ygaci commited on
Commit
56c150a
·
verified ·
1 Parent(s): 44f5a94

Training in progress, step 10000, 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:f05cdda58d7895e22ade49db4926d4f06eab08cef3e73f89fae90f91d5419c6b
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59bd411e79042118c02e15b3e73a6a1cb50b0914583a977d568fce9ce3dbce59
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:365c9ac214b7e7ceceaa2701492a26dba108ff8a38fa28cb6913b887c41aec8e
3
  size 170920532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407ecc084feacd63d77c727ceb9d30e97e48fb103a256b1a91ec7045a34f247e
3
  size 170920532
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7338c1e89775f36a57790992c5173212172ebdc3bd52e8141df50018376ad945
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c207a54abb3cdadafbdbdacd769a0e065ea16bec9650266598b5913d48317f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32b91a34ac9d6cd2d7e5c6854463a263c0baf66161ffcb9a41ac4a208f5f4bee
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d7a943450e8e28bacaf54eada64053d937d2a527ef484bc1cc4dd9d2e24ec15
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": 9.9,
5
  "eval_steps": 100,
6
- "global_step": 9900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1492,6 +1492,21 @@
1492
  "eval_samples_per_second": 0.32,
1493
  "eval_steps_per_second": 0.32,
1494
  "step": 9900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1495
  }
1496
  ],
1497
  "logging_steps": 100,
@@ -1506,12 +1521,12 @@
1506
  "should_evaluate": false,
1507
  "should_log": false,
1508
  "should_save": true,
1509
- "should_training_stop": false
1510
  },
1511
  "attributes": {}
1512
  }
1513
  },
1514
- "total_flos": 1.5589000089054413e+18,
1515
  "train_batch_size": 1,
1516
  "trial_name": null,
1517
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
  "eval_steps": 100,
6
+ "global_step": 10000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1492
  "eval_samples_per_second": 0.32,
1493
  "eval_steps_per_second": 0.32,
1494
  "step": 9900
1495
+ },
1496
+ {
1497
+ "epoch": 10.0,
1498
+ "grad_norm": 0.14566577970981598,
1499
+ "learning_rate": 1.5151515151515152e-07,
1500
+ "loss": 0.0029,
1501
+ "step": 10000
1502
+ },
1503
+ {
1504
+ "epoch": 10.0,
1505
+ "eval_loss": 0.3273286819458008,
1506
+ "eval_runtime": 442.9181,
1507
+ "eval_samples_per_second": 0.321,
1508
+ "eval_steps_per_second": 0.321,
1509
+ "step": 10000
1510
  }
1511
  ],
1512
  "logging_steps": 100,
 
1521
  "should_evaluate": false,
1522
  "should_log": false,
1523
  "should_save": true,
1524
+ "should_training_stop": true
1525
  },
1526
  "attributes": {}
1527
  }
1528
  },
1529
+ "total_flos": 1.574590401440809e+18,
1530
  "train_batch_size": 1,
1531
  "trial_name": null,
1532
  "trial_params": null