Commit
•
42bfd6c
1
Parent(s):
c8aef10
Training in progress, step 40, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12803224
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7598e4d11a7e88a2cd048c7d81b03a00065ebccc133982b8a62f1502da78a828
|
3 |
size 12803224
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6472698
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a4f962e98152e4483562134f22c0dc802b8248172bece5a8ff75520d4f6a44c
|
3 |
size 6472698
|
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 sha256:67110d532e979886893031bdb5eeb12ac85e80c1a0b21dee3750c4d2c6feb8c2
|
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 sha256:49529a8a08195bb413b67911c12112ee8fc35503e6add1381465d2e9e7251e57
|
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,
|
@@ -14,6 +14,13 @@
|
|
14 |
"learning_rate": 1.6666666666666667e-06,
|
15 |
"loss": 3.6651,
|
16 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 20,
|
@@ -21,7 +28,7 @@
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 1,
|
23 |
"save_steps": 20,
|
24 |
-
"total_flos":
|
25 |
"train_batch_size": 1,
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0001245204018895971,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 40,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
14 |
"learning_rate": 1.6666666666666667e-06,
|
15 |
"loss": 3.6651,
|
16 |
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 90.37364196777344,
|
21 |
+
"learning_rate": 3.3333333333333333e-06,
|
22 |
+
"loss": 3.7271,
|
23 |
+
"step": 40
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 20,
|
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 1,
|
30 |
"save_steps": 20,
|
31 |
+
"total_flos": 82442575564800.0,
|
32 |
"train_batch_size": 1,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|