second commit
Browse files- all_results.json +8 -7
- generated_predictions.jsonl +0 -0
- llamaboard_config.yaml +12 -59
- predict_results.json +10 -0
- running_log.txt +82 -544
- trainer_log.jsonl +15 -191
- training_args.yaml +10 -21
all_results.json
CHANGED
|
@@ -1,9 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
|
|
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"predict_bleu-4": 87.79619110576924,
|
| 3 |
+
"predict_model_preparation_time": 0.0052,
|
| 4 |
+
"predict_rouge-1": 95.2724358974359,
|
| 5 |
+
"predict_rouge-2": 0.0,
|
| 6 |
+
"predict_rouge-l": 95.2724358974359,
|
| 7 |
+
"predict_runtime": 8.8422,
|
| 8 |
+
"predict_samples_per_second": 140.575,
|
| 9 |
+
"predict_steps_per_second": 8.821
|
| 10 |
}
|
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:
|
| 3 |
top.finetuning_type: full
|
| 4 |
top.model_name: LLaMA3.1-8B-Chat
|
| 5 |
top.quantization_bit: none
|
|
@@ -7,61 +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.mask_history: false
|
| 41 |
-
train.max_grad_norm: '1.0'
|
| 42 |
-
train.max_samples: '100000'
|
| 43 |
-
train.neat_packing: false
|
| 44 |
-
train.neftune_alpha: 0
|
| 45 |
-
train.num_train_epochs: '5.0'
|
| 46 |
-
train.optim: adamw_torch
|
| 47 |
-
train.packing: false
|
| 48 |
-
train.ppo_score_norm: false
|
| 49 |
-
train.ppo_whiten_rewards: false
|
| 50 |
-
train.pref_beta: 0.1
|
| 51 |
-
train.pref_ftx: 0
|
| 52 |
-
train.pref_loss: sigmoid
|
| 53 |
-
train.report_to: false
|
| 54 |
-
train.resize_vocab: false
|
| 55 |
-
train.reward_model: null
|
| 56 |
-
train.save_steps: 5000
|
| 57 |
-
train.shift_attn: false
|
| 58 |
-
train.train_on_prompt: false
|
| 59 |
-
train.training_stage: Supervised Fine-Tuning
|
| 60 |
-
train.use_badam: false
|
| 61 |
-
train.use_dora: false
|
| 62 |
-
train.use_galore: false
|
| 63 |
-
train.use_llama_pro: false
|
| 64 |
-
train.use_pissa: false
|
| 65 |
-
train.use_rslora: false
|
| 66 |
-
train.val_size: 0
|
| 67 |
-
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_2024-07-30-02-00-04_truthqa_bench1
|
| 9 |
+
eval.predict: true
|
| 10 |
+
eval.temperature: 0.95
|
| 11 |
+
eval.top_p: 0.7
|
| 12 |
top.booster: auto
|
| 13 |
+
top.checkpoint_path: train_2024-07-30-02-00-04_llama3.1_truthqa_bench_1
|
| 14 |
top.finetuning_type: full
|
| 15 |
top.model_name: LLaMA3.1-8B-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 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu-4": 87.79619110576924,
|
| 3 |
+
"predict_model_preparation_time": 0.0052,
|
| 4 |
+
"predict_rouge-1": 95.2724358974359,
|
| 5 |
+
"predict_rouge-2": 0.0,
|
| 6 |
+
"predict_rouge-l": 95.2724358974359,
|
| 7 |
+
"predict_runtime": 8.8422,
|
| 8 |
+
"predict_samples_per_second": 140.575,
|
| 9 |
+
"predict_steps_per_second": 8.821
|
| 10 |
+
}
|
running_log.txt
CHANGED
|
@@ -1,79 +1,59 @@
|
|
| 1 |
-
07/30/2024 02:
|
| 2 |
|
| 3 |
-
|
| 4 |
|
| 5 |
-
07
|
| 6 |
|
| 7 |
-
|
| 8 |
|
| 9 |
-
|
| 10 |
|
| 11 |
-
07/30/2024 02:
|
| 12 |
|
| 13 |
-
07/30/2024 02:
|
| 14 |
|
| 15 |
-
|
| 16 |
|
| 17 |
-
07/30/2024 02:
|
| 18 |
|
| 19 |
-
07/30/2024 02:
|
| 20 |
|
| 21 |
-
07
|
| 22 |
|
| 23 |
-
07
|
| 24 |
|
| 25 |
-
07
|
| 26 |
|
| 27 |
-
07
|
| 28 |
|
| 29 |
-
07
|
| 30 |
|
| 31 |
-
07/30/2024 02:
|
| 32 |
|
| 33 |
-
07/30/2024 02:
|
| 34 |
|
| 35 |
-
07/30/2024 02:
|
| 36 |
|
| 37 |
-
07/30/2024 02:
|
| 38 |
|
| 39 |
-
07/30/2024 02:
|
| 40 |
|
| 41 |
-
|
| 42 |
|
| 43 |
-
|
| 44 |
|
| 45 |
-
|
| 46 |
|
| 47 |
-
|
| 48 |
|
| 49 |
-
|
| 50 |
|
| 51 |
-
|
| 52 |
|
| 53 |
-
[INFO|
|
| 54 |
|
| 55 |
-
07
|
| 56 |
-
|
| 57 |
-
07/30/2024 02:01:44 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
|
| 58 |
-
|
| 59 |
-
07/30/2024 02:01:45 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
|
| 60 |
-
|
| 61 |
-
07/30/2024 02:01:45 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
|
| 62 |
-
|
| 63 |
-
07/30/2024 02:01:45 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
|
| 64 |
-
|
| 65 |
-
07/30/2024 02:01:45 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
|
| 66 |
-
|
| 67 |
-
07/30/2024 02:01:45 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
|
| 68 |
-
|
| 69 |
-
07/30/2024 02:01:45 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
|
| 70 |
-
|
| 71 |
-
07/30/2024 02:01:45 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
|
| 72 |
-
|
| 73 |
-
[INFO|configuration_utils.py:733] 2024-07-30 02:01:49,540 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/b2a4d0f33b41fcd59a6d31662cc63b8d53367e1e/config.json
|
| 74 |
-
|
| 75 |
-
[INFO|configuration_utils.py:800] 2024-07-30 02:01:49,542 >> Model config LlamaConfig {
|
| 76 |
-
"_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
| 77 |
"architectures": [
|
| 78 |
"LlamaForCausalLM"
|
| 79 |
],
|
|
@@ -108,16 +88,18 @@
|
|
| 108 |
"tie_word_embeddings": false,
|
| 109 |
"torch_dtype": "bfloat16",
|
| 110 |
"transformers_version": "4.43.3",
|
| 111 |
-
"use_cache":
|
| 112 |
"vocab_size": 128256
|
| 113 |
}
|
| 114 |
|
| 115 |
|
| 116 |
-
[INFO|
|
| 117 |
|
| 118 |
-
[INFO|modeling_utils.py:
|
| 119 |
|
| 120 |
-
[INFO|
|
|
|
|
|
|
|
| 121 |
"bos_token_id": 128000,
|
| 122 |
"eos_token_id": [
|
| 123 |
128001,
|
|
@@ -127,15 +109,29 @@
|
|
| 127 |
}
|
| 128 |
|
| 129 |
|
| 130 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
|
|
|
|
| 132 |
|
| 133 |
-
[INFO|modeling_utils.py:
|
|
|
|
|
|
|
|
|
|
| 134 |
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.
|
| 135 |
|
| 136 |
-
[INFO|configuration_utils.py:
|
| 137 |
|
| 138 |
-
[INFO|configuration_utils.py:1038] 2024-07-30 02:
|
| 139 |
"bos_token_id": 128000,
|
| 140 |
"do_sample": true,
|
| 141 |
"eos_token_id": [
|
|
@@ -148,518 +144,60 @@ If your task is similar to the task the model of the checkpoint was trained on,
|
|
| 148 |
}
|
| 149 |
|
| 150 |
|
| 151 |
-
[INFO|
|
| 152 |
-
|
| 153 |
-
[INFO|attention.py:84] 2024-07-30 02:01:53,580 >> Using torch SDPA for faster training and inference.
|
| 154 |
-
|
| 155 |
-
[INFO|adapter.py:302] 2024-07-30 02:01:53,580 >> Upcasting trainable params to float32.
|
| 156 |
-
|
| 157 |
-
[INFO|adapter.py:48] 2024-07-30 02:01:53,580 >> Fine-tuning method: Full
|
| 158 |
-
|
| 159 |
-
[INFO|loader.py:196] 2024-07-30 02:01:53,625 >> trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
|
| 160 |
-
|
| 161 |
-
[INFO|trainer.py:648] 2024-07-30 02:01:53,631 >> Using auto half precision backend
|
| 162 |
-
|
| 163 |
-
07/30/2024 02:01:53 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 164 |
-
|
| 165 |
-
07/30/2024 02:01:53 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 166 |
-
|
| 167 |
-
07/30/2024 02:01:53 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 168 |
-
|
| 169 |
-
07/30/2024 02:01:53 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 170 |
-
|
| 171 |
-
07/30/2024 02:01:53 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
|
| 172 |
-
|
| 173 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 174 |
-
|
| 175 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 176 |
-
|
| 177 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 178 |
-
|
| 179 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 180 |
-
|
| 181 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
|
| 182 |
-
|
| 183 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 184 |
-
|
| 185 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 186 |
-
|
| 187 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 188 |
-
|
| 189 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 190 |
-
|
| 191 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
|
| 192 |
-
|
| 193 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 194 |
-
|
| 195 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 196 |
-
|
| 197 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 198 |
-
|
| 199 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 200 |
-
|
| 201 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
|
| 202 |
-
|
| 203 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 204 |
-
|
| 205 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 206 |
-
|
| 207 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 208 |
-
|
| 209 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 210 |
-
|
| 211 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
|
| 212 |
-
|
| 213 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 214 |
-
|
| 215 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 216 |
-
|
| 217 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 218 |
-
|
| 219 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 220 |
-
|
| 221 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
|
| 222 |
-
|
| 223 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 224 |
-
|
| 225 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 226 |
-
|
| 227 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 228 |
-
|
| 229 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 230 |
-
|
| 231 |
-
07/30/2024 02:01:54 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
|
| 232 |
-
|
| 233 |
-
[INFO|trainer.py:2134] 2024-07-30 02:02:17,907 >> ***** Running training *****
|
| 234 |
-
|
| 235 |
-
[INFO|trainer.py:2135] 2024-07-30 02:02:17,907 >> Num examples = 4,968
|
| 236 |
-
|
| 237 |
-
[INFO|trainer.py:2136] 2024-07-30 02:02:17,907 >> Num Epochs = 5
|
| 238 |
-
|
| 239 |
-
[INFO|trainer.py:2137] 2024-07-30 02:02:17,907 >> Instantaneous batch size per device = 2
|
| 240 |
-
|
| 241 |
-
[INFO|trainer.py:2140] 2024-07-30 02:02:17,907 >> Total train batch size (w. parallel, distributed & accumulation) = 128
|
| 242 |
-
|
| 243 |
-
[INFO|trainer.py:2141] 2024-07-30 02:02:17,907 >> Gradient Accumulation steps = 8
|
| 244 |
-
|
| 245 |
-
[INFO|trainer.py:2142] 2024-07-30 02:02:17,907 >> Total optimization steps = 190
|
| 246 |
-
|
| 247 |
-
[INFO|trainer.py:2143] 2024-07-30 02:02:17,909 >> Number of trainable parameters = 8,030,261,248
|
| 248 |
-
|
| 249 |
-
[INFO|callbacks.py:310] 2024-07-30 02:02:32,126 >> {'loss': 12.6483, 'learning_rate': 5.0000e-07, 'epoch': 0.03, 'throughput': 458.09}
|
| 250 |
-
|
| 251 |
-
[INFO|callbacks.py:310] 2024-07-30 02:02:45,352 >> {'loss': 12.2961, 'learning_rate': 1.0000e-06, 'epoch': 0.05, 'throughput': 468.19}
|
| 252 |
-
|
| 253 |
-
[INFO|callbacks.py:310] 2024-07-30 02:02:58,589 >> {'loss': 11.9707, 'learning_rate': 1.5000e-06, 'epoch': 0.08, 'throughput': 473.17}
|
| 254 |
-
|
| 255 |
-
[INFO|callbacks.py:310] 2024-07-30 02:03:11,796 >> {'loss': 11.1284, 'learning_rate': 2.0000e-06, 'epoch': 0.10, 'throughput': 470.33}
|
| 256 |
-
|
| 257 |
-
[INFO|callbacks.py:310] 2024-07-30 02:03:25,006 >> {'loss': 8.3234, 'learning_rate': 2.5000e-06, 'epoch': 0.13, 'throughput': 476.45}
|
| 258 |
-
|
| 259 |
-
[INFO|callbacks.py:310] 2024-07-30 02:03:38,195 >> {'loss': 5.8729, 'learning_rate': 3.0000e-06, 'epoch': 0.15, 'throughput': 475.31}
