Upload
Browse files- Predict_20/all_results.json +9 -0
- Predict_20/generated_predictions.jsonl +20 -0
- Predict_20/predict_log.txt +290 -0
- Predict_20/predict_results.json +9 -0
- README.md +65 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- all_results.json +11 -0
- eval_results.json +7 -0
- scripts/local_sft_fn_lmcocktail.sh +111 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
- train_eval_log.txt +0 -0
- train_results.json +7 -0
- trainer_log.jsonl +77 -0
- trainer_state.json +482 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
Predict_20/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu-4": 84.02507,
|
| 3 |
+
"predict_rouge-1": 88.655265,
|
| 4 |
+
"predict_rouge-2": 80.23742000000001,
|
| 5 |
+
"predict_rouge-l": 86.469845,
|
| 6 |
+
"predict_runtime": 37.4743,
|
| 7 |
+
"predict_samples_per_second": 0.534,
|
| 8 |
+
"predict_steps_per_second": 0.534
|
| 9 |
+
}
|
Predict_20/generated_predictions.jsonl
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"label": "I'm sorry, but I don't have the capability to book flights. My current function allows me to get the exchange rate between two currencies. If you need help with that, feel free to ask!", "predict": "I'm sorry, but I'm unable to assist with booking flights. My current capabilities are limited to providing exchange rates between two currencies."}
|
| 2 |
+
{"label": "<functioncall> {\"name\": \"get_news_headlines\", \"arguments\": '{\"country\": \"United States\"}'} </functioncall>", "predict": "<functioncall> {\"name\": \"get_news_headlines\", \"arguments\": '{\"country\": \"United States\"}'} </functioncall>"}
|
| 3 |
+
{"label": "Here are the latest news headlines for the United States:\n1. Biden announces new vaccine mandates\n2. Hurricane Ida devastates Louisiana\n3. Apple unveils new iPhone\n4. NASA's Perseverance rover collects first Mars rock sample", "predict": "Here are the latest news headlines for the United States:\n1. Biden announces new vaccine mandates\n2. Hurricane Ida devastates Louisiana\n3. Apple unveils new iPhone\n4. NASA's Perseverance rover collects first Mars rock sample"}
|
| 4 |
+
{"label": "<functioncall> {\"name\": \"get_news_headlines\", \"arguments\": '{\"country\": \"France\"}'} </functioncall>", "predict": "<functioncall> {\"name\": \"get_news_headlines\", \"arguments\": '{\"country\": \"France\"}'} </functioncall>"}
|
| 5 |
+
{"label": "Here are the latest news headlines for France:\n1. France recalls ambassadors to US and Australia\n2. French election: Macron's party braces for tough fight\n3. Louvre Museum to undergo major overhaul\n4. France to offer free birth control to all women under 25", "predict": "Here are the latest news headlines for France:\n1. France recalls ambassadors to US and Australia\n2. French election: Macron's party braces for tough fight\n3. Louvre Museum to undergo major overhaul\n4. France to offer free birth control to all women under 25"}
|
| 6 |
+
{"label": "Of course. How long would you like your password to be? And would you like it to include symbols?", "predict": "Of course! How long would you like your password to be? And do you want it to include symbols?"}
|
| 7 |
+
{"label": "<functioncall> {\"name\": \"generate_password\", \"arguments\": '{\"length\": 12, \"include_symbols\": true}'} </functioncall>", "predict": "<functioncall> {\"name\": \"generate_password\", \"arguments\": '{\"length\": 12, \"include_symbols\": true}'} </functioncall>"}
|
| 8 |
+
{"label": "Here is your new password: 4&7j#9@1Q6*. Please make sure to save it in a secure location.", "predict": "Here is your new password: 4&7j#9@1Q6*. Please make sure to save it in a secure place."}
|
| 9 |
+
{"label": "Of course! How long would you like your password to be? And do you want it to include numbers and special characters?", "predict": "Of course! How long would you like your password to be? And would you like it to include numbers and special characters?"}
|
| 10 |
+
{"label": "<functioncall> {\"name\": \"generate_password\", \"arguments\": '{\"length\": 12, \"include_numbers\": true, \"include_special_characters\": true}'} </functioncall>", "predict": "<functioncall> {\"name\": \"generate_password\", \"arguments\": '{\"length\": 12, \"include_numbers\": true, \"include_special_characters\": true}'} </functioncall>"}
|
| 11 |
+
{"label": "Here is your new password: 4#7gB6&9L1!0. Please make sure to save it in a secure place.", "predict": "Here is your new password: 4#7gB6&9L1!0. Please make sure to store it in a safe place."}
|
| 12 |
+
{"label": "Of course, I can help you with that. Please provide me with the list of numbers.", "predict": "Of course, I can help you with that. Please provide me with the list of numbers."}
|
| 13 |
+
{"label": "<functioncall> {\"name\": \"calculate_median\", \"arguments\": '{\"numbers\": [5, 2, 9, 1, 7, 4, 6, 3, 8]}'} </functioncall>", "predict": "<functioncall> {\"name\": \"calculate_median\", \"arguments\": '{\"numbers\": [5, 2, 9, 1, 7, 4, 6, 3, 8]}'} </functioncall>"}
|
| 14 |
+
{"label": "The median of the provided list of numbers is 5.", "predict": "The median of the given list of numbers is 5."}
|
| 15 |
+
{"label": "Of course, I can help you with that. Let me calculate it for you.\n<functioncall> {\"name\": \"calculate_loan_payment\", \"arguments\": '{\"principal\": 50000, \"interest_rate\": 5, \"loan_term\": 10}'} </functioncall>", "predict": "Of course, I can help you with that. Let me calculate the monthly payment for you.\n<functioncall> {\"name\": \"calculate_loan_payment\", \"arguments\": '{\"principal\": 50000, \"interest_rate\": 5, \"loan_term\": 10}'} </functioncall>"}
|
| 16 |
+
{"label": "Based on the information provided, your monthly loan payment would be $530.33.", "predict": "The monthly payment for your loan would be $530.33."}
|
| 17 |
+
{"label": "I'm sorry, but as an AI, I don't have the capability to book flights or perform external tasks. My current function is to calculate loan payments. I recommend using a travel booking website or app for your flight booking needs.", "predict": "I'm sorry, but as an AI, I don't have the capability to book flights or perform external tasks. My current functions are limited to the ones provided to me."}
|
| 18 |
+
{"label": "<functioncall> {\"name\": \"convert_temperature\", \"arguments\": '{\"temperature\": 30, \"from_unit\": \"Celsius\", \"to_unit\": \"Fahrenheit\"}'} </functioncall>", "predict": "<functioncall> {\"name\": \"convert_temperature\", \"arguments\": '{\"temperature\": 30, \"from_unit\": \"Celsius\", \"to_unit\": \"Fahrenheit\"}'} </functioncall>"}
|
| 19 |
+
{"label": "The converted temperature from 30 degrees Celsius to Fahrenheit is 86 degrees Fahrenheit.", "predict": "The temperature in Fahrenheit is 86 degrees."}
|
| 20 |
+
{"label": "I'm sorry, but I can't assist with that. My current capabilities allow me to provide information about movies based on their titles. I don't have the ability to place orders or perform external tasks.", "predict": "I'm sorry, but I'm unable to perform external tasks such as ordering a pizza. My current capabilities are limited to the functions provided to me, and I can only assist with getting movie details."}
|
Predict_20/predict_log.txt
ADDED
|
@@ -0,0 +1,290 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
01/18/2024 19:24:50 - WARNING - llmtuner.model.parser - `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.
|
| 2 |
+
[INFO|training_args.py:1838] 2024-01-18 19:24:50,331 >> PyTorch: setting up devices
|
| 3 |
+
/home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/transformers/training_args.py:1751: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead.
