cbpuschmann
commited on
Commit
•
175a9d8
1
Parent(s):
b37604f
Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +26 -0
- checkpoint-900/config.json +36 -0
- checkpoint-900/model.safetensors +3 -0
- checkpoint-900/optimizer.pt +3 -0
- checkpoint-900/rng_state_0.pth +3 -0
- checkpoint-900/rng_state_1.pth +3 -0
- checkpoint-900/rng_state_2.pth +3 -0
- checkpoint-900/rng_state_3.pth +3 -0
- checkpoint-900/scheduler.pt +3 -0
- checkpoint-900/trainer_state.json +333 -0
- checkpoint-900/training_args.bin +3 -0
- config.json +36 -0
- model.safetensors +3 -0
- runs/Dec02_13-27-59_r-cbpuschmann-sfautotrain-etooiy4s-3f6aa-552dm/events.out.tfevents.1733146081.r-cbpuschmann-sfautotrain-etooiy4s-3f6aa-552dm.223.0 +2 -2
- runs/Dec02_13-27-59_r-cbpuschmann-sfautotrain-etooiy4s-3f6aa-552dm/events.out.tfevents.1733146141.r-cbpuschmann-sfautotrain-etooiy4s-3f6aa-552dm.223.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +64 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- unigram.json +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
unigram.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
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: 0.022496581077575684
|
17 |
+
|
18 |
+
f1: 0.9958368026644463
|
19 |
+
|
20 |
+
precision: 0.9966666666666667
|
21 |
+
|
22 |
+
recall: 0.9950083194675541
|
23 |
+
|
24 |
+
auc: 0.9997131936477601
|
25 |
+
|
26 |
+
accuracy: 0.9958333333333333
|
checkpoint-900/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
|
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": 384,
|
13 |
+
"id2label": {
|
14 |
+
"0": "opposed",
|
15 |
+
"1": "supportive"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 1536,
|
19 |
+
"label2id": {
|
20 |
+
"opposed": 0,
|
21 |
+
"supportive": 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": "4.46.2",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 250037
|
36 |
+
}
|
checkpoint-900/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4b1495a47ad3a527c0dfcf401cc36db9493dbe7d79192b2f3c7d5fa9d042a74
|
3 |
+
size 470641664
|
checkpoint-900/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8a1a8ac5b9ea3e9cdcbc5a13bccbc9fb4f6b1f745eb0e19ce2a70d493de335f
|
3 |
+
size 941404410
|
checkpoint-900/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:233bf325aa28b77fc904e89e6c421f017b5ee612cf71ccc190d170f5a4097073
|
3 |
+
size 15024
|
checkpoint-900/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:870b887f3c980b6d6a4d950ac29c5482199c8b8c7bb380476b569b124878faff
|
3 |
+
size 15024
|
checkpoint-900/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a03fcad5a5989e48d2bc3c44f9ad81b7fbab60067b24a5602d72e9024b25a5e2
|
3 |
+
size 15024
|
checkpoint-900/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:662d5e1a7c1f44a436dd9221001266098ccd561afff244745ba684e780296cb8
|
3 |
+
size 15024
|
checkpoint-900/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb791639ba1f0ba307b15746c0eab73364f7ec0332c468978d8fa578d4b2c805
|
3 |
+
size 1064
|
checkpoint-900/trainer_state.json
ADDED
@@ -0,0 +1,333 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.033857524394989014,
|
3 |
+
"best_model_checkpoint": "autotrain-uezr0-uoiv8/checkpoint-900",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 900,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.08333333333333333,
|
13 |
+
"grad_norm": 1.82069730758667,
|
14 |
+
"learning_rate": 1.388888888888889e-05,
|
15 |
+
"loss": 0.6908,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.16666666666666666,
|
20 |
+
"grad_norm": 2.137547731399536,
|
21 |
+
"learning_rate": 2.777777777777778e-05,
|
22 |
+
"loss": 0.6406,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.25,
|
27 |
+
"grad_norm": 4.0937089920043945,
|
28 |
+
"learning_rate": 4.166666666666667e-05,
|
29 |
+
