Training in progress, step 40

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
-- trl
 - sft
+- trl
 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
@@ -28,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/shoubing-apple/huggingface/runs/8j5wiaig) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/shoubing-apple/huggingface/runs/7fvvdarg) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -15,7 +15,7 @@
   "loftq_config": {},
   "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
@@ -26,9 +26,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "c_fc",
     "c_attn",
-    "c_proj",
-    "c_fc"
+    "c_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd7aecb971ad3e3952bd7ee70bb0686045bdcf0aa0dfd282151d92cae72148c
+oid sha256:af18ac57a03f9302f156bdb886cbd59bf4dee2798128f81aa7a7cdce59130a33
 size 9449344

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1ba0f042464a14cbe6d0413d6be19e4fdf55507b5502d2009d53d7c79213f4
+oid sha256:78d0583001c3a841c3dfe9e14c938b81b9b8b47bcf0822bc152218da98197450
 size 497774208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c4dc2ccc1968527222ae4b48d920c514561a5ec43d5513429641c2f5fbdce7
+oid sha256:5a92452418d5296c17d6031c229cce7bd0be37688510d53bf398a2e36e5f9120
 size 5752