Dmitriy007
commited on
Commit
•
dd06878
1
Parent(s):
ce2ae74
Training in progress, step 6000
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:b3d6d690cae286d70fbf4bc233a889c62f4883a7ffcbe6a3638e2ff8aa416899
|
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 sha256:9101db56ff9c5dd0fae13398d3f0a8b7a953031bf7a55ac66f3a3483712630b2
|
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:d9b66b00d675b14577f8b85e7cb29664e731db41813ef81c141d1f81afa86c20
|
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 sha256:5ff29bb8fd66c4d9ef897d85c25fef6f3e2b8f96d7bae61e070b71aefa9530e8
|
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,
|
@@ -106,11 +106,31 @@
|
|
106 |
"eval_samples_per_second": 15.499,
|
107 |
"eval_steps_per_second": 5.169,
|
108 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
}
|
110 |
],
|
111 |
"max_steps": 19990,
|
112 |
"num_train_epochs": 5,
|
113 |
-
"total_flos":
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|
116 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.500750375187594,
|
5 |
+
"global_step": 6000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
106 |
"eval_samples_per_second": 15.499,
|
107 |
"eval_steps_per_second": 5.169,
|
108 |
"step": 5000
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.38,
|
112 |
+
"learning_rate": 1.4497248624312156e-05,
|
113 |
+
"loss": 2.5623,
|
114 |
+
"step": 5500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.5,
|
118 |
+
"learning_rate": 1.3996998499249626e-05,
|
119 |
+
"loss": 2.5847,
|
120 |
+
"step": 6000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 1.5,
|
124 |
+
"eval_loss": 3.1701245307922363,
|
125 |
+
"eval_runtime": 136.5649,
|
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": 8488904785920000.0,
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|
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 sha256:9101db56ff9c5dd0fae13398d3f0a8b7a953031bf7a55ac66f3a3483712630b2
|
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:c7529e4021cad539a45668c4eb0d6cf5c8155fb0b0ee4dce1a4baf2ff8b6ec02
|
3 |
+
size 6538
|