ThePyProgrammer
commited on
Commit
•
13ed01a
1
Parent(s):
87322d5
Upload 10 files
Browse files- config.json +26 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +262 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"transformers_version": "4.5.1",
|
23 |
+
"type_vocab_size": 1,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 50265
|
26 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abd53e324fc9ef1a1340fc05e3914a3fe8313d4fe41514694d7a971712a9b00b
|
3 |
+
size 997303505
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:392a4b03fd9f6e2af25e501c439a28e919b53df49babaf9625decef86478918f
|
3 |
+
size 498679241
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2846f23f31b96bcfeb24a0d5bfb1568cf06a73aabb0cd110577f7ef3c7c0742f
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base"}
|
trainer_state.json
ADDED
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.27383747696876526,
|
3 |
+
"best_model_checkpoint": "models/roberta-teacher/checkpoint-8346",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 16692,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.12,
|
12 |
+
"learning_rate": 1.952072849269111e-05,
|
13 |
+
"loss": 0.4076,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.24,
|
18 |
+
"learning_rate": 1.904145698538222e-05,
|
19 |
+
"loss": 0.3484,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.36,
|
24 |
+
"learning_rate": 1.856218547807333e-05,
|
25 |
+
"loss": 0.3104,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.48,
|
30 |
+
"learning_rate": 1.808291397076444e-05,
|
31 |
+
"loss": 0.3241,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.6,
|
36 |
+
"learning_rate": 1.7603642463455548e-05,
|
37 |
+
"loss": 0.31,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.72,
|
42 |
+
"learning_rate": 1.712437095614666e-05,
|
43 |
+
"loss": 0.3088,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.84,
|
48 |
+
"learning_rate": 1.6645099448837766e-05,
|
49 |
+
"loss": 0.303,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.96,
|
54 |
+
"learning_rate": 1.616582794152888e-05,
|
55 |
+
"loss": 0.3046,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.0,
|
60 |
+
"eval_accuracy": 0.8758252121974222,
|
61 |
+
"eval_f1": 0.8723680200515267,
|
62 |
+
"eval_kappa": 0.5282754100007345,
|
63 |
+
"eval_loss": 0.28437086939811707,
|
64 |
+
"eval_precision": 0.8700935888757716,
|
65 |
+
"eval_recall": 0.8758252121974222,
|
66 |
+
"eval_runtime": 101.4778,
|
67 |
+
"eval_samples_per_second": 94.04,
|
68 |
+
"step": 4173
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.08,
|
72 |
+
"learning_rate": 1.5686556434219985e-05,
|
73 |
+
"loss": 0.2827,
|
74 |
+
"step": 4500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.2,
|
78 |
+
"learning_rate": 1.5207284926911097e-05,
|
79 |
+
"loss": 0.2861,
|
80 |
+
"step": 5000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.32,
|
84 |
+
"learning_rate": 1.4728013419602205e-05,
|
85 |
+
"loss": 0.3014,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.44,
|
90 |
+
"learning_rate": 1.4248741912293316e-05,
|
91 |
+
"loss": 0.2807,
|
92 |
+
"step": 6000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.56,
|
96 |
+
"learning_rate": 1.3769470404984425e-05,
|
97 |
+
"loss": 0.2924,
|
98 |
+
"step": 6500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.68,
|
102 |
+
"learning_rate": 1.3290198897675534e-05,
|
103 |
+
"loss": 0.3189,
|
104 |
+
"step": 7000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.8,
|
108 |
+
"learning_rate": 1.2810927390366643e-05,
|
109 |
+
"loss": 0.2973,
|
110 |
+
"step": 7500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.92,
|
114 |
+
"learning_rate": 1.2331655883057754e-05,
|
115 |
+
"loss": 0.266,
|
116 |
+
"step": 8000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 2.0,
|
120 |
+
"eval_accuracy": 0.8917531174683013,
|
121 |
+
"eval_f1": 0.8844462847060539,
|
122 |
+
"eval_kappa": 0.560786854721061,
|
123 |
+
"eval_loss": 0.27383747696876526,
|
124 |
+
"eval_precision": 0.8838724313266608,
|
125 |
+
"eval_recall": 0.8917531174683013,
