Upload 12 files
Browse files- config.json +34 -0
- eval_results.txt +3 -0
- merges.txt +0 -0
- model_args.json +1 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
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 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-05,
|
22 |
+
"max_position_embeddings": 514,
|
23 |
+
"model_type": "roberta",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 1,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"problem_type": "regression",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.24.0",
|
31 |
+
"type_vocab_size": 1,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 50265
|
34 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.031245260064392107
|
2 |
+
pearson = 0.9175037941134756
|
3 |
+
spearman = 0.8608172592446426
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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/roberta/scaled_zpa_train_size=602/best_model", "cache_dir": "outputs/roberta/scaled_zpa_train_size=602/cache", "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, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 75, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 2, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "roberta-base", "model_type": "roberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/roberta/scaled_zpa_train_size=602", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "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": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": "outputs/roberta/scaled_zpa_train_size=602/tensorboard", "thread_count": null, "tokenizer_name": "roberta-base", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"reinit": true}, "wandb_project": "scaled_zpa", "warmup_ratio": 0.06, "warmup_steps": 12, "weight_decay": 0.0, "model_class": "ClassificationModel", "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}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdce5203883cc2b73b5ccf163649a7ed3cc3e19fea1fde9cc73f29c4aeeb471e
|
3 |
+
size 997339322
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7776c58ab87e923edee4f2ab1c69ecaf14e401ae576936597ab2f1cffe7ed4c0
|
3 |
+
size 498659506
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7419ac96e6aa63538aa043dc319a44418614c0f09992ef722964c2ef89b1f9c
|
3 |
+
size 1064
|
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
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"do_lower_case": false,
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"model_max_length": 512,
|
10 |
+
"name_or_path": "roberta-base",
|
11 |
+
"pad_token": "<pad>",
|
12 |
+
"sep_token": "</s>",
|
13 |
+
"special_tokens_map_file": null,
|
14 |
+
"tokenizer_class": "RobertaTokenizer",
|
15 |
+
"trim_offsets": true,
|
16 |
+
"unk_token": "<unk>"
|
17 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d3efd2c2390cc392bfb5046bea56ec8b5316cefd17b1484eba9ea7531e1f8b7
|
3 |
+
size 3832
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|