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-chat-no-template
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama2-7b-sft-chat-no-template
 
-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: 1.1158
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.999000999000999,
+    "eval_loss": 1.1158442497253418,
+    "eval_runtime": 10.511,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 25.117,
+    "eval_steps_per_second": 1.617,
     "total_flos": 1.2990581727276564e+18,
     "train_loss": 1.172668625831604,
     "train_runtime": 2523.6133,

config.json

@@ -25,6 +25,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32002
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999000999000999,
+    "eval_loss": 1.1158442497253418,
+    "eval_runtime": 10.511,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 25.117,
+    "eval_steps_per_second": 1.617
+}

runs/Jun07_13-16-40_195dfccd8985/events.out.tfevents.1717769327.195dfccd8985.4766.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb35014c0d52400c1c8278adebd0fdc77ba8a37fd35e3e5cb9c870750e23cce
+size 354