Model save
Browse files- all_results.json +4 -4
- config.json +1 -1
- 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": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 374,
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
+
"train_loss": 0.019628612981648565,
|
| 4 |
+
"train_runtime": 7912.6404,
|
| 5 |
"train_samples": 374,
|
| 6 |
+
"train_samples_per_second": 0.379,
|
| 7 |
+
"train_steps_per_second": 0.063
|
| 8 |
}
|
config.json
CHANGED
|
@@ -25,6 +25,6 @@
|
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
"transformers_version": "4.48.1",
|
| 28 |
-
"use_cache":
|
| 29 |
"vocab_size": 32016
|
| 30 |
}
|
|
|
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
"transformers_version": "4.48.1",
|
| 28 |
+
"use_cache": true,
|
| 29 |
"vocab_size": 32016
|
| 30 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 374,
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
+
"train_loss": 0.019628612981648565,
|
| 4 |
+
"train_runtime": 7912.6404,
|
| 5 |
"train_samples": 374,
|
| 6 |
+
"train_samples_per_second": 0.379,
|
| 7 |
+
"train_steps_per_second": 0.063
|
| 8 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|