End of training

README.md

@@ -3,6 +3,10 @@ library_name: transformers
 license: llama2
 base_model: meta-llama/Llama-2-7b-chat-hf
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
@@ -20,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5952
+- Loss: 0.5930
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.5930158495903015,
+    "eval_runtime": 0.6676,
+    "eval_samples": 20,
+    "eval_samples_per_second": 7.489,
+    "eval_steps_per_second": 1.498,
     "total_flos": 37635993108480.0,
     "train_loss": 0.4211262113518185,
     "train_runtime": 1934.4246,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.5930158495903015,
+    "eval_runtime": 0.6676,
+    "eval_samples": 20,
+    "eval_samples_per_second": 7.489,
+    "eval_steps_per_second": 1.498
+}

runs/Jan21_12-45-02_dgx-a100-12/events.out.tfevents.1737462226.dgx-a100-12.2541347.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63628d344f479b06df3d4f522cee64e0ec81c2ae166ec290d32d2d8235384950
+size 359