Amr Keleg
commited on
Commit
•
c6e93fe
1
Parent(s):
4fe5854
Track the final version of the model
Browse files- config.json +48 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +300 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "UBC-NLP/MARBERT",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2,
|
27 |
+
"LABEL_3": 3,
|
28 |
+
"LABEL_4": 4,
|
29 |
+
"LABEL_5": 5
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-12,
|
32 |
+
"max_position_embeddings": 512,
|
33 |
+
"model_type": "bert",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_layers": 12,
|
36 |
+
"pad_token_id": 0,
|
37 |
+
"pooler_fc_size": 768,
|
38 |
+
"pooler_num_attention_heads": 12,
|
39 |
+
"pooler_num_fc_layers": 3,
|
40 |
+
"pooler_size_per_head": 128,
|
41 |
+
"pooler_type": "first_token_transform",
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.26.1",
|
45 |
+
"type_vocab_size": 2,
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 100000
|
48 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:176d8f9198e9ba1890e73cb84cea6fd72029dde3aa3cfe20eb88e102fe423824
|
3 |
+
size 1298159621
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2085cc27542cc01f15c19ebc71d43d1f8f45bf197e79d0577205025461795a7
|
3 |
+
size 649093613
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dabb4b86cbf1a1b58132296db3134e785f4d2ca4284f14926f2e7f07fc8bace
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f7f223e541d8ca8282c09e6f4666d154f61e406961790c043b389c95e9eedcc
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/project/6007993/elmadany/Models/MARBERT_17M/pytorch_verison/"}
|
trainer_state.json
ADDED
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 3174,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.09,
|
12 |
+
"eval_loss": 0.2966074049472809,
|
13 |
+
"eval_runtime": 11.717,
|
14 |
+
"eval_samples_per_second": 95.246,
|
15 |
+
"eval_steps_per_second": 11.948,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.19,
|
20 |
+
"eval_loss": 0.2779335379600525,
|
21 |
+
"eval_runtime": 11.9173,
|
22 |
+
"eval_samples_per_second": 93.646,
|
23 |
+
"eval_steps_per_second": 11.748,
|
24 |
+
"step": 200
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.28,
|
28 |
+
"eval_loss": 0.3014441728591919,
|
29 |
+
"eval_runtime": 12.0302,
|
30 |
+
"eval_samples_per_second": 92.766,
|
31 |
+
"eval_steps_per_second": 11.637,
|
32 |
+
"step": 300
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.38,
|
36 |
+
"eval_loss": 0.2802102565765381,
|
37 |
+
"eval_runtime": 12.0759,
|
38 |
+
"eval_samples_per_second": 92.415,
|
39 |
+
"eval_steps_per_second": 11.593,
|
40 |
+
"step": 400
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 0.47,
|
44 |
+
"learning_rate": 4.2123503465658476e-05,
|
45 |
+
"loss": 0.2981,
|
46 |
+
"step": 500
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.47,
|
50 |
+
"eval_loss": 0.2708393931388855,
|
51 |
+
"eval_runtime": 12.0021,
|
52 |
+
"eval_samples_per_second": 92.984,
|
53 |
+
"eval_steps_per_second": 11.665,
|
54 |
+
"step": 500
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.57,
|
58 |
+
"eval_loss": 0.27258798480033875,
|
59 |
+
"eval_runtime": 11.9572,
|
60 |
+
"eval_samples_per_second": 93.333,
|
61 |
+
"eval_steps_per_second": 11.708,
|
62 |
+
"step": 600
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.66,
|
66 |
+
"eval_loss": 0.23380815982818604,
|
67 |
+
"eval_runtime": 11.9377,
|
68 |
+
"eval_samples_per_second": 93.485,
|
69 |
+
"eval_steps_per_second": 11.728,
|
70 |
+
"step": 700
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 0.76,
