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: 3.8585
-- Validation Loss: 3.6762
+- Train Loss: 3.8587
+- Validation Loss: 3.6755
 - Epoch: 0
 
 ## Model description
@@ -42,12 +42,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.8585     | 3.6762          | 0     |
+| 3.8587     | 3.6755          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.28.0
+- Transformers 4.29.2
 - TensorFlow 2.12.0
-- Datasets 2.11.0
+- Datasets 2.12.0
 - Tokenizers 0.13.3

config.json

@@ -39,7 +39,7 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.28.0",
+  "transformers_version": "4.29.2",
   "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": "4.28.0"
+  "transformers_version": "4.29.2"
 }

logs/train/events.out.tfevents.1684725926.ip-172-26-4-203.40629.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc80e0c2c8676af6d67d464bf30773277e361ee428c176df8b719f46d9d1b2bc
+size 958050

logs/validation/events.out.tfevents.1684728677.ip-172-26-4-203.40629.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4395b8a709eafe3a6fa86e63478dab11961f8041e5d27a7b6f7461db40362716
+size 232

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef552580849791532a9c36b2031c3a3945a06c9a55131e50e88526ad0f5939a
+oid sha256:7dd4faec8500b862f24cc249132d2878c80a689c43bb58f1a2b5fdd200f92180
 size 327745472