Commit
·
e2541a4
1
Parent(s):
6fea5e0
End of training
Browse files- all_results.json +11 -11
- eval_results.json +7 -7
- train_results.json +5 -5
- trainer_state.json +346 -52
all_results.json
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
"eval_gen_len": 1.0,
|
| 5 |
-
"eval_loss":
|
| 6 |
"eval_rouge1": 0.0,
|
| 7 |
"eval_rouge2": 0.0,
|
| 8 |
"eval_rougeL": 0.0,
|
| 9 |
"eval_rougeLsum": 0.0,
|
| 10 |
-
"eval_runtime": 0.
|
| 11 |
"eval_samples": 3,
|
| 12 |
-
"eval_samples_per_second":
|
| 13 |
-
"eval_steps_per_second":
|
| 14 |
-
"perplexity":
|
| 15 |
"predict_gen_len": 1.0,
|
| 16 |
"predict_loss": 5.266044616699219,
|
| 17 |
"predict_rouge1": 0.0,
|
|
@@ -22,9 +22,9 @@
|
|
| 22 |
"predict_samples": 3527,
|
| 23 |
"predict_samples_per_second": 237.858,
|
| 24 |
"predict_steps_per_second": 14.904,
|
| 25 |
-
"train_loss": 2.
|
| 26 |
-
"train_runtime":
|
| 27 |
"train_samples": 49,
|
| 28 |
-
"train_samples_per_second":
|
| 29 |
-
"train_steps_per_second":
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.6093189964157706,
|
| 4 |
"eval_gen_len": 1.0,
|
| 5 |
+
"eval_loss": 1.8930710554122925,
|
| 6 |
"eval_rouge1": 0.0,
|
| 7 |
"eval_rouge2": 0.0,
|
| 8 |
"eval_rougeL": 0.0,
|
| 9 |
"eval_rougeLsum": 0.0,
|
| 10 |
+
"eval_runtime": 0.1102,
|
| 11 |
"eval_samples": 3,
|
| 12 |
+
"eval_samples_per_second": 27.23,
|
| 13 |
+
"eval_steps_per_second": 9.077,
|
| 14 |
+
"perplexity": 6.639728375930875,
|
| 15 |
"predict_gen_len": 1.0,
|
| 16 |
"predict_loss": 5.266044616699219,
|
| 17 |
"predict_rouge1": 0.0,
|
|
|
|
| 22 |
"predict_samples": 3527,
|
| 23 |
"predict_samples_per_second": 237.858,
|
| 24 |
"predict_steps_per_second": 14.904,
|
| 25 |
+
"train_loss": 2.381487710135324,
|
| 26 |
+
"train_runtime": 18.165,
|
| 27 |
"train_samples": 49,
|
| 28 |
+
"train_samples_per_second": 26.975,
|
| 29 |
+
"train_steps_per_second": 3.854
|
| 30 |
}
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
"eval_samples": 3,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"perplexity":
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.6093189964157706,
|
| 4 |
+
"eval_loss": 1.8930710554122925,
|
| 5 |
+
"eval_runtime": 0.1102,
|
| 6 |
"eval_samples": 3,
|
| 7 |
+
"eval_samples_per_second": 27.23,
|
| 8 |
+
"eval_steps_per_second": 9.077,
|
| 9 |
+
"perplexity": 6.639728375930875
|
| 10 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 2.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 49,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 2.381487710135324,
|
| 4 |
+
"train_runtime": 18.165,
|
| 5 |
"train_samples": 49,
|
| 6 |
+
"train_samples_per_second": 26.975,
|
| 7 |
+
"train_steps_per_second": 3.854
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,151 +1,445 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.14,
|
| 12 |
-
"learning_rate": 4.
|
| 13 |
"loss": 3.0215,
|
| 14 |
"step": 1
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.29,
|
| 18 |
-
"learning_rate": 4.
|
| 19 |
"loss": 3.396,
|
| 20 |
"step": 2
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.43,
|
| 24 |
-
"learning_rate": 4.
|
| 25 |
-
"loss": 2.
|
| 26 |
"step": 3
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.57,
|
| 30 |
-
"learning_rate": 4.
|
| 31 |
-
"loss": 2.
|
| 32 |
"step": 4
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.71,
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 2.
|
| 38 |
"step": 5
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.86,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 2.
|
| 44 |
"step": 6
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 1.0,
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 3.
|
| 50 |
"step": 7
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 1.14,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 2.
|
| 56 |
"step": 8
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 1.29,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 2.
|
| 62 |
"step": 9
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 1.43,
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 2.
