End of training
Browse files- README.md +44 -6
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -16,12 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
| 20 |
-
- eval_runtime: 43.2168
|
| 21 |
-
- eval_samples_per_second: 23.139
|
| 22 |
-
- eval_steps_per_second: 2.892
|
| 23 |
-
- epoch: 0.0112
|
| 24 |
-
- step: 140
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -48,6 +43,49 @@ The following hyperparameters were used during training:
|
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- num_epochs: 3
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- Transformers 4.44.2
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.7266
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- num_epochs: 3
|
| 45 |
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 50 |
+
| 0.8268 | 0.08 | 1000 | 0.7354 |
|
| 51 |
+
| 0.7977 | 0.16 | 2000 | 0.7251 |
|
| 52 |
+
| 0.7739 | 0.24 | 3000 | 0.7259 |
|
| 53 |
+
| 0.771 | 0.32 | 4000 | 0.7269 |
|
| 54 |
+
| 0.7468 | 0.4 | 5000 | 0.7269 |
|
| 55 |
+
| 0.751 | 0.48 | 6000 | 0.7501 |
|
| 56 |
+
| 0.7483 | 0.56 | 7000 | 0.7502 |
|
| 57 |
+
| 0.7443 | 0.64 | 8000 | 0.7253 |
|
| 58 |
+
| 0.7294 | 0.72 | 9000 | 0.7309 |
|
| 59 |
+
| 0.7309 | 0.8 | 10000 | 0.7260 |
|
| 60 |
+
| 0.7424 | 0.88 | 11000 | 0.7304 |
|
| 61 |
+
| 0.7348 | 0.96 | 12000 | 0.7276 |
|
| 62 |
+
| 0.7421 | 1.04 | 13000 | 0.7327 |
|
| 63 |
+
| 0.7333 | 1.12 | 14000 | 0.7417 |
|
| 64 |
+
| 0.7444 | 1.2 | 15000 | 0.7296 |
|
| 65 |
+
| 0.7463 | 1.28 | 16000 | 0.7257 |
|
| 66 |
+
| 0.7324 | 1.3600 | 17000 | 0.7253 |
|
| 67 |
+
| 0.7297 | 1.44 | 18000 | 0.7314 |
|
| 68 |
+
| 0.7358 | 1.52 | 19000 | 0.7253 |
|
| 69 |
+
| 0.7442 | 1.6 | 20000 | 0.7248 |
|
| 70 |
+
| 0.7384 | 1.6800 | 21000 | 0.7388 |
|
| 71 |
+
| 0.7345 | 1.76 | 22000 | 0.7259 |
|
| 72 |
+
| 0.7218 | 1.8400 | 23000 | 0.7284 |
|
| 73 |
+
| 0.7426 | 1.92 | 24000 | 0.7253 |
|
| 74 |
+
| 0.7375 | 2.0 | 25000 | 0.7389 |
|
| 75 |
+
| 0.7443 | 2.08 | 26000 | 0.7305 |
|
| 76 |
+
| 0.7286 | 2.16 | 27000 | 0.7258 |
|
| 77 |
+
| 0.7269 | 2.24 | 28000 | 0.7264 |
|
| 78 |
+
| 0.7391 | 2.32 | 29000 | 0.7270 |
|
| 79 |
+
| 0.7377 | 2.4 | 30000 | 0.7283 |
|
| 80 |
+
| 0.7319 | 2.48 | 31000 | 0.7329 |
|
| 81 |
+
| 0.7352 | 2.56 | 32000 | 0.7254 |
|
| 82 |
+
| 0.7141 | 2.64 | 33000 | 0.7285 |
|
| 83 |
+
| 0.7317 | 2.7200 | 34000 | 0.7253 |
|
| 84 |
+
| 0.7334 | 2.8 | 35000 | 0.7305 |
|
| 85 |
+
| 0.7332 | 2.88 | 36000 | 0.7282 |
|
| 86 |
+
| 0.7309 | 2.96 | 37000 | 0.7266 |
|
| 87 |
+
|
| 88 |
+
|
| 89 |
### Framework versions
|
| 90 |
|
| 91 |
- Transformers 4.44.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 560077316
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d53757e00a27ecb3128ded49ed43dbf95b49aa16381a1714ca0b53439060fb43
|
| 3 |
size 560077316
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:748815ce4ceb09fa682583f72e0042c644a4a404f000681ae3fae27f0c533f7d
|
| 3 |
size 5112
|