CamiloVega
commited on
Commit
•
be97bea
1
Parent(s):
d29dc56
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-12/config.json +38 -0
- checkpoint-12/model.safetensors +3 -0
- checkpoint-12/optimizer.pt +3 -0
- checkpoint-12/rng_state.pth +3 -0
- checkpoint-12/scheduler.pt +3 -0
- checkpoint-12/trainer_state.json +141 -0
- checkpoint-12/training_args.bin +3 -0
- config.json +38 -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 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
widget:
|
7 |
+
- text: "I love AutoTrain"
|
8 |
+
datasets:
|
9 |
+
- autotrain-Tweet-Classifier/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 1.1234140396118164
|
18 |
+
|
19 |
+
f1_macro: 0.17777777777777778
|
20 |
+
|
21 |
+
f1_micro: 0.36363636363636365
|
22 |
+
|
23 |
+
f1_weighted: 0.19393939393939394
|
24 |
+
|
25 |
+
precision_macro: 0.12121212121212122
|
26 |
+
|
27 |
+
precision_micro: 0.36363636363636365
|
28 |
+
|
29 |
+
precision_weighted: 0.1322314049586777
|
30 |
+
|
31 |
+
recall_macro: 0.3333333333333333
|
32 |
+
|
33 |
+
recall_micro: 0.36363636363636365
|
34 |
+
|
35 |
+
recall_weighted: 0.36363636363636365
|
36 |
+
|
37 |
+
accuracy: 0.36363636363636365
|
checkpoint-12/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 3,
|
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": "Negativo",
|
15 |
+
"1": "Neutral",
|
16 |
+
"2": "Positivo"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"Negativo": 0,
|
22 |
+
"Neutral": 1,
|
23 |
+
"Positivo": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.38.0",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 30522
|
38 |
+
}
|
checkpoint-12/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81d197159069386f87fb4c7a88524c9cc94e17d586594f75e2695895b35664c5
|
3 |
+
size 437961724
|
checkpoint-12/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44aa1fe4707693443a04338f9b6c4571dbe2c4d513157556fc0f27792a2ab262
|
3 |
+
size 876038906
|
checkpoint-12/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5900070e851429e17b164d3847bb2a62480b49110d0593f412e9cc25b7c62c3a
|
3 |
+
size 13990
|
checkpoint-12/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:703eea4812f54e382130b8a6015717e2bb1c7f3f2350cf0fe7194a916ceb8c5d
|
3 |
+
size 1064
|
checkpoint-12/trainer_state.json
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.1234140396118164,
|
3 |
+
"best_model_checkpoint": "autotrain-Tweet-Classifier/checkpoint-12",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 12,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.17,
|
13 |
+
"grad_norm": 12.977298736572266,
|
14 |
+
"learning_rate": 2.5e-05,
|
15 |
+
"loss": 1.0989,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.33,
|
20 |
+
"grad_norm": 5.110796928405762,
|
21 |
+
"learning_rate": 5e-05,
|
22 |
+
"loss": 1.0898,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5,
|
27 |
+
"grad_norm": 6.790207862854004,
|
28 |
+
"learning_rate": 4.6875e-05,
|
29 |
+
"loss": 0.9728,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.67,
|
34 |
+
"grad_norm": 9.658609390258789,
|
35 |
+
"learning_rate": 4.375e-05,
|
36 |
+
"loss": 1.3658,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.83,
|
41 |
+
"grad_norm": 9.872339248657227,
|
42 |
+
"learning_rate": 4.0625000000000005e-05,
|
43 |
+
"loss": 1.3639,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0,
|
48 |
+
"grad_norm": 17.13404655456543,
|
49 |
+
"learning_rate": 3.7500000000000003e-05,
|
50 |
+
"loss": 1.5233,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.0,
|
55 |
+
"eval_accuracy": 0.36363636363636365,
|
56 |
+
"eval_f1_macro": 0.17777777777777778,
|
57 |
+
"eval_f1_micro": 0.36363636363636365,
|
58 |
+
"eval_f1_weighted": 0.19393939393939394,
|
59 |
+
"eval_loss": 1.1655577421188354,
|
60 |
+
"eval_precision_macro": 0.12121212121212122,
|
61 |
+
"eval_precision_micro": 0.36363636363636365,
|
62 |
+
