Training in progress epoch 0

README.md

@@ -14,8 +14,8 @@ 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: 3.8593
-- Validation Loss: 3.6735
+- Train Loss: 3.8585
+- Validation Loss: 3.6762
 - Epoch: 0
 
 ## Model description
@@ -42,12 +42,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.8593     | 3.6735          | 0     |
+| 3.8585     | 3.6762          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.27.4
+- Transformers 4.28.0
 - TensorFlow 2.12.0
 - Datasets 2.11.0
-- Tokenizers 0.13.2
+- Tokenizers 0.13.3

config.json

@@ -39,7 +39,7 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.28.0",
   "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": "4.27.4"
+  "transformers_version": "4.28.0"
 }

logs/train/events.out.tfevents.1681508244.ip-172-26-13-131.62230.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a97c3769fa5882708521778c5c93daa42902816b5ef69a6dc2d70f8ec916b7
+size 958050

logs/validation/events.out.tfevents.1681510986.ip-172-26-13-131.62230.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c1c471fa98218c39a0b2fa6cc492ca82c16340836e05ff5c1eb5b97619c1a2a
+size 232

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ t
 Ġ a
 h e

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:540a0f1919b1c239d645d82a6d6fc8ad78e69be78c3155e23abee64fcdda42e6
+oid sha256:bef552580849791532a9c36b2031c3a3945a06c9a55131e50e88526ad0f5939a
 size 327745472

tokenizer.json

@@ -39,6 +39,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -1,9 +1,9 @@
 {
   "add_prefix_space": false,
   "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
-  "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }