second commit
Browse files- all_results.json +7 -7
- generated_predictions.jsonl +0 -0
- llamaboard_config.yaml +12 -57
- predict_results.json +9 -0
- running_log.txt +78 -930
- trainer_log.jsonl +0 -0
- training_args.yaml +9 -21
all_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"predict_bleu-4": 85.30970250000001,
|
| 3 |
+
"predict_rouge-1": 92.890625,
|
| 4 |
+
"predict_rouge-2": 0.0,
|
| 5 |
+
"predict_rouge-l": 92.890625,
|
| 6 |
+
"predict_runtime": 17.8088,
|
| 7 |
+
"predict_samples_per_second": 143.412,
|
| 8 |
+
"predict_steps_per_second": 8.984
|
| 9 |
}
|
generated_predictions.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llamaboard_config.yaml
CHANGED
|
@@ -1,5 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
top.booster: auto
|
| 2 |
-
top.checkpoint_path:
|
| 3 |
top.finetuning_type: full
|
| 4 |
top.model_name: LLaMA2-7B-Chat
|
| 5 |
top.quantization_bit: none
|
|
@@ -7,59 +18,3 @@ top.quantization_method: bitsandbytes
|
|
| 7 |
top.rope_scaling: none
|
| 8 |
top.template: llama2
|
| 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: 4
|
| 16 |
-
train.compute_type: bf16
|
| 17 |
-
train.create_new_adapter: false
|
| 18 |
-
train.cutoff_len: 1024
|
| 19 |
-
train.dataset:
|
| 20 |
-
- truth_train
|
| 21 |
-
train.dataset_dir: data
|
| 22 |
-
train.ds_offload: false
|
| 23 |
-
train.ds_stage: '2'
|
| 24 |
-
train.freeze_extra_modules: ''
|
| 25 |
-
train.freeze_trainable_layers: 2
|
| 26 |
-
train.freeze_trainable_modules: all
|
| 27 |
-
train.galore_rank: 16
|
| 28 |
-
train.galore_scale: 0.25
|
| 29 |
-
train.galore_target: all
|
| 30 |
-
train.galore_update_interval: 200
|
| 31 |
-
train.gradient_accumulation_steps: 8
|
| 32 |
-
train.learning_rate: 5e-6
|
| 33 |
-
train.logging_steps: 1
|
| 34 |
-
train.lora_alpha: 16
|
| 35 |
-
train.lora_dropout: 0
|
| 36 |
-
train.lora_rank: 8
|
| 37 |
-
train.lora_target: ''
|
| 38 |
-
train.loraplus_lr_ratio: 0
|
| 39 |
-
train.lr_scheduler_type: cosine
|
| 40 |
-
train.max_grad_norm: '1.0'
|
| 41 |
-
train.max_samples: '100000'
|
| 42 |
-
train.neat_packing: false
|
| 43 |
-
train.neftune_alpha: 0
|
| 44 |
-
train.num_train_epochs: '5.0'
|
| 45 |
-
train.optim: adamw_torch
|
| 46 |
-
train.packing: false
|
| 47 |
-
train.ppo_score_norm: false
|
| 48 |
-
train.ppo_whiten_rewards: false
|
| 49 |
-
train.pref_beta: 0.1
|
| 50 |
-
train.pref_ftx: 0
|
| 51 |
-
train.pref_loss: sigmoid
|
| 52 |
-
train.report_to: false
|
| 53 |
-
train.resize_vocab: false
|
| 54 |
-
train.reward_model: null
|
| 55 |
-
train.save_steps: 980
|
| 56 |
-
train.shift_attn: false
|
| 57 |
-
train.training_stage: Supervised Fine-Tuning
|
| 58 |
-
train.use_badam: false
|
| 59 |
-
train.use_dora: false
|
| 60 |
-
train.use_galore: false
|
| 61 |
-
train.use_llama_pro: false
|
| 62 |
-
train.use_pissa: false
|
| 63 |
-
train.use_rslora: false
|
| 64 |
-
train.val_size: 0
|
| 65 |
-
train.warmup_steps: 600
|
|
|
|
| 1 |
+
eval.batch_size: 2
|
| 2 |
+
eval.cutoff_len: 1024
|
| 3 |
+
eval.dataset:
|
| 4 |
+
- truth_dev
|
| 5 |
+
eval.dataset_dir: data
|
| 6 |
+
eval.max_new_tokens: 512
|
| 7 |
+
eval.max_samples: '100000'
|
| 8 |
+
eval.output_dir: eval_2024-07-11-10-49-45
|
| 9 |
+
eval.predict: true
|
| 10 |
+
eval.temperature: 0.95
|
| 11 |
+
eval.top_p: 0.7
|
| 12 |
top.booster: auto
|
| 13 |
+
top.checkpoint_path: train_2024-07-11-09-30-54_llama2_inst_truth
|
| 14 |
top.finetuning_type: full
|
| 15 |
top.model_name: LLaMA2-7B-Chat
|
| 16 |
top.quantization_bit: none
|
|
|
|
| 18 |
top.rope_scaling: none
|
| 19 |
top.template: llama2
|
| 20 |
top.visual_inputs: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
predict_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu-4": 85.30970250000001,
|
| 3 |
+
"predict_rouge-1": 92.890625,
|
| 4 |
+
"predict_rouge-2": 0.0,
|
| 5 |
+
"predict_rouge-l": 92.890625,
|
| 6 |
+
"predict_runtime": 17.8088,
|
| 7 |
+
"predict_samples_per_second": 143.412,
|
| 8 |
+
"predict_steps_per_second": 8.984
|
| 9 |
+
}
|
running_log.txt
CHANGED
|
@@ -1,65 +1,45 @@
|
|
| 1 |
-
07
|
| 2 |
|
| 3 |
-
|
| 4 |
|
| 5 |
-
07/11/2024
|
| 6 |
|
| 7 |
-
07/11/2024
|
| 8 |
|
| 9 |
-
|
| 10 |
|
| 11 |
-
|
| 12 |
|
| 13 |
-
|
| 14 |
|
| 15 |
-
[INFO|
|
| 16 |
|
| 17 |
-
[INFO|
|
| 18 |
|
| 19 |
-
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
-
|
| 24 |
|
| 25 |
-
|
| 26 |
|
| 27 |
-
07/11/2024
|
| 28 |
|
| 29 |
-
|
| 30 |
|
| 31 |
-
|
| 32 |
|
| 33 |
-
07/11/2024
|
| 34 |
|
| 35 |
-
07/11/2024
|
| 36 |
|
| 37 |
-
07/11/2024
|
| 38 |
|
| 39 |
-
07
|
| 40 |
|
| 41 |
-
07
|
| 42 |
-
|
| 43 |
-
07/11/2024 09:33:24 - INFO - llamafactory.data.template - Add pad token: </s>
|
| 44 |
-
|
| 45 |
-
07/11/2024 09:33:25 - INFO - llamafactory.data.loader - Loading dataset train_output.json...
|
| 46 |
-
|
| 47 |
-
07/11/2024 09:33:25 - INFO - llamafactory.data.loader - Loading dataset train_output.json...
|
| 48 |
-
|
| 49 |
-
07/11/2024 09:33:25 - INFO - llamafactory.data.loader - Loading dataset train_output.json...
|
| 50 |
-
|
| 51 |
-
07/11/2024 09:33:25 - INFO - llamafactory.data.loader - Loading dataset train_output.json...
|
| 52 |
-
|
| 53 |
-
07/11/2024 09:33:25 - INFO - llamafactory.data.loader - Loading dataset train_output.json...
|
| 54 |
-
|
| 55 |
-
07/11/2024 09:33:25 - INFO - llamafactory.data.loader - Loading dataset train_output.json...
|
| 56 |
-
|
| 57 |
-
07/11/2024 09:33:25 - INFO - llamafactory.data.loader - Loading dataset train_output.json...
|
| 58 |
-
|
| 59 |
-
[INFO|configuration_utils.py:733] 2024-07-11 09:33:27,545 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-2-7b-chat-hf/snapshots/f5db02db724555f92da89c216ac04704f23d4590/config.json
|
| 60 |
-
|
| 61 |
-
[INFO|configuration_utils.py:800] 2024-07-11 09:33:27,546 >> Model config LlamaConfig {
|
| 62 |
-
"_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 63 |
"architectures": [
|
| 64 |
"LlamaForCausalLM"
|
| 65 |
],
|
|
@@ -82,944 +62,112 @@
|
|
| 82 |
"rope_scaling": null,
|
| 83 |
"rope_theta": 10000.0,
|
| 84 |
"tie_word_embeddings": false,
|
| 85 |
-
"torch_dtype": "
|
| 86 |
"transformers_version": "4.42.3",
|
| 87 |
-
"use_cache":
|
| 88 |
"vocab_size": 32000
|
| 89 |
}
|
| 90 |
|
| 91 |
|
| 92 |
-
[INFO|
|
| 93 |
-
|
| 94 |
-
[INFO|modeling_utils.py:1531] 2024-07-11 09:35:30,794 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
|
| 95 |
-
|
| 96 |
-
[INFO|configuration_utils.py:1000] 2024-07-11 09:35:30,799 >> Generate config GenerationConfig {
|
| 97 |
-
"bos_token_id": 1,
|
| 98 |
-
"eos_token_id": 2
|
| 99 |
-
}
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
[INFO|modeling_utils.py:4364] 2024-07-11 09:35:47,952 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
|
| 103 |
|
|
|
|
| 104 |
|
| 105 |
-
[INFO|modeling_utils.py:
|
| 106 |
-
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.
|
| 107 |
|
| 108 |
-
[INFO|configuration_utils.py:
|
| 109 |
-
|
| 110 |
-
[INFO|configuration_utils.py:1000] 2024-07-11 09:35:48,301 >> Generate config GenerationConfig {
|
| 111 |
"bos_token_id": 1,
|
| 112 |
-
"
|
| 113 |
-
"eos_token_id": 2,
|
| 114 |
-
"max_length": 4096,
|
| 115 |
-
"pad_token_id": 0,
|
| 116 |
-
"temperature": 0.6,
|
| 117 |
-
"top_p": 0.9
|
| 118 |
}
|
| 119 |
|
| 120 |
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
[INFO|attention.py:80] 2024-07-11 09:35:48,308 >> Using torch SDPA for faster training and inference.
|
| 124 |
-
|
| 125 |
-
[INFO|adapter.py:302] 2024-07-11 09:35:48,309 >> Upcasting trainable params to float32.
|
| 126 |
-
|
| 127 |
-
[INFO|adapter.py:48] 2024-07-11 09:35:48,309 >> Fine-tuning method: Full
|
| 128 |
-
|
| 129 |
-
[INFO|loader.py:196] 2024-07-11 09:35:48,360 >> trainable params: 6,738,415,616 || all params: 6,738,415,616 || trainable%: 100.0000
|
| 130 |
-
|
| 131 |
-
[INFO|trainer.py:642] 2024-07-11 09:35:48,366 >> Using auto half precision backend
|
| 132 |
-
|
| 133 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 134 |
-
|
| 135 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 136 |
-
|
| 137 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 138 |
-
|
| 139 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 140 |
-
|
| 141 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 142 |
-
|
| 143 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 144 |
-
|
| 145 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 146 |
-
|
| 147 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 148 |
-
|
| 149 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 150 |
-
|
| 151 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 152 |
-
|
| 153 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 154 |
-
|
| 155 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 156 |
-
|
| 157 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 158 |
-
|
| 159 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 160 |
-
|
| 161 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 162 |
-
|
| 163 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 164 |
-
|
| 165 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 166 |
-
|
| 167 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 168 |
-
|
| 169 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 170 |
-
|
| 171 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 172 |
-
|
| 173 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.loader - trainable params: 6,738,415,616 || all params: 6,738,415,616 || trainable%: 100.0000
|
| 174 |
-
|
| 175 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.loader - trainable params: 6,738,415,616 || all params: 6,738,415,616 || trainable%: 100.0000
|
| 176 |
-
|
| 177 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.loader - trainable params: 6,738,415,616 || all params: 6,738,415,616 || trainable%: 100.0000
|
| 178 |
-
|
| 179 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.loader - trainable params: 6,738,415,616 || all params: 6,738,415,616 || trainable%: 100.0000
|
| 180 |
-
|
| 181 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.loader - trainable params: 6,738,415,616 || all params: 6,738,415,616 || trainable%: 100.0000
