Markus Serloth-Schwarzer
commited on
Commit
•
27ab780
1
Parent(s):
489af13
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 +470 -0
- checkpoint-358/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/May09_20-25-11_r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt/events.out.tfevents.1715286311.r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt.59.0 +2 -2
- runs/May09_20-25-11_r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt/events.out.tfevents.1715286418.r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt.59.1 +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-df1750/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.5988922119140625
|
18 |
+
|
19 |
+
f1_macro: 0.7197485594552121
|
20 |
+
|
21 |
+
f1_micro: 0.7444444444444445
|
22 |
+
|
23 |
+
f1_weighted: 0.7445899540189744
|
24 |
+
|
25 |
+
precision_macro: 0.8311385930760716
|
26 |
+
|
27 |
+
precision_micro: 0.7444444444444445
|
28 |
+
|
29 |
+
precision_weighted: 0.7729251752611423
|
30 |
+
|
31 |
+
recall_macro: 0.6798505487345509
|
32 |
+
|
33 |
+
recall_micro: 0.7444444444444445
|
34 |
+
|
35 |
+
recall_weighted: 0.7444444444444445
|
36 |
+
|
37 |
+
accuracy: 0.7444444444444445
|
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 sha256:24fba2b6ab75eb6802621bcdda26edaad8bb3513ace8d4f08cd25756e0317eac
|
3 |
+
size 436358132
|
checkpoint-358/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d292337b8ca5fb78b7e8bc7d8b5761e43737d99405ee88bd376d1a0a415c0346
|
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 sha256:4ad4a0db14e6b35369ed3a769d4643f789d6102896ccfb8b46d2a6f25646f335
|
3 |
+
size 1064
|
checkpoint-358/trainer_state.json
ADDED
@@ -0,0 +1,470 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5988922119140625,
|
3 |
+
"best_model_checkpoint": "autotrain-df1750/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": 0.0335195530726257,
|
13 |
+
"grad_norm": 73.59092712402344,
|
14 |
+
"learning_rate": 1.6666666666666667e-06,
|
15 |
+
"loss": 2.6702,
|
16 |
+
"step": 6
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0670391061452514,
|
20 |
+
"grad_norm": 73.304931640625,
|
21 |
+
"learning_rate": 4.444444444444445e-06,
|
22 |
+
"loss": 3.0755,
|
23 |
+
"step": 12
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1005586592178771,
|
27 |
+
"grad_norm": 23.852195739746094,
|
28 |
+
"learning_rate": 7.777777777777777e-06,
|
29 |
+
"loss": 1.8661,
|
30 |
+
"step": 18
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1340782122905028,
|
34 |
+
"grad_norm": 38.33709716796875,
|
35 |
+
"learning_rate": 1.1111111111111112e-05,
|
36 |
+
"loss": 1.3438,
|
37 |
+
"step": 24
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.16759776536312848,
|
41 |
+
"grad_norm": 87.00068664550781,
|
42 |
+
"learning_rate": 1.4444444444444444e-05,
|
43 |
+
"loss": 1.4881,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2011173184357542,
|
48 |
+
"grad_norm": 46.23602294921875,
|
49 |
+
"learning_rate": 1.777777777777778e-05,
|
50 |
+
"loss": 1.8771,
|
51 |
+
"step": 36
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2346368715083799,
|
55 |
+
"grad_norm": 18.535837173461914,
|
56 |
+
"learning_rate": 2.111111111111111e-05,
|
57 |
+
"loss": 1.0011,
|
58 |
+
"step": 42
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2681564245810056,
|
62 |
+
"grad_norm": 11.598855018615723,
|
63 |
+
"learning_rate": 2.4444444444444445e-05,
|
64 |
+
"loss": 1.0259,
|
65 |
+
"step": 48
