Delete trainer_state.json
Browse files- trainer_state.json +0 -93
trainer_state.json
DELETED
|
@@ -1,93 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": 3.5722010135650635,
|
| 3 |
-
"best_model_checkpoint": "/home/dousti_group/ghanizadeh/babyLM/model-save/5-epoch-tv-tokenized/checkpoint-113408",
|
| 4 |
-
"epoch": 4.0,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 113408,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 1.0,
|
| 13 |
-
"grad_norm": 5.181252479553223,
|
| 14 |
-
"learning_rate": 4.014476851196376e-05,
|
| 15 |
-
"loss": 4.3405,
|
| 16 |
-
"step": 28352
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 1.0,
|
| 20 |
-
"eval_loss": 3.8782432079315186,
|
| 21 |
-
"eval_runtime": 163.7675,
|
| 22 |
-
"eval_samples_per_second": 291.572,
|
| 23 |
-
"eval_steps_per_second": 36.448,
|
| 24 |
-
"step": 28352
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 2.0,
|
| 28 |
-
"grad_norm": 4.64185094833374,
|
| 29 |
-
"learning_rate": 3.0112558402944925e-05,
|
| 30 |
-
"loss": 3.7749,
|
| 31 |
-
"step": 56704
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 2.0,
|
| 35 |
-
"eval_loss": 3.6707634925842285,
|
| 36 |
-
"eval_runtime": 158.0831,
|
| 37 |
-
"eval_samples_per_second": 302.056,
|
| 38 |
-
"eval_steps_per_second": 37.759,
|
| 39 |
-
"step": 56704
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 3.0,
|
| 43 |
-
"grad_norm": 6.706910610198975,
|
| 44 |
-
"learning_rate": 2.0081056208410027e-05,
|
| 45 |
-
"loss": 3.493,
|
| 46 |
-
"step": 85056
|
| 47 |
-
},
|
| 48 |
-
{
|
| 49 |
-
"epoch": 3.0,
|
| 50 |
-
"eval_loss": 3.5801351070404053,
|
| 51 |
-
"eval_runtime": 158.2132,
|
| 52 |
-
"eval_samples_per_second": 301.808,
|
| 53 |
-
"eval_steps_per_second": 37.728,
|
| 54 |
-
"step": 85056
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 4.0,
|
| 58 |
-
"grad_norm": 10.424848556518555,
|
| 59 |
-
"learning_rate": 1.005061588560102e-05,
|
| 60 |
-
"loss": 3.2244,
|
| 61 |
-
"step": 113408
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 4.0,
|
| 65 |
-
"eval_loss": 3.5722010135650635,
|
| 66 |
-
"eval_runtime": 157.7259,
|
| 67 |
-
"eval_samples_per_second": 302.74,
|
| 68 |
-
"eval_steps_per_second": 37.844,
|
| 69 |
-
"step": 113408
|
| 70 |
-
}
|
| 71 |
-
],
|
| 72 |
-
"logging_steps": 500,
|
| 73 |
-
"max_steps": 141760,
|
| 74 |
-
"num_input_tokens_seen": 0,
|
| 75 |
-
"num_train_epochs": 5,
|
| 76 |
-
"save_steps": 500,
|
| 77 |
-
"stateful_callbacks": {
|
| 78 |
-
"TrainerControl": {
|
| 79 |
-
"args": {
|
| 80 |
-
"should_epoch_stop": false,
|
| 81 |
-
"should_evaluate": false,
|
| 82 |
-
"should_log": false,
|
| 83 |
-
"should_save": true,
|
| 84 |
-
"should_training_stop": false
|
| 85 |
-
},
|
| 86 |
-
"attributes": {}
|
| 87 |
-
}
|
| 88 |
-
},
|
| 89 |
-
"total_flos": 2.959934159506637e+17,
|
| 90 |
-
"train_batch_size": 32,
|
| 91 |
-
"trial_name": null,
|
| 92 |
-
"trial_params": null
|
| 93 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|