|
| 260 |
-
|
| 261 |
-
[INFO|callbacks.py:310] 2024-07-30 02:03:51,404 >> {'loss': 4.8266, 'learning_rate': 3.5000e-06, 'epoch': 0.18, 'throughput': 472.16}
|
| 262 |
-
|
| 263 |
-
[INFO|callbacks.py:310] 2024-07-30 02:04:04,608 >> {'loss': 2.5017, 'learning_rate': 4.0000e-06, 'epoch': 0.21, 'throughput': 472.66}
|
| 264 |
-
|
| 265 |
-
[INFO|callbacks.py:310] 2024-07-30 02:04:17,826 >> {'loss': 0.5637, 'learning_rate': 4.5000e-06, 'epoch': 0.23, 'throughput': 474.73}
|
| 266 |
-
|
| 267 |
-
[INFO|callbacks.py:310] 2024-07-30 02:04:31,021 >> {'loss': 0.2757, 'learning_rate': 5.0000e-06, 'epoch': 0.26, 'throughput': 475.87}
|
| 268 |
-
|
| 269 |
-
[INFO|callbacks.py:310] 2024-07-30 02:04:44,208 >> {'loss': 1.4131, 'learning_rate': 4.9996e-06, 'epoch': 0.28, 'throughput': 475.52}
|
| 270 |
-
|
| 271 |
-
[INFO|callbacks.py:310] 2024-07-30 02:04:57,404 >> {'loss': 0.2805, 'learning_rate': 4.9985e-06, 'epoch': 0.31, 'throughput': 475.40}
|
| 272 |
-
|
| 273 |
-
[INFO|callbacks.py:310] 2024-07-30 02:05:10,617 >> {'loss': 1.1385, 'learning_rate': 4.9966e-06, 'epoch': 0.33, 'throughput': 475.72}
|
| 274 |
-
|
| 275 |
-
[INFO|callbacks.py:310] 2024-07-30 02:05:23,802 >> {'loss': 1.5128, 'learning_rate': 4.9939e-06, 'epoch': 0.36, 'throughput': 476.75}
|
| 276 |
-
|
| 277 |
-
[INFO|callbacks.py:310] 2024-07-30 02:05:37,011 >> {'loss': 0.2268, 'learning_rate': 4.9905e-06, 'epoch': 0.39, 'throughput': 476.14}
|
| 278 |
-
|
| 279 |
-
[INFO|callbacks.py:310] 2024-07-30 02:05:50,209 >> {'loss': 1.0743, 'learning_rate': 4.9863e-06, 'epoch': 0.41, 'throughput': 477.44}
|
| 280 |
-
|
| 281 |
-
[INFO|callbacks.py:310] 2024-07-30 02:06:03,432 >> {'loss': 0.5564, 'learning_rate': 4.9814e-06, 'epoch': 0.44, 'throughput': 476.62}
|
| 282 |
-
|
| 283 |
-
[INFO|callbacks.py:310] 2024-07-30 02:06:16,606 >> {'loss': 1.0090, 'learning_rate': 4.9757e-06, 'epoch': 0.46, 'throughput': 477.26}
|
| 284 |
-
|
| 285 |
-
[INFO|callbacks.py:310] 2024-07-30 02:06:29,795 >> {'loss': 0.7292, 'learning_rate': 4.9692e-06, 'epoch': 0.49, 'throughput': 477.81}
|
| 286 |
-
|
| 287 |
-
[INFO|callbacks.py:310] 2024-07-30 02:06:42,989 >> {'loss': 0.3204, 'learning_rate': 4.9620e-06, 'epoch': 0.51, 'throughput': 478.65}
|
| 288 |
-
|
| 289 |
-
[INFO|callbacks.py:310] 2024-07-30 02:06:56,204 >> {'loss': 0.2741, 'learning_rate': 4.9541e-06, 'epoch': 0.54, 'throughput': 479.15}
|
| 290 |
-
|
| 291 |
-
[INFO|callbacks.py:310] 2024-07-30 02:07:09,386 >> {'loss': 0.1732, 'learning_rate': 4.9454e-06, 'epoch': 0.57, 'throughput': 479.44}
|
| 292 |
-
|
| 293 |
-
[INFO|callbacks.py:310] 2024-07-30 02:07:22,590 >> {'loss': 0.4089, 'learning_rate': 4.9359e-06, 'epoch': 0.59, 'throughput': 479.66}
|
| 294 |
-
|
| 295 |
-
[INFO|callbacks.py:310] 2024-07-30 02:07:35,787 >> {'loss': 0.4201, 'learning_rate': 4.9257e-06, 'epoch': 0.62, 'throughput': 478.93}
|
| 296 |
-
|
| 297 |
-
[INFO|callbacks.py:310] 2024-07-30 02:07:48,982 >> {'loss': 0.1772, 'learning_rate': 4.9148e-06, 'epoch': 0.64, 'throughput': 478.78}
|
| 298 |
-
|
| 299 |
-
[INFO|callbacks.py:310] 2024-07-30 02:08:02,171 >> {'loss': 0.5611, 'learning_rate': 4.9032e-06, 'epoch': 0.67, 'throughput': 478.66}
|
| 300 |
-
|
| 301 |
-
[INFO|callbacks.py:310] 2024-07-30 02:08:15,354 >> {'loss': 0.4709, 'learning_rate': 4.8908e-06, 'epoch': 0.69, 'throughput': 479.27}
|
| 302 |
-
|
| 303 |
-
[INFO|callbacks.py:310] 2024-07-30 02:08:28,552 >> {'loss': 0.3355, 'learning_rate': 4.8776e-06, 'epoch': 0.72, 'throughput': 479.86}
|
| 304 |
-
|
| 305 |
-
[INFO|callbacks.py:310] 2024-07-30 02:08:41,745 >> {'loss': 0.1259, 'learning_rate': 4.8638e-06, 'epoch': 0.75, 'throughput': 480.33}
|
| 306 |
-
|
| 307 |
-
[INFO|callbacks.py:310] 2024-07-30 02:08:54,952 >> {'loss': 0.1584, 'learning_rate': 4.8492e-06, 'epoch': 0.77, 'throughput': 480.88}
|
| 308 |
-
|
| 309 |
-
[INFO|callbacks.py:310] 2024-07-30 02:09:08,155 >> {'loss': 0.1765, 'learning_rate': 4.8340e-06, 'epoch': 0.80, 'throughput': 480.77}
|
| 310 |
-
|
| 311 |
-
[INFO|callbacks.py:310] 2024-07-30 02:09:21,349 >> {'loss': 0.1372, 'learning_rate': 4.8180e-06, 'epoch': 0.82, 'throughput': 480.79}
|
| 312 |
-
|
| 313 |
-
[INFO|callbacks.py:310] 2024-07-30 02:09:34,545 >> {'loss': 0.1321, 'learning_rate': 4.8013e-06, 'epoch': 0.85, 'throughput': 481.24}
|
| 314 |
-
|
| 315 |
-
[INFO|callbacks.py:310] 2024-07-30 02:09:47,741 >> {'loss': 0.2427, 'learning_rate': 4.7839e-06, 'epoch': 0.87, 'throughput': 481.32}
|
| 316 |
-
|
| 317 |
-
[INFO|callbacks.py:310] 2024-07-30 02:10:00,942 >> {'loss': 0.2354, 'learning_rate': 4.7658e-06, 'epoch': 0.90, 'throughput': 481.45}
|
| 318 |
-
|
| 319 |
-
[INFO|callbacks.py:310] 2024-07-30 02:10:14,134 >> {'loss': 0.0977, 'learning_rate': 4.7470e-06, 'epoch': 0.93, 'throughput': 481.35}
|
| 320 |
-
|
| 321 |
-
[INFO|callbacks.py:310] 2024-07-30 02:10:27,351 >> {'loss': 0.1405, 'learning_rate': 4.7275e-06, 'epoch': 0.95, 'throughput': 481.53}
|
| 322 |
-
|
| 323 |
-
[INFO|callbacks.py:310] 2024-07-30 02:10:40,545 >> {'loss': 0.2396, 'learning_rate': 4.7074e-06, 'epoch': 0.98, 'throughput': 481.84}
|
| 324 |
-
|
| 325 |
-
[INFO|callbacks.py:310] 2024-07-30 02:10:53,741 >> {'loss': 0.1272, 'learning_rate': 4.6865e-06, 'epoch': 1.00, 'throughput': 482.08}
|
| 326 |
-
|
| 327 |
-
[INFO|callbacks.py:310] 2024-07-30 02:11:06,936 >> {'loss': 0.0815, 'learning_rate': 4.6651e-06, 'epoch': 1.03, 'throughput': 482.15}
|
| 328 |
-
|
| 329 |
-
[INFO|callbacks.py:310] 2024-07-30 02:11:20,135 >> {'loss': 0.0771, 'learning_rate': 4.6429e-06, 'epoch': 1.05, 'throughput': 482.43}
|
| 330 |
-
|
| 331 |
-
[INFO|callbacks.py:310] 2024-07-30 02:11:33,315 >> {'loss': 0.0821, 'learning_rate': 4.6201e-06, 'epoch': 1.08, 'throughput': 482.59}
|
| 332 |
-
|
| 333 |
-
[INFO|callbacks.py:310] 2024-07-30 02:11:46,521 >> {'loss': 0.0597, 'learning_rate': 4.5967e-06, 'epoch': 1.11, 'throughput': 482.86}
|
| 334 |
-
|
| 335 |
-
[INFO|callbacks.py:310] 2024-07-30 02:11:59,700 >> {'loss': 0.0356, 'learning_rate': 4.5726e-06, 'epoch': 1.13, 'throughput': 482.92}
|
| 336 |
-
|
| 337 |
-
[INFO|callbacks.py:310] 2024-07-30 02:12:12,896 >> {'loss': 0.0895, 'learning_rate': 4.5479e-06, 'epoch': 1.16, 'throughput': 482.54}
|
| 338 |
-
|
| 339 |
-
[INFO|callbacks.py:310] 2024-07-30 02:12:26,093 >> {'loss': 0.0402, 'learning_rate': 4.5225e-06, 'epoch': 1.18, 'throughput': 482.62}
|
| 340 |
-
|
| 341 |
-
[INFO|callbacks.py:310] 2024-07-30 02:12:39,286 >> {'loss': 0.0659, 'learning_rate': 4.4966e-06, 'epoch': 1.21, 'throughput': 482.70}
|
| 342 |
-
|
| 343 |
-
[INFO|callbacks.py:310] 2024-07-30 02:12:52,488 >> {'loss': 0.0910, 'learning_rate': 4.4700e-06, 'epoch': 1.23, 'throughput': 482.11}
|
| 344 |
-
|
| 345 |
-
[INFO|callbacks.py:310] 2024-07-30 02:13:05,678 >> {'loss': 0.0380, 'learning_rate': 4.4429e-06, 'epoch': 1.26, 'throughput': 482.47}
|
| 346 |
-
|
| 347 |
-
[INFO|callbacks.py:310] 2024-07-30 02:13:18,858 >> {'loss': 0.0998, 'learning_rate': 4.4151e-06, 'epoch': 1.29, 'throughput': 482.27}
|
| 348 |
-
|
| 349 |
-
[INFO|callbacks.py:310] 2024-07-30 02:13:32,052 >> {'loss': 0.1125, 'learning_rate': 4.3868e-06, 'epoch': 1.31, 'throughput': 482.22}
|
| 350 |
-
|
| 351 |
-
[INFO|callbacks.py:310] 2024-07-30 02:13:45,252 >> {'loss': 0.0330, 'learning_rate': 4.3579e-06, 'epoch': 1.34, 'throughput': 482.18}
|
| 352 |
-
|
| 353 |
-
[INFO|callbacks.py:310] 2024-07-30 02:13:58,458 >> {'loss': 0.0688, 'learning_rate': 4.3284e-06, 'epoch': 1.36, 'throughput': 482.16}
|
| 354 |
-
|
| 355 |
-
[INFO|callbacks.py:310] 2024-07-30 02:14:11,657 >> {'loss': 0.0433, 'learning_rate': 4.2983e-06, 'epoch': 1.39, 'throughput': 481.96}
|
| 356 |
-
|
| 357 |
-
[INFO|callbacks.py:310] 2024-07-30 02:14:24,864 >> {'loss': 0.0116, 'learning_rate': 4.2678e-06, 'epoch': 1.41, 'throughput': 482.19}
|
| 358 |
-
|
| 359 |
-
[INFO|callbacks.py:310] 2024-07-30 02:14:38,054 >> {'loss': 0.0634, 'learning_rate': 4.2366e-06, 'epoch': 1.44, 'throughput': 482.20}
|
| 360 |
-
|
| 361 |
-
[INFO|callbacks.py:310] 2024-07-30 02:14:51,257 >> {'loss': 0.0729, 'learning_rate': 4.2050e-06, 'epoch': 1.47, 'throughput': 482.35}
|
| 362 |
-
|
| 363 |
-
[INFO|callbacks.py:310] 2024-07-30 02:15:04,437 >> {'loss': 0.1315, 'learning_rate': 4.1728e-06, 'epoch': 1.49, 'throughput': 482.28}
|
| 364 |
-
|
| 365 |
-
[INFO|callbacks.py:310] 2024-07-30 02:15:17,637 >> {'loss': 0.0500, 'learning_rate': 4.1401e-06, 'epoch': 1.52, 'throughput': 482.10}
|
| 366 |
-
|
| 367 |
-
[INFO|callbacks.py:310] 2024-07-30 02:15:30,845 >> {'loss': 0.0838, 'learning_rate': 4.1070e-06, 'epoch': 1.54, 'throughput': 482.14}
|
| 368 |
-
|
| 369 |
-
[INFO|callbacks.py:310] 2024-07-30 02:15:44,056 >> {'loss': 0.0577, 'learning_rate': 4.0733e-06, 'epoch': 1.57, 'throughput': 482.16}
|
| 370 |
-
|
| 371 |
-
[INFO|callbacks.py:310] 2024-07-30 02:15:57,241 >> {'loss': 0.0465, 'learning_rate': 4.0392e-06, 'epoch': 1.59, 'throughput': 482.29}
|
| 372 |
-
|
| 373 |
-
[INFO|callbacks.py:310] 2024-07-30 02:16:10,432 >> {'loss': 0.0497, 'learning_rate': 4.0045e-06, 'epoch': 1.62, 'throughput': 482.54}
|
| 374 |
-
|
| 375 |
-
[INFO|callbacks.py:310] 2024-07-30 02:16:23,621 >> {'loss': 0.0559, 'learning_rate': 3.9695e-06, 'epoch': 1.65, 'throughput': 482.32}
|
| 376 |
-
|
| 377 |
-
[INFO|callbacks.py:310] 2024-07-30 02:16:36,808 >> {'loss': 0.0394, 'learning_rate': 3.9339e-06, 'epoch': 1.67, 'throughput': 482.29}
|
| 378 |
-
|
| 379 |
-
[INFO|callbacks.py:310] 2024-07-30 02:16:49,989 >> {'loss': 0.0737, 'learning_rate': 3.8980e-06, 'epoch': 1.70, 'throughput': 482.12}
|
| 380 |
-
|
| 381 |
-
[INFO|callbacks.py:310] 2024-07-30 02:17:03,202 >> {'loss': 0.0466, 'learning_rate': 3.8616e-06, 'epoch': 1.72, 'throughput': 482.08}
|
| 382 |
-
|
| 383 |
-
[INFO|callbacks.py:310] 2024-07-30 02:17:16,390 >> {'loss': 0.0619, 'learning_rate': 3.8248e-06, 'epoch': 1.75, 'throughput': 481.72}
|
| 384 |
-
|
| 385 |
-
[INFO|callbacks.py:310] 2024-07-30 02:17:29,587 >> {'loss': 0.0749, 'learning_rate': 3.7876e-06, 'epoch': 1.77, 'throughput': 481.78}
|
| 386 |
-
|
| 387 |
-
[INFO|callbacks.py:310] 2024-07-30 02:17:42,784 >> {'loss': 0.0328, 'learning_rate': 3.7500e-06, 'epoch': 1.80, 'throughput': 482.00}
|
| 388 |
-
|
| 389 |
-
[INFO|callbacks.py:310] 2024-07-30 02:17:55,968 >> {'loss': 0.0896, 'learning_rate': 3.7120e-06, 'epoch': 1.83, 'throughput': 482.27}
|
| 390 |
-
|
| 391 |
-
[INFO|callbacks.py:310] 2024-07-30 02:18:09,156 >> {'loss': 0.0489, 'learning_rate': 3.6737e-06, 'epoch': 1.85, 'throughput': 482.03}
|
| 392 |
-
|
| 393 |
-
[INFO|callbacks.py:310] 2024-07-30 02:18:22,353 >> {'loss': 0.0305, 'learning_rate': 3.6350e-06, 'epoch': 1.88, 'throughput': 482.12}
|
| 394 |
-
|
| 395 |
-
[INFO|callbacks.py:310] 2024-07-30 02:18:35,561 >> {'loss': 0.0547, 'learning_rate': 3.5959e-06, 'epoch': 1.90, 'throughput': 482.22}