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3016759776536313,
|
69 |
+
"grad_norm": 3.8503451347351074,
|
70 |
+
"learning_rate": 2.777777777777778e-05,
|
71 |
+
"loss": 0.8544,
|
72 |
+
"step": 54
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.33519553072625696,
|
76 |
+
"grad_norm": 27.00203514099121,
|
77 |
+
"learning_rate": 3.111111111111111e-05,
|
78 |
+
"loss": 0.8838,
|
79 |
+
"step": 60
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3687150837988827,
|
83 |
+
"grad_norm": 9.515172958374023,
|
84 |
+
"learning_rate": 3.444444444444445e-05,
|
85 |
+
"loss": 0.7537,
|
86 |
+
"step": 66
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.4022346368715084,
|
90 |
+
"grad_norm": 6.722465991973877,
|
91 |
+
"learning_rate": 3.777777777777778e-05,
|
92 |
+
"loss": 0.6945,
|
93 |
+
"step": 72
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.43575418994413406,
|
97 |
+
"grad_norm": 3.381333112716675,
|
98 |
+
"learning_rate": 4.111111111111111e-05,
|
99 |
+
"loss": 0.7916,
|
100 |
+
"step": 78
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.4692737430167598,
|
104 |
+
"grad_norm": 6.028005123138428,
|
105 |
+
"learning_rate": 4.4444444444444447e-05,
|
106 |
+
"loss": 0.7535,
|
107 |
+
"step": 84
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5027932960893855,
|
111 |
+
"grad_norm": 2.521240234375,
|
112 |
+
"learning_rate": 4.7777777777777784e-05,
|
113 |
+
"loss": 0.6608,
|
114 |
+
"step": 90
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5363128491620112,
|
118 |
+
"grad_norm": 11.346482276916504,
|
119 |
+
"learning_rate": 4.9875776397515526e-05,
|
120 |
+
"loss": 0.8989,
|
121 |
+
"step": 96
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5698324022346368,
|
125 |
+
"grad_norm": 4.411192893981934,
|
126 |
+
"learning_rate": 4.9503105590062115e-05,
|
127 |
+
"loss": 0.6739,
|
128 |
+
"step": 102
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6033519553072626,
|
132 |
+
"grad_norm": 7.383223533630371,
|
133 |
+
"learning_rate": 4.91304347826087e-05,
|
134 |
+
"loss": 0.6012,
|
135 |
+
"step": 108
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6368715083798883,
|
139 |
+
"grad_norm": 22.263490676879883,
|
140 |
+
"learning_rate": 4.875776397515528e-05,
|
141 |
+
"loss": 0.6424,
|
142 |
+
"step": 114
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.6703910614525139,
|
146 |
+
"grad_norm": 11.658171653747559,
|
147 |
+
"learning_rate": 4.8385093167701864e-05,
|
148 |
+
"loss": 0.6272,
|
149 |
+
"step": 120
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.7039106145251397,
|
153 |
+
"grad_norm": 12.783892631530762,
|
154 |
+
"learning_rate": 4.801242236024845e-05,
|
155 |
+
"loss": 0.6088,
|
156 |
+
"step": 126
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7374301675977654,
|
160 |
+
"grad_norm": 33.83137893676758,
|
161 |
+
"learning_rate": 4.763975155279503e-05,
|
162 |
+
"loss": 0.7344,
|
163 |
+
"step": 132
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.770949720670391,
|
167 |
+
"grad_norm": 9.561176300048828,
|
168 |
+
"learning_rate": 4.726708074534162e-05,
|
169 |
+
"loss": 0.7418,
|
170 |
+
"step": 138
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.8044692737430168,
|
174 |
+
"grad_norm": 8.497224807739258,
|
175 |
+
"learning_rate": 4.68944099378882e-05,
|
176 |
+
"loss": 0.5052,
|
177 |
+
"step": 144
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8379888268156425,
|
181 |
+
"grad_norm": 11.237218856811523,
