Upload folder using huggingface_hub
Browse files- added_tokens.json +1 -0
- config.json +28 -0
- eval_results.txt +20 -0
- model_args.json +1 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- test_eval.txt +43 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<e>": 250002, "</e>": 250003}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.16.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250004
|
28 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
accuracy = 0.9795918367346939
|
2 |
+
cls_report = precision recall f1-score support
|
3 |
+
|
4 |
+
0.0 1.0000 0.9574 0.9783 47
|
5 |
+
1.0 0.9623 1.0000 0.9808 51
|
6 |
+
|
7 |
+
accuracy 0.9796 98
|
8 |
+
macro avg 0.9811 0.9787 0.9795 98
|
9 |
+
weighted avg 0.9804 0.9796 0.9796 98
|
10 |
+
|
11 |
+
eval_loss = 0.08869283126394013
|
12 |
+
fn = 0
|
13 |
+
fp = 2
|
14 |
+
macro_f1 = 0.9795150501672241
|
15 |
+
mcc = 0.9598524575500934
|
16 |
+
tn = 45
|
17 |
+
tp = 51
|
18 |
+
weighted_f1 = 0.979566241212204
|
19 |
+
weighted_p = 0.9811320754716981
|
20 |
+
weighted_r = 0.9787234042553192
|
model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adam_epsilon": 1e-08, "begin_tag": "<e>", "best_model_dir": "best_model/zh_zh", "cache_dir": "temp/cache_dir/", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 70, "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": 10, "encoding": null, "end_tag": "</e>", "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": false, "evaluate_during_training_steps": 20, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 20, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 120, "model_name": "xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "num_train_epochs": 5, "output_dir": "temp/outputs/", "overwrite_output_dir": true, "process_count": 70, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 20, "save_recent_only": true, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": false, "wandb_kwargs": {"group": "zh_zh_xlm-roberta-large_CLS-ET_concat", "job_type": "2"}, "wandb_project": "TransWiC-groups", "warmup_ratio": 0.1, "warmup_steps": 56, "weight_decay": 0, "skip_special_tokens": true, "model_class": "ClassificationModel", "labels_list": [0, 1], "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": false, "stride": 0.8, "tie_value": 1, "tagging": true, "strategy": "CLS-ET", "special_tags": ["<s>", "</e>"], "merge_n": 3, "merge_type": "concat"}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffad181c528995d970e1dbce2cc0e7360dcaaba46565681f2c73f12c63226124
|
3 |
+
size 4546546317
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00aca1d13cef7257784f055a9fe576fe677eaca1c4613e96cbb94f5c07c9fb47
|
3 |
+
size 2277523261
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9d9eda7daefe95f816787315af528b50218205e1c1cb6e97e64a79d83f6f38b
|
3 |
+
size 627
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
test_eval.txt
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Default classification report:
|
2 |
+
precision recall f1-score support
|
3 |
+
|
4 |
+
F 0.5607 0.5540 0.5573 500
|
5 |
+
T 0.5593 0.5660 0.5626 500
|
6 |
+
|
7 |
+
accuracy 0.5600 1000
|
8 |
+
macro avg 0.5600 0.5600 0.5600 1000
|
9 |
+
weighted avg 0.5600 0.5600 0.5600 1000
|
10 |
+
|
11 |
+
|
12 |
+
ADJ
|
13 |
+
Accuracy = 0.5806451612903226
|
14 |
+
Weighted Recall = 0.5806451612903226
|
15 |
+
Weighted Precision = 0.6104838709677418
|
16 |
+
Weighted F1 = 0.5859311466522094
|
17 |
+
Macro Recall = 0.5888157894736843
|
18 |
+
Macro Precision = 0.584375
|
19 |
+
Macro F1 = 0.5766806722689076
|
20 |
+
ADV
|
21 |
+
Accuracy = 0.6
|
22 |
+
Weighted Recall = 0.6
|
23 |
+
Weighted Precision = 0.78
|
24 |
+
Weighted F1 = 0.6395604395604395
|
25 |
+
Macro Recall = 0.65625
|
26 |
+
Macro Precision = 0.6
|
27 |
+
Macro F1 = 0.5604395604395604
|
28 |
+
NOUN
|
29 |
+
Accuracy = 0.5487364620938628
|
30 |
+
Weighted Recall = 0.5487364620938628
|
31 |
+
Weighted Precision = 0.5512495487841089
|
32 |
+
Weighted F1 = 0.5473930125065729
|
33 |
+
Macro Recall = 0.5501825769431403
|
34 |
+
Macro Precision = 0.5507866117622215
|
35 |
+
Macro F1 = 0.5478879676176797
|
36 |
+
VERB
|
37 |
+
Accuracy = 0.5714285714285714
|
38 |
+
Weighted Recall = 0.5714285714285714
|
39 |
+
Weighted Precision = 0.5707175336645657
|
40 |
+
Weighted F1 = 0.5696699422040619
|
41 |
+
Macro Recall = 0.5693302707930368
|
42 |
+
Macro Precision = 0.5704805210765638
|
43 |
+
Macro F1 = 0.5684975227210554
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/hh2/.cache/huggingface/transformers/7766c86e10505ed9b39af34e456480399bf06e35b36b8f2b917460a2dbe94e59.a984cf52fc87644bd4a2165f1e07e0ac880272c1e82d648b4674907056912bd7", "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:412dd7561ac8f83ac269e795eab903931a88c63dd7af30e2f5a84c15a83a3f5e
|
3 |
+
size 2875
|