step": 2205
3097
+ },
3098
+ {
3099
+ "epoch": 4.144397562119081,
3100
+ "grad_norm": 0.9450485706329346,
3101
+ "learning_rate": 3.5107598253199758e-06,
3102
+ "loss": 0.5573,
3103
+ "step": 2210
3104
+ },
3105
+ {
3106
+ "epoch": 4.153774027191749,
3107
+ "grad_norm": 0.9093477129936218,
3108
+ "learning_rate": 3.4358327663902677e-06,
3109
+ "loss": 0.5788,
3110
+ "step": 2215
3111
+ },
3112
+ {
3113
+ "epoch": 4.163150492264417,
3114
+ "grad_norm": 0.9950726628303528,
3115
+ "learning_rate": 3.3616548712214756e-06,
3116
+ "loss": 0.5877,
3117
+ "step": 2220
3118
+ },
3119
+ {
3120
+ "epoch": 4.172526957337084,
3121
+ "grad_norm": 0.7849723100662231,
3122
+ "learning_rate": 3.288228716838246e-06,
3123
+ "loss": 0.5661,
3124
+ "step": 2225
3125
+ },
3126
+ {
3127
+ "epoch": 4.181903422409752,
3128
+ "grad_norm": 0.869097113609314,
3129
+ "learning_rate": 3.2155568541489268e-06,
3130
+ "loss": 0.6241,
3131
+ "step": 2230
3132
+ },
3133
+ {
3134
+ "epoch": 4.191279887482419,
3135
+ "grad_norm": 0.8070918917655945,
3136
+ "learning_rate": 3.143641807856898e-06,
3137
+ "loss": 0.5932,
3138
+ "step": 2235
3139
+ },
3140
+ {
3141
+ "epoch": 4.200656352555087,
3142
+ "grad_norm": 0.8659390807151794,
3143
+ "learning_rate": 3.0724860763728767e-06,
3144
+ "loss": 0.6129,
3145
+ "step": 2240
3146
+ },
3147
+ {
3148
+ "epoch": 4.210032817627754,
3149
+ "grad_norm": 0.7739548683166504,
3150
+ "learning_rate": 3.0020921317281264e-06,
3151
+ "loss": 0.5467,
3152
+ "step": 2245
3153
+ },
3154
+ {
3155
+ "epoch": 4.219409282700422,
3156
+ "grad_norm": 0.9735186100006104,
3157
+ "learning_rate": 2.9324624194885436e-06,
3158
+ "loss": 0.6347,
3159
+ "step": 2250
3160
+ },
3161
+ {
3162
+ "epoch": 4.22878574777309,
3163
+ "grad_norm": 0.9059353470802307,
3164
+ "learning_rate": 2.8635993586697553e-06,
3165
+ "loss": 0.5657,
3166
+ "step": 2255
3167
+ },
3168
+ {
3169
+ "epoch": 4.238162212845757,
3170
+ "grad_norm": 0.8660772442817688,
3171
+ "learning_rate": 2.795505341653007e-06,
3172
+ "loss": 0.5562,
3173
+ "step": 2260
3174
+ },
3175
+ {
3176
+ "epoch": 4.247538677918425,
3177
+ "grad_norm": 0.8667048811912537,
3178
+ "learning_rate": 2.728182734102111e-06,
3179
+ "loss": 0.5954,
3180
+ "step": 2265
3181
+ },
3182
+ {
3183
+ "epoch": 4.256915142991092,
3184
+ "grad_norm": 0.8115469217300415,
3185
+ "learning_rate": 2.6616338748812255e-06,
3186
+ "loss": 0.6499,
3187
+ "step": 2270
3188
+ },
3189
+ {
3190
+ "epoch": 4.26629160806376,
3191
+ "grad_norm": 0.8536361455917358,
3192
+ "learning_rate": 2.595861075973613e-06,
3193
+ "loss": 0.5835,
3194
+ "step": 2275
3195
+ },
3196
+ {
3197
+ "epoch": 4.275668073136427,
3198
+ "grad_norm": 0.8056153655052185,
3199
+ "learning_rate": 2.530866622401304e-06,
3200
+ "loss": 0.5804,
3201
+ "step": 2280
3202
+ },
3203
+ {
3204
+ "epoch": 4.285044538209095,
3205
+ "grad_norm": 0.8950304985046387,
3206
+ "learning_rate": 2.4666527721457416e-06,
3207
+ "loss": 0.5838,
3208
