Hugging Face's logo

Ogamon
/
llama3_inst_truthbench1_model

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Ogamon commited on
Commit
77862cc
•
1 Parent(s): 5d13203

second commit

Browse files
Files changed (7) hide show
  1. all_results.json +7 -7
  2. generated_predictions.jsonl +0 -0
  3. llamaboard_config.yaml +12 -57
  4. predict_results.json +9 -0
  5. running_log.txt +86 -544
  6. trainer_log.jsonl +15 -191
  7. training_args.yaml +9 -21
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 4.887459807073955,
3
- "num_input_tokens_seen": 1208400,
4
- "total_flos": 5.441370708980531e+16,
5
- "train_loss": 0.5078434096239538,
6
- "train_runtime": 2571.1298,
7
- "train_samples_per_second": 9.661,
8
- "train_steps_per_second": 0.074
9
  }
 
1
  {
2
+ "predict_bleu-4": 88.09424799679488,
3
+ "predict_rouge-1": 95.67307692307692,
4
+ "predict_rouge-2": 0.0,
5
+ "predict_rouge-l": 95.67307692307692,
6
+ "predict_runtime": 9.3909,
7
+ "predict_samples_per_second": 132.363,
8
+ "predict_steps_per_second": 8.306
9
  }
generated_predictions.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
llamaboard_config.yaml CHANGED
@@ -1,5 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
1
  top.booster: auto
2
- top.checkpoint_path: null
3
  top.finetuning_type: full
4
  top.model_name: LLaMA3-8B-Chat
5
  top.quantization_bit: none
@@ -7,59 +18,3 @@ top.quantization_method: bitsandbytes
7
  top.rope_scaling: none
8
  top.template: llama3
9
  top.visual_inputs: false
10
- train.additional_target: ''
11
- train.badam_mode: layer
12
- train.badam_switch_interval: 50
13
- train.badam_switch_mode: ascending
14
- train.badam_update_ratio: 0.05
15
- train.batch_size: 2
16
- train.compute_type: bf16
17
- train.create_new_adapter: false
18
- train.cutoff_len: 1024
19
- train.dataset:
20
- - truth_train_0716
21
- train.dataset_dir: data
22
- train.ds_offload: false
23
- train.ds_stage: '2'
24
- train.freeze_extra_modules: ''
25
- train.freeze_trainable_layers: 2
26
- train.freeze_trainable_modules: all
27
- train.galore_rank: 16
28
- train.galore_scale: 0.25
29
- train.galore_target: all
30
- train.galore_update_interval: 200
31
- train.gradient_accumulation_steps: 8
32
- train.learning_rate: 5e-6
33
- train.logging_steps: 1
34
- train.lora_alpha: 16
35
- train.lora_dropout: 0
36
- train.lora_rank: 8
37
- train.lora_target: ''
38
- train.loraplus_lr_ratio: 0
39
- train.lr_scheduler_type: cosine
40
- train.max_grad_norm: '1.0'
41
- train.max_samples: '100000'
42
- train.neat_packing: false
43
- train.neftune_alpha: 0
44
- train.num_train_epochs: '5.0'
45
- train.optim: adamw_torch
46
- train.packing: false
47
- train.ppo_score_norm: false
48
- train.ppo_whiten_rewards: false
49
- train.pref_beta: 0.1
50
- train.pref_ftx: 0
51
- train.pref_loss: sigmoid
52
- train.report_to: false
53
- train.resize_vocab: false
54
- train.reward_model: null
55
- train.save_steps: 1000
56
- train.shift_attn: false
57
- train.training_stage: Supervised Fine-Tuning
58
- train.use_badam: false
59
- train.use_dora: false
60
- train.use_galore: false
61
- train.use_llama_pro: false
62
- train.use_pissa: false
63
- train.use_rslora: false
64
- train.val_size: 0
65
- train.warmup_steps: 10
 
1
+ eval.batch_size: 2
2
+ eval.cutoff_len: 1024
3
+ eval.dataset:
4
+ - truth_dev_0716
5
+ eval.dataset_dir: data
6
+ eval.max_new_tokens: 512
7
+ eval.max_samples: '100000'
8
+ eval.output_dir: eval_2024-07-23-06-52-5_llama3
9
+ eval.predict: true
10
+ eval.temperature: 0.95
11
+ eval.top_p: 0.7
12
  top.booster: auto
13
+ top.checkpoint_path: train_2024-07-23-06-00-05_llama3
14
  top.finetuning_type: full
15
  top.model_name: LLaMA3-8B-Chat
16
  top.quantization_bit: none
 
18
  top.rope_scaling: none
19
  top.template: llama3
20
  top.visual_inputs: false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu-4": 88.09424799679488,
3
+ "predict_rouge-1": 95.67307692307692,
4
+ "predict_rouge-2": 0.0,
5
+ "predict_rouge-l": 95.67307692307692,
6
+ "predict_runtime": 9.3909,
7
+ "predict_samples_per_second": 132.363,
8
+ "predict_steps_per_second": 8.306
9
+ }
running_log.txt CHANGED
@@ -1,95 +1,79 @@
1
- 07/23/2024 06:01:17 - INFO - llamafactory.hparams.parser - Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
2
 
3
- 07/23/2024 06:01:17 - INFO - llamafactory.hparams.parser - Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
4
 
5
- [INFO|parser.py:325] 2024-07-23 06:01:17,828 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
6
 
7
- 07/23/2024 06:01:17 - INFO - llamafactory.hparams.parser - Process rank: 7, device: cuda:7, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
8
 
9
- 07/23/2024 06:01:17 - INFO - llamafactory.hparams.parser - Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
10
 
11
- 07/23/2024 06:01:17 - INFO - llamafactory.hparams.parser - Process rank: 6, device: cuda:6, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
12
 
13
- 07/23/2024 06:01:17 - INFO - llamafactory.hparams.parser - Process rank: 2, device: cuda:2, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
14
 
15
- [INFO|tokenization_utils_base.py:2161] 2024-07-23 06:01:18,017 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/tokenizer.json
16
 
17
- 07/23/2024 06:01:18 - INFO - llamafactory.hparams.parser - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
18
 
19
- 07/23/2024 06:01:18 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
20
 
21
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
22
 
23
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
24
 
25
- 07/23/2024 06:01:18 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
26
 
27
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
28
 
29
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
30
 
31
- 07/23/2024 06:01:18 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
32
 
33
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
34
 
35
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
36
 
37
- [INFO|tokenization_utils_base.py:2161] 2024-07-23 06:01:18,017 >> loading file added_tokens.json from cache at None
38
 
39
- [INFO|tokenization_utils_base.py:2161] 2024-07-23 06:01:18,017 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/special_tokens_map.json
40
 
41
- [INFO|tokenization_utils_base.py:2161] 2024-07-23 06:01:18,017 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/tokenizer_config.json
42
 
43
- [WARNING|logging.py:313] 2024-07-23 06:01:18,315 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
44
 
45
- [INFO|template.py:270] 2024-07-23 06:01:18,316 >> Replace eos token: <|eot_id|>
46
 
47
- [INFO|template.py:372] 2024-07-23 06:01:18,316 >> Add pad token: <|eot_id|>
48
 
49
- [INFO|loader.py:50] 2024-07-23 06:01:18,317 >> Loading dataset 0716_truthfulqa_benchmark_train.json...
50
 
51
- 07/23/2024 06:01:18 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
52
 
53
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
54
 
55
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
56
 
57
- 07/23/2024 06:01:18 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
58
 
59
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
60
 
61
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
62
 
63
- 07/23/2024 06:01:18 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
64
 
65
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
66
 
67
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
68
 
69
- 07/23/2024 06:01:18 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
70
 
71
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
72
 
73
- 07/23/2024 06:01:18 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
74
 
75
- 07/23/2024 06:01:19 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
76
-
77
- 07/23/2024 06:01:19 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
78
-
79
- 07/23/2024 06:01:19 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
80
-
81
- 07/23/2024 06:01:19 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
82
-
83
- 07/23/2024 06:01:19 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
84
-
85
- 07/23/2024 06:01:19 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
86
-
87
- 07/23/2024 06:01:19 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
88
-
89
- [INFO|configuration_utils.py:733] 2024-07-23 06:01:20,503 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/config.json
90
-
91
- [INFO|configuration_utils.py:800] 2024-07-23 06:01:20,505 >> Model config LlamaConfig {
92
- "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
93
  "architectures": [
94
  "LlamaForCausalLM"
95
  ],
@@ -114,48 +98,46 @@
114
  "tie_word_embeddings": false,
115
  "torch_dtype": "bfloat16",
116
  "transformers_version": "4.42.3",
117
- "use_cache": true,
118
  "vocab_size": 128256
119
  }
120
 
121
 
122
- [INFO|modeling_utils.py:3556] 2024-07-23 06:01:20,536 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/model.safetensors.index.json
123
 
124
- [INFO|modeling_utils.py:1531] 2024-07-23 06:01:20,537 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
125
 
126
- [INFO|configuration_utils.py:1000] 2024-07-23 06:01:20,541 >> Generate config GenerationConfig {
 
 
127
  "bos_token_id": 128000,
128
  "eos_token_id": 128009
129
  }
130
 
131
 
132
- [INFO|modeling_utils.py:4364] 2024-07-23 06:01:24,381 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
133
-
134
-
135
- [INFO|modeling_utils.py:4372] 2024-07-23 06:01:24,382 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at meta-llama/Meta-Llama-3-8B-Instruct.
136
- If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
137
 
138
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
139
 
140
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
141
 
142
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
143
 
144
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
145
 
146
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
147
 
148
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
149
 
150
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
151
 
152
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
153
 
154
- 07/23/2024 06:01:24 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
 
155
 
156
- [INFO|configuration_utils.py:955] 2024-07-23 06:01:24,557 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/generation_config.json
157
 
158
- [INFO|configuration_utils.py:1000] 2024-07-23 06:01:24,557 >> Generate config GenerationConfig {
159
  "bos_token_id": 128000,
160
  "do_sample": true,
161
  "eos_token_id": [
@@ -168,500 +150,60 @@ If your task is similar to the task the model of the checkpoint was trained on,
168
  }
169
 
