Upload folder using huggingface_hub
Browse files- .gitattributes +3 -0
- best_model/config.json +35 -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/special_tokens_map.json +15 -0
- best_model/tokenizer.json +3 -0
- best_model/tokenizer_config.json +54 -0
- best_model/training_args.bin +3 -0
- checkpoint-2000-epoch-5/config.json +35 -0
- checkpoint-2000-epoch-5/eval_results.txt +4 -0
- checkpoint-2000-epoch-5/model.safetensors +3 -0
- checkpoint-2000-epoch-5/model_args.json +1 -0
- checkpoint-2000-epoch-5/optimizer.pt +3 -0
- checkpoint-2000-epoch-5/scheduler.pt +3 -0
- checkpoint-2000-epoch-5/special_tokens_map.json +15 -0
- checkpoint-2000-epoch-5/tokenizer.json +3 -0
- checkpoint-2000-epoch-5/tokenizer_config.json +54 -0
- checkpoint-2000-epoch-5/training_args.bin +3 -0
- config.json +35 -0
- eval_results.txt +4 -0
- model.safetensors +3 -0
- model_args.json +1 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -0
- training_args.bin +3 -0
- training_progress_scores.csv +19 -0
.gitattributes
CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
best_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
checkpoint-2000-epoch-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
best_model/config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 4096,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-05,
|
22 |
+
"max_position_embeddings": 514,
|
23 |
+
"model_type": "xlm-roberta",
|
24 |
+
"num_attention_heads": 16,
|
25 |
+
"num_hidden_layers": 24,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 1,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"problem_type": "regression",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.39.3",
|
32 |
+
"type_vocab_size": 1,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 250002
|
35 |
+
}
|
best_model/eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.026975514134392142
|
2 |
+
pearson_corr = 0.8458653762395911
|
3 |
+
rmse = 0.16424224
|
4 |
+
spearman_corr = 0.7947246053750737
|
best_model/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ab3b4958f8443b61b2b91dd70a7718871579cb94fd53300cbca65fdc17ea65e
|
3 |
+
size 2239614572
|
best_model/model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/semantic_textual_similarity/xlm-roberta-large/best_model", "cache_dir": "cache_dir/semantic_textual_similarity/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": 10, "encoding": null, "eval_batch_size": 100, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 150, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 150, "loss_type": null, "loss_args": {}, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "FacebookAI/xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/semantic_textual_similarity/xlm-roberta-large", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 78, "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": 150, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "FacebookAI/xlm-roberta-large", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"name": "FacebookAI/xlm-roberta-large"}, "wandb_project": "Sinhala Semantic Textual Similarity", "warmup_ratio": 0.06, "warmup_steps": 120, "weight_decay": 0.0, "model_class": "TextClassificationModel", "labels_list": [0], "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": true, "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:d08bd83100ef389bc90ba9867fe5fd49203cc91b02a61a93dc95fbdc8615f9c3
|
3 |
+
size 4479464529
|
best_model/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55ce735aa5db5e6199276ffdaf6c91aa92de025daa6e33c87024d49b3f46ae01
|
3 |
+
size 1064
|
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.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62bf674b1c395bed20f40d50c04a2b4de2478fe605f07bc768335299bc8161e1
|
3 |
+
size 17083021
|
best_model/tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
best_model/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80b6a432d3bc0e713f70bf2e6820d1048509b99158a50949a0a2c241e21e47d8
|
3 |
+
size 3896
|
checkpoint-2000-epoch-5/config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 4096,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-05,
|
22 |
+
"max_position_embeddings": 514,
|
23 |
+
"model_type": "xlm-roberta",
|
24 |
+
"num_attention_heads": 16,
|
25 |
+
"num_hidden_layers": 24,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 1,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"problem_type": "regression",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.39.3",
|
32 |
+
"type_vocab_size": 1,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 250002
|
35 |
+
}
|
checkpoint-2000-epoch-5/eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.031083259265869856
|
2 |
+
pearson_corr = 0.8495512849002991
|
3 |
+
rmse = 0.17630444
|
4 |
+
spearman_corr = 0.7964750083045113
|
checkpoint-2000-epoch-5/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64e161665ae352628cbd6100315cdbc6cafd42f0ec7e06a62511e0df46272012
|
3 |
+
size 2239614572
|
checkpoint-2000-epoch-5/model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/semantic_textual_similarity/xlm-roberta-large/best_model", "cache_dir": "cache_dir/semantic_textual_similarity/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": 10, "encoding": null, "eval_batch_size": 100, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 150, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 150, "loss_type": null, "loss_args": {}, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "FacebookAI/xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/semantic_textual_similarity/xlm-roberta-large", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 78, "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": 150, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "FacebookAI/xlm-roberta-large", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"name": "FacebookAI/xlm-roberta-large"}, "wandb_project": "Sinhala Semantic Textual Similarity", "warmup_ratio": 0.06, "warmup_steps": 120, "weight_decay": 0.0, "model_class": "TextClassificationModel", "labels_list": [0], "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": true, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}