|
| 4 |
+
warnings.warn(
|
| 5 |
+
01/18/2024 19:24:50 - INFO - llmtuner.model.parser - Process rank: 0, device: cuda:0, n_gpu: 1
|
| 6 |
+
distributed training: True, compute dtype: None
|
| 7 |
+
01/18/2024 19:24:50 - INFO - llmtuner.model.parser - Training/evaluation parameters Seq2SeqTrainingArguments(
|
| 8 |
+
_n_gpu=1,
|
| 9 |
+
adafactor=False,
|
| 10 |
+
adam_beta1=0.9,
|
| 11 |
+
adam_beta2=0.999,
|
| 12 |
+
adam_epsilon=1e-08,
|
| 13 |
+
auto_find_batch_size=False,
|
| 14 |
+
bf16=False,
|
| 15 |
+
bf16_full_eval=False,
|
| 16 |
+
data_seed=None,
|
| 17 |
+
dataloader_drop_last=False,
|
| 18 |
+
dataloader_num_workers=0,
|
| 19 |
+
dataloader_persistent_workers=False,
|
| 20 |
+
dataloader_pin_memory=True,
|
| 21 |
+
ddp_backend=None,
|
| 22 |
+
ddp_broadcast_buffers=None,
|
| 23 |
+
ddp_bucket_cap_mb=None,
|
| 24 |
+
ddp_find_unused_parameters=False,
|
| 25 |
+
ddp_timeout=1800,
|
| 26 |
+
debug=[],
|
| 27 |
+
deepspeed=None,
|
| 28 |
+
disable_tqdm=False,
|
| 29 |
+
dispatch_batches=None,
|
| 30 |
+
do_eval=False,
|
| 31 |
+
do_predict=True,
|
| 32 |
+
do_train=False,
|
| 33 |
+
eval_accumulation_steps=None,
|
| 34 |
+
eval_delay=0,
|
| 35 |
+
eval_steps=None,
|
| 36 |
+
evaluation_strategy=IntervalStrategy.NO,
|
| 37 |
+
fp16=False,
|
| 38 |
+
fp16_backend=auto,
|
| 39 |
+
fp16_full_eval=False,
|
| 40 |
+
fp16_opt_level=O1,
|
| 41 |
+
fsdp=[],
|
| 42 |
+
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
|
| 43 |
+
fsdp_min_num_params=0,
|
| 44 |
+
fsdp_transformer_layer_cls_to_wrap=None,
|
| 45 |
+
full_determinism=False,
|
| 46 |
+
generation_config=None,
|
| 47 |
+
generation_max_length=None,
|
| 48 |
+
generation_num_beams=None,
|
| 49 |
+
gradient_accumulation_steps=1,
|
| 50 |
+
gradient_checkpointing=False,
|
| 51 |
+
gradient_checkpointing_kwargs=None,
|
| 52 |
+
greater_is_better=None,
|
| 53 |
+
group_by_length=False,
|
| 54 |
+
half_precision_backend=auto,
|
| 55 |
+
hub_always_push=False,
|
| 56 |
+
hub_model_id=None,
|
| 57 |
+
hub_private_repo=False,
|
| 58 |
+
hub_strategy=HubStrategy.EVERY_SAVE,
|
| 59 |
+
hub_token=<HUB_TOKEN>,
|
| 60 |
+
ignore_data_skip=False,
|
| 61 |
+
include_inputs_for_metrics=False,
|
| 62 |
+
include_num_input_tokens_seen=False,
|
| 63 |
+
include_tokens_per_second=False,
|
| 64 |
+
jit_mode_eval=False,
|
| 65 |
+
label_names=None,
|
| 66 |
+
label_smoothing_factor=0.0,
|
| 67 |
+
learning_rate=5e-05,
|
| 68 |
+
length_column_name=length,
|
| 69 |
+
load_best_model_at_end=False,
|
| 70 |
+
local_rank=0,
|
| 71 |
+
log_level=passive,
|
| 72 |
+
log_level_replica=warning,
|
| 73 |
+
log_on_each_node=True,
|
| 74 |
+
logging_dir=./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/Predict_20/runs/Jan18_19-24-50_yhyu13fuwuqi,
|
| 75 |
+
logging_first_step=False,
|
| 76 |
+
logging_nan_inf_filter=True,
|
| 77 |
+
logging_steps=500,
|
| 78 |
+
logging_strategy=IntervalStrategy.STEPS,
|
| 79 |
+
lr_scheduler_kwargs={},
|
| 80 |
+
lr_scheduler_type=SchedulerType.LINEAR,
|
| 81 |
+
max_grad_norm=1.0,
|
| 82 |
+
max_steps=-1,
|
| 83 |
+
metric_for_best_model=None,
|
| 84 |
+
mp_parameters=,
|
| 85 |
+
neftune_noise_alpha=None,
|
| 86 |
+
no_cuda=False,
|
| 87 |
+
num_train_epochs=3.0,
|
| 88 |
+
optim=OptimizerNames.ADAMW_TORCH,
|
| 89 |
+
optim_args=None,
|
| 90 |
+
output_dir=./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/Predict_20,
|
| 91 |
+
overwrite_output_dir=False,
|
| 92 |
+
past_index=-1,
|
| 93 |
+
per_device_eval_batch_size=1,
|
| 94 |
+
per_device_train_batch_size=8,
|
| 95 |
+
predict_with_generate=True,
|
| 96 |
+
prediction_loss_only=False,
|
| 97 |
+
push_to_hub=False,
|
| 98 |
+
push_to_hub_model_id=None,
|
| 99 |
+
push_to_hub_organization=None,
|
| 100 |
+
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
|
| 101 |
+
ray_scope=last,
|
| 102 |
+
remove_unused_columns=True,
|
| 103 |
+
report_to=['tensorboard'],
|
| 104 |
+
resume_from_checkpoint=None,
|
| 105 |
+
run_name=./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/Predict_20,
|
| 106 |
+
save_on_each_node=False,
|
| 107 |
+
save_only_model=False,
|
| 108 |
+
save_safetensors=True,
|
| 109 |
+
save_steps=500,
|
| 110 |
+
save_strategy=IntervalStrategy.STEPS,
|
| 111 |
+
save_total_limit=None,
|
| 112 |
+
seed=42,
|
| 113 |
+
skip_memory_metrics=True,
|
| 114 |
+
sortish_sampler=False,
|
| 115 |
+
split_batches=False,
|
| 116 |
+
tf32=None,
|
| 117 |
+
torch_compile=False,
|
| 118 |
+
torch_compile_backend=None,
|
| 119 |
+
torch_compile_mode=None,
|
| 120 |
+
torchdynamo=None,
|
| 121 |
+
tpu_metrics_debug=False,
|
| 122 |
+
tpu_num_cores=None,
|
| 123 |
+
use_cpu=False,
|
| 124 |
+
use_ipex=False,
|
| 125 |
+
use_legacy_prediction_loop=False,
|
| 126 |
+
use_mps_device=False,
|
| 127 |
+
warmup_ratio=0.0,
|
| 128 |
+
warmup_steps=0,
|
| 129 |
+
weight_decay=0.0,
|
| 130 |
+
)
|
| 131 |
+
01/18/2024 19:24:50 - INFO - llmtuner.data.loader - Loading dataset ./glaive-function-calling-v2-llama-factory-convert/simple-function-calling-v2_converted_2000.json...
|
| 132 |
+
01/18/2024 19:24:50 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
|
| 133 |
+
Using custom data configuration default-cb85ddec01d455d4
|
| 134 |
+
Loading Dataset Infos from /home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/datasets/packaged_modules/json
|
| 135 |
+
Overwrite dataset info from restored data version if exists.
