Training in progress, step 31000
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 sha256:3a61c5c7da353de56d11c86d198d4c6d5cda0e0d0e6bf98247fd671c1bcb0110
|
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:c8c6d623f6cf69d7a07b8a59178628e953bc076932f943b1b7c4a4aeffc5a1e5
|
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:c9d59c805fc9cc07aaaf131bf71beead08c89f1947e3098eff96bb5a47564158
|
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 sha256:7e645c1f7f1d5e2f4989839495bcb2b35bcc651cb45f6546dab5a80c8f73602e
|
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,
|
@@ -372,11 +372,17 @@
|
|
372 |
"learning_rate": 1.5351136363636365e-05,
|
373 |
"loss": 0.033,
|
374 |
"step": 30500
|
|
|
|
|
|
|
|
|
|
|
|
|
375 |
}
|
376 |
],
|
377 |
"max_steps": 44000,
|
378 |
"num_train_epochs": 1,
|
379 |
-
"total_flos": 3.
|
380 |
"trial_name": null,
|
381 |
"trial_params": null
|
382 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.42052144659377627,
|
5 |
+
"global_step": 31000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
372 |
"learning_rate": 1.5351136363636365e-05,
|
373 |
"loss": 0.033,
|
374 |
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.42,
|
378 |
+
"learning_rate": 1.4782954545454547e-05,
|
379 |
+
"loss": 0.0307,
|
380 |
+
"step": 31000
|
381 |
}
|
382 |
],
|
383 |
"max_steps": 44000,
|
384 |
"num_train_epochs": 1,
|
385 |
+
"total_flos": 3.239176972743475e+16,
|
386 |
"trial_name": null,
|
387 |
"trial_params": null
|
388 |
}
|
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:c8c6d623f6cf69d7a07b8a59178628e953bc076932f943b1b7c4a4aeffc5a1e5
|
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:eb1505f8139a42e0ed4fd8c194f8bddc6e47233f914b89d5d7d8e38bfd87f47e
|
3 |
+
size 55470
|