Training in progress, step 250

README.md

@@ -1,18 +1,17 @@
 ---
 base_model: openai-community/gpt2
-datasets: rajpurkar/squad
 library_name: transformers
 model_name: gpt2-qat
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
 # Model Card for gpt2-qat
 
-This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the [rajpurkar/squad](https://huggingface.co/datasets/rajpurkar/squad) dataset.
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -26,8 +26,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_attn",
     "c_proj",
+    "c_attn",
     "c_fc"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18c5b07d738d80b24cbf4c9370c8134f2e1eaf1e34f4e37d49993187ab4a684
+oid sha256:ec0c690a517cb2d6dedb0995e13a0b6e6b1bbe9c50cfa2636093942ec9a85faf
 size 9449344

runs/Jun26_14-31-30_b91125c80c7b/events.out.tfevents.1750948326.b91125c80c7b.2983.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa6016e5ef6e7bb4524b19047697b8f94748f3033ab961500c7abed352a9f5e
+size 41662

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95472a244a9f3c1f849809777b906e5713075c2ce4f7bc603080f2533c65665d
+oid sha256:64b29340347f365792afe9fad275fd78367586364010e6e76cf810bb5d9eab42
 size 5752