End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: Sol1986/fineweb-edu-classifier-finetuned
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fineweb-edu-classifier-finetuned
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [Sol1986/fineweb-edu-classifier-finetuned](https://huggingface.co/Sol1986/fineweb-edu-classifier-finetuned) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0069
+- Loss: 0.0003
 
 ## Model description
 
@@ -35,21 +35,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Use OptimizerNames.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: 3
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0522        | 1.0   | 50   | 0.0178          |
-| 0.015         | 2.0   | 100  | 0.0082          |
-| 0.0096        | 3.0   | 150  | 0.0069          |
+| No log        | 1.0   | 25   | 0.0027          |
+| 0.0197        | 2.0   | 50   | 0.0387          |
+| 0.0197        | 3.0   | 75   | 0.0012          |
+| 0.0169        | 4.0   | 100  | 0.0006          |
+| 0.0169        | 5.0   | 125  | 0.0004          |
+| 0.0006        | 6.0   | 150  | 0.0004          |
+| 0.0006        | 7.0   | 175  | 0.0003          |
+| 0.0004        | 8.0   | 200  | 0.0003          |
+| 0.0004        | 9.0   | 225  | 0.0003          |
+| 0.0004        | 10.0  | 250  | 0.0003          |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "Sol1986/fineweb-edu-classifier-finetuned",
   "architectures": [
     "BertForSequenceClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf4d6481925bb56c9be6ab2e9b2576ddb30eecedc17fa4b026b35d69b5cb992
+oid sha256:0f45f5f69123ae30c5ec7a3d8b398692263dfb2480dd5bafa74a391f9a4421ce
 size 437964800

runs/Jan24_22-36-50_6b52aafe569e/events.out.tfevents.1737758210.6b52aafe569e.2111.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a07edc54e8d7e4acb20a37fab7d24b495a0862aa176b11775d82ec354a9890
+size 9569

runs/Jan24_22-36-50_6b52aafe569e/events.out.tfevents.1737758278.6b52aafe569e.2111.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee47c178c66883be890cafe7950b16ae5c7bbabc2d821cca9b374b255391c9f7
+size 359

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -46,11 +46,18 @@
   "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
+  "max_length": 128,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb72317ba9e5308220e5f8e6c1f65e1406f42af6087019d01e77371c078af430
+oid sha256:5d8882cbe9c9e462393e92e994579b2b28958bd0bd2e5a678be0aa1a13bef80b
 size 5432