|
| 68 |
"step": 10
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 1.57,
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 2.
|
| 74 |
"step": 11
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 1.71,
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 2.
|
| 80 |
"step": 12
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 1.86,
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 2.
|
| 86 |
"step": 13
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 2.0,
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 2.
|
| 92 |
"step": 14
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 2.14,
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 2.
|
| 98 |
"step": 15
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 2.29,
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 2.
|
| 104 |
"step": 16
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 2.43,
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 2.
|
| 110 |
"step": 17
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 2.57,
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 2.
|
| 116 |
"step": 18
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 2.71,
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 2.
|
| 122 |
"step": 19
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 2.86,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 2.
|
| 128 |
"step": 20
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 3.0,
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 2.
|
| 134 |
"step": 21
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 3.
|
| 138 |
-
"
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 144 |
}
|
| 145 |
],
|
| 146 |
-
"max_steps":
|
| 147 |
-
"num_train_epochs":
|
| 148 |
-
"total_flos":
|
| 149 |
"trial_name": null,
|
| 150 |
"trial_params": null
|
| 151 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 70,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.14,
|
| 12 |
+
"learning_rate": 4.928571428571429e-05,
|
| 13 |
"loss": 3.0215,
|
| 14 |
"step": 1
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.29,
|
| 18 |
+
"learning_rate": 4.8571428571428576e-05,
|
| 19 |
"loss": 3.396,
|
| 20 |
"step": 2
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.43,
|
| 24 |
+
"learning_rate": 4.785714285714286e-05,
|
| 25 |
+
"loss": 2.7081,
|
| 26 |
"step": 3
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.57,
|
| 30 |
+
"learning_rate": 4.714285714285714e-05,
|
| 31 |
+
"loss": 2.81,
|
| 32 |
"step": 4
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.71,
|
| 36 |
+
"learning_rate": 4.642857142857143e-05,
|
| 37 |
+
"loss": 2.7994,
|
| 38 |
"step": 5
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.86,
|
| 42 |
+
"learning_rate": 4.5714285714285716e-05,
|
| 43 |
+
"loss": 2.5904,
|
| 44 |
"step": 6
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 1.0,
|
| 48 |
+
"learning_rate": 4.5e-05,
|
| 49 |
+
"loss": 3.1253,
|
| 50 |
"step": 7
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 1.14,
|
| 54 |
+
"learning_rate": 4.428571428571428e-05,
|
| 55 |
+
"loss": 2.7843,
|
| 56 |
"step": 8
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 1.29,
|
| 60 |
+
"learning_rate": 4.3571428571428576e-05,
|
| 61 |
+
"loss": 2.6066,
|
| 62 |
"step": 9
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 1.43,
|
| 66 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 67 |
+
"loss": 2.6174,
|
| 68 |
"step": 10
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 1.57,
|
| 72 |
+
"learning_rate": 4.214285714285714e-05,
|
| 73 |
+
"loss": 2.619,
|
| 74 |
"step": 11
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 1.71,
|
| 78 |
+
"learning_rate": 4.1428571428571437e-05,
|
| 79 |
+
"loss": 2.7048,
|
| 80 |
"step": 12
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 1.86,
|
| 84 |
+
"learning_rate": 4.0714285714285717e-05,
|
| 85 |
+
"loss": 2.5045,
|
| 86 |
"step": 13
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 2.0,
|
| 90 |
+
"learning_rate": 4e-05,
|
| 91 |
+
"loss": 2.6195,
|
| 92 |
"step": 14
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 2.14,
|
| 96 |
+
"learning_rate": 3.928571428571429e-05,
|
| 97 |
+
"loss": 2.276,
|
| 98 |
"step": 15
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 2.29,
|
| 102 |
+
"learning_rate": 3.857142857142858e-05,
|
| 103 |
+
"loss": 2.4503,
|
| 104 |
"step": 16
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 2.43,
|
| 108 |
+
"learning_rate": 3.785714285714286e-05,
|
| 109 |
+
"loss": 2.5767,
|
| 110 |
"step": 17
