Files
2026-07-19 23:52:25 +04:00

80 lines
1.9 KiB
JSON

{
"best_global_step": 100,
"best_metric": 1.6638826131820679,
"best_model_checkpoint": "./Llama-3.2-3b-ru-lora/checkpoint-100",
"epoch": 0.3368421052631579,
"eval_steps": 100,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08421052631578947,
"grad_norm": 0.22051513195037842,
"learning_rate": 8e-05,
"loss": 2.3452760314941408,
"step": 25
},
{
"epoch": 0.16842105263157894,
"grad_norm": 0.24215690791606903,
"learning_rate": 9.779326364692218e-05,
"loss": 1.873732452392578,
"step": 50
},
{
"epoch": 0.25263157894736843,
"grad_norm": 0.2318001091480255,
"learning_rate": 9.488966318234611e-05,
"loss": 1.7455740356445313,
"step": 75
},
{
"epoch": 0.3368421052631579,
"grad_norm": 0.22570297122001648,
"learning_rate": 9.198606271777003e-05,
"loss": 1.7174720764160156,
"step": 100
},
{
"epoch": 0.3368421052631579,
"eval_loss": 1.6638826131820679,
"eval_runtime": 41.5175,
"eval_samples_per_second": 3.011,
"eval_steps_per_second": 3.011,
"step": 100
}
],
"logging_steps": 25,
"max_steps": 891,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"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": false
},
"attributes": {}
}
},
"total_flos": 1.175730920742912e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}