Training done for bart-large-mnli

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4526
+- Loss: 1.5107
 
 ## Model description
 
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.4268        | 0.54  | 500  | 1.4526          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.4099        | 0.5431 | 500  | 1.5107          |
 
 
 ### Framework versions
 
-- Transformers 4.39.3
-- Pytorch 2.1.2
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -45,7 +45,7 @@
   "pad_token_id": 1,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "vocab_size": 50265
 }

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.40.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59865da2a6651a7aa47b6cf0667f7c4888f78479cf8a2440c48b4b8c6e204f5d
+oid sha256:bb9bf0d73c73e15ec1ae8547f74e144a39a50e49fd8bd770a71d2277f5083bc4
 size 1625426996

tokenizer.json

@@ -88,6 +88,7 @@
     "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 sha256:69b3527c0eb2171e9760f0aad5c1066138d2bddb2c4680c30749ecee5755e736
-size 4920
+oid sha256:74ef5f207a77a7a3bca0e3a72440be24a3828665b78d8b16c82b3f7ca15d12b1
+size 4984