Training in progress, step 11000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1001681601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85ea0a0bb88ee8c200e755fa81bfe640eb75ea8d6bc5ebcbc2b921298a1efa88
|
3 |
size 1001681601
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12f17df6da6b3966fedac5eea1c03557dd46622fa72c727483f4c301ca090da6
|
3 |
size 551185105
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9706fcd59e21ce18c9aa7726ddae6bfe7814736c01f7988d6ed9ec560b2448f6
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec038b23343723954956502448222137cdbdfb11ecc542e553da010b71c9a38c
|
3 |
size 623
|
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,
|
@@ -132,11 +132,17 @@
|
|
132 |
"learning_rate": 3.8070454545454546e-05,
|
133 |
"loss": 0.0351,
|
134 |
"step": 10500
|
|
|
|
|
|
|
|
|
|
|
|
|
135 |
}
|
136 |
],
|
137 |
"max_steps": 44000,
|
138 |
"num_train_epochs": 1,
|
139 |
-
"total_flos": 1.
|
140 |
"trial_name": null,
|
141 |
"trial_params": null
|
142 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1492172875010174,
|
5 |
+
"global_step": 11000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
132 |
"learning_rate": 3.8070454545454546e-05,
|
133 |
"loss": 0.0351,
|
134 |
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.15,
|
138 |
+
"learning_rate": 3.750227272727273e-05,
|
139 |
+
"loss": 0.0358,
|
140 |
+
"step": 11000
|
141 |
}
|
142 |
],
|
143 |
"max_steps": 44000,
|
144 |
"num_train_epochs": 1,
|
145 |
+
"total_flos": 1.1495201939914752e+16,
|
146 |
"trial_name": null,
|
147 |
"trial_params": null
|
148 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12f17df6da6b3966fedac5eea1c03557dd46622fa72c727483f4c301ca090da6
|
3 |
size 551185105
|
runs/Oct19_12-48-30_40567d3bb726/events.out.tfevents.1666183950.40567d3bb726.23.0
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 sha256:43a33145c838f06b027f2075cef0aa25856faf7c0323ff295dd89535c3d4616d
|
3 |
+
size 49100
|