"eval_precision_weighted": 0.1322314049586777,
|
63 |
+
"eval_recall_macro": 0.3333333333333333,
|
64 |
+
"eval_recall_micro": 0.36363636363636365,
|
65 |
+
"eval_recall_weighted": 0.36363636363636365,
|
66 |
+
"eval_runtime": 2.0574,
|
67 |
+
"eval_samples_per_second": 5.346,
|
68 |
+
"eval_steps_per_second": 0.486,
|
69 |
+
"step": 6
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 1.17,
|
73 |
+
"grad_norm": 15.478323936462402,
|
74 |
+
"learning_rate": 3.4375e-05,
|
75 |
+
"loss": 1.2839,
|
76 |
+
"step": 7
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 1.33,
|
80 |
+
"grad_norm": 8.981595039367676,
|
81 |
+
"learning_rate": 3.125e-05,
|
82 |
+
"loss": 1.1181,
|
83 |
+
"step": 8
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.5,
|
87 |
+
"grad_norm": 8.584152221679688,
|
88 |
+
"learning_rate": 2.8125000000000003e-05,
|
89 |
+
"loss": 1.166,
|
90 |
+
"step": 9
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 1.67,
|
94 |
+
"grad_norm": 4.148137092590332,
|
95 |
+
"learning_rate": 2.5e-05,
|
96 |
+
"loss": 1.0376,
|
97 |
+
"step": 10
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 1.83,
|
101 |
+
"grad_norm": 5.527700424194336,
|
102 |
+
"learning_rate": 2.1875e-05,
|
103 |
+
"loss": 0.9684,
|
104 |
+
"step": 11
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.0,
|
108 |
+
"grad_norm": 17.105709075927734,
|
109 |
+
"learning_rate": 1.8750000000000002e-05,
|
110 |
+
"loss": 0.7871,
|
111 |
+
"step": 12
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.0,
|
115 |
+
"eval_accuracy": 0.36363636363636365,
|
116 |
+
"eval_f1_macro": 0.17777777777777778,
|
117 |
+
"eval_f1_micro": 0.36363636363636365,
|
118 |
+
"eval_f1_weighted": 0.19393939393939394,
|
119 |
+
"eval_loss": 1.1234140396118164,
|
120 |
+
"eval_precision_macro": 0.12121212121212122,
|
121 |
+
"eval_precision_micro": 0.36363636363636365,
|
122 |
+
"eval_precision_weighted": 0.1322314049586777,
|
123 |
+
"eval_recall_macro": 0.3333333333333333,
|
124 |
+
"eval_recall_micro": 0.36363636363636365,
|
125 |
+
"eval_recall_weighted": 0.36363636363636365,
|
126 |
+
"eval_runtime": 2.0537,
|
127 |
+
"eval_samples_per_second": 5.356,
|
128 |
+
"eval_steps_per_second": 0.487,
|
129 |
+
"step": 12
|
130 |
+
}
|
131 |
+
],
|
132 |
+
"logging_steps": 1,
|
133 |
+
"max_steps": 18,
|
134 |
+
"num_input_tokens_seen": 0,
|
135 |
+
"num_train_epochs": 3,
|
136 |
+
"save_steps": 500,
|
137 |
+
"total_flos": 5788495190016.0,
|
138 |
+
"train_batch_size": 8,
|
139 |
+
"trial_name": null,
|
140 |
+
"trial_params": null
|
141 |
+
}
|
checkpoint-12/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f5639698c814fcd9f464d4f41578b56259e485785de4fa85adfa12ccaeb357e
|
3 |
+
size 4920
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 3,
|
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": "Negativo",
|
15 |
+
"1": "Neutral",
|
16 |
+
"2": "Positivo"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"Negativo": 0,
|
22 |
+
"Neutral": 1,
|
23 |
+
"Positivo": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.38.0",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 30522
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81d197159069386f87fb4c7a88524c9cc94e17d586594f75e2695895b35664c5
|
3 |
+
size 437961724
|
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": "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 sha256:2f5639698c814fcd9f464d4f41578b56259e485785de4fa85adfa12ccaeb357e
|
3 |
+
size 4920
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-Tweet-Classifier/autotrain-data",
|
3 |
+
"model": "google-bert/bert-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-Tweet-Classifier",
|
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": "CamiloVega/autotrain-Tweet-Classifier",
|
27 |
+
"evaluation_strategy": "epoch",
|
28 |
+
"username": "CamiloVega",
|
29 |
+
"log": "none"
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|