170
 
171
- 07/23/2024 06:01:24 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
172
-
173
- [INFO|checkpointing.py:103] 2024-07-23 06:01:24,565 >> Gradient checkpointing enabled.
174
-
175
- [INFO|attention.py:80] 2024-07-23 06:01:24,565 >> Using torch SDPA for faster training and inference.
176
-
177
- [INFO|adapter.py:302] 2024-07-23 06:01:24,565 >> Upcasting trainable params to float32.
178
-
179
- [INFO|adapter.py:48] 2024-07-23 06:01:24,565 >> Fine-tuning method: Full
180
-
181
- [INFO|loader.py:196] 2024-07-23 06:01:24,607 >> trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
182
-
183
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
184
-
185
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
186
-
187
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
188
-
189
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
190
-
191
- 07/23/2024 06:01:24 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
192
-
193
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
194
-
195
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
196
-
197
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
198
-
199
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
200
-
201
- 07/23/2024 06:01:24 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
202
-
203
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
204
-
205
- 07/23/2024 06:01:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
206
-
207
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
208
-
209
- 07/23/2024 06:01:24 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
210
-
211
- 07/23/2024 06:01:24 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
212
-
213
- [INFO|trainer.py:642] 2024-07-23 06:01:24,612 >> Using auto half precision backend
214
-
215
- 07/23/2024 06:01:25 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
216
-
217
- 07/23/2024 06:01:25 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
218
-
219
- 07/23/2024 06:01:25 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
220
-
221
- 07/23/2024 06:01:25 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
222
-
223
- 07/23/2024 06:01:25 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
224
-
225
- 07/23/2024 06:01:25 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
226
-
227
- 07/23/2024 06:01:25 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
228
-
229
- 07/23/2024 06:01:25 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
230
-
231
- 07/23/2024 06:01:25 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
232
-
233
- 07/23/2024 06:01:25 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
234
-
235
- [INFO|trainer.py:2128] 2024-07-23 06:01:47,813 >> ***** Running training *****
236
-
237
- [INFO|trainer.py:2129] 2024-07-23 06:01:47,813 >> Num examples = 4,968
238
-
239
- [INFO|trainer.py:2130] 2024-07-23 06:01:47,814 >> Num Epochs = 5
240
-
241
- [INFO|trainer.py:2131] 2024-07-23 06:01:47,814 >> Instantaneous batch size per device = 2
242
-
243
- [INFO|trainer.py:2134] 2024-07-23 06:01:47,814 >> Total train batch size (w. parallel, distributed & accumulation) = 128
244
-
245
- [INFO|trainer.py:2135] 2024-07-23 06:01:47,814 >> Gradient Accumulation steps = 8
246
-
247
- [INFO|trainer.py:2136] 2024-07-23 06:01:47,814 >> Total optimization steps = 190
248
-
249
- [INFO|trainer.py:2137] 2024-07-23 06:01:47,815 >> Number of trainable parameters = 8,030,261,248
250
-
251
- [INFO|callbacks.py:310] 2024-07-23 06:02:03,431 >> {'loss': 14.1364, 'learning_rate': 5.0000e-07, 'epoch': 0.03, 'throughput': 417.05}
252
-
253
- [INFO|callbacks.py:310] 2024-07-23 06:02:16,666 >> {'loss': 13.7804, 'learning_rate': 1.0000e-06, 'epoch': 0.05, 'throughput': 445.34}
254
-
255
- [INFO|callbacks.py:310] 2024-07-23 06:02:29,887 >> {'loss': 13.4871, 'learning_rate': 1.5000e-06, 'epoch': 0.08, 'throughput': 457.52}
256
-
257
- [INFO|callbacks.py:310] 2024-07-23 06:02:43,112 >> {'loss': 12.7900, 'learning_rate': 2.0000e-06, 'epoch': 0.10, 'throughput': 458.34}
258
-
259
- [INFO|callbacks.py:310] 2024-07-23 06:02:56,320 >> {'loss': 9.2748, 'learning_rate': 2.5000e-06, 'epoch': 0.13, 'throughput': 466.66}
260
-
261
- [INFO|callbacks.py:310] 2024-07-23 06:03:09,521 >> {'loss': 6.5585, 'learning_rate': 3.0000e-06, 'epoch': 0.15, 'throughput': 467.05}
262
-
263
- [INFO|callbacks.py:310] 2024-07-23 06:03:22,727 >> {'loss': 5.3984, 'learning_rate': 3.5000e-06, 'epoch': 0.18, 'throughput': 465.11}
264
-
265
- [INFO|callbacks.py:310] 2024-07-23 06:03:35,927 >> {'loss': 1.9363, 'learning_rate': 4.0000e-06, 'epoch': 0.21, 'throughput': 466.48}
266
-
267
- [INFO|callbacks.py:310] 2024-07-23 06:03:49,137 >> {'loss': 0.6783, 'learning_rate': 4.5000e-06, 'epoch': 0.23, 'throughput': 469.24}
268
-
269
- [INFO|callbacks.py:310] 2024-07-23 06:04:02,342 >> {'loss': 2.9945, 'learning_rate': 5.0000e-06, 'epoch': 0.26, 'throughput': 470.87}
270
-
271
- [INFO|callbacks.py:310] 2024-07-23 06:04:15,544 >> {'loss': 0.2916, 'learning_rate': 4.9996e-06, 'epoch': 0.28, 'throughput': 470.92}
272
-
273
- [INFO|callbacks.py:310] 2024-07-23 06:04:28,766 >> {'loss': 2.2775, 'learning_rate': 4.9985e-06, 'epoch': 0.31, 'throughput': 471.10}
274
-
275
- [INFO|callbacks.py:310] 2024-07-23 06:04:41,974 >> {'loss': 0.3757, 'learning_rate': 4.9966e-06, 'epoch': 0.33, 'throughput': 471.76}
276
-
277
- [INFO|callbacks.py:310] 2024-07-23 06:04:55,162 >> {'loss': 1.9543, 'learning_rate': 4.9939e-06, 'epoch': 0.36, 'throughput': 473.05}
278
-
279
- [INFO|callbacks.py:310] 2024-07-23 06:05:08,380 >> {'loss': 0.7398, 'learning_rate': 4.9905e-06, 'epoch': 0.39, 'throughput': 472.67}
280
-
281
- [INFO|callbacks.py:310] 2024-07-23 06:05:21,579 >> {'loss': 1.1868, 'learning_rate': 4.9863e-06, 'epoch': 0.41, 'throughput': 474.17}
282
-
283
- [INFO|callbacks.py:310] 2024-07-23 06:05:34,789 >> {'loss': 0.5418, 'learning_rate': 4.9814e-06, 'epoch': 0.44, 'throughput': 473.57}
284
-
285
- [INFO|callbacks.py:310] 2024-07-23 06:05:47,979 >> {'loss': 0.2263, 'learning_rate': 4.9757e-06, 'epoch': 0.46, 'throughput': 474.35}
286
-
287
- [INFO|callbacks.py:310] 2024-07-23 06:06:01,181 >> {'loss': 0.1612, 'learning_rate': 4.9692e-06, 'epoch': 0.49, 'throughput': 475.02}
288
-
289
- [INFO|callbacks.py:310] 2024-07-23 06:06:14,390 >> {'loss': 0.3299, 'learning_rate': 4.9620e-06, 'epoch': 0.51, 'throughput': 475.97}
290
-
291
- [INFO|callbacks.py:310] 2024-07-23 06:06:27,596 >> {'loss': 0.2013, 'learning_rate': 4.9541e-06, 'epoch': 0.54, 'throughput': 476.60}
292
-
293
- [INFO|callbacks.py:310] 2024-07-23 06:06:40,782 >> {'loss': 0.2446, 'learning_rate': 4.9454e-06, 'epoch': 0.57, 'throughput': 477.00}
294
-
295
- [INFO|callbacks.py:310] 2024-07-23 06:06:53,988 >> {'loss': 0.2235, 'learning_rate': 4.9359e-06, 'epoch': 0.59, 'throughput': 477.33}
296
-
297
- [INFO|callbacks.py:310] 2024-07-23 06:07:07,195 >> {'loss': 0.1160, 'learning_rate': 4.9257e-06, 'epoch': 0.62, 'throughput': 476.68}
298
-
299
- [INFO|callbacks.py:310] 2024-07-23 06:07:20,384 >> {'loss': 0.2179, 'learning_rate': 4.9148e-06, 'epoch': 0.64, 'throughput': 476.63}
300
-
301
- [INFO|callbacks.py:310] 2024-07-23 06:07:33,580 >> {'loss': 0.1414, 'learning_rate': 4.9032e-06, 'epoch': 0.67, 'throughput': 476.58}
302
-
303
- [INFO|callbacks.py:310] 2024-07-23 06:07:46,768 >> {'loss': 0.1181, 'learning_rate': 4.8908e-06, 'epoch': 0.69, 'throughput': 477.26}
304
-
305
- [INFO|callbacks.py:310] 2024-07-23 06:07:59,974 >> {'loss': 0.2753, 'learning_rate': 4.8776e-06, 'epoch': 0.72, 'throughput': 477.91}
306
-
307
- [INFO|callbacks.py:310] 2024-07-23 06:08:13,168 >> {'loss': 0.3255, 'learning_rate': 4.8638e-06, 'epoch': 0.75, 'throughput': 478.44}
308
-
309
- [INFO|callbacks.py:310] 2024-07-23 06:08:26,364 >> {'loss': 0.2352, 'learning_rate': 4.8492e-06, 'epoch': 0.77, 'throughput': 479.06}
310
-
311
- [INFO|callbacks.py:310] 2024-07-23 06:08:39,564 >> {'loss': 0.0630, 'learning_rate': 4.8340e-06, 'epoch': 0.80, 'throughput': 479.01}
312
-
313
- [INFO|callbacks.py:310] 2024-07-23 06:08:52,759 >> {'loss': 0.2042, 'learning_rate': 4.8180e-06, 'epoch': 0.82, 'throughput': 479.09}
314
-
315
- [INFO|callbacks.py:310] 2024-07-23 06:09:05,957 >> {'loss': 0.1364, 'learning_rate': 4.8013e-06, 'epoch': 0.85, 'throughput': 479.59}
316
-
317
- [INFO|callbacks.py:310] 2024-07-23 06:09:19,151 >> {'loss': 0.0934, 'learning_rate': 4.7839e-06, 'epoch': 0.87, 'throughput': 479.71}
318
-
319
- [INFO|callbacks.py:310] 2024-07-23 06:09:32,336 >> {'loss': 0.1332, 'learning_rate': 4.7658e-06, 'epoch': 0.90, 'throughput': 479.91}
320
-
321
- [INFO|callbacks.py:310] 2024-07-23 06:09:45,527 >> {'loss': 0.1595, 'learning_rate': 4.7470e-06, 'epoch': 0.93, 'throughput': 479.86}
322
-
323
- [INFO|callbacks.py:310] 2024-07-23 06:09:58,740 >> {'loss': 0.1528, 'learning_rate': 4.7275e-06, 'epoch': 0.95, 'throughput': 480.07}
324
-
325
- [INFO|callbacks.py:310] 2024-07-23 06:10:11,945 >> {'loss': 0.1342, 'learning_rate': 4.7074e-06, 'epoch': 0.98, 'throughput': 480.42}
326
-
327
- [INFO|callbacks.py:310] 2024-07-23 06:10:25,143 >> {'loss': 0.1586, 'learning_rate': 4.6865e-06, 'epoch': 1.00, 'throughput': 480.69}
328
-
329
- [INFO|callbacks.py:310] 2024-07-23 06:10:38,337 >> {'loss': 0.1072, 'learning_rate': 4.6651e-06, 'epoch': 1.03, 'throughput': 480.80}
330
-
331
- [INFO|callbacks.py:310] 2024-07-23 06:10:51,540 >> {'loss': 0.0357, 'learning_rate': 4.6429e-06, 'epoch': 1.05, 'throughput': 481.10}
332
-
333
- [INFO|callbacks.py:310] 2024-07-23 06:11:04,729 >> {'loss': 0.0600, 'learning_rate': 4.6201e-06, 'epoch': 1.08, 'throughput': 481.28}
334
-
335
- [INFO|callbacks.py:310] 2024-07-23 06:11:17,926 >> {'loss': 0.0902, 'learning_rate': 4.5967e-06, 'epoch': 1.11, 'throughput': 481.59}
336
-
337
- [INFO|callbacks.py:310] 2024-07-23 06:11:31,117 >> {'loss': 0.0202, 'learning_rate': 4.5726e-06, 'epoch': 1.13, 'throughput': 481.67}
338
-
339
- [INFO|callbacks.py:310] 2024-07-23 06:11:44,319 >> {'loss': 0.0380, 'learning_rate': 4.5479e-06, 'epoch': 1.16, 'throughput': 481.31}
340
-
341
- [INFO|callbacks.py:310] 2024-07-23 06:11:57,513 >> {'loss': 0.0379, 'learning_rate': 4.5225e-06, 'epoch': 1.18, 'throughput': 481.42}
342
-
343
- [INFO|callbacks.py:310] 2024-07-23 06:12:10,721 >> {'loss': 0.0742, 'learning_rate': 4.4966e-06, 'epoch': 1.21, 'throughput': 481.51}
344
-
345
- [INFO|callbacks.py:310] 2024-07-23 06:12:23,931 >> {'loss': 0.0658, 'learning_rate': 4.4700e-06, 'epoch': 1.23, 'throughput': 480.94}
346
-
347
- [INFO|callbacks.py:310] 2024-07-23 06:12:37,136 >> {'loss': 0.0336, 'learning_rate': 4.4429e-06, 'epoch': 1.26, 'throughput': 481.32}
348
-
349
- [INFO|callbacks.py:310] 2024-07-23 06:12:50,333 >> {'loss': 0.1021, 'learning_rate': 4.4151e-06, 'epoch': 1.29, 'throughput': 481.12}
350
-
351
- [INFO|callbacks.py:310] 2024-07-23 06:13:03,531 >> {'loss': 0.1312, 'learning_rate': 4.3868e-06, 'epoch': 1.31, 'throughput': 481.10}
352
-
353
- [INFO|callbacks.py:310] 2024-07-23 06:13:16,740 >> {'loss': 0.0665, 'learning_rate': 4.3579e-06, 'epoch': 1.34, 'throughput': 481.08}
354
-
355
- [INFO|callbacks.py:310] 2024-07-23 06:13:29,940 >> {'loss': 0.0679, 'learning_rate': 4.3284e-06, 'epoch': 1.36, 'throughput': 481.08}
356
-
357
- [INFO|callbacks.py:310] 2024-07-23 06:13:43,136 >> {'loss': 0.0579, 'learning_rate': 4.2983e-06, 'epoch': 1.39, 'throughput': 480.90}
358
-
359
- [INFO|callbacks.py:310] 2024-07-23 06:13:56,338 >> {'loss': 0.0542, 'learning_rate': 4.2678e-06, 'epoch': 1.41, 'throughput': 481.15}
360
-
361
- [INFO|callbacks.py:310] 2024-07-23 06:14:09,544 >> {'loss': 0.0476, 'learning_rate': 4.2366e-06, 'epoch': 1.44, 'throughput': 481.17}
362
-
363
- [INFO|callbacks.py:310] 2024-07-23 06:14:22,733 >> {'loss': 0.0613, 'learning_rate': 4.2050e-06, 'epoch': 1.47, 'throughput': 481.35}
364
-
365
- [INFO|callbacks.py:310] 2024-07-23 06:14:35,924 >> {'loss': 0.0995, 'learning_rate': 4.1728e-06, 'epoch': 1.49, 'throughput': 481.29}
366
-
367
- [INFO|callbacks.py:310] 2024-07-23 06:14:49,119 >> {'loss': 0.0532, 'learning_rate': 4.1401e-06, 'epoch': 1.52, 'throughput': 481.12}
368
-
369
- [INFO|callbacks.py:310] 2024-07-23 06:15:02,320 >> {'loss': 0.0824, 'learning_rate': 4.1070e-06, 'epoch': 1.54, 'throughput': 481.19}
370
-
371
- [INFO|callbacks.py:310] 2024-07-23 06:15:15,504 >> {'loss': 0.0499, 'learning_rate': 4.0733e-06, 'epoch': 1.57, 'throughput': 481.24}
372
-
373
- [INFO|callbacks.py:310] 2024-07-23 06:15:28,693 >> {'loss': 0.0413, 'learning_rate': 4.0392e-06, 'epoch': 1.59, 'throughput': 481.38}
374
-
375
- [INFO|callbacks.py:310] 2024-07-23 06:15:41,892 >> {'loss': 0.0637, 'learning_rate': 4.0045e-06, 'epoch': 1.62, 'throughput': 481.64}
376
-
377
- [INFO|callbacks.py:310] 2024-07-23 06:15:55,095 >> {'loss': 0.0529, 'learning_rate': 3.9695e-06, 'epoch': 1.65, 'throughput': 481.43}
378
-
379
- [INFO|callbacks.py:310] 2024-07-23 06:16:08,283 >> {'loss': 0.0474, 'learning_rate': 3.9339e-06, 'epoch': 1.67, 'throughput': 481.41}
380
-
381
- [INFO|callbacks.py:310] 2024-07-23 06:16:21,469 >> {'loss': 0.0649, 'learning_rate': 3.8980e-06, 'epoch': 1.70, 'throughput': 481.25}
382
-
383
- [INFO|callbacks.py:310] 2024-07-23 06:16:34,678 >> {'loss': 0.0505, 'learning_rate': 3.8616e-06, 'epoch': 1.72, 'throughput': 481.23}
384
-
385
- [INFO|callbacks.py:310] 2024-07-23 06:16:47,877 >> {'loss': 0.0621, 'learning_rate': 3.8248e-06, 'epoch': 1.75, 'throughput': 480.87}
386
-
387
- [INFO|callbacks.py:310] 2024-07-23 06:17:01,073 >> {'loss': 0.0769, 'learning_rate': 3.7876e-06, 'epoch': 1.77, 'throughput': 480.95}
388
-
389
- [INFO|callbacks.py:310] 2024-07-23 06:17:14,279 >> {'loss': 0.0435, 'learning_rate': 3.7500e-06, 'epoch': 1.80, 'throughput': 481.18}
390
-
391
- [INFO|callbacks.py:310] 2024-07-23 06:17:27,460 >> {'loss': 0.0673, 'learning_rate': 3.7120e-06, 'epoch': 1.83, 'throughput': 481.46}
392
-
393
- [INFO|callbacks.py:310] 2024-07-23 06:17:40,664 >> {'loss': 0.1316, 'learning_rate': 3.6737e-06, 'epoch': 1.85, 'throughput': 481.22}
394
-
395
- [INFO|callbacks.py:310] 2024-07-23 06:17:53,859 >> {'loss': 0.0531, 'learning_rate': 3.6350e-06, 'epoch': 1.88, 'throughput': 481.32}
396
-
397
- [INFO|callbacks.py:310] 2024-07-23 06:18:07,061 >> {'loss': 0.0287, 'learning_rate': 3.5959e-06, 'epoch': 1.90, 'throughput': 481.43}
398
-
399
- [INFO|callbacks.py:310] 2024-07-23 06:18:20,271 >> {'loss': 0.0648, 'learning_rate': 3.5565e-06, 'epoch': 1.93, 'throughput': 481.41}
400
-
401
- [INFO|callbacks.py:310] 2024-07-23 06:18:33,470 >> {'loss': 0.1211, 'learning_rate': 3.5168e-06, 'epoch': 1.95, 'throughput': 481.37}
402
-
403
- [INFO|callbacks.py:310] 2024-07-23 06:18:46,678 >> {'loss': 0.0879, 'learning_rate': 3.4768e-06, 'epoch': 1.98, 'throughput': 481.10}
404
-
405
- [INFO|callbacks.py:310] 2024-07-23 06:18:59,891 >> {'loss': 0.0227, 'learning_rate': 3.4365e-06, 'epoch': 2.01, 'throughput': 481.24}
406
-
407
- [INFO|callbacks.py:310] 2024-07-23 06:19:13,093 >> {'loss': 0.0228, 'learning_rate': 3.3959e-06, 'epoch': 2.03, 'throughput': 481.30}
408
-
409
