Training done for led-pubmed-20k

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [pszemraj/led-base-book-summary](https://huggingface.co/pszemraj/led-base-book-summary) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2432
+- Loss: 1.1066
 
 ## Model description
 
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.2934        | 0.75  | 500  | 1.2432          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.2197        | 0.7477 | 500  | 1.1066          |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.40.1
 - Pytorch 2.2.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -54,7 +54,7 @@
   "pad_token_id": 1,
   "repetition_penalty": 3.5,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.1",
   "use_cache": true,
   "vocab_size": 50265
 }

generation_config.json

@@ -11,5 +11,5 @@
   "num_beams": 4,
   "pad_token_id": 1,
   "repetition_penalty": 3.5,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.40.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a5d2233c5752932dfdcd6f88d2fd1a3f6dad79c7083fcd197f968414e459b1
+oid sha256:61917097c9cd1d775a9cc1a28ea6478e5038b4731383b1caa0289c3b4769142c
 size 647614116

tokenizer.json

@@ -97,6 +97,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37954f477c05d31021d47ec35c1266fc46e0573105c6226de46ed96e5f543cb7
-size 4856
+oid sha256:07a5e6df1dcd5b8c6dc862e06712e4ef081606fb6b89139367d99fa7a57170ed
+size 4984