smilemikan
commited on
Commit
•
4ddf835
1
Parent(s):
f2d5b3f
Training in progress, step 39500, 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 sha256:549ed9c913a34c98d736c418920b93aee75ea5f338f8a72583152dffe9394f92
|
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 sha256:27ff65060cdc15a19f53dbdc9d93d815f11b1fcfc429e330347d40a1a3048044
|
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 sha256:7d3f524deadc79201158d2a1b6e198e466fb4975698a11b51acf1fa7cfaec074
|
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:dd3582066fafbc8f34b4818574951b7cb4867e414999f0ebd504c560b18f73e7
|
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,
|
@@ -1099,13 +1099,27 @@
|
|
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":
|
1109 |
"trial_name": null,
|
1110 |
"trial_params": null
|
1111 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3474962711334229,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-39500",
|
4 |
+
"epoch": 8.702357347433356,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 39500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1099 |
"eval_samples_per_second": 202.265,
|
1100 |
"eval_steps_per_second": 12.655,
|
1101 |
"step": 39000
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 8.7,
|
1105 |
+
"learning_rate": 6.837666666666667e-06,
|
1106 |
+
"loss": 1.1643,
|
1107 |
+
"step": 39500
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 8.7,
|
1111 |
+
"eval_loss": 1.3474962711334229,
|
1112 |
+
"eval_runtime": 44.7028,
|
1113 |
+
"eval_samples_per_second": 203.074,
|
1114 |
+
"eval_steps_per_second": 12.706,
|
1115 |
+
"step": 39500
|
1116 |
}
|
1117 |
],
|
1118 |
"logging_steps": 500,
|
1119 |
"max_steps": 60000,
|
1120 |
"num_train_epochs": 14,
|
1121 |
"save_steps": 500,
|
1122 |
+
"total_flos": 4.002692991614976e+16,
|
1123 |
"trial_name": null,
|
1124 |
"trial_params": null
|
1125 |
}
|