Training in progress, epoch 150, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79043b597166944dbe15c71707f6c2e36d21796fbe9c5281916b05b66f1af6b0
+oid sha256:af610a13989daf4d4b17a3b61eb7f777cd37755a355e75d56787476b2fa10ec2
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79e83f088b4e79acfcdcd9eaa116feb978bcbf0afa2c1b761ab171e6db09811
+oid sha256:71730890587d3a348be1ae44e6a6b83b3fc6370b653f0b28fe7f78b6e17a9bac
 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": 0.2800098657608032,
   "best_model_checkpoint": "chickens-composite-201616161616-150-epochs-w-hybrid-transform-metrics-test/checkpoint-54500",
-  "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": 13.77,
       "eval_steps_per_second": 1.79,
       "step": 74500
+    },
+    {
+      "epoch": 149.04,
+      "grad_norm": 112.83297729492188,
+      "learning_rate": 1.0106134441850712e-09,
+      "loss": 0.2617,
+      "step": 74520
+    },
+    {
+      "epoch": 149.1,
+      "grad_norm": 50.06736755371094,
+      "learning_rate": 8.88238095955174e-10,
+      "loss": 0.2336,
+      "step": 74550
+    },
+    {
+      "epoch": 149.16,
+      "grad_norm": 63.30166244506836,
+      "learning_rate": 7.737570275573314e-10,
+      "loss": 0.2674,
+      "step": 74580
+    },
+    {
+      "epoch": 149.22,
+      "grad_norm": 39.75635528564453,
+      "learning_rate": 6.671704197735995e-10,
+      "loss": 0.2511,
+      "step": 74610
+    },
+    {
+      "epoch": 149.28,
+      "grad_norm": 29.61418342590332,
+      "learning_rate": 5.684784409182298e-10,
+      "loss": 0.2124,
+      "step": 74640
+    },
+    {
+      "epoch": 149.34,
+      "grad_norm": 57.52811050415039,
+      "learning_rate": 4.776812468398895e-10,
+      "loss": 0.268,
+      "step": 74670
+    },
+    {
+      "epoch": 149.4,
+      "grad_norm": 55.41215133666992,
+      "learning_rate": 3.9477898091944135e-10,
+      "loss": 0.2094,
+      "step": 74700
+    },
+    {
+      "epoch": 149.46,
+      "grad_norm": 29.794158935546875,
+      "learning_rate": 3.1977177407105376e-10,
+      "loss": 0.2564,
+      "step": 74730
+    },
+    {
+      "epoch": 149.52,
+      "grad_norm": 103.24960327148438,
+      "learning_rate": 2.5265974474109054e-10,
+      "loss": 0.2407,
+      "step": 74760
+    },
+    {
+      "epoch": 149.58,
+      "grad_norm": 44.9169921875,
+      "learning_rate": 1.9344299890866614e-10,
+      "loss": 0.2346,
+      "step": 74790
+    },
+    {
+      "epoch": 149.64,
+      "grad_norm": 74.23555755615234,
+      "learning_rate": 1.4212163008509028e-10,
+      "loss": 0.218,
+      "step": 74820
+    },
+    {
+      "epoch": 149.7,
+      "grad_norm": 99.87975311279297,
+      "learning_rate": 9.869571931442334e-11,
+      "loss": 0.2874,
+      "step": 74850
+    },
+    {
+      "epoch": 149.76,
+      "grad_norm": 54.385589599609375,
+      "learning_rate": 6.316533517125578e-11,
+      "loss": 0.2815,
+      "step": 74880
+    },
+    {
+      "epoch": 149.82,
+      "grad_norm": 38.39406204223633,
+      "learning_rate": 3.55305337634837e-11,
+      "loss": 0.2368,
+      "step": 74910
+    },
+    {
+      "epoch": 149.88,
+      "grad_norm": 60.73610305786133,
+      "learning_rate": 1.57913587295333e-11,
+      "loss": 0.2144,
+      "step": 74940
+    },
+    {
+      "epoch": 149.94,
+      "grad_norm": 22.630802154541016,
+      "learning_rate": 3.947841241136452e-12,
+      "loss": 0.273,
+      "step": 74970
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 25.250965118408203,
+      "learning_rate": 0.0,
+      "loss": 0.2683,
+      "step": 75000
+    },
+    {
+      "epoch": 150.0,
+      "eval_loss": 0.2826327085494995,
+      "eval_map": 0.8176,
+      "eval_map_50": 0.9579,
+      "eval_map_75": 0.9306,
+      "eval_map_chicken": 0.8172,
+      "eval_map_duck": 0.7548,
+      "eval_map_large": 0.8195,
+      "eval_map_medium": 0.8219,
+      "eval_map_plant": 0.8807,
+      "eval_map_small": 0.3875,
+      "eval_mar_1": 0.326,
+      "eval_mar_10": 0.8548,
+      "eval_mar_100": 0.8598,
+      "eval_mar_100_chicken": 0.8631,
+      "eval_mar_100_duck": 0.8103,
+      "eval_mar_100_plant": 0.9061,
+      "eval_mar_large": 0.8516,
+      "eval_mar_medium": 0.8639,
+      "eval_mar_small": 0.5,
+      "eval_runtime": 7.0466,
+      "eval_samples_per_second": 14.191,
+      "eval_steps_per_second": 1.845,
+      "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