End of training
Browse files- all_results.json +18 -18
- eval_results.json +7 -7
- generated_predictions.txt +0 -0
- predict_results.json +6 -6
- runs/May25_21-59-23_1733356bae24/events.out.tfevents.1685073147.1733356bae24.77485.2 +3 -0
- train_results.json +6 -6
- trainer_state.json +1402 -76
all_results.json
CHANGED
|
@@ -1,23 +1,23 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_bleu":
|
| 4 |
-
"eval_gen_len":
|
| 5 |
-
"eval_loss":
|
| 6 |
-
"eval_runtime":
|
| 7 |
"eval_samples": 785,
|
| 8 |
-
"eval_samples_per_second": 5.
|
| 9 |
-
"eval_steps_per_second": 0.
|
| 10 |
-
"predict_bleu":
|
| 11 |
-
"predict_gen_len":
|
| 12 |
-
"predict_loss":
|
| 13 |
-
"predict_runtime":
|
| 14 |
"predict_samples": 785,
|
| 15 |
-
"predict_samples_per_second": 5.
|
| 16 |
-
"predict_steps_per_second": 0.
|
| 17 |
-
"total_flos": 2.232877359218688e+
|
| 18 |
-
"train_loss": 0.
|
| 19 |
-
"train_runtime":
|
| 20 |
"train_samples": 6279,
|
| 21 |
-
"train_samples_per_second": 30.
|
| 22 |
-
"train_steps_per_second": 1.
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_bleu": 14.8412,
|
| 4 |
+
"eval_gen_len": 98.6675,
|
| 5 |
+
"eval_loss": 1.0916588306427002,
|
| 6 |
+
"eval_runtime": 134.8299,
|
| 7 |
"eval_samples": 785,
|
| 8 |
+
"eval_samples_per_second": 5.822,
|
| 9 |
+
"eval_steps_per_second": 0.371,
|
| 10 |
+
"predict_bleu": 14.3233,
|
| 11 |
+
"predict_gen_len": 98.2013,
|
| 12 |
+
"predict_loss": 1.0994350910186768,
|
| 13 |
+
"predict_runtime": 133.0351,
|
| 14 |
"predict_samples": 785,
|
| 15 |
+
"predict_samples_per_second": 5.901,
|
| 16 |
+
"predict_steps_per_second": 0.376,
|
| 17 |
+
"total_flos": 2.232877359218688e+17,
|
| 18 |
+
"train_loss": 0.3279189860123108,
|
| 19 |
+
"train_runtime": 20714.0027,
|
| 20 |
"train_samples": 6279,
|
| 21 |
+
"train_samples_per_second": 30.313,
|
| 22 |
+
"train_steps_per_second": 1.897
|
| 23 |
}
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_bleu":
|
| 4 |
-
"eval_gen_len":
|
| 5 |
-
"eval_loss":
|
| 6 |
-
"eval_runtime":
|
| 7 |
"eval_samples": 785,
|
| 8 |
-
"eval_samples_per_second": 5.
|
| 9 |
-
"eval_steps_per_second": 0.
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_bleu": 14.8412,
|
| 4 |
+
"eval_gen_len": 98.6675,
|
| 5 |
+
"eval_loss": 1.0916588306427002,
|
| 6 |
+
"eval_runtime": 134.8299,
|
| 7 |
"eval_samples": 785,
|
| 8 |
+
"eval_samples_per_second": 5.822,
|
| 9 |
+
"eval_steps_per_second": 0.371
|
| 10 |
}
|
generated_predictions.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
predict_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"predict_bleu":
|
| 3 |
-
"predict_gen_len":
|
| 4 |
-
"predict_loss":
|
| 5 |
-
"predict_runtime":
|
| 6 |
"predict_samples": 785,
|
| 7 |
-
"predict_samples_per_second": 5.
|
| 8 |
-
"predict_steps_per_second": 0.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"predict_bleu": 14.3233,
|
| 3 |
+
"predict_gen_len": 98.2013,
|
| 4 |
+
"predict_loss": 1.0994350910186768,
|
| 5 |
+
"predict_runtime": 133.0351,
|
| 6 |
"predict_samples": 785,
|
| 7 |
+
"predict_samples_per_second": 5.901,
|
| 8 |
+
"predict_steps_per_second": 0.376
|
| 9 |
}
|
runs/May25_21-59-23_1733356bae24/events.out.tfevents.1685073147.1733356bae24.77485.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9422907d6a6a69cf94501692003b1ee320edf55be0778d9e8ae39fc2bee0c4f9
|
| 3 |
+
size 465
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 2.232877359218688e+
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 6279,
|
| 7 |
-
"train_samples_per_second": 30.
|
| 8 |
-
"train_steps_per_second": 1.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"total_flos": 2.232877359218688e+17,
|
| 4 |
+
"train_loss": 0.3279189860123108,
|
| 5 |
+
"train_runtime": 20714.0027,
|
| 6 |
"train_samples": 6279,
|
| 7 |
+
"train_samples_per_second": 30.313,
|
| 8 |
+
"train_steps_per_second": 1.897
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,167 +1,1493 @@
|
|
| 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": 1.0,
|
| 12 |
-
"eval_bleu": 0.
|
| 13 |
"eval_gen_len": 19.0,
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_runtime":
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second": 1.
|
| 18 |
"step": 393
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.27,
|
| 22 |
-
"learning_rate": 4.
|
| 23 |
-
"loss": 1.
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"eval_bleu": 0.
|
| 29 |
"eval_gen_len": 19.0,
|
| 30 |
-
"eval_loss": 0.
|
| 31 |
-
"eval_runtime":
|
| 32 |
-
"eval_samples_per_second":
|
| 33 |
-
"eval_steps_per_second": 1.
|
| 34 |
"step": 786
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 2.54,
|
| 38 |
-
"learning_rate":
|
| 39 |
-
"loss": 1.
|
| 40 |
"step": 1000
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 3.0,
|
| 44 |
-
"eval_bleu": 0.
|
| 45 |
"eval_gen_len": 19.0,
|
| 46 |
-
"eval_loss": 0.
|
| 47 |
-
"eval_runtime":
|
| 48 |
-
"eval_samples_per_second":
|
| 49 |
-
"eval_steps_per_second": 1.
|
| 50 |
"step": 1179
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 3.82,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 1500
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 4.0,
|
| 60 |
-
"eval_bleu": 0.
|
| 61 |
"eval_gen_len": 19.0,
|
| 62 |
-
"eval_loss": 0.
|
| 63 |
-
"eval_runtime":
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second": 1.
|
| 66 |
"step": 1572
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 5.0,
|
| 70 |
-
"eval_bleu": 0.
|
| 71 |
"eval_gen_len": 19.0,
|
| 72 |
-
"eval_loss": 0.
|
| 73 |
-
"eval_runtime":
|
| 74 |
-
"eval_samples_per_second":
|
| 75 |
-
"eval_steps_per_second": 1.
|
| 76 |
"step": 1965
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 5.09,
|
| 80 |
-
"learning_rate":
|
| 81 |
-
"loss": 0.
|
| 82 |
"step": 2000
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 6.0,
|
| 86 |
-
"eval_bleu": 0.
|
| 87 |
"eval_gen_len": 19.0,
|
| 88 |
-
"eval_loss": 0.
|
| 89 |
-
"eval_runtime":
|
| 90 |
-
"eval_samples_per_second":
|
| 91 |
-
"eval_steps_per_second": 1.
|
| 92 |
"step": 2358
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 6.36,
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 2500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 7.0,
|
| 102 |
-
"eval_bleu": 0.
|
| 103 |
"eval_gen_len": 19.0,
|
| 104 |
-
"eval_loss": 0.
|
| 105 |
-
"eval_runtime":
|
| 106 |
-
"eval_samples_per_second":
|
| 107 |
-
"eval_steps_per_second": 1.
|
| 108 |
"step": 2751
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 7.63,
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 3000
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 8.0,
|
| 118 |
-
"eval_bleu": 0.
|
| 119 |
"eval_gen_len": 19.0,
|
| 120 |
-
"eval_loss": 0.
|
| 121 |
-
"eval_runtime":
|
| 122 |
-
"eval_samples_per_second":
|
| 123 |
-
"eval_steps_per_second": 1.
|
| 124 |
"step": 3144
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 8.91,
|
| 128 |
-
"learning_rate":
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 3500
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 9.0,
|
| 134 |
-
"eval_bleu": 0.
|
| 135 |
"eval_gen_len": 19.0,
|
| 136 |
-
"eval_loss": 0.
|
| 137 |
-
"eval_runtime":
|
| 138 |
-
"eval_samples_per_second":
|
| 139 |
-
"eval_steps_per_second": 1.
|
| 140 |
"step": 3537
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 10.0,
|
| 144 |
-
"eval_bleu": 0.