- [INFO|callbacks.py:310] 2024-07-23 06:19:26,288 >> {'loss': 0.0360, 'learning_rate': 3.3551e-06, 'epoch': 2.06, 'throughput': 481.33}
410
-
411
- [INFO|callbacks.py:310] 2024-07-23 06:19:39,500 >> {'loss': 0.0138, 'learning_rate': 3.3139e-06, 'epoch': 2.08, 'throughput': 481.23}
412
-
413
- [INFO|callbacks.py:310] 2024-07-23 06:19:52,712 >> {'loss': 0.0697, 'learning_rate': 3.2725e-06, 'epoch': 2.11, 'throughput': 481.06}
414
-
415
- [INFO|callbacks.py:310] 2024-07-23 06:20:05,915 >> {'loss': 0.0508, 'learning_rate': 3.2309e-06, 'epoch': 2.14, 'throughput': 480.79}
416
-
417
- [INFO|callbacks.py:310] 2024-07-23 06:20:19,109 >> {'loss': 0.0088, 'learning_rate': 3.1891e-06, 'epoch': 2.16, 'throughput': 481.08}
418
-
419
- [INFO|callbacks.py:310] 2024-07-23 06:20:32,308 >> {'loss': 0.0158, 'learning_rate': 3.1470e-06, 'epoch': 2.19, 'throughput': 481.26}
420
-
421
- [INFO|callbacks.py:310] 2024-07-23 06:20:45,510 >> {'loss': 0.0060, 'learning_rate': 3.1048e-06, 'epoch': 2.21, 'throughput': 481.23}
422
-
423
- [INFO|callbacks.py:310] 2024-07-23 06:20:58,705 >> {'loss': 0.0380, 'learning_rate': 3.0624e-06, 'epoch': 2.24, 'throughput': 481.60}
424
-
425
- [INFO|callbacks.py:310] 2024-07-23 06:21:11,910 >> {'loss': 0.0004, 'learning_rate': 3.0198e-06, 'epoch': 2.26, 'throughput': 481.51}
426
-
427
- [INFO|callbacks.py:310] 2024-07-23 06:21:25,109 >> {'loss': 0.0111, 'learning_rate': 2.9770e-06, 'epoch': 2.29, 'throughput': 481.43}
428
-
429
- [INFO|callbacks.py:310] 2024-07-23 06:21:38,303 >> {'loss': 0.0008, 'learning_rate': 2.9341e-06, 'epoch': 2.32, 'throughput': 481.60}
430
-
431
- [INFO|callbacks.py:310] 2024-07-23 06:21:51,491 >> {'loss': 0.0182, 'learning_rate': 2.8911e-06, 'epoch': 2.34, 'throughput': 481.67}
432
-
433
- [INFO|callbacks.py:310] 2024-07-23 06:22:04,691 >> {'loss': 0.0491, 'learning_rate': 2.8479e-06, 'epoch': 2.37, 'throughput': 481.64}
434
-
435
- [INFO|callbacks.py:310] 2024-07-23 06:22:17,877 >> {'loss': 0.0040, 'learning_rate': 2.8047e-06, 'epoch': 2.39, 'throughput': 481.71}
436
-
437
- [INFO|callbacks.py:310] 2024-07-23 06:22:31,075 >> {'loss': 0.0176, 'learning_rate': 2.7613e-06, 'epoch': 2.42, 'throughput': 481.77}
438
-
439
- [INFO|callbacks.py:310] 2024-07-23 06:22:44,264 >> {'loss': 0.0190, 'learning_rate': 2.7179e-06, 'epoch': 2.44, 'throughput': 481.70}
440
-
441
- [INFO|callbacks.py:310] 2024-07-23 06:22:57,479 >> {'loss': 0.0270, 'learning_rate': 2.6744e-06, 'epoch': 2.47, 'throughput': 481.50}
442
-
443
- [INFO|callbacks.py:310] 2024-07-23 06:23:10,686 >> {'loss': 0.0354, 'learning_rate': 2.6308e-06, 'epoch': 2.50, 'throughput': 481.51}
444
-
445
- [INFO|callbacks.py:310] 2024-07-23 06:23:23,876 >> {'loss': 0.0741, 'learning_rate': 2.5872e-06, 'epoch': 2.52, 'throughput': 481.62}
446
-
447
- [INFO|callbacks.py:310] 2024-07-23 06:23:37,082 >> {'loss': 0.0582, 'learning_rate': 2.5436e-06, 'epoch': 2.55, 'throughput': 481.56}
448
-
449
- [INFO|callbacks.py:310] 2024-07-23 06:23:50,275 >> {'loss': 0.0096, 'learning_rate': 2.5000e-06, 'epoch': 2.57, 'throughput': 481.71}
450
-
451
- [INFO|callbacks.py:310] 2024-07-23 06:24:03,470 >> {'loss': 0.0263, 'learning_rate': 2.4564e-06, 'epoch': 2.60, 'throughput': 481.77}
452
-
453
- [INFO|callbacks.py:310] 2024-07-23 06:24:16,658 >> {'loss': 0.0121, 'learning_rate': 2.4128e-06, 'epoch': 2.62, 'throughput': 481.72}
454
-
455
- [INFO|callbacks.py:310] 2024-07-23 06:24:29,856 >> {'loss': 0.0204, 'learning_rate': 2.3692e-06, 'epoch': 2.65, 'throughput': 481.70}
456
-
457
- [INFO|callbacks.py:310] 2024-07-23 06:24:43,053 >> {'loss': 0.0325, 'learning_rate': 2.3256e-06, 'epoch': 2.68, 'throughput': 481.83}
458
-
459
- [INFO|callbacks.py:310] 2024-07-23 06:24:56,246 >> {'loss': 0.0076, 'learning_rate': 2.2821e-06, 'epoch': 2.70, 'throughput': 481.67}
460
-
461
- [INFO|callbacks.py:310] 2024-07-23 06:25:09,456 >> {'loss': 0.0485, 'learning_rate': 2.2387e-06, 'epoch': 2.73, 'throughput': 481.57}
462
-
463
- [INFO|callbacks.py:310] 2024-07-23 06:25:22,661 >> {'loss': 0.0070, 'learning_rate': 2.1953e-06, 'epoch': 2.75, 'throughput': 481.41}
464
-
465
- [INFO|callbacks.py:310] 2024-07-23 06:25:35,871 >> {'loss': 0.0347, 'learning_rate': 2.1521e-06, 'epoch': 2.78, 'throughput': 481.34}
466
-
467
- [INFO|callbacks.py:310] 2024-07-23 06:25:49,061 >> {'loss': 0.0142, 'learning_rate': 2.1089e-06, 'epoch': 2.80, 'throughput': 481.52}
468
-
469
- [INFO|callbacks.py:310] 2024-07-23 06:26:02,269 >> {'loss': 0.0414, 'learning_rate': 2.0659e-06, 'epoch': 2.83, 'throughput': 481.52}
470
-
471
- [INFO|callbacks.py:310] 2024-07-23 06:26:15,475 >> {'loss': 0.0419, 'learning_rate': 2.0230e-06, 'epoch': 2.86, 'throughput': 481.56}
472
-
473
- [INFO|callbacks.py:310] 2024-07-23 06:26:28,670 >> {'loss': 0.0430, 'learning_rate': 1.9802e-06, 'epoch': 2.88, 'throughput': 481.65}
474
-
475
- [INFO|callbacks.py:310] 2024-07-23 06:26:41,866 >> {'loss': 0.0192, 'learning_rate': 1.9376e-06, 'epoch': 2.91, 'throughput': 481.62}
476
-
477
- [INFO|callbacks.py:310] 2024-07-23 06:26:55,067 >> {'loss': 0.0427, 'learning_rate': 1.8952e-06, 'epoch': 2.93, 'throughput': 481.66}
478
-
479
- [INFO|callbacks.py:310] 2024-07-23 06:27:08,281 >> {'loss': 0.0116, 'learning_rate': 1.8530e-06, 'epoch': 2.96, 'throughput': 481.58}
480
-
481
- [INFO|callbacks.py:310] 2024-07-23 06:27:21,473 >> {'loss': 0.0135, 'learning_rate': 1.8109e-06, 'epoch': 2.98, 'throughput': 481.53}
482
-
483
- [INFO|callbacks.py:310] 2024-07-23 06:27:34,671 >> {'loss': 0.0128, 'learning_rate': 1.7691e-06, 'epoch': 3.01, 'throughput': 481.54}
484
-
485
- [INFO|callbacks.py:310] 2024-07-23 06:27:47,872 >> {'loss': 0.0021, 'learning_rate': 1.7275e-06, 'epoch': 3.04, 'throughput': 481.65}
486
-
487
- [INFO|callbacks.py:310] 2024-07-23 06:28:01,075 >> {'loss': 0.0057, 'learning_rate': 1.6861e-06, 'epoch': 3.06, 'throughput': 481.57}
488
-
489
- [INFO|callbacks.py:310] 2024-07-23 06:28:14,261 >> {'loss': 0.0197, 'learning_rate': 1.6449e-06, 'epoch': 3.09, 'throughput': 481.54}
490
-
491
- [INFO|callbacks.py:310] 2024-07-23 06:28:27,467 >> {'loss': 0.0017, 'learning_rate': 1.6041e-06, 'epoch': 3.11, 'throughput': 481.40}
492
-
493
- [INFO|callbacks.py:310] 2024-07-23 06:28:40,676 >> {'loss': 0.0068, 'learning_rate': 1.5635e-06, 'epoch': 3.14, 'throughput': 481.24}
494
-
495
- [INFO|callbacks.py:310] 2024-07-23 06:28:53,872 >> {'loss': 0.0022, 'learning_rate': 1.5232e-06, 'epoch': 3.16, 'throughput': 481.20}
496
-
497
- [INFO|callbacks.py:310] 2024-07-23 06:29:07,052 >> {'loss': 0.0162, 'learning_rate': 1.4832e-06, 'epoch': 3.19, 'throughput': 481.37}
498
-
499
- [INFO|callbacks.py:310] 2024-07-23 06:29:20,250 >> {'loss': 0.0014, 'learning_rate': 1.4435e-06, 'epoch': 3.22, 'throughput': 481.43}
500
-
501
- [INFO|callbacks.py:310] 2024-07-23 06:29:33,459 >> {'loss': 0.0063, 'learning_rate': 1.4041e-06, 'epoch': 3.24, 'throughput': 481.43}
502
-
503
- [INFO|callbacks.py:310] 2024-07-23 06:29:46,654 >> {'loss': 0.0282, 'learning_rate': 1.3650e-06, 'epoch': 3.27, 'throughput': 481.54}
504
-
505
- [INFO|callbacks.py:310] 2024-07-23 06:29:59,860 >> {'loss': 0.0003, 'learning_rate': 1.3263e-06, 'epoch': 3.29, 'throughput': 481.60}
506
-
507
- [INFO|callbacks.py:310] 2024-07-23 06:30:13,068 >> {'loss': 0.0002, 'learning_rate': 1.2880e-06, 'epoch': 3.32, 'throughput': 481.57}
508
-
509
- [INFO|callbacks.py:310] 2024-07-23 06:30:26,274 >> {'loss': 0.0004, 'learning_rate': 1.2500e-06, 'epoch': 3.34, 'throughput': 481.59}
510
-
511
- [INFO|callbacks.py:310] 2024-07-23 06:30:39,468 >> {'loss': 0.0169, 'learning_rate': 1.2124e-06, 'epoch': 3.37, 'throughput': 481.65}
512
-
513
- [INFO|callbacks.py:310] 2024-07-23 06:30:52,681 >> {'loss': 0.0127, 'learning_rate': 1.1752e-06, 'epoch': 3.40, 'throughput': 481.55}
514
-
515
- [INFO|callbacks.py:310] 2024-07-23 06:31:05,890 >> {'loss': 0.0045, 'learning_rate': 1.1384e-06, 'epoch': 3.42, 'throughput': 481.46}
516
-
517
- [INFO|callbacks.py:310] 2024-07-23 06:31:19,081 >> {'loss': 0.0924, 'learning_rate': 1.1020e-06, 'epoch': 3.45, 'throughput': 481.54}
518
-
519
- [INFO|callbacks.py:310] 2024-07-23 06:31:32,267 >> {'loss': 0.0067, 'learning_rate': 1.0661e-06, 'epoch': 3.47, 'throughput': 481.56}
520
-
521
- [INFO|callbacks.py:310] 2024-07-23 06:31:45,479 >> {'loss': 0.0030, 'learning_rate': 1.0305e-06, 'epoch': 3.50, 'throughput': 481.43}
522
-
523
- [INFO|callbacks.py:310] 2024-07-23 06:31:58,677 >> {'loss': 0.0164, 'learning_rate': 9.9546e-07, 'epoch': 3.52, 'throughput': 481.52}
524
-
525
- [INFO|callbacks.py:310] 2024-07-23 06:32:11,871 >> {'loss': 0.0018, 'learning_rate': 9.6085e-07, 'epoch': 3.55, 'throughput': 481.54}
526
-
527
- [INFO|callbacks.py:310] 2024-07-23 06:32:25,063 >> {'loss': 0.0226, 'learning_rate': 9.2670e-07, 'epoch': 3.58, 'throughput': 481.56}
528
-
529
- [INFO|callbacks.py:310] 2024-07-23 06:32:38,283 >> {'loss': 0.0008, 'learning_rate': 8.9303e-07, 'epoch': 3.60, 'throughput': 481.50}
530
-
531
- [INFO|callbacks.py:310] 2024-07-23 06:32:51,483 >> {'loss': 0.0004, 'learning_rate': 8.5985e-07, 'epoch': 3.63, 'throughput': 481.37}
532
-
533
- [INFO|callbacks.py:310] 2024-07-23 06:33:04,683 >> {'loss': 0.0008, 'learning_rate': 8.2717e-07, 'epoch': 3.65, 'throughput': 481.41}
534
-
535
- [INFO|callbacks.py:310] 2024-07-23 06:33:17,874 >> {'loss': 0.0256, 'learning_rate': 7.9500e-07, 'epoch': 3.68, 'throughput': 481.37}
536
-
537
- [INFO|callbacks.py:310] 2024-07-23 06:33:31,067 >> {'loss': 0.0005, 'learning_rate': 7.6335e-07, 'epoch': 3.70, 'throughput': 481.34}
538
-
539
- [INFO|callbacks.py:310] 2024-07-23 06:33:44,265 >> {'loss': 0.0045, 'learning_rate': 7.3223e-07, 'epoch': 3.73, 'throughput': 481.41}
540
-
541
- [INFO|callbacks.py:310] 2024-07-23 06:33:57,472 >> {'loss': 0.0005, 'learning_rate': 7.0165e-07, 'epoch': 3.76, 'throughput': 481.25}
542
-
543
- [INFO|callbacks.py:310] 2024-07-23 06:34:10,676 >> {'loss': 0.0069, 'learning_rate': 6.7162e-07, 'epoch': 3.78, 'throughput': 481.50}
544
-
545
- [INFO|callbacks.py:310] 2024-07-23 06:34:23,871 >> {'loss': 0.0150, 'learning_rate': 6.4214e-07, 'epoch': 3.81, 'throughput': 481.56}
546
-
547
- [INFO|callbacks.py:310] 2024-07-23 06:34:37,067 >> {'loss': 0.0012, 'learning_rate': 6.1323e-07, 'epoch': 3.83, 'throughput': 481.59}
548
-
549
- [INFO|callbacks.py:310] 2024-07-23 06:34:50,261 >> {'loss': 0.0095, 'learning_rate': 5.8489e-07, 'epoch': 3.86, 'throughput': 481.60}
550
-
551
- [INFO|callbacks.py:310] 2024-07-23 06:35:03,468 >> {'loss': 0.0271, 'learning_rate': 5.5714e-07, 'epoch': 3.88, 'throughput': 481.67}
552
-
553
- [INFO|callbacks.py:310] 2024-07-23 06:35:16,672 >> {'loss': 0.0201, 'learning_rate': 5.2997e-07, 'epoch': 3.91, 'throughput': 481.58}
554
-
555
- [INFO|callbacks.py:310] 2024-07-23 06:35:29,856 >> {'loss': 0.0120, 'learning_rate': 5.0341e-07, 'epoch': 3.94, 'throughput': 481.54}
556
-
557
- [INFO|callbacks.py:310] 2024-07-23 06:35:43,060 >> {'loss': 0.0230, 'learning_rate': 4.7746e-07, 'epoch': 3.96, 'throughput': 481.59}
558
-
559
- [INFO|callbacks.py:310] 2024-07-23 06:35:56,266 >> {'loss': 0.0156, 'learning_rate': 4.5212e-07, 'epoch': 3.99, 'throughput': 481.51}
560
-
561
- [INFO|callbacks.py:310] 2024-07-23 06:36:09,469 >> {'loss': 0.0009, 'learning_rate': 4.2741e-07, 'epoch': 4.01, 'throughput': 481.59}
562
-
563
- [INFO|callbacks.py:310] 2024-07-23 06:36:22,665 >> {'loss': 0.0017, 'learning_rate': 4.0332e-07, 'epoch': 4.04, 'throughput': 481.58}
564
-
565
- [INFO|callbacks.py:310] 2024-07-23 06:36:35,861 >> {'loss': 0.0015, 'learning_rate': 3.7988e-07, 'epoch': 4.06, 'throughput': 481.58}
566
-
567
- [INFO|callbacks.py:310] 2024-07-23 06:36:49,059 >> {'loss': 0.0035, 'learning_rate': 3.5708e-07, 'epoch': 4.09, 'throughput': 481.49}
568
-
569
- [INFO|callbacks.py:310] 2024-07-23 06:37:02,272 >> {'loss': 0.0016, 'learning_rate': 3.3494e-07, 'epoch': 4.12, 'throughput': 481.58}
570
-
571
- [INFO|callbacks.py:310] 2024-07-23 06:37:15,468 >> {'loss': 0.0028, 'learning_rate': 3.1345e-07, 'epoch': 4.14, 'throughput': 481.61}
572
-
573
- [INFO|callbacks.py:310] 2024-07-23 06:37:28,670 >> {'loss': 0.0006, 'learning_rate': 2.9263e-07, 'epoch': 4.17, 'throughput': 481.65}
574
-
575
- [INFO|callbacks.py:310] 2024-07-23 06:37:41,872 >> {'loss': 0.0013, 'learning_rate': 2.7248e-07, 'epoch': 4.19, 'throughput': 481.71}
576
-
577
- [INFO|callbacks.py:310] 2024-07-23 06:37:55,073 >> {'loss': 0.0006, 'learning_rate': 2.5301e-07, 'epoch': 4.22, 'throughput': 481.69}
578
-
579
- [INFO|callbacks.py:310] 2024-07-23 06:38:08,283 >> {'loss': 0.0017, 'learning_rate': 2.3423e-07, 'epoch': 4.24, 'throughput': 481.57}
580
-
581
- [INFO|callbacks.py:310] 2024-07-23 06:38:21,478 >> {'loss': 0.0004, 'learning_rate': 2.1614e-07, 'epoch': 4.27, 'throughput': 481.61}
582
-
583
- [INFO|callbacks.py:310] 2024-07-23 06:38:34,685 >> {'loss': 0.0049, 'learning_rate': 1.9874e-07, 'epoch': 4.30, 'throughput': 481.61}
584
-
585
- [INFO|callbacks.py:310] 2024-07-23 06:38:47,883 >> {'loss': 0.0071, 'learning_rate': 1.8204e-07, 'epoch': 4.32, 'throughput': 481.58}
586
-
587
- [INFO|callbacks.py:310] 2024-07-23 06:39:01,101 >> {'loss': 0.0011, 'learning_rate': 1.6605e-07, 'epoch': 4.35, 'throughput': 481.50}
588
-
589
- [INFO|callbacks.py:310] 2024-07-23 06:39:14,310 >> {'loss': 0.0004, 'learning_rate': 1.5077e-07, 'epoch': 4.37, 'throughput': 481.50}
590
-
591
- [INFO|callbacks.py:310] 2024-07-23 06:39:27,517 >> {'loss': 0.0007, 'learning_rate': 1.3620e-07, 'epoch': 4.40, 'throughput': 481.53}
592
-
593
- [INFO|callbacks.py:310] 2024-07-23 06:39:40,725 >> {'loss': 0.0017, 'learning_rate': 1.2236e-07, 'epoch': 4.42, 'throughput': 481.55}
594
-
595
- [INFO|callbacks.py:310] 2024-07-23 06:39:53,914 >> {'loss': 0.0007, 'learning_rate': 1.0924e-07, 'epoch': 4.45, 'throughput': 481.62}
596
-
597
- [INFO|callbacks.py:310] 2024-07-23 06:40:07,118 >> {'loss': 0.0003, 'learning_rate': 9.6846e-08, 'epoch': 4.48, 'throughput': 481.52}
598
-
599
- [INFO|callbacks.py:310] 2024-07-23 06:40:20,320 >> {'loss': 0.0046, 'learning_rate': 8.5185e-08, 'epoch': 4.50, 'throughput': 481.47}
600
-
601
- [INFO|callbacks.py:310] 2024-07-23 06:40:33,527 >> {'loss': 0.0038, 'learning_rate': 7.4261e-08, 'epoch': 4.53, 'throughput': 481.39}
602
-
603
- [INFO|callbacks.py:310] 2024-07-23 06:40:46,729 >> {'loss': 0.0036, 'learning_rate': 6.4075e-08, 'epoch': 4.55, 'throughput': 481.44}
604
-
605
- [INFO|callbacks.py:310] 2024-07-23 06:40:59,918 >> {'loss': 0.0056, 'learning_rate': 5.4631e-08, 'epoch': 4.58, 'throughput': 481.44}
606
-
607
- [INFO|callbacks.py:310] 2024-07-23 06:41:13,108 >> {'loss': 0.0057, 'learning_rate': 4.5932e-08, 'epoch': 4.60, 'throughput': 481.48}
608
-
609
- [INFO|callbacks.py:310] 2024-07-23 06:41:26,307 >> {'loss': 0.0020, 'learning_rate': 3.7981e-08, 'epoch': 4.63, 'throughput': 481.54}
610
-
611
- [INFO|callbacks.py:310] 2024-07-23 06:41:39,504 >> {'loss': 0.0003, 'learning_rate': 3.0779e-08, 'epoch': 4.66, 'throughput': 481.47}
612
-
613
- [INFO|callbacks.py:310] 2024-07-23 06:41:52,709 >> {'loss': 0.0002, 'learning_rate': 2.4330e-08, 'epoch': 4.68, 'throughput': 481.39}
614
 
