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": 2.33956241607666,
|
4 |
+
"eval_CLS_accuracy": 0.622478386167147,
|
5 |
+
"eval_CLS_f1": 0.615766951227354,
|
6 |
+
"eval_CLS_precision": 0.619580054950422,
|
7 |
+
"eval_CLS_recall": 0.622478386167147,
|
8 |
+
"eval_LM loss": 11.057974815368652,
|
9 |
+
"eval_Perplexity": "63447.93",
|
10 |
+
"eval_loss": 2.3409106731414795,
|
11 |
+
"eval_runtime": 116.8259,
|
12 |
+
"eval_samples_per_second": 14.851,
|
13 |
+
"eval_steps_per_second": 7.43,
|
14 |
+
"total_flos": 1.088098614116352e+16,
|
15 |
+
"train_loss": 0.9344328573411984,
|
16 |
+
"train_runtime": 3737.2556,
|
17 |
+
"train_samples_per_second": 5.571,
|
18 |
+
"train_steps_per_second": 2.785
|
19 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 1.088098614116352e+16,
|
4 |
+
"train_loss": 0.9344328573411984,
|
5 |
+
"train_runtime": 3737.2556,
|
6 |
+
"train_samples_per_second": 5.571,
|
7 |
+
"train_steps_per_second": 2.785
|
8 |
+
}
|
with_eval_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_CLS loss": 2.33956241607666,
|
4 |
+
"eval_CLS_accuracy": 0.622478386167147,
|
5 |
+
"eval_CLS_f1": 0.615766951227354,
|
6 |
+
"eval_CLS_precision": 0.619580054950422,
|
7 |
+
"eval_CLS_recall": 0.622478386167147,
|
8 |
+
"eval_LM loss": 11.057974815368652,
|
9 |
+
"eval_Perplexity": "63447.93",
|
10 |
+
"eval_loss": 2.3409106731414795,
|
11 |
+
"eval_runtime": 116.8259,
|
12 |
+
"eval_samples_per_second": 14.851,
|
13 |
+
"eval_steps_per_second": 7.43
|
14 |
+
}
|