End of training
Browse files- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 16.0,
|
| 3 |
+
"eval_accuracy": 0.6455613969659421,
|
| 4 |
+
"eval_loss": 2.0316429138183594,
|
| 5 |
+
"eval_runtime": 16.3016,
|
| 6 |
+
"eval_samples": 2197,
|
| 7 |
+
"eval_samples_per_second": 134.772,
|
| 8 |
+
"eval_steps_per_second": 67.417,
|
| 9 |
+
"perplexity": 7.626605927943553,
|
| 10 |
+
"train_loss": 2.4320973860366,
|
| 11 |
+
"train_runtime": 3195.9564,
|
| 12 |
+
"train_samples": 19711,
|
| 13 |
+
"train_samples_per_second": 98.68,
|
| 14 |
+
"train_steps_per_second": 1.542
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 16.0,
|
| 3 |
+
"eval_accuracy": 0.6455613969659421,
|
| 4 |
+
"eval_loss": 2.0316429138183594,
|
| 5 |
+
"eval_runtime": 16.3016,
|
| 6 |
+
"eval_samples": 2197,
|
| 7 |
+
"eval_samples_per_second": 134.772,
|
| 8 |
+
"eval_steps_per_second": 67.417,
|
| 9 |
+
"perplexity": 7.626605927943553
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 16.0,
|
| 3 |
+
"train_loss": 2.4320973860366,
|
| 4 |
+
"train_runtime": 3195.9564,
|
| 5 |
+
"train_samples": 19711,
|
| 6 |
+
"train_samples_per_second": 98.68,
|
| 7 |
+
"train_steps_per_second": 1.542
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|