+ "step": 2285
3209
+ },
3210
+ {
3211
+ "epoch": 4.294421003281763,
3212
+ "grad_norm": 0.7784991264343262,
3213
+ "learning_rate": 2.40322175606931e-06,
3214
+ "loss": 0.6163,
3215
+ "step": 2290
3216
+ },
3217
+ {
3218
+ "epoch": 4.30379746835443,
3219
+ "grad_norm": 0.9436336159706116,
3220
+ "learning_rate": 2.3405757778378445e-06,
3221
+ "loss": 0.5561,
3222
+ "step": 2295
3223
+ },
3224
+ {
3225
+ "epoch": 4.313173933427098,
3226
+ "grad_norm": 0.8611324429512024,
3227
+ "learning_rate": 2.278717013844059e-06,
3228
+ "loss": 0.5709,
3229
+ "step": 2300
3230
+ },
3231
+ {
3232
+ "epoch": 4.322550398499765,
3233
+ "grad_norm": 0.8388680219650269,
3234
+ "learning_rate": 2.2176476131319707e-06,
3235
+ "loss": 0.5357,
3236
+ "step": 2305
3237
+ },
3238
+ {
3239
+ "epoch": 4.331926863572433,
3240
+ "grad_norm": 0.9825294613838196,
3241
+ "learning_rate": 2.1573696973221922e-06,
3242
+ "loss": 0.584,
3243
+ "step": 2310
3244
+ },
3245
+ {
3246
+ "epoch": 4.3413033286451,
3247
+ "grad_norm": 0.8579577803611755,
3248
+ "learning_rate": 2.0978853605382624e-06,
3249
+ "loss": 0.5967,
3250
+ "step": 2315
3251
+ },
3252
+ {
3253
+ "epoch": 4.350679793717768,
3254
+ "grad_norm": 0.8288280367851257,
3255
+ "learning_rate": 2.0391966693338733e-06,
3256
+ "loss": 0.5506,
3257
+ "step": 2320
3258
+ },
3259
+ {
3260
+ "epoch": 4.360056258790436,
3261
+ "grad_norm": 0.8322898745536804,
3262
+ "learning_rate": 1.9813056626210886e-06,
3263
+ "loss": 0.5686,
3264
+ "step": 2325
3265
+ },
3266
+ {
3267
+ "epoch": 4.369432723863103,
3268
+ "grad_norm": 0.7500792145729065,
3269
+ "learning_rate": 1.9242143515994933e-06,
3270
+ "loss": 0.5544,
3271
+ "step": 2330
3272
+ },
3273
+ {
3274
+ "epoch": 4.378809188935771,
3275
+ "grad_norm": 0.9064257144927979,
3276
+ "learning_rate": 1.8679247196863425e-06,
3277
+ "loss": 0.5756,
3278
+ "step": 2335
3279
+ },
3280
+ {
3281
+ "epoch": 4.3881856540084385,
3282
+ "grad_norm": 0.8289924263954163,
3283
+ "learning_rate": 1.8124387224476347e-06,
3284
+ "loss": 0.5522,
3285
+ "step": 2340
3286
+ },
3287
+ {
3288
+ "epoch": 4.3975621190811065,
3289
+ "grad_norm": 0.7926067113876343,
3290
+ "learning_rate": 1.757758287530195e-06,
3291
+ "loss": 0.5979,
3292
+ "step": 2345
3293
+ },
3294
+ {
3295
+ "epoch": 4.4069385841537745,
3296
+ "grad_norm": 0.8662146925926208,
3297
+ "learning_rate": 1.7038853145946804e-06,
3298
+ "loss": 0.5762,
3299
+ "step": 2350
3300
+ },
3301
+ {
3302
+ "epoch": 4.416315049226442,
3303
+ "grad_norm": 0.9003971815109253,
3304
+ "learning_rate": 1.6508216752496141e-06,
3305
+ "loss": 0.6322,
3306
+ "step": 2355
3307
+ },
3308
+ {
3309
+ "epoch": 4.42569151429911,
3310
+ "grad_norm": 0.9239695072174072,
3311
+ "learning_rate": 1.5985692129863395e-06,
3312
+ "loss": 0.5814,
3313
+ "step": 2360
3314
+ },
3315
+ {
3316
+ "epoch": 4.435067979371777,
3317
+ "grad_norm": 0.8550184369087219,
3318
+ "learning_rate": 1.547129743114978e-06,
3319
+ "loss": 0.621,
3320
