smilemikan commited on
Commit
0470196
1 Parent(s): c869313

Training in progress, step 37000, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e283bac3045331af2f920163391dc8270c8abff22512ef1f29e31862dd04a9a
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f274b0fb2acfcf842970c363fa75ef29eda93c5c3dc8f5e0d50047b852273a0
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:483348c116ccaa7174bd8084c6da2b6cc18ed069290d5dd0d0544d9cf2fd71fb
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59980f0f7c9f83d2609a2b755908b14622de2a97f1745e01c9d940f73dad22a8
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05f5bce689ca8154dc4a1c1b9f0723925cb97784a667d3c397ef5145b037402d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7382e261c2a2c60bbcfed65568fbd4dde011f09f0c636712a18bbb2ab69d90bb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a00c29dc4dd3aeb804a939b7c86e93b9e46353a7563608b7d4c84d97515cc47e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34cc7b5d6bcd766ecfa456a2d1cfee6d35d6e095ebeaec3b1a29bbbb93c53839
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.357163429260254,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-36000",
4
- "epoch": 8.041418814716899,
5
  "eval_steps": 500,
6
- "global_step": 36500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1029,13 +1029,27 @@
1029
  "eval_samples_per_second": 203.948,
1030
  "eval_steps_per_second": 12.761,
1031
  "step": 36500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1032
  }
1033
  ],
1034
  "logging_steps": 500,
1035
  "max_steps": 60000,
1036
  "num_train_epochs": 14,
1037
  "save_steps": 500,
1038
- "total_flos": 3.700439463336346e+16,
1039
  "trial_name": null,
1040
  "trial_params": null
1041
  }
 
1
  {
2
+ "best_metric": 1.356821060180664,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-37000",
4
+ "epoch": 8.151575236836308,
5
  "eval_steps": 500,
6
+ "global_step": 37000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1029
  "eval_samples_per_second": 203.948,
1030
  "eval_steps_per_second": 12.761,
1031
  "step": 36500
1032
+ },
1033
+ {
1034
+ "epoch": 8.15,
1035
+ "learning_rate": 7.671e-06,
1036
+ "loss": 1.1658,
1037
+ "step": 37000
1038
+ },
1039
+ {
1040
+ "epoch": 8.15,
1041
+ "eval_loss": 1.356821060180664,
1042
+ "eval_runtime": 44.6544,
1043
+ "eval_samples_per_second": 203.295,
1044
+ "eval_steps_per_second": 12.72,
1045
+ "step": 37000
1046
  }
1047
  ],
1048
  "logging_steps": 500,
1049
  "max_steps": 60000,
1050
  "num_train_epochs": 14,
1051
  "save_steps": 500,
1052
+ "total_flos": 3.749297513811149e+16,
1053
  "trial_name": null,
1054
  "trial_params": null
1055
  }