Upload folder using huggingface_hub
Browse files- README.md +26 -0
- checkpoint-6/config.json +34 -0
- checkpoint-6/model.safetensors +3 -0
- checkpoint-6/optimizer.pt +3 -0
- checkpoint-6/rng_state.pth +3 -0
- checkpoint-6/scheduler.pt +3 -0
- checkpoint-6/trainer_state.json +123 -0
- checkpoint-6/training_args.bin +3 -0
- config.json +34 -0
- model.safetensors +3 -0
- runs/Sep23_15-41-51_r-tomicg1-dumatrain-2e9t8w7l-2b33a-wdw2q/events.out.tfevents.1727106112.r-tomicg1-dumatrain-2e9t8w7l-2b33a-wdw2q.152.0 +2 -2
- runs/Sep23_15-41-51_r-tomicg1-dumatrain-2e9t8w7l-2b33a-wdw2q/events.out.tfevents.1727106130.r-tomicg1-dumatrain-2e9t8w7l-2b33a-wdw2q.152.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: distilbert/distilbert-base-uncased
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Text Classification
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 0.6297385692596436
|
17 |
+
|
18 |
+
f1: 0.0
|
19 |
+
|
20 |
+
precision: 0.0
|
21 |
+
|
22 |
+
recall: 0.0
|
23 |
+
|
24 |
+
auc: 0.5
|
25 |
+
|
26 |
+
accuracy: 0.6666666666666666
|
checkpoint-6/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForSequenceClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": " efectivo\"",
|
14 |
+
"1": " transferencia\""
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
" efectivo\"": 0,
|
19 |
+
" transferencia\"": 1
|
20 |
+
},
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "distilbert",
|
23 |
+
"n_heads": 12,
|
24 |
+
"n_layers": 6,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"problem_type": "single_label_classification",
|
27 |
+
"qa_dropout": 0.1,
|
28 |
+
"seq_classif_dropout": 0.2,
|
29 |
+
"sinusoidal_pos_embds": false,
|
30 |
+
"tie_weights_": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.44.2",
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
checkpoint-6/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:025931ccd664b0a8a321c429b88486020ecd6b4b336c09fad2e2f0939c0b656c
|
3 |
+
size 267832560
|
checkpoint-6/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad56a6bf0047f98119d861c25855b86f0609c95f8ecb6f454d8652b4279767c9
|
3 |
+
size 535724410
|
checkpoint-6/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3044572c68786ace002a23f2b666810b1947f579bf5d8e46512ec0d4bddeb3e4
|
3 |
+
size 13990
|
checkpoint-6/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a507d9cafa2419d0ab9d8bfd3d73565df3d210c7e1a2b8ba116f25efdab63f1
|
3 |
+
size 1064
|
checkpoint-6/trainer_state.json
ADDED
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6297385692596436,
|
3 |
+
"best_model_checkpoint": "autotrain-7ftvs-r0ee5/checkpoint-6",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.5,
|
13 |
+
"grad_norm": 1.1981409788131714,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 0.6949,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"grad_norm": 2.4536054134368896,
|
21 |
+
"learning_rate": 4e-05,
|
22 |
+
"loss": 0.6533,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"eval_accuracy": 0.6666666666666666,
|
28 |
+
"eval_auc": 0.5,
|
29 |
+
"eval_f1": 0.0,
|
30 |
+
"eval_loss": 0.6630359292030334,
|
31 |
+
"eval_precision": 0.0,
|
32 |
+
"eval_recall": 0.0,
|
33 |
+
"eval_runtime": 0.2868,
|
34 |
+
"eval_samples_per_second": 10.459,
|
35 |
+
"eval_steps_per_second": 3.486,
|
36 |
+
"step": 2
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.5,
|
40 |
+
"grad_norm": 1.474059820175171,
|
41 |
+
"learning_rate": 3e-05,
|
42 |
+
"loss": 0.6694,
|
43 |
+
"step": 3
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 2.0,
|
47 |
+
"grad_norm": 2.559450149536133,
|
48 |
+
"learning_rate": 2e-05,
|
49 |
+
"loss": 0.663,
|
50 |
+
"step": 4
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.0,
|
54 |
+
"eval_accuracy": 0.6666666666666666,
|
55 |
+
"eval_auc": 0.5,
|
56 |
+
"eval_f1": 0.0,
|
57 |
+
"eval_loss": 0.6429774761199951,