+ "step": 2365
3321
+ },
3322
+ {
3323
+ "epoch": 4.444444444444445,
3324
+ "grad_norm": 0.8961548209190369,
3325
+ "learning_rate": 1.496505052701372e-06,
3326
+ "loss": 0.5462,
3327
+ "step": 2370
3328
+ },
3329
+ {
3330
+ "epoch": 4.453820909517112,
3331
+ "grad_norm": 0.887492835521698,
3332
+ "learning_rate": 1.4466969005050013e-06,
3333
+ "loss": 0.5868,
3334
+ "step": 2375
3335
+ },
3336
+ {
3337
+ "epoch": 4.46319737458978,
3338
+ "grad_norm": 0.854110598564148,
3339
+ "learning_rate": 1.3977070169178763e-06,
3340
+ "loss": 0.582,
3341
+ "step": 2380
3342
+ },
3343
+ {
3344
+ "epoch": 4.472573839662447,
3345
+ "grad_norm": 0.806898832321167,
3346
+ "learning_rate": 1.349537103904408e-06,
3347
+ "loss": 0.5764,
3348
+ "step": 2385
3349
+ },
3350
+ {
3351
+ "epoch": 4.481950304735115,
3352
+ "grad_norm": 0.8820757269859314,
3353
+ "learning_rate": 1.3021888349423222e-06,
3354
+ "loss": 0.5745,
3355
+ "step": 2390
3356
+ },
3357
+ {
3358
+ "epoch": 4.491326769807783,
3359
+ "grad_norm": 0.8095480799674988,
3360
+ "learning_rate": 1.2556638549644644e-06,
3361
+ "loss": 0.6206,
3362
+ "step": 2395
3363
+ },
3364
+ {
3365
+ "epoch": 4.50070323488045,
3366
+ "grad_norm": 0.8199688792228699,
3367
+ "learning_rate": 1.2099637803016983e-06,
3368
+ "loss": 0.5657,
3369
+ "step": 2400
3370
+ },
3371
+ {
3372
+ "epoch": 4.510079699953118,
3373
+ "grad_norm": 0.8629977703094482,
3374
+ "learning_rate": 1.1650901986267365e-06,
3375
+ "loss": 0.5487,
3376
+ "step": 2405
3377
+ },
3378
+ {
3379
+ "epoch": 4.519456165025785,
3380
+ "grad_norm": 1.0007340908050537,
3381
+ "learning_rate": 1.1210446688989768e-06,
3382
+ "loss": 0.6923,
3383
+ "step": 2410
3384
+ },
3385
+ {
3386
+ "epoch": 4.528832630098453,
3387
+ "grad_norm": 0.9053314328193665,
3388
+ "learning_rate": 1.0778287213103478e-06,
3389
+ "loss": 0.5588,
3390
+ "step": 2415
3391
+ },
3392
+ {
3393
+ "epoch": 4.538209095171121,
3394
+ "grad_norm": 0.909077525138855,
3395
+ "learning_rate": 1.0354438572321546e-06,
3396
+ "loss": 0.5588,
3397
+ "step": 2420
3398
+ },
3399
+ {
3400
+ "epoch": 4.547585560243788,
3401
+ "grad_norm": 0.8841737508773804,
3402
+ "learning_rate": 9.938915491629063e-07,
3403
+ "loss": 0.5864,
3404
+ "step": 2425
3405
+ },
3406
+ {
3407
+ "epoch": 4.556962025316456,
3408
+ "grad_norm": 0.9441853761672974,
3409
+ "learning_rate": 9.531732406771771e-07,
3410
+ "loss": 0.5896,
3411
+ "step": 2430
3412
+ },
3413
+ {
3414
+ "epoch": 4.566338490389123,
3415
+ "grad_norm": 0.9060314893722534,
3416
+ "learning_rate": 9.132903463754256e-07,
3417
+ "loss": 0.6555,
3418
+ "step": 2435
3419
+ },
3420
+ {
3421
+ "epoch": 4.575714955461791,
3422
+ "grad_norm": 0.8534815907478333,
3423
+ "learning_rate": 8.742442518348965e-07,
3424
+ "loss": 0.5814,
3425
+ "step": 2440
3426
+ },
3427
+ {
3428
+ "epoch": 4.585091420534458,
3429
+ "grad_norm": 0.8542777895927429,
3430
+ "learning_rate": 8.360363135614307e-07,
3431
+ "loss": 0.5837,
3432