615
- [INFO|callbacks.py:310] 2024-07-23 06:42:05,913 >> {'loss': 0.0043, 'learning_rate': 1.8635e-08, 'epoch': 4.71, 'throughput': 481.25}
616
 
617
- [INFO|callbacks.py:310] 2024-07-23 06:42:19,118 >> {'loss': 0.0002, 'learning_rate': 1.3695e-08, 'epoch': 4.73, 'throughput': 481.18}
 
618
 
619
- [INFO|callbacks.py:310] 2024-07-23 06:42:32,314 >> {'loss': 0.0013, 'learning_rate': 9.5133e-09, 'epoch': 4.76, 'throughput': 481.19}
620
 
621
- [INFO|callbacks.py:310] 2024-07-23 06:42:45,516 >> {'loss': 0.0023, 'learning_rate': 6.0899e-09, 'epoch': 4.78, 'throughput': 481.22}
622
 
623
- [INFO|callbacks.py:310] 2024-07-23 06:42:58,713 >> {'loss': 0.0002, 'learning_rate': 3.4262e-09, 'epoch': 4.81, 'throughput': 481.35}
624
 
625
- [INFO|callbacks.py:310] 2024-07-23 06:43:11,906 >> {'loss': 0.0015, 'learning_rate': 1.5229e-09, 'epoch': 4.84, 'throughput': 481.32}
626
 
627
- [INFO|callbacks.py:310] 2024-07-23 06:43:25,108 >> {'loss': 0.0002, 'learning_rate': 3.8076e-10, 'epoch': 4.86, 'throughput': 481.33}
628
 
629
- [INFO|callbacks.py:310] 2024-07-23 06:43:38,296 >> {'loss': 0.0028, 'learning_rate': 0.0000e+00, 'epoch': 4.89, 'throughput': 481.34}
630
 
631
- [INFO|trainer.py:3478] 2024-07-23 06:43:46,053 >> Saving model checkpoint to saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/checkpoint-190
632
 
633
- [INFO|configuration_utils.py:472] 2024-07-23 06:43:46,056 >> Configuration saved in saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/checkpoint-190/config.json
634
 
635
- [INFO|configuration_utils.py:769] 2024-07-23 06:43:46,057 >> Configuration saved in saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/checkpoint-190/generation_config.json
636
 
637
- [INFO|modeling_utils.py:2698] 2024-07-23 06:44:02,355 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/checkpoint-190/model.safetensors.index.json.
638
 
639
- [INFO|tokenization_utils_base.py:2574] 2024-07-23 06:44:02,358 >> tokenizer config file saved in saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/checkpoint-190/tokenizer_config.json
640
 
641
- [INFO|tokenization_utils_base.py:2583] 2024-07-23 06:44:02,358 >> Special tokens file saved in saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/checkpoint-190/special_tokens_map.json
642
 
643
- [INFO|trainer.py:2383] 2024-07-23 06:44:38,945 >>
644
 
645
- Training completed. Do not forget to share your model on huggingface.co/models =)
646
 
 
647
 
 
648
 
649
- [INFO|trainer.py:3478] 2024-07-23 06:44:46,529 >> Saving model checkpoint to saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3
650
 
651
- [INFO|configuration_utils.py:472] 2024-07-23 06:44:46,532 >> Configuration saved in saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/config.json
652
 
653
- [INFO|configuration_utils.py:769] 2024-07-23 06:44:46,532 >> Configuration saved in saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/generation_config.json
654
 
655
- [INFO|modeling_utils.py:2698] 2024-07-23 06:45:03,514 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/model.safetensors.index.json.
656
 
657
- [INFO|tokenization_utils_base.py:2574] 2024-07-23 06:45:03,517 >> tokenizer config file saved in saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/tokenizer_config.json
658
 
659
- [INFO|tokenization_utils_base.py:2583] 2024-07-23 06:45:03,517 >> Special tokens file saved in saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/special_tokens_map.json
660
 
661
- [WARNING|ploting.py:89] 2024-07-23 06:45:04,844 >> No metric eval_loss to plot.
662
 
663
- [WARNING|ploting.py:89] 2024-07-23 06:45:04,844 >> No metric eval_accuracy to plot.
664
 
665
- [INFO|modelcard.py:449] 2024-07-23 06:45:04,845 >> Dropping the following result as it does not have all the necessary fields:
666
- {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
667
 
 
1
+ 07/23/2024 06:56:00 - INFO - llamafactory.hparams.parser - Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: None
2
 
3
+ 07/23/2024 06:56:00 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
4
 
5
+ 07/23/2024 06:56:00 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
6
 
7
+ 07/23/2024 06:56:00 - INFO - llamafactory.hparams.parser - Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: None
8
 
9
+ 07/23/2024 06:56:00 - INFO - llamafactory.hparams.parser - Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: None
10
 
11
+ [INFO|parser.py:325] 2024-07-23 06:56:00,990 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: None
12
 
13
+ [INFO|tokenization_utils_base.py:2159] 2024-07-23 06:56:00,992 >> loading file tokenizer.json
14
 
15
+ [INFO|tokenization_utils_base.py:2159] 2024-07-23 06:56:00,992 >> loading file added_tokens.json
16
 
17
+ 07/23/2024 06:56:01 - INFO - llamafactory.hparams.parser - Process rank: 6, device: cuda:6, n_gpu: 1, distributed training: True, compute dtype: None
18
 
19
+ 07/23/2024 06:56:01 - INFO - llamafactory.hparams.parser - Process rank: 7, device: cuda:7, n_gpu: 1, distributed training: True, compute dtype: None
20
 
21
+ 07/23/2024 06:56:01 - INFO - llamafactory.hparams.parser - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: None
22
 
23
+ 07/23/2024 06:56:01 - INFO - llamafactory.hparams.parser - Process rank: 2, device: cuda:2, n_gpu: 1, distributed training: True, compute dtype: None
24
 
25
+ 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
26
 
27
+ 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
28
 
29
+ 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
30
 
31
+ 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
32
 
33
+ [INFO|tokenization_utils_base.py:2159] 2024-07-23 06:56:00,992 >> loading file special_tokens_map.json
34
 
35
+ [INFO|tokenization_utils_base.py:2159] 2024-07-23 06:56:00,992 >> loading file tokenizer_config.json
36
 
37
+ [WARNING|logging.py:313] 2024-07-23 06:56:01,268 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
38
 
39
+ [INFO|template.py:270] 2024-07-23 06:56:01,269 >> Replace eos token: <|eot_id|>
40
 
41
+ [INFO|loader.py:50] 2024-07-23 06:56:01,269 >> Loading dataset 0716_truthfulqa_benchmark_test.json...
42
 
43
+ 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
44
 
45
+ 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
46
 
47
+ 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
48
 
49
+ 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
50
 
51
+ 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
52
 
53
+ 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
54
 
55
+ 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
56
 
57
+ 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
58
 
59
+ 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
60
 
61
+ 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
62
 
63
+ 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
64
 
65
+ 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
66
 
67
+ 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
68
 
69
+ 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
70
 
71
+ 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
72
 
73
+ [INFO|configuration_utils.py:731] 2024-07-23 06:56:05,969 >> loading configuration file saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/config.json
74
 
75
+ [INFO|configuration_utils.py:800] 2024-07-23 06:56:05,970 >> Model config LlamaConfig {
76
+ "_name_or_path": "saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  "architectures": [
78
  "LlamaForCausalLM"
79
  ],
 
98
  "tie_word_embeddings": false,
99
  "torch_dtype": "bfloat16",
100
  "transformers_version": "4.42.3",
101
+ "use_cache": false,
102
  "vocab_size": 128256
103
  }
104
 
105
 
106
+ [INFO|patcher.py:81] 2024-07-23 06:56:05,971 >> Using KV cache for faster generation.
107
 
108
+ [INFO|modeling_utils.py:3553] 2024-07-23 06:56:05,998 >> loading weights file saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/model.safetensors.index.json
109
 
110
+ [INFO|modeling_utils.py:1531] 2024-07-23 06:56:05,999 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
111
+
112
+ [INFO|configuration_utils.py:1000] 2024-07-23 06:56:06,002 >> Generate config GenerationConfig {
113
  "bos_token_id": 128000,
114
  "eos_token_id": 128009
115
  }
116
 
117
 
118
+ 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
 
 
 
 
119
 
120
+ 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
121
 
122
+ 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
123
 
124
+ 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
125
 
126
+ 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
127
 
128
+ 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
129
 
130
+ 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
131
 
132
+ [INFO|modeling_utils.py:4364] 2024-07-23 06:56:10,304 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
133
 
 
134
 
135
+ [INFO|modeling_utils.py:4372] 2024-07-23 06:56:10,304 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3.
136
+ If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
137
 
138
+ [INFO|configuration_utils.py:953] 2024-07-23 06:56:10,308 >> loading configuration file saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/generation_config.json
139
 
140
+ [INFO|configuration_utils.py:1000] 2024-07-23 06:56:10,308 >> Generate config GenerationConfig {
141
  "bos_token_id": 128000,
142
  "do_sample": true,
143
  "eos_token_id": [
 
150
  }
151
 
152
 
153
+ [INFO|attention.py:80] 2024-07-23 06:56:10,317 >> Using torch SDPA for faster training and inference.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
154
 
155
+ [INFO|loader.py:196] 2024-07-23 06:56:10,322 >> all params: 8,030,261,248
156
 
157
+ [INFO|trainer.py:3788] 2024-07-23 06:56:10,436 >>
158
+ ***** Running Prediction *****
159
 
160
+ [INFO|trainer.py:3790] 2024-07-23 06:56:10,436 >> Num examples = 1243
161
 
162
+ [INFO|trainer.py:3793] 2024-07-23 06:56:10,436 >> Batch size = 2
163
 
164
+ [WARNING|logging.py:328] 2024-07-23 06:56:11,121 >> We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
165
 
166
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
167
 
168
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
169
 
170
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
171
 
172
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248
173
 
174
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248
175
 
176
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248
177
 
178
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
179
 
180
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
181
 
182
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248
183
 
184
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248
185
 
186
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
187
 
188
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248
189
 
190
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
191
 
192
+ 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248
193
 
194
+ 07/23/2024 06:56:12 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
195
 
196
+ 07/23/2024 06:56:12 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
197
 
198
+ 07/23/2024 06:56:12 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
199
 
200
+ 07/23/2024 06:56:12 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
201
 
202
+ 07/23/2024 06:56:12 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
203
 
204
+ 07/23/2024 06:56:12 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
205
 
206
+ 07/23/2024 06:56:12 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
207
 
