Training in progress, step 35, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 389352298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe9b3c91781fb64a2a070d458f515d3474e7c0924b65e3bee5a042eae7efd121
|
3 |
size 389352298
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e91cdd026c6ca53bf4f618f41c1803502d8d870a39a3a5e36dd15f44c3e8c158
|
3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9c5635e14273caff32fe2cbaa99db1c8b9ad70215139b473d19d5cfcc622124
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2f31dfaebd277d0dbf46d8400abc3fa41c6b75740305f19558cb6f8eac4faab
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9eae1ea66cfb187245fec88c7ac2c75a907c10cb639fdccff7eb227d4f535774
|
3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93ce236cdfc3570e60fc168a599f38d18a8345a454926b769bf6e4e2c224361f
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -198,6 +198,76 @@
|
|
198 |
"eval_samples_per_second": 28.211,
|
199 |
"eval_steps_per_second": 7.335,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -221,12 +291,12 @@
|
|
221 |
"should_evaluate": false,
|
222 |
"should_log": false,
|
223 |
"should_save": true,
|
224 |
-
"should_training_stop":
|
225 |
},
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
-
"total_flos": 1.
|
230 |
"train_batch_size": 2,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
+
"epoch": 3.0434782608695654,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 35,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
198 |
"eval_samples_per_second": 28.211,
|
199 |
"eval_steps_per_second": 7.335,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.260869565217391,
|
204 |
+
"grad_norm": NaN,
|
205 |
+
"learning_rate": 2.5531266972462177e-05,
|
206 |
+
"loss": 0.0,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 2.3478260869565215,
|
211 |
+
"grad_norm": NaN,
|
212 |
+
"learning_rate": 2.2431968285271844e-05,
|
213 |
+
"loss": 0.0,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 2.4347826086956523,
|
218 |
+
"grad_norm": NaN,
|
219 |
+
"learning_rate": 1.9627610736574575e-05,
|
220 |
+
"loss": 0.0,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.5217391304347827,
|
225 |
+
"grad_norm": NaN,
|
226 |
+
"learning_rate": 1.7143591022596845e-05,
|
227 |
+
"loss": 0.0,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 2.608695652173913,
|
232 |
+
"grad_norm": NaN,
|
233 |
+
"learning_rate": 1.5002404810528451e-05,
|
234 |
+
"loss": 0.0,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 2.6956521739130435,
|
239 |
+
"grad_norm": NaN,
|
240 |
+
"learning_rate": 1.3223443014276737e-05,
|
241 |
+
"loss": 0.0,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.782608695652174,
|
246 |
+
"grad_norm": NaN,
|
247 |
+
"learning_rate": 1.1822816187347623e-05,
|
248 |
+
"loss": 0.0,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.869565217391304,
|
253 |
+
"grad_norm": NaN,
|
254 |
+
"learning_rate": 1.08132086231782e-05,
|
255 |
+
"loss": 0.0,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 2.9565217391304346,
|
260 |
+
"grad_norm": NaN,
|
261 |
+
"learning_rate": 1.0203763484211195e-05,
|
262 |
+
"loss": 0.0,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 3.0434782608695654,
|
267 |
+
"grad_norm": NaN,
|
268 |
+
"learning_rate": 1e-05,
|
269 |
+
"loss": 0.0,
|
270 |
+
"step": 35
|
271 |
}
|
272 |
],
|
273 |
"logging_steps": 1,
|
|
|
291 |
"should_evaluate": false,
|
292 |
"should_log": false,
|
293 |
"should_save": true,
|
294 |
+
"should_training_stop": true
|
295 |
},
|
296 |
"attributes": {}
|
297 |
}
|
298 |
},
|
299 |
+
"total_flos": 1.5784968764522496e+17,
|
300 |
"train_batch_size": 2,
|
301 |
"trial_name": null,
|
302 |
"trial_params": null
|