Model save

README.md

@@ -1,5 +1,7 @@
 ---
 library_name: transformers
+license: mit
+base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -12,9 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # nusa-beta-0001
 
-This model was trained from scratch on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.6995
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
 
 ## Model description
 
@@ -34,27 +34,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 2
+- gradient_accumulation_steps: 4
 - total_train_batch_size: 16
 - 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
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 20
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.1608        | 10.0  | 100  | 1.6995          |
 
 
 ### Framework versions
 
-- Transformers 4.48.3
-- Pytorch 2.5.1+cu124
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
 - Datasets 3.5.1
-- Tokenizers 0.21.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "[MASK]": 50258,
-  "[PAD]": 50257
+  "<assistant>": 50258,
+  "<user>": 50257
 }

generation_config.json

@@ -2,6 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "pad_token_id": 50257,
-  "transformers_version": "4.48.3"
+  "transformers_version": "4.51.3"
 }

special_tokens_map.json

@@ -1,37 +1,22 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "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
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "additional_special_tokens": [
+    {
+      "content": "<user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -2,19 +2,19 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 256
+      "Fixed": 512
     },
     "direction": "Right",
     "pad_to_multiple_of": null,
-    "pad_id": 50257,
+    "pad_id": 50256,
     "pad_type_id": 0,
-    "pad_token": "[PAD]"
+    "pad_token": "<|endoftext|>"
   },
   "added_tokens": [
     {
@@ -28,7 +28,7 @@
     },
     {
       "id": 50257,
-      "content": "[PAD]",
+      "content": "<user>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -37,7 +37,7 @@
     },
     {
       "id": 50258,
-      "content": "[MASK]",
+      "content": "<assistant>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -10,7 +10,7 @@
       "special": true
     },
     "50257": {
-      "content": "[PAD]",
+      "content": "<user>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -18,7 +18,7 @@
       "special": true
     },
     "50258": {
-      "content": "[MASK]",
+      "content": "<assistant>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -26,20 +26,16 @@
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<user>",
+    "<assistant>"
+  ],
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "max_length": 256,
   "model_max_length": 1024,
-  "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "stride": 0,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }