Training in progress, step 200, 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:faaee7b7cb7039fc457c7d55f4d1ebbfadadf0d819d7fd3957ebecd121016b9a
|
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:f2a79751c2b18d1f0fc924267c36532beda700ad16228728135817391208d5cf
|
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:d100e43eb84b4555796b9487301e394d9155595558ef980d5477e8ed4623a3b2
|
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 sha256:432f82e26eb9f58183a7c3367fa553cd233b33d39719613c327721b78f5e81a6
|
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":
|
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,
|
@@ -43,13 +43,25 @@
|
|
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":
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0416666666666667,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
43 |
"learning_rate": 7.307467669163655e-05,
|
44 |
"loss": 0.5623,
|
45 |
"step": 150
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.91,
|
49 |
+
"learning_rate": 4.377019014049223e-05,
|
50 |
+
"loss": 0.5581,
|
51 |
+
"step": 175
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.04,
|
55 |
+
"learning_rate": 2.03365443542764e-05,
|
56 |
+
"loss": 0.5384,
|
57 |
+
"step": 200
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 25,
|
61 |
"max_steps": 250,
|
62 |
"num_train_epochs": 2,
|
63 |
"save_steps": 50,
|
64 |
+
"total_flos": 1.1067023275008e+16,
|
65 |
"trial_name": null,
|
66 |
"trial_params": null
|
67 |
}
|