init
Browse files- checkpoint-12874/config.json +35 -0
- checkpoint-12874/model.safetensors +3 -0
- checkpoint-12874/optimizer.pt +3 -0
- checkpoint-12874/rng_state.pth +3 -0
- checkpoint-12874/scheduler.pt +3 -0
- checkpoint-12874/special_tokens_map.json +37 -0
- checkpoint-12874/tokenizer.json +0 -0
- checkpoint-12874/tokenizer_config.json +56 -0
- checkpoint-12874/trainer_state.json +218 -0
- checkpoint-12874/training_args.bin +3 -0
- checkpoint-12874/vocab.txt +0 -0
- checkpoint-25748/config.json +35 -0
- checkpoint-25748/model.safetensors +3 -0
- checkpoint-25748/optimizer.pt +3 -0
- checkpoint-25748/rng_state.pth +3 -0
- checkpoint-25748/scheduler.pt +3 -0
- checkpoint-25748/special_tokens_map.json +37 -0
- checkpoint-25748/tokenizer.json +0 -0
- checkpoint-25748/tokenizer_config.json +56 -0
- checkpoint-25748/trainer_state.json +410 -0
- checkpoint-25748/training_args.bin +3 -0
- checkpoint-25748/vocab.txt +0 -0
- checkpoint-38622/config.json +35 -0
- checkpoint-38622/model.safetensors +3 -0
- checkpoint-38622/optimizer.pt +3 -0
- checkpoint-38622/rng_state.pth +3 -0
- checkpoint-38622/scheduler.pt +3 -0
- checkpoint-38622/special_tokens_map.json +37 -0
- checkpoint-38622/tokenizer.json +0 -0
- checkpoint-38622/tokenizer_config.json +56 -0
- checkpoint-38622/trainer_state.json +602 -0
- checkpoint-38622/training_args.bin +3 -0
- checkpoint-38622/vocab.txt +0 -0
- config.json +35 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoint-12874/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ealvaradob/bert-finetuned-phishing",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Safe",
|
| 14 |
+
"1": "Not Safe"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"Not Safe": 1,
|
| 20 |
+
"Safe": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.49.0",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 30522
|
| 35 |
+
}
|
checkpoint-12874/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb1eebf35bf97c37b96deb08b43410f3070dc8adf9bc3a1f6a791a1122271f97
|
| 3 |
+
size 1340622760
|
checkpoint-12874/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b9f7fd4f604e0db92cb9197aa7aef6ab66d20190d825a2d2dd49b95edf2bce7
|
| 3 |
+
size 8417490
|
checkpoint-12874/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf15cecb8b6f939a46f8aaa638b5573fcede1102b1ff7a5aed511feeefcff036
|
| 3 |
+
size 13990
|
checkpoint-12874/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a714272fcaa73a8f1fe0353a366968a5fc542da16927474a59ff8646ef228806
|
| 3 |
+
size 1064
|
checkpoint-12874/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-12874/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-12874/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 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-12874/trainer_state.json
ADDED
|
@@ -0,0 +1,218 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.35238268971443176,
|
| 3 |
+
"best_model_checkpoint": "AthenaMailGuard_v1\\checkpoint-12874",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 12874,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03883796799751437,
|
| 13 |
+
"grad_norm": 1.689921498298645,
|
| 14 |
+
"learning_rate": 1.9741080213349905e-05,
|
| 15 |
+
"loss": 0.8085,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07767593599502874,
|
| 20 |
+
"grad_norm": 2.86164927482605,
|
| 21 |
+
"learning_rate": 1.9482160426699808e-05,
|
| 22 |
+
"loss": 0.4984,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1165139039925431,
|
| 27 |
+
"grad_norm": 1.5302910804748535,
|
| 28 |
+
"learning_rate": 1.9223240640049715e-05,
|
| 29 |
+
"loss": 0.458,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15535187199005748,
|
| 34 |
+
"grad_norm": 1.5691194534301758,
|
| 35 |
+
"learning_rate": 1.8964320853399618e-05,
|
| 36 |
+
"loss": 0.4565,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.19418983998757186,
|
| 41 |
+
"grad_norm": 2.1296744346618652,
|
| 42 |
+
"learning_rate": 1.870540106674952e-05,
|
| 43 |
+
"loss": 0.4509,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2330278079850862,
|
| 48 |
+
"grad_norm": 2.2671611309051514,
|
| 49 |
+
"learning_rate": 1.8446481280099425e-05,
|
| 50 |
+
"loss": 0.4319,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2718657759826006,
|
| 55 |
+
"grad_norm": 2.0699307918548584,
|
| 56 |
+
"learning_rate": 1.818756149344933e-05,
|
| 57 |
+
"loss": 0.4255,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.31070374398011497,
|
| 62 |
+
"grad_norm": 2.077923536300659,
|
| 63 |
+
"learning_rate": 1.7928641706799235e-05,
|
| 64 |
+
"loss": 0.4261,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.34954171197762934,
|
| 69 |
+
"grad_norm": 2.9680869579315186,
|
| 70 |
+
"learning_rate": 1.7669721920149138e-05,
|
| 71 |
+
"loss": 0.4248,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3883796799751437,
|
| 76 |
+
"grad_norm": 2.7073068618774414,
|
| 77 |
+
"learning_rate": 1.741080213349904e-05,
|
| 78 |
+
"loss": 0.4228,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.42721764797265804,
|
| 83 |
+
"grad_norm": 1.9255578517913818,
|
| 84 |
+
"learning_rate": 1.7151882346848948e-05,
|
| 85 |
+
"loss": 0.4108,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4660556159701724,
|
| 90 |
+
"grad_norm": 2.937633752822876,
|
| 91 |
+
"learning_rate": 1.689296256019885e-05,
|
| 92 |
+
"loss": 0.4188,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5048935839676868,
|
| 97 |
+
"grad_norm": 4.763959884643555,
