File size: 1,643 Bytes
fc13558 |
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_metric": null,
"best_model_checkpoint": null,
"epoch": 0.23684210526315788,
"eval_steps": 9,
"global_step": 9,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02631578947368421,
"eval_loss": 1.6184024810791016,
"eval_runtime": 4.386,
"eval_samples_per_second": 14.592,
"eval_steps_per_second": 1.824,
"step": 1
},
{
"epoch": 0.07894736842105263,
"grad_norm": 25.33377456665039,
"learning_rate": 3e-05,
"loss": 6.2534,
"step": 3
},
{
"epoch": 0.15789473684210525,
"grad_norm": 19.7912540435791,
"learning_rate": 6e-05,
"loss": 6.0633,
"step": 6
},
{
"epoch": 0.23684210526315788,
"grad_norm": 17.20012855529785,
"learning_rate": 9e-05,
"loss": 5.0168,
"step": 9
},
{
"epoch": 0.23684210526315788,
"eval_loss": 1.0376337766647339,
"eval_runtime": 4.4723,
"eval_samples_per_second": 14.31,
"eval_steps_per_second": 1.789,
"step": 9
}
],
"logging_steps": 3,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 9,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.2656345471778816e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|