File size: 1,631 Bytes
5e98e91 | 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 | {
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.960573476702509,
"eval_steps": 500,
"global_step": 2500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.7921146953405018,
"grad_norm": 0.5550134778022766,
"learning_rate": 4.1039426523297493e-05,
"loss": 1.0898,
"step": 500
},
{
"epoch": 3.5842293906810037,
"grad_norm": 0.8247848153114319,
"learning_rate": 3.207885304659498e-05,
"loss": 0.866,
"step": 1000
},
{
"epoch": 5.376344086021505,
"grad_norm": 0.9447944164276123,
"learning_rate": 2.3118279569892472e-05,
"loss": 0.7996,
"step": 1500
},
{
"epoch": 7.168458781362007,
"grad_norm": 1.0575640201568604,
"learning_rate": 1.4157706093189965e-05,
"loss": 0.7605,
"step": 2000
},
{
"epoch": 8.960573476702509,
"grad_norm": 1.0388325452804565,
"learning_rate": 5.197132616487455e-06,
"loss": 0.732,
"step": 2500
}
],
"logging_steps": 500,
"max_steps": 2790,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.255837538690007e+18,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}
|