|
| 98 |
+
"learning_rate": 1.6634042773548755e-05,
|
| 99 |
+
"loss": 0.4149,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5437315519652012,
|
| 104 |
+
"grad_norm": 1.7722175121307373,
|
| 105 |
+
"learning_rate": 1.6375122986898658e-05,
|
| 106 |
+
"loss": 0.4051,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5825695199627156,
|
| 111 |
+
"grad_norm": 1.5043563842773438,
|
| 112 |
+
"learning_rate": 1.6116203200248565e-05,
|
| 113 |
+
"loss": 0.4079,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6214074879602299,
|
| 118 |
+
"grad_norm": 3.100849151611328,
|
| 119 |
+
"learning_rate": 1.5857283413598468e-05,
|
| 120 |
+
"loss": 0.3983,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6602454559577443,
|
| 125 |
+
"grad_norm": 2.095817804336548,
|
| 126 |
+
"learning_rate": 1.559836362694837e-05,
|
| 127 |
+
"loss": 0.4214,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6990834239552587,
|
| 132 |
+
"grad_norm": 1.558356523513794,
|
| 133 |
+
"learning_rate": 1.5339443840298275e-05,
|
| 134 |
+
"loss": 0.4203,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7379213919527731,
|
| 139 |
+
"grad_norm": 4.565003871917725,
|
| 140 |
+
"learning_rate": 1.508052405364818e-05,
|
| 141 |
+
"loss": 0.4049,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7767593599502874,
|
| 146 |
+
"grad_norm": 2.9373462200164795,
|
| 147 |
+
"learning_rate": 1.4821604266998085e-05,
|
| 148 |
+
"loss": 0.4091,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8155973279478018,
|
| 153 |
+
"grad_norm": 1.9515178203582764,
|
| 154 |
+
"learning_rate": 1.4562684480347988e-05,
|
| 155 |
+
"loss": 0.4121,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8544352959453161,
|
| 160 |
+
"grad_norm": 2.4346730709075928,
|
| 161 |
+
"learning_rate": 1.4303764693697895e-05,
|
| 162 |
+
"loss": 0.4155,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8932732639428305,
|
| 167 |
+
"grad_norm": 1.920275330543518,
|
| 168 |
+
"learning_rate": 1.4044844907047798e-05,
|
| 169 |
+
"loss": 0.4051,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9321112319403448,
|
| 174 |
+
"grad_norm": 0.8134564757347107,
|
| 175 |
+
"learning_rate": 1.3785925120397703e-05,
|
| 176 |
+
"loss": 0.4115,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9709491999378592,
|
| 181 |
+
"grad_norm": 1.6996334791183472,
|
| 182 |
+
"learning_rate": 1.3527005333747607e-05,
|
| 183 |
+
"loss": 0.4134,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0,
|
| 188 |
+
"eval_AUC": 0.919,
|
| 189 |
+
"eval_Accuracy": 0.871,
|
| 190 |
+
"eval_loss": 0.35238268971443176,
|
| 191 |
+
"eval_runtime": 9979.0139,
|
| 192 |
+
"eval_samples_per_second": 2.293,
|
| 193 |
+
"eval_steps_per_second": 0.143,
|
| 194 |
+
"step": 12874
|
| 195 |
+
}
|
| 196 |
+
],
|
| 197 |
+
"logging_steps": 500,
|
| 198 |
+
"max_steps": 38622,
|
| 199 |
+
"num_input_tokens_seen": 0,
|
| 200 |
+
"num_train_epochs": 3,
|
| 201 |
+
"save_steps": 500,
|
| 202 |
+
"stateful_callbacks": {
|
| 203 |
+
"TrainerControl": {
|
| 204 |
+
"args": {
|
| 205 |
+
"should_epoch_stop": false,
|
| 206 |
+
"should_evaluate": false,
|
| 207 |
+
"should_log": false,
|
| 208 |
+
"should_save": true,
|
| 209 |
+
"should_training_stop": false
|
| 210 |
+
},
|
| 211 |
+
"attributes": {}
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"total_flos": 1.919517667673948e+17,
|
| 215 |
+
"train_batch_size": 16,
|
| 216 |
+
"trial_name": null,
|
| 217 |
+
"trial_params": null
|
| 218 |
+
}
|
checkpoint-12874/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef81828047111fb8469f346d2515430f70d6821251e87dd33c6c643512ff318
|
| 3 |
+
size 5368
|
checkpoint-12874/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-25748/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ealvaradob/bert-finetuned-phishing",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Safe",
|
| 14 |
+
"1": "Not Safe"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"Not Safe": 1,
|
| 20 |
+
"Safe": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.49.0",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 30522
|
| 35 |
+
}
|
checkpoint-25748/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c66ce3800a16bc03ebfa6c05ab86423c99cf5a999483c2e47c90869964668d4
|
| 3 |
+
size 1340622760
|
checkpoint-25748/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:781b20d4ed2c3da4e6c41f44ac992719eb72949495ae648628c769baabd1571b
|
| 3 |
+
size 8417490
|
checkpoint-25748/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71f7cba9396e8d95aec4f0c8d573c1ba347964f5dce317e1c247a91e3c2ce809
|
| 3 |
+
size 13990
|
checkpoint-25748/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b1f1471b4ed4d74d245739229a192e925719c064d39460cfad51fcf9c830bd9
|
| 3 |
+
size 1064
|
checkpoint-25748/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-25748/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-25748/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 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-25748/trainer_state.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.35110267996788025,
|
| 3 |
+
"best_model_checkpoint": "AthenaMailGuard_v1\\checkpoint-25748",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 25748,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03883796799751437,
|
| 13 |
+
"grad_norm": 1.689921498298645,
|
| 14 |
+
"learning_rate": 1.9741080213349905e-05,
|
| 15 |
+
"loss": 0.8085,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07767593599502874,
|
| 20 |
+
"grad_norm": 2.86164927482605,
|
| 21 |
+
"learning_rate": 1.9482160426699808e-05,
|
| 22 |
+
"loss": 0.4984,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1165139039925431,
|
| 27 |
+
"grad_norm": 1.5302910804748535,
|
| 28 |
+
"learning_rate": 1.9223240640049715e-05,
|
| 29 |
+
"loss": 0.458,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15535187199005748,
|
| 34 |
+
"grad_norm": 1.5691194534301758,
|
| 35 |
+
"learning_rate": 1.8964320853399618e-05,
|
| 36 |
+
"loss": 0.4565,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.19418983998757186,
|
| 41 |
+
"grad_norm": 2.1296744346618652,
|
| 42 |
+
"learning_rate": 1.870540106674952e-05,
|
| 43 |
+
"loss": 0.4509,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2330278079850862,
|
| 48 |
+
"grad_norm": 2.2671611309051514,
|
| 49 |
+
"learning_rate": 1.8446481280099425e-05,
|
| 50 |
+
"loss": 0.4319,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2718657759826006,
|
| 55 |
+
"grad_norm": 2.0699307918548584,
|
| 56 |
+
"learning_rate": 1.818756149344933e-05,
|
| 57 |
+
"loss": 0.4255,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.31070374398011497,
|
| 62 |
+
"grad_norm": 2.077923536300659,
|
| 63 |
+
"learning_rate": 1.7928641706799235e-05,
|
| 64 |
+
"loss": 0.4261,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.34954171197762934,
|
| 69 |
+
"grad_norm": 2.9680869579315186,
|
| 70 |
+
"learning_rate": 1.7669721920149138e-05,
|
| 71 |
+
"loss": 0.4248,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3883796799751437,
|
| 76 |
+
"grad_norm": 2.7073068618774414,
|
| 77 |
+
"learning_rate": 1.741080213349904e-05,
|
| 78 |
+
"loss": 0.4228,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.42721764797265804,
|
| 83 |
+
"grad_norm": 1.9255578517913818,
|
| 84 |
+
"learning_rate": 1.7151882346848948e-05,
|
| 85 |
+
"loss": 0.4108,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4660556159701724,
|
| 90 |
+
"grad_norm": 2.937633752822876,
|
| 91 |
+
"learning_rate": 1.689296256019885e-05,
|
| 92 |
+
"loss": 0.4188,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5048935839676868,
|
| 97 |
+
"grad_norm": 4.763959884643555,
|
| 98 |
+
"learning_rate": 1.6634042773548755e-05,
|
| 99 |
+
"loss": 0.4149,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5437315519652012,
|
| 104 |
+
"grad_norm": 1.7722175121307373,
|
| 105 |
+
"learning_rate": 1.6375122986898658e-05,
|
| 106 |
+
"loss": 0.4051,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5825695199627156,
|
| 111 |
+
"grad_norm": 1.5043563842773438,
|
| 112 |
+
"learning_rate": 1.6116203200248565e-05,
|
| 113 |
+
"loss": 0.4079,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6214074879602299,
|
| 118 |
+
"grad_norm": 3.100849151611328,
|
| 119 |
+
"learning_rate": 1.5857283413598468e-05,
|
| 120 |
+
"loss": 0.3983,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6602454559577443,
|
| 125 |
+
"grad_norm": 2.095817804336548,
|
| 126 |
+
"learning_rate": 1.559836362694837e-05,
|
| 127 |
+
"loss": 0.4214,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6990834239552587,
|
| 132 |
+
"grad_norm": 1.558356523513794,
|
| 133 |
+
"learning_rate": 1.5339443840298275e-05,
|
| 134 |
+
"loss": 0.4203,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7379213919527731,
|
| 139 |
+
"grad_norm": 4.565003871917725,
|
| 140 |
+
"learning_rate": 1.508052405364818e-05,
|
| 141 |
+
"loss": 0.4049,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7767593599502874,
|
| 146 |
+
"grad_norm": 2.9373462200164795,
|
| 147 |
+
"learning_rate": 1.4821604266998085e-05,
|
| 148 |
+
"loss": 0.4091,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8155973279478018,
|
| 153 |
+
"grad_norm": 1.9515178203582764,
|
| 154 |
+
"learning_rate": 1.4562684480347988e-05,
|
| 155 |
+
"loss": 0.4121,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8544352959453161,
|
| 160 |
+
"grad_norm": 2.4346730709075928,
|
| 161 |
+
"learning_rate": 1.4303764693697895e-05,
|
| 162 |
+
"loss": 0.4155,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8932732639428305,
|
| 167 |
+
"grad_norm": 1.920275330543518,
|
| 168 |
+
"learning_rate": 1.4044844907047798e-05,
|
| 169 |
+
"loss": 0.4051,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9321112319403448,
|
| 174 |
+
"grad_norm": 0.8134564757347107,
|
| 175 |
+
"learning_rate": 1.3785925120397703e-05,
|
| 176 |
+
"loss": 0.4115,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9709491999378592,
|
| 181 |
+
"grad_norm": 1.6996334791183472,
|
| 182 |
+
"learning_rate": 1.3527005333747607e-05,
|
| 183 |
+
"loss": 0.4134,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0,
|
| 188 |
+
"eval_AUC": 0.919,
|
| 189 |
+
"eval_Accuracy": 0.871,
|
| 190 |
+
"eval_loss": 0.35238268971443176,
|
| 191 |
+
"eval_runtime": 9979.0139,
|
| 192 |
+
"eval_samples_per_second": 2.293,
|
| 193 |
+
"eval_steps_per_second": 0.143,
|
| 194 |
+
"step": 12874
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.0097871679353736,
|
| 198 |
+
"grad_norm": 1.933709740638733,
|
| 199 |
+
"learning_rate": 1.3268085547097512e-05,
|
| 200 |
+
"loss": 0.412,
|
| 201 |
+
"step": 13000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.048625135932888,
|
| 205 |
+
"grad_norm": 1.2826268672943115,
|
| 206 |
+
"learning_rate": 1.3009165760447415e-05,
|
| 207 |
+
"loss": 0.4033,
|
| 208 |
+
"step": 13500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.0874631039304024,
|
| 212 |
+
"grad_norm": 2.6913065910339355,
|
| 213 |
+
"learning_rate": 1.275024597379732e-05,
|
| 214 |
+
"loss": 0.4137,
|
| 215 |
+
"step": 14000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.1263010719279167,
|
| 219 |
+
"grad_norm": 3.0463294982910156,
|
| 220 |
+
"learning_rate": 1.2491326187147223e-05,
|
| 221 |
+
"loss": 0.4045,
|
| 222 |
+
"step": 14500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.165139039925431,
|
| 226 |
+
"grad_norm": 1.5197412967681885,
|
| 227 |
+
"learning_rate": 1.2232406400497128e-05,
|
| 228 |
+
"loss": 0.4023,
|
| 229 |
+
"step": 15000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.2039770079229455,
|
| 233 |
+
"grad_norm": 2.334850788116455,
|
| 234 |
+
"learning_rate": 1.1973486613847032e-05,
|
| 235 |
+
"loss": 0.4076,
|
| 236 |
+
"step": 15500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.2428149759204599,
|
| 240 |
+
"grad_norm": 3.974278211593628,
|
| 241 |
+
"learning_rate": 1.1714566827196937e-05,
|
| 242 |
+
"loss": 0.4071,
|
| 243 |
+
"step": 16000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.2816529439179742,
|
| 247 |
+
"grad_norm": 1.8683360815048218,
|
| 248 |
+
"learning_rate": 1.145564704054684e-05,
|
| 249 |
+
"loss": 0.4101,
|
| 250 |
+
"step": 16500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.3204909119154886,
|
| 254 |
+
"grad_norm": 2.1151626110076904,
|
| 255 |
+
"learning_rate": 1.1196727253896745e-05,
|
| 256 |
+
"loss": 0.3948,
|
| 257 |
+
"step": 17000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.359328879913003,
|
| 261 |
+
"grad_norm": 1.7954820394515991,
|
| 262 |
+
"learning_rate": 1.0937807467246648e-05,
|
| 263 |
+
"loss": 0.4095,
|
| 264 |
+
"step": 17500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.3981668479105174,
|
| 268 |
+
"grad_norm": 1.9576789140701294,
|
| 269 |
+
"learning_rate": 1.0678887680596553e-05,
|
| 270 |
+
"loss": 0.3987,
|
| 271 |
+
"step": 18000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.4370048159080318,
|
| 275 |
+
"grad_norm": 1.471616268157959,
|
| 276 |
+
"learning_rate": 1.0419967893946456e-05,
|
| 277 |
+
"loss": 0.4122,
|
| 278 |
+
"step": 18500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.4758427839055461,
|
| 282 |
+
"grad_norm": 1.507846713066101,
|
| 283 |
+
"learning_rate": 1.0161048107296361e-05,
|
| 284 |
+
"loss": 0.3869,
|
| 285 |
+
"step": 19000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.5146807519030605,
|
| 289 |
+
"grad_norm": 1.9979530572891235,
|
| 290 |
+
"learning_rate": 9.902128320646265e-06,
|
| 291 |
+
"loss": 0.3949,
|
| 292 |
+
"step": 19500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.5535187199005747,
|
| 296 |
+
"grad_norm": 1.022186040878296,
|
| 297 |
+
"learning_rate": 9.643208533996168e-06,
|
| 298 |
+
"loss": 0.4082,
|
| 299 |
+
"step": 20000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.5923566878980893,
|
| 303 |
+
"grad_norm": 1.725373387336731,
|
| 304 |
+
"learning_rate": 9.384288747346073e-06,
|
| 305 |
+
"loss": 0.3983,
|
| 306 |
+
"step": 20500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.6311946558956034,
|
| 310 |
+
"grad_norm": 1.8882161378860474,
|
| 311 |
+
"learning_rate": 9.125368960695976e-06,
|
| 312 |
+
"loss": 0.3913,
|
| 313 |
+
"step": 21000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.670032623893118,
|
| 317 |
+
"grad_norm": 1.6501694917678833,
|
| 318 |
+
"learning_rate": 8.866449174045881e-06,
|
| 319 |
+
"loss": 0.3967,
|
| 320 |
+
"step": 21500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.7088705918906322,
|
| 324 |
+
"grad_norm": 3.191229820251465,
|
| 325 |
+
"learning_rate": 8.607529387395785e-06,
|
| 326 |
+
"loss": 0.4047,
|
| 327 |
+
"step": 22000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.7477085598881468,
|
| 331 |
+
"grad_norm": 2.09586763381958,
|
| 332 |
+
"learning_rate": 8.34860960074569e-06,
|
| 333 |
+
"loss": 0.4066,
|
| 334 |
+
"step": 22500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.786546527885661,
|
| 338 |
+
"grad_norm": 4.569416522979736,
|
| 339 |
+
"learning_rate": 8.089689814095593e-06,
|
| 340 |
+
"loss": 0.4041,
|
| 341 |
+
"step": 23000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.8253844958831755,
|
| 345 |
+
"grad_norm": 1.9049654006958008,
|
| 346 |
+
"learning_rate": 7.830770027445498e-06,
|
| 347 |
+
"loss": 0.4007,
|
| 348 |
+
"step": 23500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.8642224638806897,
|
| 352 |
+
"grad_norm": 2.03849720954895,
|
| 353 |
+
"learning_rate": 7.571850240795402e-06,
|
| 354 |
+
"loss": 0.4049,
|
| 355 |
+
"step": 24000
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.9030604318782043,
|
| 359 |
+
"grad_norm": 2.5075671672821045,
|
| 360 |
+
"learning_rate": 7.3129304541453064e-06,
|
| 361 |
+
"loss": 0.3868,
|
| 362 |
+
"step": 24500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.9418983998757184,
|
| 366 |
+
"grad_norm": 3.445219039916992,
|
| 367 |
+
"learning_rate": 7.054010667495211e-06,
|
| 368 |
+
"loss": 0.4054,
|
| 369 |
+
"step": 25000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.9807363678732328,
|
| 373 |
+
"grad_norm": 4.2253923416137695,
|
| 374 |
+
"learning_rate": 6.795090880845115e-06,
|
| 375 |
+
"loss": 0.414,
|
| 376 |
+
"step": 25500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.0,
|
| 380 |
+
"eval_AUC": 0.924,
