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_nq_train6000_eval6489_v1_doc_qa_v3
 metrics:
 - accuracy
 model-index:
 - name: lmind_nq_train6000_eval6489_v1_doc_qa_v3_5e-5_lora2
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: tyzhu/lmind_nq_train6000_eval6489_v1_doc_qa_v3
+      type: tyzhu/lmind_nq_train6000_eval6489_v1_doc_qa_v3
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.19302564102564101
 ---
 
 <!-- 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_nq_train6000_eval6489_v1_doc_qa_v3_5e-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_nq_train6000_eval6489_v1_doc_qa_v3 dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.1930
 - Loss: 6.7918
+- Accuracy: 0.1930
 
 ## Model description
 

all_results.json

@@ -1,8 +1,17 @@
 {
     "epoch": 50.0,
-    "train_loss": 4.017823467146472,
-    "train_runtime": 26175.2328,
+    "eval_accuracy": 0.19302564102564101,
+    "eval_exact_match": 0.0,
+    "eval_f1": 0.0,
+    "eval_loss": 6.791760444641113,
+    "eval_runtime": 4.5773,
+    "eval_samples": 500,
+    "eval_samples_per_second": 109.236,
+    "eval_steps_per_second": 13.764,
+    "perplexity": 890.4798232006837,
+    "train_loss": 0.0,
+    "train_runtime": 0.0891,
     "train_samples": 16925,
-    "train_samples_per_second": 32.33,
-    "train_steps_per_second": 1.01
+    "train_samples_per_second": 9495099.902,
+    "train_steps_per_second": 296774.467
 }

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 50.0,
+    "eval_accuracy": 0.19302564102564101,
+    "eval_exact_match": 0.0,
+    "eval_f1": 0.0,
+    "eval_loss": 6.791760444641113,
+    "eval_runtime": 4.5773,
+    "eval_samples": 500,
+    "eval_samples_per_second": 109.236,
+    "eval_steps_per_second": 13.764,
+    "perplexity": 890.4798232006837
+}

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 50.0,
-    "train_loss": 4.017823467146472,
-    "train_runtime": 26175.2328,
+    "train_loss": 0.0,
+    "train_runtime": 0.0891,
     "train_samples": 16925,
-    "train_samples_per_second": 32.33,
-    "train_steps_per_second": 1.01
+    "train_samples_per_second": 9495099.902,
+    "train_steps_per_second": 296774.467
 }

trainer_state.json

@@ -2346,10 +2346,10 @@
       "epoch": 50.0,
       "step": 26450,
       "total_flos": 4.466691005730521e+18,
-      "train_loss": 4.017823467146472,
-      "train_runtime": 26175.2328,
-      "train_samples_per_second": 32.33,
-      "train_steps_per_second": 1.01
+      "train_loss": 0.0,
+      "train_runtime": 0.0891,
+      "train_samples_per_second": 9495099.902,
+      "train_steps_per_second": 296774.467
     }
   ],
   "logging_steps": 100,