End of training

README.md

@@ -1,5 +1,6 @@
 ---
 license: mit
+base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -12,9 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # TinyStoriesTest
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.3477
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 
 ## Model description
 
@@ -34,26 +33,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 150
+- eval_batch_size: 150
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 256
+- total_train_batch_size: 1200
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
 - num_epochs: 1
+- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.852         | 0.63  | 5000 | 1.3477          |
 
 
 ### Framework versions
 
-- Transformers 4.30.2
-- Pytorch 2.0.1+cu118
-- Datasets 2.13.1
-- Tokenizers 0.13.3
+- Transformers 4.35.2
+- Pytorch 2.1.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.30.2"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4153529acd44388c630636c880b03580ad8bc69c2d152807e41f151b46f9f767
+size 497774208

tokenizer_config.json

@@ -1,33 +1,22 @@
 {
   "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 1024,
-  "pad_token": null,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb00b285b835108d785d2fa54edacfe0396efaba1465f0b50a4d8bc726434bf
-size 3899
+oid sha256:32a55722cedfe39c5b85e110d0ba6a02b728225ce003fae7616f565e0c97c58f
+size 4600