|
| 136 |
+
Loading Dataset info from /home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96
|
| 137 |
+
Found cached dataset json (/home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96)
|
| 138 |
+
Loading Dataset info from /home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96
|
| 139 |
+
[INFO|tokenization_utils_base.py:2024] 2024-01-18 19:24:51,385 >> loading file tokenizer.model
|
| 140 |
+
[INFO|tokenization_utils_base.py:2024] 2024-01-18 19:24:51,385 >> loading file added_tokens.json
|
| 141 |
+
[INFO|tokenization_utils_base.py:2024] 2024-01-18 19:24:51,385 >> loading file special_tokens_map.json
|
| 142 |
+
[INFO|tokenization_utils_base.py:2024] 2024-01-18 19:24:51,385 >> loading file tokenizer_config.json
|
| 143 |
+
[INFO|tokenization_utils_base.py:2024] 2024-01-18 19:24:51,385 >> loading file tokenizer.json
|
| 144 |
+
[INFO|configuration_utils.py:737] 2024-01-18 19:24:51,427 >> loading configuration file Yhyu13/LMCocktail-10.7B-v1/config.json
|
| 145 |
+
[INFO|configuration_utils.py:802] 2024-01-18 19:24:51,428 >> Model config LlamaConfig {
|
| 146 |
+
"_name_or_path": "Yhyu13/LMCocktail-10.7B-v1",
|
| 147 |
+
"architectures": [
|
| 148 |
+
"LlamaForCausalLM"
|
| 149 |
+
],
|
| 150 |
+
"attention_bias": false,
|
| 151 |
+
"attention_dropout": 0.0,
|
| 152 |
+
"bos_token_id": 1,
|
| 153 |
+
"eos_token_id": 2,
|
| 154 |
+
"hidden_act": "silu",
|
| 155 |
+
"hidden_size": 4096,
|
| 156 |
+
"initializer_range": 0.02,
|
| 157 |
+
"intermediate_size": 14336,
|
| 158 |
+
"max_position_embeddings": 4096,
|
| 159 |
+
"model_type": "llama",
|
| 160 |
+
"num_attention_heads": 32,
|
| 161 |
+
"num_hidden_layers": 48,
|
| 162 |
+
"num_key_value_heads": 8,
|
| 163 |
+
"pad_token_id": 2,
|
| 164 |
+
"pretraining_tp": 1,
|
| 165 |
+
"rms_norm_eps": 1e-05,
|
| 166 |
+
"rope_scaling": null,
|
| 167 |
+
"rope_theta": 10000.0,
|
| 168 |
+
"tie_word_embeddings": false,
|
| 169 |
+
"torch_dtype": "float16",
|
| 170 |
+
"transformers_version": "4.36.2",
|
| 171 |
+
"use_cache": true,
|
| 172 |
+
"vocab_size": 32000
|
| 173 |
+
}
|
| 174 |
+
|
| 175 |
+
[INFO|modeling_utils.py:3341] 2024-01-18 19:24:51,444 >> loading weights file Yhyu13/LMCocktail-10.7B-v1/model.safetensors.index.json
|
| 176 |
+
[INFO|modeling_utils.py:1341] 2024-01-18 19:24:51,444 >> Instantiating LlamaForCausalLM model under default dtype torch.float16.
|
| 177 |
+
[INFO|configuration_utils.py:826] 2024-01-18 19:24:51,445 >> Generate config GenerationConfig {
|
| 178 |
+
"bos_token_id": 1,
|
| 179 |
+
"eos_token_id": 2,
|
| 180 |
+
"pad_token_id": 2
|
| 181 |
+
}
|
| 182 |
+
|
| 183 |
+
|
| 184 |
+
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
|
| 185 |
+
Loading checkpoint shards: 20%|██ | 1/5 [00:00<00:00, 6.36it/s]
|
| 186 |
+
Loading checkpoint shards: 40%|████ | 2/5 [00:00<00:00, 6.36it/s]Yhyu13/LMCocktail-10.7B-v1
|
| 187 |
+
Loading checkpoint shards: 60%|██████ | 3/5 [00:00<00:00, 6.36it/s]
|
| 188 |
+
Loading checkpoint shards: 80%|████████ | 4/5 [00:00<00:00, 6.36it/s]Yhyu13/LMCocktail-10.7B-v1
|
| 189 |
+
Loading checkpoint shards: 100%|██████████| 5/5 [00:00<00:00, 6.42it/s]
|
| 190 |
+
Loading checkpoint shards: 100%|██████████| 5/5 [00:00<00:00, 6.39it/s]
|
| 191 |
+
[INFO|modeling_utils.py:4185] 2024-01-18 19:24:52,397 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
|
| 192 |
+
|
| 193 |
+
[INFO|modeling_utils.py:4193] 2024-01-18 19:24:52,397 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at ./models/LMCocktail-10.7B-v1.
|
| 194 |
+
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.
|
| 195 |
+
[INFO|configuration_utils.py:779] 2024-01-18 19:24:52,400 >> loading configuration file ./models/LMCocktail-10.7B-v1/generation_config.json
|
| 196 |
+
[INFO|configuration_utils.py:826] 2024-01-18 19:24:52,400 >> Generate config GenerationConfig {
|
| 197 |
+
"bos_token_id": 1,
|
| 198 |
+
"eos_token_id": 2,
|
| 199 |
+
"pad_token_id": 2,
|
| 200 |
+
"use_cache": false
|
| 201 |
+
}
|
| 202 |
+
|
| 203 |
+
01/18/2024 19:24:52 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
|
| 204 |
+
01/18/2024 19:24:54 - INFO - llmtuner.model.adapter - Merged 1 adapter(s).
|
| 205 |
+
01/18/2024 19:24:54 - INFO - llmtuner.model.adapter - Loaded adapter(s): ./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora
|
| 206 |
+
01/18/2024 19:24:54 - INFO - llmtuner.model.loader - trainable params: 0 || all params: 10731524096 || trainable%: 0.0000
|
| 207 |
+
01/18/2024 19:24:54 - INFO - llmtuner.model.loader - This IS expected that the trainable params is 0 if you are using model for inference only.
|
| 208 |
+
|
| 209 |
+
Running tokenizer on dataset: 0%| | 0/20 [00:00<?, ? examples/s]Caching processed dataset at /home/hangyu5/.cache/huggingface/datasets/json/default-cb85ddec01d455d4/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96/cache-700bf363697824f9.arrow
|
| 210 |
+
|
| 211 |
+
Running tokenizer on dataset: 100%|██████████| 20/20 [00:00<00:00, 529.06 examples/s]
|
| 212 |
+
[INFO|training_args.py:1838] 2024-01-18 19:24:54,939 >> PyTorch: setting up devices
|
| 213 |
+
Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
|
| 214 |
+
[INFO|trainer.py:3166] 2024-01-18 19:24:57,618 >> ***** Running Prediction *****
|
| 215 |
+
[INFO|trainer.py:3168] 2024-01-18 19:24:57,618 >> Num examples = 20
|
| 216 |
+
[INFO|trainer.py:3171] 2024-01-18 19:24:57,618 >> Batch size = 1
|
| 217 |
+
[INFO|configuration_utils.py:826] 2024-01-18 19:24:57,631 >> Generate config GenerationConfig {
|
| 218 |
+
"bos_token_id": 1,
|
| 219 |
+
"eos_token_id": 2,
|
| 220 |
+
"pad_token_id": 2
|
| 221 |
+
}
|
| 222 |
+
|
| 223 |
+
/home/hangyu5/anaconda3/envs/llama_factory/lib/python3.11/site-packages/transformers/generation/utils.py:1518: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use and modify the model generation configuration (see https://huggingface.co/docs/transformers/generation_strategies#default-text-generation-configuration )
|
| 224 |
+
warnings.warn(
|
| 225 |
+
input_ids:
|
| 226 |
+
[1, 774, 1247, 28747, 13, 27842, 28747, 995, 460, 264, 10865, 13892, 395, 2735, 298, 272, 2296, 5572, 28723, 5938, 706, 513, 3030, 387, 13, 28751, 13, 2287, 345, 861, 1264, 345, 527, 28730, 720, 4078, 28730, 6036, 548, 13, 2287, 345, 6518, 1264, 345, 1458, 272, 8877, 4338, 1444, 989, 1191, 951, 20023, 548, 13, 2287, 345, 11438, 1264, 371, 13, 5390, 345, 1123, 1264, 345, 2814, 548, 13, 5390, 345, 10723, 1264, 371, 13, 17422, 345, 2893, 28730, 16714, 1264, 371, 13, 1417, 28705, 345, 1123, 1264, 345, 1427, 548, 13, 1417, 28705, 345, 6518, 1264, 345, 1014, 15547, 298, 6603, 477, 28739, 13, 17422, 1630, 13, 17422, 345, 3731, 28730, 16714, 1264, 371, 13, 1417, 28705, 345, 1123, 1264, 345, 1427, 548, 13, 1417, 28705, 345, 6518, 1264, 345, 1014, 15547, 298, 6603, 298, 28739, 13, 17422, 443, 13, 5390, 1630, 13, 5390, 345, 10893, 1264, 733, 13, 17422, 345, 2893, 28730, 16714, 548, 13, 17422, 345, 3731, 28730, 16714, 28739, 13, 5390, 4709, 13, 2287, 443, 13, 28752, 13, 13, 6325, 368, 1820, 264, 9314, 354, 528, 477, 1450, 2726, 298, 4222, 28804, 13, 13, 27332, 21631, 28747, 13]
|
| 227 |
+
inputs:
|
| 228 |
+
<s>### User:
|
| 229 |
+
SYSTEM: You are a helpful assistant with access to the following functions. Use them if required -
|
| 230 |
+
{
|
| 231 |
+
"name": "get_exchange_rate",
|
| 232 |
+
"description": "Get the exchange rate between two currencies",
|
| 233 |
+
"parameters": {
|
| 234 |
+
"type": "object",
|
| 235 |
+
"properties": {
|
| 236 |
+
"base_currency": {
|
| 237 |
+
"type": "string",
|
| 238 |
+
"description": "The currency to convert from"
|
| 239 |
+
},
|
| 240 |
+
"target_currency": {
|
| 241 |
+
"type": "string",
|
| 242 |
+
"description": "The currency to convert to"
|
| 243 |
+
}
|
| 244 |
+
},
|
| 245 |
+
"required": [
|
| 246 |
+
"base_currency",
|
| 247 |
+
"target_currency"
|
| 248 |
+
]
|
| 249 |
+
}
|
| 250 |
+
}
|
| 251 |
+
|
| 252 |
+
Can you book a flight for me from New York to London?