208
+ [INFO|trainer.py:127] 2024-07-23 06:56:19,786 >> Saving prediction results to saves/LLaMA3-8B-Chat/full/eval_2024-07-23-06-52-5_llama3/generated_predictions.jsonl
 
209
 
trainer_log.jsonl CHANGED
@@ -1,191 +1,15 @@
1
- {"current_steps": 1, "total_steps": 190, "loss": 14.1364, "learning_rate": 5.000000000000001e-07, "epoch": 0.02572347266881029, "percentage": 0.53, "elapsed_time": "0:00:15", "remaining_time": "0:49:11", "throughput": "417.05", "total_tokens": 6512}
2
- {"current_steps": 2, "total_steps": 190, "loss": 13.7804, "learning_rate": 1.0000000000000002e-06, "epoch": 0.05144694533762058, "percentage": 1.05, "elapsed_time": "0:00:28", "remaining_time": "0:45:11", "throughput": "445.34", "total_tokens": 12848}
3
- {"current_steps": 3, "total_steps": 190, "loss": 13.4871, "learning_rate": 1.5e-06, "epoch": 0.07717041800643087, "percentage": 1.58, "elapsed_time": "0:00:42", "remaining_time": "0:43:42", "throughput": "457.52", "total_tokens": 19248}
4
- {"current_steps": 4, "total_steps": 190, "loss": 12.79, "learning_rate": 2.0000000000000003e-06, "epoch": 0.10289389067524116, "percentage": 2.11, "elapsed_time": "0:00:55", "remaining_time": "0:42:51", "throughput": "458.34", "total_tokens": 25344}
5
- {"current_steps": 5, "total_steps": 190, "loss": 9.2748, "learning_rate": 2.5e-06, "epoch": 0.12861736334405144, "percentage": 2.63, "elapsed_time": "0:01:08", "remaining_time": "0:42:14", "throughput": "466.66", "total_tokens": 31968}
6
- {"current_steps": 6, "total_steps": 190, "loss": 6.5585, "learning_rate": 3e-06, "epoch": 0.15434083601286175, "percentage": 3.16, "elapsed_time": "0:01:21", "remaining_time": "0:41:45", "throughput": "467.05", "total_tokens": 38160}
7
- {"current_steps": 7, "total_steps": 190, "loss": 5.3984, "learning_rate": 3.5e-06, "epoch": 0.18006430868167203, "percentage": 3.68, "elapsed_time": "0:01:34", "remaining_time": "0:41:21", "throughput": "465.11", "total_tokens": 44144}
8
- {"current_steps": 8, "total_steps": 190, "loss": 1.9363, "learning_rate": 4.000000000000001e-06, "epoch": 0.2057877813504823, "percentage": 4.21, "elapsed_time": "0:01:48", "remaining_time": "0:40:59", "throughput": "466.48", "total_tokens": 50432}
9
- {"current_steps": 9, "total_steps": 190, "loss": 0.6783, "learning_rate": 4.5e-06, "epoch": 0.2315112540192926, "percentage": 4.74, "elapsed_time": "0:02:01", "remaining_time": "0:40:39", "throughput": "469.24", "total_tokens": 56928}
10
- {"current_steps": 10, "total_steps": 190, "loss": 2.9945, "learning_rate": 5e-06, "epoch": 0.2572347266881029, "percentage": 5.26, "elapsed_time": "0:02:14", "remaining_time": "0:40:21", "throughput": "470.87", "total_tokens": 63344}
11
- {"current_steps": 11, "total_steps": 190, "loss": 0.2916, "learning_rate": 4.9996192378909785e-06, "epoch": 0.2829581993569132, "percentage": 5.79, "elapsed_time": "0:02:27", "remaining_time": "0:40:03", "throughput": "470.92", "total_tokens": 69568}
12
- {"current_steps": 12, "total_steps": 190, "loss": 2.2775, "learning_rate": 4.99847706754774e-06, "epoch": 0.3086816720257235, "percentage": 6.32, "elapsed_time": "0:02:40", "remaining_time": "0:39:47", "throughput": "471.10", "total_tokens": 75824}
13
- {"current_steps": 13, "total_steps": 190, "loss": 0.3757, "learning_rate": 4.9965738368864345e-06, "epoch": 0.33440514469453375, "percentage": 6.84, "elapsed_time": "0:02:54", "remaining_time": "0:39:31", "throughput": "471.76", "total_tokens": 82160}
14
- {"current_steps": 14, "total_steps": 190, "loss": 1.9543, "learning_rate": 4.993910125649561e-06, "epoch": 0.36012861736334406, "percentage": 7.37, "elapsed_time": "0:03:07", "remaining_time": "0:39:15", "throughput": "473.05", "total_tokens": 88624}
15
- {"current_steps": 15, "total_steps": 190, "loss": 0.7398, "learning_rate": 4.990486745229364e-06, "epoch": 0.3858520900321543, "percentage": 7.89, "elapsed_time": "0:03:20", "remaining_time": "0:38:59", "throughput": "472.67", "total_tokens": 94800}
16
- {"current_steps": 16, "total_steps": 190, "loss": 1.1868, "learning_rate": 4.986304738420684e-06, "epoch": 0.4115755627009646, "percentage": 8.42, "elapsed_time": "0:03:33", "remaining_time": "0:38:44", "throughput": "474.17", "total_tokens": 101360}
17
- {"current_steps": 17, "total_steps": 190, "loss": 0.5418, "learning_rate": 4.981365379103306e-06, "epoch": 0.43729903536977494, "percentage": 8.95, "elapsed_time": "0:03:46", "remaining_time": "0:38:29", "throughput": "473.57", "total_tokens": 107488}
18
- {"current_steps": 18, "total_steps": 190, "loss": 0.2263, "learning_rate": 4.975670171853926e-06, "epoch": 0.4630225080385852, "percentage": 9.47, "elapsed_time": "0:04:00", "remaining_time": "0:38:14", "throughput": "474.35", "total_tokens": 113920}
19
- {"current_steps": 19, "total_steps": 190, "loss": 0.1612, "learning_rate": 4.9692208514878445e-06, "epoch": 0.4887459807073955, "percentage": 10.0, "elapsed_time": "0:04:13", "remaining_time": "0:38:00", "throughput": "475.02", "total_tokens": 120352}
20
- {"current_steps": 20, "total_steps": 190, "loss": 0.3299, "learning_rate": 4.962019382530521e-06, "epoch": 0.5144694533762058, "percentage": 10.53, "elapsed_time": "0:04:26", "remaining_time": "0:37:45", "throughput": "475.97", "total_tokens": 126880}
21
- {"current_steps": 21, "total_steps": 190, "loss": 0.2013, "learning_rate": 4.9540679586191605e-06, "epoch": 0.5401929260450161, "percentage": 11.05, "elapsed_time": "0:04:39", "remaining_time": "0:37:31", "throughput": "476.60", "total_tokens": 133344}
22
- {"current_steps": 22, "total_steps": 190, "loss": 0.2446, "learning_rate": 4.9453690018345144e-06, "epoch": 0.5659163987138264, "percentage": 11.58, "elapsed_time": "0:04:52", "remaining_time": "0:37:17", "throughput": "477.00", "total_tokens": 139744}
23
- {"current_steps": 23, "total_steps": 190, "loss": 0.2235, "learning_rate": 4.935925161963089e-06, "epoch": 0.5916398713826366, "percentage": 12.11, "elapsed_time": "0:05:06", "remaining_time": "0:37:03", "throughput": "477.33", "total_tokens": 146144}
24
- {"current_steps": 24, "total_steps": 190, "loss": 0.116, "learning_rate": 4.925739315689991e-06, "epoch": 0.617363344051447, "percentage": 12.63, "elapsed_time": "0:05:19", "remaining_time": "0:36:49", "throughput": "476.68", "total_tokens": 152240}
25
- {"current_steps": 25, "total_steps": 190, "loss": 0.2179, "learning_rate": 4.914814565722671e-06, "epoch": 0.6430868167202572, "percentage": 13.16, "elapsed_time": "0:05:32", "remaining_time": "0:36:34", "throughput": "476.63", "total_tokens": 158512}
26
- {"current_steps": 26, "total_steps": 190, "loss": 0.1414, "learning_rate": 4.903154239845798e-06, "epoch": 0.6688102893890675, "percentage": 13.68, "elapsed_time": "0:05:45", "remaining_time": "0:36:20", "throughput": "476.58", "total_tokens": 164784}
27
- {"current_steps": 27, "total_steps": 190, "loss": 0.1181, "learning_rate": 4.890761889907589e-06, "epoch": 0.6945337620578779, "percentage": 14.21, "elapsed_time": "0:05:58", "remaining_time": "0:36:07", "throughput": "477.26", "total_tokens": 171312}
28
- {"current_steps": 28, "total_steps": 190, "loss": 0.2753, "learning_rate": 4.8776412907378845e-06, "epoch": 0.7202572347266881, "percentage": 14.74, "elapsed_time": "0:06:12", "remaining_time": "0:35:53", "throughput": "477.91", "total_tokens": 177856}
29
- {"current_steps": 29, "total_steps": 190, "loss": 0.3255, "learning_rate": 4.863796438998293e-06, "epoch": 0.7459807073954984, "percentage": 15.26, "elapsed_time": "0:06:25", "remaining_time": "0:35:39", "throughput": "478.44", "total_tokens": 184368}
30
- {"current_steps": 30, "total_steps": 190, "loss": 0.2352, "learning_rate": 4.849231551964771e-06, "epoch": 0.7717041800643086, "percentage": 15.79, "elapsed_time": "0:06:38", "remaining_time": "0:35:25", "throughput": "479.06", "total_tokens": 190928}
31
- {"current_steps": 31, "total_steps": 190, "loss": 0.063, "learning_rate": 4.833951066243004e-06, "epoch": 0.797427652733119, "percentage": 16.32, "elapsed_time": "0:06:51", "remaining_time": "0:35:11", "throughput": "479.01", "total_tokens": 197232}
32
- {"current_steps": 32, "total_steps": 190, "loss": 0.2042, "learning_rate": 4.817959636416969e-06, "epoch": 0.8231511254019293, "percentage": 16.84, "elapsed_time": "0:07:04", "remaining_time": "0:34:58", "throughput": "479.09", "total_tokens": 203584}
33
- {"current_steps": 33, "total_steps": 190, "loss": 0.1364, "learning_rate": 4.801262133631101e-06, "epoch": 0.8488745980707395, "percentage": 17.37, "elapsed_time": "0:07:18", "remaining_time": "0:34:44", "throughput": "479.59", "total_tokens": 210128}
34
- {"current_steps": 34, "total_steps": 190, "loss": 0.0934, "learning_rate": 4.783863644106502e-06, "epoch": 0.8745980707395499, "percentage": 17.89, "elapsed_time": "0:07:31", "remaining_time": "0:34:30", "throughput": "479.71", "total_tokens": 216512}
35
- {"current_steps": 35, "total_steps": 190, "loss": 0.1332, "learning_rate": 4.765769467591626e-06, "epoch": 0.9003215434083601, "percentage": 18.42, "elapsed_time": "0:07:44", "remaining_time": "0:34:17", "throughput": "479.91", "total_tokens": 222928}
36
- {"current_steps": 36, "total_steps": 190, "loss": 0.1595, "learning_rate": 4.746985115747918e-06, "epoch": 0.9260450160771704, "percentage": 18.95, "elapsed_time": "0:07:57", "remaining_time": "0:34:03", "throughput": "479.86", "total_tokens": 229232}
37
- {"current_steps": 37, "total_steps": 190, "loss": 0.1528, "learning_rate": 4.72751631047092e-06, "epoch": 0.9517684887459807, "percentage": 19.47, "elapsed_time": "0:08:10", "remaining_time": "0:33:50", "throughput": "480.07", "total_tokens": 235680}
38
- {"current_steps": 38, "total_steps": 190, "loss": 0.1342, "learning_rate": 4.707368982147318e-06, "epoch": 0.977491961414791, "percentage": 20.0, "elapsed_time": "0:08:24", "remaining_time": "0:33:36", "throughput": "480.42", "total_tokens": 242192}
39
- {"current_steps": 39, "total_steps": 190, "loss": 0.1586, "learning_rate": 4.68654926784849e-06, "epoch": 1.0032154340836013, "percentage": 20.53, "elapsed_time": "0:08:37", "remaining_time": "0:33:22", "throughput": "480.69", "total_tokens": 248672}
40
- {"current_steps": 40, "total_steps": 190, "loss": 0.1072, "learning_rate": 4.665063509461098e-06, "epoch": 1.0289389067524115, "percentage": 21.05, "elapsed_time": "0:08:50", "remaining_time": "0:33:09", "throughput": "480.80", "total_tokens": 255072}
41
- {"current_steps": 41, "total_steps": 190, "loss": 0.0357, "learning_rate": 4.642918251755281e-06, "epoch": 1.0546623794212218, "percentage": 21.58, "elapsed_time": "0:09:03", "remaining_time": "0:32:55", "throughput": "481.10", "total_tokens": 261584}
42
- {"current_steps": 42, "total_steps": 190, "loss": 0.06, "learning_rate": 4.620120240391065e-06, "epoch": 1.0803858520900322, "percentage": 22.11, "elapsed_time": "0:09:16", "remaining_time": "0:32:42", "throughput": "481.28", "total_tokens": 268032}
43
- {"current_steps": 43, "total_steps": 190, "loss": 0.0902, "learning_rate": 4.596676419863561e-06, "epoch": 1.1061093247588425, "percentage": 22.63, "elapsed_time": "0:09:30", "remaining_time": "0:32:28", "throughput": "481.59", "total_tokens": 274560}
44
- {"current_steps": 44, "total_steps": 190, "loss": 0.0202, "learning_rate": 4.572593931387604e-06, "epoch": 1.1318327974276527, "percentage": 23.16, "elapsed_time": "0:09:43", "remaining_time": "0:32:15", "throughput": "481.67", "total_tokens": 280960}
45
- {"current_steps": 45, "total_steps": 190, "loss": 0.038, "learning_rate": 4.54788011072248e-06, "epoch": 1.157556270096463, "percentage": 23.68, "elapsed_time": "0:09:56", "remaining_time": "0:32:02", "throughput": "481.31", "total_tokens": 287104}
46
- {"current_steps": 46, "total_steps": 190, "loss": 0.0379, "learning_rate": 4.522542485937369e-06, "epoch": 1.1832797427652733, "percentage": 24.21, "elapsed_time": "0:10:09", "remaining_time": "0:31:48", "throughput": "481.42", "total_tokens": 293520}
47
- {"current_steps": 47, "total_steps": 190, "loss": 0.0742, "learning_rate": 4.496588775118232e-06, "epoch": 1.2090032154340835, "percentage": 24.74, "elapsed_time": "0:10:22", "remaining_time": "0:31:35", "throughput": "481.51", "total_tokens": 299936}
48
- {"current_steps": 48, "total_steps": 190, "loss": 0.0658, "learning_rate": 4.470026884016805e-06, "epoch": 1.234726688102894, "percentage": 25.26, "elapsed_time": "0:10:36", "remaining_time": "0:31:21", "throughput": "480.94", "total_tokens": 305936}
49
- {"current_steps": 49, "total_steps": 190, "loss": 0.0336, "learning_rate": 4.442864903642428e-06, "epoch": 1.2604501607717042, "percentage": 25.79, "elapsed_time": "0:10:49", "remaining_time": "0:31:08", "throughput": "481.32", "total_tokens": 312528}
50
- {"current_steps": 50, "total_steps": 190, "loss": 0.1021, "learning_rate": 4.415111107797445e-06, "epoch": 1.2861736334405145, "percentage": 26.32, "elapsed_time": "0:11:02", "remaining_time": "0:30:55", "throughput": "481.12", "total_tokens": 318752}
51
- {"current_steps": 51, "total_steps": 190, "loss": 0.1312, "learning_rate": 4.386773950556931e-06, "epoch": 1.3118971061093248, "percentage": 26.84, "elapsed_time": "0:11:15", "remaining_time": "0:30:41", "throughput": "481.10", "total_tokens": 325088}
52
- {"current_steps": 52, "total_steps": 190, "loss": 0.0665, "learning_rate": 4.357862063693486e-06, "epoch": 1.337620578778135, "percentage": 27.37, "elapsed_time": "0:11:28", "remaining_time": "0:30:28", "throughput": "481.08", "total_tokens": 331424}
53
- {"current_steps": 53, "total_steps": 190, "loss": 0.0679, "learning_rate": 4.328384254047927e-06, "epoch": 1.3633440514469453, "percentage": 27.89, "elapsed_time": "0:11:42", "remaining_time": "0:30:14", "throughput": "481.08", "total_tokens": 337776}
54
- {"current_steps": 54, "total_steps": 190, "loss": 0.0579, "learning_rate": 4.2983495008466285e-06, "epoch": 1.3890675241157555, "percentage": 28.42, "elapsed_time": "0:11:55", "remaining_time": "0:30:01", "throughput": "480.90", "total_tokens": 344000}
55
- {"current_steps": 55, "total_steps": 190, "loss": 0.0542, "learning_rate": 4.267766952966369e-06, "epoch": 1.414790996784566, "percentage": 28.95, "elapsed_time": "0:12:08", "remaining_time": "0:29:48", "throughput": "481.15", "total_tokens": 350528}
56
- {"current_steps": 56, "total_steps": 190, "loss": 0.0476, "learning_rate": 4.236645926147493e-06, "epoch": 1.4405144694533762, "percentage": 29.47, "elapsed_time": "0:12:21", "remaining_time": "0:29:34", "throughput": "481.17", "total_tokens": 356896}
57
- {"current_steps": 57, "total_steps": 190, "loss": 0.0613, "learning_rate": 4.204995900156247e-06, "epoch": 1.4662379421221865, "percentage": 30.0, "elapsed_time": "0:12:34", "remaining_time": "0:29:21", "throughput": "481.35", "total_tokens": 363376}
58
- {"current_steps": 58, "total_steps": 190, "loss": 0.0995, "learning_rate": 4.172826515897146e-06, "epoch": 1.4919614147909968, "percentage": 30.53, "elapsed_time": "0:12:48", "remaining_time": "0:29:08", "throughput": "481.29", "total_tokens": 369680}
59
- {"current_steps": 59, "total_steps": 190, "loss": 0.0532, "learning_rate": 4.140147572476269e-06, "epoch": 1.517684887459807, "percentage": 31.05, "elapsed_time": "0:13:01", "remaining_time": "0:28:54", "throughput": "481.12", "total_tokens": 375904}
60
- {"current_steps": 60, "total_steps": 190, "loss": 0.0824, "learning_rate": 4.106969024216348e-06, "epoch": 1.5434083601286175, "percentage": 31.58, "elapsed_time": "0:13:14", "remaining_time": "0:28:41", "throughput": "481.19", "total_tokens": 382304}
61
- {"current_steps": 61, "total_steps": 190, "loss": 0.0499, "learning_rate": 4.073300977624594e-06, "epoch": 1.5691318327974275, "percentage": 32.11, "elapsed_time": "0:13:27", "remaining_time": "0:28:28", "throughput": "481.24", "total_tokens": 388688}
62
- {"current_steps": 62, "total_steps": 190, "loss": 0.0413, "learning_rate": 4.039153688314146e-06, "epoch": 1.594855305466238, "percentage": 32.63, "elapsed_time": "0:13:40", "remaining_time": "0:28:14", "throughput": "481.38", "total_tokens": 395152}
63
- {"current_steps": 63, "total_steps": 190, "loss": 0.0637, "learning_rate": 4.0045375578801216e-06, "epoch": 1.6205787781350482, "percentage": 33.16, "elapsed_time": "0:13:54", "remaining_time": "0:28:01", "throughput": "481.64", "total_tokens": 401728}
64
- {"current_steps": 64, "total_steps": 190, "loss": 0.0529, "learning_rate": 3.969463130731183e-06, "epoch": 1.6463022508038585, "percentage": 33.68, "elapsed_time": "0:14:07", "remaining_time": "0:27:48", "throughput": "481.43", "total_tokens": 407904}
