Spaces:
Sleeping
Sleeping
File size: 1,837 Bytes
d661bad |
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 72 73 74 75 76 77 78 79 80 81 82 83 84 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.24,
"eval_steps": 500,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.032,
"grad_norm": 671614.75,
"learning_rate": 4.9493333333333336e-05,
"loss": 2.1669,
"step": 20
},
{
"epoch": 0.064,
"grad_norm": 41173.5,
"learning_rate": 4.896e-05,
"loss": 0.5516,
"step": 40
},
{
"epoch": 0.096,
"grad_norm": 14334.6923828125,
"learning_rate": 4.842666666666667e-05,
"loss": 0.2249,
"step": 60
},
{
"epoch": 0.128,
"grad_norm": 14753.2421875,
"learning_rate": 4.789333333333334e-05,
"loss": 0.1644,
"step": 80
},
{
"epoch": 0.16,
"grad_norm": 12797.7333984375,
"learning_rate": 4.736000000000001e-05,
"loss": 0.103,
"step": 100
},
{
"epoch": 0.192,
"grad_norm": 12743.939453125,
"learning_rate": 4.682666666666667e-05,
"loss": 0.0684,
"step": 120
},
{
"epoch": 0.224,
"grad_norm": 10378.1640625,
"learning_rate": 4.629333333333333e-05,
"loss": 0.0495,
"step": 140
}
],
"logging_steps": 20,
"max_steps": 1875,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3817778813337600.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|