File size: 1,696 Bytes
f474fba |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.25,
"grad_norm": 1.3545468190942493,
"learning_rate": 4.665063509461098e-06,
"loss": 0.5496,
"mean_token_accuracy": 0.8319763600826263,
"num_tokens": 818989.0,
"step": 10
},
{
"epoch": 0.5,
"grad_norm": 1.1667092027460337,
"learning_rate": 2.9341204441673267e-06,
"loss": 0.5682,
"mean_token_accuracy": 0.8255345612764359,
"num_tokens": 1639216.0,
"step": 20
},
{
"epoch": 0.75,
"grad_norm": 1.1097172351640952,
"learning_rate": 8.930309757836517e-07,
"loss": 0.5692,
"mean_token_accuracy": 0.8248896270990371,
"num_tokens": 2463909.0,
"step": 30
},
{
"epoch": 1.0,
"grad_norm": 1.063402063268306,
"learning_rate": 0.0,
"loss": 0.5601,
"mean_token_accuracy": 0.8281995952129364,
"num_tokens": 3286234.0,
"step": 40
}
],
"logging_steps": 10,
"max_steps": 40,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8214189834240.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|