End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: gpt2
+base_model: rb05751/reuters-gpt2-text-gen
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # reuters-gpt2-text-gen
 
-This model is a trained from-scratch [gpt2](https://huggingface.co/gpt2) model on the Reuters dataset.
+This model is a fine-tuned version of [rb05751/reuters-gpt2-text-gen](https://huggingface.co/rb05751/reuters-gpt2-text-gen) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.8502
+- Loss: 4.2531
 
 ## Model description
 
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.2539        | 1.0   | 234  | 4.8502          |
+| 4.8282        | 1.0   | 234  | 4.2531          |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "rb05751/reuters-gpt2-text-gen",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4e47d511360a17e3d5306971ae46b2c86a5b9ddb3ac28a874bdccb89c58183e
+oid sha256:987c09c4c12cbfb6a5bb05487a31abfd5cdc99b72534a1746dd98228402729f7
 size 503161693

tokenizer_config.json

@@ -3,7 +3,11 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 512,
   "model_max_length": 1024,
+  "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 sha256:4ad31608d9225a3bb630a2290fb394a7c999f1de8bf81357e08ed8248bc7af1b
+oid sha256:ffcc96379ddfc61ed6f164dfcaf5517209aaa6715a43b21be6de652dba080891
 size 4091