smilemikan
commited on
Commit
•
671bf26
1
Parent(s):
0c009fe
Training in progress, step 34000, 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 sha256:5bf55d85579e0c6adc9f718769e4e0d16e8328e567279ffb0312f16494411c8e
|
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 sha256:8ab412cdfe08088109865540ebd943a5f177c089f9a05f6049ff475b9720dc40
|
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 sha256:5a0f0d972ef121f37b5d199d8aabf39ae53f41a74d952168da0c1d9d2c0016b1
|
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 sha256:88d8e8fe42a71664e0b4cbf86b623c02d909672d8ee1d83cf6a3f9e70f00918f
|
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": 7.
|
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,
|
@@ -945,13 +945,27 @@
|
|
945 |
"eval_samples_per_second": 203.462,
|
946 |
"eval_steps_per_second": 12.73,
|
947 |
"step": 33500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
948 |
}
|
949 |
],
|
950 |
"logging_steps": 500,
|
951 |
"max_steps": 60000,
|
952 |
"num_train_epochs": 14,
|
953 |
"save_steps": 500,
|
954 |
-
"total_flos": 3.
|
955 |
"trial_name": null,
|
956 |
"trial_params": null
|
957 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.370631217956543,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-34000",
|
4 |
+
"epoch": 7.49063670411985,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 34000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
945 |
"eval_samples_per_second": 203.462,
|
946 |
"eval_steps_per_second": 12.73,
|
947 |
"step": 33500
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 7.49,
|
951 |
+
"learning_rate": 8.67e-06,
|
952 |
+
"loss": 1.2131,
|
953 |
+
"step": 34000
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 7.49,
|
957 |
+
"eval_loss": 1.370631217956543,
|
958 |
+
"eval_runtime": 45.0076,
|
959 |
+
"eval_samples_per_second": 201.699,
|
960 |
+
"eval_steps_per_second": 12.62,
|
961 |
+
"step": 34000
|
962 |
}
|
963 |
],
|
964 |
"logging_steps": 500,
|
965 |
"max_steps": 60000,
|
966 |
"num_train_epochs": 14,
|
967 |
"save_steps": 500,
|
968 |
+
"total_flos": 3.4476026921877504e+16,
|
969 |
"trial_name": null,
|
970 |
"trial_params": null
|
971 |
}
|