|
| 182 |
-
|
| 183 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 184 |
-
|
| 185 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 186 |
-
|
| 187 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 188 |
-
|
| 189 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 190 |
-
|
| 191 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 192 |
-
|
| 193 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 194 |
-
|
| 195 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 196 |
-
|
| 197 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 198 |
-
|
| 199 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.loader - trainable params: 6,738,415,616 || all params: 6,738,415,616 || trainable%: 100.0000
|
| 200 |
-
|
| 201 |
-
07/11/2024 09:35:49 - INFO - llamafactory.model.loader - trainable params: 6,738,415,616 || all params: 6,738,415,616 || trainable%: 100.0000
|
| 202 |
-
|
| 203 |
-
[INFO|trainer.py:2128] 2024-07-11 09:36:08,514 >> ***** Running training *****
|
| 204 |
-
|
| 205 |
-
[INFO|trainer.py:2129] 2024-07-11 09:36:08,514 >> Num examples = 19,880
|
| 206 |
-
|
| 207 |
-
[INFO|trainer.py:2130] 2024-07-11 09:36:08,514 >> Num Epochs = 5
|
| 208 |
-
|
| 209 |
-
[INFO|trainer.py:2131] 2024-07-11 09:36:08,514 >> Instantaneous batch size per device = 4
|
| 210 |
-
|
| 211 |
-
[INFO|trainer.py:2134] 2024-07-11 09:36:08,514 >> Total train batch size (w. parallel, distributed & accumulation) = 256
|
| 212 |
-
|
| 213 |
-
[INFO|trainer.py:2135] 2024-07-11 09:36:08,514 >> Gradient Accumulation steps = 8
|
| 214 |
-
|
| 215 |
-
[INFO|trainer.py:2136] 2024-07-11 09:36:08,514 >> Total optimization steps = 385
|
| 216 |
-
|
| 217 |
-
[INFO|trainer.py:2137] 2024-07-11 09:36:08,516 >> Number of trainable parameters = 6,738,415,616
|
| 218 |
-
|
| 219 |
-
[INFO|callbacks.py:310] 2024-07-11 09:36:20,236 >> {'loss': 8.1083, 'learning_rate': 8.3333e-09, 'epoch': 0.01, 'throughput': 1411.72}
|
| 220 |
-
|
| 221 |
-
[INFO|callbacks.py:310] 2024-07-11 09:36:31,361 >> {'loss': 8.1052, 'learning_rate': 1.6667e-08, 'epoch': 0.03, 'throughput': 1455.41}
|
| 222 |
-
|
| 223 |
-
[INFO|callbacks.py:310] 2024-07-11 09:36:42,439 >> {'loss': 8.1366, 'learning_rate': 2.5000e-08, 'epoch': 0.04, 'throughput': 1466.88}
|
| 224 |
-
|
| 225 |
-
[INFO|callbacks.py:310] 2024-07-11 09:36:53,528 >> {'loss': 8.0413, 'learning_rate': 3.3333e-08, 'epoch': 0.05, 'throughput': 1462.41}
|
| 226 |
-
|
| 227 |
-
[INFO|callbacks.py:310] 2024-07-11 09:37:04,628 >> {'loss': 8.1055, 'learning_rate': 4.1667e-08, 'epoch': 0.06, 'throughput': 1471.37}
|
| 228 |
-
|
| 229 |
-
[INFO|callbacks.py:310] 2024-07-11 09:37:15,764 >> {'loss': 7.9666, 'learning_rate': 5.0000e-08, 'epoch': 0.08, 'throughput': 1484.19}
|
| 230 |
-
|
| 231 |
-
[INFO|callbacks.py:310] 2024-07-11 09:37:26,881 >> {'loss': 8.0182, 'learning_rate': 5.8333e-08, 'epoch': 0.09, 'throughput': 1477.83}
|
| 232 |
-
|
| 233 |
-
[INFO|callbacks.py:310] 2024-07-11 09:37:38,008 >> {'loss': 8.0363, 'learning_rate': 6.6667e-08, 'epoch': 0.10, 'throughput': 1468.21}
|
| 234 |
-
|
| 235 |
-
[INFO|callbacks.py:310] 2024-07-11 09:37:49,153 >> {'loss': 8.0918, 'learning_rate': 7.5000e-08, 'epoch': 0.12, 'throughput': 1469.05}
|
| 236 |
-
|
| 237 |
-
[INFO|callbacks.py:310] 2024-07-11 09:38:00,281 >> {'loss': 8.0197, 'learning_rate': 8.3333e-08, 'epoch': 0.13, 'throughput': 1467.95}
|
| 238 |
-
|
| 239 |
-
[INFO|callbacks.py:310] 2024-07-11 09:38:11,405 >> {'loss': 7.9714, 'learning_rate': 9.1667e-08, 'epoch': 0.14, 'throughput': 1470.48}
|
| 240 |
-
|
| 241 |
-
[INFO|callbacks.py:310] 2024-07-11 09:38:22,461 >> {'loss': 8.0131, 'learning_rate': 1.0000e-07, 'epoch': 0.15, 'throughput': 1463.77}
|
| 242 |
-
|
| 243 |
-
[INFO|callbacks.py:310] 2024-07-11 09:38:33,540 >> {'loss': 7.9796, 'learning_rate': 1.0833e-07, 'epoch': 0.17, 'throughput': 1457.86}
|
| 244 |
-
|
| 245 |
-
[INFO|callbacks.py:310] 2024-07-11 09:38:44,657 >> {'loss': 7.9999, 'learning_rate': 1.1667e-07, 'epoch': 0.18, 'throughput': 1460.84}
|
| 246 |
-
|
| 247 |
-
[INFO|callbacks.py:310] 2024-07-11 09:38:55,796 >> {'loss': 8.0168, 'learning_rate': 1.2500e-07, 'epoch': 0.19, 'throughput': 1461.12}
|
| 248 |
-
|
| 249 |
-
[INFO|callbacks.py:310] 2024-07-11 09:39:06,924 >> {'loss': 7.8423, 'learning_rate': 1.3333e-07, 'epoch': 0.21, 'throughput': 1463.26}
|
| 250 |
-
|
| 251 |
-
[INFO|callbacks.py:310] 2024-07-11 09:39:18,061 >> {'loss': 7.9208, 'learning_rate': 1.4167e-07, 'epoch': 0.22, 'throughput': 1461.36}
|
| 252 |
-
|
| 253 |
-
[INFO|callbacks.py:310] 2024-07-11 09:39:29,196 >> {'loss': 7.6898, 'learning_rate': 1.5000e-07, 'epoch': 0.23, 'throughput': 1462.71}
|
| 254 |
-
|
| 255 |
-
[INFO|callbacks.py:310] 2024-07-11 09:39:40,310 >> {'loss': 7.9285, 'learning_rate': 1.5833e-07, 'epoch': 0.24, 'throughput': 1459.08}
|
| 256 |
-
|
| 257 |
-
[INFO|callbacks.py:310] 2024-07-11 09:39:51,418 >> {'loss': 7.8924, 'learning_rate': 1.6667e-07, 'epoch': 0.26, 'throughput': 1458.15}
|
| 258 |
-
|
| 259 |
-
[INFO|callbacks.py:310] 2024-07-11 09:40:02,525 >> {'loss': 7.6173, 'learning_rate': 1.7500e-07, 'epoch': 0.27, 'throughput': 1460.88}
|
| 260 |
-
|
| 261 |
-
[INFO|callbacks.py:310] 2024-07-11 09:40:13,636 >> {'loss': 7.7661, 'learning_rate': 1.8333e-07, 'epoch': 0.28, 'throughput': 1463.97}
|
| 262 |
-
|
| 263 |
-
[INFO|callbacks.py:310] 2024-07-11 09:40:24,739 >> {'loss': 7.2936, 'learning_rate': 1.9167e-07, 'epoch': 0.30, 'throughput': 1464.98}
|
| 264 |
-
|
| 265 |
-
[INFO|callbacks.py:310] 2024-07-11 09:40:35,863 >> {'loss': 7.3044, 'learning_rate': 2.0000e-07, 'epoch': 0.31, 'throughput': 1468.54}
|
| 266 |
-
|
| 267 |
-
[INFO|callbacks.py:310] 2024-07-11 09:40:46,970 >> {'loss': 7.3500, 'learning_rate': 2.0833e-07, 'epoch': 0.32, 'throughput': 1468.11}
|
| 268 |
-
|
| 269 |
-
[INFO|callbacks.py:310] 2024-07-11 09:40:58,094 >> {'loss': 7.1213, 'learning_rate': 2.1667e-07, 'epoch': 0.33, 'throughput': 1469.84}
|
| 270 |
-
|
| 271 |
-
[INFO|callbacks.py:310] 2024-07-11 09:41:09,205 >> {'loss': 7.1363, 'learning_rate': 2.2500e-07, 'epoch': 0.35, 'throughput': 1469.80}
|
| 272 |
-
|
| 273 |
-
[INFO|callbacks.py:310] 2024-07-11 09:41:20,376 >> {'loss': 6.9016, 'learning_rate': 2.3333e-07, 'epoch': 0.36, 'throughput': 1468.87}
|
| 274 |
-
|
| 275 |
-
[INFO|callbacks.py:310] 2024-07-11 09:41:31,471 >> {'loss': 6.9764, 'learning_rate': 2.4167e-07, 'epoch': 0.37, 'throughput': 1467.16}
|
| 276 |
-
|
| 277 |
-
[INFO|callbacks.py:310] 2024-07-11 09:41:42,574 >> {'loss': 6.9005, 'learning_rate': 2.5000e-07, 'epoch': 0.39, 'throughput': 1467.82}
|
| 278 |
-
|
| 279 |
-
[INFO|callbacks.py:310] 2024-07-11 09:41:53,697 >> {'loss': 6.9852, 'learning_rate': 2.5833e-07, 'epoch': 0.40, 'throughput': 1468.73}
|
| 280 |
-
|
| 281 |
-
[INFO|callbacks.py:310] 2024-07-11 09:42:04,833 >> {'loss': 5.8340, 'learning_rate': 2.6667e-07, 'epoch': 0.41, 'throughput': 1469.26}
|
| 282 |
-
|
| 283 |
-
[INFO|callbacks.py:310] 2024-07-11 09:42:15,965 >> {'loss': 5.5452, 'learning_rate': 2.7500e-07, 'epoch': 0.42, 'throughput': 1471.43}
|
| 284 |
-
|
| 285 |
-
[INFO|callbacks.py:310] 2024-07-11 09:42:27,099 >> {'loss': 5.5189, 'learning_rate': 2.8333e-07, 'epoch': 0.44, 'throughput': 1473.12}
|
| 286 |
-
|
| 287 |
-
[INFO|callbacks.py:310] 2024-07-11 09:42:38,222 >> {'loss': 5.4654, 'learning_rate': 2.9167e-07, 'epoch': 0.45, 'throughput': 1473.94}
|
| 288 |
-
|
| 289 |
-
[INFO|callbacks.py:310] 2024-07-11 09:42:49,345 >> {'loss': 5.3117, 'learning_rate': 3.0000e-07, 'epoch': 0.46, 'throughput': 1472.23}
|
| 290 |
-
|
| 291 |
-
[INFO|callbacks.py:310] 2024-07-11 09:43:00,464 >> {'loss': 5.2744, 'learning_rate': 3.0833e-07, 'epoch': 0.48, 'throughput': 1470.87}
|
| 292 |
-
|
| 293 |
-
[INFO|callbacks.py:310] 2024-07-11 09:43:11,566 >> {'loss': 5.2821, 'learning_rate': 3.1667e-07, 'epoch': 0.49, 'throughput': 1470.77}
|
| 294 |
-
|
| 295 |
-
[INFO|callbacks.py:310] 2024-07-11 09:43:22,656 >> {'loss': 5.0967, 'learning_rate': 3.2500e-07, 'epoch': 0.50, 'throughput': 1470.64}
|
| 296 |
-
|
| 297 |
-
[INFO|callbacks.py:310] 2024-07-11 09:43:33,736 >> {'loss': 5.2167, 'learning_rate': 3.3333e-07, 'epoch': 0.51, 'throughput': 1470.41}
|
| 298 |
-
|
| 299 |
-
[INFO|callbacks.py:310] 2024-07-11 09:43:44,884 >> {'loss': 5.1517, 'learning_rate': 3.4167e-07, 'epoch': 0.53, 'throughput': 1471.24}
|
| 300 |
-
|
| 301 |
-
[INFO|callbacks.py:310] 2024-07-11 09:43:56,018 >> {'loss': 4.6959, 'learning_rate': 3.5000e-07, 'epoch': 0.54, 'throughput': 1471.59}
|
| 302 |
-
|
| 303 |
-
[INFO|callbacks.py:310] 2024-07-11 09:44:07,144 >> {'loss': 4.1458, 'learning_rate': 3.5833e-07, 'epoch': 0.55, 'throughput': 1471.34}
|
| 304 |
-
|
| 305 |
-
[INFO|callbacks.py:310] 2024-07-11 09:44:18,276 >> {'loss': 3.6692, 'learning_rate': 3.6667e-07, 'epoch': 0.57, 'throughput': 1471.55}
|
| 306 |
-
|
| 307 |
-
[INFO|callbacks.py:310] 2024-07-11 09:44:29,413 >> {'loss': 3.3322, 'learning_rate': 3.7500e-07, 'epoch': 0.58, 'throughput': 1472.18}
|
| 308 |
-
|
| 309 |
-
[INFO|callbacks.py:310] 2024-07-11 09:44:40,545 >> {'loss': 3.2857, 'learning_rate': 3.8333e-07, 'epoch': 0.59, 'throughput': 1472.04}
|
| 310 |
-
|
| 311 |
-
[INFO|callbacks.py:310] 2024-07-11 09:44:51,649 >> {'loss': 3.0806, 'learning_rate': 3.9167e-07, 'epoch': 0.60, 'throughput': 1472.06}
|
| 312 |
-
|
| 313 |
-
[INFO|callbacks.py:310] 2024-07-11 09:45:02,778 >> {'loss': 2.8239, 'learning_rate': 4.0000e-07, 'epoch': 0.62, 'throughput': 1472.90}
|
| 314 |
-
|
| 315 |
-
[INFO|callbacks.py:310] 2024-07-11 09:45:13,907 >> {'loss': 2.8695, 'learning_rate': 4.0833e-07, 'epoch': 0.63, 'throughput': 1474.53}
|
| 316 |
-
|
| 317 |
-
[INFO|callbacks.py:310] 2024-07-11 09:45:25,026 >> {'loss': 2.6218, 'learning_rate': 4.1667e-07, 'epoch': 0.64, 'throughput': 1475.14}
|
| 318 |
-
|
| 319 |
-
[INFO|callbacks.py:310] 2024-07-11 09:45:36,130 >> {'loss': 2.3993, 'learning_rate': 4.2500e-07, 'epoch': 0.66, 'throughput': 1474.86}
|
| 320 |
-
|
| 321 |
-
[INFO|callbacks.py:310] 2024-07-11 09:45:47,281 >> {'loss': 2.2828, 'learning_rate': 4.3333e-07, 'epoch': 0.67, 'throughput': 1474.81}