|
| 253 |
+
|
| 254 |
+
### Assistant:
|
| 255 |
+
|
| 256 |
+
|
| 257 |
+
0%| | 0/20 [00:00<?, ?it/s]
|
| 258 |
+
10%|█ | 2/20 [00:01<00:13, 1.31it/s]
|
| 259 |
+
15%|█▌ | 3/20 [00:04<00:26, 1.56s/it]
|
| 260 |
+
20%|██ | 4/20 [00:05<00:25, 1.60s/it]
|
| 261 |
+
25%|██▌ | 5/20 [00:09<00:32, 2.16s/it]
|
| 262 |
+
30%|███ | 6/20 [00:10<00:26, 1.87s/it]
|
| 263 |
+
35%|███▌ | 7/20 [00:12<00:24, 1.87s/it]
|
| 264 |
+
40%|████ | 8/20 [00:13<00:21, 1.79s/it]
|
| 265 |
+
45%|████▌ | 9/20 [00:15<00:17, 1.62s/it]
|
| 266 |
+
50%|█████ | 10/20 [00:17<00:18, 1.81s/it]
|
| 267 |
+
55%|█████▌ | 11/20 [00:18<00:15, 1.75s/it]
|
| 268 |
+
60%|██████ | 12/20 [00:19<00:12, 1.51s/it]
|
| 269 |
+
65%|██████▌ | 13/20 [00:22<00:12, 1.79s/it]
|
| 270 |
+
70%|███████ | 14/20 [00:23<00:08, 1.50s/it]
|
| 271 |
+
75%|███████▌ | 15/20 [00:26<00:10, 2.07s/it]
|
| 272 |
+
80%|████████ | 16/20 [00:27<00:06, 1.74s/it]
|
| 273 |
+
85%|████████▌ | 17/20 [00:29<00:05, 1.79s/it]
|
| 274 |
+
90%|█████████ | 18/20 [00:31<00:03, 1.99s/it]
|
| 275 |
+
95%|█████████▌| 19/20 [00:32<00:01, 1.63s/it]
|
| 276 |
+
100%|██████████| 20/20 [00:34<00:00, 1.72s/it]Building prefix dict from the default dictionary ...
|
| 277 |
+
Loading model from cache /tmp/jieba.cache
|
| 278 |
+
Loading model cost 0.675 seconds.
|
| 279 |
+
Prefix dict has been built successfully.
|
| 280 |
+
|
| 281 |
+
100%|██████████| 20/20 [00:35<00:00, 1.77s/it]
|
| 282 |
+
***** predict metrics *****
|
| 283 |
+
predict_bleu-4 = 84.0251
|
| 284 |
+
predict_rouge-1 = 88.6553
|
| 285 |
+
predict_rouge-2 = 80.2374
|
| 286 |
+
predict_rouge-l = 86.4698
|
| 287 |
+
predict_runtime = 0:00:37.47
|
| 288 |
+
predict_samples_per_second = 0.534
|
| 289 |
+
predict_steps_per_second = 0.534
|
| 290 |
+
01/18/2024 19:25:35 - INFO - llmtuner.train.sft.trainer - Saving prediction results to ./models/sft/LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora/Predict_20/generated_predictions.jsonl
|
Predict_20/predict_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu-4": 84.02507,
|
| 3 |
+
"predict_rouge-1": 88.655265,
|
| 4 |
+
"predict_rouge-2": 80.23742000000001,
|
| 5 |
+
"predict_rouge-l": 86.469845,
|
| 6 |
+
"predict_runtime": 37.4743,
|
| 7 |
+
"predict_samples_per_second": 0.534,
|
| 8 |
+
"predict_steps_per_second": 0.534
|
| 9 |
+
}
|
README.md
CHANGED
|
@@ -1,3 +1,68 @@
|
|
| 1 |
---
|
| 2 |
license: llama2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: llama2
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: Yhyu13/LMCocktail-10.7B-v1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora
|
| 11 |
+
results: []
|
| 12 |
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# LMCocktail-10.7B-v1-sft-glaive-function-calling-v2-ep1-lora
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Yhyu13/LMCocktail-10.7B-v1](https://huggingface.co/Yhyu13/LMCocktail-10.7B-v1) on the https://huggingface.co/datasets/Yhyu13/glaive-function-calling-v2-llama-factory-convert dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2787
|
| 22 |
+
|
| 23 |
+
Training script is availbale at ./scripts/
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 5e-05
|
| 43 |
+
- train_batch_size: 1
|
| 44 |
+
- eval_batch_size: 1
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 2
|
| 48 |
+
- gradient_accumulation_steps: 4
|
| 49 |
+
- total_train_batch_size: 8
|
| 50 |
+
- total_eval_batch_size: 2
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- num_epochs: 1.0
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 59 |
+
| 0.2696 | 1.0 | 747 | 0.2787 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- PEFT 0.7.1
|
| 65 |
+
- Transformers 4.36.2
|
| 66 |
+
- Pytorch 2.1.2+cu121
|
| 67 |
+
- Datasets 2.16.1
|
| 68 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Yhyu13/LMCocktail-10.7B-v1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.0,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 8,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"v_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6cac1463452a8fc823b715bbd6df7f3a3fad2a24ea5c3ed495e58545c07ea9b
|
| 3 |
+
size 20472752
|
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.27866294980049133,
|
| 4 |
+
"eval_runtime": 101.2511,
|
| 5 |
+
"eval_samples_per_second": 6.558,
|
| 6 |
+
"eval_steps_per_second": 3.279,
|
| 7 |
+
"train_loss": 0.3299662241814446,
|
| 8 |
+
"train_runtime": 2859.8545,
|
| 9 |
+
"train_samples_per_second": 2.089,
|
| 10 |
+
"train_steps_per_second": 0.261
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.27866294980049133,
|
| 4 |
+
"eval_runtime": 101.2511,
|
| 5 |
+
"eval_samples_per_second": 6.558,
|
| 6 |
+
"eval_steps_per_second": 3.279
|
| 7 |
+
}
|
scripts/local_sft_fn_lmcocktail.sh
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
|
| 3 |
+
eval "$(conda shell.bash hook)"
|
| 4 |
+
conda activate llama_factory
|
| 5 |
+
|
| 6 |
+
MODEL_NAME=LMCocktail-10.7B-v1
|
| 7 |
+
STAGE=sft
|
| 8 |
+
EPOCH=1 #3.0
|
| 9 |
+
DATA=glaive-function-calling-v2
|
| 10 |
+
|
| 11 |
+
FT_TYPE=lora
|
| 12 |
+
LoRA_TARGET=q_proj,v_proj
|
| 13 |
+
TEMPLATE=solar
|
| 14 |
+
PREDICTION_SAMPLES=20
|
| 15 |
+
|
| 16 |
+
MODEL_PATH=./models/$MODEL_NAME
|
| 17 |
+
if [ ! -d $MODEL_PATH ]; then
|
| 18 |
+
echo "Model not found: $MODEL_PATH"
|
| 19 |
+
return 1
|
| 20 |
+
fi
|
| 21 |
+
|
| 22 |
+
SAVE_PATH=./models/$STAGE/$MODEL_NAME-$STAGE-$DATA-ep$EPOCH-$FT_TYPE
|
| 23 |
+
if [ ! -d $SAVE_PATH ]; then
|
| 24 |
+
mkdir -p $SAVE_PATH
|
| 25 |
+
fi
|
| 26 |
+
|
| 27 |
+
DO_TRAIN=false
|
| 28 |
+
DO_PREDICT=false
|
| 29 |
+
DO_EXPORT=false
|
| 30 |
+
|
| 31 |
+
for arg in "$@"
|
| 32 |
+
do
|
| 33 |
+
if [[ "$arg" == "--train" ]]; then
|
| 34 |
+
echo "The '--train' argument is present in an argument: $arg"
|
| 35 |
+
DO_TRAIN=true
|
| 36 |
+
fi
|
| 37 |
+
if [[ "$arg" == "--pred" ]]; then
|
| 38 |
+
echo "The '--pred' argument is present in an argument: $arg"
|
| 39 |
+
DO_PREDICT=true
|
| 40 |
+
fi
|
| 41 |
+
if [[ "$arg" == "--exp" ]]; then
|
| 42 |
+
echo "The '--exp' argument is present in an argument: $arg"
|
| 43 |
+
DO_EXPORT=true
|
| 44 |
+
fi
|
| 45 |
+
done
|
| 46 |
+
|
| 47 |
+
if [ $DO_TRAIN == true ]; then
|
| 48 |
+
accelerate launch src/train_bash.py \
|
| 49 |
+
--seed 42 \
|
| 50 |
+
--stage $STAGE \
|
| 51 |
+
--model_name_or_path $MODEL_PATH \
|
| 52 |
+
--dataset $DATA \
|
| 53 |
+
--val_size .1 \
|
| 54 |
+
--template $TEMPLATE \
|
| 55 |
+
--finetuning_type $FT_TYPE \
|
| 56 |
+
--do_train \
|
| 57 |
+
--lora_target $LoRA_TARGET \
|
| 58 |
+
--output_dir $SAVE_PATH \
|
| 59 |
+
--overwrite_output_dir \
|
| 60 |
+
--overwrite_cache \
|
| 61 |
+
--per_device_train_batch_size 1 \
|
| 62 |
+
--gradient_accumulation_steps 4 \
|
| 63 |
+
--lr_scheduler_type cosine \
|
| 64 |
+
--logging_steps 500 \
|
| 65 |
+
--save_steps 500 \
|
| 66 |
+
--learning_rate 5e-5 \
|
| 67 |
+
--num_train_epochs $EPOCH \
|
| 68 |
+
--do_eval \
|
| 69 |
+
--evaluation_strategy steps \
|
| 70 |
+
--per_device_eval_batch_size 1 \
|
| 71 |
+
--prediction_loss_only \
|
| 72 |
+
--plot_loss \
|
| 73 |
+
--quantization_bit 4 \
|
| 74 |
+
--report_to tensorboard \
|
| 75 |
+
|& tee $SAVE_PATH/train_eval_log.txt
|
| 76 |
+
fi
|
| 77 |
+
|
| 78 |
+
if [ $DO_PREDICT == true ]; then
|
| 79 |
+
SAVE_PATH_PREDICT=$SAVE_PATH/Predict_$PREDICTION_SAMPLES
|
| 80 |
+
if [ ! -d $SAVE_PATH_PREDICT ]; then
|
| 81 |
+
mkdir -p $SAVE_PATH_PREDICT
|
| 82 |
+
fi
|
| 83 |
+
CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
|
| 84 |
+
--stage $STAGE \
|
| 85 |
+
--model_name_or_path $MODEL_PATH \
|
| 86 |
+
--do_predict \
|
| 87 |
+
--max_samples $PREDICTION_SAMPLES \
|
| 88 |
+
--predict_with_generate \
|
| 89 |
+
--dataset $DATA \
|
| 90 |
+
--template $TEMPLATE \
|
| 91 |
+
--finetuning_type $FT_TYPE \
|
| 92 |
+
--adapter_name_or_path $SAVE_PATH \
|
| 93 |
+
