Training in progress, step 684000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +39 -3
- pytorch_model.bin +1 -1
- runs/Jun07_08-27-15_3a7f67f8b43f/events.out.tfevents.1686127999.3a7f67f8b43f.172.0 +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 3871544599
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37c607bba26cfdf38c86d0008c177a08f19a45729aead65386002738a39ce45e
|
3 |
size 3871544599
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05f8278eaad5064bce348e243541474803f31744bfcd30ad256947619c9ae9f5
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
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:dfef95a4a19d3c28dbe54f1b9376def4f126fc6365803f9152a5a3d630c2ea72
|
3 |
+
size 14639
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8da14a4d7b374e30001d1fc00d8b9d526bac9574b28d04936c4dec866d2841d6
|
3 |
size 557
|
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 sha256:37a8bcedf9c9c261cc261ff2ba8a990ec5b8474bbc3ead50de227b40f6dbad74
|
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": 17.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -8178,11 +8178,47 @@
|
|
8178 |
"learning_rate": 1.4191554616482833e-07,
|
8179 |
"loss": 1.0191,
|
8180 |
"step": 681000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8181 |
}
|
8182 |
],
|
8183 |
"max_steps": 762960,
|
8184 |
"num_train_epochs": 20,
|
8185 |
-
"total_flos": 8.
|
8186 |
"trial_name": null,
|
8187 |
"trial_params": null
|
8188 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 17.930156965954012,
|
5 |
+
"global_step": 684000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
8178 |
"learning_rate": 1.4191554616482833e-07,
|
8179 |
"loss": 1.0191,
|
8180 |
"step": 681000
|
8181 |
+
},
|
8182 |
+
{
|
8183 |
+
"epoch": 17.86,
|
8184 |
+
"learning_rate": 1.4021105872006806e-07,
|
8185 |
+
"loss": 1.0105,
|
8186 |
+
"step": 681500
|
8187 |
+
},
|
8188 |
+
{
|
8189 |
+
"epoch": 17.88,
|
8190 |
+
"learning_rate": 1.3851657379057583e-07,
|
8191 |
+
"loss": 1.0194,
|
8192 |
+
"step": 682000
|
8193 |
+
},
|
8194 |
+
{
|
8195 |
+
"epoch": 17.89,
|
8196 |
+
"learning_rate": 1.3683209855882006e-07,
|
8197 |
+
"loss": 1.0161,
|
8198 |
+
"step": 682500
|
8199 |
+
},
|
8200 |
+
{
|
8201 |
+
"epoch": 17.9,
|
8202 |
+
"learning_rate": 1.3515764016484245e-07,
|
8203 |
+
"loss": 1.0071,
|
8204 |
+
"step": 683000
|
8205 |
+
},
|
8206 |
+
{
|
8207 |
+
"epoch": 17.92,
|
8208 |
+
"learning_rate": 1.3349320570622464e-07,
|
8209 |
+
"loss": 1.0057,
|
8210 |
+
"step": 683500
|
8211 |
+
},
|
8212 |
+
{
|
8213 |
+
"epoch": 17.93,
|
8214 |
+
"learning_rate": 1.318388022380601e-07,
|
8215 |
+
"loss": 1.0081,
|
8216 |
+
"step": 684000
|
8217 |
}
|
8218 |
],
|
8219 |
"max_steps": 762960,
|
8220 |
"num_train_epochs": 20,
|
8221 |
+
"total_flos": 8.09446081806803e+17,
|
8222 |
"trial_name": null,
|
8223 |
"trial_params": null
|
8224 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05f8278eaad5064bce348e243541474803f31744bfcd30ad256947619c9ae9f5
|
3 |
size 1944201353
|
runs/Jun07_08-27-15_3a7f67f8b43f/events.out.tfevents.1686127999.3a7f67f8b43f.172.0
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 sha256:05004feb8aae3123de67b4b51994475f6af5d6991098a7a0c1db6e1cd7676114
|
3 |
+
size 12141
|