End of training

README.md

@@ -1,6 +1,5 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: finiteautomata/bertweet-base-sentiment-analysis
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model_IMDB_peft
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [finiteautomata/bertweet-base-sentiment-analysis](https://huggingface.co/finiteautomata/bertweet-base-sentiment-analysis) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3273
-- Accuracy: 0.8609
+- Loss: 0.2832
+- Accuracy: 0.8872
 
 ## Model description
 
@@ -38,8 +37,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- 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
@@ -47,18 +46,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5985        | 1.0   | 782  | 0.4118          | 0.8278   |
-| 0.3869        | 2.0   | 1564 | 0.3600          | 0.8443   |
-| 0.3759        | 3.0   | 2346 | 0.3488          | 0.8490   |
-| 0.3587        | 4.0   | 3128 | 0.3379          | 0.8545   |
-| 0.3617        | 5.0   | 3910 | 0.3336          | 0.8571   |
-| 0.351         | 6.0   | 4692 | 0.3305          | 0.8586   |
-| 0.3468        | 7.0   | 5474 | 0.3299          | 0.8592   |
-| 0.3442        | 8.0   | 6256 | 0.3275          | 0.8604   |
-| 0.3493        | 9.0   | 7038 | 0.3298          | 0.8596   |
-| 0.3414        | 10.0  | 7820 | 0.3273          | 0.8609   |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.3355        | 1.0   | 1563  | 0.3167          | 0.8643   |
+| 0.3203        | 2.0   | 3126  | 0.3084          | 0.8722   |
+| 0.3024        | 3.0   | 4689  | 0.2950          | 0.8797   |
+| 0.2932        | 4.0   | 6252  | 0.2907          | 0.8820   |
+| 0.2784        | 5.0   | 7815  | 0.2887          | 0.8838   |
+| 0.2817        | 6.0   | 9378  | 0.2833          | 0.8859   |
+| 0.2755        | 7.0   | 10941 | 0.2848          | 0.8860   |
+| 0.2714        | 8.0   | 12504 | 0.2819          | 0.8866   |
+| 0.2727        | 9.0   | 14067 | 0.2832          | 0.8871   |
+| 0.2795        | 10.0  | 15630 | 0.2832          | 0.8872   |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc26c994448e1b35f4a730897f55efbeb4160050942d9e761be1d752bf4d16d
+oid sha256:6ad8a4fcf98e3d3df31d82b5c130bc67284244eed9d4c6924b1404ca84798c28
 size 3570125