Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-28212/config.json +59 -0
- checkpoint-28212/model.safetensors +3 -0
- checkpoint-28212/optimizer.pt +3 -0
- checkpoint-28212/rng_state.pth +3 -0
- checkpoint-28212/scheduler.pt +3 -0
- checkpoint-28212/trainer_state.json +495 -0
- checkpoint-28212/training_args.bin +3 -0
- config.json +59 -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 |
+
- bert-toc-classification-95k/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.5102838277816772
|
18 |
+
|
19 |
+
f1_macro: 0.605011586308457
|
20 |
+
|
21 |
+
f1_micro: 0.8910038281582305
|
22 |
+
|
23 |
+
f1_weighted: 0.8870714364293508
|
24 |
+
|
25 |
+
precision_macro: 0.6869883411452264
|
26 |
+
|
27 |
+
precision_micro: 0.8910038281582305
|
28 |
+
|
29 |
+
precision_weighted: 0.8858066104824025
|
30 |
+
|
31 |
+
recall_macro: 0.5550753643871188
|
32 |
+
|
33 |
+
recall_micro: 0.8910038281582305
|
34 |
+
|
35 |
+
recall_weighted: 0.8910038281582305
|
36 |
+
|
37 |
+
accuracy: 0.8910038281582305
|
checkpoint-28212/config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-multilingual-cased",
|
3 |
+
"_num_labels": 11,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": 0,
|
15 |
+
"1": 1,
|
16 |
+
"2": 2,
|
17 |
+
"3": 3,
|
18 |
+
"4": 4,
|
19 |
+
"5": 5,
|
20 |
+
"6": 6,
|
21 |
+
"7": 7,
|
22 |
+
"8": 8,
|
23 |
+
"9": 9,
|
24 |
+
"10": 10
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"0": 0,
|
30 |
+
"1": 1,
|
31 |
+
"2": 2,
|
32 |
+
"3": 3,
|
33 |
+
"4": 4,
|
34 |
+
"5": 5,
|
35 |
+
"6": 6,
|
36 |
+
"7": 7,
|
37 |
+
"8": 8,
|
38 |
+
"9": 9,
|
39 |
+
"10": 10
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-12,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "bert",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"pooler_fc_size": 768,
|
48 |
+
"pooler_num_attention_heads": 12,
|
49 |
+
"pooler_num_fc_layers": 3,
|
50 |
+
"pooler_size_per_head": 128,
|
51 |
+
"pooler_type": "first_token_transform",
|
52 |
+
"position_embedding_type": "absolute",
|
53 |
+
"problem_type": "single_label_classification",
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.38.2",
|
56 |
+
"type_vocab_size": 2,
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 119547
|
59 |
+
}
|
checkpoint-28212/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea42433a66192fafb34d42228d32b817da608c47db2a7bd785bb25b50818a4e9
|
3 |
+
size 711471148
|
checkpoint-28212/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe20c55315e2c05b2a2adda99f48ac05e5ab7b664cbae04895bffb9e1cb76e8b
|
3 |
+
size 1423063290
|
checkpoint-28212/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a31a9a170891f40e07b29db582053bd25bc0bbcf34d8a745995d0637b96079c1
|
3 |
+
size 14244
|
checkpoint-28212/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e8d4493168547bf202fe8b7e872049f12a91ed55c0e69539ed76a6046772c76
|
3 |
+
size 1064
|
checkpoint-28212/trainer_state.json
ADDED
@@ -0,0 +1,495 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5102838277816772,
|
3 |
+
"best_model_checkpoint": "bert-toc-classification-95k/checkpoint-28212",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 28212,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05,
|
13 |
+
"grad_norm": 10.0037260055542,
|
14 |
+
"learning_rate": 8.2388377037562e-06,
|
15 |
+
"loss": 1.488,
|
16 |
+
"step": 470