|
182 |
+
"learning_rate": 4.6521739130434785e-05,
|
183 |
+
"loss": 0.7463,
|
184 |
+
"step": 150
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8715083798882681,
|
188 |
+
"grad_norm": 5.342649459838867,
|
189 |
+
"learning_rate": 4.614906832298137e-05,
|
190 |
+
"loss": 0.5899,
|
191 |
+
"step": 156
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.9050279329608939,
|
195 |
+
"grad_norm": 9.221810340881348,
|
196 |
+
"learning_rate": 4.577639751552795e-05,
|
197 |
+
"loss": 0.6203,
|
198 |
+
"step": 162
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.9385474860335196,
|
202 |
+
"grad_norm": 8.265608787536621,
|
203 |
+
"learning_rate": 4.5403726708074534e-05,
|
204 |
+
"loss": 0.6055,
|
205 |
+
"step": 168
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.9720670391061452,
|
209 |
+
"grad_norm": 41.970157623291016,
|
210 |
+
"learning_rate": 4.5031055900621124e-05,
|
211 |
+
"loss": 0.76,
|
212 |
+
"step": 174
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.0,
|
216 |
+
"eval_accuracy": 0.6777777777777778,
|
217 |
+
"eval_f1_macro": 0.6235276146807568,
|
218 |
+
"eval_f1_micro": 0.6777777777777778,
|
219 |
+
"eval_f1_weighted": 0.6417678337751553,
|
220 |
+
"eval_loss": 0.6414533853530884,
|
221 |
+
"eval_precision_macro": 0.6587301587301587,
|
222 |
+
"eval_precision_micro": 0.6777777777777778,
|
223 |
+
"eval_precision_weighted": 0.7171075837742504,
|
224 |
+
"eval_recall_macro": 0.7109298963614522,
|
225 |
+
"eval_recall_micro": 0.6777777777777778,
|
226 |
+
"eval_recall_weighted": 0.6777777777777778,
|
227 |
+
"eval_runtime": 0.7181,
|
228 |
+
"eval_samples_per_second": 375.983,
|
229 |
+
"eval_steps_per_second": 23.673,
|
230 |
+
"step": 179
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.005586592178771,
|
234 |
+
"grad_norm": 19.538753509521484,
|
235 |
+
"learning_rate": 4.465838509316771e-05,
|
236 |
+
"loss": 0.6712,
|
237 |
+
"step": 180
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.0391061452513966,
|
241 |
+
"grad_norm": 3.879540205001831,
|
242 |
+
"learning_rate": 4.428571428571428e-05,
|
243 |
+
"loss": 0.5233,
|
244 |
+
"step": 186
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.0726256983240223,
|
248 |
+
"grad_norm": 3.905611515045166,
|
249 |
+
"learning_rate": 4.391304347826087e-05,
|
250 |
+
"loss": 0.5226,
|
251 |
+
"step": 192
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.106145251396648,
|
255 |
+
"grad_norm": 5.837283611297607,
|
256 |
+
"learning_rate": 4.3540372670807455e-05,
|
257 |
+
"loss": 0.5184,
|
258 |
+
"step": 198
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.1396648044692737,
|
262 |
+
"grad_norm": 13.354449272155762,
|
263 |
+
"learning_rate": 4.316770186335404e-05,
|
264 |
+
"loss": 0.4915,
|
265 |
+
"step": 204
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.1731843575418994,
|
269 |
+
"grad_norm": 14.286345481872559,
|
270 |
+
"learning_rate": 4.279503105590063e-05,
|
271 |
+
"loss": 0.6749,
|
272 |
+
"step": 210
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.2067039106145252,
|
276 |
+
"grad_norm": 18.75254249572754,
|
277 |
+
"learning_rate": 4.2422360248447204e-05,
|
278 |
+
"loss": 0.4622,
|
279 |
+
"step": 216
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.2402234636871508,
|
283 |
+
"grad_norm": 14.3436279296875,
|
284 |
+
"learning_rate": 4.204968944099379e-05,
|
285 |
+
"loss": 0.4796,
|
286 |
+
"step": 222
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.2737430167597765,
