Model save

README.md

@@ -1,20 +1,49 @@
 ---
+library_name: transformers
 license: mit
-datasets:
-- Elriggs/openwebtext-100k
-language:
-- en
-pipeline_tag: text-generation
+base_model: SubhrajitSain/anwgpt2-345m
 tags:
-- gpt
-- gpt2
-- gpt2-medium
-- anw
-- anwgpt
+- generated_from_trainer
+model-index:
+- name: anwgpt2-345m
+  results: []
 ---
 
-# ANWGPT2
-Public release of anwgpt2.
-Model: `gpt2-medium`
+<!-- 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. -->
 
-### UNDER TRAINING.
+# anwgpt2-345m
+
+This model is a fine-tuned version of [SubhrajitSain/anwgpt2-345m](https://huggingface.co/SubhrajitSain/anwgpt2-345m) on an unknown dataset.
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Framework versions
+
+- Transformers 4.56.0
+- Pytorch 2.8.0+cu126
+- Datasets 2.14.6
+- Tokenizers 0.22.0

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.56.0"
+}

special_tokens_map.json

@@ -1,6 +1,24 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
+  "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
+  },
   "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -14,8 +14,15 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
+  "max_length": 128,
   "model_max_length": 1024,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b366e233c0e819d4e1e878194b1cea47ad174173aa3dcaed5593c857326723
+oid sha256:fa7a564900de06743123776d75675ff28ebed58fc1dcbcf052101ab6a3773430
 size 5777