|
| 381 |
+
"eval_Accuracy": 0.873,
|
| 382 |
+
"eval_loss": 0.35110267996788025,
|
| 383 |
+
"eval_runtime": 9961.9295,
|
| 384 |
+
"eval_samples_per_second": 2.297,
|
| 385 |
+
"eval_steps_per_second": 0.144,
|
| 386 |
+
"step": 25748
|
| 387 |
+
}
|
| 388 |
+
],
|
| 389 |
+
"logging_steps": 500,
|
| 390 |
+
"max_steps": 38622,
|
| 391 |
+
"num_input_tokens_seen": 0,
|
| 392 |
+
"num_train_epochs": 3,
|
| 393 |
+
"save_steps": 500,
|
| 394 |
+
"stateful_callbacks": {
|
| 395 |
+
"TrainerControl": {
|
| 396 |
+
"args": {
|
| 397 |
+
"should_epoch_stop": false,
|
| 398 |
+
"should_evaluate": false,
|
| 399 |
+
"should_log": false,
|
| 400 |
+
"should_save": true,
|
| 401 |
+
"should_training_stop": false
|
| 402 |
+
},
|
| 403 |
+
"attributes": {}
|
| 404 |
+
}
|
| 405 |
+
},
|
| 406 |
+
"total_flos": 3.839035335347896e+17,
|
| 407 |
+
"train_batch_size": 16,
|
| 408 |
+
"trial_name": null,
|
| 409 |
+
"trial_params": null
|
| 410 |
+
}
|
checkpoint-25748/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef81828047111fb8469f346d2515430f70d6821251e87dd33c6c643512ff318
|
| 3 |
+
size 5368
|
checkpoint-25748/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-38622/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ealvaradob/bert-finetuned-phishing",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Safe",
|
| 14 |
+
"1": "Not Safe"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"Not Safe": 1,
|
| 20 |
+
"Safe": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.49.0",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 30522
|
| 35 |
+
}
|
checkpoint-38622/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba3c2727fcc23a9001aab178b34a1ce73252b99bb58532e714eefe58721bdddd
|
| 3 |
+
size 1340622760
|
checkpoint-38622/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75341253afbafa1b9bb1318953be5d34479d5dbd5d84c1a353146fa676218653
|
| 3 |
+
size 8417490
|
checkpoint-38622/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f91e3d97ebfd547b5661095ce14603636948432cd2fb8c236ce86bdd52eb256a
|
| 3 |
+
size 13990
|
checkpoint-38622/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc1872477825a5d08b958f06ff8baa9c7d19b0bfccdea29596dd86add24e9574
|
| 3 |
+
size 1064
|
checkpoint-38622/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-38622/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-38622/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 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-38622/trainer_state.json
ADDED
|
@@ -0,0 +1,602 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.342347651720047,
|
| 3 |
+
"best_model_checkpoint": "AthenaMailGuard_v1\\checkpoint-38622",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 38622,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03883796799751437,
|
| 13 |
+
"grad_norm": 1.689921498298645,
|
| 14 |
+
"learning_rate": 1.9741080213349905e-05,
|
| 15 |
+
"loss": 0.8085,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07767593599502874,
|
| 20 |
+
"grad_norm": 2.86164927482605,
|
| 21 |
+
"learning_rate": 1.9482160426699808e-05,
|
| 22 |
+
"loss": 0.4984,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1165139039925431,
|
| 27 |
+
"grad_norm": 1.5302910804748535,
|
| 28 |
+
"learning_rate": 1.9223240640049715e-05,
|
| 29 |
+
"loss": 0.458,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15535187199005748,
|
| 34 |
+
"grad_norm": 1.5691194534301758,
|
| 35 |
+
"learning_rate": 1.8964320853399618e-05,
|
| 36 |
+
"loss": 0.4565,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.19418983998757186,
|
| 41 |
+
"grad_norm": 2.1296744346618652,
|
| 42 |
+
"learning_rate": 1.870540106674952e-05,
|
| 43 |
+
"loss": 0.4509,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2330278079850862,
|
| 48 |
+
"grad_norm": 2.2671611309051514,
|
| 49 |
+
"learning_rate": 1.8446481280099425e-05,
|
| 50 |
+
"loss": 0.4319,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2718657759826006,
|
| 55 |
+
"grad_norm": 2.0699307918548584,
|
| 56 |
+
"learning_rate": 1.818756149344933e-05,
|
| 57 |
+
"loss": 0.4255,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.31070374398011497,
|
| 62 |
+
"grad_norm": 2.077923536300659,
|
| 63 |
+
"learning_rate": 1.7928641706799235e-05,
|
| 64 |
+
"loss": 0.4261,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.34954171197762934,
|
| 69 |
+
"grad_norm": 2.9680869579315186,
|
| 70 |
+
"learning_rate": 1.7669721920149138e-05,
|
| 71 |
+
"loss": 0.4248,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3883796799751437,
|
| 76 |
+
"grad_norm": 2.7073068618774414,
|
| 77 |
+
"learning_rate": 1.741080213349904e-05,
|
| 78 |
+
"loss": 0.4228,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.42721764797265804,
|
| 83 |
+
"grad_norm": 1.9255578517913818,
|
| 84 |
+
"learning_rate": 1.7151882346848948e-05,
|
| 85 |
+
"loss": 0.4108,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4660556159701724,
|
| 90 |
+
"grad_norm": 2.937633752822876,
|
| 91 |
+
"learning_rate": 1.689296256019885e-05,
|
| 92 |
+
"loss": 0.4188,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5048935839676868,
|
| 97 |
+
"grad_norm": 4.763959884643555,
|
| 98 |
+
"learning_rate": 1.6634042773548755e-05,
|
| 99 |
+
"loss": 0.4149,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5437315519652012,
|
| 104 |
+
"grad_norm": 1.7722175121307373,
|
| 105 |
+
"learning_rate": 1.6375122986898658e-05,
|
| 106 |
+