|
| 145 |
"eval_gen_len": 19.0,
|
| 146 |
-
"eval_loss": 0.
|
| 147 |
-
"eval_runtime":
|
| 148 |
-
"eval_samples_per_second":
|
| 149 |
-
"eval_steps_per_second": 1.
|
| 150 |
"step": 3930
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch": 10.
|
| 154 |
-
"
|
| 155 |
-
"
|
| 156 |
-
"
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 160 |
}
|
| 161 |
],
|
| 162 |
-
"max_steps":
|
| 163 |
-
"num_train_epochs":
|
| 164 |
-
"total_flos": 2.232877359218688e+
|
| 165 |
"trial_name": null,
|
| 166 |
"trial_params": null
|
| 167 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"global_step": 39300,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
+
"eval_bleu": 0.0473,
|
| 13 |
"eval_gen_len": 19.0,
|
| 14 |
+
"eval_loss": 1.034566044807434,
|
| 15 |
+
"eval_runtime": 35.414,
|
| 16 |
+
"eval_samples_per_second": 22.166,
|
| 17 |
+
"eval_steps_per_second": 1.412,
|
| 18 |
"step": 393
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.27,
|
| 22 |
+
"learning_rate": 4.936386768447838e-05,
|
| 23 |
+
"loss": 1.5209,
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"eval_bleu": 0.1413,
|
| 29 |
"eval_gen_len": 19.0,
|
| 30 |
+
"eval_loss": 0.8939195275306702,
|
| 31 |
+
"eval_runtime": 35.4148,
|
| 32 |
+
"eval_samples_per_second": 22.166,
|
| 33 |
+
"eval_steps_per_second": 1.412,
|
| 34 |
"step": 786
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 2.54,
|
| 38 |
+
"learning_rate": 4.8727735368956744e-05,
|
| 39 |
+
"loss": 1.0258,
|
| 40 |
"step": 1000
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 3.0,
|
| 44 |
+
"eval_bleu": 0.1641,
|
| 45 |
"eval_gen_len": 19.0,
|
| 46 |
+
"eval_loss": 0.8333808779716492,
|
| 47 |
+
"eval_runtime": 35.2354,
|
| 48 |
+
"eval_samples_per_second": 22.279,
|
| 49 |
+
"eval_steps_per_second": 1.419,
|
| 50 |
"step": 1179
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 3.82,
|
| 54 |
+
"learning_rate": 4.809160305343512e-05,
|
| 55 |
+
"loss": 0.9177,
|
| 56 |
"step": 1500
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 4.0,
|
| 60 |
+
"eval_bleu": 0.1729,
|
| 61 |
"eval_gen_len": 19.0,
|
| 62 |
+
"eval_loss": 0.7867220044136047,
|
| 63 |
+
"eval_runtime": 35.207,
|
| 64 |
+
"eval_samples_per_second": 22.297,
|
| 65 |
+
"eval_steps_per_second": 1.42,
|
| 66 |
"step": 1572
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 5.0,
|
| 70 |
+
"eval_bleu": 0.1742,
|
| 71 |
"eval_gen_len": 19.0,
|
| 72 |
+
"eval_loss": 0.7542837858200073,
|
| 73 |
+
"eval_runtime": 35.3809,
|
| 74 |
+
"eval_samples_per_second": 22.187,
|
| 75 |
+
"eval_steps_per_second": 1.413,
|
| 76 |
"step": 1965
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 5.09,
|
| 80 |
+
"learning_rate": 4.7455470737913485e-05,
|
| 81 |
+
"loss": 0.8482,
|
| 82 |
"step": 2000
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 6.0,
|
| 86 |
+
"eval_bleu": 0.1692,
|
| 87 |
"eval_gen_len": 19.0,
|
| 88 |
+
"eval_loss": 0.7316721677780151,
|
| 89 |
+
"eval_runtime": 35.4956,
|
| 90 |
+
"eval_samples_per_second": 22.115,
|
| 91 |
+
"eval_steps_per_second": 1.409,
|
| 92 |
"step": 2358
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 6.36,
|
| 96 |
+
"learning_rate": 4.681933842239186e-05,
|
| 97 |
+
"loss": 0.7957,
|
| 98 |
"step": 2500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 7.0,
|
| 102 |
+
"eval_bleu": 0.1742,
|
| 103 |
"eval_gen_len": 19.0,
|
| 104 |
+
"eval_loss": 0.7106090188026428,
|
| 105 |
+
"eval_runtime": 35.1034,
|
| 106 |
+
"eval_samples_per_second": 22.362,
|
| 107 |
+
"eval_steps_per_second": 1.424,
|
| 108 |
"step": 2751
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 7.63,
|
| 112 |
+
"learning_rate": 4.618320610687023e-05,
|
| 113 |
+
"loss": 0.7557,
|
| 114 |
"step": 3000
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 8.0,
|
| 118 |
+
"eval_bleu": 0.216,
|
| 119 |
"eval_gen_len": 19.0,
|
| 120 |
+
"eval_loss": 0.6849327087402344,
|
| 121 |
+
"eval_runtime": 35.4066,
|
| 122 |
+
"eval_samples_per_second": 22.171,
|
| 123 |
+
"eval_steps_per_second": 1.412,
|
| 124 |
"step": 3144
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 8.91,
|
| 128 |
+
"learning_rate": 4.5547073791348604e-05,
|
| 129 |
+
"loss": 0.7204,
|
| 130 |
"step": 3500
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 9.0,
|
| 134 |
+
"eval_bleu": 0.189,
|
| 135 |
"eval_gen_len": 19.0,
|
| 136 |
+
"eval_loss": 0.6731250882148743,
|
| 137 |
+
"eval_runtime": 35.3153,
|
| 138 |
+
"eval_samples_per_second": 22.228,
|
| 139 |
+
"eval_steps_per_second": 1.416,
|
| 140 |
"step": 3537
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 10.0,
|
| 144 |
+
"eval_bleu": 0.2063,
|
| 145 |
"eval_gen_len": 19.0,
|
| 146 |
+
"eval_loss": 0.6562144160270691,
|
| 147 |
+
"eval_runtime": 35.358,
|
| 148 |
+
"eval_samples_per_second": 22.201,
|
| 149 |
+
"eval_steps_per_second": 1.414,
|
| 150 |
"step": 3930
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 10.18,
|
| 154 |
+
"learning_rate": 4.4910941475826975e-05,
|
| 155 |
+
"loss": 0.6901,
|
| 156 |
+
"step": 4000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 11.0,
|
| 160 |
+
"eval_bleu": 0.2025,
|
| 161 |
+
"eval_gen_len": 19.0,
|
| 162 |
+
"eval_loss": 0.6510306596755981,
|
| 163 |
+
"eval_runtime": 35.1746,
|
| 164 |
+
"eval_samples_per_second": 22.317,
|
| 165 |
+
"eval_steps_per_second": 1.421,
|
| 166 |
+
"step": 4323
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 11.45,
|
| 170 |
+
"learning_rate": 4.4274809160305345e-05,
|
| 171 |
+
"loss": 0.6635,
|
| 172 |
+
"step": 4500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 12.0,
|
| 176 |
+
"eval_bleu": 0.2266,
|
| 177 |
+
"eval_gen_len": 19.0,
|
| 178 |
+
"eval_loss": 0.6423279047012329,
|
| 179 |
+
"eval_runtime": 34.9781,
|
| 180 |
+
"eval_samples_per_second": 22.443,
|
| 181 |
+
"eval_steps_per_second": 1.429,
|
| 182 |
+
"step": 4716
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 12.72,
|
| 186 |
+
"learning_rate": 4.3638676844783716e-05,
|
| 187 |
+
"loss": 0.6346,
|
| 188 |
+
"step": 5000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 13.0,
|
| 192 |
+
"eval_bleu": 0.2229,
|
| 193 |
+
"eval_gen_len": 19.0,
|
| 194 |
+
"eval_loss": 0.6330356597900391,
|
| 195 |
+
"eval_runtime": 35.0795,
|
| 196 |
+
"eval_samples_per_second": 22.378,
|
| 197 |
+
"eval_steps_per_second": 1.425,
|
| 198 |
+
"step": 5109
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 13.99,
|
| 202 |
+
"learning_rate": 4.300254452926209e-05,
|
| 203 |
+
"loss": 0.6132,
|
| 204 |
+
"step": 5500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 14.0,
|
| 208 |
+
"eval_bleu": 0.2195,
|
| 209 |
+
"eval_gen_len": 19.0,
|
| 210 |
+
"eval_loss": 0.6257367134094238,
|
| 211 |
+
"eval_runtime": 34.9799,
