Delete trainer_state.json
Browse files- trainer_state.json +0 -97
trainer_state.json
DELETED
|
@@ -1,97 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 3.9981670994348555,
|
| 5 |
-
"global_step": 3272,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.61,
|
| 12 |
-
"learning_rate": 4.235941320293399e-05,
|
| 13 |
-
"loss": 0.7001,
|
| 14 |
-
"step": 500
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 1.0,
|
| 18 |
-
"eval_accuracy": 0.4946000366099213,
|
| 19 |
-
"eval_loss": 0.6950803995132446,
|
| 20 |
-
"eval_runtime": 11.8643,
|
| 21 |
-
"eval_samples_per_second": 460.458,
|
| 22 |
-
"eval_steps_per_second": 14.413,
|
| 23 |
-
"step": 818
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 1.22,
|
| 27 |
-
"learning_rate": 3.4718826405867974e-05,
|
| 28 |
-
"loss": 0.6944,
|
| 29 |
-
"step": 1000
|
| 30 |
-
},
|
| 31 |
-
{
|
| 32 |
-
"epoch": 1.83,
|
| 33 |
-
"learning_rate": 2.7078239608801957e-05,
|
| 34 |
-
"loss": 0.6939,
|
| 35 |
-
"step": 1500
|
| 36 |
-
},
|
| 37 |
-
{
|
| 38 |
-
"epoch": 2.0,
|
| 39 |
-
"eval_accuracy": 0.500823723228995,
|
| 40 |
-
"eval_loss": 0.6931571960449219,
|
| 41 |
-
"eval_runtime": 11.8884,
|
| 42 |
-
"eval_samples_per_second": 459.523,
|
| 43 |
-
"eval_steps_per_second": 14.384,
|
| 44 |
-
"step": 1636
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 2.44,
|
| 48 |
-
"learning_rate": 1.9437652811735943e-05,
|
| 49 |
-
"loss": 0.6936,
|
| 50 |
-
"step": 2000
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 3.0,
|
| 54 |
-
"eval_accuracy": 0.5053999633900788,
|
| 55 |
-
"eval_loss": 0.6934992671012878,
|
| 56 |
-
"eval_runtime": 11.87,
|
| 57 |
-
"eval_samples_per_second": 460.234,
|
| 58 |
-
"eval_steps_per_second": 14.406,
|
| 59 |
-
"step": 2455
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 3.05,
|
| 63 |
-
"learning_rate": 1.1797066014669928e-05,
|
| 64 |
-
"loss": 0.6936,
|
| 65 |
-
"step": 2500
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 3.67,
|
| 69 |
-
"learning_rate": 4.156479217603912e-06,
|
| 70 |
-
"loss": 0.6934,
|
| 71 |
-
"step": 3000
|
| 72 |
-
},
|
| 73 |
-
{
|
| 74 |
-
"epoch": 4.0,
|
| 75 |
-
"eval_accuracy": 0.5032033681127586,
|
| 76 |
-
"eval_loss": 0.6931605935096741,
|
| 77 |
-
"eval_runtime": 11.8623,
|
| 78 |
-
"eval_samples_per_second": 460.535,
|
| 79 |
-
"eval_steps_per_second": 14.415,
|
| 80 |
-
"step": 3272
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 4.0,
|
| 84 |
-
"step": 3272,
|
| 85 |
-
"total_flos": 1.0942820488367309e+17,
|
| 86 |
-
"train_loss": 0.6947066952954878,
|
| 87 |
-
"train_runtime": 2952.2911,
|
| 88 |
-
"train_samples_per_second": 141.914,
|
| 89 |
-
"train_steps_per_second": 1.108
|
| 90 |
-
}
|
| 91 |
-
],
|
| 92 |
-
"max_steps": 3272,
|
| 93 |
-
"num_train_epochs": 4,
|
| 94 |
-
"total_flos": 1.0942820488367309e+17,
|
| 95 |
-
"trial_name": null,
|
| 96 |
-
"trial_params": null
|
| 97 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|