End of training

README.md

@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.36.1
-- Pytorch 2.1.1+cu121
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
 - Datasets 2.15.0
 - Tokenizers 0.15.0

config.json

@@ -22,7 +22,7 @@
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.36.1",
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50304

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "transformers_version": "4.36.1"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78fbe9815283cfcc11c957d3f6c3b76fbf54e5c51ca43986937da92788c2dbb
+oid sha256:0d1ca1e386fc015cba0a1adcd5fba563f863c5806d7a25a6ba0f574657e6cefb
 size 281715176

runs/Dec15_03-34-23_1f37e32bd092/events.out.tfevents.1702611270.1f37e32bd092.1174.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ddcca6c30edf39594fee3fef21d99f30b17808f0c1dd87b7f07012e7471f36
+size 5098

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:416483b949185d58561313ec7ab12457a51f8359e52f5a2c3b6165464c9a3859
-size 4664
+oid sha256:dd16b84837c09c35e7956f42e87406fc85d099d96257ddd87a30557a10bc311e
+size 4536