|
| 396 |
-
|
| 397 |
-
[INFO|callbacks.py:310] 2024-07-30 02:18:48,783 >> {'loss': 0.0554, 'learning_rate': 3.5565e-06, 'epoch': 1.93, 'throughput': 482.18}
|
| 398 |
-
|
| 399 |
-
[INFO|callbacks.py:310] 2024-07-30 02:19:01,977 >> {'loss': 0.1169, 'learning_rate': 3.5168e-06, 'epoch': 1.95, 'throughput': 482.14}
|
| 400 |
-
|
| 401 |
-
[INFO|callbacks.py:310] 2024-07-30 02:19:15,182 >> {'loss': 0.0587, 'learning_rate': 3.4768e-06, 'epoch': 1.98, 'throughput': 481.85}
|
| 402 |
-
|
| 403 |
-
[INFO|callbacks.py:310] 2024-07-30 02:19:28,367 >> {'loss': 0.0624, 'learning_rate': 3.4365e-06, 'epoch': 2.01, 'throughput': 481.99}
|
| 404 |
-
|
| 405 |
-
[INFO|callbacks.py:310] 2024-07-30 02:19:41,570 >> {'loss': 0.0152, 'learning_rate': 3.3959e-06, 'epoch': 2.03, 'throughput': 482.04}
|
| 406 |
-
|
| 407 |
-
[INFO|callbacks.py:310] 2024-07-30 02:19:54,767 >> {'loss': 0.0224, 'learning_rate': 3.3551e-06, 'epoch': 2.06, 'throughput': 482.06}
|
| 408 |
-
|
| 409 |
-
[INFO|callbacks.py:310] 2024-07-30 02:20:07,979 >> {'loss': 0.0084, 'learning_rate': 3.3139e-06, 'epoch': 2.08, 'throughput': 481.96}
|
| 410 |
-
|
| 411 |
-
[INFO|callbacks.py:310] 2024-07-30 02:20:21,187 >> {'loss': 0.0293, 'learning_rate': 3.2725e-06, 'epoch': 2.11, 'throughput': 481.78}
|
| 412 |
-
|
| 413 |
-
[INFO|callbacks.py:310] 2024-07-30 02:20:34,397 >> {'loss': 0.0167, 'learning_rate': 3.2309e-06, 'epoch': 2.14, 'throughput': 481.49}
|
| 414 |
-
|
| 415 |
-
[INFO|callbacks.py:310] 2024-07-30 02:20:47,579 >> {'loss': 0.0094, 'learning_rate': 3.1891e-06, 'epoch': 2.16, 'throughput': 481.79}
|
| 416 |
-
|
| 417 |
-
[INFO|callbacks.py:310] 2024-07-30 02:21:00,789 >> {'loss': 0.0551, 'learning_rate': 3.1470e-06, 'epoch': 2.19, 'throughput': 481.95}
|
| 418 |
-
|
| 419 |
-
[INFO|callbacks.py:310] 2024-07-30 02:21:13,980 >> {'loss': 0.0684, 'learning_rate': 3.1048e-06, 'epoch': 2.21, 'throughput': 481.91}
|
| 420 |
-
|
| 421 |
-
[INFO|callbacks.py:310] 2024-07-30 02:21:27,180 >> {'loss': 0.0178, 'learning_rate': 3.0624e-06, 'epoch': 2.24, 'throughput': 482.28}
|
| 422 |
-
|
| 423 |
-
[INFO|callbacks.py:310] 2024-07-30 02:21:40,367 >> {'loss': 0.0515, 'learning_rate': 3.0198e-06, 'epoch': 2.26, 'throughput': 482.19}
|
| 424 |
-
|
| 425 |
-
[INFO|callbacks.py:310] 2024-07-30 02:21:53,575 >> {'loss': 0.0116, 'learning_rate': 2.9770e-06, 'epoch': 2.29, 'throughput': 482.10}
|
| 426 |
-
|
| 427 |
-
[INFO|callbacks.py:310] 2024-07-30 02:22:06,773 >> {'loss': 0.0010, 'learning_rate': 2.9341e-06, 'epoch': 2.32, 'throughput': 482.26}
|
| 428 |
-
|
| 429 |
-
[INFO|callbacks.py:310] 2024-07-30 02:22:19,949 >> {'loss': 0.0061, 'learning_rate': 2.8911e-06, 'epoch': 2.34, 'throughput': 482.33}
|
| 430 |
-
|
| 431 |
-
[INFO|callbacks.py:310] 2024-07-30 02:22:33,140 >> {'loss': 0.0099, 'learning_rate': 2.8479e-06, 'epoch': 2.37, 'throughput': 482.29}
|
| 432 |
-
|
| 433 |
-
[INFO|callbacks.py:310] 2024-07-30 02:22:46,325 >> {'loss': 0.0246, 'learning_rate': 2.8047e-06, 'epoch': 2.39, 'throughput': 482.35}
|
| 434 |
-
|
| 435 |
-
[INFO|callbacks.py:310] 2024-07-30 02:22:59,519 >> {'loss': 0.0235, 'learning_rate': 2.7613e-06, 'epoch': 2.42, 'throughput': 482.41}
|
| 436 |
-
|
| 437 |
-
[INFO|callbacks.py:310] 2024-07-30 02:23:12,716 >> {'loss': 0.0563, 'learning_rate': 2.7179e-06, 'epoch': 2.44, 'throughput': 482.33}
|
| 438 |
-
|
| 439 |
-
[INFO|callbacks.py:310] 2024-07-30 02:23:25,929 >> {'loss': 0.0436, 'learning_rate': 2.6744e-06, 'epoch': 2.47, 'throughput': 482.13}
|
| 440 |
-
|
| 441 |
-
[INFO|callbacks.py:310] 2024-07-30 02:23:39,130 >> {'loss': 0.0139, 'learning_rate': 2.6308e-06, 'epoch': 2.50, 'throughput': 482.13}
|
| 442 |
-
|
| 443 |
-
[INFO|callbacks.py:310] 2024-07-30 02:23:52,320 >> {'loss': 0.0301, 'learning_rate': 2.5872e-06, 'epoch': 2.52, 'throughput': 482.23}
|
| 444 |
-
|
| 445 |
-
[INFO|callbacks.py:310] 2024-07-30 02:24:05,516 >> {'loss': 0.0154, 'learning_rate': 2.5436e-06, 'epoch': 2.55, 'throughput': 482.18}
|
| 446 |
-
|
| 447 |
-
[INFO|callbacks.py:310] 2024-07-30 02:24:18,713 >> {'loss': 0.0167, 'learning_rate': 2.5000e-06, 'epoch': 2.57, 'throughput': 482.31}
|
| 448 |
-
|
| 449 |
-
[INFO|callbacks.py:310] 2024-07-30 02:24:31,913 >> {'loss': 0.0171, 'learning_rate': 2.4564e-06, 'epoch': 2.60, 'throughput': 482.36}
|
| 450 |
-
|
| 451 |
-
[INFO|callbacks.py:310] 2024-07-30 02:24:45,107 >> {'loss': 0.0219, 'learning_rate': 2.4128e-06, 'epoch': 2.62, 'throughput': 482.31}
|
| 452 |
-
|
| 453 |
-
[INFO|callbacks.py:310] 2024-07-30 02:24:58,305 >> {'loss': 0.0108, 'learning_rate': 2.3692e-06, 'epoch': 2.65, 'throughput': 482.28}
|
| 454 |
-
|
| 455 |
-
[INFO|callbacks.py:310] 2024-07-30 02:25:11,491 >> {'loss': 0.0124, 'learning_rate': 2.3256e-06, 'epoch': 2.68, 'throughput': 482.41}
|
| 456 |
-
|
| 457 |
-
[INFO|callbacks.py:310] 2024-07-30 02:25:24,706 >> {'loss': 0.0489, 'learning_rate': 2.2821e-06, 'epoch': 2.70, 'throughput': 482.24}
|
| 458 |
-
|
| 459 |
-
[INFO|callbacks.py:310] 2024-07-30 02:25:37,892 >> {'loss': 0.0131, 'learning_rate': 2.2387e-06, 'epoch': 2.73, 'throughput': 482.14}
|
| 460 |
-
|
| 461 |
-
[INFO|callbacks.py:310] 2024-07-30 02:25:51,092 >> {'loss': 0.0148, 'learning_rate': 2.1953e-06, 'epoch': 2.75, 'throughput': 481.98}
|
| 462 |
-
|
| 463 |
-
[INFO|callbacks.py:310] 2024-07-30 02:26:04,293 >> {'loss': 0.0279, 'learning_rate': 2.1521e-06, 'epoch': 2.78, 'throughput': 481.90}
|
| 464 |
-
|
| 465 |
-
[INFO|callbacks.py:310] 2024-07-30 02:26:17,491 >> {'loss': 0.0177, 'learning_rate': 2.1089e-06, 'epoch': 2.80, 'throughput': 482.07}
|
| 466 |
-
|
| 467 |
-
[INFO|callbacks.py:310] 2024-07-30 02:26:30,687 >> {'loss': 0.0362, 'learning_rate': 2.0659e-06, 'epoch': 2.83, 'throughput': 482.08}
|
| 468 |
-
|
| 469 |
-
[INFO|callbacks.py:310] 2024-07-30 02:26:43,893 >> {'loss': 0.0380, 'learning_rate': 2.0230e-06, 'epoch': 2.86, 'throughput': 482.11}
|
| 470 |
-
|
| 471 |
-
[INFO|callbacks.py:310] 2024-07-30 02:26:57,098 >> {'loss': 0.0249, 'learning_rate': 1.9802e-06, 'epoch': 2.88, 'throughput': 482.19}
|
| 472 |
-
|
| 473 |
-
[INFO|callbacks.py:310] 2024-07-30 02:27:10,288 >> {'loss': 0.0074, 'learning_rate': 1.9376e-06, 'epoch': 2.91, 'throughput': 482.16}
|
| 474 |
-
|
| 475 |
-
[INFO|callbacks.py:310] 2024-07-30 02:27:23,478 >> {'loss': 0.0147, 'learning_rate': 1.8952e-06, 'epoch': 2.93, 'throughput': 482.20}
|
| 476 |
-
|
| 477 |
-
[INFO|callbacks.py:310] 2024-07-30 02:27:36,691 >> {'loss': 0.0168, 'learning_rate': 1.8530e-06, 'epoch': 2.96, 'throughput': 482.11}
|
| 478 |
-
|
| 479 |
-
[INFO|callbacks.py:310] 2024-07-30 02:27:49,881 >> {'loss': 0.0083, 'learning_rate': 1.8109e-06, 'epoch': 2.98, 'throughput': 482.06}
|
| 480 |
-
|
| 481 |
-
[INFO|callbacks.py:310] 2024-07-30 02:28:03,079 >> {'loss': 0.0086, 'learning_rate': 1.7691e-06, 'epoch': 3.01, 'throughput': 482.07}
|
| 482 |
-
|
| 483 |
-
[INFO|callbacks.py:310] 2024-07-30 02:28:16,292 >> {'loss': 0.0025, 'learning_rate': 1.7275e-06, 'epoch': 3.04, 'throughput': 482.17}
|
| 484 |
-
|
| 485 |
-
[INFO|callbacks.py:310] 2024-07-30 02:28:29,513 >> {'loss': 0.0067, 'learning_rate': 1.6861e-06, 'epoch': 3.06, 'throughput': 482.08}
|
| 486 |
-
|
| 487 |
-
[INFO|callbacks.py:310] 2024-07-30 02:28:42,701 >> {'loss': 0.0020, 'learning_rate': 1.6449e-06, 'epoch': 3.09, 'throughput': 482.04}
|
| 488 |
-
|
| 489 |
-
[INFO|callbacks.py:310] 2024-07-30 02:28:55,898 >> {'loss': 0.0003, 'learning_rate': 1.6041e-06, 'epoch': 3.11, 'throughput': 481.90}
|
| 490 |
-
|
| 491 |
-
[INFO|callbacks.py:310] 2024-07-30 02:29:09,091 >> {'loss': 0.0012, 'learning_rate': 1.5635e-06, 'epoch': 3.14, 'throughput': 481.74}
|
| 492 |
-
|
| 493 |
-
[INFO|callbacks.py:310] 2024-07-30 02:29:22,287 >> {'loss': 0.0001, 'learning_rate': 1.5232e-06, 'epoch': 3.16, 'throughput': 481.70}
|
| 494 |
-
|
| 495 |
-
[INFO|callbacks.py:310] 2024-07-30 02:29:35,461 >> {'loss': 0.0098, 'learning_rate': 1.4832e-06, 'epoch': 3.19, 'throughput': 481.86}
|
| 496 |
-
|
| 497 |
-
[INFO|callbacks.py:310] 2024-07-30 02:29:48,673 >> {'loss': 0.0029, 'learning_rate': 1.4435e-06, 'epoch': 3.22, 'throughput': 481.92}
|
| 498 |
-
|
| 499 |
-
[INFO|callbacks.py:310] 2024-07-30 02:30:01,861 >> {'loss': 0.0000, 'learning_rate': 1.4041e-06, 'epoch': 3.24, 'throughput': 481.92}
|
| 500 |
-
|
| 501 |
-
[INFO|callbacks.py:310] 2024-07-30 02:30:15,066 >> {'loss': 0.0000, 'learning_rate': 1.3650e-06, 'epoch': 3.27, 'throughput': 482.03}
|
| 502 |
-
|
| 503 |
-
[INFO|callbacks.py:310] 2024-07-30 02:30:28,255 >> {'loss': 0.0002, 'learning_rate': 1.3263e-06, 'epoch': 3.29, 'throughput': 482.09}
|
| 504 |
-
|
| 505 |
-
[INFO|callbacks.py:310] 2024-07-30 02:30:41,464 >> {'loss': 0.0331, 'learning_rate': 1.2880e-06, 'epoch': 3.32, 'throughput': 482.05}
|
| 506 |
-
|
| 507 |
-
[INFO|callbacks.py:310] 2024-07-30 02:30:54,652 >> {'loss': 0.0000, 'learning_rate': 1.2500e-06, 'epoch': 3.34, 'throughput': 482.07}
|
| 508 |
-
|
| 509 |
-
[INFO|callbacks.py:310] 2024-07-30 02:31:07,849 >> {'loss': 0.0038, 'learning_rate': 1.2124e-06, 'epoch': 3.37, 'throughput': 482.13}
|
| 510 |
-
|
| 511 |
-
[INFO|callbacks.py:310] 2024-07-30 02:31:21,051 >> {'loss': 0.0000, 'learning_rate': 1.1752e-06, 'epoch': 3.40, 'throughput': 482.03}
|
| 512 |
-
|
| 513 |
-
[INFO|callbacks.py:310] 2024-07-30 02:31:34,257 >> {'loss': 0.0051, 'learning_rate': 1.1384e-06, 'epoch': 3.42, 'throughput': 481.94}
|
| 514 |
-
|
| 515 |
-
[INFO|callbacks.py:310] 2024-07-30 02:31:47,439 >> {'loss': 0.0589, 'learning_rate': 1.1020e-06, 'epoch': 3.45, 'throughput': 482.01}
|
| 516 |
-
|
| 517 |
-
[INFO|callbacks.py:310] 2024-07-30 02:32:00,633 >> {'loss': 0.0003, 'learning_rate': 1.0661e-06, 'epoch': 3.47, 'throughput': 482.02}
|
| 518 |
-
|
| 519 |
-
[INFO|callbacks.py:310] 2024-07-30 02:32:13,818 >> {'loss': 0.0355, 'learning_rate': 1.0305e-06, 'epoch': 3.50, 'throughput': 481.90}
|
| 520 |
-
|
| 521 |
-
[INFO|callbacks.py:310] 2024-07-30 02:32:27,019 >> {'loss': 0.0402, 'learning_rate': 9.9546e-07, 'epoch': 3.52, 'throughput': 481.99}
|
| 522 |
-
|
| 523 |
-
[INFO|callbacks.py:310] 2024-07-30 02:32:40,217 >> {'loss': 0.0000, 'learning_rate': 9.6085e-07, 'epoch': 3.55, 'throughput': 482.00}
|
| 524 |
-
|
| 525 |
-
[INFO|callbacks.py:310] 2024-07-30 02:32:53,422 >> {'loss': 0.0083, 'learning_rate': 9.2670e-07, 'epoch': 3.58, 'throughput': 482.01}
|
| 526 |
-
|
| 527 |
-
[INFO|callbacks.py:310] 2024-07-30 02:33:06,623 >> {'loss': 0.0000, 'learning_rate': 8.9303e-07, 'epoch': 3.60, 'throughput': 481.96}
|
| 528 |
-
|
| 529 |
-
[INFO|callbacks.py:310] 2024-07-30 02:33:19,818 >> {'loss': 0.0012, 'learning_rate': 8.5985e-07, 'epoch': 3.63, 'throughput': 481.83}
|
| 530 |
-
|
| 531 |
-
[INFO|callbacks.py:310] 2024-07-30 02:33:33,015 >> {'loss': 0.0342, 'learning_rate': 8.2717e-07, 'epoch': 3.65, 'throughput': 481.86}