|
74 |
+
"eval_loss": 0.25188755989074707,
|
75 |
+
"eval_runtime": 11.9371,
|
76 |
+
"eval_samples_per_second": 93.49,
|
77 |
+
"eval_steps_per_second": 11.728,
|
78 |
+
"step": 800
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 0.85,
|
82 |
+
"eval_loss": 0.23985548317432404,
|
83 |
+
"eval_runtime": 11.9193,
|
84 |
+
"eval_samples_per_second": 93.629,
|
85 |
+
"eval_steps_per_second": 11.746,
|
86 |
+
"step": 900
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.95,
|
90 |
+
"learning_rate": 3.424700693131695e-05,
|
91 |
+
"loss": 0.214,
|
92 |
+
"step": 1000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.95,
|
96 |
+
"eval_loss": 0.22884804010391235,
|
97 |
+
"eval_runtime": 11.9226,
|
98 |
+
"eval_samples_per_second": 93.604,
|
99 |
+
"eval_steps_per_second": 11.742,
|
100 |
+
"step": 1000
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.04,
|
104 |
+
"eval_loss": 0.24154280126094818,
|
105 |
+
"eval_runtime": 11.8882,
|
106 |
+
"eval_samples_per_second": 93.874,
|
107 |
+
"eval_steps_per_second": 11.776,
|
108 |
+
"step": 1100
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.13,
|
112 |
+
"eval_loss": 0.24035201966762543,
|
113 |
+
"eval_runtime": 11.909,
|
114 |
+
"eval_samples_per_second": 93.711,
|
115 |
+
"eval_steps_per_second": 11.756,
|
116 |
+
"step": 1200
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.23,
|
120 |
+
"eval_loss": 0.23449723422527313,
|
121 |
+
"eval_runtime": 11.9228,
|
122 |
+
"eval_samples_per_second": 93.602,
|
123 |
+
"eval_steps_per_second": 11.742,
|
124 |
+
"step": 1300
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 1.32,
|
128 |
+
"eval_loss": 0.24555914103984833,
|
129 |
+
"eval_runtime": 11.933,
|
130 |
+
"eval_samples_per_second": 93.522,
|
131 |
+
"eval_steps_per_second": 11.732,
|
132 |
+
"step": 1400
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 1.42,
|
136 |
+
"learning_rate": 2.637051039697543e-05,
|
137 |
+
"loss": 0.1437,
|
138 |
+
"step": 1500
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 1.42,
|
142 |
+
"eval_loss": 0.2533697783946991,
|
143 |
+
"eval_runtime": 11.9364,
|
144 |
+
"eval_samples_per_second": 93.495,
|
145 |
+
"eval_steps_per_second": 11.729,
|
146 |
+
"step": 1500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.51,
|
150 |
+
"eval_loss": 0.24284188449382782,
|
151 |
+
"eval_runtime": 11.9364,
|
152 |
+
"eval_samples_per_second": 93.496,
|
153 |
+
"eval_steps_per_second": 11.729,
|
154 |
+
"step": 1600
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 1.61,
|
158 |
+
"eval_loss": 0.22709068655967712,
|
159 |
+
"eval_runtime": 11.9235,
|
160 |
+
"eval_samples_per_second": 93.596,
|
161 |
+
"eval_steps_per_second": 11.741,
|
162 |
+
"step": 1700
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.7,
|
166 |
+
"eval_loss": 0.2449030727148056,
|
167 |
+
"eval_runtime": 11.9438,
|
168 |
+
"eval_samples_per_second": 93.438,
|
169 |
+
"eval_steps_per_second": 11.722,
|
170 |
+
"step": 1800
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.8,
|
174 |
+
"eval_loss": 0.2384931743144989,
|
175 |
+
"eval_runtime": 11.9427,
|
176 |
+
"eval_samples_per_second": 93.446,
|
177 |
+
"eval_steps_per_second": 11.723,
|
178 |
+
"step": 1900
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 1.89,
|
182 |
+
"learning_rate": 1.8494013862633903e-05,
|
183 |
+
"loss": 0.1391,
|
184 |
+
"step": 2000
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.89,
|
188 |
+
"eval_loss": 0.23267678916454315,
|
189 |
+
"eval_runtime": 11.9443,
