Hugging Face's logo

abaddon182
/
9db6cbba-2a7f-4aa3-98b7-fa898ca8f99a

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
abaddon182 commited on
Commit
b3cbd3b
·
verified ·
1 Parent(s): 77cff8b

Training in progress, step 5000, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +84 -6
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c740c75859f6b4747d6b83e9722f50e8a04f6a21925575500e455579ddd2d923
3
  size 113864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f3f5367722895174de5519e9df05cd73c324ff4623566e7480dae735438794
3
  size 113864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b16f6cf90cf2896c9d90c88194445b042487e06564d58421f27beb60ccccfbe
3
  size 244938
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00633e4f11ec15035f9549533eae551856e1c457d0bc4602cc8c4d1dd717fe24
3
  size 244938
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15ef5cec074d369e04dae576296b3c1caf5a7c1b88c4cd48b2a1b362fed32a7a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e7bb60563f4c2e925e31010d85157242034556d96dfa52e12c735cdbb2376f9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f6d93467eee9f7eb66e857b295a064a9a7b557fc916f9b5131020a127e4f67a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016e25fda59c3776a60450c0d95b5f609ee100d53eaff927c1f903b335520ed3
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.26805305480957,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-4500",
4
- "epoch": 1.511461919556638,
5
  "eval_steps": 500,
6
- "global_step": 4500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -717,6 +717,84 @@
717
  "eval_samples_per_second": 278.393,
718
  "eval_steps_per_second": 139.197,
719
  "step": 4500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
720
  }
721
  ],
722
  "logging_steps": 50,
@@ -740,12 +818,12 @@
740
  "should_evaluate": false,
741
  "should_log": false,
742
  "should_save": true,
743
- "should_training_stop": false
744
  },
745
  "attributes": {}
746
  }
747
  },
748
- "total_flos": 122952082489344.0,
749
  "train_batch_size": 2,
750
  "trial_name": null,
751
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.267985343933105,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-5000",
4
+ "epoch": 1.6794021328407087,
5
  "eval_steps": 500,
6
+ "global_step": 5000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
717
  "eval_samples_per_second": 278.393,
718
  "eval_steps_per_second": 139.197,
719
  "step": 4500
720
+ },
721
+ {
722
+ "epoch": 1.528255940885045,
723
+ "grad_norm": 0.6842604279518127,
724
+ "learning_rate": 4.050702638550275e-06,
725
+ "loss": 41.082,
726
+ "step": 4550
727
+ },
728
+ {
729
+ "epoch": 1.5450499622134521,
730
+ "grad_norm": 0.6457563042640686,
731
+ "learning_rate": 3.2051298603643753e-06,
732
+ "loss": 41.0935,
733
+ "step": 4600
734
+ },
735
+ {
736
+ "epoch": 1.5618439835418592,
737
+ "grad_norm": 0.6898395419120789,
738
+ "learning_rate": 2.4570213114592954e-06,
739
+ "loss": 41.0955,
740
+ "step": 4650
741
+ },
742
+ {
743
+ "epoch": 1.5786380048702662,
744
+ "grad_norm": 0.7416620254516602,
745
+ "learning_rate": 1.8071302737293295e-06,
746
+ "loss": 41.0833,
747
+ "step": 4700
748
+ },
749
+ {
750
+ "epoch": 1.5954320261986732,
751
+ "grad_norm": 0.7633203864097595,
752
+ "learning_rate": 1.2561111323605712e-06,
753
+ "loss": 41.0889,
754
+ "step": 4750
755
+ },
756
+ {
757
+ "epoch": 1.6122260475270802,
758
+ "grad_norm": 0.6480950117111206,
759
+ "learning_rate": 8.04518716920466e-07,
760
+ "loss": 41.089,
761
+ "step": 4800
762
+ },
763
+ {
764
+ "epoch": 1.6290200688554874,
765
+ "grad_norm": 0.6868506669998169,
766
+ "learning_rate": 4.5280774269154115e-07,
767
+ "loss": 41.0865,
768
+ "step": 4850
769
+ },
770
+ {
771
+ "epoch": 1.6458140901838947,
772
+ "grad_norm": 1.0123971700668335,
773
+ "learning_rate": 2.0133235281156736e-07,
774
+ "loss": 41.082,
775
+ "step": 4900
776
+ },
777
+ {
778
+ "epoch": 1.6626081115123017,
779
+ "grad_norm": 0.7502777576446533,
780
+ "learning_rate": 5.0345761681491746e-08,
781
+ "loss": 41.0922,
782
+ "step": 4950
783
+ },
784
+ {
785
+ "epoch": 1.6794021328407087,
786
+ "grad_norm": 0.5540114045143127,
787
+ "learning_rate": 0.0,
788
+ "loss": 41.0899,
789
+ "step": 5000
790
+ },
791
+ {
792
+ "epoch": 1.6794021328407087,
793
+ "eval_loss": 10.267985343933105,
794
+ "eval_runtime": 4.5648,
795
+ "eval_samples_per_second": 274.712,
796
+ "eval_steps_per_second": 137.356,
797
+ "step": 5000
798
  }
799
  ],
800
  "logging_steps": 50,
 
818
  "should_evaluate": false,
819
  "should_log": false,
820
  "should_save": true,
821
+ "should_training_stop": true
822
  },
823
  "attributes": {}
824
  }
825
  },
826
+ "total_flos": 136653775405056.0,
827
  "train_batch_size": 2,
828
  "trial_name": null,
829
  "trial_params": null