End of training

README.md

@@ -1,17 +1,20 @@
 ---
 base_model: barc0/Llama-3.1-ARC-Potpourri-Induction-8B
+datasets:
+- suehyunpark/induction_arc_inputs_train_bc_trajectories_max10-per-task_check_answer
 library_name: transformers
-model_name: potpourri-8b-inst-fft-induction-bc-trajectory-max10-per-task-check-answer
+model_name: barc0/Llama-3.1-ARC-Potpourri-Induction-8B
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for potpourri-8b-inst-fft-induction-bc-trajectory-max10-per-task-check-answer
+# Model Card for barc0/Llama-3.1-ARC-Potpourri-Induction-8B
 
-This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Induction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Induction-8B).
+This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Induction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Induction-8B) on the [['suehyunpark/induction_arc_inputs_train_bc_trajectories_max10-per-task_check_answer']](https://huggingface.co/datasets/['suehyunpark/induction_arc_inputs_train_bc_trajectories_max10-per-task_check_answer']) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.1237141489982605,
+    "eval_runtime": 7.1287,
+    "eval_samples": 84,
+    "eval_samples_per_second": 11.783,
+    "eval_steps_per_second": 2.946,
     "total_flos": 11109249515520.0,
     "train_loss": 0.31718048006296157,
     "train_runtime": 911.8037,

config.json

@@ -35,6 +35,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.1237141489982605,
+    "eval_runtime": 7.1287,
+    "eval_samples": 84,
+    "eval_samples_per_second": 11.783,
+    "eval_steps_per_second": 2.946
+}