Model save

README.md

@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # checkpoints
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6955
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.13043478260869565,
-    "eval_loss": 1.6952797174453735,
-    "eval_runtime": 2.2512,
-    "eval_samples_per_second": 274.076,
-    "eval_steps_per_second": 4.442,
+    "eval_loss": 1.6954997777938843,
+    "eval_runtime": 2.0177,
+    "eval_samples_per_second": 305.789,
+    "eval_steps_per_second": 4.956,
     "total_flos": 3.355230384370483e+16,
-    "train_loss": 1.4136702219645183,
-    "train_runtime": 204.3723,
-    "train_samples_per_second": 7.516,
+    "train_loss": 1.413570721944173,
+    "train_runtime": 204.0944,
+    "train_samples_per_second": 7.526,
     "train_steps_per_second": 0.015
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.13043478260869565,
-    "eval_loss": 1.6952797174453735,
-    "eval_runtime": 2.2512,
-    "eval_samples_per_second": 274.076,
-    "eval_steps_per_second": 4.442
+    "eval_loss": 1.6954997777938843,
+    "eval_runtime": 2.0177,
+    "eval_samples_per_second": 305.789,
+    "eval_steps_per_second": 4.956
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.13043478260869565,
     "total_flos": 3.355230384370483e+16,
-    "train_loss": 1.4136702219645183,
-    "train_runtime": 204.3723,
-    "train_samples_per_second": 7.516,
+    "train_loss": 1.413570721944173,
+    "train_runtime": 204.0944,
+    "train_samples_per_second": 7.526,
     "train_steps_per_second": 0.015
 }

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 0.13043478260869565,
-      "eval_loss": 1.6952797174453735,
-      "eval_runtime": 1.8822,
-      "eval_samples_per_second": 327.804,
-      "eval_steps_per_second": 5.313,
+      "eval_loss": 1.6954997777938843,
+      "eval_runtime": 1.8869,
+      "eval_samples_per_second": 326.995,
+      "eval_steps_per_second": 5.3,
       "step": 3
     },
     {
       "epoch": 0.13043478260869565,
       "step": 3,
       "total_flos": 3.355230384370483e+16,
-      "train_loss": 1.4136702219645183,
-      "train_runtime": 204.3723,
-      "train_samples_per_second": 7.516,
+      "train_loss": 1.413570721944173,
+      "train_runtime": 204.0944,
+      "train_samples_per_second": 7.526,
       "train_steps_per_second": 0.015
     }
   ],