End of training
Browse files- all_results.json +18 -0
- eval_results.json +13 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_bleu": 78.2542,
|
| 4 |
+
"eval_cer": 2.1669,
|
| 5 |
+
"eval_chrF": 95.73544319509031,
|
| 6 |
+
"eval_gen_len": 16.777936,
|
| 7 |
+
"eval_loss": 0.48148927092552185,
|
| 8 |
+
"eval_runtime": 7352.4857,
|
| 9 |
+
"eval_samples": 250000,
|
| 10 |
+
"eval_samples_per_second": 34.002,
|
| 11 |
+
"eval_steps_per_second": 0.531,
|
| 12 |
+
"eval_wer": 12.1294,
|
| 13 |
+
"train_loss": 0.2851236777235189,
|
| 14 |
+
"train_runtime": 119967.4266,
|
| 15 |
+
"train_samples": 11385346,
|
| 16 |
+
"train_samples_per_second": 474.518,
|
| 17 |
+
"train_steps_per_second": 7.414
|
| 18 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_bleu": 78.2542,
|
| 4 |
+
"eval_cer": 2.1669,
|
| 5 |
+
"eval_chrF": 95.73544319509031,
|
| 6 |
+
"eval_gen_len": 16.777936,
|
| 7 |
+
"eval_loss": 0.48148927092552185,
|
| 8 |
+
"eval_runtime": 7352.4857,
|
| 9 |
+
"eval_samples": 250000,
|
| 10 |
+
"eval_samples_per_second": 34.002,
|
| 11 |
+
"eval_steps_per_second": 0.531,
|
| 12 |
+
"eval_wer": 12.1294
|
| 13 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.2851236777235189,
|
| 4 |
+
"train_runtime": 119967.4266,
|
| 5 |
+
"train_samples": 11385346,
|
| 6 |
+
"train_samples_per_second": 474.518,
|
| 7 |
+
"train_steps_per_second": 7.414
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|