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/May26_10-05-21_1733356bae24/events.out.tfevents.1685117591.1733356bae24.77485.8 +3 -0
- train_results.json +6 -6
- trainer_state.json +1408 -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": 139.
|
| 7 |
"eval_samples": 794,
|
| 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": 795,
|
| 15 |
-
"predict_samples_per_second": 5.
|
| 16 |
-
"predict_steps_per_second": 0.
|
| 17 |
-
"total_flos": 2.
|
| 18 |
-
"train_loss": 0.
|
| 19 |
-
"train_runtime":
|
| 20 |
"train_samples": 6354,
|
| 21 |
-
"train_samples_per_second": 30.
|
| 22 |
-
"train_steps_per_second": 1.
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_bleu": 16.0295,
|
| 4 |
+
"eval_gen_len": 98.8829,
|
| 5 |
+
"eval_loss": 1.0861998796463013,
|
| 6 |
+
"eval_runtime": 139.467,
|
| 7 |
"eval_samples": 794,
|
| 8 |
+
"eval_samples_per_second": 5.693,
|
| 9 |
+
"eval_steps_per_second": 0.359,
|
| 10 |
+
"predict_bleu": 16.4199,
|
| 11 |
+
"predict_gen_len": 99.7396,
|
| 12 |
+
"predict_loss": 1.0474767684936523,
|
| 13 |
+
"predict_runtime": 138.8934,
|
| 14 |
"predict_samples": 795,
|
| 15 |
+
"predict_samples_per_second": 5.724,
|
| 16 |
+
"predict_steps_per_second": 0.36,
|
| 17 |
+
"total_flos": 2.2595375365462426e+17,
|
| 18 |
+
"train_loss": 0.31051562630351465,
|
| 19 |
+
"train_runtime": 21104.6673,
|
| 20 |
"train_samples": 6354,
|
| 21 |
+
"train_samples_per_second": 30.107,
|
| 22 |
+
"train_steps_per_second": 1.886
|
| 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": 139.
|
| 7 |
"eval_samples": 794,
|
| 8 |
-
"eval_samples_per_second": 5.
|
| 9 |
-
"eval_steps_per_second": 0.
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_bleu": 16.0295,
|
| 4 |
+
"eval_gen_len": 98.8829,
|
| 5 |
+
"eval_loss": 1.0861998796463013,
|
| 6 |
+
"eval_runtime": 139.467,
|
| 7 |
"eval_samples": 794,
|
| 8 |
+
"eval_samples_per_second": 5.693,
|
| 9 |
+
"eval_steps_per_second": 0.359
|
| 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": 795,
|
| 7 |
-
"predict_samples_per_second": 5.
|
| 8 |
-
"predict_steps_per_second": 0.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"predict_bleu": 16.4199,
|
| 3 |
+
"predict_gen_len": 99.7396,
|
| 4 |
+
"predict_loss": 1.0474767684936523,
|
| 5 |
+
"predict_runtime": 138.8934,
|
| 6 |
"predict_samples": 795,
|
| 7 |
+
"predict_samples_per_second": 5.724,
|
| 8 |
+
"predict_steps_per_second": 0.36
|
| 9 |
}
|
runs/May26_10-05-21_1733356bae24/events.out.tfevents.1685117591.1733356bae24.77485.8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:527f66f5d6c6e38d1abd9268c1a0676e8eb91cbf695778b572eaa4ee846765e5
|
| 3 |
+
size 465
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 2.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 6354,
|
| 7 |
-
"train_samples_per_second": 30.
|
| 8 |
-
"train_steps_per_second": 1.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"total_flos": 2.2595375365462426e+17,
|
| 4 |
+
"train_loss": 0.31051562630351465,
|
| 5 |
+
"train_runtime": 21104.6673,
|
| 6 |
"train_samples": 6354,
|
| 7 |
+
"train_samples_per_second": 30.107,
|
| 8 |
+
"train_steps_per_second": 1.886
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,167 +1,1499 @@
|
|
| 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": 0.
|
| 15 |
-
"eval_runtime":
|
| 16 |
-
"eval_samples_per_second": 20.
|
| 17 |
-
"eval_steps_per_second": 1.
|
| 18 |
"step": 398
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.26,
|
| 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": 796
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 2.51,
|
| 38 |
-
"learning_rate":
|
| 39 |
-
"loss": 0.
|
| 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": 1194
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 3.77,
|
| 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": 1592
|
| 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": 1990
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 5.03,
|
| 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": 2388
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 6.28,
|
| 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": 2786
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 7.54,
|
| 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": 3184
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 8.79,
|
| 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": 3582
|
| 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": 3980
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch": 10.
|
| 154 |
-
"
|
| 155 |
-
"
|
| 156 |
-
"
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 160 |
}
|
| 161 |
],
|
| 162 |
-
"max_steps":
|
| 163 |
-
"num_train_epochs":
|
| 164 |
-
"total_flos": 2.
|
| 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": 39800,
|
| 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": 0.0907,
|
| 13 |
"eval_gen_len": 19.0,
|
| 14 |
+
"eval_loss": 0.9955226182937622,
|
| 15 |
+
"eval_runtime": 38.0064,
|
| 16 |
+
"eval_samples_per_second": 20.891,
|
| 17 |
+
"eval_steps_per_second": 1.316,
|
| 18 |
"step": 398
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.26,
|
| 22 |
+
"learning_rate": 4.937185929648241e-05,
|
| 23 |
+
"loss": 1.4196,
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"eval_bleu": 0.5548,
|
| 29 |
"eval_gen_len": 19.0,
|
| 30 |
+
"eval_loss": 0.8669910430908203,
|
| 31 |
+
"eval_runtime": 36.5925,
|
| 32 |
+
"eval_samples_per_second": 21.698,
|
| 33 |
+
"eval_steps_per_second": 1.366,
|
| 34 |
"step": 796
|
| 35 |
},
|
| 36 |
{
|
| 37 |
"epoch": 2.51,
|
| 38 |
+
"learning_rate": 4.874371859296483e-05,
|
| 39 |
+
"loss": 0.9762,
|
| 40 |
"step": 1000
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 3.0,
|
| 44 |
+
"eval_bleu": 0.2508,
|
| 45 |
"eval_gen_len": 19.0,
|
| 46 |
+
"eval_loss": 0.8083329796791077,
|
| 47 |
+
"eval_runtime": 36.4935,
|
| 48 |
+
"eval_samples_per_second": 21.757,
|
| 49 |
+
"eval_steps_per_second": 1.37,
|
| 50 |
"step": 1194
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 3.77,
|
| 54 |
+
"learning_rate": 4.8115577889447235e-05,
|
| 55 |
+
"loss": 0.8703,
|
| 56 |
"step": 1500
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 4.0,
|
| 60 |
+
"eval_bleu": 0.5692,
|
| 61 |
"eval_gen_len": 19.0,
|
| 62 |
+
"eval_loss": 0.7637783288955688,
|
| 63 |
+
"eval_runtime": 36.123,
|
| 64 |
+
"eval_samples_per_second": 21.98,
|
| 65 |
+
