alexpaunoiu
commited on
Commit
•
0880624
1
Parent(s):
cf7e803
Model save
Browse files- README.md +14 -12
- config.json +1 -1
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
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 [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -43,22 +43,24 @@ The following hyperparameters were used during training:
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 100
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
|
|
|
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.0069
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 100
|
46 |
+
- num_epochs: 12
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 11.322 | 0.99 | 14 | 10.9937 |
|
53 |
+
| 9.3954 | 1.98 | 28 | 8.8487 |
|
54 |
+
| 6.5458 | 2.97 | 42 | 5.9401 |
|
55 |
+
| 5.1036 | 3.96 | 56 | 4.6196 |
|
56 |
+
| 3.8587 | 4.96 | 70 | 3.4009 |
|
57 |
+
| 2.7987 | 5.95 | 84 | 2.7571 |
|
58 |
+
| 2.6306 | 6.94 | 98 | 2.5074 |
|
59 |
+
| 2.3636 | 8.0 | 113 | 2.3132 |
|
60 |
+
| 2.2169 | 8.99 | 127 | 2.2248 |
|
61 |
+
| 2.1732 | 9.98 | 141 | 2.1092 |
|
62 |
+
| 2.0377 | 10.97 | 155 | 2.0351 |
|
63 |
+
| 1.9973 | 11.89 | 168 | 2.0069 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
config.json
CHANGED
@@ -71,5 +71,5 @@
|
|
71 |
"torch_dtype": "float32",
|
72 |
"transformers_version": "4.34.1",
|
73 |
"use_cache": true,
|
74 |
-
"vocab_size":
|
75 |
}
|
|
|
71 |
"torch_dtype": "float32",
|
72 |
"transformers_version": "4.34.1",
|
73 |
"use_cache": true,
|
74 |
+
"vocab_size": 75112
|
75 |
}
|
pytorch_model.bin
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:cf98856a6adbce02467c2d4c158ae1a485773fc3136f6e3fce4184022a6c173c
|
3 |
+
size 634400605
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4283
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6da1e295eb1209757d7a9fdcb78bb2abcfb5b870204d750d48b3fc5be1b70210
|
3 |
size 4283
|