Training in progress, epoch 150, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8831b1cd31506b3f518175109a1d440aa8d79a20cfbe4386023e913e037f4a2
+oid sha256:332b563fb47416fc125a21e6f75c0755569e52e2f5b8430dae602a4c8c8390a0
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27a852d4a1637fbdfc0d7c8bbc89da8ba98d7ba0d4ecdd25926f6f2511bb1ee
+oid sha256:3a8ba93568afea1b227cf90cddd7f89c34a171129e70914e1cc6adbbb38a6d32
 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": 0.2845112681388855,
   "best_model_checkpoint": "chickens-composite-02020202020-150-epochs-w-transform-metrics-test/checkpoint-70000",
-  "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": 13.927,
       "eval_steps_per_second": 1.811,
       "step": 74500
+    },
+    {
+      "epoch": 149.04,
+      "grad_norm": 30.943519592285156,
+      "learning_rate": 1.0106134441850712e-09,
+      "loss": 0.3966,
+      "step": 74520
+    },
+    {
+      "epoch": 149.1,
+      "grad_norm": 48.05521011352539,
+      "learning_rate": 8.88238095955174e-10,
+      "loss": 0.3603,
+      "step": 74550
+    },
+    {
+      "epoch": 149.16,
+      "grad_norm": 37.670833587646484,
+      "learning_rate": 7.737570275573314e-10,
+      "loss": 0.3404,
+      "step": 74580
+    },
+    {
+      "epoch": 149.22,
+      "grad_norm": 263.9615783691406,
+      "learning_rate": 6.671704197735995e-10,
+      "loss": 0.4225,
+      "step": 74610
+    },
+    {
+      "epoch": 149.28,
+      "grad_norm": 81.36726379394531,
+      "learning_rate": 5.684784409182298e-10,
+      "loss": 0.5982,
+      "step": 74640
+    },
+    {
+      "epoch": 149.34,
+      "grad_norm": 47.25887680053711,
+      "learning_rate": 4.776812468398895e-10,
+      "loss": 0.3138,
+      "step": 74670
+    },
+    {
+      "epoch": 149.4,
+      "grad_norm": 57.88069152832031,
+      "learning_rate": 3.9477898091944135e-10,
+      "loss": 0.2951,
+      "step": 74700
+    },
+    {
+      "epoch": 149.46,
+      "grad_norm": 149.3201904296875,
+      "learning_rate": 3.1977177407105376e-10,
+      "loss": 0.3334,
+      "step": 74730
+    },
+    {
+      "epoch": 149.52,
+      "grad_norm": 72.26154327392578,
+      "learning_rate": 2.5265974474109054e-10,
+      "loss": 0.2984,
+      "step": 74760
+    },
+    {
+      "epoch": 149.58,
+      "grad_norm": 53.02653121948242,
+      "learning_rate": 1.9344299890866614e-10,
+      "loss": 0.3437,
+      "step": 74790
+    },
+    {
+      "epoch": 149.64,
+      "grad_norm": 159.47000122070312,
+      "learning_rate": 1.4212163008509028e-10,
+      "loss": 0.3413,
+      "step": 74820
+    },
+    {
+      "epoch": 149.7,
+      "grad_norm": 91.67048645019531,
+      "learning_rate": 9.869571931442334e-11,
+      "loss": 0.3171,
+      "step": 74850
+    },
+    {
+      "epoch": 149.76,
+      "grad_norm": 52.964149475097656,
+      "learning_rate": 6.316533517125578e-11,
+      "loss": 0.2708,
+      "step": 74880
+    },
+    {
+      "epoch": 149.82,
+      "grad_norm": 40.839210510253906,
+      "learning_rate": 3.55305337634837e-11,
+      "loss": 0.424,
+      "step": 74910
+    },
+    {
+      "epoch": 149.88,
+      "grad_norm": 50.875953674316406,
+      "learning_rate": 1.57913587295333e-11,
+      "loss": 0.3058,
+      "step": 74940
+    },
+    {
+      "epoch": 149.94,
+      "grad_norm": 72.69674682617188,
+      "learning_rate": 3.947841241136452e-12,
+      "loss": 0.4069,
+      "step": 74970
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 23.560426712036133,
+      "learning_rate": 0.0,
+      "loss": 0.4439,
+      "step": 75000
+    },
+    {
+      "epoch": 150.0,
+      "eval_loss": 0.28673917055130005,
+      "eval_map": 0.7918,
+      "eval_map_50": 0.9463,
+      "eval_map_75": 0.8926,
+      "eval_map_chicken": 0.7868,
+      "eval_map_duck": 0.7203,
+      "eval_map_large": 0.8114,
+      "eval_map_medium": 0.7785,
+      "eval_map_plant": 0.8682,
+      "eval_map_small": 0.2343,
+      "eval_mar_1": 0.3499,
+      "eval_mar_10": 0.8327,
+      "eval_mar_100": 0.8371,
+      "eval_mar_100_chicken": 0.8356,
+      "eval_mar_100_duck": 0.7758,
+      "eval_mar_100_plant": 0.9,
+      "eval_mar_large": 0.842,
+      "eval_mar_medium": 0.8275,
+      "eval_mar_small": 0.2786,
+      "eval_runtime": 7.2684,
+      "eval_samples_per_second": 13.758,
+      "eval_steps_per_second": 1.789,
+      "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