Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +103 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 19420,
|
| 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": 1.0474146604537964,
|
| 14 |
+
"learning_rate": 9.932086511308698e-05,
|
| 15 |
+
"loss": 0.7626,
|
| 16 |
+
"step": 1942
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0,
|
| 20 |
+
"grad_norm": 0.34481489658355713,
|
| 21 |
+
"learning_rate": 9.398178969222977e-05,
|
| 22 |
+
"loss": 0.2322,
|
| 23 |
+
"step": 3884
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.0,
|
| 27 |
+
"grad_norm": 0.41964319348335266,
|
| 28 |
+
"learning_rate": 8.387660491043735e-05,
|
| 29 |
+
"loss": 0.1471,
|
| 30 |
+
"step": 5826
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 4.0,
|
| 34 |
+
"grad_norm": 0.8369811773300171,
|
| 35 |
+
"learning_rate": 7.01081600148828e-05,
|
| 36 |
+
"loss": 0.1128,
|
| 37 |
+
"step": 7768
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.0,
|
| 41 |
+
"grad_norm": 0.27606743574142456,
|
| 42 |
+
"learning_rate": 5.4154422280282916e-05,
|
| 43 |
+
"loss": 0.096,
|
| 44 |
+
"step": 9710
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.0,
|
| 48 |
+
"grad_norm": 1.0203839540481567,
|
| 49 |
+
"learning_rate": 3.775048842911087e-05,
|
| 50 |
+
"loss": 0.0836,
|
| 51 |
+
"step": 11652
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 7.0,
|
| 55 |
+
"grad_norm": 0.27634188532829285,
|
| 56 |
+
"learning_rate": 2.2681109856932215e-05,
|
| 57 |
+
"loss": 0.0769,
|
| 58 |
+
"step": 13594
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 8.0,
|
| 62 |
+
"grad_norm": 0.1679644137620926,
|
| 63 |
+
"learning_rate": 1.0563901955241806e-05,
|
| 64 |
+
"loss": 0.0709,
|
| 65 |
+
"step": 15536
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.0,
|
| 69 |
+
"grad_norm": 0.0655561313033104,
|
| 70 |
+
"learning_rate": 2.720207190809809e-06,
|
| 71 |
+
"loss": 0.0667,
|
| 72 |
+
"step": 17478
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 10.0,
|
| 76 |
+
"grad_norm": 0.24803902208805084,
|
| 77 |
+
"learning_rate": 1.1598826660241813e-11,
|
| 78 |
+
"loss": 0.0636,
|
| 79 |
+
"step": 19420
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"logging_steps": 500,
|
| 83 |
+
"max_steps": 19420,
|
| 84 |
+
"num_input_tokens_seen": 0,
|
| 85 |
+
"num_train_epochs": 10,
|
| 86 |
+
"save_steps": 500,
|
| 87 |
+
"stateful_callbacks": {
|
| 88 |
+
"TrainerControl": {
|
| 89 |
+
"args": {
|
| 90 |
+
"should_epoch_stop": false,
|
| 91 |
+
"should_evaluate": false,
|
| 92 |
+
"should_log": false,
|
| 93 |
+
"should_save": true,
|
| 94 |
+
"should_training_stop": true
|
| 95 |
+
},
|
| 96 |
+
"attributes": {}
|
| 97 |
+
}
|
| 98 |
+
},
|
| 99 |
+
"total_flos": 1.0777248659423232e+17,
|
| 100 |
+
"train_batch_size": 1,
|
| 101 |
+
"trial_name": null,
|
| 102 |
+
"trial_params": null
|
| 103 |
+
}
|