65
- {"current_steps": 65, "total_steps": 190, "loss": 0.0474, "learning_rate": 3.933941090877615e-06, "epoch": 1.6720257234726688, "percentage": 34.21, "elapsed_time": "0:14:20", "remaining_time": "0:27:34", "throughput": "481.41", "total_tokens": 414240}
66
- {"current_steps": 66, "total_steps": 190, "loss": 0.0649, "learning_rate": 3.897982258676867e-06, "epoch": 1.697749196141479, "percentage": 34.74, "elapsed_time": "0:14:33", "remaining_time": "0:27:21", "throughput": "481.25", "total_tokens": 420448}
67
- {"current_steps": 67, "total_steps": 190, "loss": 0.0505, "learning_rate": 3.861597587537568e-06, "epoch": 1.7234726688102895, "percentage": 35.26, "elapsed_time": "0:14:46", "remaining_time": "0:27:08", "throughput": "481.23", "total_tokens": 426784}
68
- {"current_steps": 68, "total_steps": 190, "loss": 0.0621, "learning_rate": 3.824798160583012e-06, "epoch": 1.7491961414790995, "percentage": 35.79, "elapsed_time": "0:15:00", "remaining_time": "0:26:54", "throughput": "480.87", "total_tokens": 432816}
69
- {"current_steps": 69, "total_steps": 190, "loss": 0.0769, "learning_rate": 3.787595187275136e-06, "epoch": 1.77491961414791, "percentage": 36.32, "elapsed_time": "0:15:13", "remaining_time": "0:26:41", "throughput": "480.95", "total_tokens": 439232}
70
- {"current_steps": 70, "total_steps": 190, "loss": 0.0435, "learning_rate": 3.7500000000000005e-06, "epoch": 1.8006430868167203, "percentage": 36.84, "elapsed_time": "0:15:26", "remaining_time": "0:26:28", "throughput": "481.18", "total_tokens": 445792}
71
- {"current_steps": 71, "total_steps": 190, "loss": 0.0673, "learning_rate": 3.7120240506158433e-06, "epoch": 1.8263665594855305, "percentage": 37.37, "elapsed_time": "0:15:39", "remaining_time": "0:26:14", "throughput": "481.46", "total_tokens": 452400}
72
- {"current_steps": 72, "total_steps": 190, "loss": 0.1316, "learning_rate": 3.6736789069647273e-06, "epoch": 1.852090032154341, "percentage": 37.89, "elapsed_time": "0:15:52", "remaining_time": "0:26:01", "throughput": "481.22", "total_tokens": 458528}
73
- {"current_steps": 73, "total_steps": 190, "loss": 0.0531, "learning_rate": 3.634976249348867e-06, "epoch": 1.877813504823151, "percentage": 38.42, "elapsed_time": "0:16:06", "remaining_time": "0:25:48", "throughput": "481.32", "total_tokens": 464976}
74
- {"current_steps": 74, "total_steps": 190, "loss": 0.0287, "learning_rate": 3.595927866972694e-06, "epoch": 1.9035369774919615, "percentage": 38.95, "elapsed_time": "0:16:19", "remaining_time": "0:25:35", "throughput": "481.43", "total_tokens": 471440}
75
- {"current_steps": 75, "total_steps": 190, "loss": 0.0648, "learning_rate": 3.556545654351749e-06, "epoch": 1.9292604501607717, "percentage": 39.47, "elapsed_time": "0:16:32", "remaining_time": "0:25:21", "throughput": "481.41", "total_tokens": 477776}
76
- {"current_steps": 76, "total_steps": 190, "loss": 0.1211, "learning_rate": 3.516841607689501e-06, "epoch": 1.954983922829582, "percentage": 40.0, "elapsed_time": "0:16:45", "remaining_time": "0:25:08", "throughput": "481.37", "total_tokens": 484096}
77
- {"current_steps": 77, "total_steps": 190, "loss": 0.0879, "learning_rate": 3.476827821223184e-06, "epoch": 1.9807073954983923, "percentage": 40.53, "elapsed_time": "0:16:58", "remaining_time": "0:24:55", "throughput": "481.10", "total_tokens": 490176}
78
- {"current_steps": 78, "total_steps": 190, "loss": 0.0227, "learning_rate": 3.436516483539781e-06, "epoch": 2.0064308681672025, "percentage": 41.05, "elapsed_time": "0:17:12", "remaining_time": "0:24:41", "throughput": "481.24", "total_tokens": 496672}
79
- {"current_steps": 79, "total_steps": 190, "loss": 0.0228, "learning_rate": 3.39591987386325e-06, "epoch": 2.032154340836013, "percentage": 41.58, "elapsed_time": "0:17:25", "remaining_time": "0:24:28", "throughput": "481.30", "total_tokens": 503088}
80
- {"current_steps": 80, "total_steps": 190, "loss": 0.036, "learning_rate": 3.3550503583141726e-06, "epoch": 2.057877813504823, "percentage": 42.11, "elapsed_time": "0:17:38", "remaining_time": "0:24:15", "throughput": "481.33", "total_tokens": 509472}
81
- {"current_steps": 81, "total_steps": 190, "loss": 0.0138, "learning_rate": 3.313920386142892e-06, "epoch": 2.0836012861736335, "percentage": 42.63, "elapsed_time": "0:17:51", "remaining_time": "0:24:02", "throughput": "481.23", "total_tokens": 515728}
82
- {"current_steps": 82, "total_steps": 190, "loss": 0.0697, "learning_rate": 3.272542485937369e-06, "epoch": 2.1093247588424435, "percentage": 43.16, "elapsed_time": "0:18:04", "remaining_time": "0:23:48", "throughput": "481.06", "total_tokens": 521904}
83
- {"current_steps": 83, "total_steps": 190, "loss": 0.0508, "learning_rate": 3.230929261806842e-06, "epoch": 2.135048231511254, "percentage": 43.68, "elapsed_time": "0:18:18", "remaining_time": "0:23:35", "throughput": "480.79", "total_tokens": 527952}
84
- {"current_steps": 84, "total_steps": 190, "loss": 0.0088, "learning_rate": 3.189093389542498e-06, "epoch": 2.1607717041800645, "percentage": 44.21, "elapsed_time": "0:18:31", "remaining_time": "0:23:22", "throughput": "481.08", "total_tokens": 534624}
85
- {"current_steps": 85, "total_steps": 190, "loss": 0.0158, "learning_rate": 3.147047612756302e-06, "epoch": 2.1864951768488745, "percentage": 44.74, "elapsed_time": "0:18:44", "remaining_time": "0:23:09", "throughput": "481.26", "total_tokens": 541168}
86
- {"current_steps": 86, "total_steps": 190, "loss": 0.006, "learning_rate": 3.1048047389991693e-06, "epoch": 2.212218649517685, "percentage": 45.26, "elapsed_time": "0:18:57", "remaining_time": "0:22:55", "throughput": "481.23", "total_tokens": 547488}
87
- {"current_steps": 87, "total_steps": 190, "loss": 0.038, "learning_rate": 3.062377635859663e-06, "epoch": 2.237942122186495, "percentage": 45.79, "elapsed_time": "0:19:10", "remaining_time": "0:22:42", "throughput": "481.60", "total_tokens": 554272}
88
- {"current_steps": 88, "total_steps": 190, "loss": 0.0004, "learning_rate": 3.019779227044398e-06, "epoch": 2.2636655948553055, "percentage": 46.32, "elapsed_time": "0:19:24", "remaining_time": "0:22:29", "throughput": "481.51", "total_tokens": 560528}
89
- {"current_steps": 89, "total_steps": 190, "loss": 0.0111, "learning_rate": 2.9770224884413625e-06, "epoch": 2.289389067524116, "percentage": 46.84, "elapsed_time": "0:19:37", "remaining_time": "0:22:16", "throughput": "481.43", "total_tokens": 566784}
90
- {"current_steps": 90, "total_steps": 190, "loss": 0.0008, "learning_rate": 2.9341204441673267e-06, "epoch": 2.315112540192926, "percentage": 47.37, "elapsed_time": "0:19:50", "remaining_time": "0:22:02", "throughput": "481.60", "total_tokens": 573344}
91
- {"current_steps": 91, "total_steps": 190, "loss": 0.0182, "learning_rate": 2.8910861626005774e-06, "epoch": 2.3408360128617365, "percentage": 47.89, "elapsed_time": "0:20:03", "remaining_time": "0:21:49", "throughput": "481.67", "total_tokens": 579776}
92
- {"current_steps": 92, "total_steps": 190, "loss": 0.0491, "learning_rate": 2.847932752400164e-06, "epoch": 2.3665594855305465, "percentage": 48.42, "elapsed_time": "0:20:16", "remaining_time": "0:21:36", "throughput": "481.64", "total_tokens": 586096}
93
- {"current_steps": 93, "total_steps": 190, "loss": 0.004, "learning_rate": 2.804673358512869e-06, "epoch": 2.392282958199357, "percentage": 48.95, "elapsed_time": "0:20:30", "remaining_time": "0:21:22", "throughput": "481.71", "total_tokens": 592528}
94
- {"current_steps": 94, "total_steps": 190, "loss": 0.0176, "learning_rate": 2.761321158169134e-06, "epoch": 2.418006430868167, "percentage": 49.47, "elapsed_time": "0:20:43", "remaining_time": "0:21:09", "throughput": "481.77", "total_tokens": 598960}
95
- {"current_steps": 95, "total_steps": 190, "loss": 0.019, "learning_rate": 2.717889356869146e-06, "epoch": 2.4437299035369775, "percentage": 50.0, "elapsed_time": "0:20:56", "remaining_time": "0:20:56", "throughput": "481.70", "total_tokens": 605232}
96
- {"current_steps": 96, "total_steps": 190, "loss": 0.027, "learning_rate": 2.6743911843603134e-06, "epoch": 2.469453376205788, "percentage": 50.53, "elapsed_time": "0:21:09", "remaining_time": "0:20:43", "throughput": "481.50", "total_tokens": 611344}
97
- {"current_steps": 97, "total_steps": 190, "loss": 0.0354, "learning_rate": 2.6308398906073603e-06, "epoch": 2.495176848874598, "percentage": 51.05, "elapsed_time": "0:21:22", "remaining_time": "0:20:29", "throughput": "481.51", "total_tokens": 617712}
98
- {"current_steps": 98, "total_steps": 190, "loss": 0.0741, "learning_rate": 2.587248741756253e-06, "epoch": 2.5209003215434085, "percentage": 51.58, "elapsed_time": "0:21:36", "remaining_time": "0:20:16", "throughput": "481.62", "total_tokens": 624208}
99
- {"current_steps": 99, "total_steps": 190, "loss": 0.0582, "learning_rate": 2.543631016093209e-06, "epoch": 2.5466237942122185, "percentage": 52.11, "elapsed_time": "0:21:49", "remaining_time": "0:20:03", "throughput": "481.56", "total_tokens": 630496}
100
- {"current_steps": 100, "total_steps": 190, "loss": 0.0096, "learning_rate": 2.5e-06, "epoch": 2.572347266881029, "percentage": 52.63, "elapsed_time": "0:22:02", "remaining_time": "0:19:50", "throughput": "481.71", "total_tokens": 637040}
101
- {"current_steps": 101, "total_steps": 190, "loss": 0.0263, "learning_rate": 2.4563689839067913e-06, "epoch": 2.598070739549839, "percentage": 53.16, "elapsed_time": "0:22:15", "remaining_time": "0:19:36", "throughput": "481.77", "total_tokens": 643472}
102
- {"current_steps": 102, "total_steps": 190, "loss": 0.0121, "learning_rate": 2.4127512582437486e-06, "epoch": 2.6237942122186495, "percentage": 53.68, "elapsed_time": "0:22:28", "remaining_time": "0:19:23", "throughput": "481.72", "total_tokens": 649760}
103
- {"current_steps": 103, "total_steps": 190, "loss": 0.0204, "learning_rate": 2.3691601093926406e-06, "epoch": 2.64951768488746, "percentage": 54.21, "elapsed_time": "0:22:42", "remaining_time": "0:19:10", "throughput": "481.70", "total_tokens": 656096}
104
- {"current_steps": 104, "total_steps": 190, "loss": 0.0325, "learning_rate": 2.325608815639687e-06, "epoch": 2.67524115755627, "percentage": 54.74, "elapsed_time": "0:22:55", "remaining_time": "0:18:57", "throughput": "481.83", "total_tokens": 662624}
105
- {"current_steps": 105, "total_steps": 190, "loss": 0.0076, "learning_rate": 2.2821106431308546e-06, "epoch": 2.7009646302250805, "percentage": 55.26, "elapsed_time": "0:23:08", "remaining_time": "0:18:43", "throughput": "481.67", "total_tokens": 668768}
106
- {"current_steps": 106, "total_steps": 190, "loss": 0.0485, "learning_rate": 2.238678841830867e-06, "epoch": 2.7266881028938905, "percentage": 55.79, "elapsed_time": "0:23:21", "remaining_time": "0:18:30", "throughput": "481.57", "total_tokens": 674992}
107
- {"current_steps": 107, "total_steps": 190, "loss": 0.007, "learning_rate": 2.195326641487132e-06, "epoch": 2.752411575562701, "percentage": 56.32, "elapsed_time": "0:23:34", "remaining_time": "0:18:17", "throughput": "481.41", "total_tokens": 681120}
108
- {"current_steps": 108, "total_steps": 190, "loss": 0.0347, "learning_rate": 2.1520672475998374e-06, "epoch": 2.778135048231511, "percentage": 56.84, "elapsed_time": "0:23:48", "remaining_time": "0:18:04", "throughput": "481.34", "total_tokens": 687376}
109
- {"current_steps": 109, "total_steps": 190, "loss": 0.0142, "learning_rate": 2.1089138373994226e-06, "epoch": 2.8038585209003215, "percentage": 57.37, "elapsed_time": "0:24:01", "remaining_time": "0:17:51", "throughput": "481.52", "total_tokens": 693984}
110
- {"current_steps": 110, "total_steps": 190, "loss": 0.0414, "learning_rate": 2.0658795558326745e-06, "epoch": 2.829581993569132, "percentage": 57.89, "elapsed_time": "0:24:14", "remaining_time": "0:17:37", "throughput": "481.52", "total_tokens": 700352}
111
- {"current_steps": 111, "total_steps": 190, "loss": 0.0419, "learning_rate": 2.022977511558638e-06, "epoch": 2.855305466237942, "percentage": 58.42, "elapsed_time": "0:24:27", "remaining_time": "0:17:24", "throughput": "481.56", "total_tokens": 706768}
112
- {"current_steps": 112, "total_steps": 190, "loss": 0.043, "learning_rate": 1.9802207729556023e-06, "epoch": 2.8810289389067525, "percentage": 58.95, "elapsed_time": "0:24:40", "remaining_time": "0:17:11", "throughput": "481.65", "total_tokens": 713248}
113
- {"current_steps": 113, "total_steps": 190, "loss": 0.0192, "learning_rate": 1.937622364140338e-06, "epoch": 2.906752411575563, "percentage": 59.47, "elapsed_time": "0:24:54", "remaining_time": "0:16:58", "throughput": "481.62", "total_tokens": 719568}
114
- {"current_steps": 114, "total_steps": 190, "loss": 0.0427, "learning_rate": 1.895195261000831e-06, "epoch": 2.932475884244373, "percentage": 60.0, "elapsed_time": "0:25:07", "remaining_time": "0:16:44", "throughput": "481.66", "total_tokens": 725984}
115
- {"current_steps": 115, "total_steps": 190, "loss": 0.0116, "learning_rate": 1.852952387243698e-06, "epoch": 2.958199356913183, "percentage": 60.53, "elapsed_time": "0:25:20", "remaining_time": "0:16:31", "throughput": "481.58", "total_tokens": 732224}
116
- {"current_steps": 116, "total_steps": 190, "loss": 0.0135, "learning_rate": 1.8109066104575023e-06, "epoch": 2.9839228295819935, "percentage": 61.05, "elapsed_time": "0:25:33", "remaining_time": "0:16:18", "throughput": "481.53", "total_tokens": 738496}
117
- {"current_steps": 117, "total_steps": 190, "loss": 0.0128, "learning_rate": 1.7690707381931585e-06, "epoch": 3.009646302250804, "percentage": 61.58, "elapsed_time": "0:25:46", "remaining_time": "0:16:05", "throughput": "481.54", "total_tokens": 744880}
118
- {"current_steps": 118, "total_steps": 190, "loss": 0.0021, "learning_rate": 1.7274575140626318e-06, "epoch": 3.035369774919614, "percentage": 62.11, "elapsed_time": "0:26:00", "remaining_time": "0:15:51", "throughput": "481.65", "total_tokens": 751408}
119
- {"current_steps": 119, "total_steps": 190, "loss": 0.0057, "learning_rate": 1.686079613857109e-06, "epoch": 3.0610932475884245, "percentage": 62.63, "elapsed_time": "0:26:13", "remaining_time": "0:15:38", "throughput": "481.57", "total_tokens": 757632}
120
- {"current_steps": 120, "total_steps": 190, "loss": 0.0197, "learning_rate": 1.6449496416858285e-06, "epoch": 3.0868167202572345, "percentage": 63.16, "elapsed_time": "0:26:26", "remaining_time": "0:15:25", "throughput": "481.54", "total_tokens": 763936}
121
- {"current_steps": 121, "total_steps": 190, "loss": 0.0017, "learning_rate": 1.6040801261367494e-06, "epoch": 3.112540192926045, "percentage": 63.68, "elapsed_time": "0:26:39", "remaining_time": "0:15:12", "throughput": "481.40", "total_tokens": 770064}
122
- {"current_steps": 122, "total_steps": 190, "loss": 0.0068, "learning_rate": 1.56348351646022e-06, "epoch": 3.1382636655948555, "percentage": 64.21, "elapsed_time": "0:26:52", "remaining_time": "0:14:58", "throughput": "481.24", "total_tokens": 776176}
123
- {"current_steps": 123, "total_steps": 190, "loss": 0.0022, "learning_rate": 1.5231721787768162e-06, "epoch": 3.1639871382636655, "percentage": 64.74, "elapsed_time": "0:27:06", "remaining_time": "0:14:45", "throughput": "481.20", "total_tokens": 782464}
124
- {"current_steps": 124, "total_steps": 190, "loss": 0.0162, "learning_rate": 1.4831583923105e-06, "epoch": 3.189710610932476, "percentage": 65.26, "elapsed_time": "0:27:19", "remaining_time": "0:14:32", "throughput": "481.37", "total_tokens": 789072}
125
- {"current_steps": 125, "total_steps": 190, "loss": 0.0014, "learning_rate": 1.443454345648252e-06, "epoch": 3.215434083601286, "percentage": 65.79, "elapsed_time": "0:27:32", "remaining_time": "0:14:19", "throughput": "481.43", "total_tokens": 795536}
126
- {"current_steps": 126, "total_steps": 190, "loss": 0.0063, "learning_rate": 1.4040721330273063e-06, "epoch": 3.2411575562700965, "percentage": 66.32, "elapsed_time": "0:27:45", "remaining_time": "0:14:06", "throughput": "481.43", "total_tokens": 801888}
127
- {"current_steps": 127, "total_steps": 190, "loss": 0.0282, "learning_rate": 1.3650237506511333e-06, "epoch": 3.266881028938907, "percentage": 66.84, "elapsed_time": "0:27:58", "remaining_time": "0:13:52", "throughput": "481.54", "total_tokens": 808432}
128
