Uploading model files

README.md

@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 75
+- num_epochs: 45
 
 ### Training results
 
@@ -56,7 +56,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.12.0
-- Transformers 4.48.3
+- Transformers 4.49.0
 - Pytorch 2.6.0+cu124
-- Datasets 3.2.0
+- Datasets 3.3.2
 - Tokenizers 0.21.0

adapter_config.json

@@ -10,20 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 64,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_up_proj",
     "qkv_proj",
-    "down_proj"
+    "gate_up_proj",
+    "down_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a815bb53bf38a9f05063bec0cc11541d8a1fc1b452d953fbf7fe8ece151ef8
-size 201361312
+oid sha256:f4bea0ff163cf7ea9957d1b7bba2349aa023a0f4ec73065c64b0273cb92068aa
+size 50365768

tokenizer_config.json

@@ -125,7 +125,7 @@
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "legacy": false,
-  "model_max_length": 8192,
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce19553498dc9c6160cbe0c3b990b2c9b8613949c39358da086dc9b4812c64d
+oid sha256:d0ce7d00ec896115415e7e2005f57ca498d7ddbf4c99b9c490c3d9b7599bf238
 size 5688