End of training
Browse files- README.md +2 -2
- all_results.json +14 -14
- eval_results.json +8 -8
- train_results.json +7 -7
- trainer_state.json +0 -0
README.md
CHANGED
|
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 3.
|
| 20 |
-
- Accuracy: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 3.3092
|
| 20 |
+
- Accuracy: 0.3933
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
all_results.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 3.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples":
|
| 7 |
-
"eval_samples_per_second": 99.
|
| 8 |
-
"eval_steps_per_second": 6.
|
| 9 |
-
"perplexity":
|
| 10 |
-
"total_flos":
|
| 11 |
-
"train_loss":
|
| 12 |
-
"train_runtime":
|
| 13 |
-
"train_samples":
|
| 14 |
-
"train_samples_per_second":
|
| 15 |
-
"train_steps_per_second":
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.3932824917497146,
|
| 4 |
+
"eval_loss": 3.3091650009155273,
|
| 5 |
+
"eval_runtime": 181.0992,
|
| 6 |
+
"eval_samples": 18011,
|
| 7 |
+
"eval_samples_per_second": 99.454,
|
| 8 |
+
"eval_steps_per_second": 6.218,
|
| 9 |
+
"perplexity": 27.3622684613255,
|
| 10 |
+
"total_flos": 7.7681598529536e+17,
|
| 11 |
+
"train_loss": 3.4581795185890973,
|
| 12 |
+
"train_runtime": 79338.7604,
|
| 13 |
+
"train_samples": 297298,
|
| 14 |
+
"train_samples_per_second": 37.472,
|
| 15 |
+
"train_steps_per_second": 1.171
|
| 16 |
}
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 3.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples":
|
| 7 |
-
"eval_samples_per_second": 99.
|
| 8 |
-
"eval_steps_per_second": 6.
|
| 9 |
-
"perplexity":
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.3932824917497146,
|
| 4 |
+
"eval_loss": 3.3091650009155273,
|
| 5 |
+
"eval_runtime": 181.0992,
|
| 6 |
+
"eval_samples": 18011,
|
| 7 |
+
"eval_samples_per_second": 99.454,
|
| 8 |
+
"eval_steps_per_second": 6.218,
|
| 9 |
+
"perplexity": 27.3622684613255
|
| 10 |
}
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples":
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 7.7681598529536e+17,
|
| 4 |
+
"train_loss": 3.4581795185890973,
|
| 5 |
+
"train_runtime": 79338.7604,
|
| 6 |
+
"train_samples": 297298,
|
| 7 |
+
"train_samples_per_second": 37.472,
|
| 8 |
+
"train_steps_per_second": 1.171
|
| 9 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|