Upload ./ with huggingface_hub
Browse files- config.json +54 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +208 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dbmdz/bert-base-turkish-128k-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Lojistik",
|
13 |
+
"1": "Elektrik Kaynagi",
|
14 |
+
"2": "Arama Ekipmani",
|
15 |
+
"3": "Cenaze",
|
16 |
+
"4": "Giysi",
|
17 |
+
"5": "Enkaz Kaldirma",
|
18 |
+
"6": "Isinma",
|
19 |
+
"7": "Bar\u0131nma",
|
20 |
+
"8": "Tuvalet",
|
21 |
+
"9": "Su",
|
22 |
+
"10": "Yemek",
|
23 |
+
"11": "Saglik"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"Arama Ekipmani": 2,
|
29 |
+
"Bar\u0131nma": 7,
|
30 |
+
"Cenaze": 3,
|
31 |
+
"Elektrik Kaynagi": 1,
|
32 |
+
"Enkaz Kaldirma": 5,
|
33 |
+
"Giysi": 4,
|
34 |
+
"Isinma": 6,
|
35 |
+
"Lojistik": 0,
|
36 |
+
"Saglik": 11,
|
37 |
+
"Su": 9,
|
38 |
+
"Tuvalet": 8,
|
39 |
+
"Yemek": 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 |
+
"position_embedding_type": "absolute",
|
48 |
+
"problem_type": "multi_label_classification",
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.26.1",
|
51 |
+
"type_vocab_size": 2,
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 128000
|
54 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc2868d5a8db714ebf9d0d572968b75fe0ece92f8abfeaa804d6989a54df4dcf
|
3 |
+
size 1474954373
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a07fdb3fd82d9bb5a45939f74ade2d0b5db09c659cc1084c1ff898a3bc6ce06e
|
3 |
+
size 737491061
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64d84a501acc3e69dd59a22ff93ff43c806d71b9915703f1b64891dbd900df42
|
3 |
+
size 14575
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc81e80b77ab2c970f6f7bf3d3b21edddb9ce82f2c9177c04030356dbc953210
|
3 |
+
size 557
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c71ca19e7e3b8c14ed531770775ca470b4716a6488b350e7c7074ac6f6cfe65
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8242820390801596,
|
3 |
+
"best_model_checkpoint": "turkish_multilabel_intent_bert-base-turkish-128k-uncased/checkpoint-384",
|
4 |
+
"epoch": 2.887218045112782,
|
5 |
+
"global_step": 384,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.24,
|
12 |
+
"learning_rate": 4.7987362585716124e-05,
|
13 |
+
"loss": 0.0139,
|
14 |
+
"step": 32
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.24,
|
18 |
+
"eval_loss": 0.009882427752017975,
|
19 |
+
"eval_macro f1": 0.3392960248919277,
|
20 |
+
"eval_micro f1": 0.7193911317008603,
|
21 |
+
"eval_runtime": 2.3212,
|
22 |
+
"eval_samples_per_second": 461.408,
|
23 |
+
"eval_steps_per_second": 7.324,
|
24 |
+
"step": 32
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.48,
|
28 |
+
"learning_rate": 4.491617138023029e-05,
|
29 |
+
"loss": 0.0082,
|
30 |
+
"step": 64
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.48,
|
34 |
+
"eval_loss": 0.00571652315557003,
|
35 |
+
"eval_macro f1": 0.5888766985486856,
|
36 |
+
"eval_micro f1": 0.8291472868217056,
|
37 |
+
"eval_runtime": 2.3143,
|
38 |
+
"eval_samples_per_second": 462.783,
|
39 |
+
"eval_steps_per_second": 7.346,
|
40 |
+
"step": 64
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 0.72,
|
44 |
+
"learning_rate": 4.184498017474446e-05,
|
45 |
+
"loss": 0.0062,
|
46 |
+
"step": 96
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.72,
|
50 |
+
"eval_loss": 0.004936754237860441,
|
51 |
+
"eval_macro f1": 0.6479513036422692,
|
52 |
+
"eval_micro f1": 0.8529040404040404,
|
53 |
+
"eval_runtime": 2.335,
|
54 |
+
"eval_samples_per_second": 458.676,
|
55 |
+
"eval_steps_per_second": 7.281,
|
56 |
+
"step": 96
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.96,
|
60 |
+
"learning_rate": 3.877378896925863e-05,
|
61 |
+
"loss": 0.0046,
|
62 |
+
"step": 128
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.96,
|
66 |
+
"eval_loss": 0.0039069755002856255,
|
67 |
+
"eval_macro f1": 0.7036941962393284,
|
68 |
+
"eval_micro f1": 0.8735053492762743,
|
69 |
+
"eval_runtime": 2.3196,
|
70 |
+
"eval_samples_per_second": 461.727,
|
71 |
+
"eval_steps_per_second": 7.329,
|
72 |
+
"step": 128
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.2,
|
76 |
+
"learning_rate": 3.57025977637728e-05,
|
77 |
+
"loss": 0.0035,