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.1,
|
20 |
+
"grad_norm": 21.113529205322266,
|
21 |
+
"learning_rate": 1.6566265060240965e-05,
|
22 |
+
"loss": 0.8951,
|
23 |
+
"step": 940
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.15,
|
27 |
+
"grad_norm": 22.580860137939453,
|
28 |
+
"learning_rate": 2.489369241672573e-05,
|
29 |
+
"loss": 0.8119,
|
30 |
+
"step": 1410
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2,
|
34 |
+
"grad_norm": 7.799249172210693,
|
35 |
+
"learning_rate": 3.3221119773210494e-05,
|
36 |
+
"loss": 0.7839,
|
37 |
+
"step": 1880
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.25,
|
41 |
+
"grad_norm": 2.7983133792877197,
|
42 |
+
"learning_rate": 4.154854712969525e-05,
|
43 |
+
"loss": 0.8125,
|
44 |
+
"step": 2350
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3,
|
48 |
+
"grad_norm": 8.185538291931152,
|
49 |
+
"learning_rate": 4.9875974486180016e-05,
|
50 |
+
"loss": 0.8436,
|
51 |
+
"step": 2820
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.35,
|
55 |
+
"grad_norm": 27.348609924316406,
|
56 |
+
"learning_rate": 4.90882237101221e-05,
|
57 |
+
"loss": 0.7903,
|
58 |
+
"step": 3290
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.4,
|
62 |
+
"grad_norm": 5.916811466217041,
|
63 |
+
"learning_rate": 4.816266246553762e-05,
|
64 |
+
"loss": 0.72,
|
65 |
+
"step": 3760
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.45,
|
69 |
+
"grad_norm": 5.276752471923828,
|
70 |
+
"learning_rate": 4.723710122095314e-05,
|
71 |
+
"loss": 0.7309,
|
72 |
+
"step": 4230
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.5,
|
76 |
+
"grad_norm": 5.423086643218994,
|
77 |
+
"learning_rate": 4.631350925561245e-05,
|
78 |
+
"loss": 0.7232,
|
79 |
+
"step": 4700
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.55,
|
83 |
+
"grad_norm": 5.894528865814209,
|
84 |
+
"learning_rate": 4.538794801102797e-05,
|
85 |
+
"loss": 0.7158,
|
86 |
+
"step": 5170
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.6,
|
90 |
+
"grad_norm": 11.838452339172363,
|
91 |
+
"learning_rate": 4.446238676644348e-05,
|
92 |
+
"loss": 0.6685,
|
93 |
+
"step": 5640
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.65,
|
97 |
+
"grad_norm": 9.664875984191895,
|
98 |
+
"learning_rate": 4.3536825521859006e-05,
|
99 |
+
"loss": 0.6529,
|
100 |
+
"step": 6110
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.7,
|
104 |
+
"grad_norm": 2.137725830078125,
|
105 |
+
"learning_rate": 4.2613233556518316e-05,
|
106 |
+
"loss": 0.6989,
|
107 |
+
"step": 6580
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.75,
|
111 |
+
"grad_norm": 3.258774757385254,
|
112 |
+
"learning_rate": 4.1687672311933836e-05,
|
113 |
+
"loss": 0.6726,
|
114 |
+
"step": 7050
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.8,
|
118 |
+
"grad_norm": 7.028015613555908,
|
119 |
+
"learning_rate": 4.076211106734935e-05,
|
120 |
+
"loss": 0.6223,
|
121 |
+
"step": 7520
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.85,
|
125 |
+
"grad_norm": 18.01885986328125,
|
126 |
+
"learning_rate": 3.983654982276487e-05,
|
127 |
+
"loss": 0.6508,
|
128 |
+
"step": 7990
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.9,
|
132 |
+
"grad_norm": 25.15569305419922,
|
133 |
+
"learning_rate": 3.891098857818039e-05,
|
134 |
+
"loss": 0.6331,
|
135 |
+
"step": 8460