--output_dir $SAVE_PATH_PREDICT \
|
| 94 |
+
--per_device_eval_batch_size 1 \
|
| 95 |
+
|& tee $SAVE_PATH_PREDICT/predict_log.txt
|
| 96 |
+
fi
|
| 97 |
+
|
| 98 |
+
if [ $DO_EXPORT == true ]; then
|
| 99 |
+
EXPORT_PATH=./models/export/$MODEL_NAME-$STAGE-$DATA-ep$EPOCH
|
| 100 |
+
if [ ! -d $EXPORT_PATH ]; then
|
| 101 |
+
mkdir -p $EXPORT_PATH
|
| 102 |
+
fi
|
| 103 |
+
CUDA_VISIBLE_DEVICES=0 python src/export_model.py \
|
| 104 |
+
--model_name_or_path $MODEL_PATH \
|
| 105 |
+
--adapter_name_or_path $SAVE_PATH \
|
| 106 |
+
--template $TEMPLATE \
|
| 107 |
+
--finetuning_type $FT_TYPE \
|
| 108 |
+
--export_dir $EXPORT_PATH \
|
| 109 |
+
--export_size 5 \
|
| 110 |
+
|& tee $EXPORT_PATH/export_log.txt
|
| 111 |
+
fi
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": true
|
| 45 |
+
}
|
train_eval_log.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.3299662241814446,
|
| 4 |
+
"train_runtime": 2859.8545,
|
| 5 |
+
"train_samples_per_second": 2.089,
|
| 6 |
+
"train_steps_per_second": 0.261
|
| 7 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 747, "loss": 1.6077, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.997789428625975e-05, "epoch": 0.01, "percentage": 1.34, "elapsed_time": "0:00:36", "remaining_time": "0:44:29"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 747, "loss": 0.9415, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.99116162380454e-05, "epoch": 0.03, "percentage": 2.68, "elapsed_time": "0:01:13", "remaining_time": "0:44:28"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 747, "loss": 0.6271, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.980128306524183e-05, "epoch": 0.04, "percentage": 4.02, "elapsed_time": "0:01:48", "remaining_time": "0:43:13"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 747, "loss": 0.5335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.964708988733178e-05, "epoch": 0.05, "percentage": 5.35, "elapsed_time": "0:02:27", "remaining_time": "0:43:20"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 747, "loss": 0.3693, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.944930938833535e-05, "epoch": 0.07, "percentage": 6.69, "elapsed_time": "0:03:01", "remaining_time": "0:42:14"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 747, "loss": 0.47, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9208291334580104e-05, "epoch": 0.08, "percentage": 8.03, "elapsed_time": "0:03:39", "remaining_time": "0:41:57"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 747, "loss": 0.4268, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.892446195615423e-05, "epoch": 0.09, "percentage": 9.37, "elapsed_time": "0:04:16", "remaining_time": "0:41:19"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 747, "loss": 0.3653, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.859832319313697e-05, "epoch": 0.11, "percentage": 10.71, "elapsed_time": "0:04:53", "remaining_time": "0:40:49"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 747, "loss": 0.3466, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8230451807939135e-05, "epoch": 0.12, "percentage": 12.05, "elapsed_time": "0:05:31", "remaining_time": "0:40:21"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 747, "loss": 0.3241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.782149836532345e-05, "epoch": 0.13, "percentage": 13.39, "elapsed_time": "0:06:07", "remaining_time": "0:39:39"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 747, "loss": 0.3763, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.737218608190878e-05, "epoch": 0.15, "percentage": 14.73, "elapsed_time": "0:06:47", "remaining_time": "0:39:21"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 747, "loss": 0.3333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6883309547192476e-05, "epoch": 0.16, "percentage": 16.06, "elapsed_time": "0:07:25", "remaining_time": "0:38:48"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 747, "loss": 0.3106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.635573331835302e-05, "epoch": 0.17, "percentage": 17.4, "elapsed_time": "0:08:01", "remaining_time": "0:38:05"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 747, "loss": 0.3241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5790390391317675e-05, "epoch": 0.19, "percentage": 18.74, "elapsed_time": "0:08:39", "remaining_time": "0:37:33"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 747, "loss": 0.2781, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.518828055079925e-05, "epoch": 0.2, "percentage": 20.08, "elapsed_time": "0:09:15", "remaining_time": "0:36:50"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 747, "loss": 0.3, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4550468602219716e-05, "epoch": 0.21, "percentage": 21.42, "elapsed_time": "0:09:54", "remaining_time": "0:36:19"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 747, "loss": 0.3229, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.387808248864751e-05, "epoch": 0.23, "percentage": 22.76, "elapsed_time": "0:10:29", "remaining_time": "0:35:37"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 747, "loss": 0.3347, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3172311296078595e-05, "epoch": 0.24, "percentage": 24.1, "elapsed_time": "0:11:05", "remaining_time": "0:34:56"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 747, "loss": 0.2897, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2434403150588895e-05, "epoch": 0.25, "percentage": 25.44, "elapsed_time": "0:11:42", "remaining_time": "0:34:19"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 747, "loss": 0.2951, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.166566301107687e-05, "epoch": 0.27, "percentage": 26.77, "elapsed_time": "0:12:18", "remaining_time": "0:33:40"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 747, "loss": 0.3081, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.08674503614997e-05, "epoch": 0.28, "percentage": 28.11, "elapsed_time": "0:12:56", "remaining_time": "0:33:04"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 747, "loss": 0.2889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.004117680668422e-05, "epoch": 0.29, "percentage": 29.45, "elapsed_time": "0:13:29", "remaining_time": "0:32:18"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 747, "loss": 0.3207, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.918830357596434e-05, "epoch": 0.31, "percentage": 30.79, "elapsed_time": "0:14:05", "remaining_time": "0:31:40"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 747, "loss": 0.3238, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8310338939059644e-05, "epoch": 0.32, "percentage": 32.13, "elapsed_time": "0:14:41", "remaining_time": "0:31:02"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 747, "loss": 0.3146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.740883553876515e-05, "epoch": 0.33, "percentage": 33.47, "elapsed_time": "0:15:19", "remaining_time": "0:30:27"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 747, "loss": 0.2973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6485387645169064e-05, "epoch": 0.35, "percentage": 34.81, "elapsed_time": "0:15:53", "remaining_time": "0:29:46"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 747, "loss": 0.2631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.55416283362546e-05, "epoch": 0.36, "percentage": 36.14, "elapsed_time": "0:16:31", "remaining_time": "0:29:11"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 747, "loss": 0.3323, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.457922660987155e-05, "epoch": 0.37, "percentage": 37.48, "elapsed_time": "0:17:10", "remaining_time": "0:28:38"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 747, "loss": 