- {"current_steps": 128, "total_steps": 190, "loss": 0.0003, "learning_rate": 1.3263210930352737e-06, "epoch": 3.292604501607717, "percentage": 67.37, "elapsed_time": "0:28:12", "remaining_time": "0:13:39", "throughput": "481.60", "total_tokens": 814896}
129
- {"current_steps": 129, "total_steps": 190, "loss": 0.0002, "learning_rate": 1.2879759493841577e-06, "epoch": 3.3183279742765275, "percentage": 67.89, "elapsed_time": "0:28:25", "remaining_time": "0:13:26", "throughput": "481.57", "total_tokens": 821200}
130
- {"current_steps": 130, "total_steps": 190, "loss": 0.0004, "learning_rate": 1.2500000000000007e-06, "epoch": 3.3440514469453375, "percentage": 68.42, "elapsed_time": "0:28:38", "remaining_time": "0:13:13", "throughput": "481.59", "total_tokens": 827584}
131
- {"current_steps": 131, "total_steps": 190, "loss": 0.0169, "learning_rate": 1.2124048127248644e-06, "epoch": 3.369774919614148, "percentage": 68.95, "elapsed_time": "0:28:51", "remaining_time": "0:12:59", "throughput": "481.65", "total_tokens": 834048}
132
- {"current_steps": 132, "total_steps": 190, "loss": 0.0127, "learning_rate": 1.1752018394169882e-06, "epoch": 3.395498392282958, "percentage": 69.47, "elapsed_time": "0:29:04", "remaining_time": "0:12:46", "throughput": "481.55", "total_tokens": 840240}
133
- {"current_steps": 133, "total_steps": 190, "loss": 0.0045, "learning_rate": 1.1384024124624324e-06, "epoch": 3.4212218649517685, "percentage": 70.0, "elapsed_time": "0:29:18", "remaining_time": "0:12:33", "throughput": "481.46", "total_tokens": 846448}
134
- {"current_steps": 134, "total_steps": 190, "loss": 0.0924, "learning_rate": 1.1020177413231334e-06, "epoch": 3.446945337620579, "percentage": 70.53, "elapsed_time": "0:29:31", "remaining_time": "0:12:20", "throughput": "481.54", "total_tokens": 852928}
135
- {"current_steps": 135, "total_steps": 190, "loss": 0.0067, "learning_rate": 1.0660589091223854e-06, "epoch": 3.472668810289389, "percentage": 71.05, "elapsed_time": "0:29:44", "remaining_time": "0:12:06", "throughput": "481.56", "total_tokens": 859312}
136
- {"current_steps": 136, "total_steps": 190, "loss": 0.003, "learning_rate": 1.0305368692688175e-06, "epoch": 3.4983922829581995, "percentage": 71.58, "elapsed_time": "0:29:57", "remaining_time": "0:11:53", "throughput": "481.43", "total_tokens": 865440}
137
- {"current_steps": 137, "total_steps": 190, "loss": 0.0164, "learning_rate": 9.95462442119879e-07, "epoch": 3.5241157556270095, "percentage": 72.11, "elapsed_time": "0:30:10", "remaining_time": "0:11:40", "throughput": "481.52", "total_tokens": 871968}
138
- {"current_steps": 138, "total_steps": 190, "loss": 0.0018, "learning_rate": 9.608463116858544e-07, "epoch": 3.54983922829582, "percentage": 72.63, "elapsed_time": "0:30:24", "remaining_time": "0:11:27", "throughput": "481.54", "total_tokens": 878352}
139
- {"current_steps": 139, "total_steps": 190, "loss": 0.0226, "learning_rate": 9.266990223754069e-07, "epoch": 3.57556270096463, "percentage": 73.16, "elapsed_time": "0:30:37", "remaining_time": "0:11:14", "throughput": "481.56", "total_tokens": 884736}
140
- {"current_steps": 140, "total_steps": 190, "loss": 0.0008, "learning_rate": 8.930309757836517e-07, "epoch": 3.6012861736334405, "percentage": 73.68, "elapsed_time": "0:30:50", "remaining_time": "0:11:00", "throughput": "481.50", "total_tokens": 891008}
141
- {"current_steps": 141, "total_steps": 190, "loss": 0.0004, "learning_rate": 8.598524275237321e-07, "epoch": 3.627009646302251, "percentage": 74.21, "elapsed_time": "0:31:03", "remaining_time": "0:10:47", "throughput": "481.37", "total_tokens": 897120}
142
- {"current_steps": 142, "total_steps": 190, "loss": 0.0008, "learning_rate": 8.271734841028553e-07, "epoch": 3.652733118971061, "percentage": 74.74, "elapsed_time": "0:31:16", "remaining_time": "0:10:34", "throughput": "481.41", "total_tokens": 903536}
143
- {"current_steps": 143, "total_steps": 190, "loss": 0.0256, "learning_rate": 7.950040998437541e-07, "epoch": 3.6784565916398715, "percentage": 75.26, "elapsed_time": "0:31:30", "remaining_time": "0:10:21", "throughput": "481.37", "total_tokens": 909824}
144
- {"current_steps": 144, "total_steps": 190, "loss": 0.0005, "learning_rate": 7.633540738525066e-07, "epoch": 3.7041800643086815, "percentage": 75.79, "elapsed_time": "0:31:43", "remaining_time": "0:10:07", "throughput": "481.34", "total_tokens": 916112}
145
- {"current_steps": 145, "total_steps": 190, "loss": 0.0045, "learning_rate": 7.322330470336314e-07, "epoch": 3.729903536977492, "percentage": 76.32, "elapsed_time": "0:31:56", "remaining_time": "0:09:54", "throughput": "481.41", "total_tokens": 922592}
146
- {"current_steps": 146, "total_steps": 190, "loss": 0.0005, "learning_rate": 7.016504991533727e-07, "epoch": 3.755627009646302, "percentage": 76.84, "elapsed_time": "0:32:09", "remaining_time": "0:09:41", "throughput": "481.25", "total_tokens": 928640}
147
- {"current_steps": 147, "total_steps": 190, "loss": 0.0069, "learning_rate": 6.716157459520739e-07, "epoch": 3.7813504823151125, "percentage": 77.37, "elapsed_time": "0:32:22", "remaining_time": "0:09:28", "throughput": "481.50", "total_tokens": 935488}
148
- {"current_steps": 148, "total_steps": 190, "loss": 0.015, "learning_rate": 6.421379363065142e-07, "epoch": 3.807073954983923, "percentage": 77.89, "elapsed_time": "0:32:36", "remaining_time": "0:09:15", "throughput": "481.56", "total_tokens": 941952}
149
- {"current_steps": 149, "total_steps": 190, "loss": 0.0012, "learning_rate": 6.1322604944307e-07, "epoch": 3.832797427652733, "percentage": 78.42, "elapsed_time": "0:32:49", "remaining_time": "0:09:01", "throughput": "481.59", "total_tokens": 948368}
150
- {"current_steps": 150, "total_steps": 190, "loss": 0.0095, "learning_rate": 5.848888922025553e-07, "epoch": 3.8585209003215435, "percentage": 78.95, "elapsed_time": "0:33:02", "remaining_time": "0:08:48", "throughput": "481.60", "total_tokens": 954752}
151
- {"current_steps": 151, "total_steps": 190, "loss": 0.0271, "learning_rate": 5.571350963575728e-07, "epoch": 3.884244372990354, "percentage": 79.47, "elapsed_time": "0:33:15", "remaining_time": "0:08:35", "throughput": "481.67", "total_tokens": 961248}
152
- {"current_steps": 152, "total_steps": 190, "loss": 0.0201, "learning_rate": 5.299731159831953e-07, "epoch": 3.909967845659164, "percentage": 80.0, "elapsed_time": "0:33:28", "remaining_time": "0:08:22", "throughput": "481.58", "total_tokens": 967424}
153
- {"current_steps": 153, "total_steps": 190, "loss": 0.012, "learning_rate": 5.034112248817685e-07, "epoch": 3.935691318327974, "percentage": 80.53, "elapsed_time": "0:33:42", "remaining_time": "0:08:08", "throughput": "481.54", "total_tokens": 973696}
154
- {"current_steps": 154, "total_steps": 190, "loss": 0.023, "learning_rate": 4.774575140626317e-07, "epoch": 3.9614147909967845, "percentage": 81.05, "elapsed_time": "0:33:55", "remaining_time": "0:07:55", "throughput": "481.59", "total_tokens": 980144}
155
- {"current_steps": 155, "total_steps": 190, "loss": 0.0156, "learning_rate": 4.5211988927752026e-07, "epoch": 3.987138263665595, "percentage": 81.58, "elapsed_time": "0:34:08", "remaining_time": "0:07:42", "throughput": "481.51", "total_tokens": 986352}
156
- {"current_steps": 156, "total_steps": 190, "loss": 0.0009, "learning_rate": 4.27406068612396e-07, "epoch": 4.012861736334405, "percentage": 82.11, "elapsed_time": "0:34:21", "remaining_time": "0:07:29", "throughput": "481.59", "total_tokens": 992880}
157
- {"current_steps": 157, "total_steps": 190, "loss": 0.0017, "learning_rate": 4.033235801364402e-07, "epoch": 4.038585209003215, "percentage": 82.63, "elapsed_time": "0:34:34", "remaining_time": "0:07:16", "throughput": "481.58", "total_tokens": 999200}
158
- {"current_steps": 158, "total_steps": 190, "loss": 0.0015, "learning_rate": 3.798797596089351e-07, "epoch": 4.064308681672026, "percentage": 83.16, "elapsed_time": "0:34:48", "remaining_time": "0:07:02", "throughput": "481.58", "total_tokens": 1005568}
159
- {"current_steps": 159, "total_steps": 190, "loss": 0.0035, "learning_rate": 3.5708174824471947e-07, "epoch": 4.090032154340836, "percentage": 83.68, "elapsed_time": "0:35:01", "remaining_time": "0:06:49", "throughput": "481.49", "total_tokens": 1011728}
160
- {"current_steps": 160, "total_steps": 190, "loss": 0.0016, "learning_rate": 3.3493649053890325e-07, "epoch": 4.115755627009646, "percentage": 84.21, "elapsed_time": "0:35:14", "remaining_time": "0:06:36", "throughput": "481.58", "total_tokens": 1018272}
161
- {"current_steps": 161, "total_steps": 190, "loss": 0.0028, "learning_rate": 3.134507321515107e-07, "epoch": 4.141479099678457, "percentage": 84.74, "elapsed_time": "0:35:27", "remaining_time": "0:06:23", "throughput": "481.61", "total_tokens": 1024688}
162
- {"current_steps": 162, "total_steps": 190, "loss": 0.0006, "learning_rate": 2.9263101785268253e-07, "epoch": 4.167202572347267, "percentage": 85.26, "elapsed_time": "0:35:40", "remaining_time": "0:06:10", "throughput": "481.65", "total_tokens": 1031152}
163
- {"current_steps": 163, "total_steps": 190, "loss": 0.0013, "learning_rate": 2.7248368952908055e-07, "epoch": 4.192926045016077, "percentage": 85.79, "elapsed_time": "0:35:54", "remaining_time": "0:05:56", "throughput": "481.71", "total_tokens": 1037632}
164
- {"current_steps": 164, "total_steps": 190, "loss": 0.0006, "learning_rate": 2.53014884252083e-07, "epoch": 4.218649517684887, "percentage": 86.32, "elapsed_time": "0:36:07", "remaining_time": "0:05:43", "throughput": "481.69", "total_tokens": 1043936}
165
- {"current_steps": 165, "total_steps": 190, "loss": 0.0017, "learning_rate": 2.3423053240837518e-07, "epoch": 4.244372990353698, "percentage": 86.84, "elapsed_time": "0:36:20", "remaining_time": "0:05:30", "throughput": "481.57", "total_tokens": 1050048}
166
- {"current_steps": 166, "total_steps": 190, "loss": 0.0004, "learning_rate": 2.1613635589349756e-07, "epoch": 4.270096463022508, "percentage": 87.37, "elapsed_time": "0:36:33", "remaining_time": "0:05:17", "throughput": "481.61", "total_tokens": 1056496}
167
- {"current_steps": 167, "total_steps": 190, "loss": 0.0049, "learning_rate": 1.9873786636889908e-07, "epoch": 4.295819935691318, "percentage": 87.89, "elapsed_time": "0:36:46", "remaining_time": "0:05:03", "throughput": "481.61", "total_tokens": 1062848}
168
- {"current_steps": 168, "total_steps": 190, "loss": 0.0071, "learning_rate": 1.8204036358303173e-07, "epoch": 4.321543408360129, "percentage": 88.42, "elapsed_time": "0:37:00", "remaining_time": "0:04:50", "throughput": "481.58", "total_tokens": 1069136}
169
- {"current_steps": 169, "total_steps": 190, "loss": 0.0011, "learning_rate": 1.6604893375699594e-07, "epoch": 4.347266881028939, "percentage": 88.95, "elapsed_time": "0:37:13", "remaining_time": "0:04:37", "throughput": "481.50", "total_tokens": 1075328}
170
- {"current_steps": 170, "total_steps": 190, "loss": 0.0004, "learning_rate": 1.507684480352292e-07, "epoch": 4.372990353697749, "percentage": 89.47, "elapsed_time": "0:37:26", "remaining_time": "0:04:24", "throughput": "481.50", "total_tokens": 1081696}
171
- {"current_steps": 171, "total_steps": 190, "loss": 0.0007, "learning_rate": 1.362035610017079e-07, "epoch": 4.39871382636656, "percentage": 90.0, "elapsed_time": "0:37:39", "remaining_time": "0:04:11", "throughput": "481.53", "total_tokens": 1088112}
172
- {"current_steps": 172, "total_steps": 190, "loss": 0.0017, "learning_rate": 1.223587092621162e-07, "epoch": 4.42443729903537, "percentage": 90.53, "elapsed_time": "0:37:52", "remaining_time": "0:03:57", "throughput": "481.55", "total_tokens": 1094512}
173
- {"current_steps": 173, "total_steps": 190, "loss": 0.0007, "learning_rate": 1.0923811009241142e-07, "epoch": 4.45016077170418, "percentage": 91.05, "elapsed_time": "0:38:06", "remaining_time": "0:03:44", "throughput": "481.62", "total_tokens": 1101040}
174
- {"current_steps": 174, "total_steps": 190, "loss": 0.0003, "learning_rate": 9.684576015420277e-08, "epoch": 4.47588424437299, "percentage": 91.58, "elapsed_time": "0:38:19", "remaining_time": "0:03:31", "throughput": "481.52", "total_tokens": 1107168}
175
- {"current_steps": 175, "total_steps": 190, "loss": 0.0046, "learning_rate": 8.518543427732951e-08, "epoch": 4.501607717041801, "percentage": 92.11, "elapsed_time": "0:38:32", "remaining_time": "0:03:18", "throughput": "481.47", "total_tokens": 1113408}
176
- {"current_steps": 176, "total_steps": 190, "loss": 0.0038, "learning_rate": 7.426068431000883e-08, "epoch": 4.527331189710611, "percentage": 92.63, "elapsed_time": "0:38:45", "remaining_time": "0:03:04", "throughput": "481.39", "total_tokens": 1119568}
177
- {"current_steps": 177, "total_steps": 190, "loss": 0.0036, "learning_rate": 6.407483803691216e-08, "epoch": 4.553054662379421, "percentage": 93.16, "elapsed_time": "0:38:58", "remaining_time": "0:02:51", "throughput": "481.44", "total_tokens": 1126048}
178
- {"current_steps": 178, "total_steps": 190, "loss": 0.0056, "learning_rate": 5.463099816548578e-08, "epoch": 4.578778135048232, "percentage": 93.68, "elapsed_time": "0:39:12", "remaining_time": "0:02:38", "throughput": "481.44", "total_tokens": 1132400}
179
- {"current_steps": 179, "total_steps": 190, "loss": 0.0057, "learning_rate": 4.593204138084006e-08, "epoch": 4.604501607717042, "percentage": 94.21, "elapsed_time": "0:39:25", "remaining_time": "0:02:25", "throughput": "481.48", "total_tokens": 1138832}
180
- {"current_steps": 180, "total_steps": 190, "loss": 0.002, "learning_rate": 3.798061746947995e-08, "epoch": 4.630225080385852, "percentage": 94.74, "elapsed_time": "0:39:38", "remaining_time": "0:02:12", "throughput": "481.54", "total_tokens": 1145344}
181
- {"current_steps": 181, "total_steps": 190, "loss": 0.0003, "learning_rate": 3.077914851215585e-08, "epoch": 4.655948553054662, "percentage": 95.26, "elapsed_time": "0:39:51", "remaining_time": "0:01:58", "throughput": "481.47", "total_tokens": 1151536}
182
- {"current_steps": 182, "total_steps": 190, "loss": 0.0002, "learning_rate": 2.4329828146074096e-08, "epoch": 4.681672025723473, "percentage": 95.79, "elapsed_time": "0:40:04", "remaining_time": "0:01:45", "throughput": "481.39", "total_tokens": 1157696}
183
- {"current_steps": 183, "total_steps": 190, "loss": 0.0043, "learning_rate": 1.8634620896695044e-08, "epoch": 4.707395498392283, "percentage": 96.32, "elapsed_time": "0:40:18", "remaining_time": "0:01:32", "throughput": "481.25", "total_tokens": 1163712}
184
- {"current_steps": 184, "total_steps": 190, "loss": 0.0002, "learning_rate": 1.3695261579316776e-08, "epoch": 4.733118971061093, "percentage": 96.84, "elapsed_time": "0:40:31", "remaining_time": "0:01:19", "throughput": "481.18", "total_tokens": 1169888}
185
- {"current_steps": 185, "total_steps": 190, "loss": 0.0013, "learning_rate": 9.513254770636138e-09, "epoch": 4.758842443729904, "percentage": 97.37, "elapsed_time": "0:40:44", "remaining_time": "0:01:06", "throughput": "481.19", "total_tokens": 1176272}
186
- {"current_steps": 186, "total_steps": 190, "loss": 0.0023, "learning_rate": 6.089874350439507e-09, "epoch": 4.784565916398714, "percentage": 97.89, "elapsed_time": "0:40:57", "remaining_time": "0:00:52", "throughput": "481.22", "total_tokens": 1182688}
187
- {"current_steps": 187, "total_steps": 190, "loss": 0.0002, "learning_rate": 3.4261631135654174e-09, "epoch": 4.810289389067524, "percentage": 98.42, "elapsed_time": "0:41:10", "remaining_time": "0:00:39", "throughput": "481.35", "total_tokens": 1189360}
188
- {"current_steps": 188, "total_steps": 190, "loss": 0.0015, "learning_rate": 1.5229324522605949e-09, "epoch": 4.836012861736334, "percentage": 98.95, "elapsed_time": "0:41:24", "remaining_time": "0:00:26", "throughput": "481.32", "total_tokens": 1195632}
189
- {"current_steps": 189, "total_steps": 190, "loss": 0.0002, "learning_rate": 3.8076210902182607e-10, "epoch": 4.861736334405145, "percentage": 99.47, "elapsed_time": "0:41:37", "remaining_time": "0:00:13", "throughput": "481.33", "total_tokens": 1202016}
190
- {"current_steps": 190, "total_steps": 190, "loss": 0.0028, "learning_rate": 0.0, "epoch": 4.887459807073955, "percentage": 100.0, "elapsed_time": "0:41:50", "remaining_time": "0:00:00", "throughput": "481.34", "total_tokens": 1208400}
191
- {"current_steps": 190, "total_steps": 190, "epoch": 4.887459807073955, "percentage": 100.0, "elapsed_time": "0:42:51", "remaining_time": "0:00:00", "throughput": "469.99", "total_tokens": 1208400}
 
