Dmitriy007
commited on
Commit
•
612a42a
1
Parent(s):
7e6de7a
Training in progress, step 8000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +23 -3
- pytorch_model.bin +1 -1
- runs/Mar21_09-39-35_da74753029b6/events.out.tfevents.1679391593.da74753029b6.214.2 +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 2847145157
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0704f0d00f025493932be8af6eafa1214a16165edd5aef7aaeb4d534b83cb484
|
3 |
size 2847145157
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35572a82b527720c0df5131e0d6f81dc619385cf7bc2556f1693da285a21d49d
|
3 |
size 1524261149
|
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 sha256:326c62b603e1867014c0e00d29e0f336a94266395a6f689146790ebe2cd08615
|
3 |
size 14575
|
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:d15a334fbe03b226a5464d27274f9bac8d107ef88fd62590b1de78f146f48128
|
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,
|
@@ -146,11 +146,31 @@
|
|
146 |
"eval_samples_per_second": 15.528,
|
147 |
"eval_steps_per_second": 5.179,
|
148 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
149 |
}
|
150 |
],
|
151 |
"max_steps": 19990,
|
152 |
"num_train_epochs": 5,
|
153 |
-
"total_flos":
|
154 |
"trial_name": null,
|
155 |
"trial_params": null
|
156 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.001000500250125,
|
5 |
+
"global_step": 8000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
146 |
"eval_samples_per_second": 15.528,
|
147 |
"eval_steps_per_second": 5.179,
|
148 |
"step": 7000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 1.88,
|
152 |
+
"learning_rate": 1.2496248124062031e-05,
|
153 |
+
"loss": 2.817,
|
154 |
+
"step": 7500
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 2.0,
|
158 |
+
"learning_rate": 1.19959979989995e-05,
|
159 |
+
"loss": 2.8338,
|
160 |
+
"step": 8000
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 2.0,
|
164 |
+
"eval_loss": 3.089996814727783,
|
165 |
+
"eval_runtime": 136.545,
|
166 |
+
"eval_samples_per_second": 15.504,
|
167 |
+
"eval_steps_per_second": 5.17,
|
168 |
+
"step": 8000
|
169 |
}
|
170 |
],
|
171 |
"max_steps": 19990,
|
172 |
"num_train_epochs": 5,
|
173 |
+
"total_flos": 1.131853971456e+16,
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
176 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35572a82b527720c0df5131e0d6f81dc619385cf7bc2556f1693da285a21d49d
|
3 |
size 1524261149
|
runs/Mar21_09-39-35_da74753029b6/events.out.tfevents.1679391593.da74753029b6.214.2
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 sha256:9e0d919c4d922143bafd6737c13ee59f12fdcccbcec5a7c46e0520697109e448
|
3 |
+
size 7708
|