Model save

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-0.5B-Instruct
 tags:
@@ -38,8 +39,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
@@ -51,7 +52,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.43.3
+- Transformers 4.44.2
 - Pytorch 2.4.0+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.43.3"
+  "transformers_version": "4.44.2"
 }

runs/Sep26_13-33-55_nlu12a2/events.out.tfevents.1727325250.nlu12a2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e9d8d5e569327673a0dbc525fa917c67f53fea5c0bb8b2dbefaeafe34c7559
-size 11661
+oid sha256:ff38e1605b5a22b7e53586038a6e9c32731a6dabc5b60e1087c7095ea5ddf24a
+size 12226