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
@@ -19,6 +23,8 @@ should probably proofread and complete it, then remove this comment. -->
 # llama_2_cot_simplest_code_math_1_3_epoch_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: 0.6809
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.769230769230769,
+    "eval_loss": 0.6808622479438782,
+    "eval_runtime": 0.6971,
+    "eval_samples": 20,
+    "eval_samples_per_second": 5.738,
+    "eval_steps_per_second": 1.435,
     "total_flos": 1832071987200.0,
     "train_loss": 0.7698192728890313,
     "train_runtime": 98.1264,

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": 2.769230769230769,
+    "eval_loss": 0.6808622479438782,
+    "eval_runtime": 0.6971,
+    "eval_samples": 20,
+    "eval_samples_per_second": 5.738,
+    "eval_steps_per_second": 1.435
+}

runs/Jan21_11-39-24_dgx-a100-12/events.out.tfevents.1737456451.dgx-a100-12.2486491.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1425e96f8efaeff0ca872f6e54085af01c9c28ae108d1bf40d00c5e4bb45b9
+size 354