Commit
·
7e6de7a
1
Parent(s):
dd06878
Training in progress, step 7000
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:d0fd2e6c5e2cb9363ad890f92a0f6f751126366a03df290a22863d0f78f6d8fb
|
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 sha256:1361d8306f36617a8150a247b418cd809f3843997b78fa3a4c4e75255ae4bc6b
|
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 sha256:4586e3d54f410af4be81ad23b602c9d46e66a6c0a91d8a158fd7bc21129fdb64
|
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 sha256:9d5645f3009253210cdc42c9db63c62928c668e12c10d4d259752e3d751ef6fa
|
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": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -126,11 +126,31 @@
|
|
126 |
"eval_samples_per_second": 15.502,
|
127 |
"eval_steps_per_second": 5.17,
|
128 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
129 |
}
|
130 |
],
|
131 |
"max_steps": 19990,
|
132 |
"num_train_epochs": 5,
|
133 |
-
"total_flos":
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.7508754377188596,
|
5 |
+
"global_step": 7000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
126 |
"eval_samples_per_second": 15.502,
|
127 |
"eval_steps_per_second": 5.17,
|
128 |
"step": 6000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.63,
|
132 |
+
"learning_rate": 1.3496748374187095e-05,
|
133 |
+
"loss": 2.8256,
|
134 |
+
"step": 6500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.75,
|
138 |
+
"learning_rate": 1.2996498249124563e-05,
|
139 |
+
"loss": 2.8415,
|
140 |
+
"step": 7000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.75,
|
144 |
+
"eval_loss": 3.097115993499756,
|
145 |
+
"eval_runtime": 136.3306,
|
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": 9903722250240000.0,
|
154 |
"trial_name": null,
|
155 |
"trial_params": null
|
156 |
}
|
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 sha256:1361d8306f36617a8150a247b418cd809f3843997b78fa3a4c4e75255ae4bc6b
|
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:e584c9d53a064cddf55a18913421636bc878d3e5a57a6fe543cc35d1b6085f47
|
3 |
+
size 7123
|