|
| 532 |
-
|
| 533 |
-
[INFO|callbacks.py:310] 2024-07-30 02:33:46,211 >> {'loss': 0.0723, 'learning_rate': 7.9500e-07, 'epoch': 3.68, 'throughput': 481.82}
|
| 534 |
-
|
| 535 |
-
[INFO|callbacks.py:310] 2024-07-30 02:33:59,393 >> {'loss': 0.0000, 'learning_rate': 7.6335e-07, 'epoch': 3.70, 'throughput': 481.79}
|
| 536 |
-
|
| 537 |
-
[INFO|callbacks.py:310] 2024-07-30 02:34:12,587 >> {'loss': 0.0410, 'learning_rate': 7.3223e-07, 'epoch': 3.73, 'throughput': 481.85}
|
| 538 |
-
|
| 539 |
-
[INFO|callbacks.py:310] 2024-07-30 02:34:25,760 >> {'loss': 0.0000, 'learning_rate': 7.0165e-07, 'epoch': 3.76, 'throughput': 481.70}
|
| 540 |
-
|
| 541 |
-
[INFO|callbacks.py:310] 2024-07-30 02:34:38,959 >> {'loss': 0.0001, 'learning_rate': 6.7162e-07, 'epoch': 3.78, 'throughput': 481.95}
|
| 542 |
-
|
| 543 |
-
[INFO|callbacks.py:310] 2024-07-30 02:34:52,147 >> {'loss': 0.0220, 'learning_rate': 6.4214e-07, 'epoch': 3.81, 'throughput': 482.01}
|
| 544 |
-
|
| 545 |
-
[INFO|callbacks.py:310] 2024-07-30 02:35:05,342 >> {'loss': 0.0000, 'learning_rate': 6.1323e-07, 'epoch': 3.83, 'throughput': 482.03}
|
| 546 |
-
|
| 547 |
-
[INFO|callbacks.py:310] 2024-07-30 02:35:18,550 >> {'loss': 0.0095, 'learning_rate': 5.8489e-07, 'epoch': 3.86, 'throughput': 482.04}
|
| 548 |
-
|
| 549 |
-
[INFO|callbacks.py:310] 2024-07-30 02:35:31,746 >> {'loss': 0.0002, 'learning_rate': 5.5714e-07, 'epoch': 3.88, 'throughput': 482.11}
|
| 550 |
-
|
| 551 |
-
[INFO|callbacks.py:310] 2024-07-30 02:35:44,947 >> {'loss': 0.0000, 'learning_rate': 5.2997e-07, 'epoch': 3.91, 'throughput': 482.02}
|
| 552 |
-
|
| 553 |
-
[INFO|callbacks.py:310] 2024-07-30 02:35:58,134 >> {'loss': 0.0274, 'learning_rate': 5.0341e-07, 'epoch': 3.94, 'throughput': 481.97}
|
| 554 |
-
|
| 555 |
-
[INFO|callbacks.py:310] 2024-07-30 02:36:11,327 >> {'loss': 0.0284, 'learning_rate': 4.7746e-07, 'epoch': 3.96, 'throughput': 482.02}
|
| 556 |
-
|
| 557 |
-
[INFO|callbacks.py:310] 2024-07-30 02:36:24,527 >> {'loss': 0.0001, 'learning_rate': 4.5212e-07, 'epoch': 3.99, 'throughput': 481.94}
|
| 558 |
-
|
| 559 |
-
[INFO|callbacks.py:310] 2024-07-30 02:36:37,725 >> {'loss': 0.0000, 'learning_rate': 4.2741e-07, 'epoch': 4.01, 'throughput': 482.02}
|
| 560 |
-
|
| 561 |
-
[INFO|callbacks.py:310] 2024-07-30 02:36:50,932 >> {'loss': 0.0001, 'learning_rate': 4.0332e-07, 'epoch': 4.04, 'throughput': 482.00}
|
| 562 |
-
|
| 563 |
-
[INFO|callbacks.py:310] 2024-07-30 02:37:04,125 >> {'loss': 0.0001, 'learning_rate': 3.7988e-07, 'epoch': 4.06, 'throughput': 482.01}
|
| 564 |
-
|
| 565 |
-
[INFO|callbacks.py:310] 2024-07-30 02:37:17,326 >> {'loss': 0.0121, 'learning_rate': 3.5708e-07, 'epoch': 4.09, 'throughput': 481.91}
|
| 566 |
-
|
| 567 |
-
[INFO|callbacks.py:310] 2024-07-30 02:37:30,524 >> {'loss': 0.0000, 'learning_rate': 3.3494e-07, 'epoch': 4.12, 'throughput': 482.00}
|
| 568 |
-
|
| 569 |
-
[INFO|callbacks.py:310] 2024-07-30 02:37:43,706 >> {'loss': 0.0001, 'learning_rate': 3.1345e-07, 'epoch': 4.14, 'throughput': 482.03}
|
| 570 |
-
|
| 571 |
-
[INFO|callbacks.py:310] 2024-07-30 02:37:56,913 >> {'loss': 0.0001, 'learning_rate': 2.9263e-07, 'epoch': 4.17, 'throughput': 482.07}
|
| 572 |
-
|
| 573 |
-
[INFO|callbacks.py:310] 2024-07-30 02:38:10,110 >> {'loss': 0.0002, 'learning_rate': 2.7248e-07, 'epoch': 4.19, 'throughput': 482.13}
|
| 574 |
-
|
| 575 |
-
[INFO|callbacks.py:310] 2024-07-30 02:38:23,292 >> {'loss': 0.0005, 'learning_rate': 2.5301e-07, 'epoch': 4.22, 'throughput': 482.10}
|
| 576 |
-
|
| 577 |
-
[INFO|callbacks.py:310] 2024-07-30 02:38:36,504 >> {'loss': 0.0001, 'learning_rate': 2.3423e-07, 'epoch': 4.24, 'throughput': 481.98}
|
| 578 |
-
|
| 579 |
-
[INFO|callbacks.py:310] 2024-07-30 02:38:49,692 >> {'loss': 0.0001, 'learning_rate': 2.1614e-07, 'epoch': 4.27, 'throughput': 482.03}
|
| 580 |
-
|
| 581 |
-
[INFO|callbacks.py:310] 2024-07-30 02:39:02,905 >> {'loss': 0.0001, 'learning_rate': 1.9874e-07, 'epoch': 4.30, 'throughput': 482.02}
|
| 582 |
-
|
| 583 |
-
[INFO|callbacks.py:310] 2024-07-30 02:39:16,096 >> {'loss': 0.0001, 'learning_rate': 1.8204e-07, 'epoch': 4.32, 'throughput': 481.99}
|
| 584 |
-
|
| 585 |
-
[INFO|callbacks.py:310] 2024-07-30 02:39:29,295 >> {'loss': 0.0001, 'learning_rate': 1.6605e-07, 'epoch': 4.35, 'throughput': 481.91}
|
| 586 |
-
|
| 587 |
-
[INFO|callbacks.py:310] 2024-07-30 02:39:42,485 >> {'loss': 0.0002, 'learning_rate': 1.5077e-07, 'epoch': 4.37, 'throughput': 481.92}
|
| 588 |
-
|
| 589 |
-
[INFO|callbacks.py:310] 2024-07-30 02:39:55,679 >> {'loss': 0.0026, 'learning_rate': 1.3620e-07, 'epoch': 4.40, 'throughput': 481.94}
|
| 590 |
-
|
| 591 |
-
[INFO|callbacks.py:310] 2024-07-30 02:40:08,863 >> {'loss': 0.0032, 'learning_rate': 1.2236e-07, 'epoch': 4.42, 'throughput': 481.96}
|
| 592 |
-
|
| 593 |
-
[INFO|callbacks.py:310] 2024-07-30 02:40:22,060 >> {'loss': 0.0004, 'learning_rate': 1.0924e-07, 'epoch': 4.45, 'throughput': 482.04}
|
| 594 |
-
|
| 595 |
-
[INFO|callbacks.py:310] 2024-07-30 02:40:35,246 >> {'loss': 0.0001, 'learning_rate': 9.6846e-08, 'epoch': 4.48, 'throughput': 481.94}
|
| 596 |
-
|
| 597 |
-
[INFO|callbacks.py:310] 2024-07-30 02:40:48,451 >> {'loss': 0.0074, 'learning_rate': 8.5185e-08, 'epoch': 4.50, 'throughput': 481.88}
|
| 598 |
-
|
| 599 |
-
[INFO|callbacks.py:310] 2024-07-30 02:41:01,650 >> {'loss': 0.0029, 'learning_rate': 7.4261e-08, 'epoch': 4.53, 'throughput': 481.80}
|
| 600 |
-
|
| 601 |
-
[INFO|callbacks.py:310] 2024-07-30 02:41:14,857 >> {'loss': 0.0001, 'learning_rate': 6.4075e-08, 'epoch': 4.55, 'throughput': 481.85}
|
| 602 |
-
|
| 603 |
-
[INFO|callbacks.py:310] 2024-07-30 02:41:28,042 >> {'loss': 0.0000, 'learning_rate': 5.4631e-08, 'epoch': 4.58, 'throughput': 481.85}
|
| 604 |
-
|
| 605 |
-
[INFO|callbacks.py:310] 2024-07-30 02:41:41,246 >> {'loss': 0.0082, 'learning_rate': 4.5932e-08, 'epoch': 4.60, 'throughput': 481.87}
|
| 606 |
-
|
| 607 |
-
[INFO|callbacks.py:310] 2024-07-30 02:41:54,426 >> {'loss': 0.0001, 'learning_rate': 3.7981e-08, 'epoch': 4.63, 'throughput': 481.94}
|
| 608 |
-
|
| 609 |
-
[INFO|callbacks.py:310] 2024-07-30 02:42:07,625 >> {'loss': 0.0000, 'learning_rate': 3.0779e-08, 'epoch': 4.66, 'throughput': 481.87}
|
| 610 |
-
|
| 611 |
-
[INFO|callbacks.py:310] 2024-07-30 02:42:20,822 >> {'loss': 0.0001, 'learning_rate': 2.4330e-08, 'epoch': 4.68, 'throughput': 481.79}
|
| 612 |
|
| 613 |
-
[INFO|
|
| 614 |
|
| 615 |
-
[INFO|
|
|
|
|
| 616 |
|
| 617 |
-
[INFO|
|
| 618 |
|
| 619 |
-
[INFO|
|
| 620 |
|
| 621 |
-
[
|
| 622 |
|
| 623 |
-
|
| 624 |
|
| 625 |
-
|
| 626 |
|
| 627 |
-
|
| 628 |
|
| 629 |
-
|
| 630 |
|
| 631 |
-
|
| 632 |
|
| 633 |
-
|
| 634 |
|
| 635 |
-
|
| 636 |
|
| 637 |
-
|
| 638 |
|
| 639 |
-
|
| 640 |
|
| 641 |
-
|
| 642 |
|
| 643 |
-
|
| 644 |
|
|
|
|
| 645 |
|
|
|
|
| 646 |
|
| 647 |
-
|
| 648 |
|
| 649 |
-
|
| 650 |
|
| 651 |
-
|
| 652 |
|
| 653 |
-
|
| 654 |
|
| 655 |
-
|
| 656 |
|
| 657 |
-
|
| 658 |
|
| 659 |
-
|
| 660 |
|
| 661 |
-
|
| 662 |
|
| 663 |
-
[INFO|
|
| 664 |
-
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
|
| 665 |
|
|
|
|
| 1 |
+
07/30/2024 02:46:48 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
|
| 2 |
|
| 3 |
+
07/30/2024 02:46:48 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
|
| 4 |
|
| 5 |
+
[INFO|parser.py:344] 2024-07-30 02:46:48,688 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: None
|
| 6 |
|
| 7 |
+
[INFO|tokenization_utils_base.py:2287] 2024-07-30 02:46:48,690 >> loading file tokenizer.json
|
| 8 |
|
| 9 |
+
[INFO|tokenization_utils_base.py:2287] 2024-07-30 02:46:48,690 >> loading file added_tokens.json
|
| 10 |
|
| 11 |
+
07/30/2024 02:46:48 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
|
| 12 |
|
| 13 |
+
07/30/2024 02:46:48 - INFO - llamafactory.hparams.parser - Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: None
|
| 14 |
|
| 15 |
+
07/30/2024 02:46:48 - INFO - llamafactory.hparams.parser - Process rank: 7, device: cuda:7, n_gpu: 1, distributed training: True, compute dtype: None
|
| 16 |
|
| 17 |
+
07/30/2024 02:46:48 - INFO - llamafactory.hparams.parser - Process rank: 6, device: cuda:6, n_gpu: 1, distributed training: True, compute dtype: None
|
| 18 |
|
| 19 |
+
07/30/2024 02:46:48 - INFO - llamafactory.hparams.parser - Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: None
|
| 20 |
|
| 21 |
+
[INFO|tokenization_utils_base.py:2287] 2024-07-30 02:46:48,690 >> loading file special_tokens_map.json
|
| 22 |
|
| 23 |
+
[INFO|tokenization_utils_base.py:2287] 2024-07-30 02:46:48,690 >> loading file tokenizer_config.json
|
| 24 |
|
| 25 |
+
[INFO|tokenization_utils_base.py:2533] 2024-07-30 02:46:48,952 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
| 26 |
|
| 27 |
+
[INFO|template.py:270] 2024-07-30 02:46:48,953 >> Replace eos token: <|eot_id|>
|
| 28 |
|
| 29 |
+
[INFO|loader.py:52] 2024-07-30 02:46:48,953 >> Loading dataset 0716_truthfulqa_benchmark_test.json...
|
| 30 |
|
| 31 |
+
07/30/2024 02:46:49 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
|
| 32 |
|
| 33 |
+
07/30/2024 02:46:49 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
|
| 34 |
|
| 35 |
+
07/30/2024 02:46:49 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
|
| 36 |
|
| 37 |
+
07/30/2024 02:46:49 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
|
| 38 |
|
| 39 |
+
07/30/2024 02:46:50 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
|
| 40 |
|
| 41 |
+
07/30/2024 02:46:50 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
|
| 42 |
|
| 43 |
+
07/30/2024 02:46:50 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
|
| 44 |
|
| 45 |
+
07/30/2024 02:46:50 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
|
| 46 |
|
| 47 |
+
07/30/2024 02:46:50 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
|
| 48 |
|
| 49 |
+
07/30/2024 02:46:50 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
|
| 50 |
|
| 51 |
+
07/30/2024 02:46:50 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json...
|
| 52 |
|
| 53 |
+
[INFO|configuration_utils.py:731] 2024-07-30 02:46:54,353 >> loading configuration file saves/LLaMA3.1-8B-Chat/full/train_2024-07-30-02-00-04_llama3.1_truthqa_bench_1/config.json
|
| 54 |
|
| 55 |
+
[INFO|configuration_utils.py:800] 2024-07-30 02:46:54,354 >> Model config LlamaConfig {
|
| 56 |
+
"_name_or_path": "saves/LLaMA3.1-8B-Chat/full/train_2024-07-30-02-00-04_llama3.1_truthqa_bench_1",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
"architectures": [
|
| 58 |
"LlamaForCausalLM"
|
| 59 |
],
|
|
|
|
| 88 |
"tie_word_embeddings": false,
|
| 89 |
"torch_dtype": "bfloat16",
|
| 90 |
"transformers_version": "4.43.3",
|
| 91 |
+
"use_cache": false,
|
| 92 |
"vocab_size": 128256
|
| 93 |
}
|
| 94 |
|
| 95 |
|
| 96 |
+
[INFO|patcher.py:81] 2024-07-30 02:46:54,354 >> Using KV cache for faster generation.
