End of training

README.md

@@ -1,6 +1,5 @@
 ---
-license: other
-base_model: facebook/opt-350m
+base_model: domsebalj/GPcroaT
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Unh_model
 
-This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the None dataset.
+This model is a fine-tuned version of [domsebalj/GPcroaT](https://huggingface.co/domsebalj/GPcroaT) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3884
+- Loss: 4.8975
 
 ## Model description
 

generation_config.json

@@ -1,7 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 2,
+  "bos_token_id": 0,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.36.0.dev0"
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:956e9f52a24eaa3c8b8fbeb4fc376c9e93044092cbe2392493cdcb2c7ff9de55
+oid sha256:7be4366488ed29e7c429c48d2e896feb211bdaa575e54560986eb38a27f2bd5a
 size 497774208

runs/Apr25_01-16-05_DESKTOP-0IP9EM7/events.out.tfevents.1714000979.DESKTOP-0IP9EM7.8980.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:952805ba68353e5f8c7edacbf1007ed82d178cc122bb68e351bf50fc2b62aeb1
-size 4914
+oid sha256:782bc0a6835f9a402a9700be77045a14122502bdaa48ff35f3b0665c1ffdc2f8
+size 5268

runs/Apr25_01-16-05_DESKTOP-0IP9EM7/events.out.tfevents.1714034300.DESKTOP-0IP9EM7.8980.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9396fb382d21f8fe461e66f9214d8141ac56436b2204e90dd32ecb471aedcb57
+size 359