neihc/miniCPM_finetune

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: neihc/SLM_qlora
+base_model: openbmb/MiniCPM-1B-sft-bf16
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # minicpm_finetune
 
-This model is a fine-tuned version of [neihc/SLM_qlora](https://huggingface.co/neihc/SLM_qlora) on the None dataset.
+This model is a fine-tuned version of [openbmb/MiniCPM-1B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-1B-sft-bf16) on the None dataset.
 
 ## Model description
 
@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 2
 - mixed_precision_training: Native AMP
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.14.0
-- Transformers 4.44.2
-- Pytorch 2.4.1+cu121
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu121
 - Datasets 3.2.0
-- Tokenizers 0.19.1
+- Tokenizers 0.21.0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "neihc/SLM_qlora",
+  "base_model_name_or_path": "openbmb/MiniCPM-1B-sft-bf16",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,8 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
+    "v_proj",
     "o_proj",
     "k_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f63df9d462b777e14ff171a67b847379e9a9b7ab7a7a45e0d132b9ccbb04717
+oid sha256:285777da51029bfc50a99e98a6456101df4c533d9c89d5f61b8896435ff388ba
 size 34134464

runs/Jan16_02-39-34_e0c7518cedc5/events.out.tfevents.1736995174.e0c7518cedc5.18.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe70eb8c66db47e5a26a17f3988bf2df79a2fa45bc29b51425cbb255a4ceb68
+size 7718

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a349fa059098bf71cd473a8be27ebd3ac2246cc2d2e8e0ede2781672f2f510a3
-size 5176
+oid sha256:978467cc92b25fec1329cc368ce5651dae15cbbc67f296c4187d8bc2a3af8aee
+size 5304