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 2.57,
|
| 114 |
+
"learning_rate": 3.7142857142857143e-05,
|
| 115 |
+
"loss": 2.4256,
|
| 116 |
"step": 18
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 2.71,
|
| 120 |
+
"learning_rate": 3.642857142857143e-05,
|
| 121 |
+
"loss": 2.6956,
|
| 122 |
"step": 19
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 2.86,
|
| 126 |
+
"learning_rate": 3.571428571428572e-05,
|
| 127 |
+
"loss": 2.5666,
|
| 128 |
"step": 20
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 3.0,
|
| 132 |
+
"learning_rate": 3.5e-05,
|
| 133 |
+
"loss": 2.5238,
|
| 134 |
"step": 21
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 3.14,
|
| 138 |
+
"learning_rate": 3.428571428571429e-05,
|
| 139 |
+
"loss": 2.4623,
|
| 140 |
+
"step": 22
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.29,
|
| 144 |
+
"learning_rate": 3.357142857142857e-05,
|
| 145 |
+
"loss": 2.5452,
|
| 146 |
+
"step": 23
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.43,
|
| 150 |
+
"learning_rate": 3.285714285714286e-05,
|
| 151 |
+
"loss": 2.4905,
|
| 152 |
+
"step": 24
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.57,
|
| 156 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 157 |
+
"loss": 2.5106,
|
| 158 |
+
"step": 25
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.71,
|
| 162 |
+
"learning_rate": 3.142857142857143e-05,
|
| 163 |
+
"loss": 2.2134,
|
| 164 |
+
"step": 26
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.86,
|
| 168 |
+
"learning_rate": 3.071428571428572e-05,
|
| 169 |
+
"loss": 2.3214,
|
| 170 |
+
"step": 27
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.0,
|
| 174 |
+
"learning_rate": 3e-05,
|
| 175 |
+
"loss": 1.8621,
|
| 176 |
+
"step": 28
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.14,
|
| 180 |
+
"learning_rate": 2.9285714285714288e-05,
|
| 181 |
+
"loss": 2.4828,
|
| 182 |
+
"step": 29
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.29,
|
| 186 |
+
"learning_rate": 2.857142857142857e-05,
|
| 187 |
+
"loss": 2.3785,
|
| 188 |
+
"step": 30
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.43,
|
| 192 |
+
"learning_rate": 2.785714285714286e-05,
|
| 193 |
+
"loss": 2.2715,
|
| 194 |
+
"step": 31
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.57,
|
| 198 |
+
"learning_rate": 2.714285714285714e-05,
|
| 199 |
+
"loss": 2.1797,
|
| 200 |
+
"step": 32
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.71,
|
| 204 |
+
"learning_rate": 2.642857142857143e-05,
|
| 205 |
+
"loss": 2.22,
|
| 206 |
+
"step": 33
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.86,
|
| 210 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 211 |
+
"loss": 2.4549,
|
| 212 |
+
"step": 34
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 5.0,
|
| 216 |
+
"learning_rate": 2.5e-05,
|
| 217 |
+
"loss": 2.207,
|
| 218 |
+
"step": 35
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 5.14,
|
| 222 |
+
"learning_rate": 2.4285714285714288e-05,
|
| 223 |
+
"loss": 2.3845,
|
| 224 |
+
"step": 36
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 5.29,
|
| 228 |
+
"learning_rate": 2.357142857142857e-05,
|
| 229 |
+
"loss": 2.2862,
|
| 230 |
+
"step": 37
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.43,
|
| 234 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 235 |
+
"loss": 2.2408,
|
| 236 |
+
"step": 38
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 5.57,
|
| 240 |
+
"learning_rate": 2.214285714285714e-05,
|
| 241 |
+
"loss": 2.4339,
|
| 242 |
+
"step": 39
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 5.71,
|
| 246 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 247 |
+
"loss": 1.9903,
|
| 248 |
+
"step": 40
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 5.86,
|
| 252 |
+
"learning_rate": 2.0714285714285718e-05,
|
| 253 |
+
"loss": 2.2583,
|
| 254 |
+
"step": 41
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 6.0,
|
| 258 |
+
"learning_rate": 2e-05,
|
| 259 |
+
"loss": 2.6031,
|
| 260 |
+
"step": 42
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 6.14,
|
| 264 |
+
"learning_rate": 1.928571428571429e-05,
|
| 265 |
+
"loss": 2.1461,
|
| 266 |
+
"step": 43
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.29,
|
| 270 |
+
"learning_rate": 1.8571428571428572e-05,
|
| 271 |
+
"loss": 2.1812,
|
| 272 |
+
"step": 44
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 6.43,
|
| 276 |
+
"learning_rate": 1.785714285714286e-05,
|
| 277 |
+
"loss": 2.1179,
|
| 278 |
+
"step": 45
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 6.57,