"loss": 0.4051,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5825695199627156,
|
| 111 |
+
"grad_norm": 1.5043563842773438,
|
| 112 |
+
"learning_rate": 1.6116203200248565e-05,
|
| 113 |
+
"loss": 0.4079,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6214074879602299,
|
| 118 |
+
"grad_norm": 3.100849151611328,
|
| 119 |
+
"learning_rate": 1.5857283413598468e-05,
|
| 120 |
+
"loss": 0.3983,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6602454559577443,
|
| 125 |
+
"grad_norm": 2.095817804336548,
|
| 126 |
+
"learning_rate": 1.559836362694837e-05,
|
| 127 |
+
"loss": 0.4214,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6990834239552587,
|
| 132 |
+
"grad_norm": 1.558356523513794,
|
| 133 |
+
"learning_rate": 1.5339443840298275e-05,
|
| 134 |
+
"loss": 0.4203,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7379213919527731,
|
| 139 |
+
"grad_norm": 4.565003871917725,
|
| 140 |
+
"learning_rate": 1.508052405364818e-05,
|
| 141 |
+
"loss": 0.4049,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7767593599502874,
|
| 146 |
+
"grad_norm": 2.9373462200164795,
|
| 147 |
+
"learning_rate": 1.4821604266998085e-05,
|
| 148 |
+
"loss": 0.4091,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8155973279478018,
|
| 153 |
+
"grad_norm": 1.9515178203582764,
|
| 154 |
+
"learning_rate": 1.4562684480347988e-05,
|
| 155 |
+
"loss": 0.4121,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8544352959453161,
|
| 160 |
+
"grad_norm": 2.4346730709075928,
|
| 161 |
+
"learning_rate": 1.4303764693697895e-05,
|
| 162 |
+
"loss": 0.4155,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8932732639428305,
|
| 167 |
+
"grad_norm": 1.920275330543518,
|
| 168 |
+
"learning_rate": 1.4044844907047798e-05,
|
| 169 |
+
"loss": 0.4051,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9321112319403448,
|
| 174 |
+
"grad_norm": 0.8134564757347107,
|
| 175 |
+
"learning_rate": 1.3785925120397703e-05,
|
| 176 |
+
"loss": 0.4115,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9709491999378592,
|
| 181 |
+
"grad_norm": 1.6996334791183472,
|
| 182 |
+
"learning_rate": 1.3527005333747607e-05,
|
| 183 |
+
"loss": 0.4134,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0,
|
| 188 |
+
"eval_AUC": 0.919,
|
| 189 |
+
"eval_Accuracy": 0.871,
|
| 190 |
+
"eval_loss": 0.35238268971443176,
|
| 191 |
+
"eval_runtime": 9979.0139,
|
| 192 |
+
"eval_samples_per_second": 2.293,
|
| 193 |
+
"eval_steps_per_second": 0.143,
|
| 194 |
+
"step": 12874
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.0097871679353736,
|
| 198 |
+
"grad_norm": 1.933709740638733,
|
| 199 |
+
"learning_rate": 1.3268085547097512e-05,
|
| 200 |
+
"loss": 0.412,
|
| 201 |
+
"step": 13000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.048625135932888,
|
| 205 |
+
"grad_norm": 1.2826268672943115,
|
| 206 |
+
"learning_rate": 1.3009165760447415e-05,
|
| 207 |
+
"loss": 0.4033,
|
| 208 |
+
"step": 13500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.0874631039304024,
|
| 212 |
+
"grad_norm": 2.6913065910339355,
|
| 213 |
+
"learning_rate": 1.275024597379732e-05,
|
| 214 |
+
"loss": 0.4137,
|
| 215 |
+
"step": 14000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.1263010719279167,
|
| 219 |
+
"grad_norm": 3.0463294982910156,
|
| 220 |
+
"learning_rate": 1.2491326187147223e-05,
|
| 221 |
+
"loss": 0.4045,
|
| 222 |
+
"step": 14500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.165139039925431,
|
| 226 |
+
"grad_norm": 1.5197412967681885,
|
| 227 |
+
"learning_rate": 1.2232406400497128e-05,
|
| 228 |
+
"loss": 0.4023,
|
| 229 |
+
"step": 15000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.2039770079229455,
|
| 233 |
+
"grad_norm": 2.334850788116455,
|
| 234 |
+
"learning_rate": 1.1973486613847032e-05,
|
| 235 |
+
"loss": 0.4076,
|
| 236 |
+
"step": 15500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.2428149759204599,
|
| 240 |
+
"grad_norm": 3.974278211593628,
|
| 241 |
+
"learning_rate": 1.1714566827196937e-05,
|
| 242 |
+
"loss": 0.4071,
|
| 243 |
+
"step": 16000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.2816529439179742,
|
| 247 |
+
"grad_norm": 1.8683360815048218,
|
| 248 |
+
"learning_rate": 1.145564704054684e-05,
|
| 249 |
+
"loss": 0.4101,
|
| 250 |
+
"step": 16500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.3204909119154886,
|
| 254 |
+
"grad_norm": 2.1151626110076904,
|
| 255 |
+
"learning_rate": 1.1196727253896745e-05,
|
| 256 |
+
"loss": 0.3948,
|
| 257 |
+
"step": 17000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.359328879913003,
|
| 261 |
+
"grad_norm": 1.7954820394515991,
|
| 262 |
+
"learning_rate": 1.0937807467246648e-05,
|
| 263 |
+
"loss": 0.4095,
|
| 264 |
+
"step": 17500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.3981668479105174,
|
| 268 |
+
"grad_norm": 1.9576789140701294,
|
| 269 |
+
"learning_rate": 1.0678887680596553e-05,
|
| 270 |
+
"loss": 0.3987,
|
| 271 |
+
"step": 18000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.4370048159080318,
|
| 275 |
+
"grad_norm": 1.471616268157959,
|
| 276 |
+
"learning_rate": 1.0419967893946456e-05,
|
| 277 |
+
"loss": 0.4122,
|
| 278 |
+
"step": 18500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.4758427839055461,
|
| 282 |
+
"grad_norm": 1.507846713066101,
|
| 283 |
+
"learning_rate": 1.0161048107296361e-05,
|
| 284 |
+
"loss": 0.3869,
|
| 285 |
+
"step": 19000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.5146807519030605,
