Model save

README.md

@@ -27,17 +27,17 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/speechlabx/huggingface/runs/16y652o3) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/speechlabx/huggingface/runs/z3wf3e81) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.16.0.dev0
-- Transformers: 4.49.0.dev0
+- TRL: 0.15.0
+- Transformers: 4.48.2
 - Pytorch: 2.5.1
-- Datasets: 3.3.0
+- Datasets: 3.3.1
 - Tokenizers: 0.21.0
 
 ## Citations

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 230593791000576.0,
-    "train_loss": 0.7078155129410982,
-    "train_runtime": 41256.6124,
+    "train_loss": 0.7156181658528796,
+    "train_runtime": 41815.0838,
     "train_samples": 16610,
-    "train_samples_per_second": 1.572,
-    "train_steps_per_second": 0.025
+    "train_samples_per_second": 1.551,
+    "train_steps_per_second": 0.024
 }

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.49.0.dev0"
+  "transformers_version": "4.48.2"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 230593791000576.0,
-    "train_loss": 0.7078155129410982,
-    "train_runtime": 41256.6124,
+    "train_loss": 0.7156181658528796,
+    "train_runtime": 41815.0838,
     "train_samples": 16610,
-    "train_samples_per_second": 1.572,
-    "train_steps_per_second": 0.025
+    "train_samples_per_second": 1.551,
+    "train_steps_per_second": 0.024
 }