Upload folder using huggingface_hub
Browse files- best_model/config.json +52 -0
- best_model/eval_results.txt +4 -0
- best_model/model.safetensors +3 -0
- best_model/model_args.json +1 -0
- best_model/optimizer.pt +3 -0
- best_model/scheduler.pt +3 -0
- best_model/sentencepiece.bpe.model +3 -0
- best_model/special_tokens_map.json +15 -0
- best_model/tokenizer_config.json +56 -0
- best_model/training_args.bin +3 -0
- checkpoint-20390-epoch-5/config.json +52 -0
- checkpoint-20390-epoch-5/eval_results.txt +4 -0
- checkpoint-20390-epoch-5/model.safetensors +3 -0
- checkpoint-20390-epoch-5/model_args.json +1 -0
- checkpoint-20390-epoch-5/optimizer.pt +3 -0
- checkpoint-20390-epoch-5/scheduler.pt +3 -0
- checkpoint-20390-epoch-5/sentencepiece.bpe.model +3 -0
- checkpoint-20390-epoch-5/special_tokens_map.json +15 -0
- checkpoint-20390-epoch-5/tokenizer_config.json +56 -0
- checkpoint-20390-epoch-5/training_args.bin +3 -0
- config.json +52 -0
- eval_results.txt +4 -0
- model.safetensors +3 -0
- model_args.json +1 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- training_progress_scores.csv +26 -0
best_model/config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/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 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 4096,
|
27 |
+
"label2id": {
|
28 |
+
"LABEL_0": 0,
|
29 |
+
"LABEL_1": 1,
|
30 |
+
"LABEL_2": 2,
|
31 |
+
"LABEL_3": 3,
|
32 |
+
"LABEL_4": 4,
|
33 |
+
"LABEL_5": 5,
|
34 |
+
"LABEL_6": 6,
|
35 |
+
"LABEL_7": 7,
|
36 |
+
"LABEL_8": 8,
|
37 |
+
"LABEL_9": 9
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"max_position_embeddings": 514,
|
41 |
+
"model_type": "xlm-roberta",
|
42 |
+
"num_attention_heads": 16,
|
43 |
+
"num_hidden_layers": 24,
|
44 |
+
"output_past": true,
|
45 |
+
"pad_token_id": 1,
|
46 |
+
"position_embedding_type": "absolute",
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.35.2",
|
49 |
+
"type_vocab_size": 1,
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 250002
|
52 |
+
}
|
best_model/eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.3116283849013009
|
2 |
+
macro_f1 = 0.8819395511428582
|
3 |
+
mcc = 0.8882957443605236
|
4 |
+
weighted_f1 = 0.8984244949202081
|
best_model/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1f9a3c07fc5c7460206d4012284a1d05d5e4d203b6b50b254e5e63a3f45547d
|
3 |
+
size 2243850072
|
best_model/model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adam_epsilon": 1e-08, "best_model_dir": "outputs/xlm-roberta-large/best_model", "cache_dir": "cache_dir/xlm-roberta-large", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "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, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 16, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 1000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 1000, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "FacebookAI/xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/xlm-roberta-large", "overwrite_output_dir": true, "process_count": 78, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "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_recent_only": true, "save_steps": 1000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": false, "wandb_kwargs": {}, "wandb_project": "NSINa_media_identification", "warmup_ratio": 0.06, "warmup_steps": 1224, "weight_decay": 0.0, "model_class": "LCPModel", "labels_list": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9], "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, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}
|
best_model/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4552f2187671f496687cd4e317d42718cdc2e1fdc48814e839f874006b71d03
|
3 |
+
size 4479437242
|
best_model/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d37e3e29c08b2fcf1df39edd5c11fe8464071f8224bccf8b4de7702a75b42b3
|
3 |
+
size 1064
|
best_model/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
best_model/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
best_model/tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_lower_case": false,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_token": "<pad>",
|
52 |
+
"sep_token": "</s>",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
55 |
+
"unk_token": "<unk>"
|
56 |
+
}
|
best_model/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d6091517ced2275432c9399627e5674dab8903ccd59f5c927bd70517ca145f3
|
3 |
+
size 3576
|