|
290 |
+
"grad_norm": 8.52850341796875,
|
291 |
+
"learning_rate": 4.167701863354038e-05,
|
292 |
+
"loss": 0.5933,
|
293 |
+
"step": 228
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.3072625698324023,
|
297 |
+
"grad_norm": 8.049199104309082,
|
298 |
+
"learning_rate": 4.130434782608696e-05,
|
299 |
+
"loss": 0.4508,
|
300 |
+
"step": 234
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.3407821229050279,
|
304 |
+
"grad_norm": 12.118001937866211,
|
305 |
+
"learning_rate": 4.093167701863354e-05,
|
306 |
+
"loss": 0.6934,
|
307 |
+
"step": 240
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.3743016759776536,
|
311 |
+
"grad_norm": 8.314793586730957,
|
312 |
+
"learning_rate": 4.0559006211180126e-05,
|
313 |
+
"loss": 0.6691,
|
314 |
+
"step": 246
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.4078212290502794,
|
318 |
+
"grad_norm": 48.661590576171875,
|
319 |
+
"learning_rate": 4.018633540372671e-05,
|
320 |
+
"loss": 0.3235,
|
321 |
+
"step": 252
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.441340782122905,
|
325 |
+
"grad_norm": 13.549777030944824,
|
326 |
+
"learning_rate": 3.981366459627329e-05,
|
327 |
+
"loss": 0.5038,
|
328 |
+
"step": 258
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.4748603351955307,
|
332 |
+
"grad_norm": 8.670489311218262,
|
333 |
+
"learning_rate": 3.944099378881988e-05,
|
334 |
+
"loss": 0.418,
|
335 |
+
"step": 264
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.5083798882681565,
|
339 |
+
"grad_norm": 31.06993865966797,
|
340 |
+
"learning_rate": 3.9068322981366464e-05,
|
341 |
+
"loss": 0.4584,
|
342 |
+
"step": 270
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.541899441340782,
|
346 |
+
"grad_norm": 10.52939510345459,
|
347 |
+
"learning_rate": 3.869565217391305e-05,
|
348 |
+
"loss": 0.5596,
|
349 |
+
"step": 276
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.5754189944134078,
|
353 |
+
"grad_norm": 12.9683198928833,
|
354 |
+
"learning_rate": 3.832298136645963e-05,
|
355 |
+
"loss": 0.4865,
|
356 |
+
"step": 282
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.6089385474860336,
|
360 |
+
"grad_norm": 8.783909797668457,
|
361 |
+
"learning_rate": 3.795031055900621e-05,
|
362 |
+
"loss": 0.5476,
|
363 |
+
"step": 288
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 1.6424581005586592,
|
367 |
+
"grad_norm": 18.032865524291992,
|
368 |
+
"learning_rate": 3.7577639751552796e-05,
|
369 |
+
"loss": 0.6996,
|
370 |
+
"step": 294
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.675977653631285,
|
374 |
+
"grad_norm": 5.003455638885498,
|
375 |
+
"learning_rate": 3.7204968944099385e-05,
|
376 |
+
"loss": 0.5503,
|
377 |
+
"step": 300
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.7094972067039107,
|
381 |
+
"grad_norm": 16.561975479125977,
|
382 |
+
"learning_rate": 3.683229813664597e-05,
|
383 |
+
"loss": 0.6051,
|
384 |
+
"step": 306
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.7430167597765363,
|
388 |
+
"grad_norm": 6.354936122894287,
|
389 |
+
"learning_rate": 3.6459627329192544e-05,
|
390 |
+
"loss": 0.6112,
|
391 |
+
"step": 312
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 1.776536312849162,
|
395 |
+
"grad_norm": 4.840208530426025,
|
396 |
+
"learning_rate": 3.6086956521739134e-05,
|
397 |
+
"loss": 0.429,
|
398 |
+
"step": 318
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.8100558659217878,
|
402 |
+
"grad_norm": 7.309473991394043,
