Training in progress, step 30000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:436e75c0d1e47eacd20d2b2d2e5a4aa210ee17f0be2ca65d05b9cb97567a4668
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54a06b175d674b22c2347a361834c9aaeb843f7997bad40fc730d21afa3a73c5
|
3 |
size 484163514
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e7105a3e5233eafd7fa043bb9adbf40d6645658ca3da87ca53a597d955f15fd
|
3 |
size 14244
|
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 sha256:866c0eede7c095b73541d89431e86f84cb24179d3b08d9741fd4e74a2f843ad6
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 4.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -401,13 +401,19 @@
|
|
401 |
"learning_rate": 9.49048496009822e-05,
|
402 |
"loss": 0.4549,
|
403 |
"step": 29500
|
|
|
|
|
|
|
|
|
|
|
|
|
404 |
}
|
405 |
],
|
406 |
"logging_steps": 500,
|
407 |
"max_steps": 32580,
|
408 |
"num_train_epochs": 5,
|
409 |
"save_steps": 500,
|
410 |
-
"total_flos": 1.
|
411 |
"trial_name": null,
|
412 |
"trial_params": null
|
413 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.6040515653775325,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 30000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
401 |
"learning_rate": 9.49048496009822e-05,
|
402 |
"loss": 0.4549,
|
403 |
"step": 29500
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 4.6,
|
407 |
+
"learning_rate": 7.955801104972376e-05,
|
408 |
+
"loss": 0.4533,
|
409 |
+
"step": 30000
|
410 |
}
|
411 |
],
|
412 |
"logging_steps": 500,
|
413 |
"max_steps": 32580,
|
414 |
"num_train_epochs": 5,
|
415 |
"save_steps": 500,
|
416 |
+
"total_flos": 1.590680651563008e+16,
|
417 |
"trial_name": null,
|
418 |
"trial_params": null
|
419 |
}
|