|
| 97 |
|
| 98 |
+
[INFO|modeling_utils.py:3631] 2024-07-30 02:46:54,380 >> loading weights file saves/LLaMA3.1-8B-Chat/full/train_2024-07-30-02-00-04_llama3.1_truthqa_bench_1/model.safetensors.index.json
|
| 99 |
|
| 100 |
+
[INFO|modeling_utils.py:1572] 2024-07-30 02:46:54,380 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
|
| 101 |
+
|
| 102 |
+
[INFO|configuration_utils.py:1038] 2024-07-30 02:46:54,382 >> Generate config GenerationConfig {
|
| 103 |
"bos_token_id": 128000,
|
| 104 |
"eos_token_id": [
|
| 105 |
128001,
|
|
|
|
| 109 |
}
|
| 110 |
|
| 111 |
|
| 112 |
+
07/30/2024 02:46:54 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 113 |
+
|
| 114 |
+
07/30/2024 02:46:54 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 115 |
+
|
| 116 |
+
07/30/2024 02:46:54 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 117 |
+
|
| 118 |
+
07/30/2024 02:46:54 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 119 |
+
|
| 120 |
+
07/30/2024 02:46:54 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 121 |
+
|
| 122 |
+
07/30/2024 02:46:54 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 123 |
|
| 124 |
+
07/30/2024 02:46:54 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 125 |
|
| 126 |
+
[INFO|modeling_utils.py:4463] 2024-07-30 02:46:58,526 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
|
| 127 |
+
|
| 128 |
+
|
| 129 |
+
[INFO|modeling_utils.py:4471] 2024-07-30 02:46:58,526 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at saves/LLaMA3.1-8B-Chat/full/train_2024-07-30-02-00-04_llama3.1_truthqa_bench_1.
|
| 130 |
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.
|
| 131 |
|
| 132 |
+
[INFO|configuration_utils.py:991] 2024-07-30 02:46:58,530 >> loading configuration file saves/LLaMA3.1-8B-Chat/full/train_2024-07-30-02-00-04_llama3.1_truthqa_bench_1/generation_config.json
|
| 133 |
|
| 134 |
+
[INFO|configuration_utils.py:1038] 2024-07-30 02:46:58,530 >> Generate config GenerationConfig {
|
| 135 |
"bos_token_id": 128000,
|
| 136 |
"do_sample": true,
|
| 137 |
"eos_token_id": [
|
|
|
|
| 144 |
}
|
| 145 |
|
| 146 |
|
| 147 |
+
[INFO|attention.py:84] 2024-07-30 02:46:58,536 >> Using torch SDPA for faster training and inference.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
|
| 149 |
+
[INFO|loader.py:196] 2024-07-30 02:46:58,541 >> all params: 8,030,261,248
|
| 150 |
|
| 151 |
+
[INFO|trainer.py:3819] 2024-07-30 02:46:58,652 >>
|
| 152 |
+
***** Running Prediction *****
|
| 153 |
|
| 154 |
+
[INFO|trainer.py:3821] 2024-07-30 02:46:58,652 >> Num examples = 1243
|
| 155 |
|
| 156 |
+
[INFO|trainer.py:3824] 2024-07-30 02:46:58,652 >> Batch size = 2
|
| 157 |
|
| 158 |
+
[WARNING|logging.py:328] 2024-07-30 02:46:59,326 >> 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)
|
| 159 |
|
| 160 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 161 |
|
| 162 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 163 |
|
| 164 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.loader - all params: 8,030,261,248
|
| 165 |
|
| 166 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.loader - all params: 8,030,261,248
|
| 167 |
|
| 168 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 169 |
|
| 170 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 171 |
|
| 172 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.loader - all params: 8,030,261,248
|
| 173 |
|
| 174 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.loader - all params: 8,030,261,248
|
| 175 |
|
| 176 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 177 |
|
| 178 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.loader - all params: 8,030,261,248
|
| 179 |
|
| 180 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 181 |
|
| 182 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.loader - all params: 8,030,261,248
|
| 183 |
|
| 184 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 185 |
|
| 186 |
+
07/30/2024 02:46:59 - INFO - llamafactory.model.loader - all params: 8,030,261,248
|
| 187 |
|
| 188 |
+
07/30/2024 02:47:00 - 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)
|
| 189 |
|
| 190 |
+
07/30/2024 02:47:00 - 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)
|
| 191 |
|
| 192 |
+
07/30/2024 02:47:00 - 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)
|
| 193 |
|
| 194 |
+
07/30/2024 02:47:00 - 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 |
+
07/30/2024 02:47:00 - 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 |
+
07/30/2024 02:47:00 - 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 |
+
07/30/2024 02:47:00 - 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 |
+
[INFO|trainer.py:127] 2024-07-30 02:47:07,461 >> Saving prediction results to saves/LLaMA3.1-8B-Chat/full/eval_2024-07-30-02-00-04_truthqa_bench1/generated_predictions.jsonl
|
|
|
|
| 203 |
|
trainer_log.jsonl
CHANGED
|
@@ -1,191 +1,15 @@
|
|
| 1 |
-
{"current_steps":
|
| 2 |
-
{"current_steps":
|
| 3 |
-
{"current_steps":
|
| 4 |
-
{"current_steps":
|
| 5 |
-
{"current_steps":
|
| 6 |
-
{"current_steps":
|
| 7 |
-
{"current_steps":
|
| 8 |
-
{"current_steps":
|
| 9 |
-
{"current_steps":
|
| 10 |
-
{"current_steps":
|
| 11 |
-
{"current_steps":
|
| 12 |
-
{"current_steps":
|
| 13 |
-
{"current_steps":
|
| 14 |
-
{"current_steps":
|
| 15 |
-
{"current_steps":
|
| 16 |
-
{"current_steps": 16, "total_steps": 190, "loss": 1.0743, "learning_rate": 4.986304738420684e-06, "epoch": 0.4115755627009646, "percentage": 8.42, "elapsed_time": "0:03:32", "remaining_time": "0:38:28", "throughput": "477.44", "total_tokens": 101360}
|
| 17 |
-
{"current_steps": 17, "total_steps": 190, "loss": 0.5564, "learning_rate": 4.981365379103306e-06, "epoch": 0.43729903536977494, "percentage": 8.95, "elapsed_time": "0:03:45", "remaining_time": "0:38:15", "throughput": "476.62", "total_tokens": 107488}
|
| 18 |
-
{"current_steps": 18, "total_steps": 190, "loss": 1.009, "learning_rate": 4.975670171853926e-06, "epoch": 0.4630225080385852, "percentage": 9.47, "elapsed_time": "0:03:58", "remaining_time": "0:38:00", "throughput": "477.26", "total_tokens": 113920}
|
| 19 |
-
{"current_steps": 19, "total_steps": 190, "loss": 0.7292, "learning_rate": 4.9692208514878445e-06, "epoch": 0.4887459807073955, "percentage": 10.0, "elapsed_time": "0:04:11", "remaining_time": "0:37:46", "throughput": "477.81", "total_tokens": 120352}
|
| 20 |
-
{"current_steps": 20, "total_steps": 190, "loss": 0.3204, "learning_rate": 4.962019382530521e-06, "epoch": 0.5144694533762058, "percentage": 10.53, "elapsed_time": "0:04:25", "remaining_time": "0:37:33", "throughput": "478.65", "total_tokens": 126880}
|
| 21 |
-
{"current_steps": 21, "total_steps": 190, "loss": 0.2741, "learning_rate": 4.9540679586191605e-06, "epoch": 0.5401929260450161, "percentage": 11.05, "elapsed_time": "0:04:38", "remaining_time": "0:37:19", "throughput": "479.15", "total_tokens": 133344}
|
| 22 |
-
{"current_steps": 22, "total_steps": 190, "loss": 0.1732, "learning_rate": 4.9453690018345144e-06, "epoch": 0.5659163987138264, "percentage": 11.58, "elapsed_time": "0:04:51", "remaining_time": "0:37:05", "throughput": "479.44", "total_tokens": 139744}
|
| 23 |
-
{"current_steps": 23, "total_steps": 190, "loss": 0.4089, "learning_rate": 4.935925161963089e-06, "epoch": 0.5916398713826366, "percentage": 12.11, "elapsed_time": "0:05:04", "remaining_time": "0:36:52", "throughput": "479.66", "total_tokens": 146144}
|
| 24 |
-
{"current_steps": 24, "total_steps": 190, "loss": 0.4201, "learning_rate": 4.925739315689991e-06, "epoch": 0.617363344051447, "percentage": 12.63, "elapsed_time": "0:05:17", "remaining_time": "0:36:38", "throughput": "478.93", "total_tokens": 152240}
|
| 25 |
-
{"current_steps": 25, "total_steps": 190, "loss": 0.1772, "learning_rate": 4.914814565722671e-06, "epoch": 0.6430868167202572, "percentage": 13.16, "elapsed_time": "0:05:31", "remaining_time": "0:36:25", "throughput": "478.78", "total_tokens": 158512}
|
| 26 |
-
{"current_steps": 26, "total_steps": 190, "loss": 0.5611, "learning_rate": 4.903154239845798e-06, "epoch": 0.6688102893890675, "percentage": 13.68, "elapsed_time": "0:05:44", "remaining_time": "0:36:11", "throughput": "478.66", "total_tokens": 164784}
|
| 27 |
-
{"current_steps": 27, "total_steps": 190, "loss": 0.4709, "learning_rate": 4.890761889907589e-06, "epoch": 0.6945337620578779, "percentage": 14.21, "elapsed_time": "0:05:57", "remaining_time": "0:35:57", "throughput": "479.27", "total_tokens": 171312}
|
| 28 |
-
{"current_steps": 28, "total_steps": 190, "loss": 0.3355, "learning_rate": 4.8776412907378845e-06, "epoch": 0.7202572347266881, "percentage": 14.74, "elapsed_time": "0:06:10", "remaining_time": "0:35:44", "throughput": "479.86", "total_tokens": 177856}
|
| 29 |
-
{"current_steps": 29, "total_steps": 190, "loss": 0.1259, "learning_rate": 4.863796438998293e-06, "epoch": 0.7459807073954984, "percentage": 15.26, "elapsed_time": "0:06:23", "remaining_time": "0:35:30", "throughput": "480.33", "total_tokens": 184368}
|
| 30 |
-
{"current_steps": 30, "total_steps": 190, "loss": 0.1584, "learning_rate": 4.849231551964771e-06, "epoch": 0.7717041800643086, "percentage": 15.79, "elapsed_time": "0:06:37", "remaining_time": "0:35:17", "throughput": "480.88", "total_tokens": 190928}
|
| 31 |
-
{"current_steps": 31, "total_steps": 190, "loss": 0.1765, "learning_rate": 4.833951066243004e-06, "epoch": 0.797427652733119, "percentage": 16.32, "elapsed_time": "0:06:50", "remaining_time": "0:35:04", "throughput": "480.77", "total_tokens": 197232}
|
| 32 |
-
{"current_steps": 32, "total_steps": 190, "loss": 0.1372, "learning_rate": 4.817959636416969e-06, "epoch": 0.8231511254019293, "percentage": 16.84, "elapsed_time": "0:07:03", "remaining_time": "0:34:50", "throughput": "480.79", "total_tokens": 203584}
|
| 33 |
-
{"current_steps": 33, "total_steps": 190, "loss": 0.1321, "learning_rate": 4.801262133631101e-06, "epoch": 0.8488745980707395, "percentage": 17.37, "elapsed_time": "0:07:16", "remaining_time": "0:34:37", "throughput": "481.24", "total_tokens": 210128}
|
| 34 |
-
{"current_steps": 34, "total_steps": 190, "loss": 0.2427, "learning_rate": 4.783863644106502e-06, "epoch": 0.8745980707395499, "percentage": 17.89, "elapsed_time": "0:07:29", "remaining_time": "0:34:23", "throughput": "481.32", "total_tokens": 216512}
|
| 35 |
-
{"current_steps": 35, "total_steps": 190, "loss": 0.2354, "learning_rate": 4.765769467591626e-06, "epoch": 0.9003215434083601, "percentage": 18.42, "elapsed_time": "0:07:43", "remaining_time": "0:34:10", "throughput": "481.45", "total_tokens": 222928}
|
| 36 |
-
{"current_steps": 36, "total_steps": 190, "loss": 0.0977, "learning_rate": 4.746985115747918e-06, "epoch": 0.9260450160771704, "percentage": 18.95, "elapsed_time": "0:07:56", "remaining_time": "0:33:57", "throughput": "481.35", "total_tokens": 229232}
|
| 37 |
-
{"current_steps": 37, "total_steps": 190, "loss": 0.1405, "learning_rate": 4.72751631047092e-06, "epoch": 0.9517684887459807, "percentage": 19.47, "elapsed_time": "0:08:09", "remaining_time": "0:33:43", "throughput": "481.53", "total_tokens": 235680}
|
| 38 |
-
{"current_steps": 38, "total_steps": 190, "loss": 0.2396, "learning_rate": 4.707368982147318e-06, "epoch": 0.977491961414791, "percentage": 20.0, "elapsed_time": "0:08:22", "remaining_time": "0:33:30", "throughput": "481.84", "total_tokens": 242192}
|
| 39 |
-
{"current_steps": 39, "total_steps": 190, "loss": 0.1272, "learning_rate": 4.68654926784849e-06, "epoch": 1.0032154340836013, "percentage": 20.53, "elapsed_time": "0:08:35", "remaining_time": "0:33:17", "throughput": "482.08", "total_tokens": 248672}
|
| 40 |
-
{"current_steps": 40, "total_steps": 190, "loss": 0.0815, "learning_rate": 4.665063509461098e-06, "epoch": 1.0289389067524115, "percentage": 21.05, "elapsed_time": "0:08:49", "remaining_time": "0:33:03", "throughput": "482.15", "total_tokens": 255072}
|
| 41 |
-
{"current_steps": 41, "total_steps": 190, "loss": 0.0771, "learning_rate": 4.642918251755281e-06, "epoch": 1.0546623794212218, "percentage": 21.58, "elapsed_time": "0:09:02", "remaining_time": "0:32:50", "throughput": "482.43", "total_tokens": 261584}
|
| 42 |
-
{"current_steps": 42, "total_steps": 190, "loss": 0.0821, "learning_rate": 4.620120240391065e-06, "epoch": 1.0803858520900322, "percentage": 22.11, "elapsed_time": "0:09:15", "remaining_time": "0:32:37", "throughput": "482.59", "total_tokens": 268032}
|
| 43 |
-
{"current_steps": 43, "total_steps": 190, "loss": 0.0597, "learning_rate": 4.596676419863561e-06, "epoch": 1.1061093247588425, "percentage": 22.63, "elapsed_time": "0:09:28", "remaining_time": "0:32:23", "throughput": "482.86", "total_tokens": 274560}
|
| 44 |
-
{"current_steps": 44, "total_steps": 190, "loss": 0.0356, "learning_rate": 4.572593931387604e-06, "epoch": 1.1318327974276527, "percentage": 23.16, "elapsed_time": "0:09:41", "remaining_time": "0:32:10", "throughput": "482.92", "total_tokens": 280960}
|
| 45 |
-
{"current_steps": 45, "total_steps": 190, "loss": 0.0895, "learning_rate": 4.54788011072248e-06, "epoch": 1.157556270096463, "percentage": 23.68, "elapsed_time": "0:09:54", "remaining_time": "0:31:57", "throughput": "482.54", "total_tokens": 287104}
|
| 46 |
-