|
58 |
+
"eval_precision": 0.0,
|
59 |
+
"eval_recall": 0.0,
|
60 |
+
"eval_runtime": 0.2796,
|
61 |
+
"eval_samples_per_second": 10.729,
|
62 |
+
"eval_steps_per_second": 3.576,
|
63 |
+
"step": 4
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.5,
|
67 |
+
"grad_norm": 1.582867980003357,
|
68 |
+
"learning_rate": 1e-05,
|
69 |
+
"loss": 0.6843,
|
70 |
+
"step": 5
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 3.0,
|
74 |
+
"grad_norm": 3.4363346099853516,
|
75 |
+
"learning_rate": 0.0,
|
76 |
+
"loss": 0.7342,
|
77 |
+
"step": 6
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 3.0,
|
81 |
+
"eval_accuracy": 0.6666666666666666,
|
82 |
+
"eval_auc": 0.5,
|
83 |
+
"eval_f1": 0.0,
|
84 |
+
"eval_loss": 0.6297385692596436,
|
85 |
+
"eval_precision": 0.0,
|
86 |
+
"eval_recall": 0.0,
|
87 |
+
"eval_runtime": 0.2889,
|
88 |
+
"eval_samples_per_second": 10.385,
|
89 |
+
"eval_steps_per_second": 3.462,
|
90 |
+
"step": 6
|
91 |
+
}
|
92 |
+
],
|
93 |
+
"logging_steps": 1,
|
94 |
+
"max_steps": 6,
|
95 |
+
"num_input_tokens_seen": 0,
|
96 |
+
"num_train_epochs": 3,
|
97 |
+
"save_steps": 500,
|
98 |
+
"stateful_callbacks": {
|
99 |
+
"EarlyStoppingCallback": {
|
100 |
+
"args": {
|
101 |
+
"early_stopping_patience": 5,
|
102 |
+
"early_stopping_threshold": 0.01
|
103 |
+
},
|
104 |
+
"attributes": {
|
105 |
+
"early_stopping_patience_counter": 0
|
106 |
+
}
|
107 |
+
},
|
108 |
+
"TrainerControl": {
|
109 |
+
"args": {
|
110 |
+
"should_epoch_stop": false,
|
111 |
+
"should_evaluate": false,
|
112 |
+
"should_log": false,
|
113 |
+
"should_save": true,
|
114 |
+
"should_training_stop": true
|
115 |
+
},
|
116 |
+
"attributes": {}
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"total_flos": 1092856038912.0,
|
120 |
+
"train_batch_size": 8,
|
121 |
+
"trial_name": null,
|
122 |
+
"trial_params": null
|
123 |
+
}
|
checkpoint-6/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5d2555d5b437bdd2440440829b9568a792894ff16a71da8a016a7be907c21a8
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForSequenceClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": " efectivo\"",
|
14 |
+
"1": " transferencia\""
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
" efectivo\"": 0,
|
19 |
+
" transferencia\"": 1
|
20 |
+
},
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "distilbert",
|
23 |
+
"n_heads": 12,
|
24 |
+
"n_layers": 6,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"problem_type": "single_label_classification",
|
27 |
+
"qa_dropout": 0.1,
|
28 |
+
"seq_classif_dropout": 0.2,
|
29 |
+
"sinusoidal_pos_embds": false,
|
30 |
+
"tie_weights_": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.44.2",
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:025931ccd664b0a8a321c429b88486020ecd6b4b336c09fad2e2f0939c0b656c
|
3 |
+
size 267832560
|
runs/Sep23_15-41-51_r-tomicg1-dumatrain-2e9t8w7l-2b33a-wdw2q/events.out.tfevents.1727106112.r-tomicg1-dumatrain-2e9t8w7l-2b33a-wdw2q.152.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94ac4e5de3524559f28a09eaaefa6c96b2c72bcfbf97f578314c9f41efa2e48e
|
3 |
+
size 8111
|
runs/Sep23_15-41-51_r-tomicg1-dumatrain-2e9t8w7l-2b33a-wdw2q/events.out.tfevents.1727106130.r-tomicg1-dumatrain-2e9t8w7l-2b33a-wdw2q.152.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d34194fc5b10f49843ed9c69e63281a517da31aa7c0f744d8213eeaf2b1c01ad
|
3 |
+
size 597
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5d2555d5b437bdd2440440829b9568a792894ff16a71da8a016a7be907c21a8
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-7ftvs-r0ee5/autotrain-data",
|
3 |
+
"model": "distilbert/distilbert-base-uncased",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "autotrain-7ftvs-r0ee5",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "tomicg1",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|