End of training

README.md

@@ -3,11 +3,19 @@ library_name: transformers
 license: bigcode-openrail-m
 base_model: bigcode/starcoder2-15b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/airoboros-3.2
+- HuggingFaceH4/Code-Feedback
+- HuggingFaceH4/orca-math-word-problems-200k
+- HuggingFaceH4/SystemChat
+- HuggingFaceH4/capybara
 model-index:
 - name: starchat2-15b-v0.1
   results: []
@@ -18,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # starchat2-15b-v0.1
 
-This model is a fine-tuned version of [bigcode/starcoder2-15b](https://huggingface.co/bigcode/starcoder2-15b) on the generator dataset.
+This model is a fine-tuned version of [bigcode/starcoder2-15b](https://huggingface.co/bigcode/starcoder2-15b) on the HuggingFaceH4/airoboros-3.2, the HuggingFaceH4/Code-Feedback, the HuggingFaceH4/orca-math-word-problems-200k, the HuggingFaceH4/SystemChat and the HuggingFaceH4/capybara datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.6601
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.6600508093833923,
+    "eval_runtime": 57.294,
+    "eval_samples": 3200,
+    "eval_samples_per_second": 24.051,
+    "eval_steps_per_second": 0.105,
     "total_flos": 1.183665069490176e+16,
     "train_loss": 0.5413940727492392,
     "train_runtime": 63958.3461,

config.json

@@ -28,6 +28,6 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.2",
   "use_bias": true,
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 49154
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6600508093833923,
+    "eval_runtime": 57.294,
+    "eval_samples": 3200,
+    "eval_samples_per_second": 24.051,
+    "eval_steps_per_second": 0.105
+}