lora-midm-7b-nsmc-understanding

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- training_steps: 300
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -8,8 +8,11 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 16,
   "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 8,
@@ -17,8 +20,8 @@
   "revision": null,
   "target_modules": [
     "c_attn",
-    "c_fc",
-    "c_proj"
+    "c_proj",
+    "c_fc"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b66383ed1f8d49f162b68e87c82d9bcc3392e096a94575639c6e066aef7487
+oid sha256:0eb12ce63d73cf4f2fe773a73c6052b92be17aef53c68bbdb4c7471e8e4a7bba
 size 67010784

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:474fa3089c1c5bd5d95917d8633bd175db5c4d50a81e173e04696a14232b0583
+oid sha256:3dd25a991cf6c7d5956de6bbd14c0423c1da7c6d1ffe423a8625e334575972de
 size 4664