116 lines
2.7 KiB
JSON
116 lines
2.7 KiB
JSON
|
{
|
||
|
|
"best_global_step": 8,
|
||
|
|
"best_metric": 0.8479433059692383,
|
||
|
|
"best_model_checkpoint": "./qwen3_test/checkpoint-8",
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 5,
|
||
|
|
"global_step": 8,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.13793103448275862,
|
||
|
|
"grad_norm": 13.323616027832031,
|
||
|
|
"learning_rate": 0.0,
|
||
|
|
"loss": 3.0943310260772705,
|
||
|
|
"step": 1
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.27586206896551724,
|
||
|
|
"grad_norm": 16.41815948486328,
|
||
|
|
"learning_rate": 4e-05,
|
||
|
|
"loss": 3.3327062129974365,
|
||
|
|
"step": 2
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.41379310344827586,
|
||
|
|
"grad_norm": 7.304614543914795,
|
||
|
|
"learning_rate": 8e-05,
|
||
|
|
"loss": 2.7867822647094727,
|
||
|
|
"step": 3
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5517241379310345,
|
||
|
|
"grad_norm": 4.277826309204102,
|
||
|
|
"learning_rate": 0.00012,
|
||
|
|
"loss": 2.2829997539520264,
|
||
|
|
"step": 4
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6896551724137931,
|
||
|
|
"grad_norm": 3.1133782863616943,
|
||
|
|
"learning_rate": 0.00016,
|
||
|
|
"loss": 1.864999532699585,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6896551724137931,
|
||
|
|
"eval_loss": 1.3821078538894653,
|
||
|
|
"eval_runtime": 16.3177,
|
||
|
|
"eval_samples_per_second": 1.716,
|
||
|
|
"eval_steps_per_second": 0.858,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8275862068965517,
|
||
|
|
"grad_norm": 2.3315927982330322,
|
||
|
|
"learning_rate": 0.0002,
|
||
|
|
"loss": 1.4849250316619873,
|
||
|
|
"step": 6
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9655172413793104,
|
||
|
|
"grad_norm": 2.310718059539795,
|
||
|
|
"learning_rate": 0.00015000000000000001,
|
||
|
|
"loss": 1.1298978328704834,
|
||
|
|
"step": 7
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 1.6008613109588623,
|
||
|
|
"learning_rate": 5.000000000000002e-05,
|
||
|
|
"loss": 0.9973629713058472,
|
||
|
|
"step": 8
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_loss": 0.8479433059692383,
|
||
|
|
"eval_runtime": 15.6771,
|
||
|
|
"eval_samples_per_second": 1.786,
|
||
|
|
"eval_steps_per_second": 0.893,
|
||
|
|
"step": 8
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 1,
|
||
|
|
"max_steps": 8,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 5,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"EarlyStoppingCallback": {
|
||
|
|
"args": {
|
||
|
|
"early_stopping_patience": 3,
|
||
|
|
"early_stopping_threshold": 0.0
|
||
|
|
},
|
||
|
|
"attributes": {
|
||
|
|
"early_stopping_patience_counter": 0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 4757074357770240.0,
|
||
|
|
"train_batch_size": 4,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|