Training in progress, epoch 1

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [HooshvareLab/bert-fa-base-uncased](https://huggingface.co/HooshvareLab/bert-fa-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0154
-- Accuracy: 0.8333
-- F1: 0.8456
+- Loss: 1.0798
+- Accuracy: 0.5652
+- F1: 0.5901
 
 ## Model description
 
@@ -40,38 +40,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
-- train_batch_size: 32
-- eval_batch_size: 64
+- learning_rate: 3e-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: 15
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 68   | 0.5588          | 0.8333   | 0.8419 |
-| No log        | 2.0   | 136  | 0.5678          | 0.8417   | 0.8557 |
-| No log        | 3.0   | 204  | 0.6083          | 0.8208   | 0.8311 |
-| No log        | 4.0   | 272  | 0.6749          | 0.8167   | 0.8285 |
-| No log        | 5.0   | 340  | 0.7690          | 0.8292   | 0.8424 |
-| No log        | 6.0   | 408  | 0.8706          | 0.8208   | 0.8328 |
-| No log        | 7.0   | 476  | 0.8554          | 0.8292   | 0.8424 |
-| 0.0725        | 8.0   | 544  | 0.8950          | 0.825    | 0.8390 |
-| 0.0725        | 9.0   | 612  | 0.9200          | 0.825    | 0.8390 |
-| 0.0725        | 10.0  | 680  | 0.9511          | 0.8292   | 0.8455 |
-| 0.0725        | 11.0  | 748  | 0.9698          | 0.8375   | 0.8490 |
-| 0.0725        | 12.0  | 816  | 0.9829          | 0.8333   | 0.8456 |
-| 0.0725        | 13.0  | 884  | 1.0022          | 0.8333   | 0.8456 |
-| 0.0725        | 14.0  | 952  | 1.0130          | 0.8333   | 0.8456 |
-| 0.0167        | 15.0  | 1020 | 1.0154          | 0.8333   | 0.8456 |
+| No log        | 1.0   | 52   | 1.0320          | 0.4130   | 0.2269 |
+| No log        | 2.0   | 104  | 0.9651          | 0.4783   | 0.4406 |
+| No log        | 3.0   | 156  | 1.0128          | 0.5435   | 0.5541 |
+| No log        | 4.0   | 208  | 1.0869          | 0.5870   | 0.6025 |
+| No log        | 5.0   | 260  | 1.0798          | 0.5652   | 0.5901 |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
-- Pytorch 2.4.0+cu121
-- Datasets 2.21.0
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HooshvareLab/bert-fa-base-uncased",
+  "_name_or_path": "farshadafx/Bert-Sentiment-Fa",
   "architectures": [
     "BertForSequenceClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1303c33c429278abfac2d01fd9bbd791db5f36829ae3236961ee0275da760a1c
+oid sha256:dfd483b82190b3025e70895e6895848eb16170bbbaede2b09384f027995c28d9
 size 651398148

runs/Oct10_05-01-46_1a38898cabb0/events.out.tfevents.1728536518.1a38898cabb0.414.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adea320e45107497a8261d0a9229833d0fe1145c7507e90143b0327c91791e86
+size 7220

runs/Oct10_05-34-27_1a38898cabb0/events.out.tfevents.1728538482.1a38898cabb0.414.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e566fa2e3f90dd051098879af40f1bf3dc5d8472afc8d6944a685595cd0ee8
+size 5483

special_tokens_map.json

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,57 +1,109 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "[UNK]",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "[CLS]",
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "[MASK]",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "4": {
-      "content": "[SEP]",
-      "lstrip": false,
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "5": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<nl>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<hs>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "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 sha256:73804e0015ef9aaeaf3d5b283bc23bb3f31aeaa1c1e5e87009d6a303877cda43
+oid sha256:0eebbea113a6ab9c78db2c8be78371056e9cb3e33c1bfd7436b8a9400d488d08
 size 5176