End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: khalidalt/AceGPT-v2-8b-chat
+datasets: HuggingFaceH4/Bespoke-Stratos-17k
 library_name: transformers
 model_name: AceGPT-v2-8b-chat-Open-R1-Distill
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for AceGPT-v2-8b-chat-Open-R1-Distill
 
-This model is a fine-tuned version of [khalidalt/AceGPT-v2-8b-chat](https://huggingface.co/khalidalt/AceGPT-v2-8b-chat).
+This model is a fine-tuned version of [khalidalt/AceGPT-v2-8b-chat](https://huggingface.co/khalidalt/AceGPT-v2-8b-chat) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.6932045221328735,
+    "eval_runtime": 3.255,
+    "eval_samples": 100,
+    "eval_samples_per_second": 38.403,
+    "eval_steps_per_second": 1.229,
     "total_flos": 136410845675520.0,
     "train_loss": 0.7452732097883166,
     "train_runtime": 1860.6281,

config.json

@@ -25,6 +25,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 0.6932045221328735,
+    "eval_runtime": 3.255,
+    "eval_samples": 100,
+    "eval_samples_per_second": 38.403,
+    "eval_steps_per_second": 1.229
+}