Upload 9 files
Browse files- config.json +62 -0
- model_args.json +1 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6",
|
| 20 |
+
"7": "LABEL_7",
|
| 21 |
+
"8": "LABEL_8",
|
| 22 |
+
"9": "LABEL_9",
|
| 23 |
+
"10": "LABEL_10",
|
| 24 |
+
"11": "LABEL_11",
|
| 25 |
+
"12": "LABEL_12",
|
| 26 |
+
"13": "LABEL_13",
|
| 27 |
+
"14": "LABEL_14",
|
| 28 |
+
"15": "LABEL_15",
|
| 29 |
+
"16": "LABEL_16",
|
| 30 |
+
"17": "LABEL_17"
|
| 31 |
+
},
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"intermediate_size": 4096,
|
| 34 |
+
"label2id": {
|
| 35 |
+
"LABEL_0": 0,
|
| 36 |
+
"LABEL_1": 1,
|
| 37 |
+
"LABEL_10": 10,
|
| 38 |
+
"LABEL_11": 11,
|
| 39 |
+
"LABEL_12": 12,
|
| 40 |
+
"LABEL_13": 13,
|
| 41 |
+
"LABEL_14": 14,
|
| 42 |
+
"LABEL_15": 15,
|
| 43 |
+
"LABEL_16": 16,
|
| 44 |
+
"LABEL_17": 17,
|
| 45 |
+
"LABEL_2": 2,
|
| 46 |
+
"LABEL_3": 3,
|
| 47 |
+
"LABEL_4": 4,
|
| 48 |
+
"LABEL_5": 5,
|
| 49 |
+
"LABEL_6": 6,
|
| 50 |
+
"LABEL_7": 7,
|
| 51 |
+
"LABEL_8": 8,
|
| 52 |
+
"LABEL_9": 9
|
| 53 |
+
},
|
| 54 |
+
"layer_norm_eps": 1e-05,
|
| 55 |
+
"max_position_embeddings": 514,
|
| 56 |
+
"model_type": "roberta",
|
| 57 |
+
"num_attention_heads": 16,
|
| 58 |
+
"num_hidden_layers": 24,
|
| 59 |
+
"pad_token_id": 1,
|
| 60 |
+
"type_vocab_size": 1,
|
| 61 |
+
"vocab_size": 50265
|
| 62 |
+
}
|
model_args.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"adam_epsilon": 1e-08, "best_model_dir": "CARDS_1e-5_m4/best_model/", "cache_dir": "cache_dir/", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 94, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": -1, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "roberta-large", "model_type": "roberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "num_train_epochs": 12, "output_dir": "CARDS_1e-5_m4/", "overwrite_output_dir": false, "process_count": 94, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 6, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 2814, "weight_decay": 0, "model_class": "ClassificationModel", "labels_list": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": true, "stride": 0.6, "tie_value": 1}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b1148c49e1d470551d43d32d305ea132a9a011a92b7572651afa9e79d871f36
|
| 3 |
+
size 2843272401
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4a36dc95413437c31065aed0d5ff59cb98afeb417ace836b397bd95501f179d
|
| 3 |
+
size 1425885467
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:967aa5a68d8ef81ef65494903a5f1b3f4cec9ba32d7304feac0db5abc8838515
|
| 3 |
+
size 559
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "model_max_length": 512}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b131cac9ac3743c4527fb0f659b01d0869ff8db157cec190748a6d8843cc9df0
|
| 3 |
+
size 2479
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|