|
checkpoint-2000-epoch-5/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba37a808c78c0f18717b47cff2fe41fb9ca6c99f9f25f46dbb40e31da6d3eead
|
3 |
+
size 4479464529
|
checkpoint-2000-epoch-5/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:382782d862255d071016cff9c6a4b56eed27c6324967e51b062457330841da4d
|
3 |
+
size 1064
|
checkpoint-2000-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-2000-epoch-5/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62bf674b1c395bed20f40d50c04a2b4de2478fe605f07bc768335299bc8161e1
|
3 |
+
size 17083021
|
checkpoint-2000-epoch-5/tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
checkpoint-2000-epoch-5/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80b6a432d3bc0e713f70bf2e6820d1048509b99158a50949a0a2c241e21e47d8
|
3 |
+
size 3896
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 4096,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-05,
|
22 |
+
"max_position_embeddings": 514,
|
23 |
+
"model_type": "xlm-roberta",
|
24 |
+
"num_attention_heads": 16,
|
25 |
+
"num_hidden_layers": 24,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 1,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"problem_type": "regression",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.39.3",
|
32 |
+
"type_vocab_size": 1,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 250002
|
35 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.031083259265869856
|
2 |
+
pearson_corr = 0.8495512849002991
|
3 |
+
rmse = 0.17630444
|
4 |
+
spearman_corr = 0.7964750083045113
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64e161665ae352628cbd6100315cdbc6cafd42f0ec7e06a62511e0df46272012
|
3 |
+
size 2239614572
|
model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/semantic_textual_similarity/xlm-roberta-large/best_model", "cache_dir": "cache_dir/semantic_textual_similarity/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": 10, "encoding": null, "eval_batch_size": 100, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 150, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 150, "loss_type": null, "loss_args": {}, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "FacebookAI/xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/semantic_textual_similarity/xlm-roberta-large", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 78, "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": 150, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "FacebookAI/xlm-roberta-large", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"name": "FacebookAI/xlm-roberta-large"}, "wandb_project": "Sinhala Semantic Textual Similarity", "warmup_ratio": 0.06, "warmup_steps": 120, "weight_decay": 0.0, "model_class": "TextClassificationModel", "labels_list": [0], "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": true, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}
|
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.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62bf674b1c395bed20f40d50c04a2b4de2478fe605f07bc768335299bc8161e1
|
3 |
+
size 17083021
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80b6a432d3bc0e713f70bf2e6820d1048509b99158a50949a0a2c241e21e47d8
|
3 |
+
size 3896
|
training_progress_scores.csv
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
global_step,train_loss,pearson_corr,spearman_corr,rmse,eval_loss
|
2 |
+
150,0.09485940635204315,0.5766605328340815,0.5668820518455754,0.24539411,0.06021827179938555
|
3 |
+
300,0.03772255778312683,0.6800963646607021,0.652511464571298,0.31500244,0.09922653436660767
|
4 |
+
400,0.09586181491613388,0.6554188959982579,0.657276278258717,0.24972324,0.06236169533804059
|
5 |
+
450,0.048542894423007965,0.6856338634666208,0.6816073362019631,0.22121319,0.04893527599051595
|
6 |
+
600,0.04848804324865341,0.7317382200433852,0.7187978838430901,0.22512493,0.0506812259554863
|
7 |
+
750,0.04521271586418152,0.7778720144224749,0.7465405502381361,0.20466287,0.04188689147122204
|
8 |
+
800,0.13570499420166016,0.7827372118568713,0.7476864701509479,0.2145231,0.04602016042917967
|
9 |
+
900,0.05691898986697197,0.7887277083816643,0.7442120785354234,0.19055538,0.03631135378964245
|
10 |
+
1050,0.059201665222644806,0.8073442372904693,0.7667117756490306,0.1825778,0.033334651263430715
|
11 |
+
1200,0.011668585240840912,0.8172123465304022,0.7553049515212552,0.20618767,0.042513348860666156
|
12 |
+
1200,0.011668585240840912,0.8172123465304022,0.7553049515212552,0.20618767,0.042513348860666156
|
13 |
+
1350,0.04106896370649338,0.8389105898418777,0.7897815602399257,0.18713556,0.035019718343392015
|
14 |
+
1500,0.00994273740798235,0.8340410820667061,0.7798463796820537,0.17811576,0.031725223176181316
|
15 |
+
1600,0.017237914726138115,0.8339999292651987,0.7780857579952913,0.18461075,0.0340811291243881
|
16 |
+
1650,0.011701724492013454,0.8458653762395911,0.7947246053750737,0.16424224,0.026975514134392142
|
17 |
+
1800,0.02710156887769699,0.8496031357259926,0.7967718547958919,0.17373106,0.03018247871659696
|
18 |
+
1950,0.02306658774614334,0.8504976448874041,0.7969991360908377,0.17590636,0.030943043529987335
|
19 |
+
2000,0.021671902388334274,0.8495512849002991,0.7964750083045113,0.17630444,0.031083259265869856
|