End of training
Browse files- README.md +16 -6
- pytorch_model.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 [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss:
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -36,10 +36,10 @@ More information needed
|
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 2e-05
|
| 38 |
- train_batch_size: 2
|
| 39 |
-
- eval_batch_size:
|
| 40 |
- seed: 42
|
| 41 |
-
- gradient_accumulation_steps:
|
| 42 |
-
- total_train_batch_size:
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 1500
|
|
@@ -49,8 +49,18 @@ The following hyperparameters were used during training:
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
-
|
|
| 53 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
|
| 56 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.6416
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 2e-05
|
| 38 |
- train_batch_size: 2
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 56
|
| 42 |
+
- total_train_batch_size: 112
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 1500
|
|
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 4.3605 | 0.31 | 50 | 3.7983 |
|
| 53 |
+
| 3.9502 | 0.62 | 100 | 3.4157 |
|
| 54 |
+
| 3.4719 | 0.93 | 150 | 3.2378 |
|
| 55 |
+
| 3.3937 | 1.24 | 200 | 3.0982 |
|
| 56 |
+
| 3.3123 | 1.56 | 250 | 3.0227 |
|
| 57 |
+
| 3.3164 | 1.87 | 300 | 2.9341 |
|
| 58 |
+
| 2.9789 | 2.18 | 350 | 2.8408 |
|
| 59 |
+
| 2.9593 | 2.49 | 400 | 2.8201 |
|
| 60 |
+
| 2.8724 | 2.8 | 450 | 2.7561 |
|
| 61 |
+
| 2.8753 | 3.11 | 500 | 2.7083 |
|
| 62 |
+
| 2.8017 | 3.42 | 550 | 2.6593 |
|
| 63 |
+
| 2.7496 | 3.73 | 600 | 2.6416 |
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 626344146
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:739f8278b32d9705eec0fb4d6cc347ab990f8df9d0de0f5aaa3b3cec082a55bf
|
| 3 |
size 626344146
|