Training in progress, step 24500
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1001681601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19153d9a74506d936c22a5bb33afb6676315e86faa63f8bf1b361be31b2267ba
|
3 |
size 1001681601
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4fd18134831c4533ec2be2bf377eea317ade7ce0474ffb78e4ccc66ae0e5abc
|
3 |
size 551185105
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d9fc17460ee9bafbd31c2e822bf90ce75cd0e412de50a2621626d3c404e6f8d
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9287c104ef7fa8522795863b79e88381104f50bf4d5ce49fe33ad956c758281e
|
3 |
size 623
|
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 +294,17 @@
|
|
294 |
"learning_rate": 2.273409090909091e-05,
|
295 |
"loss": 0.0324,
|
296 |
"step": 24000
|
|
|
|
|
|
|
|
|
|
|
|
|
297 |
}
|
298 |
],
|
299 |
"max_steps": 44000,
|
300 |
"num_train_epochs": 1,
|
301 |
-
"total_flos": 2.
|
302 |
"trial_name": null,
|
303 |
"trial_params": null
|
304 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.33234759488862964,
|
5 |
+
"global_step": 24500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
294 |
"learning_rate": 2.273409090909091e-05,
|
295 |
"loss": 0.0324,
|
296 |
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.33,
|
300 |
+
"learning_rate": 2.2167045454545455e-05,
|
301 |
+
"loss": 0.0334,
|
302 |
+
"step": 24500
|
303 |
}
|
304 |
],
|
305 |
"max_steps": 44000,
|
306 |
"num_train_epochs": 1,
|
307 |
+
"total_flos": 2.560038519649075e+16,
|
308 |
"trial_name": null,
|
309 |
"trial_params": null
|
310 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4fd18134831c4533ec2be2bf377eea317ade7ce0474ffb78e4ccc66ae0e5abc
|
3 |
size 551185105
|
runs/Oct19_12-48-30_40567d3bb726/events.out.tfevents.1666183950.40567d3bb726.23.0
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 sha256:82670b647a752ae74e59b4d5503c7dd45410f56610a8964a1344dd382e199b1d
|
3 |
+
size 53390
|