|
| 289 |
+
"grad_norm": 1.9979530572891235,
|
| 290 |
+
"learning_rate": 9.902128320646265e-06,
|
| 291 |
+
"loss": 0.3949,
|
| 292 |
+
"step": 19500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.5535187199005747,
|
| 296 |
+
"grad_norm": 1.022186040878296,
|
| 297 |
+
"learning_rate": 9.643208533996168e-06,
|
| 298 |
+
"loss": 0.4082,
|
| 299 |
+
"step": 20000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.5923566878980893,
|
| 303 |
+
"grad_norm": 1.725373387336731,
|
| 304 |
+
"learning_rate": 9.384288747346073e-06,
|
| 305 |
+
"loss": 0.3983,
|
| 306 |
+
"step": 20500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.6311946558956034,
|
| 310 |
+
"grad_norm": 1.8882161378860474,
|
| 311 |
+
"learning_rate": 9.125368960695976e-06,
|
| 312 |
+
"loss": 0.3913,
|
| 313 |
+
"step": 21000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.670032623893118,
|
| 317 |
+
"grad_norm": 1.6501694917678833,
|
| 318 |
+
"learning_rate": 8.866449174045881e-06,
|
| 319 |
+
"loss": 0.3967,
|
| 320 |
+
"step": 21500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.7088705918906322,
|
| 324 |
+
"grad_norm": 3.191229820251465,
|
| 325 |
+
"learning_rate": 8.607529387395785e-06,
|
| 326 |
+
"loss": 0.4047,
|
| 327 |
+
"step": 22000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.7477085598881468,
|
| 331 |
+
"grad_norm": 2.09586763381958,
|
| 332 |
+
"learning_rate": 8.34860960074569e-06,
|
| 333 |
+
"loss": 0.4066,
|
| 334 |
+
"step": 22500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.786546527885661,
|
| 338 |
+
"grad_norm": 4.569416522979736,
|
| 339 |
+
"learning_rate": 8.089689814095593e-06,
|
| 340 |
+
"loss": 0.4041,
|
| 341 |
+
"step": 23000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.8253844958831755,
|
| 345 |
+
"grad_norm": 1.9049654006958008,
|
| 346 |
+
"learning_rate": 7.830770027445498e-06,
|
| 347 |
+
"loss": 0.4007,
|
| 348 |
+
"step": 23500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.8642224638806897,
|
| 352 |
+
"grad_norm": 2.03849720954895,
|
| 353 |
+
"learning_rate": 7.571850240795402e-06,
|
| 354 |
+
"loss": 0.4049,
|
| 355 |
+
"step": 24000
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.9030604318782043,
|
| 359 |
+
"grad_norm": 2.5075671672821045,
|
| 360 |
+
"learning_rate": 7.3129304541453064e-06,
|
| 361 |
+
"loss": 0.3868,
|
| 362 |
+
"step": 24500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.9418983998757184,
|
| 366 |
+
"grad_norm": 3.445219039916992,
|
| 367 |
+
"learning_rate": 7.054010667495211e-06,
|
| 368 |
+
"loss": 0.4054,
|
| 369 |
+
"step": 25000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.9807363678732328,
|
| 373 |
+
"grad_norm": 4.2253923416137695,
|
| 374 |
+
"learning_rate": 6.795090880845115e-06,
|
| 375 |
+
"loss": 0.414,
|
| 376 |
+
"step": 25500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.0,
|
| 380 |
+
"eval_AUC": 0.924,
|
| 381 |
+
"eval_Accuracy": 0.873,
|
| 382 |
+
"eval_loss": 0.35110267996788025,
|
| 383 |
+
"eval_runtime": 9961.9295,
|
| 384 |
+
"eval_samples_per_second": 2.297,
|
| 385 |
+
"eval_steps_per_second": 0.144,
|
| 386 |
+
"step": 25748
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.019574335870747,
|
| 390 |
+
"grad_norm": 1.9335342645645142,
|
| 391 |
+
"learning_rate": 6.536171094195019e-06,
|
| 392 |
+
"loss": 0.3919,
|
| 393 |
+
"step": 26000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.058412303868262,
|
| 397 |
+
"grad_norm": 1.5774650573730469,
|
| 398 |
+
"learning_rate": 6.277251307544922e-06,
|
| 399 |
+
"loss": 0.3931,
|
| 400 |
+
"step": 26500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.097250271865776,
|
| 404 |
+
"grad_norm": 3.0770256519317627,
|
| 405 |
+
"learning_rate": 6.018331520894826e-06,
|
| 406 |
+
"loss": 0.4035,
|
| 407 |
+
"step": 27000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.1360882398632905,
|
| 411 |
+
"grad_norm": 3.341671943664551,
|
| 412 |
+
"learning_rate": 5.759411734244732e-06,
|
| 413 |
+
"loss": 0.3992,
|
| 414 |
+
"step": 27500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.1749262078608047,
|
| 418 |
+
"grad_norm": 2.3136978149414062,
|
| 419 |
+
"learning_rate": 5.500491947594636e-06,
|
| 420 |
+
"loss": 0.4097,
|
| 421 |
+
"step": 28000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.2137641758583193,
|
| 425 |
+
"grad_norm": 2.660843849182129,
|
| 426 |
+
"learning_rate": 5.2415721609445406e-06,
|
| 427 |
+
"loss": 0.4059,
|
| 428 |
+
"step": 28500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.2526021438558335,
|
| 432 |
+
"grad_norm": 2.168541669845581,
|
| 433 |
+
"learning_rate": 4.982652374294444e-06,
|
| 434 |
+
"loss": 0.3995,
|
| 435 |
+
"step": 29000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.2914401118533476,
|
| 439 |
+
"grad_norm": 1.3290666341781616,
|
| 440 |
+
"learning_rate": 4.723732587644348e-06,
|
| 441 |
+
"loss": 0.4083,
|
| 442 |
+
"step": 29500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.330278079850862,
|
| 446 |
+
"grad_norm": 2.1573784351348877,
|
| 447 |
+
"learning_rate": 4.464812800994252e-06,
|
| 448 |
+
"loss": 0.3954,
|
| 449 |
+
"step": 30000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.369116047848377,
|
| 453 |
+
"grad_norm": 1.7208375930786133,
|
| 454 |
+
"learning_rate": 4.205893014344156e-06,
|
| 455 |
+
"loss": 0.401,
|
| 456 |
+
"step": 30500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.407954015845891,