|
| 212 |
+
"eval_samples_per_second": 22.441,
|
| 213 |
+
"eval_steps_per_second": 1.429,
|
| 214 |
+
"step": 5502
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 15.0,
|
| 218 |
+
"eval_bleu": 0.2344,
|
| 219 |
+
"eval_gen_len": 19.0,
|
| 220 |
+
"eval_loss": 0.6191786527633667,
|
| 221 |
+
"eval_runtime": 35.2808,
|
| 222 |
+
"eval_samples_per_second": 22.25,
|
| 223 |
+
"eval_steps_per_second": 1.417,
|
| 224 |
+
"step": 5895
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 15.27,
|
| 228 |
+
"learning_rate": 4.236641221374046e-05,
|
| 229 |
+
"loss": 0.5885,
|
| 230 |
+
"step": 6000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 16.0,
|
| 234 |
+
"eval_bleu": 0.2424,
|
| 235 |
+
"eval_gen_len": 19.0,
|
| 236 |
+
"eval_loss": 0.6103959083557129,
|
| 237 |
+
"eval_runtime": 35.1057,
|
| 238 |
+
"eval_samples_per_second": 22.361,
|
| 239 |
+
"eval_steps_per_second": 1.424,
|
| 240 |
+
"step": 6288
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 16.54,
|
| 244 |
+
"learning_rate": 4.1730279898218835e-05,
|
| 245 |
+
"loss": 0.5682,
|
| 246 |
+
"step": 6500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 17.0,
|
| 250 |
+
"eval_bleu": 0.2536,
|
| 251 |
+
"eval_gen_len": 19.0,
|
| 252 |
+
"eval_loss": 0.6047710180282593,
|
| 253 |
+
"eval_runtime": 35.079,
|
| 254 |
+
"eval_samples_per_second": 22.378,
|
| 255 |
+
"eval_steps_per_second": 1.425,
|
| 256 |
+
"step": 6681
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 17.81,
|
| 260 |
+
"learning_rate": 4.10941475826972e-05,
|
| 261 |
+
"loss": 0.5452,
|
| 262 |
+
"step": 7000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 18.0,
|
| 266 |
+
"eval_bleu": 0.2541,
|
| 267 |
+
"eval_gen_len": 19.0,
|
| 268 |
+
"eval_loss": 0.6057348847389221,
|
| 269 |
+
"eval_runtime": 35.3873,
|
| 270 |
+
"eval_samples_per_second": 22.183,
|
| 271 |
+
"eval_steps_per_second": 1.413,
|
| 272 |
+
"step": 7074
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 19.0,
|
| 276 |
+
"eval_bleu": 0.2526,
|
| 277 |
+
"eval_gen_len": 19.0,
|
| 278 |
+
"eval_loss": 0.6047215461730957,
|
| 279 |
+
"eval_runtime": 35.004,
|
| 280 |
+
"eval_samples_per_second": 22.426,
|
| 281 |
+
"eval_steps_per_second": 1.428,
|
| 282 |
+
"step": 7467
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 19.08,
|
| 286 |
+
"learning_rate": 4.0458015267175576e-05,
|
| 287 |
+
"loss": 0.5294,
|
| 288 |
+
"step": 7500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 20.0,
|
| 292 |
+
"eval_bleu": 0.2644,
|
| 293 |
+
"eval_gen_len": 19.0,
|
| 294 |
+
"eval_loss": 0.6065888404846191,
|
| 295 |
+
"eval_runtime": 35.2375,
|
| 296 |
+
"eval_samples_per_second": 22.277,
|
| 297 |
+
"eval_steps_per_second": 1.419,
|
| 298 |
+
"step": 7860
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 20.36,
|
| 302 |
+
"learning_rate": 3.982188295165395e-05,
|
| 303 |
+
"loss": 0.5072,
|
| 304 |
+
"step": 8000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 21.0,
|
| 308 |
+
"eval_bleu": 0.2666,
|
| 309 |
+
"eval_gen_len": 19.0,
|
| 310 |
+
"eval_loss": 0.6080436706542969,
|
| 311 |
+
"eval_runtime": 35.085,
|
| 312 |
+
"eval_samples_per_second": 22.374,
|
| 313 |
+
"eval_steps_per_second": 1.425,
|
| 314 |
+
"step": 8253
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 21.63,
|
| 318 |
+
"learning_rate": 3.918575063613232e-05,
|
| 319 |
+
"loss": 0.4921,
|
| 320 |
+
"step": 8500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 22.0,
|
| 324 |
+
"eval_bleu": 0.2499,
|
| 325 |
+
"eval_gen_len": 19.0,
|
| 326 |
+
"eval_loss": 0.6091626882553101,
|
| 327 |
+
"eval_runtime": 35.0913,
|
| 328 |
+
"eval_samples_per_second": 22.37,
|
| 329 |
+
"eval_steps_per_second": 1.425,
|
| 330 |
+
"step": 8646
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 22.9,
|
| 334 |
+
"learning_rate": 3.854961832061069e-05,
|
| 335 |
+
"loss": 0.4753,
|
| 336 |
+
"step": 9000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 23.0,
|
| 340 |
+
"eval_bleu": 0.2719,
|
| 341 |
+
"eval_gen_len": 19.0,
|
| 342 |
+
"eval_loss": 0.6132063269615173,
|
| 343 |
+
"eval_runtime": 35.0981,
|
| 344 |
+
"eval_samples_per_second": 22.366,
|
| 345 |
+
"eval_steps_per_second": 1.425,
|
| 346 |
+
"step": 9039
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 24.0,
|
| 350 |
+
"eval_bleu": 0.2724,
|
| 351 |
+
"eval_gen_len": 19.0,
|
| 352 |
+
"eval_loss": 0.6088494658470154,
|
| 353 |
+
"eval_runtime": 35.1025,
|
| 354 |
+
"eval_samples_per_second": 22.363,
|
| 355 |
+
"eval_steps_per_second": 1.424,
|
| 356 |
+
"step": 9432
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 24.17,
|
| 360 |
+
"learning_rate": 3.791348600508906e-05,
|
| 361 |
+
"loss": 0.4597,
|
| 362 |
+
"step": 9500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 25.0,
|
| 366 |
+
"eval_bleu": 0.2683,
|
| 367 |
+
"eval_gen_len": 19.0,
|
| 368 |
+
"eval_loss": 0.6127578020095825,
|
| 369 |
+
"eval_runtime": 35.0847,
|
| 370 |
+
"eval_samples_per_second": 22.374,
|
| 371 |
+
"eval_steps_per_second": 1.425,
|
| 372 |
+
"step": 9825
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 25.45,
|
| 376 |
+
"learning_rate": 3.727735368956743e-05,
|
| 377 |
+
"loss": 0.4443,
|
| 378 |
+
"step": 10000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 26.0,
|
| 382 |
+
"eval_bleu": 0.2856,
|
| 383 |
+
"eval_gen_len": 19.0,
|
| 384 |
+
"eval_loss": 0.6183450818061829,
|
| 385 |
+
"eval_runtime": 35.0496,
|
| 386 |
+
"eval_samples_per_second": 22.397,
|
| 387 |
+
"eval_steps_per_second": 1.427,
|
| 388 |
+
"step": 10218
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 26.72,
|
| 392 |
+
"learning_rate": 3.66412213740458e-05,
|
| 393 |
+
"loss": 0.4301,
|
| 394 |
+
"step": 10500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 27.0,
|
| 398 |
+
"eval_bleu": 0.3006,
|
| 399 |
+
"eval_gen_len": 19.0,
|
| 400 |
+
"eval_loss": 0.6246443390846252,
|
| 401 |
+
"eval_runtime": 35.1774,
|
| 402 |
+
"eval_samples_per_second": 22.315,
|
| 403 |
+
"eval_steps_per_second": 1.421,
|
| 404 |
+
"step": 10611
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 27.99,
|
| 408 |
+
"learning_rate": 3.600508905852418e-05,
|
| 409 |
+
"loss": 0.418,
|
| 410 |
+
"step": 11000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 28.0,
|
| 414 |
+
"eval_bleu": 0.2788,
|
| 415 |
+
"eval_gen_len": 19.0,
|
| 416 |
+
"eval_loss": 0.6312348246574402,
|
| 417 |
+
"eval_runtime": 35.3395,
|
| 418 |
+
"eval_samples_per_second": 22.213,
|
| 419 |
+
"eval_steps_per_second": 1.415,
|
| 420 |
+
"step": 11004
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 29.0,
|
| 424 |
+
"eval_bleu": 0.2843,
|
| 425 |
+
"eval_gen_len": 19.0,
|
| 426 |
+
"eval_loss": 0.6295350790023804,
|
| 427 |
+
"eval_runtime": 35.2861,
