Markus Serloth-Schwarzer
commited on
Commit
•
95ec84e
1
Parent(s):
02e0eb6
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-358/config.json +38 -0
- checkpoint-358/model.safetensors +3 -0
- checkpoint-358/optimizer.pt +3 -0
- checkpoint-358/rng_state.pth +3 -0
- checkpoint-358/scheduler.pt +3 -0
- checkpoint-358/trainer_state.json +414 -0
- checkpoint-358/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/May09_20-59-32_r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu/events.out.tfevents.1715288373.r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu.61.0 +2 -2
- runs/May09_20-59-32_r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu/events.out.tfevents.1715288436.r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu.61.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +28 -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-df1770/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.5543721318244934
|
18 |
+
|
19 |
+
f1_macro: 0.7679742314070671
|
20 |
+
|
21 |
+
f1_micro: 0.7777777777777778
|
22 |
+
|
23 |
+
f1_weighted: 0.7707658289747842
|
24 |
+
|
25 |
+
precision_macro: 0.7848406546080966
|
26 |
+
|
27 |
+
precision_micro: 0.7777777777777778
|
28 |
+
|
29 |
+
precision_weighted: 0.7778696525983347
|
30 |
+
|
31 |
+
recall_macro: 0.7620894891084323
|
32 |
+
|
33 |
+
recall_micro: 0.7777777777777778
|
34 |
+
|
35 |
+
recall_weighted: 0.7777777777777778
|
36 |
+
|
37 |
+
accuracy: 0.7777777777777778
|
checkpoint-358/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-358/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa35e386bcb6d05883882a045e9e5520d3b382d42a52bcb68d41f4cb4628cbc8
|
3 |
+
size 436358132
|
checkpoint-358/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bd4bae24da1f02b1b88674e62abbdf305d2dbfc88c7b25f02a578639ee8afa6
|
3 |
+
size 872837370
|
checkpoint-358/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77a91a1e219bba43507a1274dfd27d4d9a8bbd8422c54cafd6ede13bb9de2e25
|
3 |
+
size 14244
|
checkpoint-358/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b1044cd1233e65bcc195c80ba0eb84054070ff00b7f6a4d3bb6c667322091d1
|
3 |
+
size 1064
|
checkpoint-358/trainer_state.json
ADDED
@@ -0,0 +1,414 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5543721318244934,
|
3 |
+
"best_model_checkpoint": "autotrain-df1770/checkpoint-358",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 358,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03910614525139665,
|
13 |
+
"grad_norm": Infinity,
|
14 |
+
"learning_rate": 2.777777777777778e-06,
|
15 |
+
"loss": 2.7849,
|
16 |
+
"step": 7
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0782122905027933,
|
20 |
+
"grad_norm": 26.998300552368164,
|
21 |
+
"learning_rate": 8.333333333333334e-06,
|
22 |
+
"loss": 2.7974,
|
23 |
+
"step": 14
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.11731843575418995,
|
27 |
+
"grad_norm": 72.14756774902344,
|
28 |
+
"learning_rate": 1.4814814814814815e-05,
|
29 |
+
"loss": 1.3511,
|
30 |
+
"step": 21
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1564245810055866,
|
34 |
+
"grad_norm": 40.11323165893555,
|
35 |
+
"learning_rate": 2.1296296296296296e-05,
|
36 |
+
"loss": 1.2651,
|
37 |
+
"step": 28
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.19553072625698323,
|
41 |
+
"grad_norm": 34.13031768798828,
|
42 |
+
"learning_rate": 2.777777777777778e-05,
|
43 |
+
"loss": 1.65,
|
44 |
+
"step": 35
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2346368715083799,
|
48 |
+
"grad_norm": 4.031013488769531,
|
49 |
+
"learning_rate": 3.425925925925926e-05,
|
50 |
+
"loss": 0.7898,
|
51 |
+
"step": 42
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2737430167597765,
|
55 |
+
"grad_norm": 37.36408615112305,
|
56 |
+
"learning_rate": 4.074074074074074e-05,
|
57 |
+
"loss": 0.7657,
|
58 |
+
"step": 49
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.3128491620111732,
|
62 |
+
"grad_norm": 9.450926780700684,
|
63 |
+
"learning_rate": 4.722222222222222e-05,
|
64 |
+
"loss": 0.7868,
|
65 |
+
"step": 56