"loss": 0.4508,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.3333333333333333,
|
34 |
+
"grad_norm": 1.7516766786575317,
|
35 |
+
"learning_rate": 4.938271604938271e-05,
|
36 |
+
"loss": 0.221,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.4166666666666667,
|
41 |
+
"grad_norm": 0.4161239266395569,
|
42 |
+
"learning_rate": 4.7901234567901237e-05,
|
43 |
+
"loss": 0.1776,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.5,
|
48 |
+
"grad_norm": 0.2219855636358261,
|
49 |
+
"learning_rate": 4.635802469135803e-05,
|
50 |
+
"loss": 0.077,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.5833333333333334,
|
55 |
+
"grad_norm": 0.8288750648498535,
|
56 |
+
"learning_rate": 4.481481481481482e-05,
|
57 |
+
"loss": 0.0728,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.6666666666666666,
|
62 |
+
"grad_norm": 0.7433828115463257,
|
63 |
+
"learning_rate": 4.327160493827161e-05,
|
64 |
+
"loss": 0.1121,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.75,
|
69 |
+
"grad_norm": 0.09709342569112778,
|
70 |
+
"learning_rate": 4.17283950617284e-05,
|
71 |
+
"loss": 0.0739,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.8333333333333334,
|
76 |
+
"grad_norm": 0.078657366335392,
|
77 |
+
"learning_rate": 4.018518518518519e-05,
|
78 |
+
"loss": 0.0763,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.9166666666666666,
|
83 |
+
"grad_norm": 0.0632229894399643,
|
84 |
+
"learning_rate": 3.864197530864197e-05,
|
85 |
+
"loss": 0.0652,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.0,
|
90 |
+
"grad_norm": 0.05742119625210762,
|
91 |
+
"learning_rate": 3.709876543209877e-05,
|
92 |
+
"loss": 0.0975,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.0,
|
97 |
+
"eval_accuracy": 0.9879166666666667,
|
98 |
+
"eval_auc": 0.9982201339448166,
|
99 |
+
"eval_f1": 0.9879317519766958,
|
100 |
+
"eval_loss": 0.0525396354496479,
|
101 |
+
"eval_precision": 0.9883430474604497,
|
102 |
+
"eval_recall": 0.9875207986688852,
|
103 |
+
"eval_runtime": 1.0448,
|
104 |
+
"eval_samples_per_second": 2297.14,
|
105 |
+
"eval_steps_per_second": 36.371,
|
106 |
+
"step": 300
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 1.0833333333333333,
|
110 |
+
"grad_norm": 0.05390068516135216,
|
111 |
+
"learning_rate": 3.555555555555556e-05,
|
112 |
+
"loss": 0.0312,
|
113 |
+
"step": 325
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.1666666666666667,
|
117 |
+
"grad_norm": 0.04680803418159485,
|
118 |
+
"learning_rate": 3.401234567901235e-05,
|
119 |
+
"loss": 0.056,
|
120 |
+
"step": 350
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 1.25,
|
124 |
+
"grad_norm": 0.044450074434280396,
|
125 |
+
"learning_rate": 3.2469135802469134e-05,
|
126 |
+
"loss": 0.0256,
|
127 |
+
"step": 375
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 1.3333333333333333,
|
131 |
+
"grad_norm": 7.118642330169678,
|
132 |
+
"learning_rate": 3.0925925925925924e-05,
|
133 |
+
"loss": 0.0274,
|
134 |
+
"step": 400
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.4166666666666667,
|
138 |
+
"grad_norm": 0.03718909993767738,
|
139 |
+
"learning_rate": 2.9382716049382718e-05,
|
140 |
+
"loss": 0.0424,
|
141 |
+
"step": 425
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.5,
|
145 |
+
"grad_norm": 0.03126256540417671,
|
146 |
+
"learning_rate": 2.783950617283951e-05,
|
147 |
+
"loss": 0.028,
|
148 |
+
"step": 450
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 1.5833333333333335,
|
152 |
+
"grad_norm": 0.04140450805425644,
|
153 |
+
"learning_rate": 2.6296296296296296e-05,
|
154 |
+
"loss": 0.0809,
|
155 |
+
"step": 475
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 1.6666666666666665,
|
159 |
+
"grad_norm": 0.031227530911564827,
|
160 |
+
"learning_rate": 2.475308641975309e-05,
|
161 |