|
| 428 |
+
"eval_samples_per_second": 22.247,
|
| 429 |
+
"eval_steps_per_second": 1.417,
|
| 430 |
+
"step": 11397
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 29.26,
|
| 434 |
+
"learning_rate": 3.536895674300255e-05,
|
| 435 |
+
"loss": 0.4002,
|
| 436 |
+
"step": 11500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 30.0,
|
| 440 |
+
"eval_bleu": 0.2982,
|
| 441 |
+
"eval_gen_len": 19.0,
|
| 442 |
+
"eval_loss": 0.6349673271179199,
|
| 443 |
+
"eval_runtime": 35.0212,
|
| 444 |
+
"eval_samples_per_second": 22.415,
|
| 445 |
+
"eval_steps_per_second": 1.428,
|
| 446 |
+
"step": 11790
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 30.53,
|
| 450 |
+
"learning_rate": 3.473282442748092e-05,
|
| 451 |
+
"loss": 0.3913,
|
| 452 |
+
"step": 12000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 31.0,
|
| 456 |
+
"eval_bleu": 0.2822,
|
| 457 |
+
"eval_gen_len": 19.0,
|
| 458 |
+
"eval_loss": 0.6441249847412109,
|
| 459 |
+
"eval_runtime": 35.0154,
|
| 460 |
+
"eval_samples_per_second": 22.419,
|
| 461 |
+
"eval_steps_per_second": 1.428,
|
| 462 |
+
"step": 12183
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 31.81,
|
| 466 |
+
"learning_rate": 3.409669211195929e-05,
|
| 467 |
+
"loss": 0.3755,
|
| 468 |
+
"step": 12500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 32.0,
|
| 472 |
+
"eval_bleu": 0.3215,
|
| 473 |
+
"eval_gen_len": 19.0,
|
| 474 |
+
"eval_loss": 0.6430069804191589,
|
| 475 |
+
"eval_runtime": 35.1225,
|
| 476 |
+
"eval_samples_per_second": 22.35,
|
| 477 |
+
"eval_steps_per_second": 1.424,
|
| 478 |
+
"step": 12576
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 33.0,
|
| 482 |
+
"eval_bleu": 0.3024,
|
| 483 |
+
"eval_gen_len": 19.0,
|
| 484 |
+
"eval_loss": 0.6485504508018494,
|
| 485 |
+
"eval_runtime": 35.0519,
|
| 486 |
+
"eval_samples_per_second": 22.395,
|
| 487 |
+
"eval_steps_per_second": 1.426,
|
| 488 |
+
"step": 12969
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 33.08,
|
| 492 |
+
"learning_rate": 3.346055979643766e-05,
|
| 493 |
+
"loss": 0.3673,
|
| 494 |
+
"step": 13000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 34.0,
|
| 498 |
+
"eval_bleu": 0.2985,
|
| 499 |
+
"eval_gen_len": 19.0,
|
| 500 |
+
"eval_loss": 0.6527048945426941,
|
| 501 |
+
"eval_runtime": 34.9946,
|
| 502 |
+
"eval_samples_per_second": 22.432,
|
| 503 |
+
"eval_steps_per_second": 1.429,
|
| 504 |
+
"step": 13362
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 34.35,
|
| 508 |
+
"learning_rate": 3.282442748091603e-05,
|
| 509 |
+
"loss": 0.352,
|
| 510 |
+
"step": 13500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 35.0,
|
| 514 |
+
"eval_bleu": 0.31,
|
| 515 |
+
"eval_gen_len": 19.0,
|
| 516 |
+
"eval_loss": 0.6660041213035583,
|
| 517 |
+
"eval_runtime": 34.9679,
|
| 518 |
+
"eval_samples_per_second": 22.449,
|
| 519 |
+
"eval_steps_per_second": 1.43,
|
| 520 |
+
"step": 13755
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 35.62,
|
| 524 |
+
"learning_rate": 3.21882951653944e-05,
|
| 525 |
+
"loss": 0.3408,
|
| 526 |
+
"step": 14000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 36.0,
|
| 530 |
+
"eval_bleu": 0.288,
|
| 531 |
+
"eval_gen_len": 19.0,
|
| 532 |
+
"eval_loss": 0.6737257838249207,
|
| 533 |
+
"eval_runtime": 35.0785,
|
| 534 |
+
"eval_samples_per_second": 22.378,
|
| 535 |
+
"eval_steps_per_second": 1.425,
|
| 536 |
+
"step": 14148
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 36.9,
|
| 540 |
+
"learning_rate": 3.155216284987277e-05,
|
| 541 |
+
"loss": 0.3307,
|
| 542 |
+
"step": 14500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 37.0,
|
| 546 |
+
"eval_bleu": 0.2995,
|
| 547 |
+
"eval_gen_len": 19.0,
|
| 548 |
+
"eval_loss": 0.6772977113723755,
|
| 549 |
+
"eval_runtime": 35.0227,
|
| 550 |
+
"eval_samples_per_second": 22.414,
|
| 551 |
+
"eval_steps_per_second": 1.428,
|
| 552 |
+
"step": 14541
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 38.0,
|
| 556 |
+
"eval_bleu": 0.29,
|
| 557 |
+
"eval_gen_len": 19.0,
|
| 558 |
+
"eval_loss": 0.6903324723243713,
|
| 559 |
+
"eval_runtime": 35.1225,
|
| 560 |
+
"eval_samples_per_second": 22.35,
|
| 561 |
+
"eval_steps_per_second": 1.424,
|
| 562 |
+
"step": 14934
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 38.17,
|
| 566 |
+
"learning_rate": 3.091603053435115e-05,
|
| 567 |
+
"loss": 0.3182,
|
| 568 |
+
"step": 15000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 39.0,
|
| 572 |
+
"eval_bleu": 0.2848,
|
| 573 |
+
"eval_gen_len": 19.0,
|
| 574 |
+
"eval_loss": 0.7059388160705566,
|
| 575 |
+
"eval_runtime": 34.9533,
|
| 576 |
+
"eval_samples_per_second": 22.459,
|
| 577 |
+
"eval_steps_per_second": 1.43,
|
| 578 |
+
"step": 15327
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 39.44,
|
| 582 |
+
"learning_rate": 3.0279898218829518e-05,
|
| 583 |
+
"loss": 0.3077,
|
| 584 |
+
"step": 15500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 40.0,
|
| 588 |
+
"eval_bleu": 0.2878,
|
| 589 |
+
"eval_gen_len": 19.0,
|
| 590 |
+
"eval_loss": 0.6985650658607483,
|
| 591 |
+
"eval_runtime": 35.0758,
|
| 592 |
+
"eval_samples_per_second": 22.38,
|
| 593 |
+
"eval_steps_per_second": 1.425,
|
| 594 |
+
"step": 15720
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 40.71,
|
| 598 |
+
"learning_rate": 2.9643765903307892e-05,
|
| 599 |
+
"loss": 0.298,
|
| 600 |
+
"step": 16000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 41.0,
|
| 604 |
+
"eval_bleu": 0.2859,
|
| 605 |
+
"eval_gen_len": 19.0,
|
| 606 |
+
"eval_loss": 0.7053300142288208,
|
| 607 |
+
"eval_runtime": 35.1562,
|
| 608 |
+
"eval_samples_per_second": 22.329,
|
| 609 |
+
"eval_steps_per_second": 1.422,
|
| 610 |
+
"step": 16113
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 41.98,
|
| 614 |
+
"learning_rate": 2.900763358778626e-05,
|
| 615 |
+
"loss": 0.29,
|
| 616 |
+
"step": 16500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 42.0,
|
| 620 |
+
"eval_bleu": 0.2871,
|
| 621 |
+
"eval_gen_len": 19.0,
|
| 622 |
+
"eval_loss": 0.719767689704895,
|
| 623 |
+
"eval_runtime": 35.1382,
|
| 624 |
+
"eval_samples_per_second": 22.34,
|
| 625 |
+
"eval_steps_per_second": 1.423,
|
| 626 |
+
"step": 16506
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 43.0,
|
| 630 |
+
"eval_bleu": 0.2813,
|
| 631 |
+
"eval_gen_len": 19.0,
|
| 632 |
+
"eval_loss": 0.7274527549743652,
|
| 633 |
+
"eval_runtime": 35.0854,
|
| 634 |
+
"eval_samples_per_second": 22.374,
|
| 635 |
+
"eval_steps_per_second": 1.425,
|
| 636 |
+
"step": 16899
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 43.26,
|
| 640 |
+
"learning_rate": 2.8371501272264633e-05,
|
| 641 |
+
"loss": 0.2787,
|
| 642 |
+
"step": 17000
