smilemikan
commited on
Commit
•
89c2f93
1
Parent(s):
8291a4f
Training in progress, step 38500, 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:c0f4ffc6ea154b0ddcba762e530088eebd72f19343dc4893e6f7fc82bf012db2
|
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 sha256:81ef7154c73b6a2ff32182243747f3aa28d95688b1089c1aec3eb6a8efaf80e4
|
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:eb7d8230b10dd6b50fe2be2667069023c469b1be39eae3b29e5aebde90c707a4
|
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:b9b6d8b6dfd662993e98ba2976dd0778e8d20c9450d9216b3a71acc7ed2ddfce
|
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,
|
@@ -1071,13 +1071,27 @@
|
|
1071 |
"eval_samples_per_second": 205.016,
|
1072 |
"eval_steps_per_second": 12.828,
|
1073 |
"step": 38000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1074 |
}
|
1075 |
],
|
1076 |
"logging_steps": 500,
|
1077 |
"max_steps": 60000,
|
1078 |
"num_train_epochs": 14,
|
1079 |
"save_steps": 500,
|
1080 |
-
"total_flos": 3.
|
1081 |
"trial_name": null,
|
1082 |
"trial_params": null
|
1083 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3513332605361938,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-38500",
|
4 |
+
"epoch": 8.482044503194537,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 38500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1071 |
"eval_samples_per_second": 205.016,
|
1072 |
"eval_steps_per_second": 12.828,
|
1073 |
"step": 38000
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 8.48,
|
1077 |
+
"learning_rate": 7.1710000000000005e-06,
|
1078 |
+
"loss": 1.1666,
|
1079 |
+
"step": 38500
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 8.48,
|
1083 |
+
"eval_loss": 1.3513332605361938,
|
1084 |
+
"eval_runtime": 44.2333,
|
1085 |
+
"eval_samples_per_second": 205.23,
|
1086 |
+
"eval_steps_per_second": 12.841,
|
1087 |
+
"step": 38500
|
1088 |
}
|
1089 |
],
|
1090 |
"logging_steps": 500,
|
1091 |
"max_steps": 60000,
|
1092 |
"num_train_epochs": 14,
|
1093 |
"save_steps": 500,
|
1094 |
+
"total_flos": 3.900591889947034e+16,
|
1095 |
"trial_name": null,
|
1096 |
"trial_params": null
|
1097 |
}
|