Training in progress, step 31500, 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 sha256:6fd732c02dfd257fc56e22a5c772f8b31c2590b627b9aa9759bf11b2a4ae6cd1
|
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:adb108aaca9a16c60cf8cd7440a2a71703db5e8027b221da435e10f6bb487be3
|
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 sha256:88ce6c02c4d3aa0fa5e5f64e20639965e8b171ac596a85430567deeb197f908c
|
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:b5682475cdf9ce1d9d8a6757c148146046420a6063cceb4d17e9f63c61f57742
|
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,
|
@@ -419,13 +419,19 @@
|
|
419 |
"learning_rate": 4.8895027624309394e-05,
|
420 |
"loss": 0.4555,
|
421 |
"step": 31000
|
|
|
|
|
|
|
|
|
|
|
|
|
422 |
}
|
423 |
],
|
424 |
"logging_steps": 500,
|
425 |
"max_steps": 32580,
|
426 |
"num_train_epochs": 5,
|
427 |
"save_steps": 500,
|
428 |
-
"total_flos": 1.
|
429 |
"trial_name": null,
|
430 |
"trial_params": null
|
431 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.834254143646409,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 31500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
419 |
"learning_rate": 4.8895027624309394e-05,
|
420 |
"loss": 0.4555,
|
421 |
"step": 31000
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 4.83,
|
425 |
+
"learning_rate": 3.3548189073050956e-05,
|
426 |
+
"loss": 0.4563,
|
427 |
+
"step": 31500
|
428 |
}
|
429 |
],
|
430 |
"logging_steps": 500,
|
431 |
"max_steps": 32580,
|
432 |
"num_train_epochs": 5,
|
433 |
"save_steps": 500,
|
434 |
+
"total_flos": 1.670320842866688e+16,
|
435 |
"trial_name": null,
|
436 |
"trial_params": null
|
437 |
}
|