|
126 |
+
"eval_runtime": 100.1991,
|
127 |
+
"eval_samples_per_second": 95.24,
|
128 |
+
"step": 8346
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.04,
|
132 |
+
"learning_rate": 1.1852384375748862e-05,
|
133 |
+
"loss": 0.2906,
|
134 |
+
"step": 8500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.16,
|
138 |
+
"learning_rate": 1.1373112868439973e-05,
|
139 |
+
"loss": 0.2792,
|
140 |
+
"step": 9000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 2.28,
|
144 |
+
"learning_rate": 1.0893841361131082e-05,
|
145 |
+
"loss": 0.2777,
|
146 |
+
"step": 9500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.4,
|
150 |
+
"learning_rate": 1.0414569853822191e-05,
|
151 |
+
"loss": 0.2786,
|
152 |
+
"step": 10000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.52,
|
156 |
+
"learning_rate": 9.9352983465133e-06,
|
157 |
+
"loss": 0.2707,
|
158 |
+
"step": 10500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.64,
|
162 |
+
"learning_rate": 9.45602683920441e-06,
|
163 |
+
"loss": 0.2628,
|
164 |
+
"step": 11000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.76,
|
168 |
+
"learning_rate": 8.976755331895519e-06,
|
169 |
+
"loss": 0.2794,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.88,
|
174 |
+
"learning_rate": 8.497483824586628e-06,
|
175 |
+
"loss": 0.2591,
|
176 |
+
"step": 12000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 3.0,
|
180 |
+
"learning_rate": 8.018212317277739e-06,
|
181 |
+
"loss": 0.2715,
|
182 |
+
"step": 12500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 3.0,
|
186 |
+
"eval_accuracy": 0.8908100178141046,
|
187 |
+
"eval_f1": 0.8893163070910289,
|
188 |
+
"eval_kappa": 0.5958280873418562,
|
189 |
+
"eval_loss": 0.3180936276912689,
|
190 |
+
"eval_precision": 0.8881406833580966,
|
191 |
+
"eval_recall": 0.8908100178141046,
|
192 |
+
"eval_runtime": 100.3133,
|
193 |
+
"eval_samples_per_second": 95.132,
|
194 |
+
"step": 12519
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 3.12,
|
198 |
+
"learning_rate": 7.538940809968847e-06,
|
199 |
+
"loss": 0.2559,
|
200 |
+
"step": 13000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 3.24,
|
204 |
+
"learning_rate": 7.0596693026599574e-06,
|
205 |
+
"loss": 0.2426,
|
206 |
+
"step": 13500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 3.35,
|
210 |
+
"learning_rate": 6.580397795351067e-06,
|
211 |
+
"loss": 0.2494,
|
212 |
+
"step": 14000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 3.47,
|
216 |
+
"learning_rate": 6.101126288042176e-06,
|
217 |
+
"loss": 0.2481,
|
218 |
+
"step": 14500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 3.59,
|
222 |
+
"learning_rate": 5.621854780733286e-06,
|
223 |
+
"loss": 0.2438,
|
224 |
+
"step": 15000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 3.71,
|
228 |
+
"learning_rate": 5.142583273424395e-06,
|
229 |
+
"loss": 0.2599,
|
230 |
+
"step": 15500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 3.83,
|
234 |
+
"learning_rate": 4.663311766115504e-06,
|
235 |
+
"loss": 0.2401,
|
236 |
+
"step": 16000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 3.95,
|
240 |
+
"learning_rate": 4.1840402588066145e-06,
|
241 |
+
"loss": 0.2553,
|
242 |
+
"step": 16500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 4.0,
|
246 |
+
"eval_accuracy": 0.8920674840197003,
|
247 |
+
"eval_f1": 0.8862888705299119,
|
248 |
+
"eval_kappa": 0.5716616874732978,
|
249 |
+
"eval_loss": 0.37104833126068115,
|
250 |
+
"eval_precision": 0.884886094916698,
|
251 |
+
"eval_recall": 0.8920674840197003,
|
252 |
+
"eval_runtime": 100.4865,
|
253 |
+
"eval_samples_per_second": 94.968,
|
254 |
+
"step": 16692
|
255 |
+
}
|
256 |
+
],
|
257 |
+
"max_steps": 20865,
|
258 |
+
"num_train_epochs": 5,
|
259 |
+
"total_flos": 4.294687728722784e+16,
|
260 |
+
"trial_name": null,
|
261 |
+
"trial_params": null
|
262 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97c81886b094d326f2bf9f4bc2c37a4190de8ba10d377142576d1602e74291e0
|
3 |
+
size 2351
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|