aee4 commited on
Commit
2f7fca8
·
verified ·
1 Parent(s): 9948e6f

Training in progress, step 6500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02485aa3e2cf2a4a6ad84433dd1a155da64dc7e47529f9a635aae8a0c706ca1a
3
  size 24995616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60912c4bd62ee6008f71a903d574bfeb9c46e28ab8facf7f5ec1f66e460adf4e
3
  size 24995616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84f3b2b67d109203d6ab8246310900a6aad8242fe4283704af4270e417337f50
3
  size 49993547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c3b278c5f5c08a752093a345b7c27875989cf52b3f2dbd85c84697a9876203
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:f9fa43c056b3ab45fe85f9466b65b836ad0704cd1574d226c1baa6a7c1dcb77f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b04015a5468c4c71a68f8a7c3be6fa1a5ab0c6b493b0d95c32db53b793b58b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:031b91e78321e96d3c2046bc3d802cbc572e93737238895fb2d5fe621fa21002
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd42148ca06af3dcaae7c3c41a36858ecdc4d5a2efcfa7856aea721e403ac06a
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 5250,
3
- "best_metric": 0.8170367604268931,
4
- "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-5250",
5
- "epoch": 29.620853080568722,
6
  "eval_steps": 250,
7
- "global_step": 6250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2083,6 +2083,89 @@
2083
  "eval_specificity": 0.984537025140904,
2084
  "eval_steps_per_second": 25.892,
2085
  "step": 6250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2086
  }
2087
  ],
2088
  "logging_steps": 25,
@@ -2097,7 +2180,7 @@
2097
  "early_stopping_threshold": 0.0
2098
  },
2099
  "attributes": {
2100
- "early_stopping_patience_counter": 4
2101
  }
2102
  },
2103
  "TrainerControl": {
 
1
  {
2
+ "best_global_step": 6500,
3
+ "best_metric": 0.8276172389105805,
4
+ "best_model_checkpoint": "/kaggle/working/G17_training/trainer_output/checkpoint-6500",
5
+ "epoch": 30.805687203791468,
6
  "eval_steps": 250,
7
+ "global_step": 6500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2083
  "eval_specificity": 0.984537025140904,
2084
  "eval_steps_per_second": 25.892,
2085
  "step": 6250
2086
+ },
2087
+ {
2088
+ "epoch": 29.739336492890995,
2089
+ "grad_norm": 5.019454479217529,
2090
+ "learning_rate": 0.00015132701421800946,
2091
+ "loss": 0.2982,
2092
+ "step": 6275
2093
+ },
2094
+ {
2095
+ "epoch": 29.85781990521327,
2096
+ "grad_norm": 2.5394093990325928,
2097
+ "learning_rate": 0.00015073459715639808,
2098
+ "loss": 0.3094,
2099
+ "step": 6300
2100
+ },
2101
+ {
2102
+ "epoch": 29.976303317535546,
2103
+ "grad_norm": 3.266801118850708,
2104
+ "learning_rate": 0.0001501421800947867,
2105
+ "loss": 0.3041,
2106
+ "step": 6325
2107
+ },
2108
+ {
2109
+ "epoch": 30.09478672985782,
2110
+ "grad_norm": 1.4742696285247803,
2111
+ "learning_rate": 0.00014954976303317534,
2112
+ "loss": 0.2781,
2113
+ "step": 6350
2114
+ },
2115
+ {
2116
+ "epoch": 30.213270142180093,
2117
+ "grad_norm": 3.4327144622802734,
2118
+ "learning_rate": 0.00014895734597156397,
2119
+ "loss": 0.2816,
2120
+ "step": 6375
2121
+ },
2122
+ {
2123
+ "epoch": 30.33175355450237,
2124
+ "grad_norm": 2.5286035537719727,
2125
+ "learning_rate": 0.0001483649289099526,
2126
+ "loss": 0.2871,
2127
+ "step": 6400
2128
+ },
2129
+ {
2130
+ "epoch": 30.450236966824644,
2131
+ "grad_norm": 2.3594565391540527,
2132
+ "learning_rate": 0.00014777251184834123,
2133
+ "loss": 0.3143,
2134
+ "step": 6425
2135
+ },
2136
+ {
2137
+ "epoch": 30.56872037914692,
2138
+ "grad_norm": 1.1651090383529663,
2139
+ "learning_rate": 0.00014718009478672985,
2140
+ "loss": 0.2555,
2141
+ "step": 6450
2142
+ },
2143
+ {
2144
+ "epoch": 30.687203791469194,
2145
+ "grad_norm": 0.8595591187477112,
2146
+ "learning_rate": 0.00014658767772511848,
2147
+ "loss": 0.2785,
2148
+ "step": 6475
2149
+ },
2150
+ {
2151
+ "epoch": 30.805687203791468,
2152
+ "grad_norm": 2.7474441528320312,
2153
+ "learning_rate": 0.00014599526066350708,
2154
+ "loss": 0.289,
2155
+ "step": 6500
2156
+ },
2157
+ {
2158
+ "epoch": 30.805687203791468,
2159
+ "eval_dice": 0.8276172389105805,
2160
+ "eval_iou": 0.743831211106206,
2161
+ "eval_loss": 0.29712679982185364,
2162
+ "eval_precision": 0.8676792649198588,
2163
+ "eval_recall": 0.8298783862249671,
2164
+ "eval_runtime": 4.0034,
2165
+ "eval_samples_per_second": 104.911,
2166
+ "eval_specificity": 0.9867214788840634,
2167
+ "eval_steps_per_second": 26.228,
2168
+ "step": 6500
2169
  }
2170
  ],
2171
  "logging_steps": 25,
 
2180
  "early_stopping_threshold": 0.0
2181
  },
2182
  "attributes": {
2183
+ "early_stopping_patience_counter": 0
2184
  }
2185
  },
2186
  "TrainerControl": {