Training in progress, step 100, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109098378
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e82124fa33dfc5f03da9ab79744d178b4289e9dd3c57171fda6cbcbfdd96d628
|
3 |
size 109098378
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218182458
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c253fa2283556ee0de3aceabba498ca098d948b0b699b126056a5ea2684332d
|
3 |
size 218182458
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25d688a2388d63ae631929b6adc93a369ba8fcf217ffb2f18236f4f4f5f16de3
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f03c40f5d8d354bf32a3e9f1aa7d9b1d73430eba02e5d7fec0599e6d11c23204
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -19,13 +19,25 @@
|
|
19 |
"learning_rate": 0.00018550053929480202,
|
20 |
"loss": 0.6524,
|
21 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 25,
|
25 |
"max_steps": 250,
|
26 |
"num_train_epochs": 2,
|
27 |
"save_steps": 50,
|
28 |
-
"total_flos":
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5208333333333334,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
19 |
"learning_rate": 0.00018550053929480202,
|
20 |
"loss": 0.6524,
|
21 |
"step": 50
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.39,
|
25 |
+
"learning_rate": 0.00016449948488669639,
|
26 |
+
"loss": 0.605,
|
27 |
+
"step": 75
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.52,
|
31 |
+
"learning_rate": 0.000136764169663272,
|
32 |
+
"loss": 0.5817,
|
33 |
+
"step": 100
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 25,
|
37 |
"max_steps": 250,
|
38 |
"num_train_epochs": 2,
|
39 |
"save_steps": 50,
|
40 |
+
"total_flos": 5591881680814080.0,
|
41 |
"trial_name": null,
|
42 |
"trial_params": null
|
43 |
}
|