End of training
Browse files- README.md +47 -1
- model.safetensors +1 -1
README.md
CHANGED
@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# clinical_longformer_same_tokens_exp_gpu
|
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 |
|
18 |
## Model description
|
19 |
|
@@ -41,10 +43,54 @@ The following hyperparameters were used during training:
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 1500
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
|
50 |
### Framework versions
|
|
|
14 |
# clinical_longformer_same_tokens_exp_gpu
|
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: 1.1468
|
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: 1500
|
46 |
+
- num_epochs: 3
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 3.0528 | 0.07 | 65 | 2.6194 |
|
53 |
+
| 3.2272 | 0.14 | 130 | 2.4923 |
|
54 |
+
| 2.8624 | 0.21 | 195 | 2.3739 |
|
55 |
+
| 2.552 | 0.29 | 260 | 2.2678 |
|
56 |
+
| 2.7232 | 0.36 | 325 | 2.1829 |
|
57 |
+
| 2.361 | 0.43 | 390 | 2.0939 |
|
58 |
+
| 2.6223 | 0.5 | 455 | 2.0165 |
|
59 |
+
| 2.2567 | 0.57 | 520 | 1.9490 |
|
60 |
+
| 2.1168 | 0.64 | 585 | 1.8869 |
|
61 |
+
| 2.1214 | 0.71 | 650 | 1.8269 |
|
62 |
+
| 2.3123 | 0.79 | 715 | 1.7750 |
|
63 |
+
| 2.2535 | 0.86 | 780 | 1.7338 |
|
64 |
+
| 1.8926 | 0.93 | 845 | 1.6785 |
|
65 |
+
| 1.7711 | 1.0 | 910 | 1.6277 |
|
66 |
+
| 1.7578 | 1.07 | 975 | 1.5990 |
|
67 |
+
| 2.0243 | 1.14 | 1040 | 1.5484 |
|
68 |
+
| 2.2152 | 1.21 | 1105 | 1.5203 |
|
69 |
+
| 1.6819 | 1.28 | 1170 | 1.4809 |
|
70 |
+
| 1.5537 | 1.36 | 1235 | 1.4518 |
|
71 |
+
| 1.574 | 1.43 | 1300 | 1.4189 |
|
72 |
+
| 1.6772 | 1.5 | 1365 | 1.3917 |
|
73 |
+
| 1.6269 | 1.57 | 1430 | 1.3563 |
|
74 |
+
| 1.5375 | 1.64 | 1495 | 1.3363 |
|
75 |
+
| 1.5477 | 1.71 | 1560 | 1.3118 |
|
76 |
+
| 1.4559 | 1.78 | 1625 | 1.2857 |
|
77 |
+
| 1.4579 | 1.86 | 1690 | 1.2716 |
|
78 |
+
| 1.4705 | 1.93 | 1755 | 1.2587 |
|
79 |
+
| 1.4205 | 2.0 | 1820 | 1.2346 |
|
80 |
+
| 1.423 | 2.07 | 1885 | 1.2277 |
|
81 |
+
| 1.3852 | 2.14 | 1950 | 1.2123 |
|
82 |
+
| 1.3362 | 2.21 | 2015 | 1.2078 |
|
83 |
+
| 1.2793 | 2.28 | 2080 | 1.1854 |
|
84 |
+
| 1.3126 | 2.36 | 2145 | 1.1806 |
|
85 |
+
| 1.28 | 2.43 | 2210 | 1.1731 |
|
86 |
+
| 1.3789 | 2.5 | 2275 | 1.1646 |
|
87 |
+
| 1.3572 | 2.57 | 2340 | 1.1648 |
|
88 |
+
| 1.3398 | 2.64 | 2405 | 1.1539 |
|
89 |
+
| 1.2831 | 2.71 | 2470 | 1.1518 |
|
90 |
+
| 1.3269 | 2.78 | 2535 | 1.1488 |
|
91 |
+
| 1.2208 | 2.86 | 2600 | 1.1478 |
|
92 |
+
| 1.2955 | 2.93 | 2665 | 1.1421 |
|
93 |
+
| 1.2286 | 3.0 | 2730 | 1.1468 |
|
94 |
|
95 |
|
96 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 594879308
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:672631653e20d0eed0e5a30134add6f5f02b3e3812f4cc824577d0e672f7b04b
|
3 |
size 594879308
|