+
"loss": 0.0303,
|
162 |
+
"step": 500
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.75,
|
166 |
+
"grad_norm": 0.03383219987154007,
|
167 |
+
"learning_rate": 2.3209876543209877e-05,
|
168 |
+
"loss": 0.0297,
|
169 |
+
"step": 525
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 1.8333333333333335,
|
173 |
+
"grad_norm": 0.21085390448570251,
|
174 |
+
"learning_rate": 2.1666666666666667e-05,
|
175 |
+
"loss": 0.058,
|
176 |
+
"step": 550
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.9166666666666665,
|
180 |
+
"grad_norm": 0.0288908202201128,
|
181 |
+
"learning_rate": 2.0123456790123457e-05,
|
182 |
+
"loss": 0.0398,
|
183 |
+
"step": 575
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 2.0,
|
187 |
+
"grad_norm": 0.045943427830934525,
|
188 |
+
"learning_rate": 1.8580246913580248e-05,
|
189 |
+
"loss": 0.0309,
|
190 |
+
"step": 600
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 2.0,
|
194 |
+
"eval_accuracy": 0.9891666666666666,
|
195 |
+
"eval_auc": 0.9969343664843513,
|
196 |
+
"eval_f1": 0.9891576313594662,
|
197 |
+
"eval_loss": 0.051070552319288254,
|
198 |
+
"eval_precision": 0.9916387959866221,
|
199 |
+
"eval_recall": 0.9866888519134775,
|
200 |
+
"eval_runtime": 1.0335,
|
201 |
+
"eval_samples_per_second": 2322.126,
|
202 |
+
"eval_steps_per_second": 36.767,
|
203 |
+
"step": 600
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 2.0833333333333335,
|
207 |
+
"grad_norm": 0.03196296840906143,
|
208 |
+
"learning_rate": 1.7037037037037038e-05,
|
209 |
+
"loss": 0.032,
|
210 |
+
"step": 625
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 2.1666666666666665,
|
214 |
+
"grad_norm": 0.029745565727353096,
|
215 |
+
"learning_rate": 1.549382716049383e-05,
|
216 |
+
"loss": 0.0309,
|
217 |
+
"step": 650
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 2.25,
|
221 |
+
"grad_norm": 0.027830524370074272,
|
222 |
+
"learning_rate": 1.3950617283950617e-05,
|
223 |
+
"loss": 0.0329,
|
224 |
+
"step": 675
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.3333333333333335,
|
228 |
+
"grad_norm": 0.025451036170125008,
|
229 |
+
"learning_rate": 1.2407407407407408e-05,
|
230 |
+
"loss": 0.0092,
|
231 |
+
"step": 700
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 2.4166666666666665,
|
235 |
+
"grad_norm": 0.024281444028019905,
|
236 |
+
"learning_rate": 1.0864197530864198e-05,
|
237 |
+
"loss": 0.0362,
|
238 |
+
"step": 725
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 2.5,
|
242 |
+
"grad_norm": 0.02248438447713852,
|
243 |
+
"learning_rate": 9.320987654320989e-06,
|
244 |
+
"loss": 0.0189,
|
245 |
+
"step": 750
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 2.5833333333333335,
|
249 |
+
"grad_norm": 0.022118769586086273,
|
250 |
+
"learning_rate": 7.777777777777777e-06,
|
251 |
+
"loss": 0.0134,
|
252 |
+
"step": 775
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 2.6666666666666665,
|
256 |
+
"grad_norm": 0.0221453458070755,
|
257 |
+
"learning_rate": 6.234567901234569e-06,
|
258 |
+
"loss": 0.0096,
|
259 |
+
"step": 800
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 2.75,
|
263 |
+
"grad_norm": 0.02116595022380352,
|
264 |
+
"learning_rate": 4.691358024691358e-06,
|
265 |
+
"loss": 0.0194,
|
266 |
+
"step": 825
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.8333333333333335,
|
270 |
+
"grad_norm": 0.02011377364397049,
|
271 |
+
"learning_rate": 3.148148148148148e-06,
|
272 |
+
"loss": 0.0106,
|
273 |
+
"step": 850
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 2.9166666666666665,
|
277 |
+
"grad_norm": 0.02164468728005886,
|
278 |
+
"learning_rate": 1.6049382716049385e-06,
|
279 |
+
"loss": 0.0093,
|
280 |
+
"step": 875
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 3.0,
|
284 |
+
