Training in progress, step 29500, 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 sha256:45445e00cb3b3c3160cd09518014a8d548f750ce07810fcb59cab4716d686a75
|
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 sha256:860e5480ec58ae105f232369752de1e46086b5b8a9a8e02e0568f739e3db47da
|
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:cfbdbe9095547e18c17d320549c5472267ced14c1f90d6cc0b45691b4f8984ab
|
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:dee25058dffca5a1a617a9686f45627e411c625a3da5c1337d0c291ae5eea0ea
|
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,
|
@@ -395,13 +395,19 @@
|
|
395 |
"learning_rate": 0.00011025168815224063,
|
396 |
"loss": 0.453,
|
397 |
"step": 29000
|
|
|
|
|
|
|
|
|
|
|
|
|
398 |
}
|
399 |
],
|
400 |
"logging_steps": 500,
|
401 |
"max_steps": 32580,
|
402 |
"num_train_epochs": 5,
|
403 |
"save_steps": 500,
|
404 |
-
"total_flos": 1.
|
405 |
"trial_name": null,
|
406 |
"trial_params": null
|
407 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.52731737262124,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 29500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
395 |
"learning_rate": 0.00011025168815224063,
|
396 |
"loss": 0.453,
|
397 |
"step": 29000
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 4.53,
|
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": 1.5641688844271616e+16,
|
411 |
"trial_name": null,
|
412 |
"trial_params": null
|
413 |
}
|