Upload 15 files

Distinguisher_PTCV/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/root/autodl-tmp/LLM-Research",
+  "base_model_name_or_path": "/root/autodl-tmp",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -14,15 +14,18 @@
   "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
   "peft_type": "LORA",
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "qkv_proj",
-    "o_proj",
     "gate_up_proj",
+    "o_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

Distinguisher_PTCV/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa4fbe096f3e9ab9a1ca8863f6e5df23c69e830e1e5b1423981434916fa30548
-size 111454040
+oid sha256:c326209645cf82455cd23e251067e8e8d9ac0bfe61771c65100ccab6f7c929ce
+size 1424796984

Distinguisher_RC/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: /root/autodl-tmp/LLM-Research
+base_model: /root/autodl-tmp
 library_name: peft
 license: other
 tags:
@@ -7,16 +7,16 @@ tags:
 - lora
 - generated_from_trainer
 model-index:
-- name: sft
+- name: task2
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# sft
+# task2
 
-This model is a fine-tuned version of [/root/autodl-tmp/LLM-Research](https://huggingface.co//root/autodl-tmp/LLM-Research) on the bighuman, the biggpt, the oodgpt3train120209, the oodgpt3train40209, the oodgpt3train30209, the oodreal0209, the openllmgpt0209 and the openllmhuman0209 datasets.
+This model is a fine-tuned version of [/root/autodl-tmp](https://huggingface.co//root/autodl-tmp) on the task2_hwt_no and the task2_lgt_yes datasets.
 
 ## Model description
 
@@ -39,11 +39,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 3
 - eval_batch_size: 8
 - seed: 42
-- distributed_type: multi-GPU
-- num_devices: 6
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 144
-- total_eval_batch_size: 48
+- total_train_batch_size: 24
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1

Distinguisher_RC/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/root/autodl-tmp/LLM-Research",
+  "base_model_name_or_path": "/root/autodl-tmp",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "qkv_proj",
     "o_proj",
     "gate_up_proj",
-    "qkv_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

Distinguisher_RC/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874dbbb3855f941ed21ecc0040491a8a80ee170c564e2cd1e00e0db47c00649b
+oid sha256:1d720d46e798bff1f3304b609bf6172ce09a60b3471747992aafe6f6fc1917c6
 size 111454040

Distinguisher_RC/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b360b992d8d24e161927e9679d955ca5f1abe1505a8a6c0e7fb266de3ef76c15
+oid sha256:47a548c78559e83e372536564473a8223dbf5d326d78fee90db0bd570d0f0967
 size 5432