|
| 460 |
+
"grad_norm": 2.6122512817382812,
|
| 461 |
+
"learning_rate": 3.9469732276940605e-06,
|
| 462 |
+
"loss": 0.3947,
|
| 463 |
+
"step": 31000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.446791983843405,
|
| 467 |
+
"grad_norm": 1.2965220212936401,
|
| 468 |
+
"learning_rate": 3.688053441043965e-06,
|
| 469 |
+
"loss": 0.3972,
|
| 470 |
+
"step": 31500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.4856299518409197,
|
| 474 |
+
"grad_norm": 2.537813186645508,
|
| 475 |
+
"learning_rate": 3.4291336543938693e-06,
|
| 476 |
+
"loss": 0.4117,
|
| 477 |
+
"step": 32000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.5244679198384343,
|
| 481 |
+
"grad_norm": 1.7891920804977417,
|
| 482 |
+
"learning_rate": 3.1702138677437734e-06,
|
| 483 |
+
"loss": 0.3911,
|
| 484 |
+
"step": 32500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.5633058878359485,
|
| 488 |
+
"grad_norm": 1.5513118505477905,
|
| 489 |
+
"learning_rate": 2.911294081093677e-06,
|
| 490 |
+
"loss": 0.392,
|
| 491 |
+
"step": 33000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.6021438558334626,
|
| 495 |
+
"grad_norm": 1.7818597555160522,
|
| 496 |
+
"learning_rate": 2.6523742944435813e-06,
|
| 497 |
+
"loss": 0.4004,
|
| 498 |
+
"step": 33500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.6409818238309772,
|
| 502 |
+
"grad_norm": 3.2013604640960693,
|
| 503 |
+
"learning_rate": 2.3934545077934855e-06,
|
| 504 |
+
"loss": 0.3873,
|
| 505 |
+
"step": 34000
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.6798197918284914,
|
| 509 |
+
"grad_norm": 1.8388571739196777,
|
| 510 |
+
"learning_rate": 2.13453472114339e-06,
|
| 511 |
+
"loss": 0.3905,
|
| 512 |
+
"step": 34500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.718657759826006,
|
| 516 |
+
"grad_norm": 1.5580964088439941,
|
| 517 |
+
"learning_rate": 1.8756149344932943e-06,
|
| 518 |
+
"loss": 0.399,
|
| 519 |
+
"step": 35000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.75749572782352,
|
| 523 |
+
"grad_norm": 1.9616905450820923,
|
| 524 |
+
"learning_rate": 1.6166951478431982e-06,
|
| 525 |
+
"loss": 0.3982,
|
| 526 |
+
"step": 35500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.7963336958210347,
|
| 530 |
+
"grad_norm": 1.4767934083938599,
|
| 531 |
+
"learning_rate": 1.3577753611931024e-06,
|
| 532 |
+
"loss": 0.4026,
|
| 533 |
+
"step": 36000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.835171663818549,
|
| 537 |
+
"grad_norm": 2.7453653812408447,
|
| 538 |
+
"learning_rate": 1.0988555745430067e-06,
|
| 539 |
+
"loss": 0.3974,
|
| 540 |
+
"step": 36500
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.8740096318160635,
|
| 544 |
+
"grad_norm": 1.8026459217071533,
|
| 545 |
+
"learning_rate": 8.399357878929108e-07,
|
| 546 |
+
"loss": 0.3922,
|
| 547 |
+
"step": 37000
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 2.9128475998135777,
|
| 551 |
+
"grad_norm": 2.550091505050659,
|
| 552 |
+
"learning_rate": 5.810160012428151e-07,
|
| 553 |
+
"loss": 0.3864,
|
| 554 |
+
"step": 37500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.9516855678110923,
|
| 558 |
+
"grad_norm": 1.742976427078247,
|
| 559 |
+
"learning_rate": 3.2209621459271923e-07,
|
| 560 |
+
"loss": 0.393,
|
| 561 |
+
"step": 38000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.9905235358086064,
|
| 565 |
+
"grad_norm": 1.7563802003860474,
|
| 566 |
+
"learning_rate": 6.317642794262338e-08,
|
| 567 |
+
"loss": 0.4036,
|
| 568 |
+
"step": 38500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.0,
|
| 572 |
+
"eval_AUC": 0.924,
|
| 573 |
+
"eval_Accuracy": 0.877,
|
| 574 |
+
"eval_loss": 0.342347651720047,
|
| 575 |
+
"eval_runtime": 10030.6709,
|
| 576 |
+
"eval_samples_per_second": 2.282,
|
| 577 |
+
"eval_steps_per_second": 0.143,
|
| 578 |
+
"step": 38622
|
| 579 |
+
}
|
| 580 |
+
],
|
| 581 |
+
"logging_steps": 500,
|
| 582 |
+
"max_steps": 38622,
|
| 583 |
+
"num_input_tokens_seen": 0,
|
| 584 |
+
"num_train_epochs": 3,
|
| 585 |
+
"save_steps": 500,
|
| 586 |
+
"stateful_callbacks": {
|
| 587 |
+
"TrainerControl": {
|
| 588 |
+
"args": {
|
| 589 |
+
"should_epoch_stop": false,
|
| 590 |
+
"should_evaluate": false,
|
| 591 |
+
"should_log": false,
|
| 592 |
+
"should_save": true,
|
| 593 |
+
"should_training_stop": true
|
| 594 |
+
},
|
| 595 |
+
"attributes": {}
|
| 596 |
+
}
|
| 597 |
+
},
|
| 598 |
+
"total_flos": 5.7585530030218445e+17,
|
| 599 |
+
"train_batch_size": 16,
|
| 600 |
+
"trial_name": null,
|
| 601 |
+
"trial_params": null
|
| 602 |
+
}
|
checkpoint-38622/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef81828047111fb8469f346d2515430f70d6821251e87dd33c6c643512ff318
|
| 3 |
+
size 5368
|
checkpoint-38622/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ealvaradob/bert-finetuned-phishing",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Safe",
|
| 14 |
+
"1": "Not Safe"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"Not Safe": 1,
|
| 20 |
+
"Safe": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.49.0",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 30522
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba3c2727fcc23a9001aab178b34a1ce73252b99bb58532e714eefe58721bdddd
|
| 3 |
+
size 1340622760
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef81828047111fb8469f346d2515430f70d6821251e87dd33c6c643512ff318
|
| 3 |
+
size 5368
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|