|
190 |
+
"eval_samples_per_second": 93.434,
|
191 |
+
"eval_steps_per_second": 11.721,
|
192 |
+
"step": 2000
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 1.98,
|
196 |
+
"eval_loss": 0.25874465703964233,
|
197 |
+
"eval_runtime": 11.9432,
|
198 |
+
"eval_samples_per_second": 93.442,
|
199 |
+
"eval_steps_per_second": 11.722,
|
200 |
+
"step": 2100
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.08,
|
204 |
+
"eval_loss": 0.2706637382507324,
|
205 |
+
"eval_runtime": 11.937,
|
206 |
+
"eval_samples_per_second": 93.49,
|
207 |
+
"eval_steps_per_second": 11.728,
|
208 |
+
"step": 2200
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 2.17,
|
212 |
+
"eval_loss": 0.2850804626941681,
|
213 |
+
"eval_runtime": 11.9389,
|
214 |
+
"eval_samples_per_second": 93.476,
|
215 |
+
"eval_steps_per_second": 11.726,
|
216 |
+
"step": 2300
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 2.27,
|
220 |
+
"eval_loss": 0.25478190183639526,
|
221 |
+
"eval_runtime": 11.9433,
|
222 |
+
"eval_samples_per_second": 93.442,
|
223 |
+
"eval_steps_per_second": 11.722,
|
224 |
+
"step": 2400
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.36,
|
228 |
+
"learning_rate": 1.0617517328292375e-05,
|
229 |
+
"loss": 0.0837,
|
230 |
+
"step": 2500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.36,
|
234 |
+
"eval_loss": 0.27440693974494934,
|
235 |
+
"eval_runtime": 11.943,
|
236 |
+
"eval_samples_per_second": 93.444,
|
237 |
+
"eval_steps_per_second": 11.722,
|
238 |
+
"step": 2500
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 2.46,
|
242 |
+
"eval_loss": 0.2777708172798157,
|
243 |
+
"eval_runtime": 11.9475,
|
244 |
+
"eval_samples_per_second": 93.409,
|
245 |
+
"eval_steps_per_second": 11.718,
|
246 |
+
"step": 2600
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 2.55,
|
250 |
+
"eval_loss": 0.2835574746131897,
|
251 |
+
"eval_runtime": 11.9494,
|
252 |
+
"eval_samples_per_second": 93.394,
|
253 |
+
"eval_steps_per_second": 11.716,
|
254 |
+
"step": 2700
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.65,
|
258 |
+
"eval_loss": 0.2683883607387543,
|
259 |
+
"eval_runtime": 11.9508,
|
260 |
+
"eval_samples_per_second": 93.383,
|
261 |
+
"eval_steps_per_second": 11.715,
|
262 |
+
"step": 2800
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 2.74,
|
266 |
+
"eval_loss": 0.2776583731174469,
|
267 |
+
"eval_runtime": 11.9471,
|
268 |
+
"eval_samples_per_second": 93.412,
|
269 |
+
"eval_steps_per_second": 11.718,
|
270 |
+
"step": 2900
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 2.84,
|
274 |
+
"learning_rate": 2.741020793950851e-06,
|
275 |
+
"loss": 0.0691,
|
276 |
+
"step": 3000
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 2.84,
|
280 |
+
"eval_loss": 0.2755170464515686,
|
281 |
+
"eval_runtime": 11.9482,
|
282 |
+
"eval_samples_per_second": 93.403,
|
283 |
+
"eval_steps_per_second": 11.717,
|
284 |
+
"step": 3000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.93,
|
288 |
+
"eval_loss": 0.27257075905799866,
|
289 |
+
"eval_runtime": 11.9469,
|
290 |
+
"eval_samples_per_second": 93.413,
|
291 |
+
"eval_steps_per_second": 11.718,
|
292 |
+
"step": 3100
|
293 |
+
}
|
294 |
+
],
|
295 |
+
"max_steps": 3174,
|
296 |
+
"num_train_epochs": 3,
|
297 |
+
"total_flos": 6635087188033536.0,
|
298 |
+
"trial_name": null,
|
299 |
+
"trial_params": null
|
300 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f4a455147ccbf0036de19db71d29ec98151af0398abdc00582c31cb72d154c5
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|