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.95,
|
139 |
+
"grad_norm": 24.006214141845703,
|
140 |
+
"learning_rate": 3.7987396612839705e-05,
|
141 |
+
"loss": 0.611,
|
142 |
+
"step": 8930
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.0,
|
146 |
+
"grad_norm": 2.1655495166778564,
|
147 |
+
"learning_rate": 3.706183536825522e-05,
|
148 |
+
"loss": 0.6087,
|
149 |
+
"step": 9400
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.0,
|
153 |
+
"eval_accuracy": 0.8187473415567843,
|
154 |
+
"eval_f1_macro": 0.46294521980012443,
|
155 |
+
"eval_f1_micro": 0.8187473415567843,
|
156 |
+
"eval_f1_weighted": 0.8059661307178965,
|
157 |
+
"eval_loss": 0.572761058807373,
|
158 |
+
"eval_precision_macro": 0.5758322996430759,
|
159 |
+
"eval_precision_micro": 0.8187473415567843,
|
160 |
+
"eval_precision_weighted": 0.8086829791224769,
|
161 |
+
"eval_recall_macro": 0.41762623775804325,
|
162 |
+
"eval_recall_micro": 0.8187473415567843,
|
163 |
+
"eval_recall_weighted": 0.8187473415567843,
|
164 |
+
"eval_runtime": 26.045,
|
165 |
+
"eval_samples_per_second": 722.134,
|
166 |
+
"eval_steps_per_second": 45.153,
|
167 |
+
"step": 9404
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 1.05,
|
171 |
+
"grad_norm": 17.25170135498047,
|
172 |
+
"learning_rate": 3.613627412367074e-05,
|
173 |
+
"loss": 0.5375,
|
174 |
+
"step": 9870
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.1,
|
178 |
+
"grad_norm": 23.737775802612305,
|
179 |
+
"learning_rate": 3.521071287908626e-05,
|
180 |
+
"loss": 0.5672,
|
181 |
+
"step": 10340
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 1.15,
|
185 |
+
"grad_norm": 13.758621215820312,
|
186 |
+
"learning_rate": 3.428515163450177e-05,
|
187 |
+
"loss": 0.5488,
|
188 |
+
"step": 10810
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.2,
|
192 |
+
"grad_norm": 61.011051177978516,
|
193 |
+
"learning_rate": 3.3361559669161094e-05,
|
194 |
+
"loss": 0.5117,
|
195 |
+
"step": 11280
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.25,
|
199 |
+
"grad_norm": 3.6547300815582275,
|
200 |
+
"learning_rate": 3.243599842457661e-05,
|
201 |
+
"loss": 0.5172,
|
202 |
+
"step": 11750
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.3,
|
206 |
+
"grad_norm": 22.888540267944336,
|
207 |
+
"learning_rate": 3.1510437179992126e-05,
|
208 |
+
"loss": 0.5444,
|
209 |
+
"step": 12220
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.35,
|
213 |
+
"grad_norm": 34.05695724487305,
|
214 |
+
"learning_rate": 3.058487593540764e-05,
|
215 |
+
"loss": 0.541,
|
216 |
+
"step": 12690
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.4,
|
220 |
+
"grad_norm": 8.264917373657227,
|
221 |
+
"learning_rate": 2.965931469082316e-05,
|
222 |
+
"loss": 0.5244,
|
223 |
+
"step": 13160
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.45,
|
227 |
+
"grad_norm": 15.04733657836914,
|
228 |
+
"learning_rate": 2.8735722725482473e-05,
|
229 |
+
"loss": 0.5083,
|
230 |
+
"step": 13630
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.5,
|
234 |
+
"grad_norm": 12.602872848510742,
|
235 |
+
"learning_rate": 2.7810161480897996e-05,
|
236 |
+
"loss": 0.5199,
|
237 |
+
"step": 14100
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.55,
|
241 |
+
"grad_norm": 1.5008900165557861,
|
242 |
+
"learning_rate": 2.6884600236313512e-05,
|
243 |
+
"loss": 0.5217,
|
