Training in progress, step 500

adapter_config.json

@@ -1,17 +1,27 @@
 {
+  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "bert-base-cased",
-  "encoder_dropout": 0.0,
-  "encoder_hidden_size": 128,
-  "encoder_num_layers": 2,
-  "encoder_reparameterization_type": "MLP",
+  "bias": "all",
+  "fan_in_fan_out": false,
   "inference_mode": true,
-  "num_attention_heads": 12,
-  "num_layers": 12,
-  "num_transformer_submodules": 1,
-  "num_virtual_tokens": 20,
-  "peft_type": "P_TUNING",
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
   "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
   "task_type": "QUESTION_ANS",
-  "token_dim": 768
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3beea8687cb989945a190036d31b11a8363c82fb9e2bfbe171773711d4a7ca
-size 67880
+oid sha256:6fa682901a95b7a45d5786fd59151fc63030e0826adc633faa7c8ac47a8001a4
+size 2793840

runs/Feb14_18-10-21_pjt20230003-aer2024010004-dp-5d9c8bc8b6-8b5n8/events.out.tfevents.1707901822.pjt20230003-aer2024010004-dp-5d9c8bc8b6-8b5n8.3422.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:541d7ab63af87121de309ae467f0b77c6ce080f63e9372ccf3fa99b034df1b7c
+size 4714

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d529ceebfb68641d9c046d2e37d0dc64758c44d546119f541618309d3ad9b4b
+oid sha256:0a766ab644c27b2c02584808356c1d63fe59bcab51abdfed98abedffabbea258
 size 4283