All Dunn!!!
Browse files- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +259 -0
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.10460054101646599,
|
4 |
+
"train_runtime": 331532.8168,
|
5 |
+
"train_samples_per_second": 0.353,
|
6 |
+
"train_steps_per_second": 0.006
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.10460054101646599,
|
4 |
+
"train_runtime": 331532.8168,
|
5 |
+
"train_samples_per_second": 0.353,
|
6 |
+
"train_steps_per_second": 0.006
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7772539776075428,
|
3 |
+
"best_model_checkpoint": "ibert-roberta-base-Abusive_Or_Threatening_Speech/checkpoint-1828",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 1828,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 1.9989059080962803e-05,
|
13 |
+
"loss": 0.7234,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.03,
|
18 |
+
"learning_rate": 1.9452954048140046e-05,
|
19 |
+
"loss": 0.3222,
|
20 |
+
"step": 50
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.05,
|
24 |
+
"learning_rate": 1.890590809628009e-05,
|
25 |
+
"loss": 0.132,
|
26 |
+
"step": 100
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.08,
|
30 |
+
"learning_rate": 1.8358862144420135e-05,
|
31 |
+
"loss": 0.1327,
|
32 |
+
"step": 150
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.11,
|
36 |
+
"learning_rate": 1.7811816192560176e-05,
|
37 |
+
"loss": 0.1067,
|
38 |
+
"step": 200
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.14,
|
42 |
+
"learning_rate": 1.726477024070022e-05,
|
43 |
+
"loss": 0.1085,
|
44 |
+
"step": 250
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.16,
|
48 |
+
"learning_rate": 1.6717724288840264e-05,
|
49 |
+
"loss": 0.0917,
|
50 |
+
"step": 300
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.19,
|
54 |
+
"learning_rate": 1.617067833698031e-05,
|
55 |
+
"loss": 0.1098,
|
56 |
+
"step": 350
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.22,
|
60 |
+
"learning_rate": 1.562363238512035e-05,
|
61 |
+
"loss": 0.1011,
|
62 |
+
"step": 400
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.25,
|
66 |
+
"learning_rate": 1.5076586433260396e-05,
|
67 |
+
"loss": 0.0979,
|
68 |
+
"step": 450
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.27,
|
72 |
+
"learning_rate": 1.452954048140044e-05,
|
73 |
+
"loss": 0.1076,
|
74 |
+
"step": 500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.3,
|
78 |
+
"learning_rate": 1.3982494529540483e-05,
|
79 |
+
"loss": 0.1102,
|
80 |
+
"step": 550
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.33,
|
84 |
+
"learning_rate": 1.3435448577680525e-05,
|
85 |
+
"loss": 0.0987,
|
86 |
+
"step": 600
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.36,
|
90 |
+
"learning_rate": 1.2888402625820571e-05,
|
91 |
+
"loss": 0.0958,
|
92 |
+
"step": 650
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.38,
|
96 |
+
"learning_rate": 1.2341356673960614e-05,
|
97 |
+
"loss": 0.0906,
|
98 |
+
"step": 700
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.41,
|
102 |
+
"learning_rate": 1.1794310722100657e-05,
|
103 |
+
"loss": 0.1108,
|
104 |
+
"step": 750
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.44,
|
108 |
+
"learning_rate": 1.12472647702407e-05,
|
109 |
+
"loss": 0.1282,
|
110 |
+
"step": 800
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.46,
|
114 |
+
"learning_rate": 1.0700218818380745e-05,
|
115 |
+
"loss": 0.0975,
|
116 |
+
"step": 850
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.49,
|
120 |
+
"learning_rate": 1.0153172866520788e-05,
|
121 |
+
"loss": 0.0944,
|
122 |
+
"step": 900
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.52,
|
126 |
+
