Training in progress, epoch 150, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68268e16da69d8fe8a8e7e37d485efb925f3f14720b6d34544e5f5574babace3
+oid sha256:640c4132eadd39acc5aa82c3460e3f7fca4c6f6cbfda7711d4de0cdbf5aed051
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a561df4892c97bbda430a7586982240601df132ede23b9d9c027884d755cdd4
+oid sha256:a40efc4ff75a70ab30d3f736af3e65b76678897d0e4e9059c4b6b2f80cb0a583
 size 330495866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a396222dff59b097bed0889ab42f3d144ca156561494a7c8362451cc383f6f2
+oid sha256:37ba61eb21dd151ab9b4feb5d400cf275fed96c693759a03f3af4b2aaa247d58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d97cfcad85d9182f57a6d2bdf768ab9899061715a0c3f6d191db6d91a27ccfef
+oid sha256:96205cabb1588b7cd4f382979691c79dabb654b1f45a221ef5567a570af3df90
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2871710956096649,
   "best_model_checkpoint": "chickens-composite-101818181818-150-epochs-wo-transform-metrics-test-shfld/checkpoint-63500",
-  "epoch": 149.0,
+  "epoch": 150.0,
   "eval_steps": 500,
-  "global_step": 74500,
+  "global_step": 75000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21262,6 +21262,151 @@
       "eval_samples_per_second": 11.655,
       "eval_steps_per_second": 1.515,
       "step": 74500
+    },
+    {
+      "epoch": 149.04,
+      "grad_norm": 63.2837028503418,
+      "learning_rate": 1.0106134441850712e-09,
+      "loss": 0.2435,
+      "step": 74520
+    },
+    {
+      "epoch": 149.1,
+      "grad_norm": 28.710081100463867,
+      "learning_rate": 8.88238095955174e-10,
+      "loss": 0.2073,
+      "step": 74550
+    },
+    {
+      "epoch": 149.16,
+      "grad_norm": 82.03565979003906,
+      "learning_rate": 7.737570275573314e-10,
+      "loss": 0.1986,
+      "step": 74580
+    },
+    {
+      "epoch": 149.22,
+      "grad_norm": 46.29703140258789,
+      "learning_rate": 6.671704197735995e-10,
+      "loss": 0.2221,
+      "step": 74610
+    },
+    {
+      "epoch": 149.28,
+      "grad_norm": 31.06247901916504,
+      "learning_rate": 5.684784409182298e-10,
+      "loss": 0.2073,
+      "step": 74640
+    },
+    {
+      "epoch": 149.34,
+      "grad_norm": 56.10593032836914,
+      "learning_rate": 4.776812468398895e-10,
+      "loss": 0.2109,
+      "step": 74670
+    },
+    {
+      "epoch": 149.4,
+      "grad_norm": 91.21040344238281,
+      "learning_rate": 3.9477898091944135e-10,
+      "loss": 0.2,
+      "step": 74700
+    },
+    {
+      "epoch": 149.46,
+      "grad_norm": 74.87627410888672,
+      "learning_rate": 3.1977177407105376e-10,
+      "loss": 0.2192,
+      "step": 74730
+    },
+    {
+      "epoch": 149.52,
+      "grad_norm": 65.67242431640625,
+      "learning_rate": 2.5265974474109054e-10,
+      "loss": 0.2463,
+      "step": 74760
+    },
+    {
+      "epoch": 149.58,
+      "grad_norm": 42.597694396972656,
+      "learning_rate": 1.9344299890866614e-10,
+      "loss": 0.2088,
+      "step": 74790
+    },
+    {
+      "epoch": 149.64,
+      "grad_norm": 94.26192474365234,
+      "learning_rate": 1.4212163008509028e-10,
+      "loss": 0.2141,
+      "step": 74820
+    },
+    {
+      "epoch": 149.7,
+      "grad_norm": 45.02417755126953,
+      "learning_rate": 9.869571931442334e-11,
+      "loss": 0.2118,
+      "step": 74850
+    },
+    {
+      "epoch": 149.76,
+      "grad_norm": 60.162017822265625,
+      "learning_rate": 6.316533517125578e-11,
+      "loss": 0.2294,
+      "step": 74880
+    },
+    {
+      "epoch": 149.82,
+      "grad_norm": 50.14275360107422,
+      "learning_rate": 3.55305337634837e-11,
+      "loss": 0.2066,
+      "step": 74910
+    },
+    {
+      "epoch": 149.88,
+      "grad_norm": 69.46136474609375,
+      "learning_rate": 1.57913587295333e-11,
+      "loss": 0.2046,
+      "step": 74940
+    },
+    {
+      "epoch": 149.94,
+      "grad_norm": 49.06306076049805,
+      "learning_rate": 3.947841241136452e-12,
+      "loss": 0.195,
+      "step": 74970
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 82.4388427734375,
+      "learning_rate": 0.0,
+      "loss": 0.2197,
+      "step": 75000
+    },
+    {
+      "epoch": 150.0,
+      "eval_loss": 0.2923794090747833,
+      "eval_map": 0.8009,
+      "eval_map_50": 0.9452,
+      "eval_map_75": 0.8912,
+      "eval_map_chicken": 0.8118,
+      "eval_map_duck": 0.7142,
+      "eval_map_large": 0.7895,
+      "eval_map_medium": 0.8037,
+      "eval_map_plant": 0.8766,
+      "eval_map_small": 0.3686,
+      "eval_mar_1": 0.3378,
+      "eval_mar_10": 0.8405,
+      "eval_mar_100": 0.8439,
+      "eval_mar_100_chicken": 0.852,
+      "eval_mar_100_duck": 0.7705,
+      "eval_mar_100_plant": 0.909,
+      "eval_mar_large": 0.8254,
+      "eval_mar_medium": 0.8478,
+      "eval_mar_small": 0.4542,
+      "eval_runtime": 7.6091,
+      "eval_samples_per_second": 13.142,
+      "eval_steps_per_second": 1.708,
+      "step": 75000
     }
   ],
   "logging_steps": 30,
@@ -21276,12 +21421,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.56297219117056e+19,
+  "total_flos": 2.580173346816e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null