"eval_steps_per_second": 1.384,
|
| 66 |
"step": 1592
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 5.0,
|
| 70 |
+
"eval_bleu": 0.3461,
|
| 71 |
"eval_gen_len": 19.0,
|
| 72 |
+
"eval_loss": 0.7334607243537903,
|
| 73 |
+
"eval_runtime": 36.0793,
|
| 74 |
+
"eval_samples_per_second": 22.007,
|
| 75 |
+
"eval_steps_per_second": 1.386,
|
| 76 |
"step": 1990
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 5.03,
|
| 80 |
+
"learning_rate": 4.748743718592965e-05,
|
| 81 |
+
"loss": 0.8098,
|
| 82 |
"step": 2000
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 6.0,
|
| 86 |
+
"eval_bleu": 0.399,
|
| 87 |
"eval_gen_len": 19.0,
|
| 88 |
+
"eval_loss": 0.7078682780265808,
|
| 89 |
+
"eval_runtime": 36.1012,
|
| 90 |
+
"eval_samples_per_second": 21.994,
|
| 91 |
+
"eval_steps_per_second": 1.385,
|
| 92 |
"step": 2388
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 6.28,
|
| 96 |
+
"learning_rate": 4.685929648241206e-05,
|
| 97 |
+
"loss": 0.7592,
|
| 98 |
"step": 2500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 7.0,
|
| 102 |
+
"eval_bleu": 0.3376,
|
| 103 |
"eval_gen_len": 19.0,
|
| 104 |
+
"eval_loss": 0.6845763325691223,
|
| 105 |
+
"eval_runtime": 35.9042,
|
| 106 |
+
"eval_samples_per_second": 22.114,
|
| 107 |
+
"eval_steps_per_second": 1.393,
|
| 108 |
"step": 2786
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 7.54,
|
| 112 |
+
"learning_rate": 4.6231155778894475e-05,
|
| 113 |
+
"loss": 0.7167,
|
| 114 |
"step": 3000
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 8.0,
|
| 118 |
+
"eval_bleu": 0.4617,
|
| 119 |
"eval_gen_len": 19.0,
|
| 120 |
+
"eval_loss": 0.6675065755844116,
|
| 121 |
+
"eval_runtime": 35.9616,
|
| 122 |
+
"eval_samples_per_second": 22.079,
|
| 123 |
+
"eval_steps_per_second": 1.39,
|
| 124 |
"step": 3184
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 8.79,
|
| 128 |
+
"learning_rate": 4.5603015075376884e-05,
|
| 129 |
+
"loss": 0.6881,
|
| 130 |
"step": 3500
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 9.0,
|
| 134 |
+
"eval_bleu": 0.438,
|
| 135 |
"eval_gen_len": 19.0,
|
| 136 |
+
"eval_loss": 0.6496185660362244,
|
| 137 |
+
"eval_runtime": 36.0502,
|
| 138 |
+
"eval_samples_per_second": 22.025,
|
| 139 |
+
"eval_steps_per_second": 1.387,
|
| 140 |
"step": 3582
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 10.0,
|
| 144 |
+
"eval_bleu": 0.4397,
|
| 145 |
"eval_gen_len": 19.0,
|
| 146 |
+
"eval_loss": 0.6296620965003967,
|
| 147 |
+
"eval_runtime": 36.04,
|
| 148 |
+
"eval_samples_per_second": 22.031,
|
| 149 |
+
"eval_steps_per_second": 1.387,
|
| 150 |
"step": 3980
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 10.05,
|
| 154 |
+
"learning_rate": 4.49748743718593e-05,
|
| 155 |
+
"loss": 0.6543,
|
| 156 |
+
"step": 4000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 11.0,
|
| 160 |
+
"eval_bleu": 0.4078,
|
| 161 |
+
"eval_gen_len": 19.0,
|
| 162 |
+
"eval_loss": 0.6143925189971924,
|
| 163 |
+
"eval_runtime": 36.2369,
|
| 164 |
+
"eval_samples_per_second": 21.911,
|
| 165 |
+
"eval_steps_per_second": 1.38,
|
| 166 |
+
"step": 4378
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 11.31,
|
| 170 |
+
"learning_rate": 4.434673366834171e-05,
|
| 171 |
+
"loss": 0.6245,
|
| 172 |
+
"step": 4500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 12.0,
|
| 176 |
+
"eval_bleu": 0.3468,
|
| 177 |
+
"eval_gen_len": 19.0,
|
| 178 |
+
"eval_loss": 0.6090631484985352,
|
| 179 |
+
"eval_runtime": 36.2496,
|
| 180 |
+
"eval_samples_per_second": 21.904,
|
| 181 |
+
"eval_steps_per_second": 1.379,
|
| 182 |
+
"step": 4776
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 12.56,
|
| 186 |
+
"learning_rate": 4.3718592964824124e-05,
|
| 187 |
+
"loss": 0.5959,
|
| 188 |
+
"step": 5000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 13.0,
|
| 192 |
+
"eval_bleu": 0.433,
|
| 193 |
+
"eval_gen_len": 19.0,
|
| 194 |
+
"eval_loss": 0.603904664516449,
|
| 195 |
+
"eval_runtime": 36.0829,
|
| 196 |
+
"eval_samples_per_second": 22.005,
|
| 197 |
+
"eval_steps_per_second": 1.386,
|
| 198 |
+
"step": 5174
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 13.82,
|
| 202 |
+
"learning_rate": 4.309045226130653e-05,
|
| 203 |
+
"loss": 0.5766,
|
| 204 |
+
"step": 5500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 14.0,
|
| 208 |
+
"eval_bleu": 0.4332,
|
| 209 |
+
"eval_gen_len": 19.0,
|
| 210 |
+
"eval_loss": 0.5970507264137268,
|
| 211 |
+
"eval_runtime": 36.1622,
|
| 212 |
+
"eval_samples_per_second": 21.957,
|
| 213 |
+
"eval_steps_per_second": 1.383,
|
| 214 |
+
"step": 5572
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 15.0,
|
| 218 |
+
"eval_bleu": 0.4291,
|
| 219 |
+
"eval_gen_len": 19.0,
|
| 220 |
+
"eval_loss": 0.5931375622749329,
|
| 221 |
+
"eval_runtime": 36.0907,
|
| 222 |
+
"eval_samples_per_second": 22.0,
|
| 223 |
+
"eval_steps_per_second": 1.385,
|
| 224 |
+
"step": 5970
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 15.08,
|
| 228 |
+
"learning_rate": 4.246231155778895e-05,
|
| 229 |
+
"loss": 0.5541,
|
| 230 |
+
"step": 6000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 16.0,
|
| 234 |
+
"eval_bleu": 0.4504,
|
| 235 |
+
"eval_gen_len": 19.0,
|
| 236 |
+
"eval_loss": 0.5876542329788208,
|
| 237 |
+
"eval_runtime": 36.3841,
|
| 238 |
+
"eval_samples_per_second": 21.823,
|
| 239 |
+
"eval_steps_per_second": 1.374,
|
| 240 |
+
"step": 6368
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 16.33,
|
| 244 |
+
"learning_rate": 4.183417085427136e-05,
|
| 245 |
+
"loss": 0.5331,
|
| 246 |
+
"step": 6500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 17.0,
|
| 250 |
+
"eval_bleu": 0.4359,
|
| 251 |
+
"eval_gen_len": 19.0,
|
| 252 |
+
"eval_loss": 0.5872967839241028,
|
| 253 |
+
"eval_runtime": 36.0616,
|
| 254 |
+
"eval_samples_per_second": 22.018,
|
| 255 |
+
"eval_steps_per_second": 1.387,
|
| 256 |
+
"step": 6766
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 17.59,
|
| 260 |
+
"learning_rate": 4.120603015075377e-05,
|
| 261 |
+
"loss": 0.5169,
|
| 262 |
+
"step": 7000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 18.0,
|
| 266 |
+
"eval_bleu": 0.419,
|
| 267 |
+
"eval_gen_len": 19.0,
|
| 268 |
+
"eval_loss": 0.5864170789718628,
|
| 269 |
+
"eval_runtime": 36.0624,
|
| 270 |
+
"eval_samples_per_second": 22.017,
|
| 271 |
+
"eval_steps_per_second": 1.386,
|
| 272 |
+
"step": 7164
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 18.84,
