Training in progress, step 10

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "chaoyi-wu/PMC_LLAMA_7B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad97e300b7291fc510547c93dfef18124d35201660770dbc90813de392da8736
+size 16794200

trainer_peft.log

@@ -0,0 +1,217 @@
+2024-05-29 18:45 - Cuda check
+2024-05-29 18:45 - True
+2024-05-29 18:45 - 1
+2024-05-29 18:45 - Configue Model and tokenizer
+2024-05-29 18:45 - Memory usage in   0.00 GB
+2024-05-29 18:45 - Dataset loaded successfully:
+ train-Jingmei/Pandemic_Wiki
+ test -Jingmei/Pandemic_WHO
+2024-05-29 18:46 - Tokenize data: DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 2152
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 8264
+    })
+})
+2024-05-29 18:49 - Split data into chunks:DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 24863
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 198964
+    })
+})
+2024-05-29 18:49 - Setup PEFT
+2024-05-29 18:49 - Setup optimizer
+2024-05-29 18:49 - Start training
+2024-05-29 18:57 - Cuda check
+2024-05-29 18:57 - True
+2024-05-29 18:57 - 1
+2024-05-29 18:57 - Configue Model and tokenizer
+2024-05-29 18:57 - Memory usage in   25.17 GB
+2024-05-29 18:57 - Dataset loaded successfully:
+ train-Jingmei/Pandemic_Wiki
+ test -Jingmei/Pandemic_WHO
+2024-05-29 18:57 - Tokenize data: DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 2152
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 8264
+    })
+})
+2024-05-29 18:57 - Split data into chunks:DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 24863
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 198964
+    })
+})
+2024-05-29 18:57 - Setup PEFT
+2024-05-29 18:57 - Setup optimizer
+2024-05-29 18:57 - Start training
+2024-05-29 19:04 - Cuda check
+2024-05-29 19:04 - True
+2024-05-29 19:04 - 1
+2024-05-29 19:04 - Configue Model and tokenizer
+2024-05-29 19:04 - Memory usage in   25.17 GB
+2024-05-29 19:04 - Dataset loaded successfully:
+ train-Jingmei/Pandemic_Wiki
+ test -Jingmei/Pandemic_WHO
+2024-05-29 19:04 - Tokenize data: DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 2152
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 8264
+    })
+})
+2024-05-29 19:04 - Split data into chunks:DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 24863
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 198964
+    })
+})
+2024-05-29 19:04 - Setup PEFT
+2024-05-29 19:04 - Setup optimizer
+2024-05-29 19:04 - Start training
+2024-05-29 19:10 - Cuda check
+2024-05-29 19:10 - True
+2024-05-29 19:10 - 1
+2024-05-29 19:10 - Configue Model and tokenizer
+2024-05-29 19:10 - Memory usage in   25.17 GB
+2024-05-29 19:10 - Dataset loaded successfully:
+ train-Jingmei/Pandemic_Wiki
+ test -Jingmei/Pandemic_WHO
+2024-05-29 19:10 - Tokenize data: DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 2152
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 8264
+    })
+})
+2024-05-29 19:10 - Split data into chunks:DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 24863
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 198964
+    })
+})
+2024-05-29 19:10 - Setup PEFT
+2024-05-29 19:10 - Setup optimizer
+2024-05-29 19:10 - Start training
+2024-05-29 19:16 - Cuda check
+2024-05-29 19:16 - True
+2024-05-29 19:16 - 1
+2024-05-29 19:16 - Configue Model and tokenizer
+2024-05-29 19:16 - Memory usage in   25.17 GB
+2024-05-29 19:16 - Dataset loaded successfully:
+ train-Jingmei/Pandemic_Wiki
+ test -Jingmei/Pandemic_WHO
+2024-05-29 19:16 - Tokenize data: DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 2152
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 8264
+    })
+})
+2024-05-29 19:16 - Split data into chunks:DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 24863
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 198964
+    })
+})
+2024-05-29 19:16 - Setup PEFT
+2024-05-29 19:16 - Setup optimizer
+2024-05-29 19:16 - Start training
+2024-05-29 19:22 - Cuda check
+2024-05-29 19:22 - True
+2024-05-29 19:22 - 1
+2024-05-29 19:22 - Configue Model and tokenizer
+2024-05-29 19:22 - Memory usage in   25.17 GB
+2024-05-29 19:22 - Dataset loaded successfully:
+ train-Jingmei/Pandemic_Wiki
+ test -Jingmei/Pandemic_WHO
+2024-05-29 19:22 - Tokenize data: DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 2152
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 8264
+    })
+})
+2024-05-29 19:22 - Split data into chunks:DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 24863
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 198964
+    })
+})
+2024-05-29 19:22 - Setup PEFT
+2024-05-29 19:22 - Setup optimizer
+2024-05-29 19:22 - Start training
+2024-05-29 19:29 - Cuda check
+2024-05-29 19:29 - True
+2024-05-29 19:29 - 1
+2024-05-29 19:29 - Configue Model and tokenizer
+2024-05-29 19:29 - Memory usage in   25.17 GB
+2024-05-29 19:29 - Dataset loaded successfully:
+ train-Jingmei/Pandemic_Wiki
+ test -Jingmei/Pandemic_WHO
+2024-05-29 19:29 - Tokenize data: DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 2152
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 8264
+    })
+})
+2024-05-29 19:29 - Split data into chunks:DatasetDict({
+    train: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 24863
+    })
+    test: Dataset({
+        features: ['input_ids', 'attention_mask'],
+        num_rows: 198964
+    })
+})
+2024-05-29 19:29 - Setup PEFT
+2024-05-29 19:29 - Setup optimizer
+2024-05-29 19:29 - Start training

