Upload 6 files

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2db5656113ea547493d25f0a6a6951fa0c9f8165d60ad30707ecd409c04ed7e
+size 425649026

tokenizer_config.json

@@ -4,7 +4,7 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

train_v1b_0818_1117_seed_1.log

@@ -0,0 +1,18 @@
+11:17:49 {'seed': 1, 'ver': 'v1b', 'use_log': True, 'use_tqdm': True, 'debug': False, 'tokenizer': BertTokenizerFast(name_or_path='yiyanghkust/finbert-tone', vocab_size=30873, model_max_length=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'unk_token': '[UNK]', 'sep_token': '[SEP]', 'pad_token': '[PAD]', 'cls_token': '[CLS]', 'mask_token': '[MASK]'}, clean_up_tokenization_spaces=True), 'config': <custom_config.LongBERTConfig object at 0x7f4e984f26d0>, 'max_len': 50000, 'train_one_part': False, 'gradient_accumulation_steps': 2, 'apex': True, 'device': device(type='cuda', index=1), 'nepochs': 10, 'batch_size': 2, 'num_workers': 128, 'lr': 2e-05, 'weight_decay': 0.01, 'encoder_lr': 2e-05, 'decoder_lr': 0.001, 'min_lr': 1e-06, 'eps': 1e-06, 'betas': (0.9, 0.999), 'scheduler_type': 'cosine', 'num_cycles': 0.5, 'num_warmup_steps': 0.0, 'train_data_dir': 'data/train', 'valid_data_dir': 'data/valid', 'test_data_dir': '.', 'output_dir': 'model/v1/b'}
+11:17:49 Preparing training materials...
+11:17:49 Preparing the model...
+11:17:50 loading weights file pytorch_model.bin from cache at /home/tphan/.cache/huggingface/hub/models--yiyanghkust--finbert-tone/snapshots/4921590d3c0c3832c0efea24c8381ce0bda7844b/pytorch_model.bin
+11:17:51 Some weights of the model checkpoint at yiyanghkust/finbert-tone were not used when initializing BertModel: ['classifier.bias', 'classifier.weight']
+- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+11:17:51 All the weights of BertModel were initialized from the model checkpoint at yiyanghkust/finbert-tone.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use BertModel for predictions without further training.
+11:17:53 Preparing the dataloaders...
+06:22:24 Epoch: [1] - Train/Valid Loss: 4.8630/4.4170
+06:22:24 Saving the model to model/v1/b
+01:29:20 Epoch: [2] - Train/Valid Loss: 4.2652/4.0695
+01:29:20 Saving the model to model/v1/b
+20:33:57 Epoch: [3] - Train/Valid Loss: 4.0235/3.9188
+20:33:57 Saving the model to model/v1/b
+15:40:47 Epoch: [4] - Train/Valid Loss: 3.8973/3.8104
+15:40:47 Saving the model to model/v1/b