aee4 commited on
Commit
5f1babd
·
verified ·
1 Parent(s): b02155c

Training in progress, step 25000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf6f92f5cead0b55e9039d86c2f34e56fac99de594be2c4e6242b11129eec63b
3
  size 76153420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15fe9ca760adf8b1de6126c76774d044f365f87464c6fa823fa000f96890a98f
3
  size 76153420
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e9c9e3c8eba8c3a23e8d1f5008742f827782029b429d807fcc0cb4464c12242
3
  size 152327371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ec77486ad1f510c324b28c0af1e7048278cdd21e408c0ff6c1124dbdbc0c0f
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:acb5cd8d790926f87a61764ced4598531d15a21dda0771e484b1d836b5c851e2
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53e89b4dd924821239ce07e4b1cd83255d84da817bd9ae57d609333ea61ca381
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef9add21fa268b698b3a5b76d6915a09037e3b69b20c46c261fec18f527f895a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9fedbac6a4cb25b0146acd9217dd3b4e452b97ef5f47a75d8821ffbba633524
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": 139.83050847457628,
6
  "eval_steps": 250,
7
- "global_step": 24750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -8126,6 +8126,88 @@
8126
  "eval_samples_per_second": 50.857,
8127
  "eval_steps_per_second": 12.714,
8128
  "step": 24750
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8129
  }
8130
  ],
8131
  "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": 141.24293785310735,
6
  "eval_steps": 250,
7
+ "global_step": 25000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
8126
  "eval_samples_per_second": 50.857,
8127
  "eval_steps_per_second": 12.714,
8128
  "step": 24750
8129
+ },
8130
+ {
8131
+ "epoch": 139.97175141242937,
8132
+ "grad_norm": 1.3990654945373535,
8133
+ "learning_rate": 1.220703125e-07,
8134
+ "loss": 0.2648,
8135
+ "step": 24775
8136
+ },
8137
+ {
8138
+ "epoch": 140.1129943502825,
8139
+ "grad_norm": 1.069877028465271,
8140
+ "learning_rate": 6.103515625e-08,
8141
+ "loss": 0.2641,
8142
+ "step": 24800
8143
+ },
8144
+ {
8145
+ "epoch": 140.25423728813558,
8146
+ "grad_norm": 1.1417135000228882,
8147
+ "learning_rate": 6.103515625e-08,
8148
+ "loss": 0.2431,
8149
+ "step": 24825
8150
+ },
8151
+ {
8152
+ "epoch": 140.3954802259887,
8153
+ "grad_norm": 0.7752037048339844,
8154
+ "learning_rate": 6.103515625e-08,
8155
+ "loss": 0.2549,
8156
+ "step": 24850
8157
+ },
8158
+ {
8159
+ "epoch": 140.5367231638418,
8160
+ "grad_norm": 0.8644000291824341,
8161
+ "learning_rate": 6.103515625e-08,
8162
+ "loss": 0.258,
8163
+ "step": 24875
8164
+ },
8165
+ {
8166
+ "epoch": 140.67796610169492,
8167
+ "grad_norm": 2.7392101287841797,
8168
+ "learning_rate": 6.103515625e-08,
8169
+ "loss": 0.2744,
8170
+ "step": 24900
8171
+ },
8172
+ {
8173
+ "epoch": 140.819209039548,
8174
+ "grad_norm": 1.7025507688522339,
8175
+ "learning_rate": 6.103515625e-08,
8176
+ "loss": 0.2821,
8177
+ "step": 24925
8178
+ },
8179
+ {
8180
+ "epoch": 140.96045197740114,
8181
+ "grad_norm": 1.7400317192077637,
8182
+ "learning_rate": 6.103515625e-08,
8183
+ "loss": 0.2605,
8184
+ "step": 24950
8185
+ },
8186
+ {
8187
+ "epoch": 141.10169491525423,
8188
+ "grad_norm": 2.5572502613067627,
8189
+ "learning_rate": 6.103515625e-08,
8190
+ "loss": 0.2749,
8191
+ "step": 24975
8192
+ },
8193
+ {
8194
+ "epoch": 141.24293785310735,
8195
+ "grad_norm": 0.8519913554191589,
8196
+ "learning_rate": 6.103515625e-08,
8197
+ "loss": 0.2421,
8198
+ "step": 25000
8199
+ },
8200
+ {
8201
+ "epoch": 141.24293785310735,
8202
+ "eval_asd": 10.119951532853545,
8203
+ "eval_dice": 0.7918581254911912,
8204
+ "eval_hd95": 31.144266735947312,
8205
+ "eval_jaccard": 0.6977805881687986,
8206
+ "eval_loss": 0.3454740643501282,
8207
+ "eval_runtime": 5.1394,
8208
+ "eval_samples_per_second": 50.59,
8209
+ "eval_steps_per_second": 12.648,
8210
+ "step": 25000
8211
  }
8212
  ],
8213
  "logging_steps": 25,