File size: 1,571 Bytes
88edadd | 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": 2.0,
"eval_steps": 500,
"global_step": 4,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5,
"grad_norm": 0.025232185668638253,
"learning_rate": 5e-05,
"loss": 0.1498,
"step": 1
},
{
"epoch": 1.0,
"grad_norm": 0.025267347429546894,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.1515,
"step": 2
},
{
"epoch": 1.5,
"grad_norm": 0.028300648150527005,
"learning_rate": 1.2500000000000006e-05,
"loss": 0.1478,
"step": 3
},
{
"epoch": 2.0,
"grad_norm": 0.0274135417163776,
"learning_rate": 0.0,
"loss": 0.147,
"step": 4
},
{
"epoch": 2.0,
"step": 4,
"total_flos": 76039485128704.0,
"train_loss": 0.1490258015692234,
"train_runtime": 252.7524,
"train_samples_per_second": 0.142,
"train_steps_per_second": 0.016
}
],
"logging_steps": 1,
"max_steps": 4,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 76039485128704.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|