Training complete
Browse files- README.md +19 -17
- adapter_config.json +2 -2
- adapter_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Bleu:
|
22 |
-
- Gen Len:
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -39,27 +39,29 @@ More information needed
|
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 0.0001
|
42 |
-
- train_batch_size:
|
43 |
-
- eval_batch_size:
|
44 |
- seed: 42
|
|
|
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- num_epochs: 10
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
-
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len
|
52 |
-
|
53 |
-
| No log |
|
54 |
-
| No log | 2.0 |
|
55 |
-
| No log |
|
56 |
-
| No log | 4.0 |
|
57 |
-
| No log |
|
58 |
-
| No log | 6.0 |
|
59 |
-
| No log |
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.1142
|
21 |
+
- Bleu: 58.3679
|
22 |
+
- Gen Len: 74.4727
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 0.0001
|
42 |
+
- train_batch_size: 8
|
43 |
+
- eval_batch_size: 8
|
44 |
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 4
|
46 |
+
- total_train_batch_size: 32
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
- num_epochs: 10
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:--------:|
|
55 |
+
| No log | 0.99 | 33 | 3.5500 | 28.0752 | 98.4545 |
|
56 |
+
| No log | 2.0 | 67 | 2.6889 | 28.4762 | 97.7273 |
|
57 |
+
| No log | 2.99 | 100 | 2.1016 | 13.9425 | 131.9636 |
|
58 |
+
| No log | 4.0 | 134 | 1.6955 | 20.9551 | 114.3091 |
|
59 |
+
| No log | 4.99 | 167 | 1.4578 | 44.5358 | 83.4 |
|
60 |
+
| No log | 6.0 | 201 | 1.2986 | 53.9615 | 75.0545 |
|
61 |
+
| No log | 6.99 | 234 | 1.2113 | 56.6086 | 77.4182 |
|
62 |
+
| No log | 8.0 | 268 | 1.1550 | 57.2346 | 73.8364 |
|
63 |
+
| No log | 8.99 | 301 | 1.1222 | 58.1529 | 74.2 |
|
64 |
+
| No log | 9.85 | 330 | 1.1142 | 58.3679 | 74.4727 |
|
65 |
|
66 |
|
67 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,8 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "SEQ_2_SEQ_LM",
|
27 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
],
|
26 |
"task_type": "SEQ_2_SEQ_LM",
|
27 |
"use_dora": false,
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9490378
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57fe5c5a9627945acff7a4c3b2533a16c27cb0237c2a7359e9fb3624bba63c68
|
3 |
size 9490378
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a706b21a1a550b35711b310fd213517ab949b1fbc24ae6e053bf6cb0d2a55fb
|
3 |
size 4664
|