+ "step": 2445
3433
+ },
3434
+ {
3435
+ "epoch": 4.594467885607126,
3436
+ "grad_norm": 0.8332429528236389,
3437
+ "learning_rate": 7.986678589423758e-07,
3438
+ "loss": 0.6351,
3439
+ "step": 2450
3440
+ },
3441
+ {
3442
+ "epoch": 4.603844350679793,
3443
+ "grad_norm": 0.7473989725112915,
3444
+ "learning_rate": 7.621401862004634e-07,
3445
+ "loss": 0.6131,
3446
+ "step": 2455
3447
+ },
3448
+ {
3449
+ "epoch": 4.613220815752461,
3450
+ "grad_norm": 0.944680392742157,
3451
+ "learning_rate": 7.264545643486997e-07,
3452
+ "loss": 0.5549,
3453
+ "step": 2460
3454
+ },
3455
+ {
3456
+ "epoch": 4.622597280825129,
3457
+ "grad_norm": 0.8840490579605103,
3458
+ "learning_rate": 6.916122331462799e-07,
3459
+ "loss": 0.5807,
3460
+ "step": 2465
3461
+ },
3462
+ {
3463
+ "epoch": 4.631973745897796,
3464
+ "grad_norm": 0.821358859539032,
3465
+ "learning_rate": 6.576144030555259e-07,
3466
+ "loss": 0.6375,
3467
+ "step": 2470
3468
+ },
3469
+ {
3470
+ "epoch": 4.641350210970464,
3471
+ "grad_norm": 0.7711257934570312,
3472
+ "learning_rate": 6.244622551998203e-07,
3473
+ "loss": 0.58,
3474
+ "step": 2475
3475
+ },
3476
+ {
3477
+ "epoch": 4.650726676043131,
3478
+ "grad_norm": 0.9030258059501648,
3479
+ "learning_rate": 5.921569413225913e-07,
3480
+ "loss": 0.6019,
3481
+ "step": 2480
3482
+ },
3483
+ {
3484
+ "epoch": 4.660103141115799,
3485
+ "grad_norm": 0.8605978488922119,
3486
+ "learning_rate": 5.606995837472817e-07,
3487
+ "loss": 0.5911,
3488
+ "step": 2485
3489
+ },
3490
+ {
3491
+ "epoch": 4.669479606188467,
3492
+ "grad_norm": 0.8807564377784729,
3493
+ "learning_rate": 5.300912753383625e-07,
3494
+ "loss": 0.5959,
3495
+ "step": 2490
3496
+ },
3497
+ {
3498
+ "epoch": 4.6788560712611345,
3499
+ "grad_norm": 0.7941368222236633,
3500
+ "learning_rate": 5.003330794633776e-07,
3501
+ "loss": 0.5758,
3502
+ "step": 2495
3503
+ },
3504
+ {
3505
+ "epoch": 4.688232536333802,
3506
+ "grad_norm": 0.9393755197525024,
3507
+ "learning_rate": 4.714260299559875e-07,
3508
+ "loss": 0.6281,
3509
+ "step": 2500
3510
+ },
3511
+ {
3512
+ "epoch": 4.6976090014064695,
3513
+ "grad_norm": 0.9173010587692261,
3514
+ "learning_rate": 4.4337113108005314e-07,
3515
+ "loss": 0.5875,
3516
+ "step": 2505
3517
+ },
3518
+ {
3519
+ "epoch": 4.7069854664791375,
3520
+ "grad_norm": 0.8334708213806152,
3521
+ "learning_rate": 4.161693574947556e-07,
3522
+ "loss": 0.6487,
3523
+ "step": 2510
3524
+ },
3525
+ {
3526
+ "epoch": 4.716361931551805,
3527
+ "grad_norm": 0.8359082937240601,
3528
+ "learning_rate": 3.8982165422073445e-07,
3529
+ "loss": 0.558,
3530
+ "step": 2515
3531
+ },
3532
+ {
3533
+ "epoch": 4.725738396624473,
3534
+ "grad_norm": 0.8860461711883545,
3535
+ "learning_rate": 3.6432893660723886e-07,
3536
+ "loss": 0.6207,
3537
+ "step": 2520
3538
+ },
3539
+ {
3540
+ "epoch": 4.73511486169714,
3541
+ "grad_norm": 0.8132157921791077,
3542
+ "learning_rate": 3.396920903003559e-07,
3543
+ "loss": 0.5592,
3544
