End of training

README.md

@@ -3,11 +3,23 @@ license: other
 base_model: Qwen/Qwen1.5-4B
 tags:
 - generated_from_trainer
+datasets:
+- tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa
 metrics:
 - accuracy
 model-index:
 - name: lmind_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_lora2
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa
+      type: tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7780232896652111
 library_name: peft
 ---
 
@@ -16,10 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lmind_hotpot_train8000_eval7405_v1_recite_qa_Qwen_Qwen1.5-4B_lora2
 
-This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on the tyzhu/lmind_hotpot_train8000_eval7405_v1_recite_qa dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.7780
 - Loss: 0.4804
+- Accuracy: 0.7780
 
 ## Model description
 

all_results.json

@@ -2,15 +2,15 @@
     "epoch": 19.99770484278173,
     "eval_accuracy": 0.7780232896652111,
     "eval_loss": 0.4803846478462219,
-    "eval_runtime": 8.961,
+    "eval_runtime": 9.7336,
     "eval_samples": 500,
-    "eval_samples_per_second": 55.798,
-    "eval_steps_per_second": 7.03,
+    "eval_samples_per_second": 51.368,
+    "eval_steps_per_second": 6.472,
     "perplexity": 1.6166961412986696,
     "total_flos": 2.2953494160657613e+18,
-    "train_loss": 0.14266219607616806,
-    "train_runtime": 24051.9241,
+    "train_loss": 0.0,
+    "train_runtime": 0.0873,
     "train_samples": 34854,
-    "train_samples_per_second": 28.982,
-    "train_steps_per_second": 0.906
+    "train_samples_per_second": 7982672.15,
+    "train_steps_per_second": 249415.561
 }

eval_results.json

@@ -2,9 +2,9 @@
     "epoch": 19.99770484278173,
     "eval_accuracy": 0.7780232896652111,
     "eval_loss": 0.4803846478462219,
-    "eval_runtime": 8.961,
+    "eval_runtime": 9.7336,
     "eval_samples": 500,
-    "eval_samples_per_second": 55.798,
-    "eval_steps_per_second": 7.03,
+    "eval_samples_per_second": 51.368,
+    "eval_steps_per_second": 6.472,
     "perplexity": 1.6166961412986696
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 19.99770484278173,
     "total_flos": 2.2953494160657613e+18,
-    "train_loss": 0.14266219607616806,
-    "train_runtime": 24051.9241,
+    "train_loss": 0.0,
+    "train_runtime": 0.0873,
     "train_samples": 34854,
-    "train_samples_per_second": 28.982,
-    "train_steps_per_second": 0.906
+    "train_samples_per_second": 7982672.15,
+    "train_steps_per_second": 249415.561
 }

trainer_state.json

@@ -1711,10 +1711,10 @@
       "epoch": 19.99770484278173,
       "step": 21780,
       "total_flos": 2.2953494160657613e+18,
-      "train_loss": 0.14266219607616806,
-      "train_runtime": 24051.9241,
-      "train_samples_per_second": 28.982,
-      "train_steps_per_second": 0.906
+      "train_loss": 0.0,
+      "train_runtime": 0.0873,
+      "train_samples_per_second": 7982672.15,
+      "train_steps_per_second": 249415.561
     }
   ],
   "logging_steps": 100,