ramdhanfirdaus commited on
Commit
2584f19
1 Parent(s): 8f88538

Training in progress, step 3600, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:766823c3351c436a73f412e2d52b8493d7080a8306cdf3fd6d37c248da77694a
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d68bbb11be68bac250fdb245929bc5c33eb92572532a1c32e8786929240c64d
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b91c4e67a8aa750e8008400aa454f6ceb88e26b5e996d2c8b5f67663947fb71d
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9aade19b93275ace19302d959a9374b28d9a3d7a83c64fc202a6ecfd3051f30
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55cc1817d8def71a3bc8f24bf4582f8ab4532c2542185ddc75da7e42fa5e372c
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef0cbe118e41f50f73b72dc69901b2174467b76d419ab6a1e3302e9eaafde12a
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2808809280395508,
3
- "best_model_checkpoint": "./outputs/checkpoint-3500",
4
- "epoch": 2.5500910746812386,
5
  "eval_steps": 100,
6
- "global_step": 3500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -497,13 +497,27 @@
497
  "eval_samples_per_second": 43.572,
498
  "eval_steps_per_second": 5.452,
499
  "step": 3500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500
  }
501
  ],
502
  "logging_steps": 100,
503
  "max_steps": 4116,
504
  "num_train_epochs": 3,
505
  "save_steps": 100,
506
- "total_flos": 2.0862010999423795e+17,
507
  "trial_name": null,
508
  "trial_params": null
509
  }
 
1
  {
2
+ "best_metric": 1.2679202556610107,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3600",
4
+ "epoch": 2.6229508196721314,
5
  "eval_steps": 100,
6
+ "global_step": 3600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
497
  "eval_samples_per_second": 43.572,
498
  "eval_steps_per_second": 5.452,
499
  "step": 3500
500
+ },
501
+ {
502
+ "epoch": 2.62,
503
+ "learning_rate": 0.0002,
504
+ "loss": 1.2515,
505
+ "step": 3600
506
+ },
507
+ {
508
+ "epoch": 2.62,
509
+ "eval_loss": 1.2679202556610107,
510
+ "eval_runtime": 144.0312,
511
+ "eval_samples_per_second": 43.56,
512
+ "eval_steps_per_second": 5.45,
513
+ "step": 3600
514
  }
515
  ],
516
  "logging_steps": 100,
517
  "max_steps": 4116,
518
  "num_train_epochs": 3,
519
  "save_steps": 100,
520
+ "total_flos": 2.145691983734784e+17,
521
  "trial_name": null,
522
  "trial_params": null
523
  }