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
 - alignment-handbook
@@ -21,7 +25,7 @@ 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: 0.5445
+- Loss: 0.5425
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.5658748745918274,
-    "eval_runtime": 0.6657,
+    "eval_loss": 0.5425216555595398,
+    "eval_runtime": 0.6709,
     "eval_samples": 20,
-    "eval_samples_per_second": 7.511,
-    "eval_steps_per_second": 1.502,
+    "eval_samples_per_second": 7.453,
+    "eval_steps_per_second": 1.491,
     "total_flos": 12510434426880.0,
     "train_loss": 0.6044951339562734,
     "train_runtime": 648.7175,

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

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.5658748745918274,
-    "eval_runtime": 0.6657,
+    "eval_loss": 0.5425216555595398,
+    "eval_runtime": 0.6709,
     "eval_samples": 20,
-    "eval_samples_per_second": 7.511,
-    "eval_steps_per_second": 1.502
+    "eval_samples_per_second": 7.453,
+    "eval_steps_per_second": 1.491
 }

runs/Jan20_13-18-14_dgx-a100-16/events.out.tfevents.1737376509.dgx-a100-16.3048174.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2e4f59e866209ee08162e5aac4f5a2e6f8b4dd9458ae551c7456e0daaeb442
+size 354