"grad_norm": 0.037997905164957047,
|
285 |
+
"learning_rate": 6.17283950617284e-08,
|
286 |
+
"loss": 0.0185,
|
287 |
+
"step": 900
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 3.0,
|
291 |
+
"eval_accuracy": 0.9933333333333333,
|
292 |
+
"eval_auc": 0.9984406206683908,
|
293 |
+
"eval_f1": 0.9933333333333333,
|
294 |
+
"eval_loss": 0.033857524394989014,
|
295 |
+
"eval_precision": 0.994991652754591,
|
296 |
+
"eval_recall": 0.9916805324459235,
|
297 |
+
"eval_runtime": 1.0406,
|
298 |
+
"eval_samples_per_second": 2306.446,
|
299 |
+
"eval_steps_per_second": 36.519,
|
300 |
+
"step": 900
|
301 |
+
}
|
302 |
+
],
|
303 |
+
"logging_steps": 25,
|
304 |
+
"max_steps": 900,
|
305 |
+
"num_input_tokens_seen": 0,
|
306 |
+
"num_train_epochs": 3,
|
307 |
+
"save_steps": 500,
|
308 |
+
"stateful_callbacks": {
|
309 |
+
"EarlyStoppingCallback": {
|
310 |
+
"args": {
|
311 |
+
"early_stopping_patience": 5,
|
312 |
+
"early_stopping_threshold": 0.01
|
313 |
+
},
|
314 |
+
"attributes": {
|
315 |
+
"early_stopping_patience_counter": 0
|
316 |
+
}
|
317 |
+
},
|
318 |
+
"TrainerControl": {
|
319 |
+
"args": {
|
320 |
+
"should_epoch_stop": false,
|
321 |
+
"should_evaluate": false,
|
322 |
+
"should_log": false,
|
323 |
+
"should_save": true,
|
324 |
+
"should_training_stop": true
|
325 |
+
},
|
326 |
+
"attributes": {}
|
327 |
+
}
|
328 |
+
},
|
329 |
+
"total_flos": 474283650318336.0,
|
330 |
+
"train_batch_size": 8,
|
331 |
+
"trial_name": null,
|
332 |
+
"trial_params": null
|
333 |
+
}
|
checkpoint-900/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c99223f295eb8289ffaaffb2bf13f03bcb39de34bf1519699c18c5a5402376c6
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
|
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": 384,
|
13 |
+
"id2label": {
|
14 |
+
"0": "opposed",
|
15 |
+
"1": "supportive"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 1536,
|
19 |
+
"label2id": {
|
20 |
+
"opposed": 0,
|
21 |
+
"supportive": 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": "4.46.2",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 250037
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4b1495a47ad3a527c0dfcf401cc36db9493dbe7d79192b2f3c7d5fa9d042a74
|
3 |
+
size 470641664
|
runs/Dec02_13-27-59_r-cbpuschmann-sfautotrain-etooiy4s-3f6aa-552dm/events.out.tfevents.1733146081.r-cbpuschmann-sfautotrain-etooiy4s-3f6aa-552dm.223.0
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 sha256:494c25e0d9824b424f5b82ea60255a16b7698a2ce64dfe8ca3219ee4f8b0a240
|
3 |
+
size 14746
|
runs/Dec02_13-27-59_r-cbpuschmann-sfautotrain-etooiy4s-3f6aa-552dm/events.out.tfevents.1733146141.r-cbpuschmann-sfautotrain-etooiy4s-3f6aa-552dm.223.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf7a444262de009e35009429c744a90f3129008516a2a074a7ffa1cff5984d63
|
3 |
+
size 607
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c088c06cf975b7097e469bd69630cdb0d675c6db1ce3af1042b6e19c6d01f22
|
3 |
+
size 17082999
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": false,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"max_length": 128,
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "</s>",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "<unk>"
|
64 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c99223f295eb8289ffaaffb2bf13f03bcb39de34bf1519699c18c5a5402376c6
|
3 |
+
size 5304
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-uezr0-uoiv8/autotrain-data",
|
3 |
+
"model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
|
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-uezr0-uoiv8",
|
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": "cbpuschmann",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
unigram.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
|
3 |
+
size 14763260
|