Training in progress, step 5000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/tokenizer.json +1 -6
- last-checkpoint/trainer_state.json +283 -13
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/May23_07-22-44_dca52c8e2827/events.out.tfevents.1684826793.dca52c8e2827.3255.0 +2 -2
- runs/May23_07-36-34_dca52c8e2827/1684827413.8551283/events.out.tfevents.1684827413.dca52c8e2827.7053.1 +3 -0
- runs/May23_07-36-34_dca52c8e2827/events.out.tfevents.1684827413.dca52c8e2827.7053.0 +3 -0
- tokenizer.json +1 -6
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1987250795
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26691bc9a079139ff112d3623490b7b1e1181a57365dcb4317ef510c4b654c15
|
3 |
size 1987250795
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996026489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d566856493e99b473f5448f5f84d98cb96b54b8037b5594753fc824379258f8
|
3 |
size 996026489
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac960100d4e349cafe09cf7d725afb9f58100ddb997772f90eb4ed86a91940a7
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dd12b75c68171d6b843ea8287729b2926e26ccf6f0ecf6e8495fe66f0329742
|
3 |
size 627
|
last-checkpoint/tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 256,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,46 +1,316 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.04,
|
12 |
-
"learning_rate":
|
13 |
-
"loss":
|
14 |
"step": 100
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.08,
|
18 |
-
"learning_rate":
|
19 |
-
"loss":
|
20 |
"step": 200
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.12,
|
24 |
-
"learning_rate":
|
25 |
-
"loss":
|
26 |
"step": 300
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.17,
|
30 |
-
"learning_rate":
|
31 |
-
"loss":
|
32 |
"step": 400
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.21,
|
36 |
-
"learning_rate":
|
37 |
-
"loss":
|
38 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
}
|
40 |
],
|
41 |
"max_steps": 24100,
|
42 |
"num_train_epochs": 10,
|
43 |
-
"total_flos":
|
44 |
"trial_name": null,
|
45 |
"trial_params": null
|
46 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.074688796680498,
|
5 |
+
"global_step": 5000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.04,
|
12 |
+
"learning_rate": 2.0000000000000003e-06,
|
13 |
+
"loss": 92.256,
|
14 |
"step": 100
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.08,
|
18 |
+
"learning_rate": 4.000000000000001e-06,
|
19 |
+
"loss": 52.0764,
|
20 |
"step": 200
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.12,
|
24 |
+
"learning_rate": 6e-06,
|
25 |
+
"loss": 41.3627,
|
26 |
"step": 300
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.17,
|
30 |
+
"learning_rate": 8.000000000000001e-06,
|
31 |
+
"loss": 37.237,
|
32 |
"step": 400
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.21,
|
36 |
+
"learning_rate": 1e-05,
|
37 |
+
"loss": 34.3031,
|
38 |
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.25,
|
42 |
+
"learning_rate": 1.2e-05,
|
43 |
+
"loss": 31.7147,
|
44 |
+
"step": 600
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.29,
|
48 |
+
"learning_rate": 1.4000000000000001e-05,
|
49 |
+
"loss": 29.5475,
|
50 |
+
"step": 700
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.33,
|
54 |
+
"learning_rate": 1.6000000000000003e-05,
|
55 |
+
"loss": 27.914,
|
56 |
+
"step": 800
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.37,
|
60 |
+
"learning_rate": 1.8e-05,
|
61 |
+
"loss": 26.1499,
|
62 |
+
"step": 900
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.41,
|
66 |
+
"learning_rate": 2e-05,
|
67 |
+
"loss": 24.1629,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.46,
|
72 |
+
"learning_rate": 2.2000000000000003e-05,