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 44.0,
|
| 646 |
+
"eval_bleu": 0.2972,
|
| 647 |
+
"eval_gen_len": 19.0,
|
| 648 |
+
"eval_loss": 0.7369562983512878,
|
| 649 |
+
"eval_runtime": 35.1464,
|
| 650 |
+
"eval_samples_per_second": 22.335,
|
| 651 |
+
"eval_steps_per_second": 1.423,
|
| 652 |
+
"step": 17292
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 44.53,
|
| 656 |
+
"learning_rate": 2.7735368956743e-05,
|
| 657 |
+
"loss": 0.268,
|
| 658 |
+
"step": 17500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 45.0,
|
| 662 |
+
"eval_bleu": 0.26,
|
| 663 |
+
"eval_gen_len": 19.0,
|
| 664 |
+
"eval_loss": 0.7426473498344421,
|
| 665 |
+
"eval_runtime": 35.1116,
|
| 666 |
+
"eval_samples_per_second": 22.357,
|
| 667 |
+
"eval_steps_per_second": 1.424,
|
| 668 |
+
"step": 17685
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 45.8,
|
| 672 |
+
"learning_rate": 2.7099236641221375e-05,
|
| 673 |
+
"loss": 0.2638,
|
| 674 |
+
"step": 18000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 46.0,
|
| 678 |
+
"eval_bleu": 0.2846,
|
| 679 |
+
"eval_gen_len": 19.0,
|
| 680 |
+
"eval_loss": 0.7529018521308899,
|
| 681 |
+
"eval_runtime": 35.1433,
|
| 682 |
+
"eval_samples_per_second": 22.337,
|
| 683 |
+
"eval_steps_per_second": 1.423,
|
| 684 |
+
"step": 18078
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 47.0,
|
| 688 |
+
"eval_bleu": 0.2898,
|
| 689 |
+
"eval_gen_len": 19.0,
|
| 690 |
+
"eval_loss": 0.7602871060371399,
|
| 691 |
+
"eval_runtime": 35.1079,
|
| 692 |
+
"eval_samples_per_second": 22.36,
|
| 693 |
+
"eval_steps_per_second": 1.424,
|
| 694 |
+
"step": 18471
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 47.07,
|
| 698 |
+
"learning_rate": 2.6463104325699745e-05,
|
| 699 |
+
"loss": 0.253,
|
| 700 |
+
"step": 18500
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 48.0,
|
| 704 |
+
"eval_bleu": 0.277,
|
| 705 |
+
"eval_gen_len": 19.0,
|
| 706 |
+
"eval_loss": 0.7711123824119568,
|
| 707 |
+
"eval_runtime": 35.1881,
|
| 708 |
+
"eval_samples_per_second": 22.309,
|
| 709 |
+
"eval_steps_per_second": 1.421,
|
| 710 |
+
"step": 18864
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 48.35,
|
| 714 |
+
"learning_rate": 2.582697201017812e-05,
|
| 715 |
+
"loss": 0.244,
|
| 716 |
+
"step": 19000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 49.0,
|
| 720 |
+
"eval_bleu": 0.3005,
|
| 721 |
+
"eval_gen_len": 19.0,
|
| 722 |
+
"eval_loss": 0.7778590321540833,
|
| 723 |
+
"eval_runtime": 35.1873,
|
| 724 |
+
"eval_samples_per_second": 22.309,
|
| 725 |
+
"eval_steps_per_second": 1.421,
|
| 726 |
+
"step": 19257
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 49.62,
|
| 730 |
+
"learning_rate": 2.5190839694656487e-05,
|
| 731 |
+
"loss": 0.2368,
|
| 732 |
+
"step": 19500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 50.0,
|
| 736 |
+
"eval_bleu": 0.2931,
|
| 737 |
+
"eval_gen_len": 19.0,
|
| 738 |
+
"eval_loss": 0.7815132737159729,
|
| 739 |
+
"eval_runtime": 35.108,
|
| 740 |
+
"eval_samples_per_second": 22.36,
|
| 741 |
+
"eval_steps_per_second": 1.424,
|
| 742 |
+
"step": 19650
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 50.89,
|
| 746 |
+
"learning_rate": 2.455470737913486e-05,
|
| 747 |
+
"loss": 0.2301,
|
| 748 |
+
"step": 20000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 51.0,
|
| 752 |
+
"eval_bleu": 0.2998,
|
| 753 |
+
"eval_gen_len": 19.0,
|
| 754 |
+
"eval_loss": 0.8020169734954834,
|
| 755 |
+
"eval_runtime": 35.1735,
|
| 756 |
+
"eval_samples_per_second": 22.318,
|
| 757 |
+
"eval_steps_per_second": 1.422,
|
| 758 |
+
"step": 20043
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 52.0,
|
| 762 |
+
"eval_bleu": 0.2806,
|
| 763 |
+
"eval_gen_len": 19.0,
|
| 764 |
+
"eval_loss": 0.8051058053970337,
|
| 765 |
+
"eval_runtime": 35.0481,
|
| 766 |
+
"eval_samples_per_second": 22.398,
|
| 767 |
+
"eval_steps_per_second": 1.427,
|
| 768 |
+
"step": 20436
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 52.16,
|
| 772 |
+
"learning_rate": 2.391857506361323e-05,
|
| 773 |
+
"loss": 0.2217,
|
| 774 |
+
"step": 20500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 53.0,
|
| 778 |
+
"eval_bleu": 0.294,
|
| 779 |
+
"eval_gen_len": 19.0,
|
| 780 |
+
"eval_loss": 0.811935544013977,
|
| 781 |
+
"eval_runtime": 35.104,
|
| 782 |
+
"eval_samples_per_second": 22.362,
|
| 783 |
+
"eval_steps_per_second": 1.424,
|
| 784 |
+
"step": 20829
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 53.44,
|
| 788 |
+
"learning_rate": 2.3282442748091605e-05,
|
| 789 |
+
"loss": 0.2158,
|
| 790 |
+
"step": 21000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 54.0,
|
| 794 |
+
"eval_bleu": 0.2921,
|
| 795 |
+
"eval_gen_len": 19.0,
|
| 796 |
+
"eval_loss": 0.8288211226463318,
|
| 797 |
+
"eval_runtime": 35.1084,
|
| 798 |
+
"eval_samples_per_second": 22.359,
|
| 799 |
+
"eval_steps_per_second": 1.424,
|
| 800 |
+
"step": 21222
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 54.71,
|
| 804 |
+
"learning_rate": 2.2646310432569976e-05,
|
| 805 |
+
"loss": 0.2079,
|
| 806 |
+
"step": 21500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 55.0,
|
| 810 |
+
"eval_bleu": 0.2954,
|
| 811 |
+
"eval_gen_len": 19.0,
|
| 812 |
+
"eval_loss": 0.8340888619422913,
|
| 813 |
+
"eval_runtime": 35.1775,
|
| 814 |
+
"eval_samples_per_second": 22.315,
|
| 815 |
+
"eval_steps_per_second": 1.421,
|
| 816 |
+
"step": 21615
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 55.98,
|
| 820 |
+
"learning_rate": 2.2010178117048347e-05,
|
| 821 |
+
"loss": 0.2027,
|
| 822 |
+
"step": 22000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 56.0,
|
| 826 |
+
"eval_bleu": 0.2884,
|
| 827 |
+
"eval_gen_len": 19.0,
|
| 828 |
+
"eval_loss": 0.8364927768707275,
|
| 829 |
+
"eval_runtime": 35.072,
|
| 830 |
+
"eval_samples_per_second": 22.383,
|
| 831 |
+
"eval_steps_per_second": 1.426,
|
| 832 |
+
"step": 22008
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 57.0,
|
| 836 |
+
"eval_bleu": 0.2995,
|
| 837 |
+
"eval_gen_len": 19.0,
|
| 838 |
+
"eval_loss": 0.8441442251205444,
|
| 839 |
+
"eval_runtime": 35.1154,
|
| 840 |
+
"eval_samples_per_second": 22.355,
|
| 841 |
+
"eval_steps_per_second": 1.424,
|
| 842 |
+
"step": 22401
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 57.25,
|
| 846 |
+
"learning_rate": 2.1374045801526718e-05,
|
| 847 |
+
"loss": 0.1954,
|
| 848 |
+
"step": 22500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 58.0,
|
| 852 |
+
"eval_bleu": 0.3115,
|
| 853 |
+
"eval_gen_len": 19.0,
|
| 854 |
+
"eval_loss": 0.8488335609436035,
|
| 855 |
+
"eval_runtime": 34.9312,
|
| 856 |
+
"eval_samples_per_second": 22.473,
|
| 857 |
+
"eval_steps_per_second": 1.431,
|
| 858 |
