aee4 commited on
Commit
afc9879
·
verified ·
1 Parent(s): fe3639e

Training in progress, step 30750, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e34b5b9dbea8c1024fb8352b98d984bc7d951761831c373fb7c19b4991dcf88
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7192f4dfcde6abee19be606c714caca7cddb75199ccaa2b0363f307b966fdff2
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:528b866e0e566decbd85324628d3695260fb21dbe2bb0e7063999d756e1bb123
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84bd613a51db68149e04db02519ba028266e01a7c71e176b8b93899548c2ad57
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02da9206c600f41cfc448f58148735f047e923d8398cf367f2fb1bff4185f160
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6916278eb9941b31b4efb91a08ec4b4a924021286a2e6dbe3a81d736b09428eb
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09e513432c458961b120cc1c5ffaa2a42ce25ac3985908c90806e94e7a15172d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:284ee03e21ae78aa0e6c2d53b84620ac106e85176a3a773e497d88812a8f7304
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": 172.31638418079095,
6
  "eval_steps": 250,
7
- "global_step": 30500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -10012,6 +10012,88 @@
10012
  "eval_samples_per_second": 50.51,
10013
  "eval_steps_per_second": 12.628,
10014
  "step": 30500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10015
  }
10016
  ],
10017
  "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": 173.72881355932202,
6
  "eval_steps": 250,
7
+ "global_step": 30750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
10012
  "eval_samples_per_second": 50.51,
10013
  "eval_steps_per_second": 12.628,
10014
  "step": 30500
10015
+ },
10016
+ {
10017
+ "epoch": 172.45762711864407,
10018
+ "grad_norm": 1.9986635446548462,
10019
+ "learning_rate": 7.62939453125e-09,
10020
+ "loss": 0.2456,
10021
+ "step": 30525
10022
+ },
10023
+ {
10024
+ "epoch": 172.59887005649716,
10025
+ "grad_norm": 1.876315951347351,
10026
+ "learning_rate": 7.62939453125e-09,
10027
+ "loss": 0.2387,
10028
+ "step": 30550
10029
+ },
10030
+ {
10031
+ "epoch": 172.74011299435028,
10032
+ "grad_norm": 1.556243658065796,
10033
+ "learning_rate": 7.62939453125e-09,
10034
+ "loss": 0.264,
10035
+ "step": 30575
10036
+ },
10037
+ {
10038
+ "epoch": 172.88135593220338,
10039
+ "grad_norm": 1.4101954698562622,
10040
+ "learning_rate": 7.62939453125e-09,
10041
+ "loss": 0.291,
10042
+ "step": 30600
10043
+ },
10044
+ {
10045
+ "epoch": 173.0225988700565,
10046
+ "grad_norm": 3.425081253051758,
10047
+ "learning_rate": 7.62939453125e-09,
10048
+ "loss": 0.268,
10049
+ "step": 30625
10050
+ },
10051
+ {
10052
+ "epoch": 173.1638418079096,
10053
+ "grad_norm": 1.403749704360962,
10054
+ "learning_rate": 7.62939453125e-09,
10055
+ "loss": 0.2496,
10056
+ "step": 30650
10057
+ },
10058
+ {
10059
+ "epoch": 173.3050847457627,
10060
+ "grad_norm": 1.4747495651245117,
10061
+ "learning_rate": 7.62939453125e-09,
10062
+ "loss": 0.2574,
10063
+ "step": 30675
10064
+ },
10065
+ {
10066
+ "epoch": 173.4463276836158,
10067
+ "grad_norm": 1.4201232194900513,
10068
+ "learning_rate": 7.62939453125e-09,
10069
+ "loss": 0.2496,
10070
+ "step": 30700
10071
+ },
10072
+ {
10073
+ "epoch": 173.58757062146893,
10074
+ "grad_norm": 1.0772000551223755,
10075
+ "learning_rate": 7.62939453125e-09,
10076
+ "loss": 0.2723,
10077
+ "step": 30725
10078
+ },
10079
+ {
10080
+ "epoch": 173.72881355932202,
10081
+ "grad_norm": 1.1473816633224487,
10082
+ "learning_rate": 7.62939453125e-09,
10083
+ "loss": 0.2515,
10084
+ "step": 30750
10085
+ },
10086
+ {
10087
+ "epoch": 173.72881355932202,
10088
+ "eval_asd": 10.190330600425149,
10089
+ "eval_dice": 0.7923945833521473,
10090
+ "eval_hd95": 31.220900529269024,
10091
+ "eval_jaccard": 0.698293635498097,
10092
+ "eval_loss": 0.3460894525051117,
10093
+ "eval_runtime": 5.1029,
10094
+ "eval_samples_per_second": 50.951,
10095
+ "eval_steps_per_second": 12.738,
10096
+ "step": 30750
10097
  }
10098
  ],
10099
  "logging_steps": 25,