Training in progress, step 500

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "all",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "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": [
+    "v_lin",
+    "q_lin"
+  ],
+  "task_type": "QUESTION_ANS"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1734b65cea0a2268164b19cb490b2d514d8b0bbee1bf2c103f453f4f09c766
+size 1403408

runs/Jan09_15-27-10_pjt20230003-aer2024010004-dp-6f7b5c9687-mrddk/events.out.tfevents.1704781632.pjt20230003-aer2024010004-dp-6f7b5c9687-mrddk.2426.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf80b82bea84d8372683a82314048a63afdf61e3355004b242c7e5f4cee67ca
-size 4654
+oid sha256:2b499a4aef668bef5800f8b13b43b06690e4368c8956154cf3ce82572c0f70cf
+size 5550

runs/Jan09_16-37-00_pjt20230003-aer2024010004-dp-6f7b5c9687-mrddk/events.out.tfevents.1704785821.pjt20230003-aer2024010004-dp-6f7b5c9687-mrddk.2426.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b82bfb9f92f618d525e2134b7fcdada41e4a286a2e2ed746ff14327163e0788
+size 4654

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 384,
-    "strategy": "OnlySecond",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 384
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -45,11 +45,18 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 384,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6559088ac296cc521b436ca5d836e7c79c2deb6cab249067a2a2f44c956249cd
+oid sha256:b317972c14c1d2c07670060350ce9fdbb90686009c2cc6f3784849f304f9fa6b
 size 4283