aee4 commited on
Commit
14a1097
·
verified ·
1 Parent(s): ae9153f

Training in progress, step 27500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2979ef3cf00c936313a7a929cd81352822ce62b97ac05abaf0f3c1bf12febeee
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f731edb26d094b1436f1ae8f7feaa219b758523706d306645d29104e63aae2ba
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c118766de402bfe3e62206a87f39c6d46fe3ee0a0bb740392a806a10d2bcb8d6
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1286378412bc9be0eede836aaf9f4084d97b0af067b04ec6703f0542481f3542
3
  size 152327371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ffe34d77c5cee36911714512c5937860963bc471f0847054916c4e38e6e7621
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc5a91327442f77fce656478cc43bf2f2d788ef73078caf9dba3f5f5dd81fc6
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73b784d21d353cb1ab7af74bca30ff375492629f7fd3b8564b00c00b73c05a05
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de9c31898faa90e078c2be80f244ffb340d326fd9201a02b537a0f01fd6fdae
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": 153.954802259887,
6
  "eval_steps": 250,
7
- "global_step": 27250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -8946,6 +8946,88 @@
8946
  "eval_samples_per_second": 51.011,
8947
  "eval_steps_per_second": 12.753,
8948
  "step": 27250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8949
  }
8950
  ],
8951
  "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": 155.36723163841808,
6
  "eval_steps": 250,
7
+ "global_step": 27500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
8946
  "eval_samples_per_second": 51.011,
8947
  "eval_steps_per_second": 12.753,
8948
  "step": 27250
8949
+ },
8950
+ {
8951
+ "epoch": 154.09604519774012,
8952
+ "grad_norm": 1.7880581617355347,
8953
+ "learning_rate": 3.0517578125e-08,
8954
+ "loss": 0.2409,
8955
+ "step": 27275
8956
+ },
8957
+ {
8958
+ "epoch": 154.23728813559322,
8959
+ "grad_norm": 1.6240562200546265,
8960
+ "learning_rate": 3.0517578125e-08,
8961
+ "loss": 0.2649,
8962
+ "step": 27300
8963
+ },
8964
+ {
8965
+ "epoch": 154.37853107344634,
8966
+ "grad_norm": 1.1167521476745605,
8967
+ "learning_rate": 3.0517578125e-08,
8968
+ "loss": 0.2602,
8969
+ "step": 27325
8970
+ },
8971
+ {
8972
+ "epoch": 154.51977401129943,
8973
+ "grad_norm": 2.0708067417144775,
8974
+ "learning_rate": 3.0517578125e-08,
8975
+ "loss": 0.2435,
8976
+ "step": 27350
8977
+ },
8978
+ {
8979
+ "epoch": 154.66101694915255,
8980
+ "grad_norm": 3.665379762649536,
8981
+ "learning_rate": 3.0517578125e-08,
8982
+ "loss": 0.2426,
8983
+ "step": 27375
8984
+ },
8985
+ {
8986
+ "epoch": 154.80225988700565,
8987
+ "grad_norm": 2.4747049808502197,
8988
+ "learning_rate": 3.0517578125e-08,
8989
+ "loss": 0.2479,
8990
+ "step": 27400
8991
+ },
8992
+ {
8993
+ "epoch": 154.94350282485877,
8994
+ "grad_norm": 2.2483785152435303,
8995
+ "learning_rate": 3.0517578125e-08,
8996
+ "loss": 0.2785,
8997
+ "step": 27425
8998
+ },
8999
+ {
9000
+ "epoch": 155.08474576271186,
9001
+ "grad_norm": 1.7626383304595947,
9002
+ "learning_rate": 3.0517578125e-08,
9003
+ "loss": 0.2437,
9004
+ "step": 27450
9005
+ },
9006
+ {
9007
+ "epoch": 155.22598870056498,
9008
+ "grad_norm": 2.3040082454681396,
9009
+ "learning_rate": 3.0517578125e-08,
9010
+ "loss": 0.2565,
9011
+ "step": 27475
9012
+ },
9013
+ {
9014
+ "epoch": 155.36723163841808,
9015
+ "grad_norm": 2.613694906234741,
9016
+ "learning_rate": 3.0517578125e-08,
9017
+ "loss": 0.3,
9018
+ "step": 27500
9019
+ },
9020
+ {
9021
+ "epoch": 155.36723163841808,
9022
+ "eval_asd": 9.828743858003728,
9023
+ "eval_dice": 0.7898013508478644,
9024
+ "eval_hd95": 30.01546147959176,
9025
+ "eval_jaccard": 0.6961190689898142,
9026
+ "eval_loss": 0.35276085138320923,
9027
+ "eval_runtime": 5.1102,
9028
+ "eval_samples_per_second": 50.879,
9029
+ "eval_steps_per_second": 12.72,
9030
+ "step": 27500
9031
  }
9032
  ],
9033
  "logging_steps": 25,