|
| 282 |
+
"learning_rate": 1.7142857142857145e-05,
|
| 283 |
+
"loss": 2.3383,
|
| 284 |
+
"step": 46
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.71,
|
| 288 |
+
"learning_rate": 1.642857142857143e-05,
|
| 289 |
+
"loss": 2.3931,
|
| 290 |
+
"step": 47
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.86,
|
| 294 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 295 |
+
"loss": 2.1934,
|
| 296 |
+
"step": 48
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.0,
|
| 300 |
+
"learning_rate": 1.5e-05,
|
| 301 |
+
"loss": 2.189,
|
| 302 |
+
"step": 49
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 7.14,
|
| 306 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 307 |
+
"loss": 2.0834,
|
| 308 |
+
"step": 50
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 7.29,
|
| 312 |
+
"learning_rate": 1.357142857142857e-05,
|
| 313 |
+
"loss": 2.1371,
|
| 314 |
+
"step": 51
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 7.43,
|
| 318 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 319 |
+
"loss": 2.0772,
|
| 320 |
+
"step": 52
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 7.57,
|
| 324 |
+
"learning_rate": 1.2142857142857144e-05,
|
| 325 |
+
"loss": 2.3063,
|
| 326 |
+
"step": 53
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 7.71,
|
| 330 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 331 |
+
"loss": 2.2691,
|
| 332 |
+
"step": 54
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 7.86,
|
| 336 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 337 |
+
"loss": 2.2412,
|
| 338 |
+
"step": 55
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 8.0,
|
| 342 |
+
"learning_rate": 1e-05,
|
| 343 |
+
"loss": 2.5235,
|
| 344 |
+
"step": 56
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 8.14,
|
| 348 |
+
"learning_rate": 9.285714285714286e-06,
|
| 349 |
+
"loss": 2.239,
|
| 350 |
+
"step": 57
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 8.29,
|
| 354 |
+
"learning_rate": 8.571428571428573e-06,
|
| 355 |
+
"loss": 2.1908,
|
| 356 |
+
"step": 58
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 8.43,
|
| 360 |
+
"learning_rate": 7.857142857142858e-06,
|
| 361 |
+
"loss": 2.1594,
|
| 362 |
+
"step": 59
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 8.57,
|
| 366 |
+
"learning_rate": 7.142857142857143e-06,
|
| 367 |
+
"loss": 2.2055,
|
| 368 |
+
"step": 60
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 8.71,
|
| 372 |
+
"learning_rate": 6.428571428571429e-06,
|
| 373 |
+
"loss": 1.975,
|
| 374 |
+
"step": 61
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 8.86,
|
| 378 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 379 |
+
"loss": 2.2883,
|
| 380 |
+
"step": 62
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 9.0,
|
| 384 |
+
"learning_rate": 5e-06,
|
| 385 |
+
"loss": 1.9735,
|
| 386 |
+
"step": 63
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 9.14,
|
| 390 |
+
"learning_rate": 4.285714285714286e-06,
|
| 391 |
+
"loss": 2.189,
|
| 392 |
+
"step": 64
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 9.29,
|
| 396 |
+
"learning_rate": 3.5714285714285714e-06,
|
| 397 |
+
"loss": 2.3047,
|
| 398 |
+
"step": 65
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 9.43,
|
| 402 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 403 |
+
"loss": 1.908,
|
| 404 |
+
"step": 66
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 9.57,
|
| 408 |
+
"learning_rate": 2.142857142857143e-06,
|
| 409 |
+
"loss": 2.0436,
|
| 410 |
+
"step": 67
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 9.71,
|
| 414 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 415 |
+
"loss": 2.2566,
|
| 416 |
+
"step": 68
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 9.86,
|
| 420 |
+
"learning_rate": 7.142857142857143e-07,
|
| 421 |
+
"loss": 2.2008,
|
| 422 |
+
"step": 69
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 10.0,
|
| 426 |
+
"learning_rate": 0.0,
|
| 427 |
+
"loss": 2.3549,
|
| 428 |
+
"step": 70
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 10.0,
|
| 432 |
+
"step": 70,
|
| 433 |
+
"total_flos": 256066191360000.0,
|
| 434 |
+
"train_loss": 2.381487710135324,
|
| 435 |
+
"train_runtime": 18.165,
|
| 436 |
+
"train_samples_per_second": 26.975,
|
| 437 |
+
"train_steps_per_second": 3.854
|
| 438 |
}
|
| 439 |
],
|
| 440 |
+
"max_steps": 70,
|
| 441 |
+
"num_train_epochs": 10,
|
| 442 |
+
"total_flos": 256066191360000.0,
|
| 443 |
"trial_name": null,
|
| 444 |
"trial_params": null
|
| 445 |
}
|