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_2_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: 0.5966
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.96,
+    "eval_loss": 0.5965979695320129,
+    "eval_runtime": 0.6884,
+    "eval_samples": 20,
+    "eval_samples_per_second": 4.358,
+    "eval_steps_per_second": 1.453,
     "total_flos": 1203933020160.0,
     "train_loss": 0.9038037260373434,
     "train_runtime": 66.4635,

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": 0.96,
+    "eval_loss": 0.5965979695320129,
+    "eval_runtime": 0.6884,
+    "eval_samples": 20,
+    "eval_samples_per_second": 4.358,
+    "eval_steps_per_second": 1.453
+}

runs/Jan20_05-22-16_dgx-a100-12/events.out.tfevents.1737347425.dgx-a100-12.982045.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e18ebb26c38c839605dd63e4b8696366c109eb48a9ff7cba99a4fbdf782c288
+size 354