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.35195530726256985,
|
69 |
+
"grad_norm": 5.750401496887207,
|
70 |
+
"learning_rate": 4.958592132505176e-05,
|
71 |
+
"loss": 0.9469,
|
72 |
+
"step": 63
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.39106145251396646,
|
76 |
+
"grad_norm": 6.385225772857666,
|
77 |
+
"learning_rate": 4.886128364389234e-05,
|
78 |
+
"loss": 0.7381,
|
79 |
+
"step": 70
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.4301675977653631,
|
83 |
+
"grad_norm": 5.707835674285889,
|
84 |
+
"learning_rate": 4.8136645962732924e-05,
|
85 |
+
"loss": 0.7006,
|
86 |
+
"step": 77
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.4692737430167598,
|
90 |
+
"grad_norm": 14.439386367797852,
|
91 |
+
"learning_rate": 4.74120082815735e-05,
|
92 |
+
"loss": 0.6639,
|
93 |
+
"step": 84
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5083798882681564,
|
97 |
+
"grad_norm": 26.590147018432617,
|
98 |
+
"learning_rate": 4.668737060041408e-05,
|
99 |
+
"loss": 0.7436,
|
100 |
+
"step": 91
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.547486033519553,
|
104 |
+
"grad_norm": 8.74451732635498,
|
105 |
+
"learning_rate": 4.5962732919254656e-05,
|
106 |
+
"loss": 0.6531,
|
107 |
+
"step": 98
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5865921787709497,
|
111 |
+
"grad_norm": 14.613375663757324,
|
112 |
+
"learning_rate": 4.523809523809524e-05,
|
113 |
+
"loss": 0.5502,
|
114 |
+
"step": 105
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.6256983240223464,
|
118 |
+
"grad_norm": 18.908952713012695,
|
119 |
+
"learning_rate": 4.451345755693582e-05,
|
120 |
+
"loss": 0.578,
|
121 |
+
"step": 112
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.664804469273743,
|
125 |
+
"grad_norm": 7.9073333740234375,
|
126 |
+
"learning_rate": 4.3788819875776396e-05,
|
127 |
+
"loss": 0.6046,
|
128 |
+
"step": 119
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.7039106145251397,
|
132 |
+
"grad_norm": 13.5628080368042,
|
133 |
+
"learning_rate": 4.306418219461698e-05,
|
134 |
+
"loss": 0.6825,
|
135 |
+
"step": 126
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.7430167597765364,
|
139 |
+
"grad_norm": 21.76129913330078,
|
140 |
+
"learning_rate": 4.233954451345756e-05,
|
141 |
+
"loss": 0.6136,
|
142 |
+
"step": 133
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.7821229050279329,
|
146 |
+
"grad_norm": 8.919886589050293,
|
147 |
+
"learning_rate": 4.161490683229814e-05,
|
148 |
+
"loss": 0.7172,
|
149 |
+
"step": 140
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.8212290502793296,
|
153 |
+
"grad_norm": 17.3486270904541,
|
154 |
+
"learning_rate": 4.089026915113872e-05,
|
155 |
+
"loss": 0.6536,
|
156 |
+
"step": 147
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.8603351955307262,
|
160 |
+
"grad_norm": 5.042856693267822,
|
161 |
+
"learning_rate": 4.01656314699793e-05,
|
162 |
+
"loss": 0.5795,
|
163 |
+
"step": 154
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.8994413407821229,
|
167 |
+
"grad_norm": 10.089982032775879,
|
168 |
+
"learning_rate": 3.944099378881988e-05,
|
169 |
+
"loss": 0.4422,
|
170 |
+
"step": 161
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.9385474860335196,
|
174 |
+
"grad_norm": 8.185463905334473,
|
175 |
+
"learning_rate": 3.8716356107660456e-05,
|
176 |
+
"loss": 0.5781,
|
177 |
+
"step": 168
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.9776536312849162,
|
181 |
+
"grad_norm": 8.611544609069824,
|
182 |
+
"learning_rate": 3.799171842650104e-05,
|
183 |
+
"loss": 0.7085,
|
184 |
+
"step": 175
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.0,
|
188 |
+
"eval_accuracy": 0.6793650793650794,
|
189 |
+
"eval_f1_macro": 0.5782240623162028,
|
190 |
+
"eval_f1_micro": 0.6793650793650794,
|
191 |
+
"eval_f1_weighted": 0.6491507979511092,
|
192 |
+
"eval_loss": 0.7037036418914795,
|
193 |
+
"eval_precision_macro": 0.6092237192939769,
|
194 |
+
"eval_precision_micro": 0.6793650793650794,
|
195 |
+
"eval_precision_weighted": 0.7107957653290541,
|
196 |
+
"eval_recall_macro": 0.6734765400767394,
|