|
| 276 |
+
"learning_rate": 4.057788944723618e-05,
|
| 277 |
+
"loss": 0.4991,
|
| 278 |
+
"step": 7500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 19.0,
|
| 282 |
+
"eval_bleu": 0.4191,
|
| 283 |
+
"eval_gen_len": 19.0,
|
| 284 |
+
"eval_loss": 0.5880436897277832,
|
| 285 |
+
"eval_runtime": 36.0649,
|
| 286 |
+
"eval_samples_per_second": 22.016,
|
| 287 |
+
"eval_steps_per_second": 1.386,
|
| 288 |
+
"step": 7562
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 20.0,
|
| 292 |
+
"eval_bleu": 0.4535,
|
| 293 |
+
"eval_gen_len": 19.0,
|
| 294 |
+
"eval_loss": 0.5844656825065613,
|
| 295 |
+
"eval_runtime": 36.1564,
|
| 296 |
+
"eval_samples_per_second": 21.96,
|
| 297 |
+
"eval_steps_per_second": 1.383,
|
| 298 |
+
"step": 7960
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 20.1,
|
| 302 |
+
"learning_rate": 3.9949748743718597e-05,
|
| 303 |
+
"loss": 0.4827,
|
| 304 |
+
"step": 8000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 21.0,
|
| 308 |
+
"eval_bleu": 0.4614,
|
| 309 |
+
"eval_gen_len": 19.0,
|
| 310 |
+
"eval_loss": 0.588854968547821,
|
| 311 |
+
"eval_runtime": 36.034,
|
| 312 |
+
"eval_samples_per_second": 22.035,
|
| 313 |
+
"eval_steps_per_second": 1.388,
|
| 314 |
+
"step": 8358
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 21.36,
|
| 318 |
+
"learning_rate": 3.9321608040201005e-05,
|
| 319 |
+
"loss": 0.4646,
|
| 320 |
+
"step": 8500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 22.0,
|
| 324 |
+
"eval_bleu": 0.4075,
|
| 325 |
+
"eval_gen_len": 19.0,
|
| 326 |
+
"eval_loss": 0.5893688201904297,
|
| 327 |
+
"eval_runtime": 36.2919,
|
| 328 |
+
"eval_samples_per_second": 21.878,
|
| 329 |
+
"eval_steps_per_second": 1.378,
|
| 330 |
+
"step": 8756
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 22.61,
|
| 334 |
+
"learning_rate": 3.869346733668342e-05,
|
| 335 |
+
"loss": 0.4523,
|
| 336 |
+
"step": 9000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 23.0,
|
| 340 |
+
"eval_bleu": 0.4399,
|
| 341 |
+
"eval_gen_len": 19.0,
|
| 342 |
+
"eval_loss": 0.5904817581176758,
|
| 343 |
+
"eval_runtime": 36.1578,
|
| 344 |
+
"eval_samples_per_second": 21.959,
|
| 345 |
+
"eval_steps_per_second": 1.383,
|
| 346 |
+
"step": 9154
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 23.87,
|
| 350 |
+
"learning_rate": 3.806532663316583e-05,
|
| 351 |
+
"loss": 0.437,
|
| 352 |
+
"step": 9500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 24.0,
|
| 356 |
+
"eval_bleu": 0.4369,
|
| 357 |
+
"eval_gen_len": 19.0,
|
| 358 |
+
"eval_loss": 0.5984958410263062,
|
| 359 |
+
"eval_runtime": 36.0725,
|
| 360 |
+
"eval_samples_per_second": 22.011,
|
| 361 |
+
"eval_steps_per_second": 1.386,
|
| 362 |
+
"step": 9552
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 25.0,
|
| 366 |
+
"eval_bleu": 0.4056,
|
| 367 |
+
"eval_gen_len": 19.0,
|
| 368 |
+
"eval_loss": 0.5959633588790894,
|
| 369 |
+
"eval_runtime": 35.9929,
|
| 370 |
+
"eval_samples_per_second": 22.06,
|
| 371 |
+
"eval_steps_per_second": 1.389,
|
| 372 |
+
"step": 9950
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 25.13,
|
| 376 |
+
"learning_rate": 3.7437185929648245e-05,
|
| 377 |
+
"loss": 0.4229,
|
| 378 |
+
"step": 10000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 26.0,
|
| 382 |
+
"eval_bleu": 0.4252,
|
| 383 |
+
"eval_gen_len": 19.0,
|
| 384 |
+
"eval_loss": 0.5961562395095825,
|
| 385 |
+
"eval_runtime": 36.1884,
|
| 386 |
+
"eval_samples_per_second": 21.941,
|
| 387 |
+
"eval_steps_per_second": 1.382,
|
| 388 |
+
"step": 10348
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 26.38,
|
| 392 |
+
"learning_rate": 3.6809045226130654e-05,
|
| 393 |
+
"loss": 0.4091,
|
| 394 |
+
"step": 10500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 27.0,
|
| 398 |
+
"eval_bleu": 0.4713,
|
| 399 |
+
"eval_gen_len": 19.0,
|
| 400 |
+
"eval_loss": 0.6049270629882812,
|
| 401 |
+
"eval_runtime": 36.1335,
|
| 402 |
+
"eval_samples_per_second": 21.974,
|
| 403 |
+
"eval_steps_per_second": 1.384,
|
| 404 |
+
"step": 10746
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 27.64,
|
| 408 |
+
"learning_rate": 3.618090452261307e-05,
|
| 409 |
+
"loss": 0.3965,
|
| 410 |
+
"step": 11000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 28.0,
|
| 414 |
+
"eval_bleu": 0.4242,
|
| 415 |
+
"eval_gen_len": 19.0,
|
| 416 |
+
"eval_loss": 0.6118378639221191,
|
| 417 |
+
"eval_runtime": 36.0809,
|
| 418 |
+
"eval_samples_per_second": 22.006,
|
| 419 |
+
"eval_steps_per_second": 1.386,
|
| 420 |
+
"step": 11144
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 28.89,
|
| 424 |
+
"learning_rate": 3.555276381909548e-05,
|
| 425 |
+
"loss": 0.3842,
|
| 426 |
+
"step": 11500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 29.0,
|
| 430 |
+
"eval_bleu": 0.3924,
|
| 431 |
+
"eval_gen_len": 19.0,
|
| 432 |
+
"eval_loss": 0.6169702410697937,
|
| 433 |
+
"eval_runtime": 35.9704,
|
| 434 |
+
"eval_samples_per_second": 22.074,
|
| 435 |
+
"eval_steps_per_second": 1.39,
|
| 436 |
+
"step": 11542
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 30.0,
|
| 440 |
+
"eval_bleu": 0.3984,
|
| 441 |
+
"eval_gen_len": 19.0,
|
| 442 |
+
"eval_loss": 0.6114440560340881,
|
| 443 |
+
"eval_runtime": 35.9519,
|
| 444 |
+
"eval_samples_per_second": 22.085,
|
| 445 |
+
"eval_steps_per_second": 1.391,
|
| 446 |
+
"step": 11940
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 30.15,
|
| 450 |
+
"learning_rate": 3.4924623115577894e-05,
|
| 451 |
+
"loss": 0.3718,
|
| 452 |
+
"step": 12000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 31.0,
|
| 456 |
+
"eval_bleu": 0.4186,
|
| 457 |
+
"eval_gen_len": 19.0,
|
| 458 |
+
"eval_loss": 0.6303505301475525,
|
| 459 |
+
"eval_runtime": 36.0633,
|
| 460 |
+
"eval_samples_per_second": 22.017,
|
| 461 |
+
"eval_steps_per_second": 1.386,
|
| 462 |
+
"step": 12338
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 31.41,
|
| 466 |
+
"learning_rate": 3.42964824120603e-05,
|
| 467 |
+
"loss": 0.3585,
|
| 468 |
+
"step": 12500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 32.0,
|
| 472 |
+
"eval_bleu": 0.3846,
|
| 473 |
+
"eval_gen_len": 19.0,
|
| 474 |
+
"eval_loss": 0.6364237070083618,
|
| 475 |
+
"eval_runtime": 36.1959,
|
| 476 |
+
"eval_samples_per_second": 21.936,
|
| 477 |
+
"eval_steps_per_second": 1.381,
|
| 478 |
+
"step": 12736
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 32.66,
