End of training

README.md

@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.39.3
+- Transformers 4.41.2
 - Pytorch 2.1.2
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.19.1

config.json

@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61411e8b548af7597574881890f70313567cea7b8823c1b4f3c4b8810694a27f
+oid sha256:bdc4c3e7ed9d833122aff41c8fcffbef0becf272b4a37443b54b2e79b780fb11
 size 497774208

runs/Jun17_06-33-03_4ff59a08e159/events.out.tfevents.1718605985.4ff59a08e159.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7e24fd6b6d465c231e3e30d115ef80a43c836fd76507e40fecd35f24e34ec8
+size 5613

tokenizer.json

@@ -40,6 +40,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b24ea6724d6aaa447214d8200359cd9d6bb052821aa654da36aff8434ac940b
-size 4920
+oid sha256:d4ca1f9b97a529bfe5c6e592b026bc73b65e553f25cc19abbe24d8b5323668e0
+size 5112