197 |
+
"eval_recall_micro": 0.6793650793650794,
|
198 |
+
"eval_recall_weighted": 0.6793650793650794,
|
199 |
+
"eval_runtime": 0.8316,
|
200 |
+
"eval_samples_per_second": 378.776,
|
201 |
+
"eval_steps_per_second": 24.049,
|
202 |
+
"step": 179
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.0167597765363128,
|
206 |
+
"grad_norm": 6.034320831298828,
|
207 |
+
"learning_rate": 3.7267080745341614e-05,
|
208 |
+
"loss": 0.5818,
|
209 |
+
"step": 182
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.0558659217877095,
|
213 |
+
"grad_norm": 4.3413405418396,
|
214 |
+
"learning_rate": 3.6542443064182196e-05,
|
215 |
+
"loss": 0.4607,
|
216 |
+
"step": 189
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.094972067039106,
|
220 |
+
"grad_norm": 7.182992935180664,
|
221 |
+
"learning_rate": 3.581780538302277e-05,
|
222 |
+
"loss": 0.5552,
|
223 |
+
"step": 196
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.1340782122905029,
|
227 |
+
"grad_norm": 25.679845809936523,
|
228 |
+
"learning_rate": 3.509316770186335e-05,
|
229 |
+
"loss": 0.357,
|
230 |
+
"step": 203
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.1731843575418994,
|
234 |
+
"grad_norm": 15.53803825378418,
|
235 |
+
"learning_rate": 3.4368530020703935e-05,
|
236 |
+
"loss": 0.5809,
|
237 |
+
"step": 210
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.2122905027932962,
|
241 |
+
"grad_norm": 17.502534866333008,
|
242 |
+
"learning_rate": 3.364389233954452e-05,
|
243 |
+
"loss": 0.5119,
|
244 |
+
"step": 217
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.2513966480446927,
|
248 |
+
"grad_norm": 20.31743621826172,
|
249 |
+
"learning_rate": 3.29192546583851e-05,
|
250 |
+
"loss": 0.5289,
|
251 |
+
"step": 224
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.2905027932960893,
|
255 |
+
"grad_norm": 46.659828186035156,
|
256 |
+
"learning_rate": 3.2194616977225674e-05,
|
257 |
+
"loss": 0.6035,
|
258 |
+
"step": 231
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.329608938547486,
|
262 |
+
"grad_norm": 20.15818214416504,
|
263 |
+
"learning_rate": 3.1469979296066256e-05,
|
264 |
+
"loss": 0.5148,
|
265 |
+
"step": 238
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.3687150837988826,
|
269 |
+
"grad_norm": 6.627427101135254,
|
270 |
+
"learning_rate": 3.074534161490684e-05,
|
271 |
+
"loss": 0.5968,
|
272 |
+
"step": 245
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.4078212290502794,
|
276 |
+
"grad_norm": 11.544679641723633,
|
277 |
+
"learning_rate": 3.0020703933747414e-05,
|
278 |
+
"loss": 0.2539,
|
279 |
+
"step": 252
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.446927374301676,
|
283 |
+
"grad_norm": 4.748214244842529,
|
284 |
+
"learning_rate": 2.9296066252587996e-05,
|
285 |
+
"loss": 0.4293,
|
286 |
+
"step": 259
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.4860335195530725,
|
290 |
+
"grad_norm": 28.907987594604492,
|
291 |
+
"learning_rate": 2.857142857142857e-05,
|
292 |
+
"loss": 0.5849,
|
293 |
+
"step": 266
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.5251396648044693,
|
297 |
+
"grad_norm": 12.41960334777832,
|
298 |
+
"learning_rate": 2.7846790890269153e-05,
|
299 |
+
"loss": 0.4464,
|
300 |
+
"step": 273
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.564245810055866,
|
304 |
+
"grad_norm": 22.844667434692383,
|
305 |
+
"learning_rate": 2.7122153209109728e-05,
|
306 |
+
"loss": 0.514,
|
307 |
+
"step": 280
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.6033519553072626,
|
311 |
+
"grad_norm": 16.901336669921875,
|
312 |
+
"learning_rate": 2.639751552795031e-05,
|
313 |
+
"loss": 0.4497,
|
314 |
+
"step": 287
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.6424581005586592,
|
318 |
+
"grad_norm": 23.846860885620117,
|
319 |
+
"learning_rate": 2.5672877846790892e-05,
|
320 |
+
"loss": 0.5861,
|
321 |
+
"step": 294
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.6815642458100557,
|
325 |
+
"grad_norm": 28.805133819580078,
|
326 |
+
"learning_rate": 2.494824016563147e-05,
|
327 |
+
"loss": 0.4996,
|
328 |
+