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d57b2583d86e2ed6d84da0f503e8cc8b5ab9a9038e8eae344efc26164f159e6
+size 5176

transformed_cache/test_chunked_00000_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae2e9968e4f98dd4f16f89da1efc7aa266ab4d0d26b7f30b51e309c6f828c27
+size 62148672

transformed_cache/test_chunked_00001_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11db4c2496f57ecbc395ef6fcf09d9e00a87a226a605445f53a43b3e85022dc8
+size 59367216

transformed_cache/test_chunked_00002_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40e232ff015f3c9bd7b9a1e1e3027bd690b95110d8e7602d6b8b4a181e3b3bc
+size 68269120

transformed_cache/test_chunked_00003_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ade749ffe68b29e54cc4c5076e3d14f88a6ce323b5c578d71b5395017aa532
+size 80368176

transformed_cache/test_chunked_00004_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b933533de1fa4a3ab31ecd0a428a9bc09a5bc5a543c3f609300df5294af90db7
+size 55943760

transformed_cache/test_chunked_00005_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1794b5460b5b248bbe30abdcbcd5a9473c1f0301faa1c1f58dda59e64c4ad5
+size 62541568

transformed_cache/test_chunked_00006_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485d66f28cad901af230c63ce95c958968af004a3c647855c513f6a9ecd4cb98
+size 58971744

transformed_cache/test_chunked_00007_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb3d0575e477eb043fe5cfedd358c449c7b758a5299fade16672fe3402979fa
+size 63397008

transformed_cache/test_tokenized_00000_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f19e4e96ea46d5b1cb50a3d5f173d13cc65d5105bf59bc4287252fa1b6dd05e
+size 61957552

transformed_cache/test_tokenized_00001_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de30f634c4db0778fb02c6647561302c0e6d82d9edffb28241e2abc3ef74f87
+size 59187104

transformed_cache/test_tokenized_00002_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a96c44a43cf8d01a7f5567064c039c413d77b368e2b6ae86d1e440cdd5053650
+size 68057936

transformed_cache/test_tokenized_00003_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4daeadd552b3364911e35740457a497ee896c85c721da89603f7b0103af0ee
+size 80121008

transformed_cache/test_tokenized_00004_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f9aa02a689092fb09c4cce9d4560c0e9ac3560d7f5b2e3827bfd690a2689c7
+size 55773176

transformed_cache/test_tokenized_00005_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eeb72ac2d0ecb57de088b4f6558020a5946e833d28dfeabebad937c3c553190
+size 62349352

transformed_cache/test_tokenized_00006_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1175f22330a67782d122ddd79d40c6bac37cf81a99012f452b3549055eeecff
+size 58791688

transformed_cache/test_tokenized_00007_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2c05949063ade79e6e710254bda5068062d53d3862bb7a094eee3162833500
+size 63205208

transformed_cache/train_chunked_00000_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b95e6793aeafcaa2d4964868dc52637199ce2c6a47272fcec347c47d57eda89
+size 7184208

transformed_cache/train_chunked_00001_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2236d0790dfa94c4a687688ee379b2b34cc5b34e668809c6b658073909079b38
+size 8260512

transformed_cache/train_chunked_00002_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4471933f4dde7bdc2581ec4c18993149fd5020c2cc5b68db1ed54def6a73c925
+size 7898416

transformed_cache/train_chunked_00003_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81165c3d8c0ef0373f4cc00e15e3b38bf10bb4c203f31c26f83a6d7abb56dcd8
+size 8237392

transformed_cache/train_chunked_00004_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b919ee6dae99de6a36facd60126885a306d893e64da7408ca7ead656f4ce3e
+size 8342688

transformed_cache/train_chunked_00005_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b3ccabb6a5f30597e582f07e48480cb5210c3c483d230ebfca37d6c1fbd072
+size 8848576

transformed_cache/train_chunked_00006_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37de1908b28108464569ab1b34f8f8d8f3ddc1c604282f971acef60fb6d98621
+size 7538592

transformed_cache/train_chunked_00007_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403da53b850cd65cb3b6f1e9c41c35c44c0c9da4c8c7c84a7c96cfd0adb48648
+size 7551440

transformed_cache/train_tokenized_00000_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab46d354dc75989c187c176b231b957d40cf5fb6f1cbb7c900970ea9e3355e3b
+size 7164512

transformed_cache/train_tokenized_00001_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94da0daa98038663cb57dfe1608c8df4f923c2d4db39a030349bc7a25374be06
+size 8236248

transformed_cache/train_tokenized_00002_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f696795dee6c02fe594b04ac52f23c4d3b0d4f7daa66f42b9798a2abb1cf93
+size 7876672

transformed_cache/train_tokenized_00003_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d477a0a9b8ff7cf1da7281b895b11e05affe217d81f44fcfc68eab70ecf0b3e
+size 8214000

transformed_cache/train_tokenized_00004_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b30406de2a4fb0ae56a08aca3a7457d6d63aa0ac66a7b950c84cd4252de96ed
+size 8318008

transformed_cache/train_tokenized_00005_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c3e9c2abf180bda95e87458b6f610b45173b3eb4d7c10e37db10ee1b07cf64
+size 8823040

transformed_cache/train_tokenized_00006_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a714384172fed68834fc866a5a799ffe9cb301598b41d5433d24a74727fa15a4
+size 7516936

transformed_cache/train_tokenized_00007_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15c328603fef8a816eae22386f22485b37040adc7237397620e129656c9a565
+size 7529536