Markus Serloth-Schwarzer commited on
Commit
69688c0
·
verified ·
1 Parent(s): 42d95f3

Upload folder using huggingface_hub

Browse files
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
+ - v21/autotrain-data
10
+ ---
11
+
12
+ # Model Trained Using AutoTrain
13
+
14
+ - Problem type: Text Classification
15
+
16
+ ## Validation Metrics
17
+ loss: 0.5896586775779724
18
+
19
+ f1_macro: 0.6544353292567254
20
+
21
+ f1_micro: 0.707936507936508
22
+
23
+ f1_weighted: 0.693246083160111
24
+
25
+ precision_macro: 0.7424193199047
26
+
27
+ precision_micro: 0.707936507936508
28
+
29
+ precision_weighted: 0.7052234495704283
30
+
31
+ recall_macro: 0.6125864829753165
32
+
33
+ recall_micro: 0.707936507936508
34
+
35
+ recall_weighted: 0.707936507936508
36
+
37
+ accuracy: 0.707936507936508
checkpoint-177/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "oliverguhr/german-sentiment-bert",
3
+ "_num_labels": 3,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "finetuning_task": "germansentiment",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "negative",
15
+ "1": "neutral",
16
+ "2": "positive"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "negative": 0,
22
+ "neutral": 1,
23
+ "positive": 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": "4.40.1",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30000
38
+ }
checkpoint-177/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ede11c254ee8772eed41adf91113db6b28218ed36d65879d12df66f4200718
3
+ size 436358132
checkpoint-177/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3281214c66eb126c300eac06e9e08267f16b3372437b44179db3b6bc2eca91
3
+ size 872837370
checkpoint-177/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d4d80e5ef2faacde450252ab9219600781af9e4ebaf59d822865924980ce5f
3
+ size 14244
checkpoint-177/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2664ce8dc26f9f022b989f96785278c32b1185fa37fe1b90ca44985c6c5018f4
3
+ size 1064
checkpoint-177/trainer_state.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5896586775779724,
3
+ "best_model_checkpoint": "v21/checkpoint-177",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 177,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03954802259887006,
13
+ "grad_norm": 73.34220886230469,
14
+ "learning_rate": 1.6853932584269663e-06,
15
+ "loss": 3.1497,
16
+ "step": 7
17
+ },
18
+ {
19
+ "epoch": 0.07909604519774012,
20
+ "grad_norm": 39.214630126953125,
21
+ "learning_rate": 5.056179775280899e-06,
22
+ "loss": 2.5072,
23
+ "step": 14
24
+ },
25
+ {
26
+ "epoch": 0.11864406779661017,
27
+ "grad_norm": 43.25741195678711,
28
+ "learning_rate": 8.98876404494382e-06,
29
+ "loss": 1.752,
30
+ "step": 21
31
+ },
32
+ {
33
+ "epoch": 0.15819209039548024,
34
+ "grad_norm": 47.583980560302734,
35
+ "learning_rate": 1.2921348314606743e-05,
36
+ "loss": 1.5765,
37
+ "step": 28
38
+ },
39
+ {
40
+ "epoch": 0.1977401129943503,
41
+ "grad_norm": 21.266357421875,
42
+ "learning_rate": 1.6853932584269665e-05,
43
+ "loss": 1.287,
44
+ "step": 35
45
+ },
46
+ {
47
+ "epoch": 0.23728813559322035,
48
+ "grad_norm": 15.081623077392578,
49
+ "learning_rate": 2.0786516853932585e-05,
50
+ "loss": 1.2136,
51
+ "step": 42
52
+ },
53
+ {
54
