Hugging Face's logo

chloeli
/
qwen-2.5-0.5B-instruct-sft-lora-countdown-search-1k

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
alignment-handbook
trl
sft
conversational
text-generation-inference
Model card Files
xet
Community
1
qwen-2.5-0.5B-instruct-sft-lora-countdown-search-1k / trainer_state.json
chloeli's picture
chloeli
Model save
28c454a verified
raw
history blame contribute delete
6.63 kB
 {
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 125,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008,
"grad_norm": 1.0864604711532593,
"learning_rate": 1.5384615384615387e-05,
"loss": 0.4927,
"mean_token_accuracy": 0.8949072062969208,
"step": 1
},
{
"epoch": 0.04,
"grad_norm": 0.8317855596542358,
"learning_rate": 7.692307692307693e-05,
"loss": 0.5321,
"mean_token_accuracy": 0.8870031237602234,
"step": 5
},
{
"epoch": 0.08,
"grad_norm": 0.35360249876976013,
"learning_rate": 0.00015384615384615385,
"loss": 0.4318,
"mean_token_accuracy": 0.8946158409118652,
"step": 10
},
{
"epoch": 0.12,
"grad_norm": 0.26475989818573,
"learning_rate": 0.00019984268150178167,
"loss": 0.3243,
"mean_token_accuracy": 0.9152041494846344,
"step": 15
},
{
"epoch": 0.16,
"grad_norm": 0.21459443867206573,
"learning_rate": 0.00019807852804032305,
"loss": 0.2103,
"mean_token_accuracy": 0.941685950756073,
"step": 20
},
{
"epoch": 0.2,
"grad_norm": 0.15868614614009857,
"learning_rate": 0.00019438833303083678,
"loss": 0.1155,
"mean_token_accuracy": 0.9637313485145569,
"step": 25
},
{
"epoch": 0.24,
"grad_norm": 0.15498687326908112,
"learning_rate": 0.00018884456359788724,
"loss": 0.0816,
"mean_token_accuracy": 0.9711011052131653,
"step": 30
},
{
"epoch": 0.28,
"grad_norm": 0.11740818619728088,
"learning_rate": 0.00018155608689592604,
"loss": 0.0622,
"mean_token_accuracy": 0.9760455787181854,
"step": 35
},
{
"epoch": 0.32,
"grad_norm": 0.10971173644065857,
"learning_rate": 0.0001726660322034027,
"loss": 0.0545,
"mean_token_accuracy": 0.9776363372802734,
"step": 40
},
{
"epoch": 0.36,
"grad_norm": 0.08847042918205261,
"learning_rate": 0.00016234898018587337,
"loss": 0.0519,
"mean_token_accuracy": 0.977908480167389,
"step": 45
},
{
"epoch": 0.4,
"grad_norm": 0.09057971835136414,
"learning_rate": 0.00015080753452465296,
"loss": 0.0497,
"mean_token_accuracy": 0.9789802670478821,
"step": 50
},
{
"epoch": 0.44,
"grad_norm": 0.08262317627668381,
"learning_rate": 0.000138268343236509,
"loss": 0.0434,
"mean_token_accuracy": 0.9816033959388732,
"step": 55
},
{
"epoch": 0.48,
"grad_norm": 0.08489084988832474,
"learning_rate": 0.0001249776478167227,
"loss": 0.043,
"mean_token_accuracy": 0.9817807137966156,
"step": 60
},
{
"epoch": 0.52,
"grad_norm": 0.07146206498146057,
"learning_rate": 0.00011119644761033078,
"loss": 0.0397,
"mean_token_accuracy": 0.9835689246654511,
"step": 65
},
{
"epoch": 0.56,
"grad_norm": 0.08493078500032425,
"learning_rate": 9.719537437241312e-05,
"loss": 0.0432,
"mean_token_accuracy": 0.981769073009491,
"step": 70
},
{
"epoch": 0.6,
"grad_norm": 0.06853792816400528,
"learning_rate": 8.324937766952638e-05,
"loss": 0.0416,
"mean_token_accuracy": 0.9825034320354462,
"step": 75
},
{
"epoch": 0.64,
"grad_norm": 0.07850378751754761,
"learning_rate": 6.963232548903853e-05,
"loss": 0.0416,
"mean_token_accuracy": 0.9826254367828369,
"step": 80
},
{
"epoch": 0.68,
"grad_norm": 0.10064064711332321,
"learning_rate": 5.6611626088244194e-05,
"loss": 0.0411,
"mean_token_accuracy": 0.9827791035175324,
"step": 85
},
{
"epoch": 0.72,
"grad_norm": 0.07430274784564972,
"learning_rate": 4.444297669803981e-05,
"loss": 0.0432,
"mean_token_accuracy": 0.9819111526012421,
"step": 90
},
{
"epoch": 0.76,
"grad_norm": 0.05630122497677803,
"learning_rate": 3.336534220479961e-05,
"loss": 0.0381,
"mean_token_accuracy": 0.984023529291153,
"step": 95
},
{
"epoch": 0.8,
"grad_norm": 0.07422107458114624,
"learning_rate": 2.3596262417839255e-05,
"loss": 0.041,
"mean_token_accuracy": 0.9828759372234345,
"step": 100
},
{
"epoch": 0.84,
"grad_norm": 0.06742699444293976,
"learning_rate": 1.5327580077171587e-05,
"loss": 0.0435,
"mean_token_accuracy": 0.9813436925411224,
"step": 105
},
{
"epoch": 0.88,
"grad_norm": 0.07175164669752121,
"learning_rate": 8.72167349386811e-06,
"loss": 0.0406,
"mean_token_accuracy": 0.9831586062908173,
"step": 110
},
{
"epoch": 0.92,
"grad_norm": 0.06535231322050095,
"learning_rate": 3.908267805490051e-06,
"loss": 0.0411,
"mean_token_accuracy": 0.9826524317264557,
"step": 115
},
{
"epoch": 0.96,
"grad_norm": 0.07355163991451263,
"learning_rate": 9.818874663554357e-07,
"loss": 0.0407,
"mean_token_accuracy": 0.9827761054039001,
"step": 120
},
{
"epoch": 1.0,
"grad_norm": 0.07261276245117188,
"learning_rate": 0.0,
"loss": 0.04,
"mean_token_accuracy": 0.9830402076244354,
"step": 125
},
{
"epoch": 1.0,
"eval_loss": 0.0398690365254879,
"eval_mean_token_accuracy": 0.9831665050983429,
"eval_runtime": 167.2529,
"eval_samples_per_second": 11.958,
"eval_steps_per_second": 1.495,
"step": 125
},
{
"epoch": 1.0,
"step": 125,
"total_flos": 4505964279496704.0,
"train_loss": 0.1011103401184082,
"train_runtime": 450.8333,
"train_samples_per_second": 2.218,
"train_steps_per_second": 0.277
}
],
"logging_steps": 5,
"max_steps": 125,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4505964279496704.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}