End of training

README.md

@@ -3,11 +3,23 @@ license: llama2
 base_model: meta-llama/Llama-2-7b-hf
 tags:
 - generated_from_trainer
+datasets:
+- tyzhu/lmind_hotpot_train8000_eval7405_v1_qa
 metrics:
 - accuracy
 model-index:
 - name: lmind_hotpot_train8000_eval7405_v1_qa_3e-5_lora2
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: tyzhu/lmind_hotpot_train8000_eval7405_v1_qa
+      type: tyzhu/lmind_hotpot_train8000_eval7405_v1_qa
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5822278481012658
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lmind_hotpot_train8000_eval7405_v1_qa_3e-5_lora2
 
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the tyzhu/lmind_hotpot_train8000_eval7405_v1_qa dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.5822
 - Loss: 3.7015
+- Accuracy: 0.5822
 
 ## Model description
 

all_results.json

@@ -4,14 +4,14 @@
     "eval_exact_match": 19.4,
     "eval_f1": 26.94522921522923,
     "eval_loss": 3.701465368270874,
-    "eval_runtime": 4.7587,
+    "eval_runtime": 5.4758,
     "eval_samples": 500,
-    "eval_samples_per_second": 105.071,
-    "eval_steps_per_second": 13.239,
+    "eval_samples_per_second": 91.311,
+    "eval_steps_per_second": 11.505,
     "perplexity": 40.50661800407129,
-    "train_loss": 0.6210551054382324,
-    "train_runtime": 10560.0995,
+    "train_loss": 0.0,
+    "train_runtime": 0.0441,
     "train_samples": 8000,
-    "train_samples_per_second": 37.878,
-    "train_steps_per_second": 1.184
+    "train_samples_per_second": 9078629.213,
+    "train_steps_per_second": 283707.163
 }

eval_results.json

@@ -4,9 +4,9 @@
     "eval_exact_match": 19.4,
     "eval_f1": 26.94522921522923,
     "eval_loss": 3.701465368270874,
-    "eval_runtime": 4.7587,
+    "eval_runtime": 5.4758,
     "eval_samples": 500,
-    "eval_samples_per_second": 105.071,
-    "eval_steps_per_second": 13.239,
+    "eval_samples_per_second": 91.311,
+    "eval_steps_per_second": 11.505,
     "perplexity": 40.50661800407129
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 50.0,
-    "train_loss": 0.6210551054382324,
-    "train_runtime": 10560.0995,
+    "train_loss": 0.0,
+    "train_runtime": 0.0441,
     "train_samples": 8000,
-    "train_samples_per_second": 37.878,
-    "train_steps_per_second": 1.184
+    "train_samples_per_second": 9078629.213,
+    "train_steps_per_second": 283707.163
 }

trainer_state.json

@@ -1512,10 +1512,10 @@
       "epoch": 50.0,
       "step": 12500,
       "total_flos": 7.99330713965953e+17,
-      "train_loss": 0.6210551054382324,
-      "train_runtime": 10560.0995,
-      "train_samples_per_second": 37.878,
-      "train_steps_per_second": 1.184
+      "train_loss": 0.0,
+      "train_runtime": 0.0441,
+      "train_samples_per_second": 9078629.213,
+      "train_steps_per_second": 283707.163
     }
   ],
   "logging_steps": 100,