|
73 |
+
"loss": 22.1829,
|
74 |
+
"step": 1100
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.5,
|
78 |
+
"learning_rate": 2.4e-05,
|
79 |
+
"loss": 20.2111,
|
80 |
+
"step": 1200
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.54,
|
84 |
+
"learning_rate": 2.6000000000000002e-05,
|
85 |
+
"loss": 18.6642,
|
86 |
+
"step": 1300
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.58,
|
90 |
+
"learning_rate": 2.8000000000000003e-05,
|
91 |
+
"loss": 16.7946,
|
92 |
+
"step": 1400
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.62,
|
96 |
+
"learning_rate": 3e-05,
|
97 |
+
"loss": 15.0783,
|
98 |
+
"step": 1500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.66,
|
102 |
+
"learning_rate": 3.2000000000000005e-05,
|
103 |
+
"loss": 13.366,
|
104 |
+
"step": 1600
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.71,
|
108 |
+
"learning_rate": 3.4000000000000007e-05,
|
109 |
+
"loss": 11.706,
|
110 |
+
"step": 1700
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.75,
|
114 |
+
"learning_rate": 3.6e-05,
|
115 |
+
"loss": 10.2113,
|
116 |
+
"step": 1800
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.79,
|
120 |
+
"learning_rate": 3.8e-05,
|
121 |
+
"loss": 8.5921,
|
122 |
+
"step": 1900
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.83,
|
126 |
+
"learning_rate": 4e-05,
|
127 |
+
"loss": 7.2445,
|
128 |
+
"step": 2000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.87,
|
132 |
+
"learning_rate": 4.2e-05,
|
133 |
+
"loss": 6.8461,
|
134 |
+
"step": 2100
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.91,
|
138 |
+
"learning_rate": 4.4000000000000006e-05,
|
139 |
+
"loss": 6.223,
|
140 |
+
"step": 2200
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.95,
|
144 |
+
"learning_rate": 4.600000000000001e-05,
|
145 |
+
"loss": 6.1167,
|
146 |
+
"step": 2300
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.0,
|
150 |
+
"learning_rate": 4.8e-05,
|
151 |
+
"loss": 5.7623,
|
152 |
+
"step": 2400
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.04,
|
156 |
+
"learning_rate": 5e-05,
|
157 |
+
"loss": 5.5056,
|
158 |
+
"step": 2500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.08,
|
162 |
+
"learning_rate": 4.976851851851852e-05,
|
163 |
+
"loss": 5.2979,
|
164 |
+
"step": 2600
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.12,
|
168 |
+
"learning_rate": 4.9537037037037035e-05,
|
169 |
+
"loss": 4.9765,
|
170 |
+
"step": 2700
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.16,
|
174 |
+
"learning_rate": 4.930555555555556e-05,
|
175 |
+
"loss": 4.7721,
|
176 |
+
"step": 2800
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.2,
|
180 |
+
"learning_rate": 4.9074074074074075e-05,
|
181 |
+
"loss": 4.6957,
|
182 |
+
"step": 2900
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.24,
|
186 |
+
"learning_rate": 4.8842592592592595e-05,
|
187 |
+
"loss": 4.7368,
|
188 |
+
"step": 3000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.29,
|
192 |
+
"learning_rate": 4.8611111111111115e-05,
|
193 |
+
"loss": 4.6074,
|
194 |
+
"step": 3100
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.33,
|
198 |
+
"learning_rate": 4.837962962962963e-05,
|
199 |
+
"loss": 4.3678,
|
200 |
+
"step": 3200
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.37,
|
204 |
+
"learning_rate": 4.814814814814815e-05,
|
205 |
+
"loss": 4.19,
|
206 |
+
"step": 3300
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.41,
|
210 |
+
"learning_rate": 4.791666666666667e-05,
|
211 |
+
"loss": 4.0959,
|
212 |
+
"step": 3400
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.45,
|
216 |
+
"learning_rate": 4.768518518518519e-05,
|
217 |
+
"loss": 4.0323,
|
218 |
+
"step": 3500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.49,
