Model save

README.md

@@ -37,7 +37,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant
 - num_epochs: 10
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.52.4
-- Pytorch 2.7.1+cu126
-- Datasets 3.6.0
-- Tokenizers 0.21.1
+- Transformers 4.54.1
+- Pytorch 2.2.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.21.4

config.json

@@ -21,7 +21,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.52.4",
+  "transformers_version": "4.54.1",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.52.4"
+  "transformers_version": "4.54.1"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f8b5359eaf817edd8a1275ab46518ba54f8b1cc13a090c9a45c49b432c5c477
+oid sha256:74496829602f30365a8297ec98836e9595371197917b5edf910fa4529efb6c34
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a916d190b7382cfcd959fe3082df62b8548f5303235fb8fb6e2e75c77131c05c
+oid sha256:803448b914a2660234a8deb6f5bdc12984d25662a54bdd0ecf8660014e652dfb
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:617c7821d4a727f69c7e4a35f5ceeb437289679aa3901f2e9e553d2083187a6d
+oid sha256:7df58de682b83275d1140299e3ac771f62b033cbc06c946c6c400c71d38da11c
 size 4540516344

model.safetensors.index.json

@@ -1,5 +1,6 @@
 {
   "metadata": {
+    "total_parameters": 7241732096,
     "total_size": 14483464192
   },
   "weight_map": {

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e88064fbdeee62f7dc6888ef52c7bb966725b9a8639d5c858a688f93753bf335
-size 5777
+oid sha256:97a8320fdacd2ba156e6a705250f518b61bfb681f56c298cd82e2186310336f3
+size 5368