|
| 482 |
+
"learning_rate": 3.366834170854272e-05,
|
| 483 |
+
"loss": 0.3473,
|
| 484 |
+
"step": 13000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 33.0,
|
| 488 |
+
"eval_bleu": 0.4058,
|
| 489 |
+
"eval_gen_len": 19.0,
|
| 490 |
+
"eval_loss": 0.6325276494026184,
|
| 491 |
+
"eval_runtime": 36.1326,
|
| 492 |
+
"eval_samples_per_second": 21.975,
|
| 493 |
+
"eval_steps_per_second": 1.384,
|
| 494 |
+
"step": 13134
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 33.92,
|
| 498 |
+
"learning_rate": 3.3040201005025127e-05,
|
| 499 |
+
"loss": 0.3377,
|
| 500 |
+
"step": 13500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 34.0,
|
| 504 |
+
"eval_bleu": 0.3669,
|
| 505 |
+
"eval_gen_len": 19.0,
|
| 506 |
+
"eval_loss": 0.6433637142181396,
|
| 507 |
+
"eval_runtime": 36.0557,
|
| 508 |
+
"eval_samples_per_second": 22.021,
|
| 509 |
+
"eval_steps_per_second": 1.387,
|
| 510 |
+
"step": 13532
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 35.0,
|
| 514 |
+
"eval_bleu": 0.396,
|
| 515 |
+
"eval_gen_len": 19.0,
|
| 516 |
+
"eval_loss": 0.6559302806854248,
|
| 517 |
+
"eval_runtime": 36.0966,
|
| 518 |
+
"eval_samples_per_second": 21.997,
|
| 519 |
+
"eval_steps_per_second": 1.385,
|
| 520 |
+
"step": 13930
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 35.18,
|
| 524 |
+
"learning_rate": 3.241206030150754e-05,
|
| 525 |
+
"loss": 0.3258,
|
| 526 |
+
"step": 14000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 36.0,
|
| 530 |
+
"eval_bleu": 0.4449,
|
| 531 |
+
"eval_gen_len": 19.0,
|
| 532 |
+
"eval_loss": 0.6613517999649048,
|
| 533 |
+
"eval_runtime": 36.0456,
|
| 534 |
+
"eval_samples_per_second": 22.028,
|
| 535 |
+
"eval_steps_per_second": 1.387,
|
| 536 |
+
"step": 14328
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 36.43,
|
| 540 |
+
"learning_rate": 3.178391959798995e-05,
|
| 541 |
+
"loss": 0.3144,
|
| 542 |
+
"step": 14500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 37.0,
|
| 546 |
+
"eval_bleu": 0.3988,
|
| 547 |
+
"eval_gen_len": 19.0,
|
| 548 |
+
"eval_loss": 0.6619016528129578,
|
| 549 |
+
"eval_runtime": 36.1443,
|
| 550 |
+
"eval_samples_per_second": 21.967,
|
| 551 |
+
"eval_steps_per_second": 1.383,
|
| 552 |
+
"step": 14726
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 37.69,
|
| 556 |
+
"learning_rate": 3.1155778894472366e-05,
|
| 557 |
+
"loss": 0.3062,
|
| 558 |
+
"step": 15000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 38.0,
|
| 562 |
+
"eval_bleu": 0.4133,
|
| 563 |
+
"eval_gen_len": 19.0,
|
| 564 |
+
"eval_loss": 0.681207537651062,
|
| 565 |
+
"eval_runtime": 36.0276,
|
| 566 |
+
"eval_samples_per_second": 22.039,
|
| 567 |
+
"eval_steps_per_second": 1.388,
|
| 568 |
+
"step": 15124
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 38.94,
|
| 572 |
+
"learning_rate": 3.0527638190954775e-05,
|
| 573 |
+
"loss": 0.2976,
|
| 574 |
+
"step": 15500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 39.0,
|
| 578 |
+
"eval_bleu": 0.4102,
|
| 579 |
+
"eval_gen_len": 19.0,
|
| 580 |
+
"eval_loss": 0.679516077041626,
|
| 581 |
+
"eval_runtime": 35.9945,
|
| 582 |
+
"eval_samples_per_second": 22.059,
|
| 583 |
+
"eval_steps_per_second": 1.389,
|
| 584 |
+
"step": 15522
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 40.0,
|
| 588 |
+
"eval_bleu": 0.3953,
|
| 589 |
+
"eval_gen_len": 19.0,
|
| 590 |
+
"eval_loss": 0.679844856262207,
|
| 591 |
+
"eval_runtime": 36.0821,
|
| 592 |
+
"eval_samples_per_second": 22.005,
|
| 593 |
+
"eval_steps_per_second": 1.386,
|
| 594 |
+
"step": 15920
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 40.2,
|
| 598 |
+
"learning_rate": 2.989949748743719e-05,
|
| 599 |
+
"loss": 0.2883,
|
| 600 |
+
"step": 16000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 41.0,
|
| 604 |
+
"eval_bleu": 0.3846,
|
| 605 |
+
"eval_gen_len": 19.0,
|
| 606 |
+
"eval_loss": 0.7088426947593689,
|
| 607 |
+
"eval_runtime": 36.412,
|
| 608 |
+
"eval_samples_per_second": 21.806,
|
| 609 |
+
"eval_steps_per_second": 1.373,
|
| 610 |
+
"step": 16318
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 41.46,
|
| 614 |
+
"learning_rate": 2.9271356783919603e-05,
|
| 615 |
+
"loss": 0.2791,
|
| 616 |
+
"step": 16500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 42.0,
|
| 620 |
+
"eval_bleu": 0.3701,
|
| 621 |
+
"eval_gen_len": 19.0,
|
| 622 |
+
"eval_loss": 0.7109950184822083,
|
| 623 |
+
"eval_runtime": 36.0424,
|
| 624 |
+
"eval_samples_per_second": 22.03,
|
| 625 |
+
"eval_steps_per_second": 1.387,
|
| 626 |
+
"step": 16716
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 42.71,
|
| 630 |
+
"learning_rate": 2.8643216080402015e-05,
|
| 631 |
+
"loss": 0.2701,
|
| 632 |
+
"step": 17000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 43.0,
|
| 636 |
+
"eval_bleu": 0.3985,
|
| 637 |
+
"eval_gen_len": 19.0,
|
| 638 |
+
"eval_loss": 0.7159502506256104,
|
| 639 |
+
"eval_runtime": 36.0448,
|
| 640 |
+
"eval_samples_per_second": 22.028,
|
| 641 |
+
"eval_steps_per_second": 1.387,
|
| 642 |
+
"step": 17114
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 43.97,
|
| 646 |
+
"learning_rate": 2.8015075376884427e-05,
|
| 647 |
+
"loss": 0.2619,
|
| 648 |
+
"step": 17500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 44.0,
|
| 652 |
+
"eval_bleu": 0.3654,
|
| 653 |
+
"eval_gen_len": 19.0,
|
| 654 |
+
"eval_loss": 0.7150431275367737,
|
| 655 |
+
"eval_runtime": 36.1383,
|
| 656 |
+
"eval_samples_per_second": 21.971,
|
| 657 |
+
"eval_steps_per_second": 1.384,
|
| 658 |
+
"step": 17512
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 45.0,
|
| 662 |
+
"eval_bleu": 0.394,
|
| 663 |
+
"eval_gen_len": 19.0,
|
| 664 |
+
"eval_loss": 0.7196872234344482,
|
| 665 |
+
"eval_runtime": 36.0028,
|
| 666 |
+
"eval_samples_per_second": 22.054,
|
| 667 |
+
"eval_steps_per_second": 1.389,
|
| 668 |
+
"step": 17910
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 45.23,
|
| 672 |
+
"learning_rate": 2.738693467336684e-05,
|
| 673 |
+
"loss": 0.2527,
|
| 674 |
+
"step": 18000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 46.0,
|
| 678 |
+
"eval_bleu": 0.4033,
|
| 679 |
+
"eval_gen_len": 19.0,
|
| 680 |
+
"eval_loss": 0.7386982440948486,
|
| 681 |
+
"eval_runtime": 36.1228,
|
| 682 |
+
"eval_samples_per_second": 21.981,
|
| 683 |
+
"eval_steps_per_second": 1.384,
|
| 684 |
+
"step": 18308
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 46.48,
