Dmitriy007
commited on
Commit
•
989671e
1
Parent(s):
612a42a
Training in progress, step 9000
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:a4d988df7e612332e81308e1250ddbe63685dd74911946160c55466ace61b388
|
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 sha256:6c69015cf37e5110d0f1fa35408d6a71ac9b0b7660f9fdcd13ac73a9ae5158c9
|
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 sha256:5f24eb1227cfa1aa4237d9ebb9ac5182ec2f6b34fd67007f4ed211576e6af96e
|
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 sha256:9f5017fab71cba7889a6488075810c49a1cd074dc0e9ef76358f7ff98a878c06
|
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": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -166,11 +166,31 @@
|
|
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.
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
176 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.251125562781391,
|
5 |
+
"global_step": 9000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
166 |
"eval_samples_per_second": 15.504,
|
167 |
"eval_steps_per_second": 5.17,
|
168 |
"step": 8000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 2.13,
|
172 |
+
"learning_rate": 1.149574787393697e-05,
|
173 |
+
"loss": 2.6335,
|
174 |
+
"step": 8500
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 2.25,
|
178 |
+
"learning_rate": 1.0995497748874438e-05,
|
179 |
+
"loss": 2.6223,
|
180 |
+
"step": 9000
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 2.25,
|
184 |
+
"eval_loss": 3.1363072395324707,
|
185 |
+
"eval_runtime": 136.5056,
|
186 |
+
"eval_samples_per_second": 15.509,
|
187 |
+
"eval_steps_per_second": 5.172,
|
188 |
+
"step": 9000
|
189 |
}
|
190 |
],
|
191 |
"max_steps": 19990,
|
192 |
"num_train_epochs": 5,
|
193 |
+
"total_flos": 1.273335717888e+16,
|
194 |
"trial_name": null,
|
195 |
"trial_params": null
|
196 |
}
|
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 sha256:6c69015cf37e5110d0f1fa35408d6a71ac9b0b7660f9fdcd13ac73a9ae5158c9
|
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 sha256:7f9067c8fd31230cdfb7ef3c3aeb814e61fb1443c3f0cdf24440868fca2c8f50
|
3 |
+
size 8293
|