|
| 322 |
-
|
| 323 |
-
[INFO|callbacks.py:310] 2024-07-11 09:45:58,412 >> {'loss': 2.2063, 'learning_rate': 4.4167e-07, 'epoch': 0.68, 'throughput': 1475.84}
|
| 324 |
-
|
| 325 |
-
[INFO|callbacks.py:310] 2024-07-11 09:46:09,535 >> {'loss': 1.8878, 'learning_rate': 4.5000e-07, 'epoch': 0.69, 'throughput': 1474.30}
|
| 326 |
-
|
| 327 |
-
[INFO|callbacks.py:310] 2024-07-11 09:46:20,652 >> {'loss': 1.5971, 'learning_rate': 4.5833e-07, 'epoch': 0.71, 'throughput': 1475.65}
|
| 328 |
-
|
| 329 |
-
[INFO|callbacks.py:310] 2024-07-11 09:46:31,747 >> {'loss': 0.9604, 'learning_rate': 4.6667e-07, 'epoch': 0.72, 'throughput': 1475.05}
|
| 330 |
-
|
| 331 |
-
[INFO|callbacks.py:310] 2024-07-11 09:46:42,858 >> {'loss': 0.6287, 'learning_rate': 4.7500e-07, 'epoch': 0.73, 'throughput': 1475.70}
|
| 332 |
-
|
| 333 |
-
[INFO|callbacks.py:310] 2024-07-11 09:46:53,999 >> {'loss': 0.4844, 'learning_rate': 4.8333e-07, 'epoch': 0.75, 'throughput': 1476.45}
|
| 334 |
-
|
| 335 |
-
[INFO|callbacks.py:310] 2024-07-11 09:47:05,114 >> {'loss': 0.3891, 'learning_rate': 4.9167e-07, 'epoch': 0.76, 'throughput': 1475.83}
|
| 336 |
-
|
| 337 |
-
[INFO|callbacks.py:310] 2024-07-11 09:47:16,243 >> {'loss': 0.3570, 'learning_rate': 5.0000e-07, 'epoch': 0.77, 'throughput': 1476.05}
|
| 338 |
-
|
| 339 |
-
[INFO|callbacks.py:310] 2024-07-11 09:47:27,365 >> {'loss': 0.2854, 'learning_rate': 5.0833e-07, 'epoch': 0.78, 'throughput': 1476.53}
|
| 340 |
-
|
| 341 |
-
[INFO|callbacks.py:310] 2024-07-11 09:47:38,471 >> {'loss': 0.2403, 'learning_rate': 5.1667e-07, 'epoch': 0.80, 'throughput': 1476.18}
|
| 342 |
-
|
| 343 |
-
[INFO|callbacks.py:310] 2024-07-11 09:47:49,613 >> {'loss': 0.2522, 'learning_rate': 5.2500e-07, 'epoch': 0.81, 'throughput': 1477.05}
|
| 344 |
-
|
| 345 |
-
[INFO|callbacks.py:310] 2024-07-11 09:48:00,728 >> {'loss': 0.2339, 'learning_rate': 5.3333e-07, 'epoch': 0.82, 'throughput': 1476.51}
|
| 346 |
-
|
| 347 |
-
[INFO|callbacks.py:310] 2024-07-11 09:48:11,827 >> {'loss': 0.2214, 'learning_rate': 5.4167e-07, 'epoch': 0.84, 'throughput': 1477.43}
|
| 348 |
-
|
| 349 |
-
[INFO|callbacks.py:310] 2024-07-11 09:48:22,937 >> {'loss': 0.1912, 'learning_rate': 5.5000e-07, 'epoch': 0.85, 'throughput': 1478.13}
|
| 350 |
-
|
| 351 |
-
[INFO|callbacks.py:310] 2024-07-11 09:48:34,066 >> {'loss': 0.2157, 'learning_rate': 5.5833e-07, 'epoch': 0.86, 'throughput': 1479.16}
|
| 352 |
-
|
| 353 |
-
[INFO|callbacks.py:310] 2024-07-11 09:48:45,169 >> {'loss': 0.2045, 'learning_rate': 5.6667e-07, 'epoch': 0.87, 'throughput': 1478.13}
|
| 354 |
-
|
| 355 |
-
[INFO|callbacks.py:310] 2024-07-11 09:48:56,325 >> {'loss': 0.1964, 'learning_rate': 5.7500e-07, 'epoch': 0.89, 'throughput': 1478.54}
|
| 356 |
-
|
| 357 |
-
[INFO|callbacks.py:310] 2024-07-11 09:49:07,421 >> {'loss': 0.1901, 'learning_rate': 5.8333e-07, 'epoch': 0.90, 'throughput': 1477.07}
|
| 358 |
-
|
| 359 |
-
[INFO|callbacks.py:310] 2024-07-11 09:49:18,532 >> {'loss': 0.1891, 'learning_rate': 5.9167e-07, 'epoch': 0.91, 'throughput': 1477.00}
|
| 360 |
-
|
| 361 |
-
[INFO|callbacks.py:310] 2024-07-11 09:49:29,697 >> {'loss': 0.1841, 'learning_rate': 6.0000e-07, 'epoch': 0.93, 'throughput': 1477.26}
|
| 362 |
-
|
| 363 |
-
[INFO|callbacks.py:310] 2024-07-11 09:49:40,800 >> {'loss': 0.1803, 'learning_rate': 6.0833e-07, 'epoch': 0.94, 'throughput': 1477.28}
|
| 364 |
-
|
| 365 |
-
[INFO|callbacks.py:310] 2024-07-11 09:49:51,887 >> {'loss': 0.1657, 'learning_rate': 6.1667e-07, 'epoch': 0.95, 'throughput': 1477.17}
|
| 366 |
-
|
| 367 |
-
[INFO|callbacks.py:310] 2024-07-11 09:50:02,989 >> {'loss': 0.2157, 'learning_rate': 6.2500e-07, 'epoch': 0.96, 'throughput': 1477.26}
|
| 368 |
-
|
| 369 |
-
[INFO|callbacks.py:310] 2024-07-11 09:50:14,088 >> {'loss': 0.2000, 'learning_rate': 6.3333e-07, 'epoch': 0.98, 'throughput': 1477.40}
|
| 370 |
-
|
| 371 |
-
[INFO|callbacks.py:310] 2024-07-11 09:50:25,168 >> {'loss': 0.1519, 'learning_rate': 6.4167e-07, 'epoch': 0.99, 'throughput': 1476.86}
|
| 372 |
-
|
| 373 |
-
[INFO|callbacks.py:310] 2024-07-11 09:50:36,302 >> {'loss': 0.1765, 'learning_rate': 6.5000e-07, 'epoch': 1.00, 'throughput': 1477.71}
|
| 374 |
-
|
| 375 |
-
[INFO|callbacks.py:310] 2024-07-11 09:50:47,461 >> {'loss': 0.1907, 'learning_rate': 6.5833e-07, 'epoch': 1.02, 'throughput': 1478.10}
|
| 376 |
-
|
| 377 |
-
[INFO|callbacks.py:310] 2024-07-11 09:50:58,581 >> {'loss': 0.1593, 'learning_rate': 6.6667e-07, 'epoch': 1.03, 'throughput': 1477.21}
|
| 378 |
-
|
| 379 |
-
[INFO|callbacks.py:310] 2024-07-11 09:51:09,696 >> {'loss': 0.1659, 'learning_rate': 6.7500e-07, 'epoch': 1.04, 'throughput': 1477.14}
|
| 380 |
-
|
| 381 |
-
[INFO|callbacks.py:310] 2024-07-11 09:51:20,799 >> {'loss': 0.1619, 'learning_rate': 6.8333e-07, 'epoch': 1.05, 'throughput': 1477.58}
|
| 382 |
-
|
| 383 |
-
[INFO|callbacks.py:310] 2024-07-11 09:51:31,873 >> {'loss': 0.1680, 'learning_rate': 6.9167e-07, 'epoch': 1.07, 'throughput': 1477.08}
|
| 384 |
-
|
| 385 |
-
[INFO|callbacks.py:310] 2024-07-11 09:51:43,028 >> {'loss': 0.1627, 'learning_rate': 7.0000e-07, 'epoch': 1.08, 'throughput': 1477.67}
|
| 386 |
-
|
| 387 |
-
[INFO|callbacks.py:310] 2024-07-11 09:51:54,163 >> {'loss': 0.1421, 'learning_rate': 7.0833e-07, 'epoch': 1.09, 'throughput': 1478.13}
|
| 388 |
-
|
| 389 |
-
[INFO|callbacks.py:310] 2024-07-11 09:52:05,268 >> {'loss': 0.1517, 'learning_rate': 7.1667e-07, 'epoch': 1.11, 'throughput': 1478.20}
|
| 390 |
-
|
| 391 |
-
[INFO|callbacks.py:310] 2024-07-11 09:52:16,378 >> {'loss': 0.1519, 'learning_rate': 7.2500e-07, 'epoch': 1.12, 'throughput': 1477.17}
|
| 392 |
-
|
| 393 |
-
[INFO|callbacks.py:310] 2024-07-11 09:52:27,517 >> {'loss': 0.1280, 'learning_rate': 7.3333e-07, 'epoch': 1.13, 'throughput': 1477.75}
|
| 394 |
-
|
| 395 |
-
[INFO|callbacks.py:310] 2024-07-11 09:52:38,648 >> {'loss': 0.1481, 'learning_rate': 7.4167e-07, 'epoch': 1.14, 'throughput': 1477.59}
|
| 396 |
-
|
| 397 |
-
[INFO|callbacks.py:310] 2024-07-11 09:52:49,791 >> {'loss': 0.1636, 'learning_rate': 7.5000e-07, 'epoch': 1.16, 'throughput': 1478.21}
|
| 398 |
-
|
| 399 |
-
[INFO|callbacks.py:310] 2024-07-11 09:53:00,912 >> {'loss': 0.1443, 'learning_rate': 7.5833e-07, 'epoch': 1.17, 'throughput': 1478.70}
|
| 400 |
-
|
| 401 |
-
[INFO|callbacks.py:310] 2024-07-11 09:53:12,019 >> {'loss': 0.1592, 'learning_rate': 7.6667e-07, 'epoch': 1.18, 'throughput': 1479.03}
|
| 402 |
-
|
| 403 |
-
[INFO|callbacks.py:310] 2024-07-11 09:53:23,069 >> {'loss': 0.1744, 'learning_rate': 7.7500e-07, 'epoch': 1.20, 'throughput': 1478.61}
|
| 404 |
-
|
| 405 |
-
[INFO|callbacks.py:310] 2024-07-11 09:53:34,191 >> {'loss': 0.1615, 'learning_rate': 7.8333e-07, 'epoch': 1.21, 'throughput': 1478.86}
|
| 406 |
-
|
| 407 |
-
[INFO|callbacks.py:310] 2024-07-11 09:53:45,333 >> {'loss': 0.1466, 'learning_rate': 7.9167e-07, 'epoch': 1.22, 'throughput': 1480.34}
|
| 408 |
-
|
| 409 |
-
[INFO|callbacks.py:310] 2024-07-11 09:53:56,455 >> {'loss': 0.1333, 'learning_rate': 8.0000e-07, 'epoch': 1.23, 'throughput': 1480.18}
|
| 410 |
-
|
| 411 |
-
[INFO|callbacks.py:310] 2024-07-11 09:54:07,585 >> {'loss': 0.1475, 'learning_rate': 8.0833e-07, 'epoch': 1.25, 'throughput': 1479.91}
|
| 412 |
-
|
| 413 |
-
[INFO|callbacks.py:310] 2024-07-11 09:54:18,772 >> {'loss': 0.1420, 'learning_rate': 8.1667e-07, 'epoch': 1.26, 'throughput': 1480.14}
|
| 414 |
-
|
| 415 |
-
[INFO|callbacks.py:310] 2024-07-11 09:54:29,887 >> {'loss': 0.1480, 'learning_rate': 8.2500e-07, 'epoch': 1.27, 'throughput': 1480.08}
|
| 416 |
-
|
| 417 |
-
[INFO|callbacks.py:310] 2024-07-11 09:54:40,939 >> {'loss': 0.1539, 'learning_rate': 8.3333e-07, 'epoch': 1.29, 'throughput': 1478.98}
|
| 418 |
-
|
| 419 |
-
[INFO|callbacks.py:310] 2024-07-11 09:54:52,040 >> {'loss': 0.1496, 'learning_rate': 8.4167e-07, 'epoch': 1.30, 'throughput': 1479.63}
|
| 420 |
-
|
| 421 |
-
[INFO|callbacks.py:310] 2024-07-11 09:55:03,133 >> {'loss': 0.1563, 'learning_rate': 8.5000e-07, 'epoch': 1.31, 'throughput': 1479.38}
|
| 422 |
-
|
| 423 |
-
[INFO|callbacks.py:310] 2024-07-11 09:55:14,217 >> {'loss': 0.1295, 'learning_rate': 8.5833e-07, 'epoch': 1.32, 'throughput': 1478.95}
|
| 424 |
-
|
| 425 |
-
[INFO|callbacks.py:310] 2024-07-11 09:55:25,352 >> {'loss': 0.1353, 'learning_rate': 8.6667e-07, 'epoch': 1.34, 'throughput': 1478.71}
|
| 426 |
-
|
| 427 |
-
[INFO|callbacks.py:310] 2024-07-11 09:55:36,494 >> {'loss': 0.1376, 'learning_rate': 8.7500e-07, 'epoch': 1.35, 'throughput': 1478.25}
|
| 428 |
-
|
| 429 |
-
[INFO|callbacks.py:310] 2024-07-11 09:55:47,650 >> {'loss': 0.1313, 'learning_rate': 8.8333e-07, 'epoch': 1.36, 'throughput': 1478.13}
|
| 430 |
-
|
| 431 |
-
[INFO|callbacks.py:310] 2024-07-11 09:55:58,764 >> {'loss': 0.1367, 'learning_rate': 8.9167e-07, 'epoch': 1.38, 'throughput': 1477.58}
|
| 432 |
-
|
| 433 |
-
[INFO|callbacks.py:310] 2024-07-11 09:56:09,911 >> {'loss': 0.1350, 'learning_rate': 9.0000e-07, 'epoch': 1.39, 'throughput': 1477.67}
|
| 434 |
-
|
| 435 |
-
[INFO|callbacks.py:310] 2024-07-11 09:56:20,982 >> {'loss': 0.1212, 'learning_rate': 9.0833e-07, 'epoch': 1.40, 'throughput': 1477.90}
|
| 436 |
-
|
| 437 |
-
[INFO|callbacks.py:310] 2024-07-11 09:56:32,078 >> {'loss': 0.1355, 'learning_rate': 9.1667e-07, 'epoch': 1.41, 'throughput': 1478.26}
|
| 438 |
-
|
| 439 |
-
[INFO|callbacks.py:310] 2024-07-11 09:56:43,192 >> {'loss': 0.1439, 'learning_rate': 9.2500e-07, 'epoch': 1.43, 'throughput': 1478.53}
|
| 440 |
-
|
| 441 |
-
[INFO|callbacks.py:310] 2024-07-11 09:56:54,346 >> {'loss': 0.1323, 'learning_rate': 9.3333e-07, 'epoch': 1.44, 'throughput': 1478.60}
|
| 442 |
-
|
| 443 |
-
[INFO|callbacks.py:310] 2024-07-11 09:57:05,472 >> {'loss': 0.1376, 'learning_rate': 9.4167e-07, 'epoch': 1.45, 'throughput': 1478.52}
|
| 444 |
-
|
| 445 |
-
[INFO|callbacks.py:310] 2024-07-11 09:57:16,583 >> {'loss': 0.1191, 'learning_rate': 9.5000e-07, 'epoch': 1.47, 'throughput': 1478.08}
|
| 446 |
-
|
| 447 |
-
[INFO|callbacks.py:310] 2024-07-11 09:57:27,706 >> {'loss': 0.1045, 'learning_rate': 9.5833e-07, 'epoch': 1.48, 'throughput': 1477.61}
|
| 448 |
