End of training
Browse files- all_results.json +19 -0
- train_results.json +8 -0
- with_eval_results.json +14 -0
all_results.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_CLS loss": 1.5777798891067505,
|
4 |
+
"eval_CLS_accuracy": 0.6201729106628242,
|
5 |
+
"eval_CLS_f1": 0.6125731879708048,
|
6 |
+
"eval_CLS_precision": 0.6216224034048498,
|
7 |
+
"eval_CLS_recall": 0.6201729106628242,
|
8 |
+
"eval_LM loss": 3.9608688354492188,
|
9 |
+
"eval_Perplexity": "52.50",
|
10 |
+
"eval_loss": 4.355612277984619,
|
11 |
+
"eval_runtime": 106.4477,
|
12 |
+
"eval_samples_per_second": 16.299,
|
13 |
+
"eval_steps_per_second": 8.154,
|
14 |
+
"total_flos": 1.088098614116352e+16,
|
15 |
+
"train_loss": 4.11131799351585,
|
16 |
+
"train_runtime": 5817.7923,
|
17 |
+
"train_samples_per_second": 3.579,
|
18 |
+
"train_steps_per_second": 1.789
|
19 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 1.088098614116352e+16,
|
4 |
+
"train_loss": 4.11131799351585,
|
5 |
+
"train_runtime": 5817.7923,
|
6 |
+
"train_samples_per_second": 3.579,
|
7 |
+
"train_steps_per_second": 1.789
|
8 |
+
}
|
with_eval_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_CLS loss": 1.5777798891067505,
|
4 |
+
"eval_CLS_accuracy": 0.6201729106628242,
|
5 |
+
"eval_CLS_f1": 0.6125731879708048,
|
6 |
+
"eval_CLS_precision": 0.6216224034048498,
|
7 |
+
"eval_CLS_recall": 0.6201729106628242,
|
8 |
+
"eval_LM loss": 3.9608688354492188,
|
9 |
+
"eval_Perplexity": "52.50",
|
10 |
+
"eval_loss": 4.355612277984619,
|
11 |
+
"eval_runtime": 106.4477,
|
12 |
+
"eval_samples_per_second": 16.299,
|
13 |
+
"eval_steps_per_second": 8.154
|
14 |
+
}
|