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: 0.5805
+- Loss: 0.5801
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.9955156950672646,
-    "eval_loss": 0.5801262855529785,
-    "eval_runtime": 0.6673,
+    "eval_loss": 0.5800525546073914,
+    "eval_runtime": 0.6697,
     "eval_samples": 20,
-    "eval_samples_per_second": 7.493,
-    "eval_steps_per_second": 1.499,
+    "eval_samples_per_second": 7.466,
+    "eval_steps_per_second": 1.493,
     "total_flos": 11568225976320.0,
     "train_loss": 0.6219194515331371,
     "train_runtime": 596.6457,

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": 0.9955156950672646,
-    "eval_loss": 0.5801262855529785,
-    "eval_runtime": 0.6673,
+    "eval_loss": 0.5800525546073914,
+    "eval_runtime": 0.6697,
     "eval_samples": 20,
-    "eval_samples_per_second": 7.493,
-    "eval_steps_per_second": 1.499
+    "eval_samples_per_second": 7.466,
+    "eval_steps_per_second": 1.493
 }

runs/Jan20_02-23-09_dgx-a100-13/events.out.tfevents.1737337175.dgx-a100-13.1085210.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cabdbbc66b533ba4c1e5c819f6b4cbd171b00db46148a732504abcdbbcd06fef
+size 354