flan-t5-large_question_answering_finetuining
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,19 +35,27 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 0.0003
|
38 |
-
- train_batch_size:
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
|
|
50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.5861
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 0.0003
|
38 |
+
- train_batch_size: 4
|
39 |
+
- eval_batch_size: 4
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 10
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 4.3031 | 1.0 | 79 | 0.5110 |
|
50 |
+
| 0.4051 | 2.0 | 158 | 0.4330 |
|
51 |
+
| 0.2949 | 3.0 | 237 | 0.4171 |
|
52 |
+
| 0.2191 | 4.0 | 316 | 0.4090 |
|
53 |
+
| 0.165 | 5.0 | 395 | 0.4273 |
|
54 |
+
| 0.1199 | 6.0 | 474 | 0.4527 |
|
55 |
+
| 0.0871 | 7.0 | 553 | 0.4851 |
|
56 |
+
| 0.064 | 8.0 | 632 | 0.5375 |
|
57 |
+
| 0.0497 | 9.0 | 711 | 0.5662 |
|
58 |
+
| 0.044 | 10.0 | 790 | 0.5861 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
emissions.csv
CHANGED
@@ -7,3 +7,4 @@ timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_
|
|
7 |
2024-02-17T15:19:25,60279b1c-2b5f-46ac-a314-3fd14f7593d4,codecarbon,22.601327419281006,0.0014373871409741098,0.002688287132063059,Canada,CAN,,N,,
|
8 |
2024-02-17T15:29:58,0d75896e-078a-466e-8050-ea2e72a83c48,codecarbon,44.81913948059082,0.003049913346454106,0.005704129784842451,Canada,CAN,,N,,
|
9 |
2024-02-17T15:42:11,5ecb3722-5983-4772-b503-aa34e1e20f3f,codecarbon,67.49829816818237,0.0038415553250788484,0.00718470581315977,Canada,CAN,,N,,
|
|
|
|
7 |
2024-02-17T15:19:25,60279b1c-2b5f-46ac-a314-3fd14f7593d4,codecarbon,22.601327419281006,0.0014373871409741098,0.002688287132063059,Canada,CAN,,N,,
|
8 |
2024-02-17T15:29:58,0d75896e-078a-466e-8050-ea2e72a83c48,codecarbon,44.81913948059082,0.003049913346454106,0.005704129784842451,Canada,CAN,,N,,
|
9 |
2024-02-17T15:42:11,5ecb3722-5983-4772-b503-aa34e1e20f3f,codecarbon,67.49829816818237,0.0038415553250788484,0.00718470581315977,Canada,CAN,,N,,
|
10 |
+
2024-02-17T15:51:16,2689fbc8-0b16-4e86-8e78-73a6971f21aa,codecarbon,452.72942876815796,0.03205908639002386,0.05995881481838818,Canada,CAN,,N,,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3132668808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d60fc4ea19d74aff25b16b66fa70252222dc9962edef1954646f8ddbcd86c8c
|
3 |
size 3132668808
|
runs/Feb17_15-43-37_c0c8f2aaa2e2/events.out.tfevents.1708184621.c0c8f2aaa2e2.129401.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5a5849488d40b29bf5cebddea01e1dd36da2b37fe488f51c1de53951c812377
|
3 |
+
size 9394
|