smilemikan
commited on
Commit
•
584397f
1
Parent(s):
ac68d99
Training in progress, step 40500, 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 sha256:89fed205329d3c84f62bffb95cd21a64ad2dbe5edcb2940745415be66a614843
|
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:d92e6b2de508adae1f54c46e2b03a45d02da6ae6966a242418b784a9d9fcab13
|
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 sha256:4cfcadab3674bbd679d420d67a9eb27af8c4be436695b3862644269e271a4671
|
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 sha256:49d5e3958fa5dcda40d0db70c098b34eb7a5d6a77c4cd99eff106648568d4faa
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-
|
4 |
-
"epoch": 8.
|
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,
|
@@ -1127,13 +1127,27 @@
|
|
1127 |
"eval_samples_per_second": 204.743,
|
1128 |
"eval_steps_per_second": 12.811,
|
1129 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1130 |
}
|
1131 |
],
|
1132 |
"logging_steps": 500,
|
1133 |
"max_steps": 60000,
|
1134 |
"num_train_epochs": 14,
|
1135 |
"save_steps": 500,
|
1136 |
-
"total_flos": 4.
|
1137 |
"trial_name": null,
|
1138 |
"trial_params": null
|
1139 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3412760496139526,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-40500",
|
4 |
+
"epoch": 8.922670191672175,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 40500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1127 |
"eval_samples_per_second": 204.743,
|
1128 |
"eval_steps_per_second": 12.811,
|
1129 |
"step": 40000
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 8.92,
|
1133 |
+
"learning_rate": 6.504333333333334e-06,
|
1134 |
+
"loss": 1.1696,
|
1135 |
+
"step": 40500
|
1136 |
+
},
|
1137 |
+
{
|
1138 |
+
"epoch": 8.92,
|
1139 |
+
"eval_loss": 1.3412760496139526,
|
1140 |
+
"eval_runtime": 44.0851,
|
1141 |
+
"eval_samples_per_second": 205.92,
|
1142 |
+
"eval_steps_per_second": 12.884,
|
1143 |
+
"step": 40500
|
1144 |
}
|
1145 |
],
|
1146 |
"logging_steps": 500,
|
1147 |
"max_steps": 60000,
|
1148 |
"num_train_epochs": 14,
|
1149 |
"save_steps": 500,
|
1150 |
+
"total_flos": 4.104753460071629e+16,
|
1151 |
"trial_name": null,
|
1152 |
"trial_params": null
|
1153 |
}
|