discharge-prepped-8000

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2539
-- Accuracy: 0.9072
-- F1: 0.9072
+- Loss: 0.1394
+- Accuracy: 0.9577
+- F1: 0.9577
 
 ## Model description
 
@@ -40,24 +40,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.4848        | 1.0   | 1613 | 0.3375          | 0.8592   | 0.8589 |
-| 0.3454        | 2.0   | 3226 | 0.2539          | 0.9072   | 0.9072 |
+| No log        | 1.0   | 820  | 0.5591          | 0.7316   | 0.7247 |
+| 0.5723        | 2.0   | 1640 | 0.4173          | 0.8082   | 0.8060 |
+| 0.5723        | 3.0   | 2460 | 0.3228          | 0.8703   | 0.8693 |
+| 0.3567        | 4.0   | 3280 | 0.2463          | 0.9050   | 0.9045 |
+| 0.3567        | 5.0   | 4100 | 0.1633          | 0.9444   | 0.9443 |
+| 0.2179        | 6.0   | 4920 | 0.1394          | 0.9577   | 0.9577 |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
+- Transformers 4.36.2
+- Pytorch 2.0.0
+- Datasets 2.1.0
 - Tokenizers 0.15.0

config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3776db29a7d6b099dd99f952f78f4b3920b48261d18df75fb7759a6d9d03b5bd
+oid sha256:aad53f9b053304a02044137a396344aaa3c268a52055b0c917440b81fffdaff3
 size 267832560

runs/Jan18_11-31-29_144e5e2edd0b/events.out.tfevents.1705577490.144e5e2edd0b.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511c36a97bba50ed835a4dbe4d0c00fc1751f6bed4d6121aefcae512920cf93c
+size 7363

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e878d9f233667a01235c9bc39e9b02e9b977ac1ebbf068078ca5d9b0b93f9df
-size 4600
+oid sha256:70e43082842eafdb6b547ceaf50d5c565f2d2d71829b69e9a2b6a23106e51eb1
+size 4283