1
+ {"current_steps": 5, "total_steps": 78, "percentage": 6.41, "elapsed_time": "0:00:00", "remaining_time": "0:00:05"}
2
+ {"current_steps": 10, "total_steps": 78, "percentage": 12.82, "elapsed_time": "0:00:00", "remaining_time": "0:00:05"}
3
+ {"current_steps": 15, "total_steps": 78, "percentage": 19.23, "elapsed_time": "0:00:01", "remaining_time": "0:00:04"}
4
+ {"current_steps": 20, "total_steps": 78, "percentage": 25.64, "elapsed_time": "0:00:01", "remaining_time": "0:00:04"}
5
+ {"current_steps": 25, "total_steps": 78, "percentage": 32.05, "elapsed_time": "0:00:01", "remaining_time": "0:00:04"}
6
+ {"current_steps": 30, "total_steps": 78, "percentage": 38.46, "elapsed_time": "0:00:02", "remaining_time": "0:00:03"}
7
+ {"current_steps": 35, "total_steps": 78, "percentage": 44.87, "elapsed_time": "0:00:02", "remaining_time": "0:00:03"}
8
+ {"current_steps": 40, "total_steps": 78, "percentage": 51.28, "elapsed_time": "0:00:03", "remaining_time": "0:00:02"}
9
+ {"current_steps": 45, "total_steps": 78, "percentage": 57.69, "elapsed_time": "0:00:03", "remaining_time": "0:00:02"}
10
+ {"current_steps": 50, "total_steps": 78, "percentage": 64.1, "elapsed_time": "0:00:03", "remaining_time": "0:00:02"}
11
+ {"current_steps": 55, "total_steps": 78, "percentage": 70.51, "elapsed_time": "0:00:04", "remaining_time": "0:00:01"}
12
+ {"current_steps": 60, "total_steps": 78, "percentage": 76.92, "elapsed_time": "0:00:04", "remaining_time": "0:00:01"}
13
+ {"current_steps": 65, "total_steps": 78, "percentage": 83.33, "elapsed_time": "0:00:05", "remaining_time": "0:00:01"}
14
+ {"current_steps": 70, "total_steps": 78, "percentage": 89.74, "elapsed_time": "0:00:05", "remaining_time": "0:00:00"}
15
+ {"current_steps": 75, "total_steps": 78, "percentage": 96.15, "elapsed_time": "0:00:05", "remaining_time": "0:00:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.yaml CHANGED
@@ -1,30 +1,18 @@
1
- bf16: true
2
  cutoff_len: 1024
3
- dataset: truth_train_0716
4
  dataset_dir: data
5
- ddp_timeout: 180000000
6
- deepspeed: cache/ds_z2_config.json
7
- do_train: true
8
  finetuning_type: full
9
  flash_attn: auto
10
- gradient_accumulation_steps: 8
11
- include_num_input_tokens_seen: true
12
- learning_rate: 5.0e-06
13
- logging_steps: 1
14
- lr_scheduler_type: cosine
15
- max_grad_norm: 1.0
16
  max_samples: 100000
17
- model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
18
- num_train_epochs: 5.0
19
- optim: adamw_torch
20
- output_dir: saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3
21
- packing: false
22
- per_device_train_batch_size: 2
23
- plot_loss: true
24
  preprocessing_num_workers: 16
25
  quantization_method: bitsandbytes
26
- report_to: none
27
- save_steps: 1000
28
  stage: sft
 
29
  template: llama3
30
- warmup_steps: 10
 
 
1
  cutoff_len: 1024
2
+ dataset: truth_dev_0716
3
  dataset_dir: data
4
+ do_predict: true
 
 
5
  finetuning_type: full
6
  flash_attn: auto
7
+ max_new_tokens: 512
 
 
 
 
 
8
  max_samples: 100000
9
+ model_name_or_path: saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3
10
+ output_dir: saves/LLaMA3-8B-Chat/full/eval_2024-07-23-06-52-5_llama3
11
+ per_device_eval_batch_size: 2
12
+ predict_with_generate: true
 
 
 
13
  preprocessing_num_workers: 16
14
  quantization_method: bitsandbytes
 
 
15
  stage: sft
16
+ temperature: 0.95
17
  template: llama3
18
+ top_p: 0.7