+
"step": 22794
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 58.52,
|
| 862 |
+
"learning_rate": 2.0737913486005088e-05,
|
| 863 |
+
"loss": 0.1918,
|
| 864 |
+
"step": 23000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 59.0,
|
| 868 |
+
"eval_bleu": 0.3085,
|
| 869 |
+
"eval_gen_len": 19.0,
|
| 870 |
+
"eval_loss": 0.8709967732429504,
|
| 871 |
+
"eval_runtime": 35.0738,
|
| 872 |
+
"eval_samples_per_second": 22.381,
|
| 873 |
+
"eval_steps_per_second": 1.426,
|
| 874 |
+
"step": 23187
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 59.8,
|
| 878 |
+
"learning_rate": 2.0101781170483462e-05,
|
| 879 |
+
"loss": 0.1857,
|
| 880 |
+
"step": 23500
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 60.0,
|
| 884 |
+
"eval_bleu": 0.2932,
|
| 885 |
+
"eval_gen_len": 19.0,
|
| 886 |
+
"eval_loss": 0.8718471527099609,
|
| 887 |
+
"eval_runtime": 35.1809,
|
| 888 |
+
"eval_samples_per_second": 22.313,
|
| 889 |
+
"eval_steps_per_second": 1.421,
|
| 890 |
+
"step": 23580
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 61.0,
|
| 894 |
+
"eval_bleu": 0.2923,
|
| 895 |
+
"eval_gen_len": 19.0,
|
| 896 |
+
"eval_loss": 0.8777070045471191,
|
| 897 |
+
"eval_runtime": 35.0923,
|
| 898 |
+
"eval_samples_per_second": 22.37,
|
| 899 |
+
"eval_steps_per_second": 1.425,
|
| 900 |
+
"step": 23973
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 61.07,
|
| 904 |
+
"learning_rate": 1.9465648854961833e-05,
|
| 905 |
+
"loss": 0.1796,
|
| 906 |
+
"step": 24000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 62.0,
|
| 910 |
+
"eval_bleu": 0.3038,
|
| 911 |
+
"eval_gen_len": 19.0,
|
| 912 |
+
"eval_loss": 0.8831952214241028,
|
| 913 |
+
"eval_runtime": 35.1476,
|
| 914 |
+
"eval_samples_per_second": 22.334,
|
| 915 |
+
"eval_steps_per_second": 1.423,
|
| 916 |
+
"step": 24366
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 62.34,
|
| 920 |
+
"learning_rate": 1.8829516539440204e-05,
|
| 921 |
+
"loss": 0.1753,
|
| 922 |
+
"step": 24500
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 63.0,
|
| 926 |
+
"eval_bleu": 0.3063,
|
| 927 |
+
"eval_gen_len": 19.0,
|
| 928 |
+
"eval_loss": 0.8996883630752563,
|
| 929 |
+
"eval_runtime": 35.1466,
|
| 930 |
+
"eval_samples_per_second": 22.335,
|
| 931 |
+
"eval_steps_per_second": 1.423,
|
| 932 |
+
"step": 24759
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 63.61,
|
| 936 |
+
"learning_rate": 1.8193384223918574e-05,
|
| 937 |
+
"loss": 0.1703,
|
| 938 |
+
"step": 25000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 64.0,
|
| 942 |
+
"eval_bleu": 0.3047,
|
| 943 |
+
"eval_gen_len": 19.0,
|
| 944 |
+
"eval_loss": 0.9198061227798462,
|
| 945 |
+
"eval_runtime": 35.8655,
|
| 946 |
+
"eval_samples_per_second": 21.887,
|
| 947 |
+
"eval_steps_per_second": 1.394,
|
| 948 |
+
"step": 25152
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 64.89,
|
| 952 |
+
"learning_rate": 1.7557251908396945e-05,
|
| 953 |
+
"loss": 0.1661,
|
| 954 |
+
"step": 25500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 65.0,
|
| 958 |
+
"eval_bleu": 0.3159,
|
| 959 |
+
"eval_gen_len": 19.0,
|
| 960 |
+
"eval_loss": 0.9193503856658936,
|
| 961 |
+
"eval_runtime": 35.1603,
|
| 962 |
+
"eval_samples_per_second": 22.326,
|
| 963 |
+
"eval_steps_per_second": 1.422,
|
| 964 |
+
"step": 25545
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 66.0,
|
| 968 |
+
"eval_bleu": 0.2962,
|
| 969 |
+
"eval_gen_len": 19.0,
|
| 970 |
+
"eval_loss": 0.9242938756942749,
|
| 971 |
+
"eval_runtime": 35.073,
|
| 972 |
+
"eval_samples_per_second": 22.382,
|
| 973 |
+
"eval_steps_per_second": 1.426,
|
| 974 |
+
"step": 25938
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 66.16,
|
| 978 |
+
"learning_rate": 1.692111959287532e-05,
|
| 979 |
+
"loss": 0.1606,
|
| 980 |
+
"step": 26000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 67.0,
|
| 984 |
+
"eval_bleu": 0.3065,
|
| 985 |
+
"eval_gen_len": 19.0,
|
| 986 |
+
"eval_loss": 0.9375536441802979,
|
| 987 |
+
"eval_runtime": 34.9169,
|
| 988 |
+
"eval_samples_per_second": 22.482,
|
| 989 |
+
"eval_steps_per_second": 1.432,
|
| 990 |
+
"step": 26331
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 67.43,
|
| 994 |
+
"learning_rate": 1.628498727735369e-05,
|
| 995 |
+
"loss": 0.1582,
|
| 996 |
+
"step": 26500
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 68.0,
|
| 1000 |
+
"eval_bleu": 0.3002,
|
| 1001 |
+
"eval_gen_len": 19.0,
|
| 1002 |
+
"eval_loss": 0.9338624477386475,
|
| 1003 |
+
"eval_runtime": 35.1084,
|
| 1004 |
+
"eval_samples_per_second": 22.359,
|
| 1005 |
+
"eval_steps_per_second": 1.424,
|
| 1006 |
+
"step": 26724
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 68.7,
|
| 1010 |
+
"learning_rate": 1.5648854961832064e-05,
|
| 1011 |
+
"loss": 0.1533,
|
| 1012 |
+
"step": 27000
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 69.0,
|
| 1016 |
+
"eval_bleu": 0.3096,
|
| 1017 |
+
"eval_gen_len": 19.0,
|
| 1018 |
+
"eval_loss": 0.9420493841171265,
|
| 1019 |
+
"eval_runtime": 35.122,
|
| 1020 |
+
"eval_samples_per_second": 22.351,
|
| 1021 |
+
"eval_steps_per_second": 1.424,
|
| 1022 |
+
"step": 27117
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 69.97,
|
| 1026 |
+
"learning_rate": 1.5012722646310435e-05,
|
| 1027 |
+
"loss": 0.1503,
|
| 1028 |
+
"step": 27500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 70.0,
|
| 1032 |
+
"eval_bleu": 0.2919,
|
| 1033 |
+
"eval_gen_len": 19.0,
|
| 1034 |
+
"eval_loss": 0.9522092342376709,
|
| 1035 |
+
"eval_runtime": 35.4031,
|
| 1036 |
+
"eval_samples_per_second": 22.173,
|
| 1037 |
+
"eval_steps_per_second": 1.412,
|
| 1038 |
+
"step": 27510
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 71.0,
|
| 1042 |
+
"eval_bleu": 0.3085,
|
| 1043 |
+
"eval_gen_len": 19.0,
|
| 1044 |
+
"eval_loss": 0.9620120525360107,
|
| 1045 |
+
"eval_runtime": 35.926,
|
| 1046 |
+
"eval_samples_per_second": 21.85,
|
| 1047 |
+
"eval_steps_per_second": 1.392,
|
| 1048 |
+
"step": 27903
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 71.25,
|
| 1052 |
+
"learning_rate": 1.4376590330788805e-05,
|
| 1053 |
+
"loss": 0.1469,
|
| 1054 |
+
"step": 28000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 72.0,
|
| 1058 |
+
"eval_bleu": 0.2946,
|
| 1059 |
+
"eval_gen_len": 19.0,
|
| 1060 |
+
"eval_loss": 0.9673256874084473,
|
| 1061 |
+
"eval_runtime": 35.209,
|
| 1062 |
+
"eval_samples_per_second": 22.295,
|
| 1063 |
+
"eval_steps_per_second": 1.42,
|
| 1064 |
+
"step": 28296
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 72.52,
|
| 1068 |
+
"learning_rate": 1.3740458015267178e-05,
|
| 1069 |
+
"loss": 0.1416,
|
| 1070 |
+
"step": 28500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 73.0,
