tiagoblima
commited on
Commit
•
a7a9ced
1
Parent(s):
aa2dee1
End of training
Browse files- README.md +5 -1
- all_results.json +6 -6
- eval_results.json +3 -3
- train_results.json +3 -3
- trainer_state.json +3 -3
README.md
CHANGED
@@ -3,6 +3,8 @@ license: mit
|
|
3 |
base_model: unicamp-dl/ptt5-small-t5-vocab
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: t5_small-qg-ctx-a
|
8 |
results: []
|
@@ -13,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# t5_small-qg-ctx-a
|
15 |
|
16 |
-
This model is a fine-tuned version of [unicamp-dl/ptt5-small-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-small-t5-vocab) on
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
3 |
base_model: unicamp-dl/ptt5-small-t5-vocab
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- tiagoblima/qg_squad_v1_pt
|
8 |
model-index:
|
9 |
- name: t5_small-qg-ctx-a
|
10 |
results: []
|
|
|
15 |
|
16 |
# t5_small-qg-ctx-a
|
17 |
|
18 |
+
This model is a fine-tuned version of [unicamp-dl/ptt5-small-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-small-t5-vocab) on the tiagoblima/qg_squad_v1_pt dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.4560
|
21 |
|
22 |
## Model description
|
23 |
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 1.99,
|
3 |
"eval_loss": 1.4559680223464966,
|
4 |
-
"eval_runtime": 73.
|
5 |
"eval_samples": 8961,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 15.
|
8 |
"train_loss": 0.0,
|
9 |
-
"train_runtime": 1.
|
10 |
"train_samples": 52135,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second":
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.99,
|
3 |
"eval_loss": 1.4559680223464966,
|
4 |
+
"eval_runtime": 73.4318,
|
5 |
"eval_samples": 8961,
|
6 |
+
"eval_samples_per_second": 122.032,
|
7 |
+
"eval_steps_per_second": 15.266,
|
8 |
"train_loss": 0.0,
|
9 |
+
"train_runtime": 1.4602,
|
10 |
"train_samples": 52135,
|
11 |
+
"train_samples_per_second": 178521.398,
|
12 |
+
"train_steps_per_second": 2790.734
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.99,
|
3 |
"eval_loss": 1.4559680223464966,
|
4 |
-
"eval_runtime": 73.
|
5 |
"eval_samples": 8961,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 15.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.99,
|
3 |
"eval_loss": 1.4559680223464966,
|
4 |
+
"eval_runtime": 73.4318,
|
5 |
"eval_samples": 8961,
|
6 |
+
"eval_samples_per_second": 122.032,
|
7 |
+
"eval_steps_per_second": 15.266
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.99,
|
3 |
"train_loss": 0.0,
|
4 |
-
"train_runtime": 1.
|
5 |
"train_samples": 52135,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.99,
|
3 |
"train_loss": 0.0,
|
4 |
+
"train_runtime": 1.4602,
|
5 |
"train_samples": 52135,
|
6 |
+
"train_samples_per_second": 178521.398,
|
7 |
+
"train_steps_per_second": 2790.734
|
8 |
}
|
trainer_state.json
CHANGED
@@ -637,9 +637,9 @@
|
|
637 |
"step": 52000,
|
638 |
"total_flos": 1.0556660514816e+16,
|
639 |
"train_loss": 0.0,
|
640 |
-
"train_runtime": 1.
|
641 |
-
"train_samples_per_second":
|
642 |
-
"train_steps_per_second":
|
643 |
}
|
644 |
],
|
645 |
"logging_steps": 500,
|
|
|
637 |
"step": 52000,
|
638 |
"total_flos": 1.0556660514816e+16,
|
639 |
"train_loss": 0.0,
|
640 |
+
"train_runtime": 1.4602,
|
641 |
+
"train_samples_per_second": 178521.398,
|
642 |
+
"train_steps_per_second": 2790.734
|
643 |
}
|
644 |
],
|
645 |
"logging_steps": 500,
|