Training in progress, epoch 150, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e9790a957a17076b2fd3e81a46a61514d45e3fd83828e7c71e313b269d2d43c
+oid sha256:ebb52cac5f3071a35cd575bf00e75571ed3dd4448f59a5e5a1b8dae1834ca28d
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda7aaccfa295b45aedc9af5b9bfb50bc9bb8fdffc88c815357e96fd66ca4fd2
+oid sha256:530bfbe04eff8688a65fe4f706c6565c86e05c710f480592b540996802f511a2
 size 330495866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a396222dff59b097bed0889ab42f3d144ca156561494a7c8362451cc383f6f2
+oid sha256:2369e82f6a6f2e47a7e47e23a9296d17f755e58759c961f78d5cc3d96e6e1325
 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": 0.29718613624572754,
   "best_model_checkpoint": "chickens-composite-201616161616-150-epochs-wo-transform-metrics-test-shfld/checkpoint-49500",
-  "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": 14.146,
       "eval_steps_per_second": 1.839,
       "step": 74500
+    },
+    {
+      "epoch": 149.04,
+      "grad_norm": 65.51058959960938,
+      "learning_rate": 1.0106134441850712e-09,
+      "loss": 0.2223,
+      "step": 74520
+    },
+    {
+      "epoch": 149.1,
+      "grad_norm": 37.981048583984375,
+      "learning_rate": 8.88238095955174e-10,
+      "loss": 0.1933,
+      "step": 74550
+    },
+    {
+      "epoch": 149.16,
+      "grad_norm": 158.58409118652344,
+      "learning_rate": 7.737570275573314e-10,
+      "loss": 0.2096,
+      "step": 74580
+    },
+    {
+      "epoch": 149.22,
+      "grad_norm": 56.425628662109375,
+      "learning_rate": 6.671704197735995e-10,
+      "loss": 0.2107,
+      "step": 74610
+    },
+    {
+      "epoch": 149.28,
+      "grad_norm": 36.22454833984375,
+      "learning_rate": 5.684784409182298e-10,
+      "loss": 0.1885,
+      "step": 74640
+    },
+    {
+      "epoch": 149.34,
+      "grad_norm": 87.21402740478516,
+      "learning_rate": 4.776812468398895e-10,
+      "loss": 0.1967,
+      "step": 74670
+    },
+    {
+      "epoch": 149.4,
+      "grad_norm": 56.854522705078125,
+      "learning_rate": 3.9477898091944135e-10,
+      "loss": 0.194,
+      "step": 74700
+    },
+    {
+      "epoch": 149.46,
+      "grad_norm": 32.06566619873047,
+      "learning_rate": 3.1977177407105376e-10,
+      "loss": 0.1959,
+      "step": 74730
+    },
+    {
+      "epoch": 149.52,
+      "grad_norm": 66.09393310546875,
+      "learning_rate": 2.5265974474109054e-10,
+      "loss": 0.2128,
+      "step": 74760
+    },
+    {
+      "epoch": 149.58,
+      "grad_norm": 60.07960510253906,
+      "learning_rate": 1.9344299890866614e-10,
+      "loss": 0.2127,
+      "step": 74790
+    },
+    {
+      "epoch": 149.64,
+      "grad_norm": 44.7581672668457,
+      "learning_rate": 1.4212163008509028e-10,
+      "loss": 0.1932,
+      "step": 74820
+    },
+    {
+      "epoch": 149.7,
+      "grad_norm": 61.01675033569336,
+      "learning_rate": 9.869571931442334e-11,
+      "loss": 0.2248,
+      "step": 74850
+    },
+    {
+      "epoch": 149.76,
+      "grad_norm": 64.22322082519531,
+      "learning_rate": 6.316533517125578e-11,
+      "loss": 0.2113,
+      "step": 74880
+    },
+    {
+      "epoch": 149.82,
+      "grad_norm": 24.638652801513672,
+      "learning_rate": 3.55305337634837e-11,
+      "loss": 0.1962,
+      "step": 74910
+    },
+    {
+      "epoch": 149.88,
+      "grad_norm": 40.451576232910156,
+      "learning_rate": 1.57913587295333e-11,
+      "loss": 0.2058,
+      "step": 74940
+    },
+    {
+      "epoch": 149.94,
+      "grad_norm": 28.84409523010254,
+      "learning_rate": 3.947841241136452e-12,
+      "loss": 0.2357,
+      "step": 74970
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 203.35765075683594,
+      "learning_rate": 0.0,
+      "loss": 0.2344,
+      "step": 75000
+    },
+    {
+      "epoch": 150.0,
+      "eval_loss": 0.30587318539619446,
+      "eval_map": 0.8044,
+      "eval_map_50": 0.9405,
+      "eval_map_75": 0.9024,
+      "eval_map_chicken": 0.7936,
+      "eval_map_duck": 0.7475,
+      "eval_map_large": 0.7843,
+      "eval_map_medium": 0.8141,
+      "eval_map_plant": 0.8722,
+      "eval_map_small": 0.2979,
+      "eval_mar_1": 0.3221,
+      "eval_mar_10": 0.8382,
+      "eval_mar_100": 0.8419,
+      "eval_mar_100_chicken": 0.844,
+      "eval_mar_100_duck": 0.7804,
+      "eval_mar_100_plant": 0.9012,
+      "eval_mar_large": 0.8145,
+      "eval_mar_medium": 0.8546,
+      "eval_mar_small": 0.3829,
+      "eval_runtime": 6.8325,
+      "eval_samples_per_second": 14.636,
+      "eval_steps_per_second": 1.903,
+      "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