Model save

README.md

@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.0           | 0.9991 | 729  | nan             |
-| 0.0           | 1.9997 | 1459 | nan             |
-| 0.0           | 2.9974 | 2187 | nan             |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0           | 1.0   | 130  | nan             |
+| 0.0           | 2.0   | 260  | nan             |
+| 0.0           | 3.0   | 390  | nan             |
 
 
 ### Framework versions
 
-- Transformers 4.41.1
+- Transformers 4.41.2
 - Pytorch 2.3.0+cu121
-- Datasets 2.19.1
+- Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -27,7 +27,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
+  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.41.1"
+  "transformers_version": "4.41.2"
 }