Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-6/config.json +36 -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 +102 -0
- checkpoint-6/training_args.bin +3 -0
- config.json +36 -0
- model.safetensors +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 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
widget:
|
7 |
+
- text: "I love AutoTrain"
|
8 |
+
datasets:
|
9 |
+
- autotrain-s2tfh-shivj5l/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.5295487642288208
|
18 |
+
|
19 |
+
f1: 0.0
|
20 |
+
|
21 |
+
precision: 0.0
|
22 |
+
|
23 |
+
recall: 0.0
|
24 |
+
|
25 |
+
auc: 1.0
|
26 |
+
|
27 |
+
accuracy: 0.75
|
checkpoint-6/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-cased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": 0,
|
15 |
+
"1": 1
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"0": 0,
|
21 |
+
"1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.39.0",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
checkpoint-6/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8e98ffcdb1486a434d3c3954d3c133bb70d736f8a1b4ffc21c6a8771c8b6da
|
3 |
+
size 433270768
|
checkpoint-6/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11b4d5bc70b86671de272b8e3fd8bcadd60141d461522abefcbcb25cb520c291
|
3 |
+
size 866657018
|
checkpoint-6/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d54deb19a80fe4a7334a91521943effdfefc73bac4323479fcaf43be23ea9c22
|
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 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5295487642288208,
|
3 |
+
"best_model_checkpoint": "autotrain-s2tfh-shivj5l/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": 7.717057704925537,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 0.5474,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"grad_norm": 3.8525986671447754,
|
21 |
+
"learning_rate": 4e-05,
|
22 |
+
"loss": 0.6347,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"eval_accuracy": 0.75,
|
28 |
+
"eval_auc": 0.33333333333333337,
|
29 |
+
"eval_f1": 0.0,
|
30 |
+
"eval_loss": 0.5581548810005188,
|
31 |
+
"eval_precision": 0.0,
|
32 |
+
"eval_recall": 0.0,
|
33 |
+
"eval_runtime": 0.7982,
|
34 |
+
"eval_samples_per_second": 5.011,
|
35 |
+
"eval_steps_per_second": 1.253,
|
36 |
+
"step": 2
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.5,
|
40 |
+
"grad_norm": 4.873136043548584,
|
41 |
+
"learning_rate": 3e-05,
|
42 |
+
"loss": 0.4156,
|
43 |
+
"step": 3
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 2.0,
|
47 |
+
"grad_norm": 5.227407455444336,
|
48 |
+
"learning_rate": 2e-05,
|
49 |
+
"loss": 0.6143,
|
50 |
+
"step": 4
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.0,
|
54 |
+
"eval_accuracy": 0.75,
|
55 |
+
"eval_auc": 1.0,
|
56 |
+
"eval_f1": 0.0,
|
57 |
+
"eval_loss": 0.5400429964065552,
|
58 |
+
"eval_precision": 0.0,
|
59 |
+
"eval_recall": 0.0,
|
60 |
+
"eval_runtime": 0.9043,
|
61 |
+
"eval_samples_per_second": 4.423,
|
62 |
+
"eval_steps_per_second": 1.106,
|
63 |
+
"step": 4
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.5,
|
67 |
+
"grad_norm": 4.113026142120361,
|
68 |
+
"learning_rate": 1e-05,
|
69 |
+
"loss": 0.4983,
|
70 |
+
"step": 5
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 3.0,
|
74 |
+
"grad_norm": 4.6406941413879395,
|
75 |
+
"learning_rate": 0.0,
|
76 |
+
"loss": 0.4676,
|
77 |
+
"step": 6
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 3.0,
|
81 |
+
"eval_accuracy": 0.75,
|
82 |
+
"eval_auc": 1.0,
|
83 |
+
"eval_f1": 0.0,
|
84 |
+
"eval_loss": 0.5295487642288208,
|
85 |
+
"eval_precision": 0.0,
|
86 |
+
"eval_recall": 0.0,
|
87 |
+
"eval_runtime": 0.8354,
|
88 |
+
"eval_samples_per_second": 4.788,
|
89 |
+
"eval_steps_per_second": 1.197,
|
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 |
+
"total_flos": 3157332664320.0,
|
99 |
+
"train_batch_size": 8,
|
100 |
+
"trial_name": null,
|
101 |
+
"trial_params": null
|
102 |
+
}
|
checkpoint-6/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fec2bae08a15702bbd33fae6549cab2454bcbcc5c1dc4b8bc2bd4addb9f7ad08
|
3 |
+
size 4984
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-cased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": 0,
|
15 |
+
"1": 1
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"0": 0,
|
21 |
+
"1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.39.0",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8e98ffcdb1486a434d3c3954d3c133bb70d736f8a1b4ffc21c6a8771c8b6da
|
3 |
+
size 433270768
|
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": false,
|
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": "BertTokenizer",
|
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:fec2bae08a15702bbd33fae6549cab2454bcbcc5c1dc4b8bc2bd4addb9f7ad08
|
3 |
+
size 4984
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-s2tfh-shivj5l/autotrain-data",
|
3 |
+
"model": "google-bert/bert-base-cased",
|
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-s2tfh-shivj5l",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": null,
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"save_strategy": "epoch",
|
25 |
+
"push_to_hub": true,
|
26 |
+
"repo_id": "shiv2050/autotrain-s2tfh-shivj5l",
|
27 |
+
"evaluation_strategy": "epoch",
|
28 |
+
"username": "shiv2050",
|
29 |
+
"log": "none"
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|