End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: tiiuae/falcon-mamba-7b-instruct
+datasets: HuggingFaceH4/Bespoke-Stratos-17k
 library_name: transformers
 model_name: mamba-distill-7b
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for mamba-distill-7b
 
-This model is a fine-tuned version of [tiiuae/falcon-mamba-7b-instruct](https://huggingface.co/tiiuae/falcon-mamba-7b-instruct).
+This model is a fine-tuned version of [tiiuae/falcon-mamba-7b-instruct](https://huggingface.co/tiiuae/falcon-mamba-7b-instruct) 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": 3.7433252334594727,
+    "eval_runtime": 42.3244,
+    "eval_samples": 100,
+    "eval_samples_per_second": 3.402,
+    "eval_steps_per_second": 0.425,
     "total_flos": 3.616227566899167e+18,
     "train_loss": 16.595592213948567,
     "train_runtime": 29081.677,

config.json

@@ -28,7 +28,7 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.1",
   "use_bias": false,
-  "use_cache": false,
+  "use_cache": true,
   "use_conv_bias": true,
   "use_mambapy": false,
   "vocab_size": 65024

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 3.7433252334594727,
+    "eval_runtime": 42.3244,
+    "eval_samples": 100,
+    "eval_samples_per_second": 3.402,
+    "eval_steps_per_second": 0.425
+}