Training in progress, step 9000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +39 -3
- pytorch_model.bin +1 -1
- runs/May25_07-14-58_27b5c1724d9c/events.out.tfevents.1684999636.27b5c1724d9c.3103.0 +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 1987250795
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c02848fe198317b9df9c7b015be7a5a8d106b3d8c95581e94d368f12e3bd2aa
|
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 sha256:8b36224e26915e60a69c3f0ca4cf1c1be64bf420a8b16ec7564af83207802475
|
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 sha256:989bf089e99481fed8a0ca8c42df0ebf959c5055d0443690a60cd2739bd951a3
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ca42b4728e4a3dd46497569040a4bcb0499b808d030d537723afa704d3d5cea
|
3 |
size 557
|
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 sha256:42803a5c9416fe30408add7b6997c032033033ede5cc3b581b72368a5f47393e
|
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,
|
@@ -294,11 +294,47 @@
|
|
294 |
"eval_samples_per_second": 2.448,
|
295 |
"eval_steps_per_second": 0.311,
|
296 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
297 |
}
|
298 |
],
|
299 |
"max_steps": 11700,
|
300 |
"num_train_epochs": 300,
|
301 |
-
"total_flos":
|
302 |
"trial_name": null,
|
303 |
"trial_params": null
|
304 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 230.76923076923077,
|
5 |
+
"global_step": 9000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
294 |
"eval_samples_per_second": 2.448,
|
295 |
"eval_steps_per_second": 0.311,
|
296 |
"step": 8000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 217.95,
|
300 |
+
"learning_rate": 1.6520618556701032e-05,
|
301 |
+
"loss": 0.0023,
|
302 |
+
"step": 8500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 217.95,
|
306 |
+
"eval_bleu": 96.4892,
|
307 |
+
"eval_em": 0.6379,
|
308 |
+
"eval_gen_len": 81.9424,
|
309 |
+
"eval_loss": 0.25497403740882874,
|
310 |
+
"eval_rm": 0.7482,
|
311 |
+
"eval_runtime": 168.8592,
|
312 |
+
"eval_samples_per_second": 2.47,
|
313 |
+
"eval_steps_per_second": 0.314,
|
314 |
+
"step": 8500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 230.77,
|
318 |
+
"learning_rate": 1.3943298969072165e-05,
|
319 |
+
"loss": 0.0022,
|
320 |
+
"step": 9000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 230.77,
|
324 |
+
"eval_bleu": 96.8559,
|
325 |
+
"eval_em": 0.6475,
|
326 |
+
"eval_gen_len": 81.5635,
|
327 |
+
"eval_loss": 0.2539912760257721,
|
328 |
+
"eval_rm": 0.7506,
|
329 |
+
"eval_runtime": 158.2741,
|
330 |
+
"eval_samples_per_second": 2.635,
|
331 |
+
"eval_steps_per_second": 0.335,
|
332 |
+
"step": 9000
|
333 |
}
|
334 |
],
|
335 |
"max_steps": 11700,
|
336 |
"num_train_epochs": 300,
|
337 |
+
"total_flos": 7171986679845120.0,
|
338 |
"trial_name": null,
|
339 |
"trial_params": null
|
340 |
}
|
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 sha256:8b36224e26915e60a69c3f0ca4cf1c1be64bf420a8b16ec7564af83207802475
|
3 |
size 996026489
|
runs/May25_07-14-58_27b5c1724d9c/events.out.tfevents.1684999636.27b5c1724d9c.3103.0
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 sha256:58cc137eff897db8b4f86e972869b1df7c24ded97a37d5527235e0aba68862a4
|
3 |
+
size 19703
|