checkpoint-20390-epoch-5/config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/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 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 4096,
|
27 |
+
"label2id": {
|
28 |
+
"LABEL_0": 0,
|
29 |
+
"LABEL_1": 1,
|
30 |
+
"LABEL_2": 2,
|
31 |
+
"LABEL_3": 3,
|
32 |
+
"LABEL_4": 4,
|
33 |
+
"LABEL_5": 5,
|
34 |
+
"LABEL_6": 6,
|
35 |
+
"LABEL_7": 7,
|
36 |
+
"LABEL_8": 8,
|
37 |
+
"LABEL_9": 9
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"max_position_embeddings": 514,
|
41 |
+
"model_type": "xlm-roberta",
|
42 |
+
"num_attention_heads": 16,
|
43 |
+
"num_hidden_layers": 24,
|
44 |
+
"output_past": true,
|
45 |
+
"pad_token_id": 1,
|
46 |
+
"position_embedding_type": "absolute",
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.35.2",
|
49 |
+
"type_vocab_size": 1,
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 250002
|
52 |
+
}
|
checkpoint-20390-epoch-5/eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.4406218791158977
|
2 |
+
macro_f1 = 0.9093819732038056
|
3 |
+
mcc = 0.9118244744956736
|
4 |
+
weighted_f1 = 0.9211243453014698
|
checkpoint-20390-epoch-5/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a5e18bc93614db983bdca3dc31092522fa7d22c1b479549b06e1ee12d659fd2
|
3 |
+
size 2243850072
|
checkpoint-20390-epoch-5/model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adam_epsilon": 1e-08, "best_model_dir": "outputs/xlm-roberta-large/best_model", "cache_dir": "cache_dir/xlm-roberta-large", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "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, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 16, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 1000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 1000, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "FacebookAI/xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/xlm-roberta-large", "overwrite_output_dir": true, "process_count": 78, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "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_recent_only": true, "save_steps": 1000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": false, "wandb_kwargs": {}, "wandb_project": "NSINa_media_identification", "warmup_ratio": 0.06, "warmup_steps": 1224, "weight_decay": 0.0, "model_class": "LCPModel", "labels_list": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9], "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, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}
|
checkpoint-20390-epoch-5/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b534712125e2c15f0f8a8fb99f281518a312e61e23a30839a5f4a516547f5e4d
|
3 |
+
size 4479437242
|
checkpoint-20390-epoch-5/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1310a09af2057ac934eeffcf08c4a346cb69134b7eca5d1c53c6eed2967cbb59
|
3 |
+
size 1064
|
checkpoint-20390-epoch-5/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
checkpoint-20390-epoch-5/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
checkpoint-20390-epoch-5/tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_lower_case": false,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_token": "<pad>",
|
52 |
+
"sep_token": "</s>",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
55 |
+
"unk_token": "<unk>"
|
56 |
+
}
|
checkpoint-20390-epoch-5/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d6091517ced2275432c9399627e5674dab8903ccd59f5c927bd70517ca145f3
|
3 |
+
size 3576
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/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 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 4096,
|
27 |
+
"label2id": {
|
28 |
+
"LABEL_0": 0,
|
29 |
+
"LABEL_1": 1,
|
30 |
+
"LABEL_2": 2,
|
31 |
+
"LABEL_3": 3,
|
32 |
+
"LABEL_4": 4,
|
33 |
+
"LABEL_5": 5,
|
34 |
+
"LABEL_6": 6,
|
35 |
+
"LABEL_7": 7,
|
36 |
+
"LABEL_8": 8,
|
37 |
+
"LABEL_9": 9
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"max_position_embeddings": 514,
|
41 |
+
"model_type": "xlm-roberta",
|
42 |
+
"num_attention_heads": 16,
|
43 |
+
"num_hidden_layers": 24,
|
44 |
+
"output_past": true,
|
45 |
+
"pad_token_id": 1,
|
46 |
+
"position_embedding_type": "absolute",
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.35.2",
|
49 |
+
"type_vocab_size": 1,
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 250002
|
52 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.4406218791158977
|
2 |
+
macro_f1 = 0.9093819732038056
|
3 |
+
mcc = 0.9118244744956736
|
4 |
+
weighted_f1 = 0.9211243453014698
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a5e18bc93614db983bdca3dc31092522fa7d22c1b479549b06e1ee12d659fd2