|
| 1074 |
+
"eval_bleu": 0.3019,
|
| 1075 |
+
"eval_gen_len": 19.0,
|
| 1076 |
+
"eval_loss": 0.9706256985664368,
|
| 1077 |
+
"eval_runtime": 35.1594,
|
| 1078 |
+
"eval_samples_per_second": 22.327,
|
| 1079 |
+
"eval_steps_per_second": 1.422,
|
| 1080 |
+
"step": 28689
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 73.79,
|
| 1084 |
+
"learning_rate": 1.3104325699745548e-05,
|
| 1085 |
+
"loss": 0.1401,
|
| 1086 |
+
"step": 29000
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 74.0,
|
| 1090 |
+
"eval_bleu": 0.3103,
|
| 1091 |
+
"eval_gen_len": 19.0,
|
| 1092 |
+
"eval_loss": 0.9876586198806763,
|
| 1093 |
+
"eval_runtime": 35.0824,
|
| 1094 |
+
"eval_samples_per_second": 22.376,
|
| 1095 |
+
"eval_steps_per_second": 1.425,
|
| 1096 |
+
"step": 29082
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 75.0,
|
| 1100 |
+
"eval_bleu": 0.2903,
|
| 1101 |
+
"eval_gen_len": 19.0,
|
| 1102 |
+
"eval_loss": 0.9860377311706543,
|
| 1103 |
+
"eval_runtime": 35.2841,
|
| 1104 |
+
"eval_samples_per_second": 22.248,
|
| 1105 |
+
"eval_steps_per_second": 1.417,
|
| 1106 |
+
"step": 29475
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 75.06,
|
| 1110 |
+
"learning_rate": 1.2468193384223919e-05,
|
| 1111 |
+
"loss": 0.1376,
|
| 1112 |
+
"step": 29500
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 76.0,
|
| 1116 |
+
"eval_bleu": 0.2855,
|
| 1117 |
+
"eval_gen_len": 19.0,
|
| 1118 |
+
"eval_loss": 1.0073317289352417,
|
| 1119 |
+
"eval_runtime": 35.1549,
|
| 1120 |
+
"eval_samples_per_second": 22.33,
|
| 1121 |
+
"eval_steps_per_second": 1.422,
|
| 1122 |
+
"step": 29868
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 76.34,
|
| 1126 |
+
"learning_rate": 1.1832061068702292e-05,
|
| 1127 |
+
"loss": 0.1341,
|
| 1128 |
+
"step": 30000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 77.0,
|
| 1132 |
+
"eval_bleu": 0.2927,
|
| 1133 |
+
"eval_gen_len": 19.0,
|
| 1134 |
+
"eval_loss": 1.0067394971847534,
|
| 1135 |
+
"eval_runtime": 35.7641,
|
| 1136 |
+
"eval_samples_per_second": 21.949,
|
| 1137 |
+
"eval_steps_per_second": 1.398,
|
| 1138 |
+
"step": 30261
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 77.61,
|
| 1142 |
+
"learning_rate": 1.1195928753180662e-05,
|
| 1143 |
+
"loss": 0.1307,
|
| 1144 |
+
"step": 30500
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 78.0,
|
| 1148 |
+
"eval_bleu": 0.3,
|
| 1149 |
+
"eval_gen_len": 19.0,
|
| 1150 |
+
"eval_loss": 1.006367564201355,
|
| 1151 |
+
"eval_runtime": 35.3184,
|
| 1152 |
+
"eval_samples_per_second": 22.226,
|
| 1153 |
+
"eval_steps_per_second": 1.416,
|
| 1154 |
+
"step": 30654
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 78.88,
|
| 1158 |
+
"learning_rate": 1.0559796437659033e-05,
|
| 1159 |
+
"loss": 0.1296,
|
| 1160 |
+
"step": 31000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 79.0,
|
| 1164 |
+
"eval_bleu": 0.2886,
|
| 1165 |
+
"eval_gen_len": 19.0,
|
| 1166 |
+
"eval_loss": 1.022121787071228,
|
| 1167 |
+
"eval_runtime": 35.3415,
|
| 1168 |
+
"eval_samples_per_second": 22.212,
|
| 1169 |
+
"eval_steps_per_second": 1.415,
|
| 1170 |
+
"step": 31047
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 80.0,
|
| 1174 |
+
"eval_bleu": 0.297,
|
| 1175 |
+
"eval_gen_len": 19.0,
|
| 1176 |
+
"eval_loss": 1.021680235862732,
|
| 1177 |
+
"eval_runtime": 35.3179,
|
| 1178 |
+
"eval_samples_per_second": 22.227,
|
| 1179 |
+
"eval_steps_per_second": 1.416,
|
| 1180 |
+
"step": 31440
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 80.15,
|
| 1184 |
+
"learning_rate": 9.923664122137405e-06,
|
| 1185 |
+
"loss": 0.126,
|
| 1186 |
+
"step": 31500
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 81.0,
|
| 1190 |
+
"eval_bleu": 0.2919,
|
| 1191 |
+
"eval_gen_len": 19.0,
|
| 1192 |
+
"eval_loss": 1.027828335762024,
|
| 1193 |
+
"eval_runtime": 35.4035,
|
| 1194 |
+
"eval_samples_per_second": 22.173,
|
| 1195 |
+
"eval_steps_per_second": 1.412,
|
| 1196 |
+
"step": 31833
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 81.42,
|
| 1200 |
+
"learning_rate": 9.287531806615776e-06,
|
| 1201 |
+
"loss": 0.1238,
|
| 1202 |
+
"step": 32000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 82.0,
|
| 1206 |
+
"eval_bleu": 0.2951,
|
| 1207 |
+
"eval_gen_len": 19.0,
|
| 1208 |
+
"eval_loss": 1.03290855884552,
|
| 1209 |
+
"eval_runtime": 35.2364,
|
| 1210 |
+
"eval_samples_per_second": 22.278,
|
| 1211 |
+
"eval_steps_per_second": 1.419,
|
| 1212 |
+
"step": 32226
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 82.7,
|
| 1216 |
+
"learning_rate": 8.651399491094148e-06,
|
| 1217 |
+
"loss": 0.1214,
|
| 1218 |
+
"step": 32500
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 83.0,
|
| 1222 |
+
"eval_bleu": 0.3043,
|
| 1223 |
+
"eval_gen_len": 19.0,
|
| 1224 |
+
"eval_loss": 1.0350806713104248,
|
| 1225 |
+
"eval_runtime": 35.1544,
|
| 1226 |
+
"eval_samples_per_second": 22.33,
|
| 1227 |
+
"eval_steps_per_second": 1.422,
|
| 1228 |
+
"step": 32619
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 83.97,
|
| 1232 |
+
"learning_rate": 8.015267175572519e-06,
|
| 1233 |
+
"loss": 0.1206,
|
| 1234 |
+
"step": 33000
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 84.0,
|
| 1238 |
+
"eval_bleu": 0.2964,
|
| 1239 |
+
"eval_gen_len": 19.0,
|
| 1240 |
+
"eval_loss": 1.04984450340271,
|
| 1241 |
+
"eval_runtime": 35.3457,
|
| 1242 |
+
"eval_samples_per_second": 22.209,
|
| 1243 |
+
"eval_steps_per_second": 1.415,
|
| 1244 |
+
"step": 33012
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 85.0,
|
| 1248 |
+
"eval_bleu": 0.2971,
|
| 1249 |
+
"eval_gen_len": 19.0,
|
| 1250 |
+
"eval_loss": 1.0432653427124023,
|
| 1251 |
+
"eval_runtime": 35.2727,
|
| 1252 |
+
"eval_samples_per_second": 22.255,
|
| 1253 |
+
"eval_steps_per_second": 1.418,
|
| 1254 |
+
"step": 33405
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 85.24,
|
| 1258 |
+
"learning_rate": 7.379134860050891e-06,
|
| 1259 |
+
"loss": 0.1186,
|
| 1260 |
+
"step": 33500
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 86.0,
|
| 1264 |
+
"eval_bleu": 0.2964,
|
| 1265 |
+
"eval_gen_len": 19.0,
|
| 1266 |
+
"eval_loss": 1.05250883102417,
|
| 1267 |
+
"eval_runtime": 35.1615,
|
| 1268 |
+
"eval_samples_per_second": 22.326,
|
| 1269 |
+
"eval_steps_per_second": 1.422,
|
| 1270 |
+
"step": 33798
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 86.51,
|
| 1274 |
+
"learning_rate": 6.743002544529263e-06,
|
| 1275 |
+
"loss": 0.116,
|
| 1276 |
+
"step": 34000
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 87.0,
|
| 1280 |
+
"eval_bleu": 0.2943,
|
| 1281 |
+
"eval_gen_len": 19.0,
|
| 1282 |
+
"eval_loss": 1.0547308921813965,
|
| 1283 |
+
"eval_runtime": 35.1782,
|
| 1284 |
