Training in progress, step 25000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +71 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- 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 893438545
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff8ac0528ae96ac37b3b802dfcf67b3e3287a79699902d5ea869bb7ecd76a86d
|
3 |
size 893438545
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f550aaa679be49bdef1e79d5263b22969a6f34b532e760e534bc4ff1c616cbeb
|
3 |
size 449471589
|
last-checkpoint/rng_state.pth
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 sha256:2dc9dc36bcc19ec50bad9e258fedb0a58fc5090294d119fe4f13612d58ae4fd2
|
3 |
+
size 15587
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50ef36672b7ac14c121f179c123c02c01d1b8c2cb6f2f99d3d54a1ecdd9a6777
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afdbfcefcd9e1661e5368ed0a7d4915dce2e8bd6a92fd4d33ed45da578d95703
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -278,11 +278,79 @@
|
|
278 |
"eval_samples_per_second": 87.452,
|
279 |
"eval_steps_per_second": 1.382,
|
280 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
281 |
}
|
282 |
],
|
283 |
"max_steps": 100000,
|
284 |
"num_train_epochs": 9,
|
285 |
-
"total_flos":
|
286 |
"trial_name": null,
|
287 |
"trial_params": null
|
288 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.4353125544140692,
|
5 |
+
"global_step": 25000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
278 |
"eval_samples_per_second": 87.452,
|
279 |
"eval_steps_per_second": 1.382,
|
280 |
"step": 20000
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 1.04,
|
284 |
+
"learning_rate": 9.169565984405851e-05,
|
285 |
+
"loss": 0.4442,
|
286 |
+
"step": 20500
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.09,
|
290 |
+
"learning_rate": 9.126411941080688e-05,
|
291 |
+
"loss": 0.4404,
|
292 |
+
"step": 21000
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 1.13,
|
296 |
+
"learning_rate": 9.082376309845848e-05,
|
297 |
+
"loss": 0.4418,
|
298 |
+
"step": 21500
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 1.17,
|
302 |
+
"learning_rate": 9.037379052736644e-05,
|
303 |
+
"loss": 0.44,
|
304 |
+
"step": 22000
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.22,
|
308 |
+
"learning_rate": 8.991518638364486e-05,
|
309 |
+
"loss": 0.4388,
|
310 |
+
"step": 22500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.26,
|
314 |
+
"learning_rate": 8.944806382100394e-05,
|
315 |
+
"loss": 0.4389,
|
316 |
+
"step": 23000
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 1.3,
|
320 |
+
"learning_rate": 8.897253809494634e-05,
|
321 |
+
"loss": 0.4386,
|
322 |
+
"step": 23500
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 1.35,
|
326 |
+
"learning_rate": 8.848872653432954e-05,
|
327 |
+
"loss": 0.4373,
|
328 |
+
"step": 24000
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.39,
|
332 |
+
"learning_rate": 8.799674851241666e-05,
|
333 |
+
"loss": 0.438,
|
334 |
+
"step": 24500
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 1.44,
|
338 |
+
"learning_rate": 8.749672541742298e-05,
|
339 |
+
"loss": 0.4379,
|
340 |
+
"step": 25000
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 1.44,
|
344 |
+
"eval_loss": 0.415912002325058,
|
345 |
+
"eval_runtime": 93.156,
|
346 |
+
"eval_samples_per_second": 53.673,
|
347 |
+
"eval_steps_per_second": 0.848,
|
348 |
+
"step": 25000
|
349 |
}
|
350 |
],
|
351 |
"max_steps": 100000,
|
352 |
"num_train_epochs": 9,
|
353 |
+
"total_flos": 1.1774609555574384e+21,
|
354 |
"trial_name": null,
|
355 |
"trial_params": null
|
356 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5679
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0091be33616f449526c621b5dc7d5430418f8d9b3aec1ceac81b29b107da733
|
3 |
size 5679
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f550aaa679be49bdef1e79d5263b22969a6f34b532e760e534bc4ff1c616cbeb
|
3 |
size 449471589
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5679
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0091be33616f449526c621b5dc7d5430418f8d9b3aec1ceac81b29b107da733
|
3 |
size 5679
|