End of training

README.md

@@ -53,7 +53,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.38.0.dev0
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1
 - Tokenizers 0.15.1

config.json

@@ -3,6 +3,7 @@
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
+  "attention_bias": true,
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "classifier_dropout": 0.1,
@@ -22,7 +23,7 @@
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.38.0.dev0",
   "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": "4.35.2"
+  "transformers_version": "4.38.0.dev0"
 }

runs/Jan29_09-34-44_5e1fc6260846/events.out.tfevents.1706520885.5e1fc6260846.16763.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4fb00c7485c95e5fc79c593aada0d5b6a35162ca2aa409f11bc4b16c86cfbb7
+size 5676

runs/Jan29_09-34-44_5e1fc6260846/events.out.tfevents.1706521126.5e1fc6260846.16763.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32c82adccefacd9aecc583934d35d63facedb50ee71d39d49b3b2bb3dae7647
+size 354

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bbc1f57774558ed8406cb3bde830bbb7d1643f60cb03e36e559327312b3c82
-size 4600
+oid sha256:364d576860d5dc85c98f649a9843348dadf902f251b4543b99e6eca6f066ed9f
+size 4728