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: 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
-- Datasets 3.2.0
-- Tokenizers 0.19.1
+- Transformers 4.46.3
+- Pytorch 2.4.0
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -24,8 +24,8 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "o_proj",
     "v_proj",
+    "o_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afef72b72afc5354303e27cf7e95dbad8f810252e65efc312b98d71041d991a9
+oid sha256:9a0834b9e719b37ac8bff5f64d662e35aa2da35d7dfb2cb8a16e2e7d73ff2c26
 size 34134464

runs/Jan10_01-58-56_384bedf9702e/events.out.tfevents.1736474337.384bedf9702e.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3ea6032380286d354c54044848b7fdfa4cf80d90890c33395eca6b96a1b022
+size 7706

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5d9a6efb8a5501b5ef31c7e1843680f6643f6a146aadf6c7195ab5d18eb253
-size 5176
+oid sha256:3373e538f6d2b1bd17825aa39f4c2e616649fe72227a0b0da8f0c778261f95fa
+size 5240