tharindu commited on
Commit
284c6bd
1 Parent(s): 94c43ed

Upload folder using huggingface_hub

Browse files
best_model/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/xlm-roberta-base",
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": 768,
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": 3072,
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": 12,
43
+ "num_hidden_layers": 12,
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 = 0.34419548488529766
2
+ macro_f1 = 0.8893845252110735
3
+ mcc = 0.8906260997529534
4
+ weighted_f1 = 0.9015008165061491
best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e97d5cb785ed758380b0b910486094feafbda234adcbd9ef2688ccfed0a03a
3
+ size 1114592184
best_model/model_args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"adam_epsilon": 1e-08, "best_model_dir": "outputs/xlm-roberta-base/best_model", "cache_dir": "cache_dir/xlm-roberta-base", "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-base", "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-base", "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 sha256:9e09c544a4f601eed6d066cb234974b06fb552bcc68fcd1f9ae1caa15386d940
3
+ size 2224529018
best_model/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f596cd69be969d8862756bf33ebe49192732adbbf4bfe524a72fc05526d4a10a
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 sha256:133ce2746ffc9a810c2e07dd023a72facf3703cb9fccce781241e7de1bbc37d6
3
+ size 3576
checkpoint-20390-epoch-5/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/xlm-roberta-base",
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": 768,
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": 3072,
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": 12,
43
+ "num_hidden_layers": 12,
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 = 0.47827733831586816
2
+ macro_f1 = 0.8993844550871992
3
+ mcc = 0.9010171513990157
4
+ weighted_f1 = 0.9113673534068617
checkpoint-20390-epoch-5/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89724089fef96078568cff945f7ba6de29ca4503da204601ce3a9398995cf44c
3
+ size 1114592184
checkpoint-20390-epoch-5/model_args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"adam_epsilon": 1e-08, "best_model_dir": "outputs/xlm-roberta-base/best_model", "cache_dir": "cache_dir/xlm-roberta-base", "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-base", "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-base", "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:e8e2cd0685a9bbb91c55d7b89a069f97851e290412c89024c8cf024e66a7fea6
3
+ size 2224529018
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 sha256:133ce2746ffc9a810c2e07dd023a72facf3703cb9fccce781241e7de1bbc37d6
3
+ size 3576
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/xlm-roberta-base",
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": 768,
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": 3072,
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": 12,
43
+ "num_hidden_layers": 12,
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 = 0.47827733831586816
2
+ macro_f1 = 0.8993844550871992
3
+ mcc = 0.9010171513990157
4
+ weighted_f1 = 0.9113673534068617
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89724089fef96078568cff945f7ba6de29ca4503da204601ce3a9398995cf44c
3
+ size 1114592184
model_args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"adam_epsilon": 1e-08, "best_model_dir": "outputs/xlm-roberta-base/best_model", "cache_dir": "cache_dir/xlm-roberta-base", "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-base", "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-base", "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 sha256:133ce2746ffc9a810c2e07dd023a72facf3703cb9fccce781241e7de1bbc37d6
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
+ 1000,0.5961726330629302,0.68450927734375,1.0888271289775024,0.5529151843672893,0.6022760219776148
3
+ 2000,0.7990190954879531,0.2014479637145996,0.54807936567567,0.7895351413646028,0.8162247027205949
4
+ 3000,0.8243457777864468,0.9415254592895508,0.47057280298896825,0.7987878220425741,0.8346932016606232
5
+ 4000,0.8501703173428728,0.5669331550598145,0.40353777019988074,0.8487732813235318,0.8651455120660406
6
+ 4078,0.8406526558230761,0.3520079255104065,0.443522126138998,0.8428222550179576,0.8580532465373002
7
+ 5000,0.8683212142286749,0.4393327236175537,0.39642832799104866,0.8675558125669951,0.881589726371757
8
+ 6000,0.863278703991842,0.49232935905456543,0.3860074796340539,0.8551242814204034,0.8755079458099895
9
+ 7000,0.8573101202246142,0.49276870489120483,0.39115879753612737,0.853423685977981,0.8712550503987964
10
+ 8000,0.8770425496154847,0.04732245206832886,0.36186922843760855,0.8744036716287681,0.889677420574137
11
+ 8156,0.8724037570264507,0.37274205684661865,0.35551749215777223,0.8691906192264793,0.8849197362198455
12
+ 9000,0.8802427482444172,0.2519146203994751,0.36651659681408416,0.8798463926107635,0.8922018926341976
13
+ 10000,0.8830692909896142,0.22778448462486267,0.386467460690616,0.8802051047040671,0.8952038475080859
14
+ 11000,0.8804607281822205,0.2828364670276642,0.40644653003646414,0.8775918680530637,0.8914381017139941
15
+ 12000,0.8906260997529534,0.8415406346321106,0.34419548488529766,0.8893845252110735,0.9015008165061491
16
+ 12234,0.8934091128527739,0.026129355654120445,0.36676401694178057,0.8923806429765497,0.9039598260857645
17
+ 13000,0.890415816568809,0.07343578338623047,0.40773928050559,0.8892525625792349,0.9015935895657434
18
+ 14000,0.8967065752482429,0.03535519540309906,0.4145004132737935,0.8946519736165234,0.9070621214112551
19
+ 15000,0.8990459642742856,0.0010558739304542542,0.4218260387885938,0.8971523916957075,0.9098267078963732
20
+ 16000,0.8994582949266786,0.009960673749446869,0.44293709048418745,0.8963738161926932,0.9095883039662259
21
+ 16312,0.9005930745109915,0.00049431505613029,0.4230956450137535,0.8990741225326915,0.9111398557645171
22
+ 17000,0.8952919467134315,0.002797521650791168,0.48256516200592864,0.893515617095658,0.9060118136733378
23
+ 18000,0.8996793018913178,0.02802237868309021,0.479371452991264,0.8977323596759392,0.9100777456525633
24
+ 19000,0.895392965720749,0.018474169075489044,0.4981402644501909,0.8929198830441998,0.9057318618798217
25
+ 20000,0.9004201655152326,0.0006030350923538208,0.48008853531881573,0.898197308219957,0.9107892617567935
26
+ 20390,0.9010171513990157,0.00026450707809999585,0.47827733831586816,0.8993844550871992,0.9113673534068617