|
| 688 |
+
"learning_rate": 2.6758793969849248e-05,
|
| 689 |
+
"loss": 0.2444,
|
| 690 |
+
"step": 18500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 47.0,
|
| 694 |
+
"eval_bleu": 0.389,
|
| 695 |
+
"eval_gen_len": 19.0,
|
| 696 |
+
"eval_loss": 0.7438174486160278,
|
| 697 |
+
"eval_runtime": 36.1308,
|
| 698 |
+
"eval_samples_per_second": 21.976,
|
| 699 |
+
"eval_steps_per_second": 1.384,
|
| 700 |
+
"step": 18706
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 47.74,
|
| 704 |
+
"learning_rate": 2.613065326633166e-05,
|
| 705 |
+
"loss": 0.239,
|
| 706 |
+
"step": 19000
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 48.0,
|
| 710 |
+
"eval_bleu": 0.3948,
|
| 711 |
+
"eval_gen_len": 19.0,
|
| 712 |
+
"eval_loss": 0.75967937707901,
|
| 713 |
+
"eval_runtime": 36.1293,
|
| 714 |
+
"eval_samples_per_second": 21.977,
|
| 715 |
+
"eval_steps_per_second": 1.384,
|
| 716 |
+
"step": 19104
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 48.99,
|
| 720 |
+
"learning_rate": 2.5502512562814072e-05,
|
| 721 |
+
"loss": 0.2303,
|
| 722 |
+
"step": 19500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 49.0,
|
| 726 |
+
"eval_bleu": 0.3976,
|
| 727 |
+
"eval_gen_len": 19.0,
|
| 728 |
+
"eval_loss": 0.7644997835159302,
|
| 729 |
+
"eval_runtime": 35.9794,
|
| 730 |
+
"eval_samples_per_second": 22.068,
|
| 731 |
+
"eval_steps_per_second": 1.39,
|
| 732 |
+
"step": 19502
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 50.0,
|
| 736 |
+
"eval_bleu": 0.385,
|
| 737 |
+
"eval_gen_len": 19.0,
|
| 738 |
+
"eval_loss": 0.7786132097244263,
|
| 739 |
+
"eval_runtime": 36.1835,
|
| 740 |
+
"eval_samples_per_second": 21.944,
|
| 741 |
+
"eval_steps_per_second": 1.382,
|
| 742 |
+
"step": 19900
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 50.25,
|
| 746 |
+
"learning_rate": 2.4874371859296484e-05,
|
| 747 |
+
"loss": 0.2212,
|
| 748 |
+
"step": 20000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 51.0,
|
| 752 |
+
"eval_bleu": 0.3948,
|
| 753 |
+
"eval_gen_len": 19.0,
|
| 754 |
+
"eval_loss": 0.7699110507965088,
|
| 755 |
+
"eval_runtime": 36.1227,
|
| 756 |
+
"eval_samples_per_second": 21.981,
|
| 757 |
+
"eval_steps_per_second": 1.384,
|
| 758 |
+
"step": 20298
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 51.51,
|
| 762 |
+
"learning_rate": 2.4246231155778896e-05,
|
| 763 |
+
"loss": 0.2157,
|
| 764 |
+
"step": 20500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 52.0,
|
| 768 |
+
"eval_bleu": 0.4265,
|
| 769 |
+
"eval_gen_len": 19.0,
|
| 770 |
+
"eval_loss": 0.7902213931083679,
|
| 771 |
+
"eval_runtime": 36.0895,
|
| 772 |
+
"eval_samples_per_second": 22.001,
|
| 773 |
+
"eval_steps_per_second": 1.385,
|
| 774 |
+
"step": 20696
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 52.76,
|
| 778 |
+
"learning_rate": 2.361809045226131e-05,
|
| 779 |
+
"loss": 0.2108,
|
| 780 |
+
"step": 21000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 53.0,
|
| 784 |
+
"eval_bleu": 0.3924,
|
| 785 |
+
"eval_gen_len": 19.0,
|
| 786 |
+
"eval_loss": 0.7906249761581421,
|
| 787 |
+
"eval_runtime": 35.9244,
|
| 788 |
+
"eval_samples_per_second": 22.102,
|
| 789 |
+
"eval_steps_per_second": 1.392,
|
| 790 |
+
"step": 21094
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 54.0,
|
| 794 |
+
"eval_bleu": 0.3849,
|
| 795 |
+
"eval_gen_len": 19.0,
|
| 796 |
+
"eval_loss": 0.8097977042198181,
|
| 797 |
+
"eval_runtime": 36.3421,
|
| 798 |
+
"eval_samples_per_second": 21.848,
|
| 799 |
+
"eval_steps_per_second": 1.376,
|
| 800 |
+
"step": 21492
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 54.02,
|
| 804 |
+
"learning_rate": 2.298994974874372e-05,
|
| 805 |
+
"loss": 0.2041,
|
| 806 |
+
"step": 21500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 55.0,
|
| 810 |
+
"eval_bleu": 0.3888,
|
| 811 |
+
"eval_gen_len": 19.0,
|
| 812 |
+
"eval_loss": 0.8166631460189819,
|
| 813 |
+
"eval_runtime": 36.1502,
|
| 814 |
+
"eval_samples_per_second": 21.964,
|
| 815 |
+
"eval_steps_per_second": 1.383,
|
| 816 |
+
"step": 21890
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 55.28,
|
| 820 |
+
"learning_rate": 2.2361809045226133e-05,
|
| 821 |
+
"loss": 0.1959,
|
| 822 |
+
"step": 22000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 56.0,
|
| 826 |
+
"eval_bleu": 0.4139,
|
| 827 |
+
"eval_gen_len": 19.0,
|
| 828 |
+
"eval_loss": 0.8316635489463806,
|
| 829 |
+
"eval_runtime": 36.2244,
|
| 830 |
+
"eval_samples_per_second": 21.919,
|
| 831 |
+
"eval_steps_per_second": 1.38,
|
| 832 |
+
"step": 22288
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 56.53,
|
| 836 |
+
"learning_rate": 2.1733668341708545e-05,
|
| 837 |
+
"loss": 0.1899,
|
| 838 |
+
"step": 22500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 57.0,
|
| 842 |
+
"eval_bleu": 0.4136,
|
| 843 |
+
"eval_gen_len": 19.0,
|
| 844 |
+
"eval_loss": 0.8344787359237671,
|
| 845 |
+
"eval_runtime": 36.367,
|
| 846 |
+
"eval_samples_per_second": 21.833,
|
| 847 |
+
"eval_steps_per_second": 1.375,
|
| 848 |
+
"step": 22686
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 57.79,
|
| 852 |
+
"learning_rate": 2.1105527638190957e-05,
|
| 853 |
+
"loss": 0.1868,
|
| 854 |
+
"step": 23000
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 58.0,
|
| 858 |
+
"eval_bleu": 0.4093,
|
| 859 |
+
"eval_gen_len": 19.0,
|
| 860 |
+
"eval_loss": 0.848408043384552,
|
| 861 |
+
"eval_runtime": 36.1717,
|
| 862 |
+
"eval_samples_per_second": 21.951,
|
| 863 |
+
"eval_steps_per_second": 1.382,
|
| 864 |
+
"step": 23084
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 59.0,
|
| 868 |
+
"eval_bleu": 0.4013,
|
| 869 |
+
"eval_gen_len": 19.0,
|
| 870 |
+
"eval_loss": 0.8663375973701477,
|
| 871 |
+
"eval_runtime": 36.2951,
|
| 872 |
+
"eval_samples_per_second": 21.876,
|
| 873 |
+
"eval_steps_per_second": 1.378,
|
| 874 |
+
"step": 23482
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 59.05,
|
| 878 |
+
"learning_rate": 2.047738693467337e-05,
|
| 879 |
+
"loss": 0.1815,
|
| 880 |
+
"step": 23500
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 60.0,
|
| 884 |
+
"eval_bleu": 0.3858,
|
| 885 |
+
"eval_gen_len": 19.0,
|
| 886 |
+
"eval_loss": 0.8709424734115601,
|
| 887 |
+
"eval_runtime": 36.2881,
|
| 888 |
+
"eval_samples_per_second": 21.88,
|
| 889 |
+
"eval_steps_per_second": 1.378,
|
| 890 |
+
"step": 23880
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 60.3,
