Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-100/config.json +36 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/pytorch_model.bin +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +149 -0
- checkpoint-100/training_args.bin +3 -0
- config.json +36 -0
- pytorch_model.bin +3 -0
- runs/Aug15_14-02-10_s-abhishek-autotrain-pvtx-agdd-0n1w-1-ad313-5f8d5b7d97-zsv4f/events.out.tfevents.1692108130.s-abhishek-autotrain-pvtx-agdd-0n1w-1-ad313-5f8d5b7d97-zsv4f.114.0 +3 -0
- runs/Aug15_14-02-10_s-abhishek-autotrain-pvtx-agdd-0n1w-1-ad313-5f8d5b7d97-zsv4f/events.out.tfevents.1692108176.s-abhishek-autotrain-pvtx-agdd-0n1w-1-ad313-5f8d5b7d97-zsv4f.114.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
- training_params.json +1 -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 |
+
- abhishek/autotrain-data-pvtx-agdd-0n1w
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.39582160115242004
|
18 |
+
|
19 |
+
f1: 0.8533333333333333
|
20 |
+
|
21 |
+
precision: 0.768
|
22 |
+
|
23 |
+
recall: 0.96
|
24 |
+
|
25 |
+
auc: 0.9411999999999999
|
26 |
+
|
27 |
+
accuracy: 0.835
|
checkpoint-100/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
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": "negative",
|
15 |
+
"1": "positive"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"negative": 0,
|
21 |
+
"positive": 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": "4.31.0",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7eda2810e05a82403ea6fceceddd4571d4549261b1da56a7220620216098324c
|
3 |
+
size 876037893
|
checkpoint-100/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dafa3560774b1999d2f59cb4adb423e712dad48c37980986362ef65630297b85
|
3 |
+
size 438003505
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7cae3153e858c89373bc02f4d541a5c908a1a786b400124233041099dba2875
|
3 |
+
size 14575
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:475abedcc89c4a580e84a248c324fef5b1419ab3ad659bfd8daf49b58f179fee
|
3 |
+
size 627
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.39582160115242004,
|
3 |
+
"best_model_checkpoint": "output/checkpoint-100",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 100,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.05,
|
12 |
+
"learning_rate": 8.333333333333334e-06,
|
13 |
+
"loss": 0.7359,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.1,
|
18 |
+
"learning_rate": 1.6666666666666667e-05,
|
19 |
+
"loss": 0.7009,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.15,
|
24 |
+
"learning_rate": 2.5e-05,
|
25 |
+
"loss": 0.6794,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.2,
|
30 |
+
"learning_rate": 3.3333333333333335e-05,
|
31 |
+
"loss": 0.6755,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.25,
|
36 |
+
"learning_rate": 4.166666666666667e-05,
|
37 |
+
"loss": 0.6509,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.3,
|
42 |
+
"learning_rate": 5e-05,
|
43 |
+
"loss": 0.6442,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.35,
|
48 |
+
"learning_rate": 4.9074074074074075e-05,
|
49 |
+
"loss": 0.5768,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.4,
|
54 |
+
"learning_rate": 4.814814814814815e-05,
|
55 |
+
"loss": 0.6882,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.45,
|
60 |
+
"learning_rate": 4.722222222222222e-05,
|
61 |
+
"loss": 0.6102,
|
62 |
+
"step": 45
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.5,
|
66 |
+
"learning_rate": 4.62962962962963e-05,
|
67 |
+
"loss": 0.5241,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.55,
|
72 |
+
"learning_rate": 4.5370370370370374e-05,
|
73 |
+
"loss": 0.6044,
|
74 |
+
"step": 55
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.6,
|
78 |
+
"learning_rate": 4.4444444444444447e-05,
|
79 |
+
"loss": 1.0186,
|
80 |
+
"step": 60
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.65,
