End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.7630
+- Loss: 9.7570
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 50   | 6.1715          |
-| 5.7578        | 2.0   | 100  | 6.4690          |
-| 5.7578        | 3.0   | 150  | 6.7630          |
+| No log        | 1.0   | 50   | 7.8194          |
+| 2.6699        | 2.0   | 100  | 9.3063          |
+| 2.6699        | 3.0   | 150  | 9.7570          |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343c80dea7d0b9a2c97ebc86e266095207da982d0cf7c455f940f04f3f67470f
+oid sha256:7102853ccf8ec4e4e2edded50c90711bce1905e42c5f2b2ba6adf32713a2aa19
 size 497780512

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}