ahmed792002/Finetuning_Longformer_IMDb_movie_reviews_Classification

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6015
-- Accuracy: 0.907
-- F1: 0.9070
+- Loss: 0.4155
+- Accuracy: 0.9173
+- F1: 0.9173
 
 ## Model description
 
@@ -46,17 +46,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
-| 0.4127        | 1.0   | 9000  | 0.5397          | 0.8718   | 0.8710 |
-| 0.3234        | 2.0   | 18000 | 0.4125          | 0.9058   | 0.9057 |
-| 0.2301        | 3.0   | 27000 | 0.5200          | 0.902    | 0.9019 |
-| 0.1731        | 4.0   | 36000 | 0.5431          | 0.9055   | 0.9055 |
-| 0.0895        | 5.0   | 45000 | 0.6015          | 0.907    | 0.9070 |
+| 0.3594        | 1.0   | 9000  | 0.4529          | 0.897    | 0.8967 |
+| 0.2779        | 2.0   | 18000 | 0.4155          | 0.9173   | 0.9173 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8ed5bf331d7db96906c9791fa9ff4ea00115696bb9f04ba379cab640e9102ba
+oid sha256:76ef2c7bbe6c531bf291b29900bad8c6f381251b5d69ed8bd23525f69e53c47d
 size 594678184

runs/Dec08_12-08-07_652049512f2d/events.out.tfevents.1733659688.652049512f2d.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea05815c5a13ca009b99801f57bf86c49edbb031bf56d6e0ea9ca82e25e0d80
+size 14058

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 200,
+    "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 200
+      "Fixed": 1024
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6626c51ff5daa41eed9946482fa132fdab8310ffadf1a26b3d3f652e3ac94cd
+oid sha256:e665ffe94041fb8a003188f68c9688298940b0a0580817a7faafc79677c62b7d
 size 5368