aee4 commited on
Commit
d58eaa6
·
verified ·
1 Parent(s): 6eecda5

Training in progress, step 29250, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cba105a991310824863a02c859bf0f6c43c9900432452a1880b1f2a5df4cf7f
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d542fe08132322cdd14ed246ad0294848c8fd0fef0b253ad614d3a974def85b
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3043e28073acc6653129beb7a2747c02a4be7fac4c0be6cc39c006bab6ec7af
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1ca3c132a93ec7f2515c4919b91a02d270db9f158da3b6b3f7ea68bbe805e5
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6566cfc6ffb2d4f489ca5e3b763009366a4a2a0b093dd01514fc2d531cbb3e0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f4803ce4d7794fd6f5758c3ecf4eb92e8b9729cd80f88f887910c38c7851b2
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71c815fd12f57f1d9b333b50556ec7142747cfb81779db9ed759d6ec3ef571f8
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be00a474d392870a734f7cefc8bcd18b1932f95d5f0244149166a1bcd99f9b62
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
- "epoch": 163.8418079096045,
6
  "eval_steps": 250,
7
- "global_step": 29000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -9520,6 +9520,88 @@
9520
  "eval_samples_per_second": 50.625,
9521
  "eval_steps_per_second": 12.656,
9522
  "step": 29000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9523
  }
9524
  ],
9525
  "logging_steps": 25,
 
2
  "best_global_step": 18500,
3
  "best_metric": 0.7932397701166506,
4
  "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-18500",
5
+ "epoch": 165.25423728813558,
6
  "eval_steps": 250,
7
+ "global_step": 29250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
9520
  "eval_samples_per_second": 50.625,
9521
  "eval_steps_per_second": 12.656,
9522
  "step": 29000
9523
+ },
9524
+ {
9525
+ "epoch": 163.98305084745763,
9526
+ "grad_norm": 1.026631236076355,
9527
+ "learning_rate": 1.52587890625e-08,
9528
+ "loss": 0.2792,
9529
+ "step": 29025
9530
+ },
9531
+ {
9532
+ "epoch": 164.12429378531073,
9533
+ "grad_norm": 1.2609233856201172,
9534
+ "learning_rate": 1.52587890625e-08,
9535
+ "loss": 0.2511,
9536
+ "step": 29050
9537
+ },
9538
+ {
9539
+ "epoch": 164.26553672316385,
9540
+ "grad_norm": 2.4460608959198,
9541
+ "learning_rate": 1.52587890625e-08,
9542
+ "loss": 0.2507,
9543
+ "step": 29075
9544
+ },
9545
+ {
9546
+ "epoch": 164.40677966101694,
9547
+ "grad_norm": 1.5734107494354248,
9548
+ "learning_rate": 1.52587890625e-08,
9549
+ "loss": 0.2642,
9550
+ "step": 29100
9551
+ },
9552
+ {
9553
+ "epoch": 164.54802259887006,
9554
+ "grad_norm": 1.9186979532241821,
9555
+ "learning_rate": 1.52587890625e-08,
9556
+ "loss": 0.2796,
9557
+ "step": 29125
9558
+ },
9559
+ {
9560
+ "epoch": 164.68926553672316,
9561
+ "grad_norm": 1.6311227083206177,
9562
+ "learning_rate": 1.52587890625e-08,
9563
+ "loss": 0.2504,
9564
+ "step": 29150
9565
+ },
9566
+ {
9567
+ "epoch": 164.83050847457628,
9568
+ "grad_norm": 3.5711512565612793,
9569
+ "learning_rate": 1.52587890625e-08,
9570
+ "loss": 0.2459,
9571
+ "step": 29175
9572
+ },
9573
+ {
9574
+ "epoch": 164.97175141242937,
9575
+ "grad_norm": 1.4528518915176392,
9576
+ "learning_rate": 1.52587890625e-08,
9577
+ "loss": 0.2735,
9578
+ "step": 29200
9579
+ },
9580
+ {
9581
+ "epoch": 165.1129943502825,
9582
+ "grad_norm": 1.5894378423690796,
9583
+ "learning_rate": 1.52587890625e-08,
9584
+ "loss": 0.2817,
9585
+ "step": 29225
9586
+ },
9587
+ {
9588
+ "epoch": 165.25423728813558,
9589
+ "grad_norm": 1.087472915649414,
9590
+ "learning_rate": 1.52587890625e-08,
9591
+ "loss": 0.2493,
9592
+ "step": 29250
9593
+ },
9594
+ {
9595
+ "epoch": 165.25423728813558,
9596
+ "eval_asd": 10.165549994958011,
9597
+ "eval_dice": 0.7908312206547277,
9598
+ "eval_hd95": 31.04794740894216,
9599
+ "eval_jaccard": 0.696562841227205,
9600
+ "eval_loss": 0.3476303815841675,
9601
+ "eval_runtime": 5.1529,
9602
+ "eval_samples_per_second": 50.457,
9603
+ "eval_steps_per_second": 12.614,
9604
+ "step": 29250
9605
  }
9606
  ],
9607
  "logging_steps": 25,