{"current_steps": 46, "total_steps": 190, "loss": 0.0402, "learning_rate": 4.522542485937369e-06, "epoch": 1.1832797427652733, "percentage": 24.21, "elapsed_time": "0:10:08", "remaining_time": "0:31:43", "throughput": "482.62", "total_tokens": 293520}
|
| 47 |
-
{"current_steps": 47, "total_steps": 190, "loss": 0.0659, "learning_rate": 4.496588775118232e-06, "epoch": 1.2090032154340835, "percentage": 24.74, "elapsed_time": "0:10:21", "remaining_time": "0:31:30", "throughput": "482.70", "total_tokens": 299936}
|
| 48 |
-
{"current_steps": 48, "total_steps": 190, "loss": 0.091, "learning_rate": 4.470026884016805e-06, "epoch": 1.234726688102894, "percentage": 25.26, "elapsed_time": "0:10:34", "remaining_time": "0:31:17", "throughput": "482.11", "total_tokens": 305936}
|
| 49 |
-
{"current_steps": 49, "total_steps": 190, "loss": 0.038, "learning_rate": 4.442864903642428e-06, "epoch": 1.2604501607717042, "percentage": 25.79, "elapsed_time": "0:10:47", "remaining_time": "0:31:03", "throughput": "482.47", "total_tokens": 312528}
|
| 50 |
-
{"current_steps": 50, "total_steps": 190, "loss": 0.0998, "learning_rate": 4.415111107797445e-06, "epoch": 1.2861736334405145, "percentage": 26.32, "elapsed_time": "0:11:00", "remaining_time": "0:30:50", "throughput": "482.27", "total_tokens": 318752}
|
| 51 |
-
{"current_steps": 51, "total_steps": 190, "loss": 0.1125, "learning_rate": 4.386773950556931e-06, "epoch": 1.3118971061093248, "percentage": 26.84, "elapsed_time": "0:11:14", "remaining_time": "0:30:37", "throughput": "482.22", "total_tokens": 325088}
|
| 52 |
-
{"current_steps": 52, "total_steps": 190, "loss": 0.033, "learning_rate": 4.357862063693486e-06, "epoch": 1.337620578778135, "percentage": 27.37, "elapsed_time": "0:11:27", "remaining_time": "0:30:24", "throughput": "482.18", "total_tokens": 331424}
|
| 53 |
-
{"current_steps": 53, "total_steps": 190, "loss": 0.0688, "learning_rate": 4.328384254047927e-06, "epoch": 1.3633440514469453, "percentage": 27.89, "elapsed_time": "0:11:40", "remaining_time": "0:30:10", "throughput": "482.16", "total_tokens": 337776}
|
| 54 |
-
{"current_steps": 54, "total_steps": 190, "loss": 0.0433, "learning_rate": 4.2983495008466285e-06, "epoch": 1.3890675241157555, "percentage": 28.42, "elapsed_time": "0:11:53", "remaining_time": "0:29:57", "throughput": "481.96", "total_tokens": 344000}
|
| 55 |
-
{"current_steps": 55, "total_steps": 190, "loss": 0.0116, "learning_rate": 4.267766952966369e-06, "epoch": 1.414790996784566, "percentage": 28.95, "elapsed_time": "0:12:06", "remaining_time": "0:29:44", "throughput": "482.19", "total_tokens": 350528}
|
| 56 |
-
{"current_steps": 56, "total_steps": 190, "loss": 0.0634, "learning_rate": 4.236645926147493e-06, "epoch": 1.4405144694533762, "percentage": 29.47, "elapsed_time": "0:12:20", "remaining_time": "0:29:31", "throughput": "482.20", "total_tokens": 356896}
|
| 57 |
-
{"current_steps": 57, "total_steps": 190, "loss": 0.0729, "learning_rate": 4.204995900156247e-06, "epoch": 1.4662379421221865, "percentage": 30.0, "elapsed_time": "0:12:33", "remaining_time": "0:29:17", "throughput": "482.35", "total_tokens": 363376}
|
| 58 |
-
{"current_steps": 58, "total_steps": 190, "loss": 0.1315, "learning_rate": 4.172826515897146e-06, "epoch": 1.4919614147909968, "percentage": 30.53, "elapsed_time": "0:12:46", "remaining_time": "0:29:04", "throughput": "482.28", "total_tokens": 369680}
|
| 59 |
-
{"current_steps": 59, "total_steps": 190, "loss": 0.05, "learning_rate": 4.140147572476269e-06, "epoch": 1.517684887459807, "percentage": 31.05, "elapsed_time": "0:12:59", "remaining_time": "0:28:51", "throughput": "482.10", "total_tokens": 375904}
|
| 60 |
-
{"current_steps": 60, "total_steps": 190, "loss": 0.0838, "learning_rate": 4.106969024216348e-06, "epoch": 1.5434083601286175, "percentage": 31.58, "elapsed_time": "0:13:12", "remaining_time": "0:28:38", "throughput": "482.14", "total_tokens": 382304}
|
| 61 |
-
{"current_steps": 61, "total_steps": 190, "loss": 0.0577, "learning_rate": 4.073300977624594e-06, "epoch": 1.5691318327974275, "percentage": 32.11, "elapsed_time": "0:13:26", "remaining_time": "0:28:24", "throughput": "482.16", "total_tokens": 388688}
|
| 62 |
-
{"current_steps": 62, "total_steps": 190, "loss": 0.0465, "learning_rate": 4.039153688314146e-06, "epoch": 1.594855305466238, "percentage": 32.63, "elapsed_time": "0:13:39", "remaining_time": "0:28:11", "throughput": "482.29", "total_tokens": 395152}
|
| 63 |
-
{"current_steps": 63, "total_steps": 190, "loss": 0.0497, "learning_rate": 4.0045375578801216e-06, "epoch": 1.6205787781350482, "percentage": 33.16, "elapsed_time": "0:13:52", "remaining_time": "0:27:58", "throughput": "482.54", "total_tokens": 401728}
|
| 64 |
-
{"current_steps": 64, "total_steps": 190, "loss": 0.0559, "learning_rate": 3.969463130731183e-06, "epoch": 1.6463022508038585, "percentage": 33.68, "elapsed_time": "0:14:05", "remaining_time": "0:27:44", "throughput": "482.32", "total_tokens": 407904}
|
| 65 |
-
{"current_steps": 65, "total_steps": 190, "loss": 0.0394, "learning_rate": 3.933941090877615e-06, "epoch": 1.6720257234726688, "percentage": 34.21, "elapsed_time": "0:14:18", "remaining_time": "0:27:31", "throughput": "482.29", "total_tokens": 414240}
|
| 66 |
-
{"current_steps": 66, "total_steps": 190, "loss": 0.0737, "learning_rate": 3.897982258676867e-06, "epoch": 1.697749196141479, "percentage": 34.74, "elapsed_time": "0:14:32", "remaining_time": "0:27:18", "throughput": "482.12", "total_tokens": 420448}
|
| 67 |
-
{"current_steps": 67, "total_steps": 190, "loss": 0.0466, "learning_rate": 3.861597587537568e-06, "epoch": 1.7234726688102895, "percentage": 35.26, "elapsed_time": "0:14:45", "remaining_time": "0:27:05", "throughput": "482.08", "total_tokens": 426784}
|
| 68 |
-
{"current_steps": 68, "total_steps": 190, "loss": 0.0619, "learning_rate": 3.824798160583012e-06, "epoch": 1.7491961414790995, "percentage": 35.79, "elapsed_time": "0:14:58", "remaining_time": "0:26:51", "throughput": "481.72", "total_tokens": 432816}
|
| 69 |
-
{"current_steps": 69, "total_steps": 190, "loss": 0.0749, "learning_rate": 3.787595187275136e-06, "epoch": 1.77491961414791, "percentage": 36.32, "elapsed_time": "0:15:11", "remaining_time": "0:26:38", "throughput": "481.78", "total_tokens": 439232}
|
| 70 |
-
{"current_steps": 70, "total_steps": 190, "loss": 0.0328, "learning_rate": 3.7500000000000005e-06, "epoch": 1.8006430868167203, "percentage": 36.84, "elapsed_time": "0:15:24", "remaining_time": "0:26:25", "throughput": "482.00", "total_tokens": 445792}
|
| 71 |
-
{"current_steps": 71, "total_steps": 190, "loss": 0.0896, "learning_rate": 3.7120240506158433e-06, "epoch": 1.8263665594855305, "percentage": 37.37, "elapsed_time": "0:15:38", "remaining_time": "0:26:12", "throughput": "482.27", "total_tokens": 452400}
|
| 72 |
-
{"current_steps": 72, "total_steps": 190, "loss": 0.0489, "learning_rate": 3.6736789069647273e-06, "epoch": 1.852090032154341, "percentage": 37.89, "elapsed_time": "0:15:51", "remaining_time": "0:25:58", "throughput": "482.03", "total_tokens": 458528}
|
| 73 |
-
{"current_steps": 73, "total_steps": 190, "loss": 0.0305, "learning_rate": 3.634976249348867e-06, "epoch": 1.877813504823151, "percentage": 38.42, "elapsed_time": "0:16:04", "remaining_time": "0:25:45", "throughput": "482.12", "total_tokens": 464976}
|
| 74 |
-
{"current_steps": 74, "total_steps": 190, "loss": 0.0547, "learning_rate": 3.595927866972694e-06, "epoch": 1.9035369774919615, "percentage": 38.95, "elapsed_time": "0:16:17", "remaining_time": "0:25:32", "throughput": "482.22", "total_tokens": 471440}
|
| 75 |
-
{"current_steps": 75, "total_steps": 190, "loss": 0.0554, "learning_rate": 3.556545654351749e-06, "epoch": 1.9292604501607717, "percentage": 39.47, "elapsed_time": "0:16:30", "remaining_time": "0:25:19", "throughput": "482.18", "total_tokens": 477776}
|
| 76 |
-
{"current_steps": 76, "total_steps": 190, "loss": 0.1169, "learning_rate": 3.516841607689501e-06, "epoch": 1.954983922829582, "percentage": 40.0, "elapsed_time": "0:16:44", "remaining_time": "0:25:06", "throughput": "482.14", "total_tokens": 484096}
|
| 77 |
-
{"current_steps": 77, "total_steps": 190, "loss": 0.0587, "learning_rate": 3.476827821223184e-06, "epoch": 1.9807073954983923, "percentage": 40.53, "elapsed_time": "0:16:57", "remaining_time": "0:24:52", "throughput": "481.85", "total_tokens": 490176}
|
| 78 |
-
{"current_steps": 78, "total_steps": 190, "loss": 0.0624, "learning_rate": 3.436516483539781e-06, "epoch": 2.0064308681672025, "percentage": 41.05, "elapsed_time": "0:17:10", "remaining_time": "0:24:39", "throughput": "481.99", "total_tokens": 496672}
|
| 79 |
-
{"current_steps": 79, "total_steps": 190, "loss": 0.0152, "learning_rate": 3.39591987386325e-06, "epoch": 2.032154340836013, "percentage": 41.58, "elapsed_time": "0:17:23", "remaining_time": "0:24:26", "throughput": "482.04", "total_tokens": 503088}
|
| 80 |
-
{"current_steps": 80, "total_steps": 190, "loss": 0.0224, "learning_rate": 3.3550503583141726e-06, "epoch": 2.057877813504823, "percentage": 42.11, "elapsed_time": "0:17:36", "remaining_time": "0:24:13", "throughput": "482.06", "total_tokens": 509472}
|
| 81 |
-
{"current_steps": 81, "total_steps": 190, "loss": 0.0084, "learning_rate": 3.313920386142892e-06, "epoch": 2.0836012861736335, "percentage": 42.63, "elapsed_time": "0:17:50", "remaining_time": "0:23:59", "throughput": "481.96", "total_tokens": 515728}
|
| 82 |
-
{"current_steps": 82, "total_steps": 190, "loss": 0.0293, "learning_rate": 3.272542485937369e-06, "epoch": 2.1093247588424435, "percentage": 43.16, "elapsed_time": "0:18:03", "remaining_time": "0:23:46", "throughput": "481.78", "total_tokens": 521904}
|
| 83 |
-
{"current_steps": 83, "total_steps": 190, "loss": 0.0167, "learning_rate": 3.230929261806842e-06, "epoch": 2.135048231511254, "percentage": 43.68, "elapsed_time": "0:18:16", "remaining_time": "0:23:33", "throughput": "481.49", "total_tokens": 527952}
|
| 84 |
-
{"current_steps": 84, "total_steps": 190, "loss": 0.0094, "learning_rate": 3.189093389542498e-06, "epoch": 2.1607717041800645, "percentage": 44.21, "elapsed_time": "0:18:29", "remaining_time": "0:23:20", "throughput": "481.79", "total_tokens": 534624}
|
| 85 |
-
{"current_steps": 85, "total_steps": 190, "loss": 0.0551, "learning_rate": 3.147047612756302e-06, "epoch": 2.1864951768488745, "percentage": 44.74, "elapsed_time": "0:18:42", "remaining_time": "0:23:07", "throughput": "481.95", "total_tokens": 541168}
|
| 86 |
-
{"current_steps": 86, "total_steps": 190, "loss": 0.0684, "learning_rate": 3.1048047389991693e-06, "epoch": 2.212218649517685, "percentage": 45.26, "elapsed_time": "0:18:56", "remaining_time": "0:22:53", "throughput": "481.91", "total_tokens": 547488}
|
| 87 |
-
{"current_steps": 87, "total_steps": 190, "loss": 0.0178, "learning_rate": 3.062377635859663e-06, "epoch": 2.237942122186495, "percentage": 45.79, "elapsed_time": "0:19:09", "remaining_time": "0:22:40", "throughput": "482.28", "total_tokens": 554272}
|
| 88 |
-
{"current_steps": 88, "total_steps": 190, "loss": 0.0515, "learning_rate": 3.019779227044398e-06, "epoch": 2.2636655948553055, "percentage": 46.32, "elapsed_time": "0:19:22", "remaining_time": "0:22:27", "throughput": "482.19", "total_tokens": 560528}
|
| 89 |
-
{"current_steps": 89, "total_steps": 190, "loss": 0.0116, "learning_rate": 2.9770224884413625e-06, "epoch": 2.289389067524116, "percentage": 46.84, "elapsed_time": "0:19:35", "remaining_time": "0:22:14", "throughput": "482.10", "total_tokens": 566784}
|
| 90 |
-
{"current_steps": 90, "total_steps": 190, "loss": 0.001, "learning_rate": 2.9341204441673267e-06, "epoch": 2.315112540192926, "percentage": 47.37, "elapsed_time": "0:19:48", "remaining_time": "0:22:00", "throughput": "482.26", "total_tokens": 573344}
|
| 91 |
-
{"current_steps": 91, "total_steps": 190, "loss": 0.0061, "learning_rate": 2.8910861626005774e-06, "epoch": 2.3408360128617365, "percentage": 47.89, "elapsed_time": "0:20:02", "remaining_time": "0:21:47", "throughput": "482.33", "total_tokens": 579776}
|
| 92 |
-
{"current_steps": 92, "total_steps": 190, "loss": 0.0099, "learning_rate": 2.847932752400164e-06, "epoch": 2.3665594855305465, "percentage": 48.42, "elapsed_time": "0:20:15", "remaining_time": "0:21:34", "throughput": "482.29", "total_tokens": 586096}
|
| 93 |
-
{"current_steps": 93, "total_steps": 190, "loss": 0.0246, "learning_rate": 2.804673358512869e-06, "epoch": 2.392282958199357, "percentage": 48.95, "elapsed_time": "0:20:28", "remaining_time": "0:21:21", "throughput": "482.35", "total_tokens": 592528}
|
| 94 |
-
{"current_steps": 94, "total_steps": 190, "loss": 0.0235, "learning_rate": 2.761321158169134e-06, "epoch": 2.418006430868167, "percentage": 49.47, "elapsed_time": "0:20:41", "remaining_time": "0:21:08", "throughput": "482.41", "total_tokens": 598960}
|
| 95 |
-
{"current_steps": 95, "total_steps": 190, "loss": 0.0563, "learning_rate": 2.717889356869146e-06, "epoch": 2.4437299035369775, "percentage": 50.0, "elapsed_time": "0:20:54", "remaining_time": "0:20:54", "throughput": "482.33", "total_tokens": 605232}
|
| 96 |
-
{"current_steps": 96, "total_steps": 190, "loss": 0.0436, "learning_rate": 2.6743911843603134e-06, "epoch": 2.469453376205788, "percentage": 50.53, "elapsed_time": "0:21:08", "remaining_time": "0:20:41", "throughput": "482.13", "total_tokens": 611344}