|
84 |
+
"learning_rate": 4.351851851851852e-05,
|
85 |
+
"loss": 0.6259,
|
86 |
+
"step": 65
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.7,
|
90 |
+
"learning_rate": 4.259259259259259e-05,
|
91 |
+
"loss": 0.5959,
|
92 |
+
"step": 70
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.75,
|
96 |
+
"learning_rate": 4.166666666666667e-05,
|
97 |
+
"loss": 0.5036,
|
98 |
+
"step": 75
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.8,
|
102 |
+
"learning_rate": 4.074074074074074e-05,
|
103 |
+
"loss": 0.3528,
|
104 |
+
"step": 80
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.85,
|
108 |
+
"learning_rate": 3.981481481481482e-05,
|
109 |
+
"loss": 0.5124,
|
110 |
+
"step": 85
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.9,
|
114 |
+
"learning_rate": 3.888888888888889e-05,
|
115 |
+
"loss": 0.4032,
|
116 |
+
"step": 90
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.95,
|
120 |
+
"learning_rate": 3.7962962962962964e-05,
|
121 |
+
"loss": 0.3113,
|
122 |
+
"step": 95
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.0,
|
126 |
+
"learning_rate": 3.7037037037037037e-05,
|
127 |
+
"loss": 0.4913,
|
128 |
+
"step": 100
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.0,
|
132 |
+
"eval_accuracy": 0.835,
|
133 |
+
"eval_auc": 0.9411999999999999,
|
134 |
+
"eval_f1": 0.8533333333333333,
|
135 |
+
"eval_loss": 0.39582160115242004,
|
136 |
+
"eval_precision": 0.768,
|
137 |
+
"eval_recall": 0.96,
|
138 |
+
"eval_runtime": 0.9665,
|
139 |
+
"eval_samples_per_second": 206.925,
|
140 |
+
"eval_steps_per_second": 13.45,
|
141 |
+
"step": 100
|
142 |
+
}
|
143 |
+
],
|
144 |
+
"max_steps": 300,
|
145 |
+
"num_train_epochs": 3,
|
146 |
+
"total_flos": 105244422144000.0,
|
147 |
+
"trial_name": null,
|
148 |
+
"trial_params": null
|
149 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfade3cb0c4ce71f81d5ef43e19b18ec7b8546ee7bb7f1226303af1015eedb20
|
3 |
+
size 4027
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
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": "negative",
|
15 |
+
"1": "positive"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"negative": 0,
|
21 |
+
"positive": 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": "4.31.0",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dafa3560774b1999d2f59cb4adb423e712dad48c37980986362ef65630297b85
|
3 |
+
size 438003505
|
runs/Aug15_14-02-10_s-abhishek-autotrain-pvtx-agdd-0n1w-1-ad313-5f8d5b7d97-zsv4f/events.out.tfevents.1692108130.s-abhishek-autotrain-pvtx-agdd-0n1w-1-ad313-5f8d5b7d97-zsv4f.114.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42d751b4a16a035bc1ff333071d834114879959f5c50c4e3aaad1bf4e6afa983
|
3 |
+
size 15443
|
runs/Aug15_14-02-10_s-abhishek-autotrain-pvtx-agdd-0n1w-1-ad313-5f8d5b7d97-zsv4f/events.out.tfevents.1692108176.s-abhishek-autotrain-pvtx-agdd-0n1w-1-ad313-5f8d5b7d97-zsv4f.114.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3e8679fcdcc0b4c1de0878957e2454136db2f706f4427384656b01617a2b6b9
|
3 |
+
size 607
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfade3cb0c4ce71f81d5ef43e19b18ec7b8546ee7bb7f1226303af1015eedb20
|
3 |
+
size 4027
|
training_params.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"data_path": "abhishek/autotrain-data-pvtx-agdd-0n1w", "model_name": "bert-base-uncased", "lr": 5e-05, "epochs": 3, "max_seq_length": 256, "batch_size": 8, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "train_split": "train", "valid_split": "validation", "text_column": "autotrain_text", "target_column": "autotrain_label", "logging_steps": -1, "project_name": "output", "auto_find_batch_size": false, "fp16": false, "save_total_limit": 1, "save_strategy": "epoch", "push_to_hub": true, "repo_id": "abhishek/autotrain-pvtx-agdd-0n1w-1", "evaluation_strategy": "epoch"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|