+ "step": 2525
3545
+ },
3546
+ {
3547
+ "epoch": 4.744491326769808,
3548
+ "grad_norm": 0.8932085037231445,
3549
+ "learning_rate": 3.1591197121222107e-07,
3550
+ "loss": 0.5857,
3551
+ "step": 2530
3552
+ },
3553
+ {
3554
+ "epoch": 4.753867791842476,
3555
+ "grad_norm": 0.9291250109672546,
3556
+ "learning_rate": 2.9298940549128964e-07,
3557
+ "loss": 0.5805,
3558
+ "step": 2535
3559
+ },
3560
+ {
3561
+ "epoch": 4.763244256915143,
3562
+ "grad_norm": 0.8858462572097778,
3563
+ "learning_rate": 2.7092518949362875e-07,
3564
+ "loss": 0.5519,
3565
+ "step": 2540
3566
+ },
3567
+ {
3568
+ "epoch": 4.772620721987811,
3569
+ "grad_norm": 0.8283771872520447,
3570
+ "learning_rate": 2.4972008975527593e-07,
3571
+ "loss": 0.6442,
3572
+ "step": 2545
3573
+ },
3574
+ {
3575
+ "epoch": 4.781997187060478,
3576
+ "grad_norm": 0.9091749787330627,
3577
+ "learning_rate": 2.2937484296556566e-07,
3578
+ "loss": 0.5744,
3579
+ "step": 2550
3580
+ },
3581
+ {
3582
+ "epoch": 4.791373652133146,
3583
+ "grad_norm": 0.8469679951667786,
3584
+ "learning_rate": 2.0989015594158058e-07,
3585
+ "loss": 0.6113,
3586
+ "step": 2555
3587
+ },
3588
+ {
3589
+ "epoch": 4.800750117205814,
3590
+ "grad_norm": 0.9119710326194763,
3591
+ "learning_rate": 1.9126670560356553e-07,
3592
+ "loss": 0.6187,
3593
+ "step": 2560
3594
+ },
3595
+ {
3596
+ "epoch": 4.810126582278481,
3597
+ "grad_norm": 0.9027541279792786,
3598
+ "learning_rate": 1.735051389514214e-07,
3599
+ "loss": 0.554,
3600
+ "step": 2565
3601
+ },
3602
+ {
3603
+ "epoch": 4.819503047351149,
3604
+ "grad_norm": 0.8532278537750244,
3605
+ "learning_rate": 1.5660607304223141e-07,
3606
+ "loss": 0.5647,
3607
+ "step": 2570
3608
+ },
3609
+ {
3610
+ "epoch": 4.828879512423816,
3611
+ "grad_norm": 0.9646401405334473,
3612
+ "learning_rate": 1.4057009496881158e-07,
3613
+ "loss": 0.6173,
3614
+ "step": 2575
3615
+ },
3616
+ {
3617
+ "epoch": 4.838255977496484,
3618
+ "grad_norm": 0.8723577260971069,
3619
+ "learning_rate": 1.2539776183932982e-07,
3620
+ "loss": 0.5928,
3621
+ "step": 2580
3622
+ },
3623
+ {
3624
+ "epoch": 4.847632442569151,
3625
+ "grad_norm": 0.8372580409049988,
3626
+ "learning_rate": 1.1108960075794372e-07,
3627
+ "loss": 0.5262,
3628
+ "step": 2585
3629
+ },
3630
+ {
3631
+ "epoch": 4.857008907641819,
3632
+ "grad_norm": 0.8806862235069275,
3633
+ "learning_rate": 9.764610880648451e-08,
3634
+ "loss": 0.5449,
3635
+ "step": 2590
3636
+ },
3637
+ {
3638
+ "epoch": 4.866385372714487,
3639
+ "grad_norm": 0.8421341180801392,
3640
+ "learning_rate": 8.506775302719039e-08,
3641
+ "loss": 0.5811,
3642
+ "step": 2595
3643
+ },
3644
+ {
3645
+ "epoch": 4.875761837787154,
3646
+ "grad_norm": 0.8507823348045349,
3647
+ "learning_rate": 7.335497040648898e-08,
3648
+ "loss": 0.5818,
3649
+ "step": 2600
3650
+ },
3651
+ {
3652
+ "epoch": 4.885138302859822,
3653
+ "grad_norm": 0.845939040184021,
3654
+ "learning_rate": 6.250816785980385e-08,
3655
+ "loss": 0.6438,
3656
