Delete trainer_state.json
Browse files- trainer_state.json +0 -106
trainer_state.json
DELETED
|
@@ -1,106 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 18.799348289259306,
|
| 5 |
-
"global_step": 150000,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 1.25,
|
| 12 |
-
"learning_rate": 1.164473409366253e-05,
|
| 13 |
-
"loss": 2.9668,
|
| 14 |
-
"step": 10000
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 2.51,
|
| 18 |
-
"learning_rate": 3.2894681873250615e-06,
|
| 19 |
-
"loss": 2.3684,
|
| 20 |
-
"step": 20000
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 3.76,
|
| 24 |
-
"learning_rate": 1.624013034214814e-05,
|
| 25 |
-
"loss": 1.5028,
|
| 26 |
-
"step": 30000
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 5.01,
|
| 30 |
-
"learning_rate": 1.498684045619752e-05,
|
| 31 |
-
"loss": 1.3541,
|
| 32 |
-
"step": 40000
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 6.27,
|
| 36 |
-
"learning_rate": 1.3733550570246898e-05,
|
| 37 |
-
"loss": 1.2438,
|
| 38 |
-
"step": 50000
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 7.52,
|
| 42 |
-
"learning_rate": 1.2480260684296278e-05,
|
| 43 |
-
"loss": 1.1711,
|
| 44 |
-
"step": 60000
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 8.77,
|
| 48 |
-
"learning_rate": 1.1226970798345658e-05,
|
| 49 |
-
"loss": 1.1123,
|
| 50 |
-
"step": 70000
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 10.03,
|
| 54 |
-
"learning_rate": 9.973680912395037e-06,
|
| 55 |
-
"loss": 1.0557,
|
| 56 |
-
"step": 80000
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 11.28,
|
| 60 |
-
"learning_rate": 8.720391026444417e-06,
|
| 61 |
-
"loss": 1.0005,
|
| 62 |
-
"step": 90000
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 12.53,
|
| 66 |
-
"learning_rate": 7.467101140493797e-06,
|
| 67 |
-
"loss": 0.9576,
|
| 68 |
-
"step": 100000
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 13.79,
|
| 72 |
-
"learning_rate": 6.213811254543176e-06,
|
| 73 |
-
"loss": 0.9233,
|
| 74 |
-
"step": 110000
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 15.04,
|
| 78 |
-
"learning_rate": 4.960521368592556e-06,
|
| 79 |
-
"loss": 0.8876,
|
| 80 |
-
"step": 120000
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 16.29,
|
| 84 |
-
"learning_rate": 3.7072314826419353e-06,
|
| 85 |
-
"loss": 0.859,
|
| 86 |
-
"step": 130000
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 17.55,
|
| 90 |
-
"learning_rate": 2.453941596691315e-06,
|
| 91 |
-
"loss": 0.8366,
|
| 92 |
-
"step": 140000
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 18.8,
|
| 96 |
-
"learning_rate": 1.2006517107406945e-06,
|
| 97 |
-
"loss": 0.818,
|
| 98 |
-
"step": 150000
|
| 99 |
-
}
|
| 100 |
-
],
|
| 101 |
-
"max_steps": 159580,
|
| 102 |
-
"num_train_epochs": 20,
|
| 103 |
-
"total_flos": 9.303396720850058e+19,
|
| 104 |
-
"trial_name": null,
|
| 105 |
-
"trial_params": null
|
| 106 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|