-
|
| 449 |
-
[INFO|callbacks.py:310] 2024-07-11 09:57:38,811 >> {'loss': 0.1467, 'learning_rate': 9.6667e-07, 'epoch': 1.49, 'throughput': 1476.92}
|
| 450 |
-
|
| 451 |
-
[INFO|callbacks.py:310] 2024-07-11 09:57:49,937 >> {'loss': 0.1142, 'learning_rate': 9.7500e-07, 'epoch': 1.50, 'throughput': 1477.03}
|
| 452 |
-
|
| 453 |
-
[INFO|callbacks.py:310] 2024-07-11 09:58:01,037 >> {'loss': 0.1107, 'learning_rate': 9.8333e-07, 'epoch': 1.52, 'throughput': 1476.73}
|
| 454 |
-
|
| 455 |
-
[INFO|callbacks.py:310] 2024-07-11 09:58:12,150 >> {'loss': 0.1460, 'learning_rate': 9.9167e-07, 'epoch': 1.53, 'throughput': 1477.00}
|
| 456 |
-
|
| 457 |
-
[INFO|callbacks.py:310] 2024-07-11 09:58:23,267 >> {'loss': 0.1533, 'learning_rate': 1.0000e-06, 'epoch': 1.54, 'throughput': 1477.02}
|
| 458 |
-
|
| 459 |
-
[INFO|callbacks.py:310] 2024-07-11 09:58:34,358 >> {'loss': 0.1315, 'learning_rate': 1.0083e-06, 'epoch': 1.56, 'throughput': 1476.81}
|
| 460 |
-
|
| 461 |
-
[INFO|callbacks.py:310] 2024-07-11 09:58:45,523 >> {'loss': 0.1197, 'learning_rate': 1.0167e-06, 'epoch': 1.57, 'throughput': 1476.92}
|
| 462 |
-
|
| 463 |
-
[INFO|callbacks.py:310] 2024-07-11 09:58:56,666 >> {'loss': 0.1228, 'learning_rate': 1.0250e-06, 'epoch': 1.58, 'throughput': 1477.06}
|
| 464 |
-
|
| 465 |
-
[INFO|callbacks.py:310] 2024-07-11 09:59:07,814 >> {'loss': 0.1273, 'learning_rate': 1.0333e-06, 'epoch': 1.59, 'throughput': 1477.06}
|
| 466 |
-
|
| 467 |
-
[INFO|callbacks.py:310] 2024-07-11 09:59:18,959 >> {'loss': 0.1410, 'learning_rate': 1.0417e-06, 'epoch': 1.61, 'throughput': 1477.45}
|
| 468 |
-
|
| 469 |
-
[INFO|callbacks.py:310] 2024-07-11 09:59:30,083 >> {'loss': 0.1315, 'learning_rate': 1.0500e-06, 'epoch': 1.62, 'throughput': 1477.73}
|
| 470 |
-
|
| 471 |
-
[INFO|callbacks.py:310] 2024-07-11 09:59:41,190 >> {'loss': 0.1136, 'learning_rate': 1.0583e-06, 'epoch': 1.63, 'throughput': 1478.09}
|
| 472 |
-
|
| 473 |
-
[INFO|callbacks.py:310] 2024-07-11 09:59:52,299 >> {'loss': 0.1013, 'learning_rate': 1.0667e-06, 'epoch': 1.65, 'throughput': 1478.54}
|
| 474 |
-
|
| 475 |
-
[INFO|callbacks.py:310] 2024-07-11 10:00:03,422 >> {'loss': 0.1056, 'learning_rate': 1.0750e-06, 'epoch': 1.66, 'throughput': 1478.14}
|
| 476 |
-
|
| 477 |
-
[INFO|callbacks.py:310] 2024-07-11 10:00:14,531 >> {'loss': 0.1071, 'learning_rate': 1.0833e-06, 'epoch': 1.67, 'throughput': 1478.54}
|
| 478 |
-
|
| 479 |
-
[INFO|callbacks.py:310] 2024-07-11 10:00:25,649 >> {'loss': 0.1357, 'learning_rate': 1.0917e-06, 'epoch': 1.68, 'throughput': 1478.41}
|
| 480 |
-
|
| 481 |
-
[INFO|callbacks.py:310] 2024-07-11 10:00:36,774 >> {'loss': 0.1181, 'learning_rate': 1.1000e-06, 'epoch': 1.70, 'throughput': 1478.26}
|
| 482 |
-
|
| 483 |
-
[INFO|callbacks.py:310] 2024-07-11 10:00:47,927 >> {'loss': 0.0826, 'learning_rate': 1.1083e-06, 'epoch': 1.71, 'throughput': 1478.30}
|
| 484 |
-
|
| 485 |
-
[INFO|callbacks.py:310] 2024-07-11 10:00:59,041 >> {'loss': 0.1221, 'learning_rate': 1.1167e-06, 'epoch': 1.72, 'throughput': 1477.92}
|
| 486 |
-
|
| 487 |
-
[INFO|callbacks.py:310] 2024-07-11 10:01:10,170 >> {'loss': 0.1021, 'learning_rate': 1.1250e-06, 'epoch': 1.74, 'throughput': 1478.20}
|
| 488 |
-
|
| 489 |
-
[INFO|callbacks.py:310] 2024-07-11 10:01:21,237 >> {'loss': 0.0980, 'learning_rate': 1.1333e-06, 'epoch': 1.75, 'throughput': 1478.17}
|
| 490 |
-
|
| 491 |
-
[INFO|callbacks.py:310] 2024-07-11 10:01:32,344 >> {'loss': 0.1085, 'learning_rate': 1.1417e-06, 'epoch': 1.76, 'throughput': 1478.40}
|
| 492 |
-
|
| 493 |
-
[INFO|callbacks.py:310] 2024-07-11 10:01:43,423 >> {'loss': 0.1038, 'learning_rate': 1.1500e-06, 'epoch': 1.77, 'throughput': 1478.07}
|
| 494 |
-
|
| 495 |
-
[INFO|callbacks.py:310] 2024-07-11 10:01:54,521 >> {'loss': 0.1081, 'learning_rate': 1.1583e-06, 'epoch': 1.79, 'throughput': 1478.19}
|
| 496 |
-
|
| 497 |
-
[INFO|callbacks.py:310] 2024-07-11 10:02:05,652 >> {'loss': 0.1287, 'learning_rate': 1.1667e-06, 'epoch': 1.80, 'throughput': 1478.10}
|
| 498 |
-
|
| 499 |
-
[INFO|callbacks.py:310] 2024-07-11 10:02:16,763 >> {'loss': 0.1068, 'learning_rate': 1.1750e-06, 'epoch': 1.81, 'throughput': 1478.11}
|
| 500 |
-
|
| 501 |
-
[INFO|callbacks.py:310] 2024-07-11 10:02:27,850 >> {'loss': 0.1202, 'learning_rate': 1.1833e-06, 'epoch': 1.83, 'throughput': 1477.67}
|
| 502 |
-
|
| 503 |
-
[INFO|callbacks.py:310] 2024-07-11 10:02:38,969 >> {'loss': 0.1190, 'learning_rate': 1.1917e-06, 'epoch': 1.84, 'throughput': 1477.42}
|
| 504 |
-
|
| 505 |
-
[INFO|callbacks.py:310] 2024-07-11 10:02:50,085 >> {'loss': 0.1273, 'learning_rate': 1.2000e-06, 'epoch': 1.85, 'throughput': 1477.51}
|
| 506 |
-
|
| 507 |
-
[INFO|callbacks.py:310] 2024-07-11 10:03:01,139 >> {'loss': 0.1024, 'learning_rate': 1.2083e-06, 'epoch': 1.86, 'throughput': 1477.11}
|
| 508 |
-
|
| 509 |
-
[INFO|callbacks.py:310] 2024-07-11 10:03:12,232 >> {'loss': 0.1143, 'learning_rate': 1.2167e-06, 'epoch': 1.88, 'throughput': 1476.97}
|
| 510 |
-
|
| 511 |
-
[INFO|callbacks.py:310] 2024-07-11 10:03:23,344 >> {'loss': 0.1229, 'learning_rate': 1.2250e-06, 'epoch': 1.89, 'throughput': 1477.01}
|
| 512 |
-
|
| 513 |
-
[INFO|callbacks.py:310] 2024-07-11 10:03:34,449 >> {'loss': 0.0964, 'learning_rate': 1.2333e-06, 'epoch': 1.90, 'throughput': 1476.61}
|
| 514 |
-
|
| 515 |
-
[INFO|callbacks.py:310] 2024-07-11 10:03:45,575 >> {'loss': 0.1132, 'learning_rate': 1.2417e-06, 'epoch': 1.92, 'throughput': 1477.03}
|
| 516 |
-
|
| 517 |
-
[INFO|callbacks.py:310] 2024-07-11 10:03:56,704 >> {'loss': 0.0734, 'learning_rate': 1.2500e-06, 'epoch': 1.93, 'throughput': 1476.98}
|
| 518 |
|
| 519 |
-
|
| 520 |
|
| 521 |
-
|
| 522 |
|
| 523 |
-
|
| 524 |
|
| 525 |
-
|
| 526 |
|
| 527 |
-
|
| 528 |
|
| 529 |
-
|
| 530 |
|
| 531 |
-
|
| 532 |
|
| 533 |
-
|
| 534 |
|
| 535 |
-
[INFO|
|
| 536 |
|
| 537 |
-
[INFO|callbacks.py:310] 2024-07-11 10:05:47,915 >> {'loss': 0.0791, 'learning_rate': 1.3333e-06, 'epoch': 2.06, 'throughput': 1476.00}
|
| 538 |
|
| 539 |
-
|
| 540 |
|
| 541 |
-
[INFO|
|
| 542 |
-
|
| 543 |
-
[INFO|callbacks.py:310] 2024-07-11 10:06:21,185 >> {'loss': 0.0584, 'learning_rate': 1.3583e-06, 'epoch': 2.10, 'throughput': 1475.48}
|
| 544 |
-
|
| 545 |
-
[INFO|callbacks.py:310] 2024-07-11 10:06:32,281 >> {'loss': 0.0811, 'learning_rate': 1.3667e-06, 'epoch': 2.11, 'throughput': 1475.35}
|
| 546 |
-
|
| 547 |
-
[INFO|callbacks.py:310] 2024-07-11 10:06:43,373 >> {'loss': 0.0663, 'learning_rate': 1.3750e-06, 'epoch': 2.12, 'throughput': 1475.17}
|
| 548 |
-
|
| 549 |
-
[INFO|callbacks.py:310] 2024-07-11 10:06:54,462 >> {'loss': 0.0802, 'learning_rate': 1.3833e-06, 'epoch': 2.14, 'throughput': 1475.13}
|
| 550 |
-
|
| 551 |
-
[INFO|callbacks.py:310] 2024-07-11 10:07:05,548 >> {'loss': 0.0587, 'learning_rate': 1.3917e-06, 'epoch': 2.15, 'throughput': 1474.82}
|
| 552 |
-
|
| 553 |
-
[INFO|callbacks.py:310] 2024-07-11 10:07:16,701 >> {'loss': 0.0953, 'learning_rate': 1.4000e-06, 'epoch': 2.16, 'throughput': 1474.73}
|
| 554 |
-
|
| 555 |
-
[INFO|callbacks.py:310] 2024-07-11 10:07:27,833 >> {'loss': 0.0795, 'learning_rate': 1.4083e-06, 'epoch': 2.17, 'throughput': 1474.63}
|
| 556 |
-
|
| 557 |
-
[INFO|callbacks.py:310] 2024-07-11 10:07:38,959 >> {'loss': 0.1015, 'learning_rate': 1.4167e-06, 'epoch': 2.19, 'throughput': 1474.63}
|
| 558 |
-
|
| 559 |
-
[INFO|callbacks.py:310] 2024-07-11 10:07:50,039 >> {'loss': 0.0614, 'learning_rate': 1.4250e-06, 'epoch': 2.20, 'throughput': 1474.37}
|
| 560 |
-
|
| 561 |
-
[INFO|callbacks.py:310] 2024-07-11 10:08:01,150 >> {'loss': 0.0753, 'learning_rate': 1.4333e-06, 'epoch': 2.21, 'throughput': 1474.59}
|
| 562 |
-
|
| 563 |
-
[INFO|callbacks.py:310] 2024-07-11 10:08:12,309 >> {'loss': 0.0800, 'learning_rate': 1.4417e-06, 'epoch': 2.23, 'throughput': 1475.05}
|
| 564 |
-
|
| 565 |
-
[INFO|callbacks.py:310] 2024-07-11 10:08:23,444 >> {'loss': 0.0603, 'learning_rate': 1.4500e-06, 'epoch': 2.24, 'throughput': 1475.13}
|
| 566 |
-
|
| 567 |
-
[INFO|callbacks.py:310] 2024-07-11 10:08:34,582 >> {'loss': 0.0874, 'learning_rate': 1.4583e-06, 'epoch': 2.25, 'throughput': 1475.01}
|
| 568 |
-
|
| 569 |
-
[INFO|callbacks.py:310] 2024-07-11 10:08:45,695 >> {'loss': 0.0833, 'learning_rate': 1.4667e-06, 'epoch': 2.26, 'throughput': 1475.02}
|
| 570 |
-
|
| 571 |
-
[INFO|callbacks.py:310] 2024-07-11 10:08:56,832 >> {'loss': 0.0676, 'learning_rate': 1.4750e-06, 'epoch': 2.28, 'throughput': 1474.80}
|
| 572 |
-
|
| 573 |
-
[INFO|callbacks.py:310] 2024-07-11 10:09:07,950 >> {'loss': 0.0860, 'learning_rate': 1.4833e-06, 'epoch': 2.29, 'throughput': 1474.96}
|
| 574 |
-
|
| 575 |
-
[INFO|callbacks.py:310] 2024-07-11 10:09:19,042 >> {'loss': 0.0662, 'learning_rate': 1.4917e-06, 'epoch': 2.30, 'throughput': 1474.55}
|
| 576 |
-
|
| 577 |
-
[INFO|callbacks.py:310] 2024-07-11 10:09:30,161 >> {'loss': 0.1028, 'learning_rate': 1.5000e-06, 'epoch': 2.32, 'throughput': 1474.63}
|
| 578 |
-
|
| 579 |
-
[INFO|callbacks.py:310] 2024-07-11 10:09:41,272 >> {'loss': 0.0882, 'learning_rate': 1.5083e-06, 'epoch': 2.33, 'throughput': 1474.45}
|
| 580 |
-
|
| 581 |
-
[INFO|callbacks.py:310] 2024-07-11 10:09:52,377 >> {'loss': 0.0806, 'learning_rate': 1.5167e-06, 'epoch': 2.34, 'throughput': 1474.52}
|
| 582 |
-
|
| 583 |
-
[INFO|callbacks.py:310] 2024-07-11 10:10:03,473 >> {'loss': 0.1108, 'learning_rate': 1.5250e-06, 'epoch': 2.35, 'throughput': 1474.19}
|
| 584 |
-
|
| 585 |
-
[INFO|callbacks.py:310] 2024-07-11 10:10:14,639 >> {'loss': 0.0687, 'learning_rate': 1.5333e-06, 'epoch': 2.37, 'throughput': 1474.68}
|
| 586 |
-
|
| 587 |
-
[INFO|callbacks.py:310] 2024-07-11 10:10:25,742 >> {'loss': 0.0736, 'learning_rate': 1.5417e-06, 'epoch': 2.38, 'throughput': 1474.67}
|
| 588 |
-
|
| 589 |
-
[INFO|callbacks.py:310] 2024-07-11 10:10:36,853 >> {'loss': 0.0779, 'learning_rate': 1.5500e-06, 'epoch': 2.39, 'throughput': 1474.70}
|
| 590 |
-
|
| 591 |
-
[INFO|callbacks.py:310] 2024-07-11 10:10:47,981 >> {'loss': 0.0709, 'learning_rate': 1.5583e-06, 'epoch': 2.41, 'throughput': 1474.61}
|
| 592 |
-
|
| 593 |
-
[INFO|callbacks.py:310] 2024-07-11 10:10:59,101 >> {'loss': 0.0652, 'learning_rate': 1.5667e-06, 'epoch': 2.42, 'throughput': 1474.76}