"learning_rate": 9.606126914660832e-06,
|
127 |
+
"loss": 0.088,
|
128 |
+
"step": 950
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.55,
|
132 |
+
"learning_rate": 9.059080962800875e-06,
|
133 |
+
"loss": 0.0919,
|
134 |
+
"step": 1000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.57,
|
138 |
+
"learning_rate": 8.51203501094092e-06,
|
139 |
+
"loss": 0.0934,
|
140 |
+
"step": 1050
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.6,
|
144 |
+
"learning_rate": 7.964989059080964e-06,
|
145 |
+
"loss": 0.0924,
|
146 |
+
"step": 1100
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.63,
|
150 |
+
"learning_rate": 7.417943107221007e-06,
|
151 |
+
"loss": 0.0975,
|
152 |
+
"step": 1150
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.66,
|
156 |
+
"learning_rate": 6.87089715536105e-06,
|
157 |
+
"loss": 0.0857,
|
158 |
+
"step": 1200
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.68,
|
162 |
+
"learning_rate": 6.323851203501094e-06,
|
163 |
+
"loss": 0.0917,
|
164 |
+
"step": 1250
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.71,
|
168 |
+
"learning_rate": 5.776805251641139e-06,
|
169 |
+
"loss": 0.0924,
|
170 |
+
"step": 1300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.74,
|
174 |
+
"learning_rate": 5.229759299781182e-06,
|
175 |
+
"loss": 0.0873,
|
176 |
+
"step": 1350
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.77,
|
180 |
+
"learning_rate": 4.682713347921226e-06,
|
181 |
+
"loss": 0.0732,
|
182 |
+
"step": 1400
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.79,
|
186 |
+
"learning_rate": 4.135667396061269e-06,
|
187 |
+
"loss": 0.1094,
|
188 |
+
"step": 1450
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.82,
|
192 |
+
"learning_rate": 3.5886214442013136e-06,
|
193 |
+
"loss": 0.0918,
|
194 |
+
"step": 1500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.85,
|
198 |
+
"learning_rate": 3.041575492341357e-06,
|
199 |
+
"loss": 0.0919,
|
200 |
+
"step": 1550
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.88,
|
204 |
+
"learning_rate": 2.4945295404814006e-06,
|
205 |
+
"loss": 0.0875,
|
206 |
+
"step": 1600
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.9,
|
210 |
+
"learning_rate": 1.9474835886214445e-06,
|
211 |
+
"loss": 0.0868,
|
212 |
+
"step": 1650
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.93,
|
216 |
+
"learning_rate": 1.400437636761488e-06,
|
217 |
+
"loss": 0.0969,
|
218 |
+
"step": 1700
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.96,
|
222 |
+
"learning_rate": 8.533916849015319e-07,
|
223 |
+
"loss": 0.0973,
|
224 |
+
"step": 1750
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.98,
|
228 |
+
"learning_rate": 3.063457330415755e-07,
|
229 |
+
"loss": 0.0771,
|
230 |
+
"step": 1800
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.0,
|
234 |
+
"eval_F1": 0.7772539776075428,
|
235 |
+
"eval_Precision": 0.7083780880773362,
|
236 |
+
"eval_Recall": 0.8609660574412533,
|
237 |
+
"eval_accuracy": 0.9741476592688849,
|
238 |
+
"eval_loss": 0.08016789704561234,
|
239 |
+
"eval_runtime": 13441.5223,
|
240 |
+
"eval_samples_per_second": 2.176,
|
241 |
+
"eval_steps_per_second": 0.034,
|
242 |
+
"step": 1828
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.0,
|
246 |
+
"step": 1828,
|
247 |
+
"total_flos": 1.92457374411324e+16,
|
248 |
+
"train_loss": 0.10460054101646599,
|
249 |
+
"train_runtime": 331532.8168,
|
250 |
+
"train_samples_per_second": 0.353,
|
251 |
+
"train_steps_per_second": 0.006
|
252 |
+
}
|
253 |
+
],
|
254 |
+
"max_steps": 1828,
|
255 |
+
"num_train_epochs": 1,
|
256 |
+
"total_flos": 1.92457374411324e+16,
|
257 |
+
"trial_name": null,
|
258 |
+
"trial_params": null
|
259 |
+
}
|