RodrigoSalazar-U commited on
Commit
3a5e2f0
1 Parent(s): fc61b72

Training in progress, step 9130, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fa462ee315f6286d0560d178e1576f9f7bc266cda332e3573e24a9be44be436
3
  size 4785762744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c53e1717fbda8e4de559f68e5b2824819aa810742670c06a7138fd1c143d23e
3
  size 4785762744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc3a6d3b8afe0402070b9a53be5a23ab45e598fb6abf993ecb0f8d70a9dec5b9
3
  size 3497859804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3a73fb7ad0bfd5931526628cdb2a2707543009b5fd5eef91f48cc4e751d52db
3
  size 3497859804
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c66a678ee8f615fe14ce6e44cecc141a68321a0815a7952fb61c3673d46702bf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13d8c799022c39630ec2c03b942fa430d1572f502a63d0346e955d3bd9c1188
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 4.928806133625411,
5
  "eval_steps": 500,
6
- "global_step": 9000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -637,6 +637,13 @@
637
  "learning_rate": 6.174623445742155e-08,
638
  "loss": 0.1721,
639
  "step": 9000
 
 
 
 
 
 
 
640
  }
641
  ],
642
  "logging_steps": 100,
@@ -651,12 +658,12 @@
651
  "should_evaluate": false,
652
  "should_log": false,
653
  "should_save": true,
654
- "should_training_stop": false
655
  },
656
  "attributes": {}
657
  }
658
  },
659
- "total_flos": 4.325169651624493e+18,
660
  "train_batch_size": 16,
661
  "trial_name": null,
662
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
  "eval_steps": 500,
6
+ "global_step": 9130,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
637
  "learning_rate": 6.174623445742155e-08,
638
  "loss": 0.1721,
639
  "step": 9000
640
+ },
641
+ {
642
+ "epoch": 4.983570646221248,
643
+ "grad_norm": 0.9348780512809753,
644
+ "learning_rate": 3.2889019651372033e-09,
645
+ "loss": 0.1666,
646
+ "step": 9100
647
  }
648
  ],
649
  "logging_steps": 100,
 
658
  "should_evaluate": false,
659
  "should_log": false,
660
  "should_save": true,
661
+ "should_training_stop": true
662
  },
663
  "attributes": {}
664
  }
665
  },
666
+ "total_flos": 4.3866120063130337e+18,
667
  "train_batch_size": 16,
668
  "trial_name": null,
669
  "trial_params": null