|
| 594 |
-
|
| 595 |
-
[INFO|callbacks.py:310] 2024-07-11 10:11:10,209 >> {'loss': 0.1095, 'learning_rate': 1.5750e-06, 'epoch': 2.43, 'throughput': 1475.00}
|
| 596 |
-
|
| 597 |
-
[INFO|callbacks.py:310] 2024-07-11 10:11:21,338 >> {'loss': 0.0618, 'learning_rate': 1.5833e-06, 'epoch': 2.44, 'throughput': 1475.18}
|
| 598 |
-
|
| 599 |
-
[INFO|callbacks.py:310] 2024-07-11 10:11:32,451 >> {'loss': 0.0666, 'learning_rate': 1.5917e-06, 'epoch': 2.46, 'throughput': 1475.36}
|
| 600 |
-
|
| 601 |
-
[INFO|callbacks.py:310] 2024-07-11 10:11:43,569 >> {'loss': 0.0573, 'learning_rate': 1.6000e-06, 'epoch': 2.47, 'throughput': 1475.40}
|
| 602 |
-
|
| 603 |
-
[INFO|callbacks.py:310] 2024-07-11 10:11:54,697 >> {'loss': 0.0577, 'learning_rate': 1.6083e-06, 'epoch': 2.48, 'throughput': 1475.50}
|
| 604 |
-
|
| 605 |
-
[INFO|callbacks.py:310] 2024-07-11 10:12:05,820 >> {'loss': 0.0813, 'learning_rate': 1.6167e-06, 'epoch': 2.50, 'throughput': 1475.34}
|
| 606 |
-
|
| 607 |
-
[INFO|callbacks.py:310] 2024-07-11 10:12:16,940 >> {'loss': 0.0660, 'learning_rate': 1.6250e-06, 'epoch': 2.51, 'throughput': 1475.24}
|
| 608 |
-
|
| 609 |
-
[INFO|callbacks.py:310] 2024-07-11 10:12:28,083 >> {'loss': 0.0622, 'learning_rate': 1.6333e-06, 'epoch': 2.52, 'throughput': 1475.32}
|
| 610 |
-
|
| 611 |
-
[INFO|callbacks.py:310] 2024-07-11 10:12:39,175 >> {'loss': 0.0616, 'learning_rate': 1.6417e-06, 'epoch': 2.53, 'throughput': 1475.12}
|
| 612 |
-
|
| 613 |
-
[INFO|callbacks.py:310] 2024-07-11 10:12:50,265 >> {'loss': 0.0993, 'learning_rate': 1.6500e-06, 'epoch': 2.55, 'throughput': 1475.12}
|
| 614 |
-
|
| 615 |
-
[INFO|callbacks.py:310] 2024-07-11 10:13:01,337 >> {'loss': 0.0702, 'learning_rate': 1.6583e-06, 'epoch': 2.56, 'throughput': 1475.10}
|
| 616 |
-
|
| 617 |
-
[INFO|callbacks.py:310] 2024-07-11 10:13:12,425 >> {'loss': 0.0743, 'learning_rate': 1.6667e-06, 'epoch': 2.57, 'throughput': 1474.97}
|
| 618 |
-
|
| 619 |
-
[INFO|callbacks.py:310] 2024-07-11 10:13:23,525 >> {'loss': 0.0647, 'learning_rate': 1.6750e-06, 'epoch': 2.59, 'throughput': 1474.93}
|
| 620 |
-
|
| 621 |
-
[INFO|callbacks.py:310] 2024-07-11 10:13:34,651 >> {'loss': 0.0814, 'learning_rate': 1.6833e-06, 'epoch': 2.60, 'throughput': 1475.03}
|
| 622 |
-
|
| 623 |
-
[INFO|callbacks.py:310] 2024-07-11 10:13:45,757 >> {'loss': 0.0861, 'learning_rate': 1.6917e-06, 'epoch': 2.61, 'throughput': 1474.89}
|
| 624 |
-
|
| 625 |
-
[INFO|callbacks.py:310] 2024-07-11 10:13:56,905 >> {'loss': 0.0769, 'learning_rate': 1.7000e-06, 'epoch': 2.62, 'throughput': 1475.15}
|
| 626 |
-
|
| 627 |
-
[INFO|callbacks.py:310] 2024-07-11 10:14:08,051 >> {'loss': 0.0888, 'learning_rate': 1.7083e-06, 'epoch': 2.64, 'throughput': 1475.31}
|
| 628 |
-
|
| 629 |
-
[INFO|callbacks.py:310] 2024-07-11 10:14:19,164 >> {'loss': 0.1017, 'learning_rate': 1.7167e-06, 'epoch': 2.65, 'throughput': 1475.34}
|
| 630 |
-
|
| 631 |
-
[INFO|callbacks.py:310] 2024-07-11 10:14:30,261 >> {'loss': 0.0677, 'learning_rate': 1.7250e-06, 'epoch': 2.66, 'throughput': 1475.25}
|
| 632 |
-
|
| 633 |
-
[INFO|callbacks.py:310] 2024-07-11 10:14:41,375 >> {'loss': 0.0861, 'learning_rate': 1.7333e-06, 'epoch': 2.68, 'throughput': 1475.55}
|
| 634 |
-
|
| 635 |
-
[INFO|callbacks.py:310] 2024-07-11 10:14:52,497 >> {'loss': 0.0562, 'learning_rate': 1.7417e-06, 'epoch': 2.69, 'throughput': 1475.69}
|
| 636 |
-
|
| 637 |
-
[INFO|callbacks.py:310] 2024-07-11 10:15:03,612 >> {'loss': 0.0641, 'learning_rate': 1.7500e-06, 'epoch': 2.70, 'throughput': 1475.59}
|
| 638 |
-
|
| 639 |
-
[INFO|callbacks.py:310] 2024-07-11 10:15:14,730 >> {'loss': 0.0829, 'learning_rate': 1.7583e-06, 'epoch': 2.71, 'throughput': 1475.88}
|
| 640 |
-
|
| 641 |
-
[INFO|callbacks.py:310] 2024-07-11 10:15:25,844 >> {'loss': 0.0632, 'learning_rate': 1.7667e-06, 'epoch': 2.73, 'throughput': 1475.70}
|
| 642 |
-
|
| 643 |
-
[INFO|callbacks.py:310] 2024-07-11 10:15:36,953 >> {'loss': 0.0620, 'learning_rate': 1.7750e-06, 'epoch': 2.74, 'throughput': 1475.36}
|
| 644 |
-
|
| 645 |
-
[INFO|callbacks.py:310] 2024-07-11 10:15:48,070 >> {'loss': 0.0816, 'learning_rate': 1.7833e-06, 'epoch': 2.75, 'throughput': 1475.14}
|
| 646 |
-
|
| 647 |
-
[INFO|callbacks.py:310] 2024-07-11 10:15:59,182 >> {'loss': 0.0960, 'learning_rate': 1.7917e-06, 'epoch': 2.77, 'throughput': 1475.26}
|
| 648 |
-
|
| 649 |
-
[INFO|callbacks.py:310] 2024-07-11 10:16:10,296 >> {'loss': 0.0639, 'learning_rate': 1.8000e-06, 'epoch': 2.78, 'throughput': 1475.21}
|
| 650 |
-
|
| 651 |
-
[INFO|callbacks.py:310] 2024-07-11 10:16:21,386 >> {'loss': 0.0915, 'learning_rate': 1.8083e-06, 'epoch': 2.79, 'throughput': 1474.69}
|
| 652 |
-
|
| 653 |
-
[INFO|callbacks.py:310] 2024-07-11 10:16:32,501 >> {'loss': 0.0610, 'learning_rate': 1.8167e-06, 'epoch': 2.80, 'throughput': 1474.53}
|
| 654 |
-
|
| 655 |
-
[INFO|callbacks.py:310] 2024-07-11 10:16:43,658 >> {'loss': 0.0572, 'learning_rate': 1.8250e-06, 'epoch': 2.82, 'throughput': 1474.35}
|
| 656 |
-
|
| 657 |
-
[INFO|callbacks.py:310] 2024-07-11 10:16:54,814 >> {'loss': 0.0497, 'learning_rate': 1.8333e-06, 'epoch': 2.83, 'throughput': 1474.44}
|
| 658 |
-
|
| 659 |
-
[INFO|callbacks.py:310] 2024-07-11 10:17:05,943 >> {'loss': 0.0672, 'learning_rate': 1.8417e-06, 'epoch': 2.84, 'throughput': 1474.31}
|
| 660 |
-
|
| 661 |
-
[INFO|callbacks.py:310] 2024-07-11 10:17:17,069 >> {'loss': 0.0563, 'learning_rate': 1.8500e-06, 'epoch': 2.86, 'throughput': 1474.33}
|
| 662 |
-
|
| 663 |
-
[INFO|callbacks.py:310] 2024-07-11 10:17:28,189 >> {'loss': 0.0690, 'learning_rate': 1.8583e-06, 'epoch': 2.87, 'throughput': 1474.50}
|
| 664 |
-
|
| 665 |
-
[INFO|callbacks.py:310] 2024-07-11 10:17:39,309 >> {'loss': 0.0824, 'learning_rate': 1.8667e-06, 'epoch': 2.88, 'throughput': 1474.59}
|
| 666 |
-
|
| 667 |
-
[INFO|callbacks.py:310] 2024-07-11 10:17:50,430 >> {'loss': 0.0570, 'learning_rate': 1.8750e-06, 'epoch': 2.89, 'throughput': 1474.72}
|
| 668 |
-
|
| 669 |
-
[INFO|callbacks.py:310] 2024-07-11 10:18:01,560 >> {'loss': 0.0549, 'learning_rate': 1.8833e-06, 'epoch': 2.91, 'throughput': 1475.08}
|
| 670 |
-
|
| 671 |
-
[INFO|callbacks.py:310] 2024-07-11 10:18:12,661 >> {'loss': 0.0652, 'learning_rate': 1.8917e-06, 'epoch': 2.92, 'throughput': 1474.98}
|
| 672 |
-
|
| 673 |
-
[INFO|callbacks.py:310] 2024-07-11 10:18:23,802 >> {'loss': 0.0743, 'learning_rate': 1.9000e-06, 'epoch': 2.93, 'throughput': 1475.20}
|
| 674 |
-
|
| 675 |
-
[INFO|callbacks.py:310] 2024-07-11 10:18:34,940 >> {'loss': 0.0416, 'learning_rate': 1.9083e-06, 'epoch': 2.95, 'throughput': 1475.35}
|
| 676 |
-
|
| 677 |
-
[INFO|callbacks.py:310] 2024-07-11 10:18:46,091 >> {'loss': 0.0668, 'learning_rate': 1.9167e-06, 'epoch': 2.96, 'throughput': 1475.75}
|
| 678 |
-
|
| 679 |
-
[INFO|callbacks.py:310] 2024-07-11 10:18:57,199 >> {'loss': 0.0603, 'learning_rate': 1.9250e-06, 'epoch': 2.97, 'throughput': 1475.60}
|
| 680 |
-
|
| 681 |
-
[INFO|callbacks.py:310] 2024-07-11 10:19:08,355 >> {'loss': 0.0660, 'learning_rate': 1.9333e-06, 'epoch': 2.98, 'throughput': 1475.88}
|
| 682 |
-
|
| 683 |
-
[INFO|callbacks.py:310] 2024-07-11 10:19:19,452 >> {'loss': 0.0692, 'learning_rate': 1.9417e-06, 'epoch': 3.00, 'throughput': 1475.87}
|
| 684 |
-
|
| 685 |
-
[INFO|callbacks.py:310] 2024-07-11 10:19:30,549 >> {'loss': 0.0323, 'learning_rate': 1.9500e-06, 'epoch': 3.01, 'throughput': 1475.89}
|
| 686 |
-
|
| 687 |
-
[INFO|callbacks.py:310] 2024-07-11 10:19:41,651 >> {'loss': 0.0403, 'learning_rate': 1.9583e-06, 'epoch': 3.02, 'throughput': 1475.72}
|
| 688 |
-
|
| 689 |
-
[INFO|callbacks.py:310] 2024-07-11 10:19:52,776 >> {'loss': 0.0477, 'learning_rate': 1.9667e-06, 'epoch': 3.04, 'throughput': 1475.66}
|
| 690 |
-
|
| 691 |
-
[INFO|callbacks.py:310] 2024-07-11 10:20:03,890 >> {'loss': 0.0356, 'learning_rate': 1.9750e-06, 'epoch': 3.05, 'throughput': 1475.41}
|
| 692 |
-
|
| 693 |
-
[INFO|callbacks.py:310] 2024-07-11 10:20:14,994 >> {'loss': 0.0324, 'learning_rate': 1.9833e-06, 'epoch': 3.06, 'throughput': 1475.56}
|
| 694 |
-
|
| 695 |
-
[INFO|callbacks.py:310] 2024-07-11 10:20:26,140 >> {'loss': 0.0428, 'learning_rate': 1.9917e-06, 'epoch': 3.07, 'throughput': 1475.76}
|
| 696 |
-
|
| 697 |
-
[INFO|callbacks.py:310] 2024-07-11 10:20:37,270 >> {'loss': 0.0315, 'learning_rate': 2.0000e-06, 'epoch': 3.09, 'throughput': 1475.75}
|
| 698 |
-
|
| 699 |
-
[INFO|callbacks.py:310] 2024-07-11 10:20:48,387 >> {'loss': 0.0366, 'learning_rate': 2.0083e-06, 'epoch': 3.10, 'throughput': 1475.78}
|
| 700 |
-
|
| 701 |
-
[INFO|callbacks.py:310] 2024-07-11 10:20:59,460 >> {'loss': 0.0307, 'learning_rate': 2.0167e-06, 'epoch': 3.11, 'throughput': 1475.47}
|
| 702 |
-
|
| 703 |
-
[INFO|callbacks.py:310] 2024-07-11 10:21:10,586 >> {'loss': 0.0338, 'learning_rate': 2.0250e-06, 'epoch': 3.13, 'throughput': 1475.52}
|
| 704 |
-
|
| 705 |
-
[INFO|callbacks.py:310] 2024-07-11 10:21:21,705 >> {'loss': 0.0348, 'learning_rate': 2.0333e-06, 'epoch': 3.14, 'throughput': 1475.62}
|
| 706 |
-
|
| 707 |
-
[INFO|callbacks.py:310] 2024-07-11 10:21:32,815 >> {'loss': 0.0355, 'learning_rate': 2.0417e-06, 'epoch': 3.15, 'throughput': 1475.75}
|
| 708 |
-
|
| 709 |
-
[INFO|callbacks.py:310] 2024-07-11 10:21:43,960 >> {'loss': 0.0272, 'learning_rate': 2.0500e-06, 'epoch': 3.16, 'throughput': 1475.84}
|
| 710 |
-
|
| 711 |
-
[INFO|callbacks.py:310] 2024-07-11 10:21:55,085 >> {'loss': 0.0464, 'learning_rate': 2.0583e-06, 'epoch': 3.18, 'throughput': 1475.83}
|
| 712 |
-
|
| 713 |
-
[INFO|callbacks.py:310] 2024-07-11 10:22:06,205 >> {'loss': 0.0268, 'learning_rate': 2.0667e-06, 'epoch': 3.19, 'throughput': 1475.60}
|
| 714 |
-
|
| 715 |
-
[INFO|callbacks.py:310] 2024-07-11 10:22:17,319 >> {'loss': 0.0229, 'learning_rate': 2.0750e-06, 'epoch': 3.20, 'throughput': 1475.38}
|
| 716 |
-
|
| 717 |
-
[INFO|callbacks.py:310] 2024-07-11 10:22:28,439 >> {'loss': 0.0373, 'learning_rate': 2.0833e-06, 'epoch': 3.22, 'throughput': 1475.74}
|
| 718 |
-
|
| 719 |
-
[INFO|callbacks.py:310] 2024-07-11 10:22:39,521 >> {'loss': 0.0361, 'learning_rate': 2.0917e-06, 'epoch': 3.23, 'throughput': 1475.59}