0.2631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3599884432185225e-05, "epoch": 0.39, "percentage": 38.82, "elapsed_time": "0:17:47", "remaining_time": "0:28:02"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 747, "loss": 0.3066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.260533372782234e-05, "epoch": 0.4, "percentage": 40.16, "elapsed_time": "0:18:22", "remaining_time": "0:27:22"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 747, "loss": 0.3131, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1597333317036545e-05, "epoch": 0.41, "percentage": 41.5, "elapsed_time": "0:18:58", "remaining_time": "0:26:44"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 747, "loss": 0.3101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.057766580531031e-05, "epoch": 0.43, "percentage": 42.84, "elapsed_time": "0:19:36", "remaining_time": "0:26:09"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 747, "loss": 0.3022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9548134430893604e-05, "epoch": 0.44, "percentage": 44.18, "elapsed_time": "0:20:14", "remaining_time": "0:25:34"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 747, "loss": 0.2496, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8510559875854377e-05, "epoch": 0.46, "percentage": 45.52, "elapsed_time": "0:20:49", "remaining_time": "0:24:56"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 747, "loss": 0.3218, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7466777046280457e-05, "epoch": 0.47, "percentage": 46.85, "elapsed_time": "0:21:25", "remaining_time": "0:24:17"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 747, "loss": 0.3064, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6418631827326857e-05, "epoch": 0.48, "percentage": 48.19, "elapsed_time": "0:21:59", "remaining_time": "0:23:38"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 747, "loss": 0.2937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5367977818847034e-05, "epoch": 0.5, "percentage": 49.53, "elapsed_time": "0:22:38", "remaining_time": "0:23:04"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 747, "loss": 0.2708, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.431667305738112e-05, "epoch": 0.51, "percentage": 50.87, "elapsed_time": "0:23:19", "remaining_time": "0:22:32"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 747, "loss": 0.2838, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3266576730297956e-05, "epoch": 0.52, "percentage": 52.21, "elapsed_time": "0:23:56", "remaining_time": "0:21:54"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 747, "loss": 0.2987, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.221954588790206e-05, "epoch": 0.54, "percentage": 53.55, "elapsed_time": "0:24:34", "remaining_time": "0:21:19"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 747, "loss": 0.3069, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1177432159319754e-05, "epoch": 0.55, "percentage": 54.89, "elapsed_time": "0:25:11", "remaining_time": "0:20:42"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 747, "loss": 0.2709, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.014207847797256e-05, "epoch": 0.56, "percentage": 56.22, "elapsed_time": "0:25:47", "remaining_time": "0:20:05"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 747, "loss": 0.3159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9115315822428437e-05, "epoch": 0.58, "percentage": 57.56, "elapsed_time": "0:26:26", "remaining_time": "0:19:29"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 747, "loss": 0.2997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.809895997839482e-05, "epoch": 0.59, "percentage": 58.9, "elapsed_time": "0:27:01", "remaining_time": "0:18:51"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 747, "loss": 0.2347, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.70948083275794e-05, "epoch": 0.6, "percentage": 60.24, "elapsed_time": "0:27:37", "remaining_time": "0:18:14"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 747, "loss": 0.2634, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6104636669097776e-05, "epoch": 0.62, "percentage": 61.58, "elapsed_time": "0:28:12", "remaining_time": "0:17:35"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 747, "loss": 0.2438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.513019607904882e-05, "epoch": 0.63, "percentage": 62.92, "elapsed_time": "0:28:49", "remaining_time": "0:16:59"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 747, "loss": 0.2289, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4173209813811788e-05, "epoch": 0.64, "percentage": 64.26, "elapsed_time": "0:29:26", "remaining_time": "0:16:22"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 747, "loss": 0.2609, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3235370262541272e-05, "epoch": 0.66, "percentage": 65.6, "elapsed_time": "0:30:05", "remaining_time": "0:15:47"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 747, "loss": 0.2724, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2318335954249669e-05, "epoch": 0.67, "percentage": 66.93, "elapsed_time": "0:30:43", "remaining_time": "0:15:10"}
|
| 51 |
+
{"current_steps": 510, "total_steps": 747, "loss": 0.272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1423728624769695e-05, "epoch": 0.68, "percentage": 68.27, "elapsed_time": "0:31:18", "remaining_time": "0:14:33"}
|
| 52 |
+
{"current_steps": 520, "total_steps": 747, "loss": 0.303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0553130348784182e-05, "epoch": 0.7, "percentage": 69.61, "elapsed_time": "0:31:57", "remaining_time": "0:13:56"}
|
| 53 |
+
{"current_steps": 530, "total_steps": 747, "loss": 0.2766, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.708080741994868e-06, "epoch": 0.71, "percentage": 70.95, "elapsed_time": "0:32:35", "remaining_time": "0:13:20"}
|
| 54 |
+
{"current_steps": 540, "total_steps": 747, "loss": 0.2333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.890074238378074e-06, "epoch": 0.72, "percentage": 72.29, "elapsed_time": "0:33:13", "remaining_time": "0:12:44"}
|
| 55 |
+
{"current_steps": 550, "total_steps": 747, "loss": 0.2326, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.100557447342327e-06, "epoch": 0.74, "percentage": 73.63, "elapsed_time": "0:33:51", "remaining_time": "0:12:07"}
|
| 56 |
+
{"current_steps": 560, "total_steps": 747, "loss": 0.2274, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.340926595461687e-06, "epoch": 0.75, "percentage": 74.97, "elapsed_time": "0:34:28", "remaining_time": "0:11:30"}
|
| 57 |
+
{"current_steps": 570, "total_steps": 747, "loss": 0.3255, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.612525057308949e-06, "epoch": 0.76, "percentage": 76.31, "elapsed_time": "0:35:05", "remaining_time": "0:10:53"}
|
| 58 |
+
{"current_steps": 580, "total_steps": 747, "loss": 0.2631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.9166409797553415e-06, "epoch": 0.78, "percentage": 77.64, "elapsed_time": "0:35:41", "remaining_time": "0:10:16"}
|
| 59 |
+
{"current_steps": 590, "total_steps": 747, "loss": 0.2938, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.254505003938043e-06, "epoch": 0.79, "percentage": 78.98, "elapsed_time": "0:36:17", "remaining_time": "0:09:39"}
|
| 60 |
+
{"current_steps": 600, "total_steps": 747, "loss": 0.2807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.627288088924156e-06, "epoch": 0.8, "percentage": 80.32, "elapsed_time": "0:36:53", "remaining_time": "0:09:02"}
|
| 61 |
+
{"current_steps": 610, "total_steps": 747, "loss": 0.2909, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.036099440919763e-06, "epoch": 0.82, "percentage": 81.66, "elapsed_time": "0:37:34", "remaining_time": "0:08:26"}
|
| 62 |
+
