smilemikan
commited on
Commit
•
59ecffc
1
Parent(s):
28dc468
Training in progress, step 39000, 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 sha256:1e240fab3967ca62dc987c930b6550cb39d47b312cf22af0933bd87b8aff7e8c
|
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:ab44b893f3e3ff1434782527e2622786ff991741e2828905fc58638d6a05c22a
|
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:b0c5eabea6aa9d5e39ca50a539405b4807a700b5bcd6c05d428827aab0e8f96c
|
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 sha256:9a7093036915a5c86df49c2a38b1350f79c2bed46816abbe49782d3acbba92b9
|
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,
|
@@ -1085,13 +1085,27 @@
|
|
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.
|
1095 |
"trial_name": null,
|
1096 |
"trial_params": null
|
1097 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3496123552322388,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-39000",
|
4 |
+
"epoch": 8.592200925313946,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 39000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1085 |
"eval_samples_per_second": 205.23,
|
1086 |
"eval_steps_per_second": 12.841,
|
1087 |
"step": 38500
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 8.59,
|
1091 |
+
"learning_rate": 7.004333333333334e-06,
|
1092 |
+
"loss": 1.1827,
|
1093 |
+
"step": 39000
|
1094 |
+
},
|
1095 |
+
{
|
1096 |
+
"epoch": 8.59,
|
1097 |
+
"eval_loss": 1.3496123552322388,
|
1098 |
+
"eval_runtime": 44.8817,
|
1099 |
+
"eval_samples_per_second": 202.265,
|
1100 |
+
"eval_steps_per_second": 12.655,
|
1101 |
+
"step": 39000
|
1102 |
}
|
1103 |
],
|
1104 |
"logging_steps": 500,
|
1105 |
"max_steps": 60000,
|
1106 |
"num_train_epochs": 14,
|
1107 |
"save_steps": 500,
|
1108 |
+
"total_flos": 3.951085427176243e+16,
|
1109 |
"trial_name": null,
|
1110 |
"trial_params": null
|
1111 |
}
|