Femboyuwu2000
commited on
Commit
•
2051b35
1
Parent(s):
9208ac0
Training in progress, step 180, 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 4725640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c866b681847079f3b9029f07492db9880da802a14740ef308276cbc48af7029
|
3 |
size 4725640
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2423738
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48b0feae9377bfd2ee4adc15c04b256d703f0f8cfe89d645ffa2f876e8acdd71
|
3 |
size 2423738
|
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 sha256:5818eed0ee5844cae7078ebbf0cd36b392212601ec7951f21f30f58ec6711de0
|
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 sha256:10bc8edf4e1fadab9976453bf48d4affbe0fded7ba378b722041dd8223dc111e
|
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,
|
@@ -63,6 +63,13 @@
|
|
63 |
"learning_rate": 2.6500000000000004e-05,
|
64 |
"loss": 3.16,
|
65 |
"step": 160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
}
|
67 |
],
|
68 |
"logging_steps": 20,
|
@@ -70,7 +77,7 @@
|
|
70 |
"num_input_tokens_seen": 0,
|
71 |
"num_train_epochs": 1,
|
72 |
"save_steps": 20,
|
73 |
-
"total_flos":
|
74 |
"train_batch_size": 1,
|
75 |
"trial_name": null,
|
76 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00014008545212579673,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 180,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
63 |
"learning_rate": 2.6500000000000004e-05,
|
64 |
"loss": 3.16,
|
65 |
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.0,
|
69 |
+
"grad_norm": 5.391817092895508,
|
70 |
+
"learning_rate": 2.9833333333333335e-05,
|
71 |
+
"loss": 3.2489,
|
72 |
+
"step": 180
|
73 |
}
|
74 |
],
|
75 |
"logging_steps": 20,
|
|
|
77 |
"num_input_tokens_seen": 0,
|
78 |
"num_train_epochs": 1,
|
79 |
"save_steps": 20,
|
80 |
+
"total_flos": 901465913585664.0,
|
81 |
"train_batch_size": 1,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|