|
| 720 |
-
|
| 721 |
-
[INFO|callbacks.py:310] 2024-07-11 10:22:50,624 >> {'loss': 0.0401, 'learning_rate': 2.1000e-06, 'epoch': 3.24, 'throughput': 1475.60}
|
| 722 |
-
|
| 723 |
-
[INFO|callbacks.py:310] 2024-07-11 10:23:01,715 >> {'loss': 0.0262, 'learning_rate': 2.1083e-06, 'epoch': 3.25, 'throughput': 1475.38}
|
| 724 |
-
|
| 725 |
-
[INFO|callbacks.py:310] 2024-07-11 10:23:12,825 >> {'loss': 0.0481, 'learning_rate': 2.1167e-06, 'epoch': 3.27, 'throughput': 1475.34}
|
| 726 |
-
|
| 727 |
-
[INFO|callbacks.py:310] 2024-07-11 10:23:23,969 >> {'loss': 0.0417, 'learning_rate': 2.1250e-06, 'epoch': 3.28, 'throughput': 1475.21}
|
| 728 |
-
|
| 729 |
-
[INFO|callbacks.py:310] 2024-07-11 10:23:35,127 >> {'loss': 0.0457, 'learning_rate': 2.1333e-06, 'epoch': 3.29, 'throughput': 1475.48}
|
| 730 |
-
|
| 731 |
-
[INFO|callbacks.py:310] 2024-07-11 10:23:46,239 >> {'loss': 0.0175, 'learning_rate': 2.1417e-06, 'epoch': 3.31, 'throughput': 1475.19}
|
| 732 |
-
|
| 733 |
-
[INFO|callbacks.py:310] 2024-07-11 10:23:57,391 >> {'loss': 0.0371, 'learning_rate': 2.1500e-06, 'epoch': 3.32, 'throughput': 1475.40}
|
| 734 |
-
|
| 735 |
-
[INFO|callbacks.py:310] 2024-07-11 10:24:08,512 >> {'loss': 0.0268, 'learning_rate': 2.1583e-06, 'epoch': 3.33, 'throughput': 1475.58}
|
| 736 |
-
|
| 737 |
-
[INFO|callbacks.py:310] 2024-07-11 10:24:19,598 >> {'loss': 0.0417, 'learning_rate': 2.1667e-06, 'epoch': 3.34, 'throughput': 1475.58}
|
| 738 |
-
|
| 739 |
-
[INFO|callbacks.py:310] 2024-07-11 10:24:30,714 >> {'loss': 0.0264, 'learning_rate': 2.1750e-06, 'epoch': 3.36, 'throughput': 1475.32}
|
| 740 |
-
|
| 741 |
-
[INFO|callbacks.py:310] 2024-07-11 10:24:41,829 >> {'loss': 0.0336, 'learning_rate': 2.1833e-06, 'epoch': 3.37, 'throughput': 1475.42}
|
| 742 |
-
|
| 743 |
-
[INFO|callbacks.py:310] 2024-07-11 10:24:52,937 >> {'loss': 0.0434, 'learning_rate': 2.1917e-06, 'epoch': 3.38, 'throughput': 1475.28}
|
| 744 |
-
|
| 745 |
-
[INFO|callbacks.py:310] 2024-07-11 10:25:04,052 >> {'loss': 0.0389, 'learning_rate': 2.2000e-06, 'epoch': 3.40, 'throughput': 1475.08}
|
| 746 |
-
|
| 747 |
-
[INFO|callbacks.py:310] 2024-07-11 10:25:15,179 >> {'loss': 0.0450, 'learning_rate': 2.2083e-06, 'epoch': 3.41, 'throughput': 1474.84}
|
| 748 |
-
|
| 749 |
-
[INFO|callbacks.py:310] 2024-07-11 10:25:26,284 >> {'loss': 0.0331, 'learning_rate': 2.2167e-06, 'epoch': 3.42, 'throughput': 1474.66}
|
| 750 |
-
|
| 751 |
-
[INFO|callbacks.py:310] 2024-07-11 10:25:37,399 >> {'loss': 0.0228, 'learning_rate': 2.2250e-06, 'epoch': 3.43, 'throughput': 1474.73}
|
| 752 |
-
|
| 753 |
-
[INFO|callbacks.py:310] 2024-07-11 10:25:48,485 >> {'loss': 0.0307, 'learning_rate': 2.2333e-06, 'epoch': 3.45, 'throughput': 1474.93}
|
| 754 |
-
|
| 755 |
-
[INFO|callbacks.py:310] 2024-07-11 10:25:59,600 >> {'loss': 0.0332, 'learning_rate': 2.2417e-06, 'epoch': 3.46, 'throughput': 1474.79}
|
| 756 |
-
|
| 757 |
-
[INFO|callbacks.py:310] 2024-07-11 10:26:10,724 >> {'loss': 0.0662, 'learning_rate': 2.2500e-06, 'epoch': 3.47, 'throughput': 1474.75}
|
| 758 |
-
|
| 759 |
-
[INFO|callbacks.py:310] 2024-07-11 10:26:21,833 >> {'loss': 0.0431, 'learning_rate': 2.2583e-06, 'epoch': 3.49, 'throughput': 1474.76}
|
| 760 |
-
|
| 761 |
-
[INFO|callbacks.py:310] 2024-07-11 10:26:32,988 >> {'loss': 0.0423, 'learning_rate': 2.2667e-06, 'epoch': 3.50, 'throughput': 1474.84}
|
| 762 |
-
|
| 763 |
-
[INFO|callbacks.py:310] 2024-07-11 10:26:44,135 >> {'loss': 0.0447, 'learning_rate': 2.2750e-06, 'epoch': 3.51, 'throughput': 1474.86}
|
| 764 |
-
|
| 765 |
-
[INFO|callbacks.py:310] 2024-07-11 10:26:55,240 >> {'loss': 0.0337, 'learning_rate': 2.2833e-06, 'epoch': 3.52, 'throughput': 1474.75}
|
| 766 |
-
|
| 767 |
-
[INFO|callbacks.py:310] 2024-07-11 10:27:06,362 >> {'loss': 0.0319, 'learning_rate': 2.2917e-06, 'epoch': 3.54, 'throughput': 1474.61}
|
| 768 |
-
|
| 769 |
-
[INFO|callbacks.py:310] 2024-07-11 10:27:17,507 >> {'loss': 0.0270, 'learning_rate': 2.3000e-06, 'epoch': 3.55, 'throughput': 1474.75}
|
| 770 |
-
|
| 771 |
-
[INFO|callbacks.py:310] 2024-07-11 10:27:28,590 >> {'loss': 0.0244, 'learning_rate': 2.3083e-06, 'epoch': 3.56, 'throughput': 1474.91}
|
| 772 |
-
|
| 773 |
-
[INFO|callbacks.py:310] 2024-07-11 10:27:39,702 >> {'loss': 0.0377, 'learning_rate': 2.3167e-06, 'epoch': 3.58, 'throughput': 1475.12}
|
| 774 |
-
|
| 775 |
-
[INFO|callbacks.py:310] 2024-07-11 10:27:50,833 >> {'loss': 0.0477, 'learning_rate': 2.3250e-06, 'epoch': 3.59, 'throughput': 1475.12}
|
| 776 |
-
|
| 777 |
-
[INFO|callbacks.py:310] 2024-07-11 10:28:01,921 >> {'loss': 0.0332, 'learning_rate': 2.3333e-06, 'epoch': 3.60, 'throughput': 1474.74}
|
| 778 |
-
|
| 779 |
-
[INFO|callbacks.py:310] 2024-07-11 10:28:13,062 >> {'loss': 0.0285, 'learning_rate': 2.3417e-06, 'epoch': 3.61, 'throughput': 1474.97}
|
| 780 |
-
|
| 781 |
-
[INFO|callbacks.py:310] 2024-07-11 10:28:24,197 >> {'loss': 0.0468, 'learning_rate': 2.3500e-06, 'epoch': 3.63, 'throughput': 1475.00}
|
| 782 |
-
|
| 783 |
-
[INFO|callbacks.py:310] 2024-07-11 10:28:35,319 >> {'loss': 0.0370, 'learning_rate': 2.3583e-06, 'epoch': 3.64, 'throughput': 1475.13}
|
| 784 |
-
|
| 785 |
-
[INFO|callbacks.py:310] 2024-07-11 10:28:46,466 >> {'loss': 0.0410, 'learning_rate': 2.3667e-06, 'epoch': 3.65, 'throughput': 1474.98}
|
| 786 |
-
|
| 787 |
-
[INFO|callbacks.py:310] 2024-07-11 10:28:57,575 >> {'loss': 0.0461, 'learning_rate': 2.3750e-06, 'epoch': 3.67, 'throughput': 1475.10}
|
| 788 |
-
|
| 789 |
-
[INFO|callbacks.py:310] 2024-07-11 10:29:08,687 >> {'loss': 0.0594, 'learning_rate': 2.3833e-06, 'epoch': 3.68, 'throughput': 1474.95}
|
| 790 |
-
|
| 791 |
-
[INFO|callbacks.py:310] 2024-07-11 10:29:19,788 >> {'loss': 0.0728, 'learning_rate': 2.3917e-06, 'epoch': 3.69, 'throughput': 1475.07}
|
| 792 |
-
|
| 793 |
-
[INFO|callbacks.py:310] 2024-07-11 10:29:30,916 >> {'loss': 0.0290, 'learning_rate': 2.4000e-06, 'epoch': 3.70, 'throughput': 1475.20}
|
| 794 |
-
|
| 795 |
-
[INFO|callbacks.py:310] 2024-07-11 10:29:42,019 >> {'loss': 0.0412, 'learning_rate': 2.4083e-06, 'epoch': 3.72, 'throughput': 1475.44}
|
| 796 |
-
|
| 797 |
-
[INFO|callbacks.py:310] 2024-07-11 10:29:53,160 >> {'loss': 0.0262, 'learning_rate': 2.4167e-06, 'epoch': 3.73, 'throughput': 1475.13}
|
| 798 |
-
|
| 799 |
-
[INFO|callbacks.py:310] 2024-07-11 10:30:04,273 >> {'loss': 0.0796, 'learning_rate': 2.4250e-06, 'epoch': 3.74, 'throughput': 1474.96}
|
| 800 |
-
|
| 801 |
-
[INFO|callbacks.py:310] 2024-07-11 10:30:15,400 >> {'loss': 0.0447, 'learning_rate': 2.4333e-06, 'epoch': 3.76, 'throughput': 1474.93}
|
| 802 |
-
|
| 803 |
-
[INFO|callbacks.py:310] 2024-07-11 10:30:26,536 >> {'loss': 0.0252, 'learning_rate': 2.4417e-06, 'epoch': 3.77, 'throughput': 1474.95}
|
| 804 |
-
|
| 805 |
-
[INFO|callbacks.py:310] 2024-07-11 10:30:37,624 >> {'loss': 0.0458, 'learning_rate': 2.4500e-06, 'epoch': 3.78, 'throughput': 1474.79}
|
| 806 |
-
|
| 807 |
-
[INFO|callbacks.py:310] 2024-07-11 10:30:48,698 >> {'loss': 0.0431, 'learning_rate': 2.4583e-06, 'epoch': 3.79, 'throughput': 1474.62}
|
| 808 |
-
|
| 809 |
-
[INFO|callbacks.py:310] 2024-07-11 10:30:59,827 >> {'loss': 0.0422, 'learning_rate': 2.4667e-06, 'epoch': 3.81, 'throughput': 1474.72}
|
| 810 |
-
|
| 811 |
-
[INFO|callbacks.py:310] 2024-07-11 10:31:10,927 >> {'loss': 0.0428, 'learning_rate': 2.4750e-06, 'epoch': 3.82, 'throughput': 1474.85}
|
| 812 |
-
|
| 813 |
-
[INFO|callbacks.py:310] 2024-07-11 10:31:22,040 >> {'loss': 0.0473, 'learning_rate': 2.4833e-06, 'epoch': 3.83, 'throughput': 1474.88}
|
| 814 |
-
|
| 815 |
-
[INFO|callbacks.py:310] 2024-07-11 10:31:33,168 >> {'loss': 0.0223, 'learning_rate': 2.4917e-06, 'epoch': 3.85, 'throughput': 1474.81}
|
| 816 |
-
|
| 817 |
-
[INFO|callbacks.py:310] 2024-07-11 10:31:44,304 >> {'loss': 0.0274, 'learning_rate': 2.5000e-06, 'epoch': 3.86, 'throughput': 1474.73}
|
| 818 |
-
|
| 819 |
-
[INFO|callbacks.py:310] 2024-07-11 10:31:55,446 >> {'loss': 0.0454, 'learning_rate': 2.5083e-06, 'epoch': 3.87, 'throughput': 1474.68}
|
| 820 |
-
|
| 821 |
-
[INFO|callbacks.py:310] 2024-07-11 10:32:06,565 >> {'loss': 0.0220, 'learning_rate': 2.5167e-06, 'epoch': 3.88, 'throughput': 1474.90}
|
| 822 |
-
|
| 823 |
-
[INFO|callbacks.py:310] 2024-07-11 10:32:17,678 >> {'loss': 0.0357, 'learning_rate': 2.5250e-06, 'epoch': 3.90, 'throughput': 1474.97}
|
| 824 |
-
|
| 825 |
-
[INFO|callbacks.py:310] 2024-07-11 10:32:28,794 >> {'loss': 0.0458, 'learning_rate': 2.5333e-06, 'epoch': 3.91, 'throughput': 1475.20}
|
| 826 |
-
|
| 827 |
-
[INFO|callbacks.py:310] 2024-07-11 10:32:39,890 >> {'loss': 0.0454, 'learning_rate': 2.5417e-06, 'epoch': 3.92, 'throughput': 1475.13}
|
| 828 |
-
|
| 829 |
-
[INFO|callbacks.py:310] 2024-07-11 10:32:51,000 >> {'loss': 0.0262, 'learning_rate': 2.5500e-06, 'epoch': 3.94, 'throughput': 1475.05}
|
| 830 |
-
|
| 831 |
-
[INFO|callbacks.py:310] 2024-07-11 10:33:02,090 >> {'loss': 0.0234, 'learning_rate': 2.5583e-06, 'epoch': 3.95, 'throughput': 1474.86}
|
| 832 |
-
|
| 833 |
-
[INFO|callbacks.py:310] 2024-07-11 10:33:13,206 >> {'loss': 0.0366, 'learning_rate': 2.5667e-06, 'epoch': 3.96, 'throughput': 1474.97}
|
| 834 |
-
|
| 835 |
-
[INFO|callbacks.py:310] 2024-07-11 10:33:24,327 >> {'loss': 0.0236, 'learning_rate': 2.5750e-06, 'epoch': 3.97, 'throughput': 1474.97}
|
| 836 |
-
|
| 837 |
-
[INFO|callbacks.py:310] 2024-07-11 10:33:35,481 >> {'loss': 0.0403, 'learning_rate': 2.5833e-06, 'epoch': 3.99, 'throughput': 1475.24}
|
| 838 |
-
|
| 839 |
-
[INFO|callbacks.py:310] 2024-07-11 10:33:46,614 >> {'loss': 0.0395, 'learning_rate': 2.5917e-06, 'epoch': 4.00, 'throughput': 1475.24}
|
| 840 |
-
|
| 841 |
-
[INFO|callbacks.py:310] 2024-07-11 10:33:57,694 >> {'loss': 0.0163, 'learning_rate': 2.6000e-06, 'epoch': 4.01, 'throughput': 1475.19}
|
| 842 |
-
|
| 843 |
-
[INFO|callbacks.py:310] 2024-07-11 10:34:08,791 >> {'loss': 0.0181, 'learning_rate': 2.6083e-06, 'epoch': 4.03, 'throughput': 1475.00}
|
| 844 |
-
|
| 845 |
-
[INFO|callbacks.py:310] 2024-07-11 10:34:19,898 >> {'loss': 0.0130, 'learning_rate': 2.6167e-06, 'epoch': 4.04, 'throughput': 1474.96}
