Training in progress, step 50, 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 3558888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f771ec08b58b5db2df1e35e840beea613fd221403cda69960cf10980b637f430
|
3 |
size 3558888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7198906
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ba8e1b2a096f1141bc55a687262f697707eec5e5ef262b6683ba51ab8056edb
|
3 |
size 7198906
|
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 sha256:04fca484010f00fef17865c6b5cf7f6664a5d9146ff300b3753875bfa60c7f76
|
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:a4ad95690c27927b8374216bcc4afe0bd6bd85edbbc60e77edab073d52865c2e
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -79,13 +79,21 @@
|
|
79 |
"eval_samples_per_second": 19.133,
|
80 |
"eval_steps_per_second": 2.392,
|
81 |
"step": 45
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
82 |
}
|
83 |
],
|
84 |
"logging_steps": 500,
|
85 |
"max_steps": 237,
|
86 |
"num_train_epochs": 1,
|
87 |
"save_steps": 5,
|
88 |
-
"total_flos":
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|
91 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2109704641350211,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
79 |
"eval_samples_per_second": 19.133,
|
80 |
"eval_steps_per_second": 2.392,
|
81 |
"step": 45
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.21,
|
85 |
+
"eval_loss": 15.608057975769043,
|
86 |
+
"eval_runtime": 121.069,
|
87 |
+
"eval_samples_per_second": 19.163,
|
88 |
+
"eval_steps_per_second": 2.395,
|
89 |
+
"step": 50
|
90 |
}
|
91 |
],
|
92 |
"logging_steps": 500,
|
93 |
"max_steps": 237,
|
94 |
"num_train_epochs": 1,
|
95 |
"save_steps": 5,
|
96 |
+
"total_flos": 206242578432000.0,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
99 |
}
|