End of training

README.md

@@ -32,13 +32,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
+- learning_rate: 0.001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.37.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.17.0
-- Tokenizers 0.15.1
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -56,7 +56,7 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.37.2"
 }

logs/events.out.tfevents.1709191609.ff1fe9468526.163.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e156d5748ad274f7361c5b30ff2672b9ca8b7fd26556a9a4d30a82e544ec4ea
+size 6463

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7986a098d3918ddf468a2e09f20d35666582f40c27dbc6090e4cd6c777aa7d2
+oid sha256:2e385e0f0427487600e7962d5d4c1ddd0739c5c005aa0f2fa997bc64c9c7b62d
 size 990345064

special_tokens_map.json

@@ -101,7 +101,25 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8610b9e67d2f1b12f843b2b355dd712731be3c0e1d3d9b2d2f25d13e6103e4ec
-size 4728
+oid sha256:902c20a2f7ccd7a7ff4b2420ce563b149346c9413563a318635f94f5e64a85bf
+size 4856