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: 0.5280
-- Accuracy: 0.9203
-- F1: 0.9202
+- Loss: 0.6015
+- Accuracy: 0.907
+- F1: 0.9070
 
 ## Model description
 
@@ -52,11 +52,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
-| 0.393         | 1.0   | 9000  | 0.3941          | 0.9103   | 0.9102 |
-| 0.2937        | 2.0   | 18000 | 0.3846          | 0.9163   | 0.9162 |
-| 0.1886        | 3.0   | 27000 | 0.4201          | 0.9247   | 0.9248 |
-| 0.1554        | 4.0   | 36000 | 0.4752          | 0.9175   | 0.9175 |
-| 0.0916        | 5.0   | 45000 | 0.5280          | 0.9203   | 0.9202 |
+| 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 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a2c10e25c09287c6c963a3e7d1ed034a76f33d5f9a508a9825caae99ebd1a4
+oid sha256:f8ed5bf331d7db96906c9791fa9ff4ea00115696bb9f04ba379cab640e9102ba
 size 594678184

runs/Dec07_10-37-18_a4abe714014b/events.out.tfevents.1733567840.a4abe714014b.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2814093f3e263a710dba49612dcfed2746d725f5bf160ba5ba9e6cf6e2a223d
+size 26796

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 200,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 200
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e3a5c35ddf4603b5a569b9cf6738e1fc8cde2b37d03cf3945bb79a861647a1
+oid sha256:f6626c51ff5daa41eed9946482fa132fdab8310ffadf1a26b3d3f652e3ac94cd
 size 5368