244 |
+
"step": 14570
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.6,
|
248 |
+
"grad_norm": 16.495512008666992,
|
249 |
+
"learning_rate": 2.5959038991729028e-05,
|
250 |
+
"loss": 0.5027,
|
251 |
+
"step": 15040
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.65,
|
255 |
+
"grad_norm": 10.326951026916504,
|
256 |
+
"learning_rate": 2.5033477747144544e-05,
|
257 |
+
"loss": 0.4826,
|
258 |
+
"step": 15510
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.7,
|
262 |
+
"grad_norm": 0.7021717429161072,
|
263 |
+
"learning_rate": 2.4107916502560064e-05,
|
264 |
+
"loss": 0.4925,
|
265 |
+
"step": 15980
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.75,
|
269 |
+
"grad_norm": 8.40272045135498,
|
270 |
+
"learning_rate": 2.3182355257975584e-05,
|
271 |
+
"loss": 0.4856,
|
272 |
+
"step": 16450
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.8,
|
276 |
+
"grad_norm": 44.403995513916016,
|
277 |
+
"learning_rate": 2.22567940133911e-05,
|
278 |
+
"loss": 0.4749,
|
279 |
+
"step": 16920
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.85,
|
283 |
+
"grad_norm": 23.918331146240234,
|
284 |
+
"learning_rate": 2.1331232768806616e-05,
|
285 |
+
"loss": 0.4797,
|
286 |
+
"step": 17390
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.9,
|
290 |
+
"grad_norm": 0.3805901110172272,
|
291 |
+
"learning_rate": 2.0405671524222136e-05,
|
292 |
+
"loss": 0.4493,
|
293 |
+
"step": 17860
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.95,
|
297 |
+
"grad_norm": 112.13935089111328,
|
298 |
+
"learning_rate": 1.948207955888145e-05,
|
299 |
+
"loss": 0.4578,
|
300 |
+
"step": 18330
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 2.0,
|
304 |
+
"grad_norm": 0.33476272225379944,
|
305 |
+
"learning_rate": 1.855651831429697e-05,
|
306 |
+
"loss": 0.4534,
|
307 |
+
"step": 18800
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 2.0,
|
311 |
+
"eval_accuracy": 0.8687792428753722,
|
312 |
+
"eval_f1_macro": 0.559681935575693,
|
313 |
+
"eval_f1_micro": 0.8687792428753722,
|
314 |
+
"eval_f1_weighted": 0.8615066948170524,
|
315 |
+
"eval_loss": 0.5368207097053528,
|
316 |
+
"eval_precision_macro": 0.6600138396353541,
|
317 |
+
"eval_precision_micro": 0.8687792428753722,
|
318 |
+
"eval_precision_weighted": 0.8644468533826618,
|
319 |
+
"eval_recall_macro": 0.507377817762126,
|
320 |
+
"eval_recall_micro": 0.8687792428753722,
|
321 |
+
"eval_recall_weighted": 0.8687792428753722,
|
322 |
+
"eval_runtime": 26.0195,
|
323 |
+
"eval_samples_per_second": 722.842,
|
324 |
+
"eval_steps_per_second": 45.197,
|
325 |
+
"step": 18808
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 2.05,
|
329 |
+
"grad_norm": 0.6752718687057495,
|
330 |
+
"learning_rate": 1.7632926348956283e-05,
|
331 |
+
"loss": 0.3658,
|
332 |
+
"step": 19270
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.1,
|
336 |
+
"grad_norm": 0.2787342369556427,
|
337 |
+
"learning_rate": 1.67073651043718e-05,
|
338 |
+
"loss": 0.3765,
|
339 |
+
"step": 19740
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 2.15,
|
343 |
+
"grad_norm": 9.497492790222168,
|
344 |
+
"learning_rate": 1.578180385978732e-05,
|
345 |
+
"loss": 0.394,
|
346 |
+
"step": 20210
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 2.2,
|
350 |
+
"grad_norm": 2.3944571018218994,
|
351 |
+
"learning_rate": 1.4856242615202837e-05,