|
| 894 |
+
"learning_rate": 1.984924623115578e-05,
|
| 895 |
+
"loss": 0.1744,
|
| 896 |
+
"step": 24000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 61.0,
|
| 900 |
+
"eval_bleu": 0.3716,
|
| 901 |
+
"eval_gen_len": 19.0,
|
| 902 |
+
"eval_loss": 0.8845000863075256,
|
| 903 |
+
"eval_runtime": 36.3319,
|
| 904 |
+
"eval_samples_per_second": 21.854,
|
| 905 |
+
"eval_steps_per_second": 1.376,
|
| 906 |
+
"step": 24278
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 61.56,
|
| 910 |
+
"learning_rate": 1.9221105527638193e-05,
|
| 911 |
+
"loss": 0.1709,
|
| 912 |
+
"step": 24500
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 62.0,
|
| 916 |
+
"eval_bleu": 0.3781,
|
| 917 |
+
"eval_gen_len": 19.0,
|
| 918 |
+
"eval_loss": 0.878656268119812,
|
| 919 |
+
"eval_runtime": 36.3634,
|
| 920 |
+
"eval_samples_per_second": 21.835,
|
| 921 |
+
"eval_steps_per_second": 1.375,
|
| 922 |
+
"step": 24676
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 62.81,
|
| 926 |
+
"learning_rate": 1.8592964824120602e-05,
|
| 927 |
+
"loss": 0.1659,
|
| 928 |
+
"step": 25000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 63.0,
|
| 932 |
+
"eval_bleu": 0.3642,
|
| 933 |
+
"eval_gen_len": 19.0,
|
| 934 |
+
"eval_loss": 0.8844317197799683,
|
| 935 |
+
"eval_runtime": 36.2676,
|
| 936 |
+
"eval_samples_per_second": 21.893,
|
| 937 |
+
"eval_steps_per_second": 1.379,
|
| 938 |
+
"step": 25074
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 64.0,
|
| 942 |
+
"eval_bleu": 0.3818,
|
| 943 |
+
"eval_gen_len": 19.0,
|
| 944 |
+
"eval_loss": 0.9034352898597717,
|
| 945 |
+
"eval_runtime": 36.4466,
|
| 946 |
+
"eval_samples_per_second": 21.785,
|
| 947 |
+
"eval_steps_per_second": 1.372,
|
| 948 |
+
"step": 25472
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 64.07,
|
| 952 |
+
"learning_rate": 1.7964824120603014e-05,
|
| 953 |
+
"loss": 0.1625,
|
| 954 |
+
"step": 25500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 65.0,
|
| 958 |
+
"eval_bleu": 0.3522,
|
| 959 |
+
"eval_gen_len": 19.0,
|
| 960 |
+
"eval_loss": 0.9116728901863098,
|
| 961 |
+
"eval_runtime": 36.294,
|
| 962 |
+
"eval_samples_per_second": 21.877,
|
| 963 |
+
"eval_steps_per_second": 1.378,
|
| 964 |
+
"step": 25870
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 65.33,
|
| 968 |
+
"learning_rate": 1.7336683417085427e-05,
|
| 969 |
+
"loss": 0.1568,
|
| 970 |
+
"step": 26000
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 66.0,
|
| 974 |
+
"eval_bleu": 0.3892,
|
| 975 |
+
"eval_gen_len": 19.0,
|
| 976 |
+
"eval_loss": 0.905901312828064,
|
| 977 |
+
"eval_runtime": 36.6662,
|
| 978 |
+
"eval_samples_per_second": 21.655,
|
| 979 |
+
"eval_steps_per_second": 1.364,
|
| 980 |
+
"step": 26268
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 66.58,
|
| 984 |
+
"learning_rate": 1.670854271356784e-05,
|
| 985 |
+
"loss": 0.1539,
|
| 986 |
+
"step": 26500
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 67.0,
|
| 990 |
+
"eval_bleu": 0.398,
|
| 991 |
+
"eval_gen_len": 19.0,
|
| 992 |
+
"eval_loss": 0.9159536957740784,
|
| 993 |
+
"eval_runtime": 36.246,
|
| 994 |
+
"eval_samples_per_second": 21.906,
|
| 995 |
+
"eval_steps_per_second": 1.379,
|
| 996 |
+
"step": 26666
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 67.84,
|
| 1000 |
+
"learning_rate": 1.608040201005025e-05,
|
| 1001 |
+
"loss": 0.1501,
|
| 1002 |
+
"step": 27000
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 68.0,
|
| 1006 |
+
"eval_bleu": 0.3831,
|
| 1007 |
+
"eval_gen_len": 19.0,
|
| 1008 |
+
"eval_loss": 0.9332515001296997,
|
| 1009 |
+
"eval_runtime": 36.3025,
|
| 1010 |
+
"eval_samples_per_second": 21.872,
|
| 1011 |
+
"eval_steps_per_second": 1.377,
|
| 1012 |
+
"step": 27064
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 69.0,
|
| 1016 |
+
"eval_bleu": 0.4036,
|
| 1017 |
+
"eval_gen_len": 19.0,
|
| 1018 |
+
"eval_loss": 0.9350541234016418,
|
| 1019 |
+
"eval_runtime": 36.3012,
|
| 1020 |
+
"eval_samples_per_second": 21.873,
|
| 1021 |
+
"eval_steps_per_second": 1.377,
|
| 1022 |
+
"step": 27462
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 69.1,
|
| 1026 |
+
"learning_rate": 1.5452261306532663e-05,
|
| 1027 |
+
"loss": 0.1461,
|
| 1028 |
+
"step": 27500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 70.0,
|
| 1032 |
+
"eval_bleu": 0.3727,
|
| 1033 |
+
"eval_gen_len": 19.0,
|
| 1034 |
+
"eval_loss": 0.9484046697616577,
|
| 1035 |
+
"eval_runtime": 36.3461,
|
| 1036 |
+
"eval_samples_per_second": 21.846,
|
| 1037 |
+
"eval_steps_per_second": 1.376,
|
| 1038 |
+
"step": 27860
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 70.35,
|
| 1042 |
+
"learning_rate": 1.4824120603015077e-05,
|
| 1043 |
+
"loss": 0.1413,
|
| 1044 |
+
"step": 28000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 71.0,
|
| 1048 |
+
"eval_bleu": 0.3638,
|
| 1049 |
+
"eval_gen_len": 19.0,
|
| 1050 |
+
"eval_loss": 0.9522455930709839,
|
| 1051 |
+
"eval_runtime": 36.2785,
|
| 1052 |
+
"eval_samples_per_second": 21.886,
|
| 1053 |
+
"eval_steps_per_second": 1.378,
|
| 1054 |
+
"step": 28258
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 71.61,
|
| 1058 |
+
"learning_rate": 1.4195979899497489e-05,
|
| 1059 |
+
"loss": 0.1405,
|
| 1060 |
+
"step": 28500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 72.0,
|
| 1064 |
+
"eval_bleu": 0.3501,
|
| 1065 |
+
"eval_gen_len": 19.0,
|
| 1066 |
+
"eval_loss": 0.97245192527771,
|
| 1067 |
+
"eval_runtime": 36.3096,
|
| 1068 |
+
"eval_samples_per_second": 21.868,
|
| 1069 |
+
"eval_steps_per_second": 1.377,
|
| 1070 |
+
"step": 28656
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 72.86,
|
| 1074 |
+
"learning_rate": 1.3567839195979901e-05,
|
| 1075 |
+
"loss": 0.1365,
|
| 1076 |
+
"step": 29000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 73.0,
|
| 1080 |
+
"eval_bleu": 0.372,
|
| 1081 |
+
"eval_gen_len": 19.0,
|
| 1082 |
+
"eval_loss": 0.9698021411895752,
|
| 1083 |
+
"eval_runtime": 36.0935,
|
| 1084 |
+
"eval_samples_per_second": 21.998,
|
| 1085 |
+
"eval_steps_per_second": 1.385,
|
| 1086 |
+
"step": 29054
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 74.0,
|
| 1090 |
+
"eval_bleu": 0.3727,
|
| 1091 |
+
"eval_gen_len": 19.0,
|
| 1092 |
+
"eval_loss": 0.9703381657600403,
|
| 1093 |
+
"eval_runtime": 36.1692,
|
| 1094 |
+
"eval_samples_per_second": 21.952,
|
| 1095 |
+
"eval_steps_per_second": 1.382,
|
| 1096 |
+
