Commit
•
f2dac18
1
Parent(s):
520c82e
End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +121 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.06589564281871974,
|
| 4 |
+
"eval_loss": 2.6640625,
|
| 5 |
+
"eval_runtime": 17.5909,
|
| 6 |
+
"eval_samples": 78,
|
| 7 |
+
"eval_samples_per_second": 4.434,
|
| 8 |
+
"eval_steps_per_second": 0.568,
|
| 9 |
+
"perplexity": 14.354485905365031,
|
| 10 |
+
"train_loss": 1.82276857816256,
|
| 11 |
+
"train_runtime": 1007.1646,
|
| 12 |
+
"train_samples": 416,
|
| 13 |
+
"train_samples_per_second": 0.826,
|
| 14 |
+
"train_steps_per_second": 0.103
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.06589564281871974,
|
| 4 |
+
"eval_loss": 2.6640625,
|
| 5 |
+
"eval_runtime": 17.5909,
|
| 6 |
+
"eval_samples": 78,
|
| 7 |
+
"eval_samples_per_second": 4.434,
|
| 8 |
+
"eval_steps_per_second": 0.568,
|
| 9 |
+
"perplexity": 14.354485905365031
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 1.82276857816256,
|
| 4 |
+
"train_runtime": 1007.1646,
|
| 5 |
+
"train_samples": 416,
|
| 6 |
+
"train_samples_per_second": 0.826,
|
| 7 |
+
"train_steps_per_second": 0.103
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 104,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 0,
|
| 13 |
+
"loss": 2.6804,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.31,
|
| 18 |
+
"learning_rate": 5e-05,
|
| 19 |
+
"loss": 2.5958,
|
| 20 |
+
"step": 16
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.31,
|
| 24 |
+
"eval_accuracy": 0.06585978124439663,
|
| 25 |
+
"eval_loss": 2.537109375,
|
| 26 |
+
"eval_runtime": 16.98,
|
| 27 |
+
"eval_samples_per_second": 4.594,
|
| 28 |
+
"eval_steps_per_second": 0.589,
|
| 29 |
+
"step": 16
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.62,
|
| 33 |
+
"learning_rate": 5e-05,
|
| 34 |
+
"loss": 2.3784,
|
| 35 |
+
"step": 32
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.62,
|
| 39 |
+
"eval_accuracy": 0.06695355926125157,
|
| 40 |
+
"eval_loss": 2.50390625,
|
| 41 |
+
"eval_runtime": 17.6527,
|
| 42 |
+
"eval_samples_per_second": 4.419,
|
| 43 |
+
"eval_steps_per_second": 0.566,
|
| 44 |
+
"step": 32
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.92,
|
| 48 |
+
"learning_rate": 5e-05,
|
| 49 |
+
"loss": 2.3578,
|
| 50 |
+
"step": 48
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.92,
|
| 54 |
+
"eval_accuracy": 0.06535771920387305,
|
| 55 |
+
"eval_loss": 2.607421875,
|
| 56 |
+
"eval_runtime": 17.1023,
|
| 57 |
+
"eval_samples_per_second": 4.561,
|
| 58 |
+
"eval_steps_per_second": 0.585,
|
| 59 |
+
"step": 48
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.23,
|
| 63 |
+
"learning_rate": 5e-05,
|
| 64 |
+
"loss": 1.3819,
|
| 65 |
+
"step": 64
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.23,
|
| 69 |
+
"eval_accuracy": 0.06575219652142729,
|
| 70 |
+
"eval_loss": 2.66796875,
|
| 71 |
+
"eval_runtime": 16.8667,
|
| 72 |
+
"eval_samples_per_second": 4.625,
|
| 73 |
+
"eval_steps_per_second": 0.593,
|
| 74 |
+
"step": 64
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.54,
|
| 78 |
+
"learning_rate": 5e-05,
|
| 79 |
+
"loss": 1.1529,
|
| 80 |
+
"step": 80
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.54,
|
| 84 |
+
"eval_accuracy": 0.06650528958221266,
|
| 85 |
+
"eval_loss": 2.673828125,
|
| 86 |
+
"eval_runtime": 17.3671,
|
| 87 |
+
"eval_samples_per_second": 4.491,
|
| 88 |
+
"eval_steps_per_second": 0.576,
|
| 89 |
+
"step": 80
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.85,
|
| 93 |
+
"learning_rate": 5e-05,
|
| 94 |
+
"loss": 1.2938,
|
| 95 |
+
"step": 96
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.85,
|
| 99 |
+
"eval_accuracy": 0.06621839698762776,
|
| 100 |
+
"eval_loss": 2.6640625,
|
| 101 |
+
"eval_runtime": 17.6569,
|
| 102 |
+
"eval_samples_per_second": 4.418,
|
| 103 |
+
"eval_steps_per_second": 0.566,
|
| 104 |
+
"step": 96
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.0,
|
| 108 |
+
"step": 104,
|
| 109 |
+
"total_flos": 7482848575488.0,
|
| 110 |
+
"train_loss": 1.82276857816256,
|
| 111 |
+
"train_runtime": 1007.1646,
|
| 112 |
+
"train_samples_per_second": 0.826,
|
| 113 |
+
"train_steps_per_second": 0.103
|
| 114 |
+
}
|
| 115 |
+
],
|
| 116 |
+
"max_steps": 104,
|
| 117 |
+
"num_train_epochs": 2,
|
| 118 |
+
"total_flos": 7482848575488.0,
|
| 119 |
+
"trial_name": null,
|
| 120 |
+
"trial_params": null
|
| 121 |
+
}
|