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
@@ -20,6 +24,8 @@ should probably proofread and complete it, then remove this comment. -->
 # llama_2_cot_simplest_code_math_4_full
 
 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: 0.6062
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.9902912621359223,
-    "eval_loss": 0.6066271066665649,
-    "eval_runtime": 0.6979,
+    "eval_loss": 0.6061546802520752,
+    "eval_runtime": 0.6963,
     "eval_samples": 20,
-    "eval_samples_per_second": 7.164,
-    "eval_steps_per_second": 1.433,
+    "eval_samples_per_second": 7.181,
+    "eval_steps_per_second": 1.436,
     "total_flos": 5286836305920.0,
     "train_loss": 0.6707944402507707,
     "train_runtime": 276.6532,

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": 0.9902912621359223,
-    "eval_loss": 0.6066271066665649,
-    "eval_runtime": 0.6979,
+    "eval_loss": 0.6061546802520752,
+    "eval_runtime": 0.6963,
     "eval_samples": 20,
-    "eval_samples_per_second": 7.164,
-    "eval_steps_per_second": 1.433
+    "eval_samples_per_second": 7.181,
+    "eval_steps_per_second": 1.436
 }

runs/Jan20_13-05-32_dgx-a100-16/events.out.tfevents.1737375370.dgx-a100-16.3037652.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15d7dc589f5e228c3c1a4aa3e6aa26bf2a4ad04618774bf600d8f30b7e8d32f
+size 354