"step": 29452
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 74.12,
|
| 1100 |
+
"learning_rate": 1.2939698492462313e-05,
|
| 1101 |
+
"loss": 0.1328,
|
| 1102 |
+
"step": 29500
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 75.0,
|
| 1106 |
+
"eval_bleu": 0.3834,
|
| 1107 |
+
"eval_gen_len": 19.0,
|
| 1108 |
+
"eval_loss": 0.9797690510749817,
|
| 1109 |
+
"eval_runtime": 36.3947,
|
| 1110 |
+
"eval_samples_per_second": 21.816,
|
| 1111 |
+
"eval_steps_per_second": 1.374,
|
| 1112 |
+
"step": 29850
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 75.38,
|
| 1116 |
+
"learning_rate": 1.2311557788944725e-05,
|
| 1117 |
+
"loss": 0.1298,
|
| 1118 |
+
"step": 30000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 76.0,
|
| 1122 |
+
"eval_bleu": 0.4008,
|
| 1123 |
+
"eval_gen_len": 19.0,
|
| 1124 |
+
"eval_loss": 0.9849729537963867,
|
| 1125 |
+
"eval_runtime": 36.4039,
|
| 1126 |
+
"eval_samples_per_second": 21.811,
|
| 1127 |
+
"eval_steps_per_second": 1.373,
|
| 1128 |
+
"step": 30248
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 76.63,
|
| 1132 |
+
"learning_rate": 1.1683417085427137e-05,
|
| 1133 |
+
"loss": 0.1283,
|
| 1134 |
+
"step": 30500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 77.0,
|
| 1138 |
+
"eval_bleu": 0.3815,
|
| 1139 |
+
"eval_gen_len": 19.0,
|
| 1140 |
+
"eval_loss": 0.9988215565681458,
|
| 1141 |
+
"eval_runtime": 36.385,
|
| 1142 |
+
"eval_samples_per_second": 21.822,
|
| 1143 |
+
"eval_steps_per_second": 1.374,
|
| 1144 |
+
"step": 30646
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 77.89,
|
| 1148 |
+
"learning_rate": 1.105527638190955e-05,
|
| 1149 |
+
"loss": 0.1247,
|
| 1150 |
+
"step": 31000
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 78.0,
|
| 1154 |
+
"eval_bleu": 0.3621,
|
| 1155 |
+
"eval_gen_len": 19.0,
|
| 1156 |
+
"eval_loss": 0.9895645380020142,
|
| 1157 |
+
"eval_runtime": 36.1282,
|
| 1158 |
+
"eval_samples_per_second": 21.977,
|
| 1159 |
+
"eval_steps_per_second": 1.384,
|
| 1160 |
+
"step": 31044
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 79.0,
|
| 1164 |
+
"eval_bleu": 0.3761,
|
| 1165 |
+
"eval_gen_len": 19.0,
|
| 1166 |
+
"eval_loss": 1.0034637451171875,
|
| 1167 |
+
"eval_runtime": 36.0695,
|
| 1168 |
+
"eval_samples_per_second": 22.013,
|
| 1169 |
+
"eval_steps_per_second": 1.386,
|
| 1170 |
+
"step": 31442
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 79.15,
|
| 1174 |
+
"learning_rate": 1.042713567839196e-05,
|
| 1175 |
+
"loss": 0.1222,
|
| 1176 |
+
"step": 31500
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 80.0,
|
| 1180 |
+
"eval_bleu": 0.3729,
|
| 1181 |
+
"eval_gen_len": 19.0,
|
| 1182 |
+
"eval_loss": 1.0222601890563965,
|
| 1183 |
+
"eval_runtime": 36.0319,
|
| 1184 |
+
"eval_samples_per_second": 22.036,
|
| 1185 |
+
"eval_steps_per_second": 1.388,
|
| 1186 |
+
"step": 31840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 80.4,
|
| 1190 |
+
"learning_rate": 9.798994974874372e-06,
|
| 1191 |
+
"loss": 0.1195,
|
| 1192 |
+
"step": 32000
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 81.0,
|
| 1196 |
+
"eval_bleu": 0.3866,
|
| 1197 |
+
"eval_gen_len": 19.0,
|
| 1198 |
+
"eval_loss": 1.0171366930007935,
|
| 1199 |
+
"eval_runtime": 36.1451,
|
| 1200 |
+
"eval_samples_per_second": 21.967,
|
| 1201 |
+
"eval_steps_per_second": 1.383,
|
| 1202 |
+
"step": 32238
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 81.66,
|
| 1206 |
+
"learning_rate": 9.170854271356784e-06,
|
| 1207 |
+
"loss": 0.1189,
|
| 1208 |
+
"step": 32500
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 82.0,
|
| 1212 |
+
"eval_bleu": 0.3698,
|
| 1213 |
+
"eval_gen_len": 19.0,
|
| 1214 |
+
"eval_loss": 1.0247294902801514,
|
| 1215 |
+
"eval_runtime": 36.1151,
|
| 1216 |
+
"eval_samples_per_second": 21.985,
|
| 1217 |
+
"eval_steps_per_second": 1.384,
|
| 1218 |
+
"step": 32636
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 82.91,
|
| 1222 |
+
"learning_rate": 8.542713567839196e-06,
|
| 1223 |
+
"loss": 0.1175,
|
| 1224 |
+
"step": 33000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 83.0,
|
| 1228 |
+
"eval_bleu": 0.3657,
|
| 1229 |
+
"eval_gen_len": 19.0,
|
| 1230 |
+
"eval_loss": 1.0150783061981201,
|
| 1231 |
+
"eval_runtime": 36.212,
|
| 1232 |
+
"eval_samples_per_second": 21.926,
|
| 1233 |
+
"eval_steps_per_second": 1.381,
|
| 1234 |
+
"step": 33034
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 84.0,
|
| 1238 |
+
"eval_bleu": 0.3786,
|
| 1239 |
+
"eval_gen_len": 19.0,
|
| 1240 |
+
"eval_loss": 1.0387886762619019,
|
| 1241 |
+
"eval_runtime": 36.1399,
|
| 1242 |
+
"eval_samples_per_second": 21.97,
|
| 1243 |
+
"eval_steps_per_second": 1.384,
|
| 1244 |
+
"step": 33432
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 84.17,
|
| 1248 |
+
"learning_rate": 7.914572864321608e-06,
|
| 1249 |
+
"loss": 0.1146,
|
| 1250 |
+
"step": 33500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 85.0,
|
| 1254 |
+
"eval_bleu": 0.3737,
|
| 1255 |
+
"eval_gen_len": 19.0,
|
| 1256 |
+
"eval_loss": 1.0412553548812866,
|
| 1257 |
+
"eval_runtime": 36.1355,
|
| 1258 |
+
"eval_samples_per_second": 21.973,
|
| 1259 |
+
"eval_steps_per_second": 1.384,
|
| 1260 |
+
"step": 33830
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 85.43,
|
| 1264 |
+
"learning_rate": 7.28643216080402e-06,
|
| 1265 |
+
"loss": 0.1124,
|
| 1266 |
+
"step": 34000
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 86.0,
|
| 1270 |
+
"eval_bleu": 0.3803,
|
| 1271 |
+
"eval_gen_len": 19.0,
|
| 1272 |
+
"eval_loss": 1.0402462482452393,
|
| 1273 |
+
"eval_runtime": 36.3349,
|
| 1274 |
+
"eval_samples_per_second": 21.852,
|
| 1275 |
+
"eval_steps_per_second": 1.376,
|
| 1276 |
+
"step": 34228
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 86.68,
|
| 1280 |
+
"learning_rate": 6.658291457286432e-06,
|
| 1281 |
+
"loss": 0.1125,
|
| 1282 |
+
"step": 34500
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 87.0,
|
| 1286 |
+
"eval_bleu": 0.3746,
|
| 1287 |
+
"eval_gen_len": 19.0,
|
| 1288 |
+
"eval_loss": 1.0519098043441772,
|
| 1289 |
+
"eval_runtime": 36.2307,
|
| 1290 |
+
"eval_samples_per_second": 21.915,
|
| 1291 |
+
"eval_steps_per_second": 1.38,
|
| 1292 |
+
"step": 34626
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 87.94,
|
| 1296 |
+
"learning_rate": 6.030150753768844e-06,
|
| 1297 |
+
"loss": 0.1102,
|
| 1298 |
+