+
"eval_samples_per_second": 22.315,
|
| 1285 |
+
"eval_steps_per_second": 1.421,
|
| 1286 |
+
"step": 34191
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 87.79,
|
| 1290 |
+
"learning_rate": 6.106870229007634e-06,
|
| 1291 |
+
"loss": 0.116,
|
| 1292 |
+
"step": 34500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 88.0,
|
| 1296 |
+
"eval_bleu": 0.2876,
|
| 1297 |
+
"eval_gen_len": 19.0,
|
| 1298 |
+
"eval_loss": 1.0584968328475952,
|
| 1299 |
+
"eval_runtime": 35.1038,
|
| 1300 |
+
"eval_samples_per_second": 22.362,
|
| 1301 |
+
"eval_steps_per_second": 1.424,
|
| 1302 |
+
"step": 34584
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 89.0,
|
| 1306 |
+
"eval_bleu": 0.2904,
|
| 1307 |
+
"eval_gen_len": 19.0,
|
| 1308 |
+
"eval_loss": 1.0630890130996704,
|
| 1309 |
+
"eval_runtime": 35.1555,
|
| 1310 |
+
"eval_samples_per_second": 22.329,
|
| 1311 |
+
"eval_steps_per_second": 1.422,
|
| 1312 |
+
"step": 34977
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 89.06,
|
| 1316 |
+
"learning_rate": 5.470737913486006e-06,
|
| 1317 |
+
"loss": 0.1131,
|
| 1318 |
+
"step": 35000
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 90.0,
|
| 1322 |
+
"eval_bleu": 0.2859,
|
| 1323 |
+
"eval_gen_len": 19.0,
|
| 1324 |
+
"eval_loss": 1.0678483247756958,
|
| 1325 |
+
"eval_runtime": 35.1133,
|
| 1326 |
+
"eval_samples_per_second": 22.356,
|
| 1327 |
+
"eval_steps_per_second": 1.424,
|
| 1328 |
+
"step": 35370
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 90.33,
|
| 1332 |
+
"learning_rate": 4.834605597964377e-06,
|
| 1333 |
+
"loss": 0.1124,
|
| 1334 |
+
"step": 35500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 91.0,
|
| 1338 |
+
"eval_bleu": 0.3027,
|
| 1339 |
+
"eval_gen_len": 19.0,
|
| 1340 |
+
"eval_loss": 1.0763660669326782,
|
| 1341 |
+
"eval_runtime": 35.192,
|
| 1342 |
+
"eval_samples_per_second": 22.306,
|
| 1343 |
+
"eval_steps_per_second": 1.421,
|
| 1344 |
+
"step": 35763
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 91.6,
|
| 1348 |
+
"learning_rate": 4.198473282442748e-06,
|
| 1349 |
+
"loss": 0.1109,
|
| 1350 |
+
"step": 36000
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 92.0,
|
| 1354 |
+
"eval_bleu": 0.3037,
|
| 1355 |
+
"eval_gen_len": 19.0,
|
| 1356 |
+
"eval_loss": 1.0759409666061401,
|
| 1357 |
+
"eval_runtime": 35.1267,
|
| 1358 |
+
"eval_samples_per_second": 22.348,
|
| 1359 |
+
"eval_steps_per_second": 1.423,
|
| 1360 |
+
"step": 36156
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 92.88,
|
| 1364 |
+
"learning_rate": 3.56234096692112e-06,
|
| 1365 |
+
"loss": 0.1097,
|
| 1366 |
+
"step": 36500
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 93.0,
|
| 1370 |
+
"eval_bleu": 0.2962,
|
| 1371 |
+
"eval_gen_len": 19.0,
|
| 1372 |
+
"eval_loss": 1.073776364326477,
|
| 1373 |
+
"eval_runtime": 35.2856,
|
| 1374 |
+
"eval_samples_per_second": 22.247,
|
| 1375 |
+
"eval_steps_per_second": 1.417,
|
| 1376 |
+
"step": 36549
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 94.0,
|
| 1380 |
+
"eval_bleu": 0.2966,
|
| 1381 |
+
"eval_gen_len": 19.0,
|
| 1382 |
+
"eval_loss": 1.0854607820510864,
|
| 1383 |
+
"eval_runtime": 35.1676,
|
| 1384 |
+
"eval_samples_per_second": 22.322,
|
| 1385 |
+
"eval_steps_per_second": 1.422,
|
| 1386 |
+
"step": 36942
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 94.15,
|
| 1390 |
+
"learning_rate": 2.9262086513994914e-06,
|
| 1391 |
+
"loss": 0.1093,
|
| 1392 |
+
"step": 37000
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 95.0,
|
| 1396 |
+
"eval_bleu": 0.2968,
|
| 1397 |
+
"eval_gen_len": 19.0,
|
| 1398 |
+
"eval_loss": 1.090211033821106,
|
| 1399 |
+
"eval_runtime": 35.1673,
|
| 1400 |
+
"eval_samples_per_second": 22.322,
|
| 1401 |
+
"eval_steps_per_second": 1.422,
|
| 1402 |
+
"step": 37335
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 95.42,
|
| 1406 |
+
"learning_rate": 2.2900763358778625e-06,
|
| 1407 |
+
"loss": 0.1082,
|
| 1408 |
+
"step": 37500
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 96.0,
|
| 1412 |
+
"eval_bleu": 0.2958,
|
| 1413 |
+
"eval_gen_len": 19.0,
|
| 1414 |
+
"eval_loss": 1.0858522653579712,
|
| 1415 |
+
"eval_runtime": 35.1286,
|
| 1416 |
+
"eval_samples_per_second": 22.346,
|
| 1417 |
+
"eval_steps_per_second": 1.423,
|
| 1418 |
+
"step": 37728
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 96.69,
|
| 1422 |
+
"learning_rate": 1.653944020356234e-06,
|
| 1423 |
+
"loss": 0.1073,
|
| 1424 |
+
"step": 38000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 97.0,
|
| 1428 |
+
"eval_bleu": 0.3023,
|
| 1429 |
+
"eval_gen_len": 19.0,
|
| 1430 |
+
"eval_loss": 1.0867019891738892,
|
| 1431 |
+
"eval_runtime": 35.1622,
|
| 1432 |
+
"eval_samples_per_second": 22.325,
|
| 1433 |
+
"eval_steps_per_second": 1.422,
|
| 1434 |
+
"step": 38121
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 97.96,
|
| 1438 |
+
"learning_rate": 1.0178117048346056e-06,
|
| 1439 |
+
"loss": 0.1063,
|
| 1440 |
+
"step": 38500
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 98.0,
|
| 1444 |
+
"eval_bleu": 0.3004,
|
| 1445 |
+
"eval_gen_len": 19.0,
|
| 1446 |
+
"eval_loss": 1.090205430984497,
|
| 1447 |
+
"eval_runtime": 35.3454,
|
| 1448 |
+
"eval_samples_per_second": 22.209,
|
| 1449 |
+
"eval_steps_per_second": 1.415,
|
| 1450 |
+
"step": 38514
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 99.0,
|
| 1454 |
+
"eval_bleu": 0.3018,
|
| 1455 |
+
"eval_gen_len": 19.0,
|
| 1456 |
+
"eval_loss": 1.0909733772277832,
|
| 1457 |
+
"eval_runtime": 35.2503,
|
| 1458 |
+
"eval_samples_per_second": 22.269,
|
| 1459 |
+
"eval_steps_per_second": 1.418,
|
| 1460 |
+
"step": 38907
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 99.24,
|
| 1464 |
+
"learning_rate": 3.816793893129771e-07,
|
| 1465 |
+
"loss": 0.1065,
|
| 1466 |
+
"step": 39000
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 100.0,
|
| 1470 |
+
"eval_bleu": 0.3021,
|
| 1471 |
+
"eval_gen_len": 19.0,
|
| 1472 |
+
"eval_loss": 1.0916588306427002,
|
| 1473 |
+
"eval_runtime": 35.2577,
|
| 1474 |
+
"eval_samples_per_second": 22.265,
|
| 1475 |
+
"eval_steps_per_second": 1.418,
|
| 1476 |
+
"step": 39300
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 100.0,
|
| 1480 |
+
"step": 39300,
|
| 1481 |
+
"total_flos": 2.232877359218688e+17,
|
| 1482 |
+
"train_loss": 0.3279189860123108,
|
| 1483 |
+
"train_runtime": 20714.0027,
|
| 1484 |
+
"train_samples_per_second": 30.313,
|
| 1485 |
+
"train_steps_per_second": 1.897
|
| 1486 |
}
|
| 1487 |
],
|
| 1488 |
+
"max_steps": 39300,
|
| 1489 |
+
"num_train_epochs": 100,
|
| 1490 |
+
"total_flos": 2.232877359218688e+17,
|
| 1491 |
"trial_name": null,
|
| 1492 |
"trial_params": null
|
| 1493 |
}
|