tzuchichen branch initial commit, end of finetuning

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: bert-finetuned-sst2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bert-finetuned-sst2
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4948
+- Accuracy: 0.77
+- F1: 0.7767
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 13   | 0.6412          | 0.57     | 0.7261 |
+| No log        | 2.0   | 26   | 0.5484          | 0.76     | 0.7600 |
+| No log        | 3.0   | 39   | 0.4948          | 0.77     | 0.7767 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2788
-- Accuracy: 0.63
-- F1: 0.5195
+- Loss: 0.9545
+- Accuracy: 0.77
+- F1: 0.7810
 
 ## Model description
 
@@ -51,9 +51,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 13   | 0.4705          | 0.79     | 0.7961 |
-| No log        | 2.0   | 26   | 1.1760          | 0.62     | 0.5    |
-| No log        | 3.0   | 39   | 1.2788          | 0.63     | 0.5195 |
+| No log        | 1.0   | 13   | 0.7069          | 0.75     | 0.7573 |
+| No log        | 2.0   | 26   | 0.8417          | 0.75     | 0.7664 |
+| No log        | 3.0   | 39   | 0.9545          | 0.77     | 0.7810 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:752ca178d47577536c2ff7acf50771734e1e6a4bc23fa2406e31bc7c444d9cf6
+oid sha256:327c5e46b920f515866d4e4856f910c7e3b55e3675f10132f443446b9df040df
 size 437958648

runs/Mar22_18-45-31_arg10/events.out.tfevents.1711104337.arg10.654.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da386250ed2b9442e78dea5a5e7544509b52e06a2e37061a1446673cbeb0feb
+size 6114

runs/Mar22_18-46-25_arg10/events.out.tfevents.1711104401.arg10.654.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e98f211c241fe9fd434716b28bcfb7da0c55a82a5bb81947ba9a3f766d3df64
+size 6023

runs/Mar23_16-51-42_arg10/events.out.tfevents.1711183904.arg10.44500.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc5aea3910632490dd4ffd4dba7a8ed1bb45e85a795a51aae9b800d0558873d
+size 6023

runs/Mar23_17-08-45_arg10/events.out.tfevents.1711184931.arg10.44500.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6470d8936a7b8da54244103aa202bce0a88fb45a54bd0c34aff7ea83fa12ac
+size 6081

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d6c40edf95ea901f1a5b5557a41bdf3ed62c78e6e7c0ddd54efaee0dcaa09d
+oid sha256:59cbdf27602463d3ea3ec3fe682c1cca3f08cf6f2e69a0622de44ebeb5d19689
 size 4920