Commit ·
d282a2b
1
Parent(s): eb7128d
Training in progress, step 1000
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 +17 -3
- pytorch_model.bin +1 -1
- runs/Feb20_09-01-29_18ffb5c4eaf2/events.out.tfevents.1676883692.18ffb5c4eaf2.214.0 +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 6082574325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c360933c4888e54f98ff9a9d57522aa75beb574165ab43790e83dcd821608944
|
| 3 |
size 6082574325
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3141974301
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23d997a50581e0c49f4a2a29f1c407934468d756400ad032532077d30e0a63ec
|
| 3 |
size 3141974301
|
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:c1978a210c8da2dc481503b680a47230059843076072eb05c1b3f1f2695beaa0
|
| 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:eca96332960acd013bca495746d45273536aa72a08aa42d3b7b2902f2e6e9626
|
| 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": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -12,11 +12,25 @@
|
|
| 12 |
"learning_rate": 1.982500349993e-05,
|
| 13 |
"loss": 3.4571,
|
| 14 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
| 16 |
],
|
| 17 |
"max_steps": 57144,
|
| 18 |
"num_train_epochs": 8,
|
| 19 |
-
"total_flos":
|
| 20 |
"trial_name": null,
|
| 21 |
"trial_params": null
|
| 22 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1399972000559989,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 12 |
"learning_rate": 1.982500349993e-05,
|
| 13 |
"loss": 3.4571,
|
| 14 |
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"learning_rate": 1.9650006999860005e-05,
|
| 19 |
+
"loss": 3.3857,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.14,
|
| 24 |
+
"eval_loss": 3.312843084335327,
|
| 25 |
+
"eval_runtime": 161.8869,
|
| 26 |
+
"eval_samples_per_second": 7.647,
|
| 27 |
+
"eval_steps_per_second": 7.647,
|
| 28 |
+
"step": 1000
|
| 29 |
}
|
| 30 |
],
|
| 31 |
"max_steps": 57144,
|
| 32 |
"num_train_epochs": 8,
|
| 33 |
+
"total_flos": 1019939328000000.0,
|
| 34 |
"trial_name": null,
|
| 35 |
"trial_params": null
|
| 36 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3141974301
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23d997a50581e0c49f4a2a29f1c407934468d756400ad032532077d30e0a63ec
|
| 3 |
size 3141974301
|
runs/Feb20_09-01-29_18ffb5c4eaf2/events.out.tfevents.1676883692.18ffb5c4eaf2.214.0
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:fd6a74a7840ee2add89717d25eeb1aa954d1c2cd276122a1d54cf315722d3454
|
| 3 |
+
size 4606
|