Model save

README.md

@@ -32,8 +32,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 15
+- eval_batch_size: 15
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.39.2
 - Pytorch 2.1.2+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

config.json

@@ -28,7 +28,7 @@
   "tie_word_embeddings": false,
   "tokenizer_class": "LlamaTokenizerFast",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.39.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.39.2"
 }

runs/Apr02_20-24-59_pcknot9/events.out.tfevents.1712082347.pcknot9.2758853.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa47867eb68754cec6877cd9df71a7e20d0c196e02f72010a078c4c6292966d
+size 19847

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86cb47a0c66dbefbcab56f316ff1c88ef9765acffae886b74c38b55c330cc7d
-size 5048
+oid sha256:7f4420f263088ddb824489a4c57cbce933a7c1d00d7c3d6894f0ae23a32a3553
+size 5112