End of training

README.md

@@ -2,11 +2,15 @@
 license: llama2
 base_model: meta-llama/Llama-2-7b-hf
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: llama2-7b-sft-full-llama2
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama2-7b-sft-full-llama2
 
-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/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0380
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.994059405940594,
+    "eval_loss": 1.0379831790924072,
+    "eval_runtime": 93.7153,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 2.838,
+    "eval_steps_per_second": 0.181,
     "total_flos": 158238674780160.0,
     "train_loss": 0.8970171990533354,
     "train_runtime": 67109.8008,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.994059405940594,
+    "eval_loss": 1.0379831790924072,
+    "eval_runtime": 93.7153,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 2.838,
+    "eval_steps_per_second": 0.181
+}

runs/Jun06_17-25-47_g29lc7ctr1717663620987-f7gj6/events.out.tfevents.1717733644.g29lc7ctr1717663620987-f7gj6.11042.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fe5099918117e0765ef6014934178af979f78550603d97651d587c59cdd9a1
+size 311