|
352 |
+
"loss": 0.3513,
|
353 |
+
"step": 20680
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 2.25,
|
357 |
+
"grad_norm": 0.1735432744026184,
|
358 |
+
"learning_rate": 1.3930681370618353e-05,
|
359 |
+
"loss": 0.4126,
|
360 |
+
"step": 21150
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 2.3,
|
364 |
+
"grad_norm": 1.655259370803833,
|
365 |
+
"learning_rate": 1.3005120126033873e-05,
|
366 |
+
"loss": 0.3784,
|
367 |
+
"step": 21620
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 2.35,
|
371 |
+
"grad_norm": 10.722052574157715,
|
372 |
+
"learning_rate": 1.207955888144939e-05,
|
373 |
+
"loss": 0.3756,
|
374 |
+
"step": 22090
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.4,
|
378 |
+
"grad_norm": 21.695981979370117,
|
379 |
+
"learning_rate": 1.1155966916108706e-05,
|
380 |
+
"loss": 0.3544,
|
381 |
+
"step": 22560
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 2.45,
|
385 |
+
"grad_norm": 12.648837089538574,
|
386 |
+
"learning_rate": 1.0230405671524222e-05,
|
387 |
+
"loss": 0.3692,
|
388 |
+
"step": 23030
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 2.5,
|
392 |
+
"grad_norm": 18.777280807495117,
|
393 |
+
"learning_rate": 9.30484442693974e-06,
|
394 |
+
"loss": 0.3594,
|
395 |
+
"step": 23500
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 2.55,
|
399 |
+
"grad_norm": 31.695280075073242,
|
400 |
+
"learning_rate": 8.37928318235526e-06,
|
401 |
+
"loss": 0.3659,
|
402 |
+
"step": 23970
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.6,
|
406 |
+
"grad_norm": 0.4333338737487793,
|
407 |
+
"learning_rate": 7.453721937770776e-06,
|
408 |
+
"loss": 0.3243,
|
409 |
+
"step": 24440
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 2.65,
|
413 |
+
"grad_norm": 13.526206016540527,
|
414 |
+
"learning_rate": 6.528160693186294e-06,
|
415 |
+
"loss": 0.3613,
|
416 |
+
"step": 24910
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.7,
|
420 |
+
"grad_norm": 6.630594253540039,
|
421 |
+
"learning_rate": 5.604568727845609e-06,
|
422 |
+
"loss": 0.3233,
|
423 |
+
"step": 25380
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 2.75,
|
427 |
+
"grad_norm": 22.810880661010742,
|
428 |
+
"learning_rate": 4.6790074832611264e-06,
|
429 |
+
"loss": 0.3294,
|
430 |
+
"step": 25850
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 2.8,
|
434 |
+
"grad_norm": 1.0214672088623047,
|
435 |
+
"learning_rate": 3.7534462386766444e-06,
|
436 |
+
"loss": 0.3317,
|
437 |
+
"step": 26320
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 2.85,
|
441 |
+
"grad_norm": 0.3469996154308319,
|
442 |
+
"learning_rate": 2.8278849940921623e-06,
|
443 |
+
"loss": 0.3314,
|
444 |
+
"step": 26790
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.9,
|
448 |
+
"grad_norm": 0.516646146774292,
|
449 |
+
"learning_rate": 1.9023237495076803e-06,
|
450 |
+
"loss": 0.2886,
|
451 |
+
"step": 27260
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 2.95,
|
455 |
+
"grad_norm": 76.06954956054688,
|
456 |
+
"learning_rate": 9.767625049231982e-07,
|
457 |
+
"loss": 0.3148,
|
458 |
+
"step": 27730
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 3.0,
|
462 |
+
"grad_norm": 46.52577209472656,
|
463 |
+
"learning_rate": 5.120126033871603e-08,
|
464 |
+
"loss": 0.298,
|
465 |
+
"step": 28200
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 3.0,
