Training in progress, step 15000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +19 -3
- nbest_predictions.json +0 -0
- predictions.json +0 -0
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 943333453
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7ce6f47f0b535e3c17cf93424dcb27acff863da3bee507ab09fd792b5441dce
|
3 |
size 943333453
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 471708325
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:936c68f355516686acc9fd8569ff44fad57e40ebab35445a8e00a909274717d0
|
3 |
size 471708325
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d26e5aedc9783fd5b42389903a55518c26dc435542e82c46eab02c99a9e3e04
|
3 |
size 14503
|
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 sha256:320e7103d68ac581e0918aaf471171063cef4a15a2322663039e70f087daa791
|
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 sha256:6b00fc05a490426638de1c3614fb5c6f7749b64a69fbff99c5dbd21e1e76058a
|
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,
|
@@ -38,11 +38,27 @@
|
|
38 |
"eval_samples_per_second": 7.505,
|
39 |
"eval_steps_per_second": 3.753,
|
40 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
}
|
42 |
],
|
43 |
"max_steps": 92088,
|
44 |
"num_train_epochs": 3,
|
45 |
-
"total_flos":
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
48 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.48866301798279904,
|
5 |
+
"global_step": 15000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
38 |
"eval_samples_per_second": 7.505,
|
39 |
"eval_steps_per_second": 3.753,
|
40 |
"step": 10000
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 0.49,
|
44 |
+
"learning_rate": 2.511695334897055e-05,
|
45 |
+
"loss": 1.0769,
|
46 |
+
"step": 15000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.49,
|
50 |
+
"eval_exact_match": 77.56042427403929,
|
51 |
+
"eval_f1": 82.22503770504048,
|
52 |
+
"eval_loss": 0.9495312571525574,
|
53 |
+
"eval_runtime": 1533.818,
|
54 |
+
"eval_samples_per_second": 7.506,
|
55 |
+
"eval_steps_per_second": 3.753,
|
56 |
+
"step": 15000
|
57 |
}
|
58 |
],
|
59 |
"max_steps": 92088,
|
60 |
"num_train_epochs": 3,
|
61 |
+
"total_flos": 3.309705437184e+16,
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|
nbest_predictions.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
predictions.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 471708325
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:936c68f355516686acc9fd8569ff44fad57e40ebab35445a8e00a909274717d0
|
3 |
size 471708325
|