"step": 35000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 88.0,
|
| 1302 |
+
"eval_bleu": 0.3863,
|
| 1303 |
+
"eval_gen_len": 19.0,
|
| 1304 |
+
"eval_loss": 1.054201364517212,
|
| 1305 |
+
"eval_runtime": 36.1231,
|
| 1306 |
+
"eval_samples_per_second": 21.98,
|
| 1307 |
+
"eval_steps_per_second": 1.384,
|
| 1308 |
+
"step": 35024
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 89.0,
|
| 1312 |
+
"eval_bleu": 0.3839,
|
| 1313 |
+
"eval_gen_len": 19.0,
|
| 1314 |
+
"eval_loss": 1.0626344680786133,
|
| 1315 |
+
"eval_runtime": 36.1414,
|
| 1316 |
+
"eval_samples_per_second": 21.969,
|
| 1317 |
+
"eval_steps_per_second": 1.383,
|
| 1318 |
+
"step": 35422
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 89.2,
|
| 1322 |
+
"learning_rate": 5.402010050251256e-06,
|
| 1323 |
+
"loss": 0.1075,
|
| 1324 |
+
"step": 35500
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 90.0,
|
| 1328 |
+
"eval_bleu": 0.3615,
|
| 1329 |
+
"eval_gen_len": 19.0,
|
| 1330 |
+
"eval_loss": 1.060184359550476,
|
| 1331 |
+
"eval_runtime": 36.2676,
|
| 1332 |
+
"eval_samples_per_second": 21.893,
|
| 1333 |
+
"eval_steps_per_second": 1.379,
|
| 1334 |
+
"step": 35820
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 90.45,
|
| 1338 |
+
"learning_rate": 4.773869346733668e-06,
|
| 1339 |
+
"loss": 0.1069,
|
| 1340 |
+
"step": 36000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 91.0,
|
| 1344 |
+
"eval_bleu": 0.3692,
|
| 1345 |
+
"eval_gen_len": 19.0,
|
| 1346 |
+
"eval_loss": 1.0700898170471191,
|
| 1347 |
+
"eval_runtime": 36.428,
|
| 1348 |
+
"eval_samples_per_second": 21.796,
|
| 1349 |
+
"eval_steps_per_second": 1.373,
|
| 1350 |
+
"step": 36218
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 91.71,
|
| 1354 |
+
"learning_rate": 4.1457286432160804e-06,
|
| 1355 |
+
"loss": 0.1062,
|
| 1356 |
+
"step": 36500
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 92.0,
|
| 1360 |
+
"eval_bleu": 0.3719,
|
| 1361 |
+
"eval_gen_len": 19.0,
|
| 1362 |
+
"eval_loss": 1.069925308227539,
|
| 1363 |
+
"eval_runtime": 36.0404,
|
| 1364 |
+
"eval_samples_per_second": 22.031,
|
| 1365 |
+
"eval_steps_per_second": 1.387,
|
| 1366 |
+
"step": 36616
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 92.96,
|
| 1370 |
+
"learning_rate": 3.5175879396984926e-06,
|
| 1371 |
+
"loss": 0.1051,
|
| 1372 |
+
"step": 37000
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 93.0,
|
| 1376 |
+
"eval_bleu": 0.3667,
|
| 1377 |
+
"eval_gen_len": 19.0,
|
| 1378 |
+
"eval_loss": 1.0732213258743286,
|
| 1379 |
+
"eval_runtime": 36.1316,
|
| 1380 |
+
"eval_samples_per_second": 21.975,
|
| 1381 |
+
"eval_steps_per_second": 1.384,
|
| 1382 |
+
"step": 37014
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 94.0,
|
| 1386 |
+
"eval_bleu": 0.3701,
|
| 1387 |
+
"eval_gen_len": 19.0,
|
| 1388 |
+
"eval_loss": 1.0749058723449707,
|
| 1389 |
+
"eval_runtime": 36.2293,
|
| 1390 |
+
"eval_samples_per_second": 21.916,
|
| 1391 |
+
"eval_steps_per_second": 1.38,
|
| 1392 |
+
"step": 37412
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 94.22,
|
| 1396 |
+
"learning_rate": 2.8894472361809047e-06,
|
| 1397 |
+
"loss": 0.1041,
|
| 1398 |
+
"step": 37500
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 95.0,
|
| 1402 |
+
"eval_bleu": 0.3744,
|
| 1403 |
+
"eval_gen_len": 19.0,
|
| 1404 |
+
"eval_loss": 1.0795801877975464,
|
| 1405 |
+
"eval_runtime": 36.2285,
|
| 1406 |
+
"eval_samples_per_second": 21.916,
|
| 1407 |
+
"eval_steps_per_second": 1.38,
|
| 1408 |
+
"step": 37810
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 95.48,
|
| 1412 |
+
"learning_rate": 2.261306532663317e-06,
|
| 1413 |
+
"loss": 0.1034,
|
| 1414 |
+
"step": 38000
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 96.0,
|
| 1418 |
+
"eval_bleu": 0.3771,
|
| 1419 |
+
"eval_gen_len": 19.0,
|
| 1420 |
+
"eval_loss": 1.0823085308074951,
|
| 1421 |
+
"eval_runtime": 36.0893,
|
| 1422 |
+
"eval_samples_per_second": 22.001,
|
| 1423 |
+
"eval_steps_per_second": 1.385,
|
| 1424 |
+
"step": 38208
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 96.73,
|
| 1428 |
+
"learning_rate": 1.6331658291457288e-06,
|
| 1429 |
+
"loss": 0.1031,
|
| 1430 |
+
"step": 38500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 97.0,
|
| 1434 |
+
"eval_bleu": 0.3775,
|
| 1435 |
+
"eval_gen_len": 19.0,
|
| 1436 |
+
"eval_loss": 1.0796533823013306,
|
| 1437 |
+
"eval_runtime": 36.264,
|
| 1438 |
+
"eval_samples_per_second": 21.895,
|
| 1439 |
+
"eval_steps_per_second": 1.379,
|
| 1440 |
+
"step": 38606
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 97.99,
|
| 1444 |
+
"learning_rate": 1.0050251256281407e-06,
|
| 1445 |
+
"loss": 0.1015,
|
| 1446 |
+
"step": 39000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 98.0,
|
| 1450 |
+
"eval_bleu": 0.3822,
|
| 1451 |
+
"eval_gen_len": 19.0,
|
| 1452 |
+
"eval_loss": 1.0842037200927734,
|
| 1453 |
+
"eval_runtime": 36.1692,
|
| 1454 |
+
"eval_samples_per_second": 21.952,
|
| 1455 |
+
"eval_steps_per_second": 1.382,
|
| 1456 |
+
"step": 39004
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 99.0,
|
| 1460 |
+
"eval_bleu": 0.3839,
|
| 1461 |
+
"eval_gen_len": 19.0,
|
| 1462 |
+
"eval_loss": 1.0859404802322388,
|
| 1463 |
+
"eval_runtime": 36.1094,
|
| 1464 |
+
"eval_samples_per_second": 21.989,
|
| 1465 |
+
"eval_steps_per_second": 1.385,
|
| 1466 |
+
"step": 39402
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 99.25,
|
| 1470 |
+
"learning_rate": 3.7688442211055275e-07,
|
| 1471 |
+
"loss": 0.1007,
|
| 1472 |
+
"step": 39500
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 100.0,
|
| 1476 |
+
"eval_bleu": 0.3829,
|
| 1477 |
+
"eval_gen_len": 19.0,
|
| 1478 |
+
"eval_loss": 1.0861998796463013,
|
| 1479 |
+
"eval_runtime": 36.126,
|
| 1480 |
+
"eval_samples_per_second": 21.979,
|
| 1481 |
+
"eval_steps_per_second": 1.384,
|
| 1482 |
+
"step": 39800
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 100.0,
|
| 1486 |
+
"step": 39800,
|
| 1487 |
+
"total_flos": 2.2595375365462426e+17,
|
| 1488 |
+
"train_loss": 0.31051562630351465,
|
| 1489 |
+
"train_runtime": 21104.6673,
|
| 1490 |
+
"train_samples_per_second": 30.107,
|
| 1491 |
+
"train_steps_per_second": 1.886
|
| 1492 |
}
|
| 1493 |
],
|
| 1494 |
+
"max_steps": 39800,
|
| 1495 |
+
"num_train_epochs": 100,
|
| 1496 |
+
"total_flos": 2.2595375365462426e+17,
|
| 1497 |
"trial_name": null,
|
| 1498 |
"trial_params": null
|
| 1499 |
}
|