|
| 97 |
-
{"current_steps": 97, "total_steps": 190, "loss": 0.0139, "learning_rate": 2.6308398906073603e-06, "epoch": 2.495176848874598, "percentage": 51.05, "elapsed_time": "0:21:21", "remaining_time": "0:20:28", "throughput": "482.13", "total_tokens": 617712}
|
| 98 |
-
{"current_steps": 98, "total_steps": 190, "loss": 0.0301, "learning_rate": 2.587248741756253e-06, "epoch": 2.5209003215434085, "percentage": 51.58, "elapsed_time": "0:21:34", "remaining_time": "0:20:15", "throughput": "482.23", "total_tokens": 624208}
|
| 99 |
-
{"current_steps": 99, "total_steps": 190, "loss": 0.0154, "learning_rate": 2.543631016093209e-06, "epoch": 2.5466237942122185, "percentage": 52.11, "elapsed_time": "0:21:47", "remaining_time": "0:20:01", "throughput": "482.18", "total_tokens": 630496}
|
| 100 |
-
{"current_steps": 100, "total_steps": 190, "loss": 0.0167, "learning_rate": 2.5e-06, "epoch": 2.572347266881029, "percentage": 52.63, "elapsed_time": "0:22:00", "remaining_time": "0:19:48", "throughput": "482.31", "total_tokens": 637040}
|
| 101 |
-
{"current_steps": 101, "total_steps": 190, "loss": 0.0171, "learning_rate": 2.4563689839067913e-06, "epoch": 2.598070739549839, "percentage": 53.16, "elapsed_time": "0:22:14", "remaining_time": "0:19:35", "throughput": "482.36", "total_tokens": 643472}
|
| 102 |
-
{"current_steps": 102, "total_steps": 190, "loss": 0.0219, "learning_rate": 2.4127512582437486e-06, "epoch": 2.6237942122186495, "percentage": 53.68, "elapsed_time": "0:22:27", "remaining_time": "0:19:22", "throughput": "482.31", "total_tokens": 649760}
|
| 103 |
-
{"current_steps": 103, "total_steps": 190, "loss": 0.0108, "learning_rate": 2.3691601093926406e-06, "epoch": 2.64951768488746, "percentage": 54.21, "elapsed_time": "0:22:40", "remaining_time": "0:19:09", "throughput": "482.28", "total_tokens": 656096}
|
| 104 |
-
{"current_steps": 104, "total_steps": 190, "loss": 0.0124, "learning_rate": 2.325608815639687e-06, "epoch": 2.67524115755627, "percentage": 54.74, "elapsed_time": "0:22:53", "remaining_time": "0:18:55", "throughput": "482.41", "total_tokens": 662624}
|
| 105 |
-
{"current_steps": 105, "total_steps": 190, "loss": 0.0489, "learning_rate": 2.2821106431308546e-06, "epoch": 2.7009646302250805, "percentage": 55.26, "elapsed_time": "0:23:06", "remaining_time": "0:18:42", "throughput": "482.24", "total_tokens": 668768}
|
| 106 |
-
{"current_steps": 106, "total_steps": 190, "loss": 0.0131, "learning_rate": 2.238678841830867e-06, "epoch": 2.7266881028938905, "percentage": 55.79, "elapsed_time": "0:23:19", "remaining_time": "0:18:29", "throughput": "482.14", "total_tokens": 674992}
|
| 107 |
-
{"current_steps": 107, "total_steps": 190, "loss": 0.0148, "learning_rate": 2.195326641487132e-06, "epoch": 2.752411575562701, "percentage": 56.32, "elapsed_time": "0:23:33", "remaining_time": "0:18:16", "throughput": "481.98", "total_tokens": 681120}
|
| 108 |
-
{"current_steps": 108, "total_steps": 190, "loss": 0.0279, "learning_rate": 2.1520672475998374e-06, "epoch": 2.778135048231511, "percentage": 56.84, "elapsed_time": "0:23:46", "remaining_time": "0:18:02", "throughput": "481.90", "total_tokens": 687376}
|
| 109 |
-
{"current_steps": 109, "total_steps": 190, "loss": 0.0177, "learning_rate": 2.1089138373994226e-06, "epoch": 2.8038585209003215, "percentage": 57.37, "elapsed_time": "0:23:59", "remaining_time": "0:17:49", "throughput": "482.07", "total_tokens": 693984}
|
| 110 |
-
{"current_steps": 110, "total_steps": 190, "loss": 0.0362, "learning_rate": 2.0658795558326745e-06, "epoch": 2.829581993569132, "percentage": 57.89, "elapsed_time": "0:24:12", "remaining_time": "0:17:36", "throughput": "482.08", "total_tokens": 700352}
|
| 111 |
-
{"current_steps": 111, "total_steps": 190, "loss": 0.038, "learning_rate": 2.022977511558638e-06, "epoch": 2.855305466237942, "percentage": 58.42, "elapsed_time": "0:24:25", "remaining_time": "0:17:23", "throughput": "482.11", "total_tokens": 706768}
|
| 112 |
-
{"current_steps": 112, "total_steps": 190, "loss": 0.0249, "learning_rate": 1.9802207729556023e-06, "epoch": 2.8810289389067525, "percentage": 58.95, "elapsed_time": "0:24:39", "remaining_time": "0:17:10", "throughput": "482.19", "total_tokens": 713248}
|
| 113 |
-
{"current_steps": 113, "total_steps": 190, "loss": 0.0074, "learning_rate": 1.937622364140338e-06, "epoch": 2.906752411575563, "percentage": 59.47, "elapsed_time": "0:24:52", "remaining_time": "0:16:56", "throughput": "482.16", "total_tokens": 719568}
|
| 114 |
-
{"current_steps": 114, "total_steps": 190, "loss": 0.0147, "learning_rate": 1.895195261000831e-06, "epoch": 2.932475884244373, "percentage": 60.0, "elapsed_time": "0:25:05", "remaining_time": "0:16:43", "throughput": "482.20", "total_tokens": 725984}
|
| 115 |
-
{"current_steps": 115, "total_steps": 190, "loss": 0.0168, "learning_rate": 1.852952387243698e-06, "epoch": 2.958199356913183, "percentage": 60.53, "elapsed_time": "0:25:18", "remaining_time": "0:16:30", "throughput": "482.11", "total_tokens": 732224}
|
| 116 |
-
{"current_steps": 116, "total_steps": 190, "loss": 0.0083, "learning_rate": 1.8109066104575023e-06, "epoch": 2.9839228295819935, "percentage": 61.05, "elapsed_time": "0:25:31", "remaining_time": "0:16:17", "throughput": "482.06", "total_tokens": 738496}
|
| 117 |
-
{"current_steps": 117, "total_steps": 190, "loss": 0.0086, "learning_rate": 1.7690707381931585e-06, "epoch": 3.009646302250804, "percentage": 61.58, "elapsed_time": "0:25:45", "remaining_time": "0:16:04", "throughput": "482.07", "total_tokens": 744880}
|
| 118 |
-
{"current_steps": 118, "total_steps": 190, "loss": 0.0025, "learning_rate": 1.7274575140626318e-06, "epoch": 3.035369774919614, "percentage": 62.11, "elapsed_time": "0:25:58", "remaining_time": "0:15:50", "throughput": "482.17", "total_tokens": 751408}
|
| 119 |
-
{"current_steps": 119, "total_steps": 190, "loss": 0.0067, "learning_rate": 1.686079613857109e-06, "epoch": 3.0610932475884245, "percentage": 62.63, "elapsed_time": "0:26:11", "remaining_time": "0:15:37", "throughput": "482.08", "total_tokens": 757632}
|
| 120 |
-
{"current_steps": 120, "total_steps": 190, "loss": 0.002, "learning_rate": 1.6449496416858285e-06, "epoch": 3.0868167202572345, "percentage": 63.16, "elapsed_time": "0:26:24", "remaining_time": "0:15:24", "throughput": "482.04", "total_tokens": 763936}
|
| 121 |
-
{"current_steps": 121, "total_steps": 190, "loss": 0.0003, "learning_rate": 1.6040801261367494e-06, "epoch": 3.112540192926045, "percentage": 63.68, "elapsed_time": "0:26:37", "remaining_time": "0:15:11", "throughput": "481.90", "total_tokens": 770064}
|
| 122 |
-
{"current_steps": 122, "total_steps": 190, "loss": 0.0012, "learning_rate": 1.56348351646022e-06, "epoch": 3.1382636655948555, "percentage": 64.21, "elapsed_time": "0:26:51", "remaining_time": "0:14:58", "throughput": "481.74", "total_tokens": 776176}
|
| 123 |
-
{"current_steps": 123, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.5231721787768162e-06, "epoch": 3.1639871382636655, "percentage": 64.74, "elapsed_time": "0:27:04", "remaining_time": "0:14:44", "throughput": "481.70", "total_tokens": 782464}
|
| 124 |
-
{"current_steps": 124, "total_steps": 190, "loss": 0.0098, "learning_rate": 1.4831583923105e-06, "epoch": 3.189710610932476, "percentage": 65.26, "elapsed_time": "0:27:17", "remaining_time": "0:14:31", "throughput": "481.86", "total_tokens": 789072}
|
| 125 |
-
{"current_steps": 125, "total_steps": 190, "loss": 0.0029, "learning_rate": 1.443454345648252e-06, "epoch": 3.215434083601286, "percentage": 65.79, "elapsed_time": "0:27:30", "remaining_time": "0:14:18", "throughput": "481.92", "total_tokens": 795536}
|
| 126 |
-
{"current_steps": 126, "total_steps": 190, "loss": 0.0, "learning_rate": 1.4040721330273063e-06, "epoch": 3.2411575562700965, "percentage": 66.32, "elapsed_time": "0:27:43", "remaining_time": "0:14:05", "throughput": "481.92", "total_tokens": 801888}
|
| 127 |
-
{"current_steps": 127, "total_steps": 190, "loss": 0.0, "learning_rate": 1.3650237506511333e-06, "epoch": 3.266881028938907, "percentage": 66.84, "elapsed_time": "0:27:57", "remaining_time": "0:13:51", "throughput": "482.03", "total_tokens": 808432}
|
| 128 |
-
{"current_steps": 128, "total_steps": 190, "loss": 0.0002, "learning_rate": 1.3263210930352737e-06, "epoch": 3.292604501607717, "percentage": 67.37, "elapsed_time": "0:28:10", "remaining_time": "0:13:38", "throughput": "482.09", "total_tokens": 814896}
|
| 129 |
-
{"current_steps": 129, "total_steps": 190, "loss": 0.0331, "learning_rate": 1.2879759493841577e-06, "epoch": 3.3183279742765275, "percentage": 67.89, "elapsed_time": "0:28:23", "remaining_time": "0:13:25", "throughput": "482.05", "total_tokens": 821200}
|
| 130 |
-
{"current_steps": 130, "total_steps": 190, "loss": 0.0, "learning_rate": 1.2500000000000007e-06, "epoch": 3.3440514469453375, "percentage": 68.42, "elapsed_time": "0:28:36", "remaining_time": "0:13:12", "throughput": "482.07", "total_tokens": 827584}
|
| 131 |
-
{"current_steps": 131, "total_steps": 190, "loss": 0.0038, "learning_rate": 1.2124048127248644e-06, "epoch": 3.369774919614148, "percentage": 68.95, "elapsed_time": "0:28:49", "remaining_time": "0:12:59", "throughput": "482.13", "total_tokens": 834048}
|
| 132 |
-
{"current_steps": 132, "total_steps": 190, "loss": 0.0, "learning_rate": 1.1752018394169882e-06, "epoch": 3.395498392282958, "percentage": 69.47, "elapsed_time": "0:29:03", "remaining_time": "0:12:45", "throughput": "482.03", "total_tokens": 840240}
|
| 133 |
-
{"current_steps": 133, "total_steps": 190, "loss": 0.0051, "learning_rate": 1.1384024124624324e-06, "epoch": 3.4212218649517685, "percentage": 70.0, "elapsed_time": "0:29:16", "remaining_time": "0:12:32", "throughput": "481.94", "total_tokens": 846448}
|
| 134 |
-
{"current_steps": 134, "total_steps": 190, "loss": 0.0589, "learning_rate": 1.1020177413231334e-06, "epoch": 3.446945337620579, "percentage": 70.53, "elapsed_time": "0:29:29", "remaining_time": "0:12:19", "throughput": "482.01", "total_tokens": 852928}
|
| 135 |
-
{"current_steps": 135, "total_steps": 190, "loss": 0.0003, "learning_rate": 1.0660589091223854e-06, "epoch": 3.472668810289389, "percentage": 71.05, "elapsed_time": "0:29:42", "remaining_time": "0:12:06", "throughput": "482.02", "total_tokens": 859312}
|
| 136 |
-
{"current_steps": 136, "total_steps": 190, "loss": 0.0355, "learning_rate": 1.0305368692688175e-06, "epoch": 3.4983922829581995, "percentage": 71.58, "elapsed_time": "0:29:55", "remaining_time": "0:11:53", "throughput": "481.90", "total_tokens": 865440}
|
| 137 |
-
{"current_steps": 137, "total_steps": 190, "loss": 0.0402, "learning_rate": 9.95462442119879e-07, "epoch": 3.5241157556270095, "percentage": 72.11, "elapsed_time": "0:30:09", "remaining_time": "0:11:39", "throughput": "481.99", "total_tokens": 871968}
|
| 138 |
-
{"current_steps": 138, "total_steps": 190, "loss": 0.0, "learning_rate": 9.608463116858544e-07, "epoch": 3.54983922829582, "percentage": 72.63, "elapsed_time": "0:30:22", "remaining_time": "0:11:26", "throughput": "482.00", "total_tokens": 878352}
|
| 139 |
-
{"current_steps": 139, "total_steps": 190, "loss": 0.0083, "learning_rate": 9.266990223754069e-07, "epoch": 3.57556270096463, "percentage": 73.16, "elapsed_time": "0:30:35", "remaining_time": "0:11:13", "throughput": "482.01", "total_tokens": 884736}
|
| 140 |
-
{"current_steps": 140, "total_steps": 190, "loss": 0.0, "learning_rate": 8.930309757836517e-07, "epoch": 3.6012861736334405, "percentage": 73.68, "elapsed_time": "0:30:48", "remaining_time": "0:11:00", "throughput": "481.96", "total_tokens": 891008}
|
| 141 |
-
{"current_steps": 141, "total_steps": 190, "loss": 0.0012, "learning_rate": 8.598524275237321e-07, "epoch": 3.627009646302251, "percentage": 74.21, "elapsed_time": "0:31:01", "remaining_time": "0:10:47", "throughput": "481.83", "total_tokens": 897120}
|
| 142 |
-
{"current_steps": 142, "total_steps": 190, "loss": 0.0342, "learning_rate": 8.271734841028553e-07, "epoch": 3.652733118971061, "percentage": 74.74, "elapsed_time": "0:31:15", "remaining_time": "0:10:33", "throughput": "481.86", "total_tokens": 903536}
|
| 143 |
-
{"current_steps": 143, "total_steps": 190, "loss": 0.0723, "learning_rate": 7.950040998437541e-07, "epoch": 3.6784565916398715, "percentage": 75.26, "elapsed_time": "0:31:28", "remaining_time": "0:10:20", "throughput": "481.82", "total_tokens": 909824}
|
| 144 |
-
{"current_steps": 144, "total_steps": 190, "loss": 0.0, "learning_rate": 7.633540738525066e-07, "epoch": 3.7041800643086815, "percentage": 75.79, "elapsed_time": "0:31:41", "remaining_time": "0:10:07", "throughput": "481.79", "total_tokens": 916112}
|
| 145 |
-
{"current_steps": 145, "total_steps": 190, "loss": 0.041, "learning_rate": 7.322330470336314e-07, "epoch": 3.729903536977492, "percentage": 76.32, "elapsed_time": "0:31:54", "remaining_time": "0:09:54", "throughput": "481.85", "total_tokens": 922592}
|
| 146 |
-
{"current_steps": 146, "total_steps": 190, "loss": 0.0, "learning_rate": 7.016504991533727e-07, "epoch": 3.755627009646302, "percentage": 76.84, "elapsed_time": "0:32:07", "remaining_time": "0:09:40", "throughput": "481.70", "total_tokens": 928640}