|
78 |
+
"step": 160
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 1.2,
|
82 |
+
"eval_loss": 0.003501879284158349,
|
83 |
+
"eval_macro f1": 0.7315796800388726,
|
84 |
+
"eval_micro f1": 0.8865718799368089,
|
85 |
+
"eval_runtime": 2.316,
|
86 |
+
"eval_samples_per_second": 462.435,
|
87 |
+
"eval_steps_per_second": 7.34,
|
88 |
+
"step": 160
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.44,
|
92 |
+
"learning_rate": 3.263140655828696e-05,
|
93 |
+
"loss": 0.0037,
|
94 |
+
"step": 192
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 1.44,
|
98 |
+
"eval_loss": 0.0034342026337981224,
|
99 |
+
"eval_macro f1": 0.7462213705474623,
|
100 |
+
"eval_micro f1": 0.8902361199744736,
|
101 |
+
"eval_runtime": 2.392,
|
102 |
+
"eval_samples_per_second": 447.74,
|
103 |
+
"eval_steps_per_second": 7.107,
|
104 |
+
"step": 192
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.68,
|
108 |
+
"learning_rate": 2.956021535280113e-05,
|
109 |
+
"loss": 0.0032,
|
110 |
+
"step": 224
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.68,
|
114 |
+
"eval_loss": 0.0032742032781243324,
|
115 |
+
"eval_macro f1": 0.7279673266730304,
|
116 |
+
"eval_micro f1": 0.8998085513720486,
|
117 |
+
"eval_runtime": 2.3105,
|
118 |
+
"eval_samples_per_second": 463.546,
|
119 |
+
"eval_steps_per_second": 7.358,
|
120 |
+
"step": 224
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 1.92,
|
124 |
+
"learning_rate": 2.64890241473153e-05,
|
125 |
+
"loss": 0.0033,
|
126 |
+
"step": 256
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 1.92,
|
130 |
+
"eval_loss": 0.003130522323772311,
|
131 |
+
"eval_macro f1": 0.7717739019762423,
|
132 |
+
"eval_micro f1": 0.912258064516129,
|
133 |
+
"eval_runtime": 2.3,
|
134 |
+
"eval_samples_per_second": 465.662,
|
135 |
+
"eval_steps_per_second": 7.391,
|
136 |
+
"step": 256
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 2.17,
|
140 |
+
"learning_rate": 2.3417832941829465e-05,
|
141 |
+
"loss": 0.0025,
|
142 |
+
"step": 288
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 2.17,
|
146 |
+
"eval_loss": 0.0031702849082648754,
|
147 |
+
"eval_macro f1": 0.7845634595933292,
|
148 |
+
"eval_micro f1": 0.9168036829990136,
|
149 |
+
"eval_runtime": 2.3461,
|
150 |
+
"eval_samples_per_second": 456.499,
|
151 |
+
"eval_steps_per_second": 7.246,
|
152 |
+
"step": 288
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.41,
|
156 |
+
"learning_rate": 2.0346641736343635e-05,
|
157 |
+
"loss": 0.0022,
|
158 |
+
"step": 320
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.41,
|
162 |
+
"eval_loss": 0.0030924060847610235,
|
163 |
+
"eval_macro f1": 0.7838887334413882,
|
164 |
+
"eval_micro f1": 0.9131561892417368,
|
165 |
+
"eval_runtime": 2.2918,
|
166 |
+
"eval_samples_per_second": 467.308,
|
167 |
+
"eval_steps_per_second": 7.418,
|
168 |
+
"step": 320
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 2.65,
|
172 |
+
"learning_rate": 1.7275450530857802e-05,
|
173 |
+
"loss": 0.0022,
|
174 |
+
"step": 352
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 2.65,
|
178 |
+
"eval_loss": 0.0030099288560450077,
|
179 |
+
"eval_macro f1": 0.7712848231573721,
|
180 |
+
"eval_micro f1": 0.908565928777671,
|
181 |
+
"eval_runtime": 2.3124,
|
182 |
+
"eval_samples_per_second": 463.146,
|
183 |
+
"eval_steps_per_second": 7.352,
|
184 |
+
"step": 352
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.89,
|
188 |
+
"learning_rate": 1.420425932537197e-05,
|
189 |
+
"loss": 0.0022,
|
190 |
+
"step": 384
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 2.89,
|
194 |
+
"eval_loss": 0.0029520909301936626,
|
195 |
+
"eval_macro f1": 0.8242820390801596,
|
196 |
+
"eval_micro f1": 0.913988964621876,
|
197 |
+
"eval_runtime": 2.3289,
|
198 |
+
"eval_samples_per_second": 459.872,
|
199 |
+
"eval_steps_per_second": 7.3,
|
200 |
+
"step": 384
|
201 |
+
}
|
202 |
+
],
|
203 |
+
"max_steps": 532,
|
204 |
+
"num_train_epochs": 4,
|
205 |
+
"total_flos": 630598146840000.0,
|
206 |
+
"trial_name": null,
|
207 |
+
"trial_params": null
|
208 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df04d1bba26173673f1004e8753370bdc5c93d2bada089b2d6c026f790538c4c
|
3 |
+
size 3579
|