|
403 |
+
"learning_rate": 3.571428571428572e-05,
|
404 |
+
"loss": 0.3584,
|
405 |
+
"step": 324
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.8435754189944134,
|
409 |
+
"grad_norm": 17.3754825592041,
|
410 |
+
"learning_rate": 3.53416149068323e-05,
|
411 |
+
"loss": 0.3328,
|
412 |
+
"step": 330
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.8770949720670391,
|
416 |
+
"grad_norm": 12.939613342285156,
|
417 |
+
"learning_rate": 3.496894409937889e-05,
|
418 |
+
"loss": 0.5574,
|
419 |
+
"step": 336
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.910614525139665,
|
423 |
+
"grad_norm": 10.317028999328613,
|
424 |
+
"learning_rate": 3.4596273291925466e-05,
|
425 |
+
"loss": 0.4618,
|
426 |
+
"step": 342
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 1.9441340782122905,
|
430 |
+
"grad_norm": 11.774768829345703,
|
431 |
+
"learning_rate": 3.422360248447205e-05,
|
432 |
+
"loss": 0.396,
|
433 |
+
"step": 348
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 1.9776536312849162,
|
437 |
+
"grad_norm": 12.681093215942383,
|
438 |
+
"learning_rate": 3.385093167701863e-05,
|
439 |
+
"loss": 0.5958,
|
440 |
+
"step": 354
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 2.0,
|
444 |
+
"eval_accuracy": 0.7444444444444445,
|
445 |
+
"eval_f1_macro": 0.7197485594552121,
|
446 |
+
"eval_f1_micro": 0.7444444444444445,
|
447 |
+
"eval_f1_weighted": 0.7445899540189744,
|
448 |
+
"eval_loss": 0.5988922119140625,
|
449 |
+
"eval_precision_macro": 0.8311385930760716,
|
450 |
+
"eval_precision_micro": 0.7444444444444445,
|
451 |
+
"eval_precision_weighted": 0.7729251752611423,
|
452 |
+
"eval_recall_macro": 0.6798505487345509,
|
453 |
+
"eval_recall_micro": 0.7444444444444445,
|
454 |
+
"eval_recall_weighted": 0.7444444444444445,
|
455 |
+
"eval_runtime": 0.7117,
|
456 |
+
"eval_samples_per_second": 379.359,
|
457 |
+
"eval_steps_per_second": 23.886,
|
458 |
+
"step": 358
|
459 |
+
}
|
460 |
+
],
|
461 |
+
"logging_steps": 6,
|
462 |
+
"max_steps": 895,
|
463 |
+
"num_input_tokens_seen": 0,
|
464 |
+
"num_train_epochs": 5,
|
465 |
+
"save_steps": 500,
|
466 |
+
"total_flos": 188389207093248.0,
|
467 |
+
"train_batch_size": 8,
|
468 |
+
"trial_name": null,
|
469 |
+
"trial_params": null
|
470 |
+
}
|
checkpoint-358/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31496e0cb13ad5d6cd9074a1fbc28a21d7d8aa565e741485a38edff9fdca5bec
|
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 sha256:24fba2b6ab75eb6802621bcdda26edaad8bb3513ace8d4f08cd25756e0317eac
|
3 |
+
size 436358132
|
runs/May09_20-25-11_r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt/events.out.tfevents.1715286311.r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt.59.0
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 sha256:42e593421e2a92840180f23383229e6a282f4b4f12358dd8cb34b78818de9798
|
3 |
+
size 40779
|
runs/May09_20-25-11_r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt/events.out.tfevents.1715286418.r-zerithas-myownmodels-v1-xqlm9i2n-c3ea0-53lkt.59.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e033d3b01be4ea96a5fc20d4c4175a8b0cc866f51bf32f7873edc795c781cf4
|
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 sha256:31496e0cb13ad5d6cd9074a1fbc28a21d7d8aa565e741485a38edff9fdca5bec
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-df1750/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": "autotrain-df1750",
|
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
|
|