|
3 |
+
size 2243850072
|
model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adam_epsilon": 1e-08, "best_model_dir": "outputs/xlm-roberta-large/best_model", "cache_dir": "cache_dir/xlm-roberta-large", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "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, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 16, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 1000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 1000, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "FacebookAI/xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/xlm-roberta-large", "overwrite_output_dir": true, "process_count": 78, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "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_recent_only": true, "save_steps": 1000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": false, "wandb_kwargs": {}, "wandb_project": "NSINa_media_identification", "warmup_ratio": 0.06, "warmup_steps": 1224, "weight_decay": 0.0, "model_class": "LCPModel", "labels_list": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9], "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, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_lower_case": false,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_token": "<pad>",
|
52 |
+
"sep_token": "</s>",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
55 |
+
"unk_token": "<unk>"
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d6091517ced2275432c9399627e5674dab8903ccd59f5c927bd70517ca145f3
|
3 |
+
size 3576
|
training_progress_scores.csv
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
global_step,mcc,train_loss,eval_loss,macro_f1,weighted_f1
|
2 |
+
1000,0.70202866019365,0.5288581848144531,0.7731002705737883,0.6646029722152949,0.7160442899878311
|
3 |
+
2000,0.8041412106587158,0.7350910902023315,0.5390888560185874,0.8009142892620906,0.8211270186694003
|
4 |
+
3000,0.8281531450421843,0.31380409002304077,0.4537427812026986,0.8186810388834017,0.843444341986931
|
5 |
+
4000,0.8501295251370721,0.362399160861969,0.3925851351101493,0.8433429002314152,0.8637604879998529
|
6 |
+
4078,0.8536454188018654,0.5993945598602295,0.3868468842973793,0.8554306500990165,0.8702307942644583
|
7 |
+
5000,0.8668051791919955,0.3673258423805237,0.37095894982898814,0.8657491940665422,0.8817709620052986
|
8 |
+
6000,0.8817328087215155,0.4679940938949585,0.3281760380197202,0.8747517748612342,0.8928429796574093
|
9 |
+
7000,0.8769075766334556,0.38791072368621826,0.35076982601820633,0.8759566155841148,0.8903763928174311
|
10 |
+
8000,0.8851779895305381,0.5748215913772583,0.31700565652831536,0.8836298666683333,0.897811803459356
|
11 |
+
8156,0.8882957443605236,0.08368898928165436,0.3116283849013009,0.8819395511428582,0.8984244949202081
|
12 |
+
9000,0.8963009900476255,0.07200937718153,0.32576664962235524,0.8962390784094005,0.9076426231593567
|
13 |
+
10000,0.8941187933147122,0.06811196357011795,0.35348847646282633,0.8881981835994143,0.9044111506388602
|
14 |
+
11000,0.8895124933977181,0.5387511849403381,0.3753478612734358,0.8868588750973097,0.9002950184893914
|
15 |
+
12000,0.9047263158028542,0.052444592118263245,0.3248993296028496,0.9024447441702593,0.9144072414420601
|
16 |
+
12234,0.8957577706319483,0.6554075479507446,0.33835022005412546,0.8954117224331384,0.907133608120228
|
17 |
+
13000,0.9022138580415664,0.31464099884033203,0.38222401283911145,0.8995964632123,0.9122009882170705
|
18 |
+
14000,0.9040636874317257,0.02189192920923233,0.4062430127339216,0.9014494001158333,0.9145963729215517
|
19 |
+
15000,0.9100643927198473,0.00011967867612838745,0.3897311443602461,0.9076109607738294,0.9197107860256006
|
20 |
+
16000,0.9075432658399867,0.0009182021021842957,0.41067392702341604,0.9041214963716329,0.9172746774717827
|
21 |
+
16312,0.9116893387306052,0.0030858884565532207,0.4037198473572206,0.909400389745816,0.921004988571814
|
22 |
+
17000,0.9102959943884493,0.003333635628223419,0.43118207606318765,0.90786008801979,0.9196217297670309
|
23 |
+
18000,0.910777540842592,3.7185847759246826e-05,0.44445651700711986,0.9073150741360376,0.9203436148939076
|
24 |
+
19000,0.9119664977816164,0.0002948567271232605,0.4435708787341475,0.9093490141880596,0.92110977902904
|
25 |
+
20000,0.9124544152934944,9.75877046585083e-05,0.44164901861863515,0.9103673390742717,0.9217533749334789
|
26 |
+
20390,0.9118244744956736,0.0005423013935796916,0.4406218791158977,0.9093819732038056,0.9211243453014698
|