End of training

README.md

@@ -2,6 +2,7 @@
 library_name: peft
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.3
 model-index:
@@ -14,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral_AAID_new_mixed_train
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the AAID_new_mixed dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5525
+- Loss: 0.5337
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.06562756357670221,
     "eval_loss": 0.5337400436401367,
-    "eval_runtime": 230.7886,
-    "eval_samples_per_second": 20.417,
-    "eval_steps_per_second": 0.641,
+    "eval_runtime": 229.7017,
+    "eval_samples_per_second": 20.514,
+    "eval_steps_per_second": 0.644,
     "total_flos": 1.143902298880082e+17,
     "train_loss": 0.43926427761713666,
-    "train_runtime": 4213.5123,
-    "train_samples_per_second": 166.635,
-    "train_steps_per_second": 0.651
+    "train_runtime": 4197.7951,
+    "train_samples_per_second": 167.259,
+    "train_steps_per_second": 0.653
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.06562756357670221,
     "eval_loss": 0.5337400436401367,
-    "eval_runtime": 230.7886,
-    "eval_samples_per_second": 20.417,
-    "eval_steps_per_second": 0.641
+    "eval_runtime": 229.7017,
+    "eval_samples_per_second": 20.514,
+    "eval_steps_per_second": 0.644
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.06562756357670221,
     "total_flos": 1.143902298880082e+17,
     "train_loss": 0.43926427761713666,
-    "train_runtime": 4213.5123,
-    "train_samples_per_second": 166.635,
-    "train_steps_per_second": 0.651
+    "train_runtime": 4197.7951,
+    "train_samples_per_second": 167.259,
+    "train_steps_per_second": 0.653
 }

trainer_state.json

@@ -18,9 +18,9 @@
     {
       "epoch": 0.010937927262783703,
       "eval_loss": 0.5337400436401367,
-      "eval_runtime": 231.0066,
-      "eval_samples_per_second": 20.398,
-      "eval_steps_per_second": 0.641,
+      "eval_runtime": 229.8812,
+      "eval_samples_per_second": 20.498,
+      "eval_steps_per_second": 0.644,
       "step": 10
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.021875854525567406,
       "eval_loss": 0.5784199833869934,
-      "eval_runtime": 231.0005,
-      "eval_samples_per_second": 20.398,
-      "eval_steps_per_second": 0.641,
+      "eval_runtime": 229.9779,
+      "eval_samples_per_second": 20.489,
+      "eval_steps_per_second": 0.644,
       "step": 20
     },
     {
@@ -48,9 +48,9 @@
     {
       "epoch": 0.03281378178835111,
       "eval_loss": 0.5616388320922852,
-      "eval_runtime": 230.9639,
-      "eval_samples_per_second": 20.401,
-      "eval_steps_per_second": 0.641,
+      "eval_runtime": 229.9158,
+      "eval_samples_per_second": 20.494,
+      "eval_steps_per_second": 0.644,
       "step": 30
     },
     {
@@ -63,9 +63,9 @@
     {
       "epoch": 0.04375170905113481,
       "eval_loss": 0.5677462220191956,
-      "eval_runtime": 231.0825,
-      "eval_samples_per_second": 20.391,
-      "eval_steps_per_second": 0.64,
+      "eval_runtime": 230.0577,
+      "eval_samples_per_second": 20.482,
+      "eval_steps_per_second": 0.643,
       "step": 40
     },
     {
@@ -78,9 +78,9 @@
     {
       "epoch": 0.05468963631391851,
       "eval_loss": 0.5386738181114197,
-      "eval_runtime": 231.0958,
-      "eval_samples_per_second": 20.39,
-      "eval_steps_per_second": 0.64,
+      "eval_runtime": 229.8738,
+      "eval_samples_per_second": 20.498,
+      "eval_steps_per_second": 0.644,
       "step": 50
     },
     {
@@ -93,9 +93,9 @@
     {
       "epoch": 0.06562756357670221,
       "eval_loss": 0.5525479912757874,
-      "eval_runtime": 230.9516,
-      "eval_samples_per_second": 20.403,
-      "eval_steps_per_second": 0.641,
+      "eval_runtime": 229.8844,
+      "eval_samples_per_second": 20.497,
+      "eval_steps_per_second": 0.644,
       "step": 60
     },
     {
@@ -103,9 +103,9 @@
       "step": 60,
       "total_flos": 1.143902298880082e+17,
       "train_loss": 0.43926427761713666,
-      "train_runtime": 4213.5123,
-      "train_samples_per_second": 166.635,
-      "train_steps_per_second": 0.651
+      "train_runtime": 4197.7951,
+      "train_samples_per_second": 167.259,
+      "train_steps_per_second": 0.653
     }
   ],
   "logging_steps": 10,