{"current_steps": 620, "total_steps": 747, "loss": 0.2997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.481984551686429e-06, "epoch": 0.83, "percentage": 83.0, "elapsed_time": "0:38:11", "remaining_time": "0:07:49"}
|
| 63 |
+
{"current_steps": 630, "total_steps": 747, "loss": 0.2424, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9659233496337786e-06, "epoch": 0.84, "percentage": 84.34, "elapsed_time": "0:38:48", "remaining_time": "0:07:12"}
|
| 64 |
+
{"current_steps": 640, "total_steps": 747, "loss": 0.2862, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4888284668582285e-06, "epoch": 0.86, "percentage": 85.68, "elapsed_time": "0:39:27", "remaining_time": "0:06:35"}
|
| 65 |
+
{"current_steps": 650, "total_steps": 747, "loss": 0.3124, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.051543625192226e-06, "epoch": 0.87, "percentage": 87.01, "elapsed_time": "0:40:04", "remaining_time": "0:05:58"}
|
| 66 |
+
{"current_steps": 660, "total_steps": 747, "loss": 0.2644, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6548421441183875e-06, "epoch": 0.88, "percentage": 88.35, "elapsed_time": "0:40:43", "remaining_time": "0:05:22"}
|
| 67 |
+
{"current_steps": 670, "total_steps": 747, "loss": 0.2622, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2994255731871963e-06, "epoch": 0.9, "percentage": 89.69, "elapsed_time": "0:41:18", "remaining_time": "0:04:44"}
|
| 68 |
+
{"current_steps": 680, "total_steps": 747, "loss": 0.2234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.85922451356694e-07, "epoch": 0.91, "percentage": 91.03, "elapsed_time": "0:41:52", "remaining_time": "0:04:07"}
|
| 69 |
+
{"current_steps": 690, "total_steps": 747, "loss": 0.334, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.148871954483105e-07, "epoch": 0.92, "percentage": 92.37, "elapsed_time": "0:42:29", "remaining_time": "0:03:30"}
|
| 70 |
+
{"current_steps": 700, "total_steps": 747, "loss": 0.2915, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.867991196844918e-07, "epoch": 0.94, "percentage": 93.71, "elapsed_time": "0:43:07", "remaining_time": "0:02:53"}
|
| 71 |
+
{"current_steps": 710, "total_steps": 747, "loss": 0.2802, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.020615880420713e-07, "epoch": 0.95, "percentage": 95.05, "elapsed_time": "0:43:42", "remaining_time": "0:02:16"}
|
| 72 |
+
{"current_steps": 720, "total_steps": 747, "loss": 0.2975, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6100130092037703e-07, "epoch": 0.96, "percentage": 96.39, "elapsed_time": "0:44:17", "remaining_time": "0:01:39"}
|
| 73 |
+
{"current_steps": 730, "total_steps": 747, "loss": 0.2531, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.386771738558506e-08, "epoch": 0.98, "percentage": 97.72, "elapsed_time": "0:44:53", "remaining_time": "0:01:02"}
|
| 74 |
+
{"current_steps": 740, "total_steps": 747, "loss": 0.2696, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0832614013073228e-08, "epoch": 0.99, "percentage": 99.06, "elapsed_time": "0:45:30", "remaining_time": "0:00:25"}
|
| 75 |
+
{"current_steps": 747, "total_steps": 747, "loss": null, "eval_loss": 0.27866294980049133, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:45:56", "remaining_time": "0:00:00"}
|
| 76 |
+
{"current_steps": 747, "total_steps": 747, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:45:56", "remaining_time": "0:00:00"}
|
| 77 |
+
{"current_steps": 332, "total_steps": 332, "loss": null, "eval_loss": 0.27866294980049133, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:49:22", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,482 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 747,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 4.997789428625975e-05,
|
| 14 |
+
"loss": 1.6077,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 4.99116162380454e-05,
|
| 20 |
+
"loss": 0.9415,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 4.980128306524183e-05,
|
| 26 |
+
"loss": 0.6271,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 4.964708988733178e-05,
|
| 32 |
+
"loss": 0.5335,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.07,
|
| 37 |
+
"learning_rate": 4.944930938833535e-05,
|
| 38 |
+
"loss": 0.3693,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"learning_rate": 4.9208291334580104e-05,
|
| 44 |
+
"loss": 0.47,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.09,
|
| 49 |
+
"learning_rate": 4.892446195615423e-05,
|
| 50 |
+
"loss": 0.4268,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11,
|
| 55 |
+
"learning_rate": 4.859832319313697e-05,
|
| 56 |
+
"loss": 0.3653,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.12,
|
| 61 |
+
"learning_rate": 4.8230451807939135e-05,
|
| 62 |
+
"loss": 0.3466,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.13,
|
| 67 |
+
"learning_rate": 4.782149836532345e-05,
|
| 68 |
+
"loss": 0.3241,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.15,
|
| 73 |
+
"learning_rate": 4.737218608190878e-05,
|
| 74 |
+
"loss": 0.3763,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.16,
|
| 79 |
+
"learning_rate": 4.6883309547192476e-05,
|
| 80 |
+
"loss": 0.3333,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.17,
|
| 85 |
+
"learning_rate": 4.635573331835302e-05,
|
| 86 |
+
"loss": 0.3106,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.19,
|
| 91 |
+
"learning_rate": 4.5790390391317675e-05,
|
| 92 |
+
"loss": 0.3241,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2,
|
| 97 |
+
"learning_rate": 4.518828055079925e-05,
|
| 98 |
+
"loss": 0.2781,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.21,
|
| 103 |
+
"learning_rate": 4.4550468602219716e-05,
|
| 104 |
+
"loss": 0.3,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.23,
|
| 109 |
+
"learning_rate": 4.387808248864751e-05,
|
| 110 |
+
"loss": 0.3229,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.24,
|
| 115 |
+
"learning_rate": 4.3172311296078595e-05,
|
| 116 |
+
"loss": 0.3347,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.25,
|
| 121 |
+
"learning_rate": 4.2434403150588895e-05,
|
| 122 |
+
"loss": 0.2897,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.27,
|
| 127 |
+
"learning_rate": 4.166566301107687e-05,
|
| 128 |
+
"loss": 0.2951,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.28,
|
| 133 |
+
"learning_rate": 4.08674503614997e-05,
|
| 134 |
+
"loss": 0.3081,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.29,
|
| 139 |
+
"learning_rate": 4.004117680668422e-05,
|
| 140 |
+
"loss": 0.2889,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.31,
|
| 145 |
+
"learning_rate": 3.918830357596434e-05,
|
| 146 |
+
"loss": 0.3207,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.32,
|
| 151 |
+
"learning_rate": 3.8310338939059644e-05,
|
| 152 |
+
"loss": 0.3238,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.33,
|
| 157 |
+
"learning_rate": 3.740883553876515e-05,
|
| 158 |
+
"loss": 0.3146,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.35,
|
| 163 |
+
"learning_rate": 3.6485387645169064e-05,
|
| 164 |
+
"loss": 0.2973,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.36,
|
| 169 |
+
"learning_rate": 3.55416283362546e-05,
|
| 170 |
+
"loss": 0.2631,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.37,
|
| 175 |
+
"learning_rate": 3.457922660987155e-05,
|
| 176 |
+
"loss": 0.3323,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.39,
|
| 181 |
+
"learning_rate": 3.3599884432185225e-05,
|
| 182 |
+
"loss": 0.2631,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.4,
|
| 187 |
+
"learning_rate": 3.260533372782234e-05,
|
| 188 |
+
"loss": 0.3066,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.41,
|
| 193 |
+
"learning_rate": 3.1597333317036545e-05,
|
| 194 |
+
"loss": 0.3131,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.43,
|
| 199 |
+
"learning_rate": 3.057766580531031e-05,
|
