End of training

README.md

@@ -1,11 +1,15 @@
 ---
 base_model: meta-llama/Llama-2-7b-hf
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/deita-10k-v0-sft
 model-index:
 - name: llama2-7b-wo-live_qa-sft
   results: []
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama2-7b-wo-live_qa-sft
 
-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 generator 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 HuggingFaceH4/deita-10k-v0-sft dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.4111
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 1.411104440689087,
+    "eval_runtime": 1.3896,
+    "eval_samples": 100,
+    "eval_samples_per_second": 5.757,
+    "eval_steps_per_second": 0.72,
     "train_loss": 0.9259367443266369,
     "train_runtime": 345.6861,
     "train_samples": 4848,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.411104440689087,
+    "eval_runtime": 1.3896,
+    "eval_samples": 100,
+    "eval_samples_per_second": 5.757,
+    "eval_steps_per_second": 0.72
+}