Dmitriy007
commited on
Commit
•
330b071
1
Parent(s):
7c1ace1
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/Mar25_07-47-44_6e686009e3a0/events.out.tfevents.1679730482.6e686009e3a0.183.0 +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:ce02a884cff9c0c33b9ea0be5dabed04223f7b92e622f67dd75b20a294f4957c
|
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:c1a06359204895a2b4ac4327b2ba9b58a11a645bfab8dc5dc5c1f33cc4c56b05
|
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 sha256:35d8ee4e99967dfddcdbfa3f701d7c423f15993ec9569b899109556fcf23f606
|
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:c8da528fd7f428de97e2b07202a1629e295196c693ae8d5d2bf4e84b9478cdc3
|
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": 15.917,
|
147 |
"eval_steps_per_second": 2.654,
|
148 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
149 |
}
|
150 |
],
|
151 |
"max_steps": 9995,
|
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": 4.00200100050025,
|
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": 15.917,
|
147 |
"eval_steps_per_second": 2.654,
|
148 |
"step": 7000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 3.75,
|
152 |
+
"learning_rate": 4.992496248124062e-06,
|
153 |
+
"loss": 2.8219,
|
154 |
+
"step": 7500
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 4.0,
|
158 |
+
"learning_rate": 3.991995997999e-06,
|
159 |
+
"loss": 2.8267,
|
160 |
+
"step": 8000
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 4.0,
|
164 |
+
"eval_loss": 3.085977077484131,
|
165 |
+
"eval_runtime": 133.3062,
|
166 |
+
"eval_samples_per_second": 15.881,
|
167 |
+
"eval_steps_per_second": 2.648,
|
168 |
+
"step": 8000
|
169 |
}
|
170 |
],
|
171 |
"max_steps": 9995,
|
172 |
"num_train_epochs": 5,
|
173 |
+
"total_flos": 2.263707942912e+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:c1a06359204895a2b4ac4327b2ba9b58a11a645bfab8dc5dc5c1f33cc4c56b05
|
3 |
size 1524261149
|
runs/Mar25_07-47-44_6e686009e3a0/events.out.tfevents.1679730482.6e686009e3a0.183.0
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 sha256:98d16bcaeb6710ed70950d0fec4cd75f9d753b93f3c01047572a1c783a9b6d19
|
3 |
+
size 5398
|