Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e646557d1714b03c01fb412f6a1095d6f0b27dd1db5951c862dfad4d6c29751
+oid sha256:7bfe6baaacbaddd015a12bab49156e00dc4c1e160550b542d0e226325ddf5db2
 size 109474784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4228557dbc6e8fb4064941b1ddaa475b330a42e7b6431885dc21d12506dd651a
+oid sha256:e6ac30952c6f539d3da6544d4a2a861e02a244be12cf1dcce8debe764ab885bf
 size 219167566

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e14e48fa7fa467aea82a41053dff7dcc24f23aa7b927758568ed7e573f1d8f
+oid sha256:51cf59aec563c848c9c9be96d1ec5da07a8b242f22b4d8d9c6b8147d291c7066
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d59504241658e218f41099a9cf64bc628eab9f2f1191eb39337b946e3c461384
+oid sha256:0387c1f4f109c89a4181c525b44fe19c547102aff44e31602a2e690f07d152e2
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88e6c307192b2d8ef1913d03dcc8581441beba1d5797a4977890061747277b7d
+oid sha256:a45dc5aad56aa99b2c784b45cd965c9e0655df0c73e21270b60c989eff8ce39c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.107725,
+  "epoch": 4.132725,
   "eval_steps": 1000,
-  "global_step": 39000,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3089,6 +3089,85 @@
       "eval_samples_per_second": 6.558,
       "eval_steps_per_second": 0.82,
       "step": 39000
+    },
+    {
+      "epoch": 4.110225,
+      "grad_norm": 0.23436564207077026,
+      "learning_rate": 6.581721081324321e-08,
+      "loss": 0.1377,
+      "step": 39100
+    },
+    {
+      "epoch": 4.112725,
+      "grad_norm": 0.46249279379844666,
+      "learning_rate": 5.20229406119066e-08,
+      "loss": 0.1134,
+      "step": 39200
+    },
+    {
+      "epoch": 4.115225,
+      "grad_norm": 0.185123011469841,
+      "learning_rate": 3.9847508890114574e-08,
+      "loss": 0.0978,
+      "step": 39300
+    },
+    {
+      "epoch": 4.117725,
+      "grad_norm": 0.8050533533096313,
+      "learning_rate": 2.9291705694176052e-08,
+      "loss": 0.1052,
+      "step": 39400
+    },
+    {
+      "epoch": 4.120225,
+      "grad_norm": 0.2137298583984375,
+      "learning_rate": 2.0356215975037006e-08,
+      "loss": 0.108,
+      "step": 39500
+    },
+    {
+      "epoch": 4.122725,
+      "grad_norm": 0.22636649012565613,
+      "learning_rate": 1.3041619543818773e-08,
+      "loss": 0.1081,
+      "step": 39600
+    },
+    {
+      "epoch": 4.125225,
+      "grad_norm": 0.8003067374229431,
+      "learning_rate": 7.34839103420093e-09,
+      "loss": 0.1003,
+      "step": 39700
+    },
+    {
+      "epoch": 4.127725,
+      "grad_norm": 0.31316348910331726,
+      "learning_rate": 3.2768998716237177e-09,
+      "loss": 0.0946,
+      "step": 39800
+    },
+    {
+      "epoch": 4.130225,
+      "grad_norm": 0.1979643851518631,
+      "learning_rate": 8.274102493155411e-10,
+      "loss": 0.1167,
+      "step": 39900
+    },
+    {
+      "epoch": 4.132725,
+      "grad_norm": 0.2671285569667816,
+      "learning_rate": 8.111114835340772e-14,
+      "loss": 0.1142,
+      "step": 40000
+    },
+    {
+      "epoch": 4.132725,
+      "eval_loss": 0.2432384490966797,
+      "eval_mean_iou": 0.38175953658272593,
+      "eval_runtime": 22.4802,
+      "eval_samples_per_second": 8.897,
+      "eval_steps_per_second": 1.112,
+      "step": 40000
     }
   ],
   "logging_steps": 100,
@@ -3103,12 +3182,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.02696903019966e+19,
+  "total_flos": 4.130233913719967e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null