Delete checkpoint-2000
Browse files- checkpoint-2000/config.json +0 -26
- checkpoint-2000/model.safetensors +0 -3
- checkpoint-2000/optimizer.pt +0 -3
- checkpoint-2000/rng_state.pth +0 -3
- checkpoint-2000/scheduler.pt +0 -3
- checkpoint-2000/special_tokens_map.json +0 -7
- checkpoint-2000/tokenizer.json +0 -0
- checkpoint-2000/tokenizer_config.json +0 -56
- checkpoint-2000/trainer_state.json +0 -118
- checkpoint-2000/training_args.bin +0 -3
- checkpoint-2000/vocab.txt +0 -0
checkpoint-2000/config.json
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"BertForSequenceClassification"
|
| 4 |
-
],
|
| 5 |
-
"attention_probs_dropout_prob": 0.1,
|
| 6 |
-
"classifier_dropout": null,
|
| 7 |
-
"gradient_checkpointing": false,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size": 768,
|
| 11 |
-
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size": 3072,
|
| 13 |
-
"layer_norm_eps": 1e-12,
|
| 14 |
-
"max_position_embeddings": 512,
|
| 15 |
-
"model_type": "bert",
|
| 16 |
-
"num_attention_heads": 12,
|
| 17 |
-
"num_hidden_layers": 12,
|
| 18 |
-
"pad_token_id": 0,
|
| 19 |
-
"position_embedding_type": "absolute",
|
| 20 |
-
"problem_type": "single_label_classification",
|
| 21 |
-
"torch_dtype": "float32",
|
| 22 |
-
"transformers_version": "4.50.2",
|
| 23 |
-
"type_vocab_size": 2,
|
| 24 |
-
"use_cache": true,
|
| 25 |
-
"vocab_size": 30522
|
| 26 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f7064ff010c82c7a755e3a7ca128f8d13310eef44f7cfc826873cf952953e519
|
| 3 |
-
size 437958648
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:00c08fe335cce814f4028b3e615cbabd83a83e99b541289a16cbf6292c4a85ca
|
| 3 |
-
size 876032762
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cc2b8196f9c3e0854dd7c9f87923599b18a237012c88013113e4e088315da416
|
| 3 |
-
size 13990
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:98427167ed878435a744ebf12bed531fbde19fdee7b460c175ee1db9180c827d
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/special_tokens_map.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": "[CLS]",
|
| 3 |
-
"mask_token": "[MASK]",
|
| 4 |
-
"pad_token": "[PAD]",
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/tokenizer_config.json
DELETED
|
@@ -1,56 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "[PAD]",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"100": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"101": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"102": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"103": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"clean_up_tokenization_spaces": false,
|
| 45 |
-
"cls_token": "[CLS]",
|
| 46 |
-
"do_lower_case": true,
|
| 47 |
-
"extra_special_tokens": {},
|
| 48 |
-
"mask_token": "[MASK]",
|
| 49 |
-
"model_max_length": 512,
|
| 50 |
-
"pad_token": "[PAD]",
|
| 51 |
-
"sep_token": "[SEP]",
|
| 52 |
-
"strip_accents": null,
|
| 53 |
-
"tokenize_chinese_chars": true,
|
| 54 |
-
"tokenizer_class": "BertTokenizer",
|
| 55 |
-
"unk_token": "[UNK]"
|
| 56 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/trainer_state.json
DELETED
|
@@ -1,118 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": 1500,
|
| 3 |
-
"best_metric": 0.9545758183032732,
|
| 4 |
-
"best_model_checkpoint": "C:\\Users\\Daniel\\Desktop\\GitHub\\NLPinitiative\\models\\dlsmallw\\NLPinitiative-Binary-Classification\\checkpoint-1500",
|
| 5 |
-
"epoch": 2.176278563656148,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 2000,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.544069640914037,
|
| 14 |
-
"grad_norm": 17.53396987915039,
|
| 15 |
-
"learning_rate": 1.637286906057309e-05,
|
| 16 |
-
"loss": 0.2811,
|
| 17 |
-
"step": 500
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.544069640914037,
|
| 21 |
-
"eval_accuracy": 0.949238578680203,
|
| 22 |
-
"eval_auprc": 0.2945266340168414,
|
| 23 |
-
"eval_auroc": 0.015546624960699109,
|
| 24 |
-
"eval_f1": 0.946914399469144,
|
| 25 |
-
"eval_loss": 0.19298532605171204,
|
| 26 |
-
"eval_precision": 0.9564343163538874,
|
| 27 |
-
"eval_recall": 0.9375821287779238,
|
| 28 |
-
"eval_runtime": 102.1508,
|
| 29 |
-
"eval_samples_per_second": 30.856,
|
| 30 |
-
"eval_steps_per_second": 3.857,
|
| 31 |
-
"step": 500
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 1.088139281828074,
|
| 35 |
-
"grad_norm": 1.0602138042449951,
|
| 36 |
-
"learning_rate": 1.2745738121146174e-05,
|
| 37 |
-
"loss": 0.1844,
|
| 38 |
-
"step": 1000
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 1.088139281828074,
|
| 42 |
-
"eval_accuracy": 0.9530456852791879,
|
| 43 |
-
"eval_auprc": 0.29439297154104793,
|
| 44 |
-
"eval_auroc": 0.013553767645090812,
|
| 45 |
-
"eval_f1": 0.9514435695538058,
|
| 46 |
-
"eval_loss": 0.19708991050720215,
|
| 47 |
-
"eval_precision": 0.9501965923984272,
|
| 48 |
-
"eval_recall": 0.9526938239159002,
|
| 49 |
-
"eval_runtime": 104.1259,
|
| 50 |
-
"eval_samples_per_second": 30.271,
|
| 51 |
-
"eval_steps_per_second": 3.784,
|
| 52 |
-
"step": 1000
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 1.632208922742111,
|
| 56 |
-
"grad_norm": 0.019807865843176842,
|
| 57 |
-
"learning_rate": 9.11860718171926e-06,
|
| 58 |
-
"loss": 0.0806,
|
| 59 |
-
"step": 1500
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 1.632208922742111,
|
| 63 |
-
"eval_accuracy": 0.9568527918781726,
|
| 64 |
-
"eval_auprc": 0.29427235149466713,
|
| 65 |
-
"eval_auroc": 0.011200752964697724,
|
| 66 |
-
"eval_f1": 0.9545758183032732,
|
| 67 |
-
"eval_loss": 0.23076476156711578,
|
| 68 |
-
"eval_precision": 0.9707880434782609,
|
| 69 |
-
"eval_recall": 0.9388961892247043,
|
| 70 |
-
"eval_runtime": 103.9447,
|
| 71 |
-
"eval_samples_per_second": 30.324,
|
| 72 |
-
"eval_steps_per_second": 3.79,
|
| 73 |
-
"step": 1500
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 2.176278563656148,
|
| 77 |
-
"grad_norm": 0.047856587916612625,
|
| 78 |
-
"learning_rate": 5.491476242292347e-06,
|
| 79 |
-
"loss": 0.0743,
|
| 80 |
-
"step": 2000
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 2.176278563656148,
|
| 84 |
-
"eval_accuracy": 0.9517766497461929,
|
| 85 |
-
"eval_auprc": 0.2942364000520487,
|
| 86 |
-
"eval_auroc": 0.010148496892206732,
|
| 87 |
-
"eval_f1": 0.9500984898227183,
|
| 88 |
-
"eval_loss": 0.2236114740371704,
|
| 89 |
-
"eval_precision": 0.949475065616798,
|
| 90 |
-
"eval_recall": 0.9507227332457293,
|
| 91 |
-
"eval_runtime": 100.9487,
|
| 92 |
-
"eval_samples_per_second": 31.224,
|
| 93 |
-
"eval_steps_per_second": 3.903,
|
| 94 |
-
"step": 2000
|
| 95 |
-
}
|
| 96 |
-
],
|
| 97 |
-
"logging_steps": 500,
|
| 98 |
-
"max_steps": 2757,
|
| 99 |
-
"num_input_tokens_seen": 0,
|
| 100 |
-
"num_train_epochs": 3,
|
| 101 |
-
"save_steps": 500,
|
| 102 |
-
"stateful_callbacks": {
|
| 103 |
-
"TrainerControl": {
|
| 104 |
-
"args": {
|
| 105 |
-
"should_epoch_stop": false,
|
| 106 |
-
"should_evaluate": false,
|
| 107 |
-
"should_log": false,
|
| 108 |
-
"should_save": true,
|
| 109 |
-
"should_training_stop": false
|
| 110 |
-
},
|
| 111 |
-
"attributes": {}
|
| 112 |
-
}
|
| 113 |
-
},
|
| 114 |
-
"total_flos": 1052444221440000.0,
|
| 115 |
-
"train_batch_size": 8,
|
| 116 |
-
"trial_name": null,
|
| 117 |
-
"trial_params": null
|
| 118 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ba1c0cd83c87672929cbce8fc2ed371343bdb0fb899364dfc5bb23635f9b95ef
|
| 3 |
-
size 5496
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-2000/vocab.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|