|
469 |
+
"eval_accuracy": 0.8910038281582305,
|
470 |
+
"eval_f1_macro": 0.605011586308457,
|
471 |
+
"eval_f1_micro": 0.8910038281582305,
|
472 |
+
"eval_f1_weighted": 0.8870714364293508,
|
473 |
+
"eval_loss": 0.5102838277816772,
|
474 |
+
"eval_precision_macro": 0.6869883411452264,
|
475 |
+
"eval_precision_micro": 0.8910038281582305,
|
476 |
+
"eval_precision_weighted": 0.8858066104824025,
|
477 |
+
"eval_recall_macro": 0.5550753643871188,
|
478 |
+
"eval_recall_micro": 0.8910038281582305,
|
479 |
+
"eval_recall_weighted": 0.8910038281582305,
|
480 |
+
"eval_runtime": 26.0873,
|
481 |
+
"eval_samples_per_second": 720.965,
|
482 |
+
"eval_steps_per_second": 45.079,
|
483 |
+
"step": 28212
|
484 |
+
}
|
485 |
+
],
|
486 |
+
"logging_steps": 470,
|
487 |
+
"max_steps": 28212,
|
488 |
+
"num_input_tokens_seen": 0,
|
489 |
+
"num_train_epochs": 3,
|
490 |
+
"save_steps": 500,
|
491 |
+
"total_flos": 1.4846977835900928e+16,
|
492 |
+
"train_batch_size": 8,
|
493 |
+
"trial_name": null,
|
494 |
+
"trial_params": null
|
495 |
+
}
|
checkpoint-28212/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35ece242e48ea882e36fb34985df0e39a5808b42f3d9a613b4d7b91d5bd40509
|
3 |
+
size 4920
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-multilingual-cased",
|
3 |
+
"_num_labels": 11,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": 0,
|
15 |
+
"1": 1,
|
16 |
+
"2": 2,
|
17 |
+
"3": 3,
|
18 |
+
"4": 4,
|
19 |
+
"5": 5,
|
20 |
+
"6": 6,
|
21 |
+
"7": 7,
|
22 |
+
"8": 8,
|
23 |
+
"9": 9,
|
24 |
+
"10": 10
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"0": 0,
|
30 |
+
"1": 1,
|
31 |
+
"2": 2,
|
32 |
+
"3": 3,
|
33 |
+
"4": 4,
|
34 |
+
"5": 5,
|
35 |
+
"6": 6,
|
36 |
+
"7": 7,
|
37 |
+
"8": 8,
|
38 |
+
"9": 9,
|
39 |
+
"10": 10
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-12,
|
42 |
+
"max_position_embeddings": 512,
|
43 |
+
"model_type": "bert",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"pooler_fc_size": 768,
|
48 |
+
"pooler_num_attention_heads": 12,
|
49 |
+
"pooler_num_fc_layers": 3,
|
50 |
+
"pooler_size_per_head": 128,
|
51 |
+
"pooler_type": "first_token_transform",
|
52 |
+
"position_embedding_type": "absolute",
|
53 |
+
"problem_type": "single_label_classification",
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.38.2",
|
56 |
+
"type_vocab_size": 2,
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 119547
|
59 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea42433a66192fafb34d42228d32b817da608c47db2a7bd785bb25b50818a4e9
|
3 |
+
size 711471148
|
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 sha256:35ece242e48ea882e36fb34985df0e39a5808b42f3d9a613b4d7b91d5bd40509
|
3 |
+
size 4920
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "bert-toc-classification-95k/autotrain-data",
|
3 |
+
"model": "google-bert/bert-base-multilingual-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": 0.01,
|
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": "bert-toc-classification-95k",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"save_strategy": "epoch",
|
25 |
+
"push_to_hub": true,
|
26 |
+
"repo_id": "pruhtopia/bert-toc-classification-95k",
|
27 |
+
"evaluation_strategy": "epoch",
|
28 |
+
"username": "pruhtopia",
|
29 |
+
"log": "none"
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|