+ "epoch": 0.2768361581920904,
55
+ "grad_norm": 9.609501838684082,
56
+ "learning_rate": 2.4719101123595505e-05,
57
+ "loss": 0.9708,
58
+ "step": 49
59
+ },
60
+ {
61
+ "epoch": 0.3163841807909605,
62
+ "grad_norm": 10.065922737121582,
63
+ "learning_rate": 2.8651685393258425e-05,
64
+ "loss": 0.7196,
65
+ "step": 56
66
+ },
67
+ {
68
+ "epoch": 0.3559322033898305,
69
+ "grad_norm": 7.166884899139404,
70
+ "learning_rate": 3.258426966292135e-05,
71
+ "loss": 0.7877,
72
+ "step": 63
73
+ },
74
+ {
75
+ "epoch": 0.3954802259887006,
76
+ "grad_norm": 12.045182228088379,
77
+ "learning_rate": 3.651685393258427e-05,
78
+ "loss": 0.7109,
79
+ "step": 70
80
+ },
81
+ {
82
+ "epoch": 0.4350282485875706,
83
+ "grad_norm": 9.929503440856934,
84
+ "learning_rate": 4.044943820224719e-05,
85
+ "loss": 0.7244,
86
+ "step": 77
87
+ },
88
+ {
89
+ "epoch": 0.4745762711864407,
90
+ "grad_norm": 21.984752655029297,
91
+ "learning_rate": 4.438202247191011e-05,
92
+ "loss": 0.6535,
93
+ "step": 84
94
+ },
95
+ {
96
+ "epoch": 0.5141242937853108,
97
+ "grad_norm": 21.552167892456055,
98
+ "learning_rate": 4.831460674157304e-05,
99
+ "loss": 0.6405,
100
+ "step": 91
101
+ },
102
+ {
103
+ "epoch": 0.5536723163841808,
104
+ "grad_norm": 9.6996431350708,
105
+ "learning_rate": 4.974874371859297e-05,
106
+ "loss": 0.6403,
107
+ "step": 98
108
+ },
109
+ {
110
+ "epoch": 0.5932203389830508,
111
+ "grad_norm": 26.493928909301758,
112
+ "learning_rate": 4.930904522613066e-05,
113
+ "loss": 0.7105,
114
+ "step": 105
115
+ },
116
+ {
117
+ "epoch": 0.632768361581921,
118
+ "grad_norm": 7.643754005432129,
119
+ "learning_rate": 4.8869346733668344e-05,
120
+ "loss": 0.683,
121
+ "step": 112
122
+ },
123
+ {
124
+ "epoch": 0.672316384180791,
125
+ "grad_norm": 8.287223815917969,
126
+ "learning_rate": 4.8429648241206034e-05,
127
+ "loss": 0.5715,
128
+ "step": 119
129
+ },
130
+ {
131
+ "epoch": 0.711864406779661,
132
+ "grad_norm": 22.24546241760254,
133
+ "learning_rate": 4.7989949748743725e-05,
134
+ "loss": 0.6342,
135
+ "step": 126
136
+ },
137
+ {
138
+ "epoch": 0.751412429378531,
139
+ "grad_norm": 11.908541679382324,
140
+ "learning_rate": 4.755025125628141e-05,
141
+ "loss": 0.5966,
142
+ "step": 133
143
+ },
144
+ {
145
+ "epoch": 0.7909604519774012,
146
+ "grad_norm": 6.27039909362793,
147
+ "learning_rate": 4.71105527638191e-05,
148
+ "loss": 0.5414,
149
+ "step": 140
150
+ },
151
+ {
152
+ "epoch": 0.8305084745762712,
153
+ "grad_norm": 16.940906524658203,
154
+ "learning_rate": 4.6670854271356784e-05,
155
+ "loss": 0.6909,
156
+ "step": 147
157
+ },
158
+ {
159
+ "epoch": 0.8700564971751412,
160
+ "grad_norm": 10.0083589553833,
161
+ "learning_rate": 4.6231155778894475e-05,
162
+ "loss": 0.5056,
163
+ "step": 154
164
+ },
165
+ {
166
+ "epoch": 0.9096045197740112,
167
+ "grad_norm": 10.436842918395996,
168
+ "learning_rate": 4.5791457286432166e-05,
169
+ "loss": 0.5116,
170
+ "step": 161
171
+ },
172
+ {
173
+ "epoch": 0.9491525423728814,
174
+ "grad_norm": 10.915926933288574,
175
+ "learning_rate": 4.535175879396985e-05,
176
+ "loss": 0.7113,
177
+ "step": 168
178
+ },
179
+ {
180
+ "epoch": 0.9887005649717514,
181
+ "grad_norm": 8.488564491271973,
182
