Model save
Browse files- all_results.json +12 -0
- generation_config.json +8 -0
- train_results.json +12 -0
- trainer_state.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"entropy": 0.15305225551128387,
|
| 3 |
+
"epoch": 1.0,
|
| 4 |
+
"mean_token_accuracy": 0.9391315132379532,
|
| 5 |
+
"num_tokens": 117107840.0,
|
| 6 |
+
"total_flos": 246067485081600.0,
|
| 7 |
+
"train_loss": 0.17793139662661192,
|
| 8 |
+
"train_runtime": 3132.2908,
|
| 9 |
+
"train_samples": 239866,
|
| 10 |
+
"train_samples_per_second": 76.578,
|
| 11 |
+
"train_steps_per_second": 0.598
|
| 12 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 128009,
|
| 5 |
+
"temperature": 0.6,
|
| 6 |
+
"top_p": 0.9,
|
| 7 |
+
"transformers_version": "4.56.1"
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"entropy": 0.15305225551128387,
|
| 3 |
+
"epoch": 1.0,
|
| 4 |
+
"mean_token_accuracy": 0.9391315132379532,
|
| 5 |
+
"num_tokens": 117107840.0,
|
| 6 |
+
"total_flos": 246067485081600.0,
|
| 7 |
+
"train_loss": 0.17793139662661192,
|
| 8 |
+
"train_runtime": 3132.2908,
|
| 9 |
+
"train_samples": 239866,
|
| 10 |
+
"train_samples_per_second": 76.578,
|
| 11 |
+
"train_steps_per_second": 0.598
|
| 12 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|