hariniiiiiiiiii
commited on
Commit
•
5575e14
1
Parent(s):
3b584c5
Training in progress, step 500
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 +75 -3
- pytorch_model.bin +1 -1
- runs/Feb08_05-23-30_74bc69b4becb/events.out.tfevents.1675836783.74bc69b4becb.290.4 +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 4115013
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c36d72b05089e24fbdb20f58edda2d589f745b59929423cb750fe3542e13898
|
3 |
size 4115013
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2329702453
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e65a378301a7811cf0ef09053f95a65dcc2ca531c1d476902b59315ede5aeab0
|
3 |
size 2329702453
|
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:c62b4adb9e39700227a9dfe709b9be3404fb7da10290b22d1a55586d48740a30
|
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:ee5d8512ea69f36ac3d76c8a2d1063766890ab26719024996676d7b75548920c
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -294,11 +294,83 @@
|
|
294 |
"eval_samples_per_second": 0.248,
|
295 |
"eval_steps_per_second": 0.248,
|
296 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
297 |
}
|
298 |
],
|
299 |
"max_steps": 3542,
|
300 |
"num_train_epochs": 7,
|
301 |
-
"total_flos":
|
302 |
"trial_name": null,
|
303 |
"trial_params": null
|
304 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9863148810257675,
|
5 |
+
"global_step": 500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
294 |
"eval_samples_per_second": 0.248,
|
295 |
"eval_steps_per_second": 0.248,
|
296 |
"step": 400
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.81,
|
300 |
+
"learning_rate": 0.0004536500579374276,
|
301 |
+
"loss": 0.2323,
|
302 |
+
"step": 410
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.83,
|
306 |
+
"learning_rate": 0.00045220162224797217,
|
307 |
+
"loss": 0.2222,
|
308 |
+
"step": 420
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.85,
|
312 |
+
"learning_rate": 0.0004507531865585168,
|
313 |
+
"loss": 0.2516,
|
314 |
+
"step": 430
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.87,
|
318 |
+
"learning_rate": 0.0004493047508690614,
|
319 |
+
"loss": 0.2851,
|
320 |
+
"step": 440
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.89,
|
324 |
+
"learning_rate": 0.000447856315179606,
|
325 |
+
"loss": 0.2677,
|
326 |
+
"step": 450
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.91,
|
330 |
+
"learning_rate": 0.00044640787949015064,
|
331 |
+
"loss": 0.2447,
|
332 |
+
"step": 460
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.93,
|
336 |
+
"learning_rate": 0.00044495944380069523,
|
337 |
+
"loss": 0.3186,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.95,
|
342 |
+
"learning_rate": 0.0004435110081112398,
|
343 |
+
"loss": 0.3035,
|
344 |
+
"step": 480
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.97,
|
348 |
+
"learning_rate": 0.0004420625724217845,
|
349 |
+
"loss": 0.3036,
|
350 |
+
"step": 490
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.99,
|
354 |
+
"learning_rate": 0.0004406141367323291,
|
355 |
+
"loss": 0.1972,
|
356 |
+
"step": 500
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.99,
|
360 |
+
"eval_loss": 1.0465357303619385,
|
361 |
+
"eval_rouge1": 0.1908791208791209,
|
362 |
+
"eval_rouge2": 0.10681818181818181,
|
363 |
+
"eval_rougeL": 0.17934065934065935,
|
364 |
+
"eval_rougeLsum": 0.19159340659340657,
|
365 |
+
"eval_runtime": 84.3482,
|
366 |
+
"eval_samples_per_second": 0.237,
|
367 |
+
"eval_steps_per_second": 0.237,
|
368 |
+
"step": 500
|
369 |
}
|
370 |
],
|
371 |
"max_steps": 3542,
|
372 |
"num_train_epochs": 7,
|
373 |
+
"total_flos": 1.2123850515499008e+16,
|
374 |
"trial_name": null,
|
375 |
"trial_params": null
|
376 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2329702453
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e65a378301a7811cf0ef09053f95a65dcc2ca531c1d476902b59315ede5aeab0
|
3 |
size 2329702453
|
runs/Feb08_05-23-30_74bc69b4becb/events.out.tfevents.1675836783.74bc69b4becb.290.4
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 sha256:1a4dba25a0bde9038c15a6af7ee58649a984a45ecfc3765c4e05acf774193a45
|
3 |
+
size 10366
|