tiagoblima
commited on
Commit
•
694c65f
1
Parent(s):
2ce81e3
End of training
Browse files- README.md +5 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +58 -0
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: debug_t5-small_squad
|
8 |
results: []
|
@@ -13,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# debug_t5-small_squad
|
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: debug_t5-small_squad
|
10 |
results: []
|
|
|
15 |
|
16 |
# debug_t5-small_squad
|
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: 1.5792
|
21 |
|
22 |
## Model description
|
23 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_loss": 1.5792150497436523,
|
4 |
+
"eval_runtime": 130.2194,
|
5 |
+
"eval_samples": 14945,
|
6 |
+
"eval_samples_per_second": 114.768,
|
7 |
+
"eval_steps_per_second": 14.353,
|
8 |
+
"train_loss": 1.4037482273500275,
|
9 |
+
"train_runtime": 3969.1352,
|
10 |
+
"train_samples": 87599,
|
11 |
+
"train_samples_per_second": 44.14,
|
12 |
+
"train_steps_per_second": 0.69
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_loss": 1.5792150497436523,
|
4 |
+
"eval_runtime": 130.2194,
|
5 |
+
"eval_samples": 14945,
|
6 |
+
"eval_samples_per_second": 114.768,
|
7 |
+
"eval_steps_per_second": 14.353
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 1.4037482273500275,
|
4 |
+
"train_runtime": 3969.1352,
|
5 |
+
"train_samples": 87599,
|
6 |
+
"train_samples_per_second": 44.14,
|
7 |
+
"train_steps_per_second": 0.69
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2738,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.37,
|
13 |
+
"learning_rate": 8.692476260043827e-06,
|
14 |
+
"loss": 1.2919,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.73,
|
19 |
+
"learning_rate": 0.0,
|
20 |
+
"loss": 1.4435,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.1,
|
25 |
+
"learning_rate": 0.0,
|
26 |
+
"loss": 1.4318,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.46,
|
31 |
+
"learning_rate": 0.0,
|
32 |
+
"loss": 1.4235,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.83,
|
37 |
+
"learning_rate": 0.0,
|
38 |
+
"loss": 1.4192,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.0,
|
43 |
+
"step": 2738,
|
44 |
+
"total_flos": 1.7783709700718592e+16,
|
45 |
+
"train_loss": 1.4037482273500275,
|
46 |
+
"train_runtime": 3969.1352,
|
47 |
+
"train_samples_per_second": 44.14,
|
48 |
+
"train_steps_per_second": 0.69
|
49 |
+
}
|
50 |
+
],
|
51 |
+
"logging_steps": 500,
|
52 |
+
"max_steps": 2738,
|
53 |
+
"num_train_epochs": 2,
|
54 |
+
"save_steps": 500,
|
55 |
+
"total_flos": 1.7783709700718592e+16,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": null
|
58 |
+
}
|