+ "learning_rate": 4.491206030150754e-05,
183
+ "loss": 0.7555,
184
+ "step": 175
185
+ },
186
+ {
187
+ "epoch": 1.0,
188
+ "eval_accuracy": 0.707936507936508,
189
+ "eval_f1_macro": 0.6544353292567254,
190
+ "eval_f1_micro": 0.707936507936508,
191
+ "eval_f1_weighted": 0.693246083160111,
192
+ "eval_loss": 0.5896586775779724,
193
+ "eval_precision_macro": 0.7424193199047,
194
+ "eval_precision_micro": 0.707936507936508,
195
+ "eval_precision_weighted": 0.7052234495704283,
196
+ "eval_recall_macro": 0.6125864829753165,
197
+ "eval_recall_micro": 0.707936507936508,
198
+ "eval_recall_weighted": 0.707936507936508,
199
+ "eval_runtime": 0.843,
200
+ "eval_samples_per_second": 373.658,
201
+ "eval_steps_per_second": 23.724,
202
+ "step": 177
203
+ }
204
+ ],
205
+ "logging_steps": 7,
206
+ "max_steps": 885,
207
+ "num_input_tokens_seen": 0,
208
+ "num_train_epochs": 5,
209
+ "save_steps": 500,
210
+ "total_flos": 93076371521280.0,
211
+ "train_batch_size": 8,
212
+ "trial_name": null,
213
+ "trial_params": null
214
+ }
checkpoint-177/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0fafaae04c1c3f3880710efe8f16cdfc22d2a1f6eec3658c5db9639764eb2f
3
+ size 4984
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "oliverguhr/german-sentiment-bert",
3
+ "_num_labels": 3,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "finetuning_task": "germansentiment",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "negative",
15
+ "1": "neutral",
16
+ "2": "positive"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "negative": 0,
22
+ "neutral": 1,
23
+ "positive": 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": "4.40.1",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 30000
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ede11c254ee8772eed41adf91113db6b28218ed36d65879d12df66f4200718
3
+ size 436358132
runs/May05_11-17-48_r-zerithas-myownmodels-v1-6p5489pl-8156b-5yart/events.out.tfevents.1714907868.r-zerithas-myownmodels-v1-6p5489pl-8156b-5yart.61.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d32e9f861816c8ecb7110e7eea61b87ccb284cd9fe1624f1f5e48466ce8d390c
3
- size 4866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19b69d00a7fc01b98614177b3ab0238c3830bc541e59b91c111ff78a6b16fc2
3
+ size 29791
runs/May05_11-17-48_r-zerithas-myownmodels-v1-6p5489pl-8156b-5yart/events.out.tfevents.1714907952.r-zerithas-myownmodels-v1-6p5489pl-8156b-5yart.61.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3820d43094b9577f2a1e5e4208afef4bdf17a0177d4f4e1812ae9f40b3bea82a
3
+ size 921
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "2": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "3": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0fafaae04c1c3f3880710efe8f16cdfc22d2a1f6eec3658c5db9639764eb2f
3
+ size 4984
training_params.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "v21/autotrain-data",
3
+ "model": "oliverguhr/german-sentiment-bert",
4
+ "lr": 5e-05,
5
+ "epochs": 5,
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": "v21",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "evaluation_strategy": "epoch",
26
+ "username": "Zerithas",
27
+ "log": "tensorboard"
28
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff