Training in progress epoch 0

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.7234
-- Validation Loss: 3.7528
-- Epoch: 2
+- Train Loss: 7.3639
+- Validation Loss: 7.0367
+- Epoch: 0
 
 ## Model description
 
@@ -42,14 +42,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.9043     | 3.7814          | 0     |
-| 3.7846     | 3.7608          | 1     |
-| 3.7234     | 3.7528          | 2     |
+| 7.3639     | 7.0367          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.26.1
+- Transformers 4.27.1
 - TensorFlow 2.11.0
 - Datasets 2.10.1
 - Tokenizers 0.13.2

config.json

@@ -39,7 +39,7 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.27.1",
   "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": "4.26.1"
+  "transformers_version": "4.27.1"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5b02e69b433bc8c4db97c802765af5f96c588b5cc96fb0d85a779835dffcb34
+oid sha256:23ff9985b7a765488552250af2b3a450ed09197988f67bc9a2be9cea342d9fb6
 size 327745496

tokenizer_config.json

@@ -3,7 +3,6 @@
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
-  "name_or_path": "distilgpt2",
   "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"