Training in progress, step 150, 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 sha256:22a7d3e572fc0636a815d6cd322ad60b4a8b8d657c0d40e162f8ae3f0c995950
|
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:a07190be175afaf0ce148acd122a436c23c55702c08faa42f591267d505a365f
|
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:a218b995b929ecde4e1eedafd6833f85a2c8d95b4692f30d4d1beec35b02fc11
|
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 sha256:7558f7bb2ee7069b2bb4e640caedc7407b4a716746baae51dcfcb82859b288f9
|
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,
|
@@ -31,13 +31,25 @@
|
|
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":
|
41 |
"trial_name": null,
|
42 |
"trial_params": null
|
43 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.78125,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 150,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
31 |
"learning_rate": 0.000136764169663272,
|
32 |
"loss": 0.5817,
|
33 |
"step": 100
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.65,
|
37 |
+
"learning_rate": 0.00010519038181318999,
|
38 |
+
"loss": 0.5779,
|
39 |
+
"step": 125
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.78,
|
43 |
+
"learning_rate": 7.307467669163655e-05,
|
44 |
+
"loss": 0.5623,
|
45 |
+
"step": 150
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 25,
|
49 |
"max_steps": 250,
|
50 |
"num_train_epochs": 2,
|
51 |
"save_steps": 50,
|
52 |
+
"total_flos": 8345812583546880.0,
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|