Training in progress, step 4000
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/trainer_state.json +134 -3
- pytorch_model.bin +1 -1
- runs/Jun05_10-45-59_0a95bf9de5ac/events.out.tfevents.1685962630.0a95bf9de5ac.3272.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2000137067
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f8804038bfc8c4fff09781205b46f28d914f21115e30a8813fb451cdb64ad17
|
3 |
size 2000137067
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1002469625
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ccb2c6910f34be7a138f85235698d8f0ec58283fab1416ef6a153c170b333ed
|
3 |
size 1002469625
|
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 sha256:047a205ba65d4143fae2458ea498dbf8e5a685cd3e2e670c6951c8a299de8ae5
|
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 sha256:5789a0b7645be9b850d95a6b32fdc2dd662d33e25aea9a3e9fcb4a7309e592af
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
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,
|
@@ -137,11 +137,142 @@
|
|
137 |
"eval_samples_per_second": 0.751,
|
138 |
"eval_steps_per_second": 0.094,
|
139 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
140 |
}
|
141 |
],
|
142 |
"max_steps": 11448,
|
143 |
"num_train_epochs": 8,
|
144 |
-
"total_flos":
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|
147 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.795248078266946,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
137 |
"eval_samples_per_second": 0.751,
|
138 |
"eval_steps_per_second": 0.094,
|
139 |
"step": 2000
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 1.47,
|
143 |
+
"learning_rate": 4.2e-05,
|
144 |
+
"loss": 6.2524,
|
145 |
+
"step": 2100
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 1.54,
|
149 |
+
"learning_rate": 4.4000000000000006e-05,
|
150 |
+
"loss": 5.8029,
|
151 |
+
"step": 2200
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 1.61,
|
155 |
+
"learning_rate": 4.600000000000001e-05,
|
156 |
+
"loss": 5.606,
|
157 |
+
"step": 2300
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 1.68,
|
161 |
+
"learning_rate": 4.8e-05,
|
162 |
+
"loss": 5.3757,
|
163 |
+
"step": 2400
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.75,
|
167 |
+
"learning_rate": 5e-05,
|
168 |
+
"loss": 5.1043,
|
169 |
+
"step": 2500
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 1.82,
|
173 |
+
"learning_rate": 4.944121591417077e-05,
|
174 |
+
"loss": 4.9414,
|
175 |
+
"step": 2600
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 1.89,
|
179 |
+
"learning_rate": 4.888243182834153e-05,
|
180 |
+
"loss": 4.7381,
|
181 |
+
"step": 2700
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 1.96,
|
185 |
+
"learning_rate": 4.8323647742512295e-05,
|
186 |
+
"loss": 4.6214,
|
187 |
+
"step": 2800
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 2.03,
|
191 |
+
"learning_rate": 4.776486365668306e-05,
|
192 |
+
"loss": 4.2971,
|
193 |
+
"step": 2900
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 2.1,
|
197 |
+
"learning_rate": 4.720607957085382e-05,
|
198 |
+
"loss": 4.1602,
|
199 |
+
"step": 3000
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 2.17,
|
203 |
+
"learning_rate": 4.664729548502459e-05,
|
204 |
+
"loss": 4.0391,
|
205 |
+
"step": 3100
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.24,
|
209 |
+
"learning_rate": 4.6088511399195353e-05,
|
210 |
+
"loss": 3.9211,
|
211 |
+
"step": 3200
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 2.31,
|
215 |
+
"learning_rate": 4.552972731336611e-05,
|
216 |
+
"loss": 3.7642,
|
217 |
+
"step": 3300
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 2.38,
|
221 |
+
"learning_rate": 4.497094322753688e-05,
|
222 |
+
"loss": 3.6698,
|
223 |
+
"step": 3400
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 2.45,
|
227 |
+
"learning_rate": 4.4412159141707646e-05,
|
228 |
+
"loss": 3.5409,
|
229 |
+
"step": 3500
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 2.52,
|
233 |
+
"learning_rate": 4.385337505587841e-05,
|
234 |
+
"loss": 3.4016,
|
235 |
+
"step": 3600
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 2.59,
|
239 |
+
"learning_rate": 4.329459097004918e-05,
|
240 |
+
"loss": 3.2761,
|
241 |
+
"step": 3700
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 2.66,
|
245 |
+
"learning_rate": 4.2735806884219945e-05,
|
246 |
+
"loss": 3.1708,
|
247 |
+
"step": 3800
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.73,
|
251 |
+
"learning_rate": 4.2177022798390704e-05,
|
252 |
+
"loss": 3.0849,
|
253 |
+
"step": 3900
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 2.8,
|
257 |
+
"learning_rate": 4.161823871256147e-05,
|
258 |
+
"loss": 3.0222,
|
259 |
+
"step": 4000
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 2.8,
|
263 |
+
"eval_bleu": 27.8543,
|
264 |
+
"eval_em": 0.0,
|
265 |
+
"eval_gen_len": 36.8,
|
266 |
+
"eval_loss": 2.8796441555023193,
|
267 |
+
"eval_runtime": 501.7382,
|
268 |
+
"eval_samples_per_second": 2.402,
|
269 |
+
"eval_steps_per_second": 0.301,
|
270 |
+
"step": 4000
|
271 |
}
|
272 |
],
|
273 |
"max_steps": 11448,
|
274 |
"num_train_epochs": 8,
|
275 |
+
"total_flos": 2632028349156096.0,
|
276 |
"trial_name": null,
|
277 |
"trial_params": null
|
278 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1002469625
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ccb2c6910f34be7a138f85235698d8f0ec58283fab1416ef6a153c170b333ed
|
3 |
size 1002469625
|
runs/Jun05_10-45-59_0a95bf9de5ac/events.out.tfevents.1685962630.0a95bf9de5ac.3272.0
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:bbc2bf10f2e8697285e6c7d205571262251279a84d779b5e1565cd93e4f856da
|
3 |
+
size 15654
|