End of training

README.md

@@ -1,11 +1,15 @@
 ---
 base_model: OrionStarAI/Orion-14B-Chat
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- ikno/rinko_v2.14
 model-index:
 - name: rinko-test
   results: []
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # rinko-test
 
-This model is a fine-tuned version of [OrionStarAI/Orion-14B-Chat](https://huggingface.co/OrionStarAI/Orion-14B-Chat) on the generator dataset.
+This model is a fine-tuned version of [OrionStarAI/Orion-14B-Chat](https://huggingface.co/OrionStarAI/Orion-14B-Chat) on the ikno/rinko_v2.14 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1385
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 1.1385215520858765,
+    "eval_runtime": 551.8633,
+    "eval_samples": 442,
+    "eval_samples_per_second": 0.386,
+    "eval_steps_per_second": 0.098,
     "train_loss": 1.2146218933042934,
     "train_runtime": 75011.8955,
     "train_samples": 5850,

config.json

@@ -28,6 +28,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 84608
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.98,
-    "eval_loss": 0.1706668883562088,
-    "eval_runtime": 131.3307,
+    "epoch": 3.0,
+    "eval_loss": 1.1385215520858765,
+    "eval_runtime": 551.8633,
     "eval_samples": 442,
-    "eval_samples_per_second": 0.274,
-    "eval_steps_per_second": 0.069
+    "eval_samples_per_second": 0.386,
+    "eval_steps_per_second": 0.098
 }