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-sft
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
 # Model Card for gpt2-sft
 
-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

@@ -13,21 +13,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
     "embed_tokens"
   ],
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_fc",
     "c_proj",
+    "c_fc",
     "c_attn"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5820656dae1f59ddc29cd6dd75f2d4d60966338de15986c9c0fbbf2e5d2337
-size 9449344
+oid sha256:47b45c8f31b8b3a37fea6b55d2e850b0b4f42736eea082ac399597b8f6370ac1
+size 18886632

runs/Jun24_03-23-29_e41449a0ce0e/events.out.tfevents.1750735414.e41449a0ce0e.21902.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6088a88160c930b045bd38f5901758c62a15f552769e66e9d213e89478315d
+size 41662

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cbb31db80f93ba2fabff595edf502bb560fbdf93e47089709635ba13b03aef8
+oid sha256:cf018642b6c872f89f54f579e09e8b98fa7758344feffb7e86eb5029f5013eb8
 size 5752