End of training

README.md

@@ -2,11 +2,15 @@
 library_name: transformers
 base_model: weqweasdas/gpt2-cpt-dutch
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- BramVanroy/ultrachat_200k_dutch
 model-index:
 - name: gpt2-sft-dutch
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2-sft-dutch
 
-This model is a fine-tuned version of [weqweasdas/gpt2-cpt-dutch](https://huggingface.co/weqweasdas/gpt2-cpt-dutch) on the generator dataset.
+This model is a fine-tuned version of [weqweasdas/gpt2-cpt-dutch](https://huggingface.co/weqweasdas/gpt2-cpt-dutch) on the BramVanroy/ultrachat_200k_dutch dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.9502
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 2.950244188308716,
+    "eval_runtime": 862.0524,
+    "eval_samples": 21424,
+    "eval_samples_per_second": 30.73,
+    "eval_steps_per_second": 0.96,
     "total_flos": 317731110912000.0,
     "train_loss": 3.1433490953947367,
     "train_runtime": 1149.309,

config.json

@@ -34,6 +34,6 @@
   },
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 50257
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.950244188308716,
+    "eval_runtime": 862.0524,
+    "eval_samples": 21424,
+    "eval_samples_per_second": 30.73,
+    "eval_steps_per_second": 0.96
+}

runs/Sep28_14-43-08_ip-10-192-36-160/events.out.tfevents.1727536605.ip-10-192-36-160.3362089.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68046a5a80d2a02e90e5be95c48e6806aa67922c94975e6dfc07c513482c156
+size 354