"step": 301
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.7206703910614525,
|
332 |
+
"grad_norm": 12.11324405670166,
|
333 |
+
"learning_rate": 2.4223602484472053e-05,
|
334 |
+
"loss": 0.487,
|
335 |
+
"step": 308
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.7597765363128492,
|
339 |
+
"grad_norm": 12.710243225097656,
|
340 |
+
"learning_rate": 2.349896480331263e-05,
|
341 |
+
"loss": 0.62,
|
342 |
+
"step": 315
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.7988826815642458,
|
346 |
+
"grad_norm": 16.51240348815918,
|
347 |
+
"learning_rate": 2.277432712215321e-05,
|
348 |
+
"loss": 0.3526,
|
349 |
+
"step": 322
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.8379888268156424,
|
353 |
+
"grad_norm": 13.733351707458496,
|
354 |
+
"learning_rate": 2.204968944099379e-05,
|
355 |
+
"loss": 0.3458,
|
356 |
+
"step": 329
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.8770949720670391,
|
360 |
+
"grad_norm": 6.4348344802856445,
|
361 |
+
"learning_rate": 2.1325051759834367e-05,
|
362 |
+
"loss": 0.3579,
|
363 |
+
"step": 336
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 1.916201117318436,
|
367 |
+
"grad_norm": 8.98593521118164,
|
368 |
+
"learning_rate": 2.060041407867495e-05,
|
369 |
+
"loss": 0.4135,
|
370 |
+
"step": 343
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.9553072625698324,
|
374 |
+
"grad_norm": 6.583544731140137,
|
375 |
+
"learning_rate": 1.9875776397515528e-05,
|
376 |
+
"loss": 0.2938,
|
377 |
+
"step": 350
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.994413407821229,
|
381 |
+
"grad_norm": 30.63981819152832,
|
382 |
+
"learning_rate": 1.915113871635611e-05,
|
383 |
+
"loss": 0.6931,
|
384 |
+
"step": 357
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 2.0,
|
388 |
+
"eval_accuracy": 0.7777777777777778,
|
389 |
+
"eval_f1_macro": 0.7679742314070671,
|
390 |
+
"eval_f1_micro": 0.7777777777777778,
|
391 |
+
"eval_f1_weighted": 0.7707658289747842,
|
392 |
+
"eval_loss": 0.5543721318244934,
|
393 |
+
"eval_precision_macro": 0.7848406546080966,
|
394 |
+
"eval_precision_micro": 0.7777777777777778,
|
395 |
+
"eval_precision_weighted": 0.7778696525983347,
|
396 |
+
"eval_recall_macro": 0.7620894891084323,
|
397 |
+
"eval_recall_micro": 0.7777777777777778,
|
398 |
+
"eval_recall_weighted": 0.7777777777777778,
|
399 |
+
"eval_runtime": 0.8305,
|
400 |
+
"eval_samples_per_second": 379.305,
|
401 |
+
"eval_steps_per_second": 24.083,
|
402 |
+
"step": 358
|
403 |
+
}
|
404 |
+
],
|
405 |
+
"logging_steps": 7,
|
406 |
+
"max_steps": 537,
|
407 |
+
"num_input_tokens_seen": 0,
|
408 |
+
"num_train_epochs": 3,
|
409 |
+
"save_steps": 500,
|
410 |
+
"total_flos": 188389207093248.0,
|
411 |
+
"train_batch_size": 8,
|
412 |
+
"trial_name": null,
|
413 |
+
"trial_params": null
|
414 |
+
}
|
checkpoint-358/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4da452457ed00503c13dba9d376a486337df1bca4546c2e0622ebf2467c596c
|
3 |
+
size 5048
|
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:fa35e386bcb6d05883882a045e9e5520d3b382d42a52bcb68d41f4cb4628cbc8
|
3 |
+
size 436358132
|
runs/May09_20-59-32_r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu/events.out.tfevents.1715288373.r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu.61.0
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 sha256:98c7f099faa3940d9838c53e0579978a9e24c6721860d20261a6dd0c54b359e7
|
3 |
+
size 23722
|
runs/May09_20-59-32_r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu/events.out.tfevents.1715288436.r-zerithas-myownmodels-v1-vp02a72g-ba25f-b21nu.61.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f84172fd3c087028fd34a2456801eb2dda1c2f90effe4931f01366a61294b25a
|
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:b4da452457ed00503c13dba9d376a486337df1bca4546c2e0622ebf2467c596c
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-df1770/autotrain-data",
|
3 |
+
"model": "oliverguhr/german-sentiment-bert",
|
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-df1770",
|
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
|
|