|
| 846 |
-
|
| 847 |
-
[INFO|callbacks.py:310] 2024-07-11 10:34:30,966 >> {'loss': 0.0178, 'learning_rate': 2.6250e-06, 'epoch': 4.05, 'throughput': 1474.78}
|
| 848 |
-
|
| 849 |
-
[INFO|callbacks.py:310] 2024-07-11 10:34:42,123 >> {'loss': 0.0153, 'learning_rate': 2.6333e-06, 'epoch': 4.06, 'throughput': 1475.20}
|
| 850 |
-
|
| 851 |
-
[INFO|callbacks.py:310] 2024-07-11 10:34:53,252 >> {'loss': 0.0205, 'learning_rate': 2.6417e-06, 'epoch': 4.08, 'throughput': 1475.09}
|
| 852 |
-
|
| 853 |
-
[INFO|callbacks.py:310] 2024-07-11 10:35:04,398 >> {'loss': 0.0021, 'learning_rate': 2.6500e-06, 'epoch': 4.09, 'throughput': 1475.17}
|
| 854 |
-
|
| 855 |
-
[INFO|callbacks.py:310] 2024-07-11 10:35:15,518 >> {'loss': 0.0220, 'learning_rate': 2.6583e-06, 'epoch': 4.10, 'throughput': 1475.20}
|
| 856 |
-
|
| 857 |
-
[INFO|callbacks.py:310] 2024-07-11 10:35:26,625 >> {'loss': 0.0134, 'learning_rate': 2.6667e-06, 'epoch': 4.12, 'throughput': 1475.14}
|
| 858 |
-
|
| 859 |
-
[INFO|callbacks.py:310] 2024-07-11 10:35:37,710 >> {'loss': 0.0175, 'learning_rate': 2.6750e-06, 'epoch': 4.13, 'throughput': 1474.95}
|
| 860 |
-
|
| 861 |
-
[INFO|callbacks.py:310] 2024-07-11 10:35:48,853 >> {'loss': 0.0230, 'learning_rate': 2.6833e-06, 'epoch': 4.14, 'throughput': 1474.98}
|
| 862 |
-
|
| 863 |
-
[INFO|callbacks.py:310] 2024-07-11 10:35:59,942 >> {'loss': 0.0303, 'learning_rate': 2.6917e-06, 'epoch': 4.15, 'throughput': 1474.77}
|
| 864 |
-
|
| 865 |
-
[INFO|callbacks.py:310] 2024-07-11 10:36:11,072 >> {'loss': 0.0187, 'learning_rate': 2.7000e-06, 'epoch': 4.17, 'throughput': 1474.91}
|
| 866 |
-
|
| 867 |
-
[INFO|callbacks.py:310] 2024-07-11 10:36:22,179 >> {'loss': 0.0126, 'learning_rate': 2.7083e-06, 'epoch': 4.18, 'throughput': 1474.71}
|
| 868 |
-
|
| 869 |
-
[INFO|callbacks.py:310] 2024-07-11 10:36:33,308 >> {'loss': 0.0203, 'learning_rate': 2.7167e-06, 'epoch': 4.19, 'throughput': 1474.67}
|
| 870 |
-
|
| 871 |
-
[INFO|callbacks.py:310] 2024-07-11 10:36:44,410 >> {'loss': 0.0078, 'learning_rate': 2.7250e-06, 'epoch': 4.21, 'throughput': 1474.62}
|
| 872 |
-
|
| 873 |
-
[INFO|callbacks.py:310] 2024-07-11 10:36:55,536 >> {'loss': 0.0165, 'learning_rate': 2.7333e-06, 'epoch': 4.22, 'throughput': 1474.50}
|
| 874 |
-
|
| 875 |
-
[INFO|callbacks.py:310] 2024-07-11 10:37:06,705 >> {'loss': 0.0113, 'learning_rate': 2.7417e-06, 'epoch': 4.23, 'throughput': 1474.78}
|
| 876 |
-
|
| 877 |
-
[INFO|callbacks.py:310] 2024-07-11 10:37:17,796 >> {'loss': 0.0058, 'learning_rate': 2.7500e-06, 'epoch': 4.24, 'throughput': 1474.81}
|
| 878 |
-
|
| 879 |
-
[INFO|callbacks.py:310] 2024-07-11 10:37:28,878 >> {'loss': 0.0070, 'learning_rate': 2.7583e-06, 'epoch': 4.26, 'throughput': 1474.67}
|
| 880 |
-
|
| 881 |
-
[INFO|callbacks.py:310] 2024-07-11 10:37:39,999 >> {'loss': 0.0270, 'learning_rate': 2.7667e-06, 'epoch': 4.27, 'throughput': 1474.84}
|
| 882 |
-
|
| 883 |
-
[INFO|callbacks.py:310] 2024-07-11 10:37:51,079 >> {'loss': 0.0276, 'learning_rate': 2.7750e-06, 'epoch': 4.28, 'throughput': 1474.61}
|
| 884 |
-
|
| 885 |
-
[INFO|callbacks.py:310] 2024-07-11 10:38:02,192 >> {'loss': 0.0367, 'learning_rate': 2.7833e-06, 'epoch': 4.30, 'throughput': 1474.55}
|
| 886 |
-
|
| 887 |
-
[INFO|callbacks.py:310] 2024-07-11 10:38:13,299 >> {'loss': 0.0161, 'learning_rate': 2.7917e-06, 'epoch': 4.31, 'throughput': 1474.44}
|
| 888 |
-
|
| 889 |
-
[INFO|callbacks.py:310] 2024-07-11 10:38:24,431 >> {'loss': 0.0180, 'learning_rate': 2.8000e-06, 'epoch': 4.32, 'throughput': 1474.57}
|
| 890 |
-
|
| 891 |
-
[INFO|callbacks.py:310] 2024-07-11 10:38:35,563 >> {'loss': 0.0044, 'learning_rate': 2.8083e-06, 'epoch': 4.33, 'throughput': 1474.64}
|
| 892 |
-
|
| 893 |
-
[INFO|callbacks.py:310] 2024-07-11 10:38:46,691 >> {'loss': 0.0109, 'learning_rate': 2.8167e-06, 'epoch': 4.35, 'throughput': 1474.75}
|
| 894 |
-
|
| 895 |
-
[INFO|callbacks.py:310] 2024-07-11 10:38:57,770 >> {'loss': 0.0173, 'learning_rate': 2.8250e-06, 'epoch': 4.36, 'throughput': 1474.67}
|
| 896 |
-
|
| 897 |
-
[INFO|callbacks.py:310] 2024-07-11 10:39:08,939 >> {'loss': 0.0107, 'learning_rate': 2.8333e-06, 'epoch': 4.37, 'throughput': 1474.70}
|
| 898 |
-
|
| 899 |
-
[INFO|callbacks.py:310] 2024-07-11 10:39:20,028 >> {'loss': 0.0116, 'learning_rate': 2.8417e-06, 'epoch': 4.39, 'throughput': 1474.55}
|
| 900 |
-
|
| 901 |
-
[INFO|callbacks.py:310] 2024-07-11 10:39:31,145 >> {'loss': 0.0281, 'learning_rate': 2.8500e-06, 'epoch': 4.40, 'throughput': 1474.78}
|
| 902 |
-
|
| 903 |
-
[INFO|callbacks.py:310] 2024-07-11 10:39:42,249 >> {'loss': 0.0246, 'learning_rate': 2.8583e-06, 'epoch': 4.41, 'throughput': 1474.86}
|
| 904 |
-
|
| 905 |
-
[INFO|callbacks.py:310] 2024-07-11 10:39:53,373 >> {'loss': 0.0146, 'learning_rate': 2.8667e-06, 'epoch': 4.42, 'throughput': 1474.84}
|
| 906 |
-
|
| 907 |
-
[INFO|callbacks.py:310] 2024-07-11 10:40:04,489 >> {'loss': 0.0439, 'learning_rate': 2.8750e-06, 'epoch': 4.44, 'throughput': 1474.62}
|
| 908 |
-
|
| 909 |
-
[INFO|callbacks.py:310] 2024-07-11 10:40:15,615 >> {'loss': 0.0279, 'learning_rate': 2.8833e-06, 'epoch': 4.45, 'throughput': 1474.60}
|
| 910 |
-
|
| 911 |
-
[INFO|callbacks.py:310] 2024-07-11 10:40:26,740 >> {'loss': 0.0276, 'learning_rate': 2.8917e-06, 'epoch': 4.46, 'throughput': 1474.70}
|
| 912 |
-
|
| 913 |
-
[INFO|callbacks.py:310] 2024-07-11 10:40:37,836 >> {'loss': 0.0167, 'learning_rate': 2.9000e-06, 'epoch': 4.48, 'throughput': 1474.63}
|
| 914 |
-
|
| 915 |
-
[INFO|callbacks.py:310] 2024-07-11 10:40:48,963 >> {'loss': 0.0258, 'learning_rate': 2.9083e-06, 'epoch': 4.49, 'throughput': 1474.83}
|
| 916 |
-
|
| 917 |
-
[INFO|callbacks.py:310] 2024-07-11 10:41:00,055 >> {'loss': 0.0306, 'learning_rate': 2.9167e-06, 'epoch': 4.50, 'throughput': 1474.91}
|
| 918 |
-
|
| 919 |
-
[INFO|callbacks.py:310] 2024-07-11 10:41:11,182 >> {'loss': 0.0395, 'learning_rate': 2.9250e-06, 'epoch': 4.51, 'throughput': 1475.01}
|
| 920 |
-
|
| 921 |
-
[INFO|callbacks.py:310] 2024-07-11 10:41:22,328 >> {'loss': 0.0203, 'learning_rate': 2.9333e-06, 'epoch': 4.53, 'throughput': 1475.06}
|
| 922 |
-
|
| 923 |
-
[INFO|callbacks.py:310] 2024-07-11 10:41:33,436 >> {'loss': 0.0241, 'learning_rate': 2.9417e-06, 'epoch': 4.54, 'throughput': 1475.01}
|
| 924 |
-
|
| 925 |
-
[INFO|callbacks.py:310] 2024-07-11 10:41:44,523 >> {'loss': 0.0151, 'learning_rate': 2.9500e-06, 'epoch': 4.55, 'throughput': 1474.68}
|
| 926 |
-
|
| 927 |
-
[INFO|callbacks.py:310] 2024-07-11 10:41:55,641 >> {'loss': 0.0355, 'learning_rate': 2.9583e-06, 'epoch': 4.57, 'throughput': 1474.59}
|
| 928 |
-
|
| 929 |
-
[INFO|callbacks.py:310] 2024-07-11 10:42:06,750 >> {'loss': 0.0093, 'learning_rate': 2.9667e-06, 'epoch': 4.58, 'throughput': 1474.72}
|
| 930 |
-
|
| 931 |
-
[INFO|callbacks.py:310] 2024-07-11 10:42:17,848 >> {'loss': 0.0314, 'learning_rate': 2.9750e-06, 'epoch': 4.59, 'throughput': 1474.75}
|
| 932 |
-
|
| 933 |
-
[INFO|callbacks.py:310] 2024-07-11 10:42:28,952 >> {'loss': 0.0155, 'learning_rate': 2.9833e-06, 'epoch': 4.60, 'throughput': 1474.77}
|
| 934 |
-
|
| 935 |
-
[INFO|callbacks.py:310] 2024-07-11 10:42:40,070 >> {'loss': 0.0138, 'learning_rate': 2.9917e-06, 'epoch': 4.62, 'throughput': 1474.94}
|
| 936 |
-
|
| 937 |
-
[INFO|callbacks.py:310] 2024-07-11 10:42:51,212 >> {'loss': 0.0212, 'learning_rate': 3.0000e-06, 'epoch': 4.63, 'throughput': 1475.10}
|
| 938 |
-
|
| 939 |
-
[INFO|callbacks.py:310] 2024-07-11 10:43:02,328 >> {'loss': 0.0255, 'learning_rate': 3.0083e-06, 'epoch': 4.64, 'throughput': 1475.11}
|
| 940 |
-
|
| 941 |
-
[INFO|callbacks.py:310] 2024-07-11 10:43:13,439 >> {'loss': 0.0231, 'learning_rate': 3.0167e-06, 'epoch': 4.66, 'throughput': 1474.99}
|
| 942 |
-
|
| 943 |
-
[INFO|callbacks.py:310] 2024-07-11 10:43:24,561 >> {'loss': 0.0083, 'learning_rate': 3.0250e-06, 'epoch': 4.67, 'throughput': 1474.99}
|
| 944 |
-
|
| 945 |
-
[INFO|callbacks.py:310] 2024-07-11 10:43:35,710 >> {'loss': 0.0122, 'learning_rate': 3.0333e-06, 'epoch': 4.68, 'throughput': 1475.18}
|
| 946 |
-
|
| 947 |
-
[INFO|callbacks.py:310] 2024-07-11 10:43:46,811 >> {'loss': 0.0142, 'learning_rate': 3.0417e-06, 'epoch': 4.69, 'throughput': 1475.37}
|
| 948 |
-
|
| 949 |
-
[INFO|callbacks.py:310] 2024-07-11 10:43:57,895 >> {'loss': 0.0293, 'learning_rate': 3.0500e-06, 'epoch': 4.71, 'throughput': 1475.24}
|
| 950 |
-
|
| 951 |
-
[INFO|callbacks.py:310] 2024-07-11 10:44:09,006 >> {'loss': 0.0292, 'learning_rate': 3.0583e-06, 'epoch': 4.72, 'throughput': 1475.50}
|
| 952 |
-
|
| 953 |
-
[INFO|callbacks.py:310] 2024-07-11 10:44:20,120 >> {'loss': 0.0320, 'learning_rate': 3.0667e-06, 'epoch': 4.73, 'throughput': 1475.46}
|
| 954 |
-
|
| 955 |
-
[INFO|callbacks.py:310] 2024-07-11 10:44:31,238 >> {'loss': 0.0189, 'learning_rate': 3.0750e-06, 'epoch': 4.75, 'throughput': 1475.50}
|
| 956 |
-
|
| 957 |
-
[INFO|callbacks.py:310] 2024-07-11 10:44:42,405 >> {'loss': 0.0220, 'learning_rate': 3.0833e-06, 'epoch': 4.76, 'throughput': 1475.57}
|
| 958 |
-
|
| 959 |
-
[INFO|callbacks.py:310] 2024-07-11 10:44:53,524 >> {'loss': 0.0242, 'learning_rate': 3.0917e-06, 'epoch': 4.77, 'throughput': 1475.68}
|
| 960 |
-
|
| 961 |
-
[INFO|callbacks.py:310] 2024-07-11 10:45:04,670 >> {'loss': 0.0150, 'learning_rate': 3.1000e-06, 'epoch': 4.78, 'throughput': 1475.82}
|
| 962 |
-
|
| 963 |
-
[INFO|callbacks.py:310] 2024-07-11 10:45:15,790 >> {'loss': 0.0154, 'learning_rate': 3.1083e-06, 'epoch': 4.80, 'throughput': 1475.81}
|
| 964 |
-
|
| 965 |
-
[INFO|callbacks.py:310] 2024-07-11 10:45:26,907 >> {'loss': 0.0195, 'learning_rate': 3.1167e-06, 'epoch': 4.81, 'throughput': 1475.92}
|
| 966 |
-
|
| 967 |
-
[INFO|callbacks.py:310] 2024-07-11 10:45:38,027 >> {'loss': 0.0310, 'learning_rate': 3.1250e-06, 'epoch': 4.82, 'throughput': 1476.19}
|
| 968 |
-
|
| 969 |
-
[INFO|callbacks.py:310] 2024-07-11 10:45:49,107 >> {'loss': 0.0376, 'learning_rate': 3.1333e-06, 'epoch': 4.84, 'throughput': 1476.09}
|
| 970 |
|
| 971 |
-
[INFO|
|
| 972 |
|
| 973 |
-
[INFO|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 974 |
|
| 975 |
-
[INFO|callbacks.py:310] 2024-07-11 10:46:22,487 >> {'loss': 0.0191, 'learning_rate': 3.1583e-06, 'epoch': 4.87, 'throughput': 1476.16}
|
| 976 |
|
| 977 |
-
|
| 978 |
|
| 979 |
-
[INFO|
|
| 980 |
|
| 981 |
-
|
| 982 |
|
| 983 |
-
|
| 984 |
|
| 985 |
-
[INFO|
|
| 986 |
|
| 987 |
-
|
| 988 |
|
| 989 |
-
|
| 990 |
|
| 991 |
-
|
| 992 |
|
| 993 |
-
|
| 994 |
|
| 995 |
-
|
| 996 |
|
| 997 |
-
|
| 998 |
|
| 999 |
-
|
| 1000 |
|
| 1001 |
-
|
| 1002 |
|
| 1003 |
-
|
|
|
|
| 1004 |
|
|
|
|
| 1005 |
|
|
|
|
| 1006 |
|
| 1007 |
-
|
| 1008 |
|
| 1009 |
-
|
| 1010 |
|
| 1011 |
-
[
|
| 1012 |
|
| 1013 |
-
|
| 1014 |
|
| 1015 |
-
|
| 1016 |
|
| 1017 |
-
|
| 1018 |
|
| 1019 |
-
|
| 1020 |
|
| 1021 |
-
|
| 1022 |
|
| 1023 |
-
[INFO|
|
| 1024 |
-
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
|
| 1025 |
|
|
|
|
| 1 |
+
[INFO|parser.py:325] 2024-07-11 11:00:10,231 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: None
|
| 2 |
|
| 3 |
+
[INFO|tokenization_utils_base.py:2159] 2024-07-11 11:00:10,234 >> loading file tokenizer.model
|
| 4 |
|
| 5 |
+
07/11/2024 11:00:10 - INFO - llamafactory.hparams.parser - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: None
|
| 6 |
|
| 7 |
+
07/11/2024 11:00:10 - INFO - llamafactory.hparams.parser - Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: None
|
| 8 |
|
| 9 |
+
[INFO|tokenization_utils_base.py:2159] 2024-07-11 11:00:10,234 >> loading file tokenizer.json
|
| 10 |
|
| 11 |
+
[INFO|tokenization_utils_base.py:2159] 2024-07-11 11:00:10,234 >> loading file added_tokens.json
|
| 12 |
|
| 13 |
+
[INFO|tokenization_utils_base.py:2159] 2024-07-11 11:00:10,234 >> loading file special_tokens_map.json
|
| 14 |
|
| 15 |
+
[INFO|tokenization_utils_base.py:2159] 2024-07-11 11:00:10,235 >> loading file tokenizer_config.json
|
| 16 |
|
| 17 |
+
[INFO|loader.py:50] 2024-07-11 11:00:10,286 >> Loading dataset dev_output.json...
|
| 18 |
|
| 19 |
+
07/11/2024 11:00:10 - INFO - llamafactory.hparams.parser - Process rank: 7, device: cuda:7, n_gpu: 1, distributed training: True, compute dtype: None
|
| 20 |
|
| 21 |
+
07/11/2024 11:00:10 - INFO - llamafactory.hparams.parser - Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: None
|
| 22 |
|
| 23 |
+
07/11/2024 11:00:10 - INFO - llamafactory.hparams.parser - Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: None
|
| 24 |
|
| 25 |
+
07/11/2024 11:00:11 - INFO - llamafactory.data.loader - Loading dataset dev_output.json...
|
| 26 |
|
| 27 |
+
07/11/2024 11:00:11 - INFO - llamafactory.data.loader - Loading dataset dev_output.json...
|
| 28 |
|
| 29 |
+
07/11/2024 11:00:11 - INFO - llamafactory.data.loader - Loading dataset dev_output.json...
|
| 30 |
|
| 31 |
+
07/11/2024 11:00:11 - INFO - llamafactory.data.loader - Loading dataset dev_output.json...
|
| 32 |
|
| 33 |
+
07/11/2024 11:00:11 - INFO - llamafactory.data.loader - Loading dataset dev_output.json...
|
| 34 |
|
| 35 |
+
07/11/2024 11:00:11 - INFO - llamafactory.data.loader - Loading dataset dev_output.json...
|
| 36 |
|
| 37 |
+
07/11/2024 11:00:11 - INFO - llamafactory.data.loader - Loading dataset dev_output.json...
|
| 38 |
|
| 39 |
+
[INFO|configuration_utils.py:731] 2024-07-11 11:00:12,504 >> loading configuration file saves/LLaMA2-7B-Chat/full/train_2024-07-11-09-30-54_llama2_inst_truth/config.json
|
| 40 |
|
| 41 |
+
[INFO|configuration_utils.py:800] 2024-07-11 11:00:12,505 >> Model config LlamaConfig {
|
| 42 |
+
"_name_or_path": "saves/LLaMA2-7B-Chat/full/train_2024-07-11-09-30-54_llama2_inst_truth",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
"architectures": [
|
| 44 |
"LlamaForCausalLM"
|
| 45 |
],
|
|
|
|
| 62 |
"rope_scaling": null,
|
| 63 |
"rope_theta": 10000.0,
|
| 64 |
"tie_word_embeddings": false,
|
| 65 |
+
"torch_dtype": "bfloat16",
|
| 66 |
"transformers_version": "4.42.3",
|
| 67 |
+
"use_cache": false,
|
| 68 |
"vocab_size": 32000
|
| 69 |
}
|
| 70 |
|
| 71 |
|
| 72 |
+
[INFO|patcher.py:81] 2024-07-11 11:00:12,505 >> Using KV cache for faster generation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
+
[INFO|modeling_utils.py:3553] 2024-07-11 11:00:12,529 >> loading weights file saves/LLaMA2-7B-Chat/full/train_2024-07-11-09-30-54_llama2_inst_truth/model.safetensors.index.json
|
| 75 |
|
| 76 |
+
[INFO|modeling_utils.py:1531] 2024-07-11 11:00:12,529 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
|
|
|
|
| 77 |
|
| 78 |
+
[INFO|configuration_utils.py:1000] 2024-07-11 11:00:12,531 >> Generate config GenerationConfig {
|
|
|
|
|
|
|
| 79 |
"bos_token_id": 1,
|
| 80 |
+
"eos_token_id": 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
}
|
| 82 |
|
| 83 |
|
| 84 |
+
07/11/2024 11:00:12 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
+
07/11/2024 11:00:12 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 87 |
|
| 88 |
+
07/11/2024 11:00:12 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 89 |
|
| 90 |
+
07/11/2024 11:00:12 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 91 |
|
| 92 |
+
07/11/2024 11:00:12 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 93 |
|
| 94 |
+
07/11/2024 11:00:12 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 95 |
|
| 96 |
+
07/11/2024 11:00:12 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.
|
| 97 |
|
| 98 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 99 |
|
| 100 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.loader - all params: 6,738,415,616
|
| 101 |
|
| 102 |
+
[INFO|modeling_utils.py:4364] 2024-07-11 11:00:16,788 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
|
| 103 |
|
|
|
|
| 104 |
|
| 105 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 106 |
|
| 107 |
+
[INFO|modeling_utils.py:4372] 2024-07-11 11:00:16,788 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at saves/LLaMA2-7B-Chat/full/train_2024-07-11-09-30-54_llama2_inst_truth.
|
| 108 |
+
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.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
|
| 110 |
+
[INFO|configuration_utils.py:953] 2024-07-11 11:00:16,792 >> loading configuration file saves/LLaMA2-7B-Chat/full/train_2024-07-11-09-30-54_llama2_inst_truth/generation_config.json
|
| 111 |
|
| 112 |
+
[INFO|configuration_utils.py:1000] 2024-07-11 11:00:16,792 >> Generate config GenerationConfig {
|
| 113 |
+
"bos_token_id": 1,
|
| 114 |
+
"do_sample": true,
|
| 115 |
+
"eos_token_id": 2,
|
| 116 |
+
"max_length": 4096,
|
| 117 |
+
"pad_token_id": 0,
|
| 118 |
+
"temperature": 0.6,
|
| 119 |
+
"top_p": 0.9
|
| 120 |
+
}
|
| 121 |
|
|
|
|
| 122 |
|
| 123 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.loader - all params: 6,738,415,616
|
| 124 |
|
| 125 |
+
[INFO|attention.py:80] 2024-07-11 11:00:16,798 >> Using torch SDPA for faster training and inference.
|
| 126 |
|
| 127 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 128 |
|
| 129 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 130 |
|
| 131 |
+
[INFO|loader.py:196] 2024-07-11 11:00:16,802 >> all params: 6,738,415,616
|
| 132 |
|
| 133 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.loader - all params: 6,738,415,616
|
| 134 |
|
| 135 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.loader - all params: 6,738,415,616
|
| 136 |
|
| 137 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 138 |
|
| 139 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.loader - all params: 6,738,415,616
|
| 140 |
|
| 141 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 142 |
|
| 143 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 144 |
|
| 145 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.loader - all params: 6,738,415,616
|
| 146 |
|
| 147 |
+
07/11/2024 11:00:16 - INFO - llamafactory.model.loader - all params: 6,738,415,616
|
| 148 |
|
| 149 |
+
[INFO|trainer.py:3788] 2024-07-11 11:00:16,914 >>
|
| 150 |
+
***** Running Prediction *****
|
| 151 |
|
| 152 |
+
[INFO|trainer.py:3790] 2024-07-11 11:00:16,914 >> Num examples = 2554
|
| 153 |
|
| 154 |
+
[INFO|trainer.py:3793] 2024-07-11 11:00:16,914 >> Batch size = 2
|
| 155 |
|
| 156 |
+
07/11/2024 11:00:17 - 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)
|
| 157 |
|
| 158 |
+
07/11/2024 11:00:17 - 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)
|
| 159 |
|
| 160 |
+
[WARNING|logging.py:328] 2024-07-11 11:00:17,582 >> 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)
|
| 161 |
|
| 162 |
+
07/11/2024 11:00:17 - 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)
|
| 163 |
|
| 164 |
+
07/11/2024 11:00:17 - 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)
|
| 165 |
|
| 166 |
+
07/11/2024 11:00:17 - 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)
|
| 167 |
|
| 168 |
+
07/11/2024 11:00:17 - 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)
|
| 169 |
|
| 170 |
+
07/11/2024 11:00:17 - 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)
|
| 171 |
|
| 172 |
+
[INFO|trainer.py:127] 2024-07-11 11:00:34,679 >> Saving prediction results to saves/LLaMA2-7B-Chat/full/eval_2024-07-11-10-49-45/generated_predictions.jsonl
|
|
|
|
| 173 |
|
trainer_log.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.yaml
CHANGED
|
@@ -1,30 +1,18 @@
|
|
| 1 |
-
bf16: true
|
| 2 |
cutoff_len: 1024
|
| 3 |
-
dataset:
|
| 4 |
dataset_dir: data
|
| 5 |
-
|
| 6 |
-
deepspeed: cache/ds_z2_config.json
|
| 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: 4
|
| 23 |
-
plot_loss: true
|
| 24 |
preprocessing_num_workers: 16
|
| 25 |
quantization_method: bitsandbytes
|
| 26 |
-
report_to: none
|
| 27 |
-
save_steps: 980
|
| 28 |
stage: sft
|
|
|
|
| 29 |
template: llama2
|
| 30 |
-
|
|
|
|
|
|
|
| 1 |
cutoff_len: 1024
|
| 2 |
+
dataset: truth_dev
|
| 3 |
dataset_dir: data
|
| 4 |
+
do_predict: true
|
|
|
|
|
|
|
| 5 |
finetuning_type: full
|
| 6 |
flash_attn: auto
|
| 7 |
+
max_new_tokens: 512
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
max_samples: 100000
|
| 9 |
+
model_name_or_path: saves/LLaMA2-7B-Chat/full/train_2024-07-11-09-30-54_llama2_inst_truth
|
| 10 |
+
output_dir: saves/LLaMA2-7B-Chat/full/eval_2024-07-11-10-49-45
|
| 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: llama2
|
| 18 |
+
top_p: 0.7
|