|
222 |
+
"learning_rate": 4.745370370370371e-05,
|
223 |
+
"loss": 3.7777,
|
224 |
+
"step": 3600
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.54,
|
228 |
+
"learning_rate": 4.722222222222222e-05,
|
229 |
+
"loss": 3.8014,
|
230 |
+
"step": 3700
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.58,
|
234 |
+
"learning_rate": 4.699074074074074e-05,
|
235 |
+
"loss": 3.6346,
|
236 |
+
"step": 3800
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.62,
|
240 |
+
"learning_rate": 4.675925925925926e-05,
|
241 |
+
"loss": 3.4876,
|
242 |
+
"step": 3900
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.66,
|
246 |
+
"learning_rate": 4.652777777777778e-05,
|
247 |
+
"loss": 3.4458,
|
248 |
+
"step": 4000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.7,
|
252 |
+
"learning_rate": 4.62962962962963e-05,
|
253 |
+
"loss": 3.4425,
|
254 |
+
"step": 4100
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.74,
|
258 |
+
"learning_rate": 4.6064814814814814e-05,
|
259 |
+
"loss": 3.3346,
|
260 |
+
"step": 4200
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.78,
|
264 |
+
"learning_rate": 4.5833333333333334e-05,
|
265 |
+
"loss": 3.2582,
|
266 |
+
"step": 4300
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.83,
|
270 |
+
"learning_rate": 4.5601851851851854e-05,
|
271 |
+
"loss": 3.1174,
|
272 |
+
"step": 4400
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.87,
|
276 |
+
"learning_rate": 4.5370370370370374e-05,
|
277 |
+
"loss": 2.9873,
|
278 |
+
"step": 4500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.91,
|
282 |
+
"learning_rate": 4.5138888888888894e-05,
|
283 |
+
"loss": 3.1041,
|
284 |
+
"step": 4600
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.95,
|
288 |
+
"learning_rate": 4.490740740740741e-05,
|
289 |
+
"loss": 2.9365,
|
290 |
+
"step": 4700
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.99,
|
294 |
+
"learning_rate": 4.467592592592593e-05,
|
295 |
+
"loss": 2.9494,
|
296 |
+
"step": 4800
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.03,
|
300 |
+
"learning_rate": 4.4444444444444447e-05,
|
301 |
+
"loss": 2.8309,
|
302 |
+
"step": 4900
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 2.07,
|
306 |
+
"learning_rate": 4.4212962962962966e-05,
|
307 |
+
"loss": 2.6814,
|
308 |
+
"step": 5000
|
309 |
}
|
310 |
],
|
311 |
"max_steps": 24100,
|
312 |
"num_train_epochs": 10,
|
313 |
+
"total_flos": 1456002534873600.0,
|
314 |
"trial_name": null,
|
315 |
"trial_params": null
|
316 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f429252c8cb29c05ad6e59b1673286f8874167a23d2a02cb8ebcefbe5762254
|
3 |
size 4155
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996026489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d566856493e99b473f5448f5f84d98cb96b54b8037b5594753fc824379258f8
|
3 |
size 996026489
|
runs/May23_07-22-44_dca52c8e2827/events.out.tfevents.1684826793.dca52c8e2827.3255.0
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 sha256:7e681168b3fb512797dffd9be7c232146379e3e2b617d82586bc9fd48579345a
|
3 |
+
size 10111
|
runs/May23_07-36-34_dca52c8e2827/1684827413.8551283/events.out.tfevents.1684827413.dca52c8e2827.7053.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0421e3bc36f1a94f5cf39951507cfe7bde638f05aa0452a214391ff4198140b
|
3 |
+
size 6302
|
runs/May23_07-36-34_dca52c8e2827/events.out.tfevents.1684827413.dca52c8e2827.7053.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:796f855eccda2926407fd876f6553f5e27ace51e3310130f87ac1460fda925b2
|
3 |
+
size 16393
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 256,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f429252c8cb29c05ad6e59b1673286f8874167a23d2a02cb8ebcefbe5762254
|
3 |
size 4155
|