Training in progress, step 800, 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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f41c3c9c664578de1870237e06cc1d44b7b8529bf810fd380b70e2f8e1caed7f
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 126034975
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e89112a01c80787e05219e51a76c9032bd2394b61ba052faad3bef6696411d28
|
3 |
size 126034975
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1f37e54feeb0570678343f9820754e267bf2abaa1042eef0b3bd028fec3ca92
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
|
3 |
size 627
|
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": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -46,13 +46,26 @@
|
|
46 |
"eval_samples_per_second": 4.264,
|
47 |
"eval_steps_per_second": 0.171,
|
48 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 200,
|
52 |
"max_steps": 960,
|
53 |
"num_train_epochs": 16,
|
54 |
"save_steps": 200,
|
55 |
-
"total_flos":
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.333333333333334,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
46 |
"eval_samples_per_second": 4.264,
|
47 |
"eval_steps_per_second": 0.171,
|
48 |
"step": 600
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 13.33,
|
52 |
+
"learning_rate": 0.0002,
|
53 |
+
"loss": 0.0203,
|
54 |
+
"step": 800
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 13.33,
|
58 |
+
"eval_runtime": 23.4455,
|
59 |
+
"eval_samples_per_second": 4.265,
|
60 |
+
"eval_steps_per_second": 0.171,
|
61 |
+
"step": 800
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 200,
|
65 |
"max_steps": 960,
|
66 |
"num_train_epochs": 16,
|
67 |
"save_steps": 200,
|
68 |
+
"total_flos": 5.11494779830272e+17,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
71 |
}
|