| 200 |
+
"loss": 0.3101,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.44,
|
| 205 |
+
"learning_rate": 2.9548134430893604e-05,
|
| 206 |
+
"loss": 0.3022,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.46,
|
| 211 |
+
"learning_rate": 2.8510559875854377e-05,
|
| 212 |
+
"loss": 0.2496,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.47,
|
| 217 |
+
"learning_rate": 2.7466777046280457e-05,
|
| 218 |
+
"loss": 0.3218,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.48,
|
| 223 |
+
"learning_rate": 2.6418631827326857e-05,
|
| 224 |
+
"loss": 0.3064,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.5,
|
| 229 |
+
"learning_rate": 2.5367977818847034e-05,
|
| 230 |
+
"loss": 0.2937,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.51,
|
| 235 |
+
"learning_rate": 2.431667305738112e-05,
|
| 236 |
+
"loss": 0.2708,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.52,
|
| 241 |
+
"learning_rate": 2.3266576730297956e-05,
|
| 242 |
+
"loss": 0.2838,
|
| 243 |
+
"step": 390
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.54,
|
| 247 |
+
"learning_rate": 2.221954588790206e-05,
|
| 248 |
+
"loss": 0.2987,
|
| 249 |
+
"step": 400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.55,
|
| 253 |
+
"learning_rate": 2.1177432159319754e-05,
|
| 254 |
+
"loss": 0.3069,
|
| 255 |
+
"step": 410
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.56,
|
| 259 |
+
"learning_rate": 2.014207847797256e-05,
|
| 260 |
+
"loss": 0.2709,
|
| 261 |
+
"step": 420
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.58,
|
| 265 |
+
"learning_rate": 1.9115315822428437e-05,
|
| 266 |
+
"loss": 0.3159,
|
| 267 |
+
"step": 430
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.59,
|
| 271 |
+
"learning_rate": 1.809895997839482e-05,
|
| 272 |
+
"loss": 0.2997,
|
| 273 |
+
"step": 440
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.6,
|
| 277 |
+
"learning_rate": 1.70948083275794e-05,
|
| 278 |
+
"loss": 0.2347,
|
| 279 |
+
"step": 450
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.62,
|
| 283 |
+
"learning_rate": 1.6104636669097776e-05,
|
| 284 |
+
"loss": 0.2634,
|
| 285 |
+
"step": 460
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.63,
|
| 289 |
+
"learning_rate": 1.513019607904882e-05,
|
| 290 |
+
"loss": 0.2438,
|
| 291 |
+
"step": 470
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.64,
|
| 295 |
+
"learning_rate": 1.4173209813811788e-05,
|
| 296 |
+
"loss": 0.2289,
|
| 297 |
+
"step": 480
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.66,
|
| 301 |
+
"learning_rate": 1.3235370262541272e-05,
|
| 302 |
+
"loss": 0.2609,
|
| 303 |
+
"step": 490
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.67,
|
| 307 |
+
"learning_rate": 1.2318335954249669e-05,
|
| 308 |
+
"loss": 0.2724,
|
| 309 |
+
"step": 500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.68,
|
| 313 |
+
"learning_rate": 1.1423728624769695e-05,
|
| 314 |
+
"loss": 0.272,
|
| 315 |
+
"step": 510
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.7,
|
| 319 |
+
"learning_rate": 1.0553130348784182e-05,
|
| 320 |
+
"loss": 0.303,
|
| 321 |
+
"step": 520
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.71,
|
| 325 |
+
"learning_rate": 9.708080741994868e-06,
|
| 326 |
+
"loss": 0.2766,
|
| 327 |
+
"step": 530
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.72,
|
| 331 |
+
"learning_rate": 8.890074238378074e-06,
|
| 332 |
+
"loss": 0.2333,
|
| 333 |
+
"step": 540
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.74,
|
| 337 |
+
"learning_rate": 8.100557447342327e-06,
|
| 338 |
+
"loss": 0.2326,
|
| 339 |
+
"step": 550
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.75,
|
| 343 |
+
"learning_rate": 7.340926595461687e-06,
|
| 344 |
+
"loss": 0.2274,
|
| 345 |
+
"step": 560
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.76,
|
| 349 |
+
"learning_rate": 6.612525057308949e-06,
|
| 350 |
+
"loss": 0.3255,
|
| 351 |
+
"step": 570
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.78,
|
| 355 |
+
"learning_rate": 5.9166409797553415e-06,
|
| 356 |
+
"loss": 0.2631,
|
| 357 |
+
"step": 580
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.79,
|
| 361 |
+
"learning_rate": 5.254505003938043e-06,
|
| 362 |
+
"loss": 0.2938,
|
| 363 |
+
"step": 590
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.8,
|
| 367 |
+
"learning_rate": 4.627288088924156e-06,
|
| 368 |
+
"loss": 0.2807,
|
| 369 |
+
"step": 600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.82,
|
| 373 |
+
"learning_rate": 4.036099440919763e-06,
|
| 374 |
+
"loss": 0.2909,
|
| 375 |
+
"step": 610
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.83,
|
| 379 |
+
"learning_rate": 3.481984551686429e-06,
|
| 380 |
+
"loss": 0.2997,
|
| 381 |
+
"step": 620
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.84,
|
| 385 |
+
"learning_rate": 2.9659233496337786e-06,
|
| 386 |
+
"loss": 0.2424,
|
| 387 |
+
"step": 630
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.86,
|
| 391 |
+
"learning_rate": 2.4888284668582285e-06,
|
| 392 |
+
"loss": 0.2862,
|
| 393 |
+
"step": 640
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.87,
|
| 397 |
+
"learning_rate": 2.051543625192226e-06,
|
| 398 |
+
"loss": 0.3124,
|
| 399 |
+
"step": 650
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.88,
|
| 403 |
+
"learning_rate": 1.6548421441183875e-06,
|
| 404 |
+
"loss": 0.2644,
|
| 405 |
+
"step": 660
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.9,
|
| 409 |
+
"learning_rate": 1.2994255731871963e-06,
|
| 410 |
+
"loss": 0.2622,
|
| 411 |
+
"step": 670
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.91,
|
| 415 |
+
"learning_rate": 9.85922451356694e-07,
|
| 416 |
+
"loss": 0.2234,
|
| 417 |
+
"step": 680
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.92,
|
| 421 |
+
"learning_rate": 7.148871954483105e-07,
|
| 422 |
+
"loss": 0.334,
|
| 423 |
+
"step": 690
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.94,
|
| 427 |
+
"learning_rate": 4.867991196844918e-07,
|
| 428 |
+
"loss": 0.2915,
|
| 429 |
+
"step": 700
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.95,
|
| 433 |
+
"learning_rate": 3.020615880420713e-07,
|
| 434 |
+
"loss": 0.2802,
|
| 435 |
+
"step": 710
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.96,
|
| 439 |
+
"learning_rate": 1.6100130092037703e-07,
|
| 440 |
+
"loss": 0.2975,
|
| 441 |
+
"step": 720
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.98,
|
| 445 |
+
"learning_rate": 6.386771738558506e-08,
|
| 446 |
+
"loss": 0.2531,
|
| 447 |
+
"step": 730
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.99,
|
| 451 |
+
"learning_rate": 1.0832614013073228e-08,
|
| 452 |
+
"loss": 0.2696,
|
| 453 |
+
"step": 740
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.0,
|
| 457 |
+
"eval_loss": 0.27866294980049133,
|
| 458 |
+
"eval_runtime": 101.2195,
|
| 459 |
+
"eval_samples_per_second": 6.56,
|
| 460 |
+
"eval_steps_per_second": 3.28,
|
| 461 |
+
"step": 747
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.0,
|
| 465 |
+
"step": 747,
|
| 466 |
+
"total_flos": 1.7883373351469056e+17,
|
| 467 |
+
"train_loss": 0.3299662241814446,
|
| 468 |
+
"train_runtime": 2859.8545,
|
| 469 |
+
"train_samples_per_second": 2.089,
|
| 470 |
+
"train_steps_per_second": 0.261
|
| 471 |
+
}
|
| 472 |
+
],
|
| 473 |
+
"logging_steps": 10,
|
| 474 |
+
"max_steps": 747,
|
| 475 |
+
"num_input_tokens_seen": 0,
|
| 476 |
+
"num_train_epochs": 1,
|
| 477 |
+
"save_steps": 1000,
|
| 478 |
+
"total_flos": 1.7883373351469056e+17,
|
| 479 |
+
"train_batch_size": 1,
|
| 480 |
+
"trial_name": null,
|
| 481 |
+
"trial_params": null
|
| 482 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05d9caf8806a8cf459511820a5f5aad699ab76b8ce2d0478c978f6d2e0bdc492
|
| 3 |
+
size 4984
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|