Training in progress, step 4800
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 +19 -3
- pytorch_model.bin +1 -1
- runs/Jun11_17-16-54_85c57c84c81b/events.out.tfevents.1686505038.85c57c84c81b.590.0 +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 2067085189
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45ef7c81a3834a08bf5dbff8f6814633aa4fa345bc009ea447f91958df650038
|
3 |
size 2067085189
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2242911029
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:688b6b6b28cc75c324df7a4068e80c754c718497b26d165babed7f2a949e9ae9
|
3 |
size 2242911029
|
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:eb165058f0a351e9b2361462265160953e690895419ea09925ddae53c2bf5afb
|
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:c5d6d9131d8c7c16eb153dcfd7bbc1ac08956d4b575d96ec4c47e608e225cef6
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -164,11 +164,27 @@
|
|
164 |
"eval_samples_per_second": 244.921,
|
165 |
"eval_steps_per_second": 0.958,
|
166 |
"step": 4400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
167 |
}
|
168 |
],
|
169 |
"max_steps": 953000,
|
170 |
"num_train_epochs": 100,
|
171 |
-
"total_flos": 1.
|
172 |
"trial_name": null,
|
173 |
"trial_params": null
|
174 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5036726128016789,
|
5 |
+
"global_step": 4800,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
164 |
"eval_samples_per_second": 244.921,
|
165 |
"eval_steps_per_second": 0.958,
|
166 |
"step": 4400
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.47,
|
170 |
+
"learning_rate": 9.953043022035678e-06,
|
171 |
+
"loss": 0.8562,
|
172 |
+
"step": 4500
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.5,
|
176 |
+
"eval_accuracy": 0.8366657321194056,
|
177 |
+
"eval_f1": 0.835771965342758,
|
178 |
+
"eval_loss": 0.791612982749939,
|
179 |
+
"eval_runtime": 553.559,
|
180 |
+
"eval_samples_per_second": 244.848,
|
181 |
+
"eval_steps_per_second": 0.957,
|
182 |
+
"step": 4800
|
183 |
}
|
184 |
],
|
185 |
"max_steps": 953000,
|
186 |
"num_train_epochs": 100,
|
187 |
+
"total_flos": 1.973057028395397e+17,
|
188 |
"trial_name": null,
|
189 |
"trial_params": null
|
190 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2242911029
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:688b6b6b28cc75c324df7a4068e80c754c718497b26d165babed7f2a949e9ae9
|
3 |
size 2242911029
|
runs/Jun11_17-16-54_85c57c84c81b/events.out.tfevents.1686505038.85c57c84c81b.590.0
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 sha256:67cdbaa254e7b8b444332d1fe04c137f2811731a70ec576b0643a523eee1daf9
|
3 |
+
size 5247
|