+ "step": 2605
3657
+ },
3658
+ {
3659
+ "epoch": 4.894514767932489,
3660
+ "grad_norm": 0.9025863409042358,
3661
+ "learning_rate": 5.2527722217421416e-08,
3662
+ "loss": 0.5808,
3663
+ "step": 2610
3664
+ },
3665
+ {
3666
+ "epoch": 4.903891233005157,
3667
+ "grad_norm": 0.9419434666633606,
3668
+ "learning_rate": 4.3413980211412516e-08,
3669
+ "loss": 0.5931,
3670
+ "step": 2615
3671
+ },
3672
+ {
3673
+ "epoch": 4.913267698077824,
3674
+ "grad_norm": 0.9738614559173584,
3675
+ "learning_rate": 3.516725846355873e-08,
3676
+ "loss": 0.551,
3677
+ "step": 2620
3678
+ },
3679
+ {
3680
+ "epoch": 4.922644163150492,
3681
+ "grad_norm": 0.97791987657547,
3682
+ "learning_rate": 2.7787843474386123e-08,
3683
+ "loss": 0.5414,
3684
+ "step": 2625
3685
+ },
3686
+ {
3687
+ "epoch": 4.93202062822316,
3688
+ "grad_norm": 0.8999043703079224,
3689
+ "learning_rate": 2.127599161318161e-08,
3690
+ "loss": 0.6081,
3691
+ "step": 2630
3692
+ },
3693
+ {
3694
+ "epoch": 4.941397093295827,
3695
+ "grad_norm": 0.82914137840271,
3696
+ "learning_rate": 1.5631929109102828e-08,
3697
+ "loss": 0.6069,
3698
+ "step": 2635
3699
+ },
3700
+ {
3701
+ "epoch": 4.950773558368495,
3702
+ "grad_norm": 0.870003879070282,
3703
+ "learning_rate": 1.0855852043323289e-08,
3704
+ "loss": 0.5897,
3705
+ "step": 2640
3706
+ },
3707
+ {
3708
+ "epoch": 4.960150023441162,
3709
+ "grad_norm": 0.9073407053947449,
3710
+ "learning_rate": 6.947926342204536e-09,
3711
+ "loss": 0.558,
3712
+ "step": 2645
3713
+ },
3714
+ {
3715
+ "epoch": 4.96952648851383,
3716
+ "grad_norm": 0.821584165096283,
3717
+ "learning_rate": 3.908287771542396e-09,
3718
+ "loss": 0.5617,
3719
+ "step": 2650
3720
+ },
3721
+ {
3722
+ "epoch": 4.978902953586498,
3723
+ "grad_norm": 0.8036399483680725,
3724
+ "learning_rate": 1.737041931845762e-09,
3725
+ "loss": 0.6366,
3726
+ "step": 2655
3727
+ },
3728
+ {
3729
+ "epoch": 4.9882794186591655,
3730
+ "grad_norm": 0.8421087861061096,
3731
+ "learning_rate": 4.3426425467008035e-10,
3732
+ "loss": 0.5921,
3733
+ "step": 2660
3734
+ },
3735
+ {
3736
+ "epoch": 4.9976558837318334,
3737
+ "grad_norm": 0.8873931765556335,
3738
+ "learning_rate": 0.0,
3739
+ "loss": 0.5838,
3740
+ "step": 2665
3741
+ },
3742
+ {
3743
+ "epoch": 4.9976558837318334,
3744
+ "step": 2665,
3745
+ "total_flos": 2.0317707214423327e+18,
3746
+ "train_loss": 0.623453339492626,
3747
+ "train_runtime": 36076.8467,
3748
+ "train_samples_per_second": 1.182,
3749
+ "train_steps_per_second": 0.074
3750
+ }
3751
+ ],
3752
+ "logging_steps": 5,
3753
+ "max_steps": 2665,
3754
+ "num_input_tokens_seen": 0,
3755
+ "num_train_epochs": 5,
3756
+ "save_steps": 100,
3757
+ "total_flos": 2.0317707214423327e+18,
3758
+ "train_batch_size": 2,
3759
+ "trial_name": null,
3760
+ "trial_params": null
3761
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36289ea5a4fbf3435fed2235994173558fed7918791a2daed3ca5b9cdad23860
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff