End of training

README.md

@@ -3,11 +3,16 @@ library_name: transformers
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- EunsuKim/GSM8K
+- EunsuKim/MATH
 model-index:
 - name: zephyr-7b-math-case-6-ep1
   results: []
@@ -18,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-math-case-6-ep1
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the generator dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the EunsuKim/GSM8K and the EunsuKim/MATH datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.8035
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.8034714460372925,
+    "eval_runtime": 13.2029,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 19.92,
+    "eval_steps_per_second": 0.379,
     "total_flos": 2093796556800.0,
     "train_loss": 1.0152987003326417,
     "train_runtime": 126.4024,

config.json

@@ -22,6 +22,6 @@
   "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": 1.0,
+    "eval_loss": 0.8034714460372925,
+    "eval_runtime": 13.2029,
+    "eval_samples": 4000,
+    "eval_samples_per_second": 19.92,
+    "eval_steps_per_second": 0.379
+}