End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # models
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the darija_finetune_train dataset.
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 10.0,
     "eval_darija_finetune_val_loss": 1.6740385293960571,
-    "eval_darija_finetune_val_runtime": 248.529,
-    "eval_darija_finetune_val_samples_per_second": 4.024,
-    "eval_darija_finetune_val_steps_per_second": 2.012,
+    "eval_darija_finetune_val_runtime": 247.6047,
+    "eval_darija_finetune_val_samples_per_second": 4.039,
+    "eval_darija_finetune_val_steps_per_second": 2.019,
     "total_flos": 2.3021942645089894e+17,
     "train_loss": 0.0,
-    "train_runtime": 2.5784,
-    "train_samples_per_second": 46541.284,
-    "train_steps_per_second": 5817.66
+    "train_runtime": 1.1327,
+    "train_samples_per_second": 105944.302,
+    "train_steps_per_second": 13243.038
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 10.0,
     "eval_darija_finetune_val_loss": 1.6740385293960571,
-    "eval_darija_finetune_val_runtime": 248.529,
-    "eval_darija_finetune_val_samples_per_second": 4.024,
-    "eval_darija_finetune_val_steps_per_second": 2.012
+    "eval_darija_finetune_val_runtime": 247.6047,
+    "eval_darija_finetune_val_samples_per_second": 4.039,
+    "eval_darija_finetune_val_steps_per_second": 2.019
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 10.0,
     "total_flos": 2.3021942645089894e+17,
     "train_loss": 0.0,
-    "train_runtime": 2.5784,
-    "train_samples_per_second": 46541.284,
-    "train_steps_per_second": 5817.66
+    "train_runtime": 1.1327,
+    "train_samples_per_second": 105944.302,
+    "train_steps_per_second": 13243.038
 }

trainer_state.json

@@ -11713,9 +11713,9 @@
       "step": 15000,
       "total_flos": 2.3021942645089894e+17,
       "train_loss": 0.0,
-      "train_runtime": 2.5784,
-      "train_samples_per_second": 46541.284,
-      "train_steps_per_second": 5817.66
+      "train_runtime": 1.1327,
+      "train_samples_per_second": 105944.302,
+      "train_steps_per_second": 13243.038
     }
   ],
   "logging_steps": 10,