Model save
Browse files- all_results.json +4 -4
- generation_config.json +1 -3
- train_results.json +4 -4
- trainer_state.json +0 -0
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 2027,
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
+
"train_loss": 0.017275968565728463,
|
| 4 |
+
"train_runtime": 4300.0312,
|
| 5 |
"train_samples": 2027,
|
| 6 |
+
"train_samples_per_second": 0.471,
|
| 7 |
+
"train_steps_per_second": 0.059
|
| 8 |
}
|
generation_config.json
CHANGED
|
@@ -2,9 +2,7 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 151646,
|
| 4 |
"do_sample": true,
|
| 5 |
-
"eos_token_id":
|
| 6 |
-
151643
|
| 7 |
-
],
|
| 8 |
"pad_token_id": 151643,
|
| 9 |
"temperature": 0.6,
|
| 10 |
"top_p": 0.95,
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 151646,
|
| 4 |
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
|
|
|
|
|
|
| 6 |
"pad_token_id": 151643,
|
| 7 |
"temperature": 0.6,
|
| 8 |
"top_p": 0.95,
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 2027,
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
+
"train_loss": 0.017275968565728463,
|
| 4 |
+
"train_runtime": 4300.0312,
|
| 5 |
"train_samples": 2027,
|
| 6 |
+
"train_samples_per_second": 0.471,
|
| 7 |
+
"train_steps_per_second": 0.059
|
| 8 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|