smilemikan
commited on
Commit
•
c608d35
1
Parent(s):
ddccd20
Training in progress, step 3500, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5125261
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc2fa15a5e9fc5174a2f2db460995507bf10f8bbf53cd1a2df5dc209c5ea3b39
|
3 |
size 5125261
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2460465086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b5ac68c94586e230c3959acb54f6801fdcc53cbf82147c8780a12f19b5068e1
|
3 |
size 2460465086
|
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:a287a7b84031c05a48ea7c5333d8eebf366f57167dc20774be9b71117c6df912
|
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:cc99e244e20972590fe93655e8af347e514b6b879b75566c51444528a67c5dee
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-
|
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,
|
@@ -91,13 +91,27 @@
|
|
91 |
"eval_samples_per_second": 212.092,
|
92 |
"eval_steps_per_second": 13.27,
|
93 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
}
|
95 |
],
|
96 |
"logging_steps": 500,
|
97 |
"max_steps": 60000,
|
98 |
"num_train_epochs": 14,
|
99 |
"save_steps": 500,
|
100 |
-
"total_flos":
|
101 |
"trial_name": null,
|
102 |
"trial_params": null
|
103 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.30385422706604,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-3500",
|
4 |
+
"epoch": 0.771094954835867,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
91 |
"eval_samples_per_second": 212.092,
|
92 |
"eval_steps_per_second": 13.27,
|
93 |
"step": 3000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.77,
|
97 |
+
"learning_rate": 1.883366666666667e-05,
|
98 |
+
"loss": 2.5068,
|
99 |
+
"step": 3500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.77,
|
103 |
+
"eval_loss": 2.30385422706604,
|
104 |
+
"eval_runtime": 44.6981,
|
105 |
+
"eval_samples_per_second": 203.096,
|
106 |
+
"eval_steps_per_second": 12.707,
|
107 |
+
"step": 3500
|
108 |
}
|
109 |
],
|
110 |
"logging_steps": 500,
|
111 |
"max_steps": 60000,
|
112 |
"num_train_epochs": 14,
|
113 |
"save_steps": 500,
|
114 |
+
"total_flos": 3540439421681664.0,
|
115 |
"trial_name": null,
|
116 |
"trial_params": null
|
117 |
}
|