|
| 147 |
-
{"current_steps": 147, "total_steps": 190, "loss": 0.0001, "learning_rate": 6.716157459520739e-07, "epoch": 3.7813504823151125, "percentage": 77.37, "elapsed_time": "0:32:21", "remaining_time": "0:09:27", "throughput": "481.95", "total_tokens": 935488}
|
| 148 |
-
{"current_steps": 148, "total_steps": 190, "loss": 0.022, "learning_rate": 6.421379363065142e-07, "epoch": 3.807073954983923, "percentage": 77.89, "elapsed_time": "0:32:34", "remaining_time": "0:09:14", "throughput": "482.01", "total_tokens": 941952}
|
| 149 |
-
{"current_steps": 149, "total_steps": 190, "loss": 0.0, "learning_rate": 6.1322604944307e-07, "epoch": 3.832797427652733, "percentage": 78.42, "elapsed_time": "0:32:47", "remaining_time": "0:09:01", "throughput": "482.03", "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": "0:33:00", "remaining_time": "0:08:48", "throughput": "482.04", "total_tokens": 954752}
|
| 151 |
-
{"current_steps": 151, "total_steps": 190, "loss": 0.0002, "learning_rate": 5.571350963575728e-07, "epoch": 3.884244372990354, "percentage": 79.47, "elapsed_time": "0:33:13", "remaining_time": "0:08:34", "throughput": "482.11", "total_tokens": 961248}
|
| 152 |
-
{"current_steps": 152, "total_steps": 190, "loss": 0.0, "learning_rate": 5.299731159831953e-07, "epoch": 3.909967845659164, "percentage": 80.0, "elapsed_time": "0:33:27", "remaining_time": "0:08:21", "throughput": "482.02", "total_tokens": 967424}
|
| 153 |
-
{"current_steps": 153, "total_steps": 190, "loss": 0.0274, "learning_rate": 5.034112248817685e-07, "epoch": 3.935691318327974, "percentage": 80.53, "elapsed_time": "0:33:40", "remaining_time": "0:08:08", "throughput": "481.97", "total_tokens": 973696}
|
| 154 |
-
{"current_steps": 154, "total_steps": 190, "loss": 0.0284, "learning_rate": 4.774575140626317e-07, "epoch": 3.9614147909967845, "percentage": 81.05, "elapsed_time": "0:33:53", "remaining_time": "0:07:55", "throughput": "482.02", "total_tokens": 980144}
|
| 155 |
-
{"current_steps": 155, "total_steps": 190, "loss": 0.0001, "learning_rate": 4.5211988927752026e-07, "epoch": 3.987138263665595, "percentage": 81.58, "elapsed_time": "0:34:06", "remaining_time": "0:07:42", "throughput": "481.94", "total_tokens": 986352}
|
| 156 |
-
{"current_steps": 156, "total_steps": 190, "loss": 0.0, "learning_rate": 4.27406068612396e-07, "epoch": 4.012861736334405, "percentage": 82.11, "elapsed_time": "0:34:19", "remaining_time": "0:07:28", "throughput": "482.02", "total_tokens": 992880}
|
| 157 |
-
{"current_steps": 157, "total_steps": 190, "loss": 0.0001, "learning_rate": 4.033235801364402e-07, "epoch": 4.038585209003215, "percentage": 82.63, "elapsed_time": "0:34:33", "remaining_time": "0:07:15", "throughput": "482.00", "total_tokens": 999200}
|
| 158 |
-
{"current_steps": 158, "total_steps": 190, "loss": 0.0001, "learning_rate": 3.798797596089351e-07, "epoch": 4.064308681672026, "percentage": 83.16, "elapsed_time": "0:34:46", "remaining_time": "0:07:02", "throughput": "482.01", "total_tokens": 1005568}
|
| 159 |
-
{"current_steps": 159, "total_steps": 190, "loss": 0.0121, "learning_rate": 3.5708174824471947e-07, "epoch": 4.090032154340836, "percentage": 83.68, "elapsed_time": "0:34:59", "remaining_time": "0:06:49", "throughput": "481.91", "total_tokens": 1011728}
|
| 160 |
-
{"current_steps": 160, "total_steps": 190, "loss": 0.0, "learning_rate": 3.3493649053890325e-07, "epoch": 4.115755627009646, "percentage": 84.21, "elapsed_time": "0:35:12", "remaining_time": "0:06:36", "throughput": "482.00", "total_tokens": 1018272}
|
| 161 |
-
{"current_steps": 161, "total_steps": 190, "loss": 0.0001, "learning_rate": 3.134507321515107e-07, "epoch": 4.141479099678457, "percentage": 84.74, "elapsed_time": "0:35:25", "remaining_time": "0:06:22", "throughput": "482.03", "total_tokens": 1024688}
|
| 162 |
-
{"current_steps": 162, "total_steps": 190, "loss": 0.0001, "learning_rate": 2.9263101785268253e-07, "epoch": 4.167202572347267, "percentage": 85.26, "elapsed_time": "0:35:39", "remaining_time": "0:06:09", "throughput": "482.07", "total_tokens": 1031152}
|
| 163 |
-
{"current_steps": 163, "total_steps": 190, "loss": 0.0002, "learning_rate": 2.7248368952908055e-07, "epoch": 4.192926045016077, "percentage": 85.79, "elapsed_time": "0:35:52", "remaining_time": "0:05:56", "throughput": "482.13", "total_tokens": 1037632}
|
| 164 |
-
{"current_steps": 164, "total_steps": 190, "loss": 0.0005, "learning_rate": 2.53014884252083e-07, "epoch": 4.218649517684887, "percentage": 86.32, "elapsed_time": "0:36:05", "remaining_time": "0:05:43", "throughput": "482.10", "total_tokens": 1043936}
|
| 165 |
-
{"current_steps": 165, "total_steps": 190, "loss": 0.0001, "learning_rate": 2.3423053240837518e-07, "epoch": 4.244372990353698, "percentage": 86.84, "elapsed_time": "0:36:18", "remaining_time": "0:05:30", "throughput": "481.98", "total_tokens": 1050048}
|
| 166 |
-
{"current_steps": 166, "total_steps": 190, "loss": 0.0001, "learning_rate": 2.1613635589349756e-07, "epoch": 4.270096463022508, "percentage": 87.37, "elapsed_time": "0:36:31", "remaining_time": "0:05:16", "throughput": "482.03", "total_tokens": 1056496}
|
| 167 |
-
{"current_steps": 167, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.9873786636889908e-07, "epoch": 4.295819935691318, "percentage": 87.89, "elapsed_time": "0:36:44", "remaining_time": "0:05:03", "throughput": "482.02", "total_tokens": 1062848}
|
| 168 |
-
{"current_steps": 168, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.8204036358303173e-07, "epoch": 4.321543408360129, "percentage": 88.42, "elapsed_time": "0:36:58", "remaining_time": "0:04:50", "throughput": "481.99", "total_tokens": 1069136}
|
| 169 |
-
{"current_steps": 169, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.6604893375699594e-07, "epoch": 4.347266881028939, "percentage": 88.95, "elapsed_time": "0:37:11", "remaining_time": "0:04:37", "throughput": "481.91", "total_tokens": 1075328}
|
| 170 |
-
{"current_steps": 170, "total_steps": 190, "loss": 0.0002, "learning_rate": 1.507684480352292e-07, "epoch": 4.372990353697749, "percentage": 89.47, "elapsed_time": "0:37:24", "remaining_time": "0:04:24", "throughput": "481.92", "total_tokens": 1081696}
|
| 171 |
-
{"current_steps": 171, "total_steps": 190, "loss": 0.0026, "learning_rate": 1.362035610017079e-07, "epoch": 4.39871382636656, "percentage": 90.0, "elapsed_time": "0:37:37", "remaining_time": "0:04:10", "throughput": "481.94", "total_tokens": 1088112}
|
| 172 |
-
{"current_steps": 172, "total_steps": 190, "loss": 0.0032, "learning_rate": 1.223587092621162e-07, "epoch": 4.42443729903537, "percentage": 90.53, "elapsed_time": "0:37:50", "remaining_time": "0:03:57", "throughput": "481.96", "total_tokens": 1094512}
|
| 173 |
-
{"current_steps": 173, "total_steps": 190, "loss": 0.0004, "learning_rate": 1.0923811009241142e-07, "epoch": 4.45016077170418, "percentage": 91.05, "elapsed_time": "0:38:04", "remaining_time": "0:03:44", "throughput": "482.04", "total_tokens": 1101040}
|
| 174 |
-
{"current_steps": 174, "total_steps": 190, "loss": 0.0001, "learning_rate": 9.684576015420277e-08, "epoch": 4.47588424437299, "percentage": 91.58, "elapsed_time": "0:38:17", "remaining_time": "0:03:31", "throughput": "481.94", "total_tokens": 1107168}
|
| 175 |
-
{"current_steps": 175, "total_steps": 190, "loss": 0.0074, "learning_rate": 8.518543427732951e-08, "epoch": 4.501607717041801, "percentage": 92.11, "elapsed_time": "0:38:30", "remaining_time": "0:03:18", "throughput": "481.88", "total_tokens": 1113408}
|
| 176 |
-
{"current_steps": 176, "total_steps": 190, "loss": 0.0029, "learning_rate": 7.426068431000883e-08, "epoch": 4.527331189710611, "percentage": 92.63, "elapsed_time": "0:38:43", "remaining_time": "0:03:04", "throughput": "481.80", "total_tokens": 1119568}
|
| 177 |
-
{"current_steps": 177, "total_steps": 190, "loss": 0.0001, "learning_rate": 6.407483803691216e-08, "epoch": 4.553054662379421, "percentage": 93.16, "elapsed_time": "0:38:56", "remaining_time": "0:02:51", "throughput": "481.85", "total_tokens": 1126048}
|
| 178 |
-
{"current_steps": 178, "total_steps": 190, "loss": 0.0, "learning_rate": 5.463099816548578e-08, "epoch": 4.578778135048232, "percentage": 93.68, "elapsed_time": "0:39:10", "remaining_time": "0:02:38", "throughput": "481.85", "total_tokens": 1132400}
|
| 179 |
-
{"current_steps": 179, "total_steps": 190, "loss": 0.0082, "learning_rate": 4.593204138084006e-08, "epoch": 4.604501607717042, "percentage": 94.21, "elapsed_time": "0:39:23", "remaining_time": "0:02:25", "throughput": "481.87", "total_tokens": 1138832}
|
| 180 |
-
{"current_steps": 180, "total_steps": 190, "loss": 0.0001, "learning_rate": 3.798061746947995e-08, "epoch": 4.630225080385852, "percentage": 94.74, "elapsed_time": "0:39:36", "remaining_time": "0:02:12", "throughput": "481.94", "total_tokens": 1145344}
|
| 181 |
-
{"current_steps": 181, "total_steps": 190, "loss": 0.0, "learning_rate": 3.077914851215585e-08, "epoch": 4.655948553054662, "percentage": 95.26, "elapsed_time": "0:39:49", "remaining_time": "0:01:58", "throughput": "481.87", "total_tokens": 1151536}
|
| 182 |
-
{"current_steps": 182, "total_steps": 190, "loss": 0.0001, "learning_rate": 2.4329828146074096e-08, "epoch": 4.681672025723473, "percentage": 95.79, "elapsed_time": "0:40:02", "remaining_time": "0:01:45", "throughput": "481.79", "total_tokens": 1157696}
|
| 183 |
-
{"current_steps": 183, "total_steps": 190, "loss": 0.0001, "learning_rate": 1.8634620896695044e-08, "epoch": 4.707395498392283, "percentage": 96.32, "elapsed_time": "0:40:16", "remaining_time": "0:01:32", "throughput": "481.65", "total_tokens": 1163712}
|
| 184 |
-
{"current_steps": 184, "total_steps": 190, "loss": 0.0052, "learning_rate": 1.3695261579316776e-08, "epoch": 4.733118971061093, "percentage": 96.84, "elapsed_time": "0:40:29", "remaining_time": "0:01:19", "throughput": "481.57", "total_tokens": 1169888}
|
| 185 |
-
{"current_steps": 185, "total_steps": 190, "loss": 0.0009, "learning_rate": 9.513254770636138e-09, "epoch": 4.758842443729904, "percentage": 97.37, "elapsed_time": "0:40:42", "remaining_time": "0:01:06", "throughput": "481.58", "total_tokens": 1176272}
|
| 186 |
-
{"current_steps": 186, "total_steps": 190, "loss": 0.0001, "learning_rate": 6.089874350439507e-09, "epoch": 4.784565916398714, "percentage": 97.89, "elapsed_time": "0:40:55", "remaining_time": "0:00:52", "throughput": "481.60", "total_tokens": 1182688}
|
| 187 |
-
{"current_steps": 187, "total_steps": 190, "loss": 0.001, "learning_rate": 3.4261631135654174e-09, "epoch": 4.810289389067524, "percentage": 98.42, "elapsed_time": "0:41:08", "remaining_time": "0:00:39", "throughput": "481.73", "total_tokens": 1189360}
|
| 188 |
-
{"current_steps": 188, "total_steps": 190, "loss": 0.0013, "learning_rate": 1.5229324522605949e-09, "epoch": 4.836012861736334, "percentage": 98.95, "elapsed_time": "0:41:22", "remaining_time": "0:00:26", "throughput": "481.70", "total_tokens": 1195632}
|
| 189 |
-
{"current_steps": 189, "total_steps": 190, "loss": 0.0001, "learning_rate": 3.8076210902182607e-10, "epoch": 4.861736334405145, "percentage": 99.47, "elapsed_time": "0:41:35", "remaining_time": "0:00:13", "throughput": "481.71", "total_tokens": 1202016}
|
| 190 |
-
{"current_steps": 190, "total_steps": 190, "loss": 0.0004, "learning_rate": 0.0, "epoch": 4.887459807073955, "percentage": 100.0, "elapsed_time": "0:41:48", "remaining_time": "0:00:00", "throughput": "481.73", "total_tokens": 1208400}
|
| 191 |
-
{"current_steps": 190, "total_steps": 190, "epoch": 4.887459807073955, "percentage": 100.0, "elapsed_time": "0:42:49", "remaining_time": "0:00:00", "throughput": "470.21", "total_tokens": 1208400}
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 78, "percentage": 6.41, "elapsed_time": "0:00:00", "remaining_time": "0:00:04"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 78, "percentage": 12.82, "elapsed_time": "0:00:00", "remaining_time": "0:00:04"}
|
| 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
|
@@ -1,29 +1,18 @@
|
|
| 1 |
-
bf16: true
|
| 2 |
cutoff_len: 1024
|
| 3 |
-
dataset: truth_train_0716
|
| 4 |
dataset_dir: data
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
do_train: true
|
| 8 |
finetuning_type: full
|
| 9 |
flash_attn: auto
|
| 10 |
-
|
| 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:
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
packing: false
|
| 22 |
-
per_device_train_batch_size: 2
|
| 23 |
-
plot_loss: true
|
| 24 |
preprocessing_num_workers: 16
|
| 25 |
-
|
| 26 |
-
save_steps: 5000
|
| 27 |
stage: sft
|
|
|
|
| 28 |
template: llama3
|
| 29 |
-
|
|
|
|
|
|
|
| 1 |
cutoff_len: 1024
|
|
|
|
| 2 |
dataset_dir: data
|
| 3 |
+
do_predict: true
|
| 4 |
+
eval_dataset: truth_dev_0716
|
|
|
|
| 5 |
finetuning_type: full
|
| 6 |
flash_attn: auto
|
| 7 |
+
max_new_tokens: 512
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
max_samples: 100000
|
| 9 |
+
model_name_or_path: saves/LLaMA3.1-8B-Chat/full/train_2024-07-30-02-00-04_llama3.1_truthqa_bench_1
|
| 10 |
+
output_dir: saves/LLaMA3.1-8B-Chat/full/eval_2024-07-30-02-00-04_truthqa_bench1
|
| 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
|