alchemist69 commited on
Commit
7f3c6fe
·
verified ·
1 Parent(s): a225ffc

Training in progress, step 107, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:742006f063ae3f0db4034eeb128b5709f56542b777656689ea0095277f539cee
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98e8ae6cfc2a017af971afc256ae817b80fefcca12c61c1dd6c680563782ef49
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d838747525a2a6f796b0676cf80131cce03dda9099a8305a2a4d0cf195925552
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eebf510cd0bd3fef633709d8b33163f265c1927a76cc985285e05c146481470f
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2405249b39507e472d56d20ef06b28870d1a10c50946071a17796ad476646778
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1098446957996748852e29c22a5ff4ec680d645333bb122801fb8220c1fbb281
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c42990581f4daa6339fc514609234771842dec67696eb959d0af5d1c324532b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9115d19f29cad07fed0dd5f8f69efe017189f597938ab6d300b5e3ea914190e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.22548285126686096,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.9345794392523364,
5
  "eval_steps": 100,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -723,6 +723,55 @@
723
  "eval_samples_per_second": 11.96,
724
  "eval_steps_per_second": 3.039,
725
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
726
  }
727
  ],
728
  "logging_steps": 1,
@@ -746,12 +795,12 @@
746
  "should_evaluate": false,
747
  "should_log": false,
748
  "should_save": true,
749
- "should_training_stop": false
750
  },
751
  "attributes": {}
752
  }
753
  },
754
- "total_flos": 1.6405085168861184e+17,
755
  "train_batch_size": 8,
756
  "trial_name": null,
757
  "trial_params": null
 
1
  {
2
  "best_metric": 0.22548285126686096,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.0,
5
  "eval_steps": 100,
6
+ "global_step": 107,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
723
  "eval_samples_per_second": 11.96,
724
  "eval_steps_per_second": 3.039,
725
  "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.9439252336448598,
729
+ "grad_norm": 0.7059941291809082,
730
+ "learning_rate": 1.1689722144956671e-06,
731
+ "loss": 0.2496,
732
+ "step": 101
733
+ },
734
+ {
735
+ "epoch": 0.9532710280373832,
736
+ "grad_norm": 0.6286365985870361,
737
+ "learning_rate": 8.127578033998662e-07,
738
+ "loss": 0.1745,
739
+ "step": 102
740
+ },
741
+ {
742
+ "epoch": 0.9626168224299065,
743
+ "grad_norm": 0.7547852993011475,
744
+ "learning_rate": 5.206741722181386e-07,
745
+ "loss": 0.2797,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 0.9719626168224299,
750
+ "grad_norm": 0.7173730134963989,
751
+ "learning_rate": 2.9310214228202013e-07,
752
+ "loss": 0.258,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 0.9813084112149533,
757
+ "grad_norm": 0.5055248737335205,
758
+ "learning_rate": 1.3033842410251075e-07,
759
+ "loss": 0.2182,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 0.9906542056074766,
764
+ "grad_norm": 0.6892708539962769,
765
+ "learning_rate": 3.259523051615254e-08,
766
+ "loss": 0.312,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 1.0,
771
+ "grad_norm": 0.596139669418335,
772
+ "learning_rate": 0.0,
773
+ "loss": 0.2149,
774
+ "step": 107
775
  }
776
  ],
777
  "logging_steps": 1,
 
795
  "should_evaluate": false,
796
  "should_log": false,
797
  "should_save": true,
798
+ "should_training_stop": true
799
  },
800
  "attributes": {}
801
  }
802
  },
803
+ "total_flos": 1.7536470352920576e+17,
804
  "train_batch_size": 8,
805
  "trial_name": null,
806
  "trial_params": null