aee4 commited on
Commit
75fc833
·
verified ·
1 Parent(s): b16a15a

Training in progress, step 27750, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f731edb26d094b1436f1ae8f7feaa219b758523706d306645d29104e63aae2ba
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11423187e1331fc94deb0bf135744867620fc9b21408610008b928d09c9147f8
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1286378412bc9be0eede836aaf9f4084d97b0af067b04ec6703f0542481f3542
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cebd3ca7c2fa506a5f2d4807c3e718be4240e9471a01e0f1cf324e0a8ecbb2d0
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:ecc5a91327442f77fce656478cc43bf2f2d788ef73078caf9dba3f5f5dd81fc6
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82dd5e2ad13d2cef7043f2cd1d3696abb2b240d4b0f342524b279387c889418
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1de9c31898faa90e078c2be80f244ffb340d326fd9201a02b537a0f01fd6fdae
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec485a156b6f127d16c572a2bf80911b4937d51d34a5c555fd7a53f85eca3e3
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": 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,
@@ -9028,6 +9028,88 @@
9028
  "eval_samples_per_second": 50.879,
9029
  "eval_steps_per_second": 12.72,
9030
  "step": 27500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9031
  }
9032
  ],
9033
  "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": 156.77966101694915,
6
  "eval_steps": 250,
7
+ "global_step": 27750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
9028
  "eval_samples_per_second": 50.879,
9029
  "eval_steps_per_second": 12.72,
9030
  "step": 27500
9031
+ },
9032
+ {
9033
+ "epoch": 155.5084745762712,
9034
+ "grad_norm": 2.098080635070801,
9035
+ "learning_rate": 3.0517578125e-08,
9036
+ "loss": 0.2638,
9037
+ "step": 27525
9038
+ },
9039
+ {
9040
+ "epoch": 155.6497175141243,
9041
+ "grad_norm": 1.2203691005706787,
9042
+ "learning_rate": 3.0517578125e-08,
9043
+ "loss": 0.2662,
9044
+ "step": 27550
9045
+ },
9046
+ {
9047
+ "epoch": 155.7909604519774,
9048
+ "grad_norm": 1.186450481414795,
9049
+ "learning_rate": 3.0517578125e-08,
9050
+ "loss": 0.2443,
9051
+ "step": 27575
9052
+ },
9053
+ {
9054
+ "epoch": 155.9322033898305,
9055
+ "grad_norm": 2.114698886871338,
9056
+ "learning_rate": 3.0517578125e-08,
9057
+ "loss": 0.2387,
9058
+ "step": 27600
9059
+ },
9060
+ {
9061
+ "epoch": 156.07344632768363,
9062
+ "grad_norm": 1.33856999874115,
9063
+ "learning_rate": 3.0517578125e-08,
9064
+ "loss": 0.2614,
9065
+ "step": 27625
9066
+ },
9067
+ {
9068
+ "epoch": 156.21468926553672,
9069
+ "grad_norm": 3.4051637649536133,
9070
+ "learning_rate": 3.0517578125e-08,
9071
+ "loss": 0.2473,
9072
+ "step": 27650
9073
+ },
9074
+ {
9075
+ "epoch": 156.35593220338984,
9076
+ "grad_norm": 0.7940350770950317,
9077
+ "learning_rate": 3.0517578125e-08,
9078
+ "loss": 0.2437,
9079
+ "step": 27675
9080
+ },
9081
+ {
9082
+ "epoch": 156.49717514124293,
9083
+ "grad_norm": 1.7233728170394897,
9084
+ "learning_rate": 3.0517578125e-08,
9085
+ "loss": 0.2639,
9086
+ "step": 27700
9087
+ },
9088
+ {
9089
+ "epoch": 156.63841807909606,
9090
+ "grad_norm": 1.9247806072235107,
9091
+ "learning_rate": 3.0517578125e-08,
9092
+ "loss": 0.2917,
9093
+ "step": 27725
9094
+ },
9095
+ {
9096
+ "epoch": 156.77966101694915,
9097
+ "grad_norm": 1.1884297132492065,
9098
+ "learning_rate": 3.0517578125e-08,
9099
+ "loss": 0.2444,
9100
+ "step": 27750
9101
+ },
9102
+ {
9103
+ "epoch": 156.77966101694915,
9104
+ "eval_asd": 10.26928203534289,
9105
+ "eval_dice": 0.7913138475512114,
9106
+ "eval_hd95": 31.576737880425377,
9107
+ "eval_jaccard": 0.6968617657714293,
9108
+ "eval_loss": 0.3468586802482605,
9109
+ "eval_runtime": 5.0639,
9110
+ "eval_samples_per_second": 51.343,
9111
+ "eval_steps_per_second": 12.836,
9112
+ "step": 27750
9113
  }
9114
  ],
9115
  "logging_steps": 25,