neihc/miniCPM_finetune

README.md

@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 16
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - 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 4.46.3
-- Pytorch 2.4.0
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -23,9 +23,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
     "q_proj",
+    "o_proj",
+    "v_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16439eca64be48994506fa9e362a71e1e694c8f6eb935be905692c466f408334
+oid sha256:a8b2a9e30f1cd2f51ba056f6db8adb4b830d7e954bf6293cdfd8bd25ccf511ea
 size 34134464

runs/Jan13_17-07-07_e7d85d5b8601/events.out.tfevents.1736788028.e7d85d5b8601.21.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18663f1d9f565e8a75cae0b283018a6067b20819c3b9fda4b3b5ee1a8a2517bb
+size 7566

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b266e8526ff0f51e736a7e149fad82bfcbabdb104d4ead74c30f1bbe4de68cc4
-size 5240
+oid sha256:9de4a5cc4f99fbba88d135806133d238a8045c0eca2487bb591f056acd9a50b5
+size 5176