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_reciteonly_qa_v3
 metrics:
 - accuracy
 model-index:
 - name: lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3_5e-5_lora2
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: tyzhu/lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3
+      type: tyzhu/lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6388470588235294
 ---
 
 <!-- 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_reciteonly_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_reciteonly_qa_v3 dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.6388
 - Loss: 2.9168
+- Accuracy: 0.6388
 
 ## Model description
 

all_results.json

@@ -1,8 +1,21 @@
 {
     "epoch": 49.87,
-    "train_loss": 0.3249321336287228,
-    "train_runtime": 27171.1238,
+    "eval_accuracy": 0.6388470588235294,
+    "eval_exact_match": 10.4,
+    "eval_f1": 16.676194916194923,
+    "eval_loss": 2.9167978763580322,
+    "eval_qa_bleu": 4.116003159748382,
+    "eval_qa_exact_match": 0.086,
+    "eval_recite_bleu": 5.897355250618618,
+    "eval_recite_exact_match": 0.002,
+    "eval_runtime": 7.9879,
+    "eval_samples": 500,
+    "eval_samples_per_second": 62.595,
+    "eval_steps_per_second": 7.887,
+    "perplexity": 18.48201092087256,
+    "train_loss": 0.0,
+    "train_runtime": 0.0361,
     "train_samples": 6000,
-    "train_samples_per_second": 11.041,
-    "train_steps_per_second": 0.344
+    "train_samples_per_second": 8317081.103,
+    "train_steps_per_second": 259215.694
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 49.87,
+    "eval_accuracy": 0.6388470588235294,
+    "eval_exact_match": 10.4,
+    "eval_f1": 16.676194916194923,
+    "eval_loss": 2.9167978763580322,
+    "eval_qa_bleu": 4.116003159748382,
+    "eval_qa_exact_match": 0.086,
+    "eval_recite_bleu": 5.897355250618618,
+    "eval_recite_exact_match": 0.002,
+    "eval_runtime": 7.9879,
+    "eval_samples": 500,
+    "eval_samples_per_second": 62.595,
+    "eval_steps_per_second": 7.887,
+    "perplexity": 18.48201092087256
+}

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 49.87,
-    "train_loss": 0.3249321336287228,
-    "train_runtime": 27171.1238,
+    "train_loss": 0.0,
+    "train_runtime": 0.0361,
     "train_samples": 6000,
-    "train_samples_per_second": 11.041,
-    "train_steps_per_second": 0.344
+    "train_samples_per_second": 8317081.103,
+    "train_steps_per_second": 259215.694
 }

trainer_state.json

@@ -1520,10 +1520,10 @@
       "epoch": 49.87,
       "step": 9350,
       "total_flos": 2.1667086796786237e+18,
-      "train_loss": 0.3249321336287228,
-      "train_runtime": 27171.1238,
-      "train_samples_per_second": 11.041,
-      "train_steps_per_second": 0.344
+      "train_loss": 0.0,
+      "train_runtime": 0.0361,
+      "train_samples_per_second": 8317081.103,
+      "train_steps_per_second": 259215.694
     }
   ],
   "logging_steps": 100,