aee4 commited on
Commit
811bc17
·
verified ·
1 Parent(s): 665c034

Training in progress, step 9750, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5241ff6249b86b35dd48f6a9ecbfd1228ec0a716500d6ecb4c1a8d55221d1d9b
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd34ffc343e647991194ef4eb422c25056fd261069fa3172e77e22aac5a3639
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bab5c0b62f690966f33802f3b921511a7f677b3f978f9198bccd3060b83739b
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573b4c504db2d78ac91d7b7aa23877153f727e02751a364bcfe56d9933c0fd66
3
  size 49993547
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c98b57040a2833b72117d0b761ba5ddf331a12f933f8e56765e492af63cdad1f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7210af27fe26778f7d9ac5f4057eac07457a093e7a0242f3d26fcc633de849c
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:217de68538807aeb5f062c8a64a7e1891c0aec085cf3700d05415a0cc8752b59
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74cc218938d202b7443905d3c4e4f0a010b063ba9a4eb1e2105a96b666dc68b1
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 9250,
3
- "best_metric": 0.8331254935254058,
4
- "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-9250",
5
- "epoch": 45.023696682464454,
6
  "eval_steps": 250,
7
- "global_step": 9500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3162,6 +3162,89 @@
3162
  "eval_specificity": 0.9888507936084833,
3163
  "eval_steps_per_second": 26.24,
3164
  "step": 9500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3165
  }
3166
  ],
3167
  "logging_steps": 25,
@@ -3176,7 +3259,7 @@
3176
  "early_stopping_threshold": 0.0
3177
  },
3178
  "attributes": {
3179
- "early_stopping_patience_counter": 1
3180
  }
3181
  },
3182
  "TrainerControl": {
 
1
  {
2
+ "best_global_step": 9750,
3
+ "best_metric": 0.8381641379059052,
4
+ "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-9750",
5
+ "epoch": 46.208530805687204,
6
  "eval_steps": 250,
7
+ "global_step": 9750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3162
  "eval_specificity": 0.9888507936084833,
3163
  "eval_steps_per_second": 26.24,
3164
  "step": 9500
3165
+ },
3166
+ {
3167
+ "epoch": 45.14218009478673,
3168
+ "grad_norm": 1.6590514183044434,
3169
+ "learning_rate": 7.43127962085308e-05,
3170
+ "loss": 0.2277,
3171
+ "step": 9525
3172
+ },
3173
+ {
3174
+ "epoch": 45.26066350710901,
3175
+ "grad_norm": 4.255414962768555,
3176
+ "learning_rate": 7.372037914691943e-05,
3177
+ "loss": 0.2577,
3178
+ "step": 9550
3179
+ },
3180
+ {
3181
+ "epoch": 45.37914691943128,
3182
+ "grad_norm": 1.847621202468872,
3183
+ "learning_rate": 7.312796208530805e-05,
3184
+ "loss": 0.2253,
3185
+ "step": 9575
3186
+ },
3187
+ {
3188
+ "epoch": 45.497630331753555,
3189
+ "grad_norm": 4.271966457366943,
3190
+ "learning_rate": 7.253554502369668e-05,
3191
+ "loss": 0.2552,
3192
+ "step": 9600
3193
+ },
3194
+ {
3195
+ "epoch": 45.61611374407583,
3196
+ "grad_norm": 6.201179504394531,
3197
+ "learning_rate": 7.19431279620853e-05,
3198
+ "loss": 0.282,
3199
+ "step": 9625
3200
+ },
3201
+ {
3202
+ "epoch": 45.7345971563981,
3203
+ "grad_norm": 3.5390589237213135,
3204
+ "learning_rate": 7.135071090047393e-05,
3205
+ "loss": 0.2247,
3206
+ "step": 9650
3207
+ },
3208
+ {
3209
+ "epoch": 45.85308056872038,
3210
+ "grad_norm": 0.7813404202461243,
3211
+ "learning_rate": 7.075829383886256e-05,
3212
+ "loss": 0.2369,
3213
+ "step": 9675
3214
+ },
3215
+ {
3216
+ "epoch": 45.97156398104266,
3217
+ "grad_norm": 2.832536220550537,
3218
+ "learning_rate": 7.016587677725117e-05,
3219
+ "loss": 0.2426,
3220
+ "step": 9700
3221
+ },
3222
+ {
3223
+ "epoch": 46.09004739336493,
3224
+ "grad_norm": 1.209977388381958,
3225
+ "learning_rate": 6.95734597156398e-05,
3226
+ "loss": 0.2224,
3227
+ "step": 9725
3228
+ },
3229
+ {
3230
+ "epoch": 46.208530805687204,
3231
+ "grad_norm": 2.9203884601593018,
3232
+ "learning_rate": 6.898104265402843e-05,
3233
+ "loss": 0.2199,
3234
+ "step": 9750
3235
+ },
3236
+ {
3237
+ "epoch": 46.208530805687204,
3238
+ "eval_dice": 0.8381641379059052,
3239
+ "eval_iou": 0.7565240022398874,
3240
+ "eval_loss": 0.2861250638961792,
3241
+ "eval_precision": 0.8597875333892834,
3242
+ "eval_recall": 0.8528275686638419,
3243
+ "eval_runtime": 4.0155,
3244
+ "eval_samples_per_second": 104.595,
3245
+ "eval_specificity": 0.9865697169845564,
3246
+ "eval_steps_per_second": 26.149,
3247
+ "step": 9750
3248
  }
3249
  ],
3250
  "logging_steps": 25,
 
3259
  "early_stopping_threshold": 0.0
3260
  },
3261
  "attributes": {
3262
+ "early_stopping_patience_counter": 0
3263
  }
3264
  },
3265
  "TrainerControl": {