Training in progress, epoch 150, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e1d1549a5bd85493690be93fc646ebd7ff7474c6a13d6c163966b1ae626fdb
+oid sha256:3ffa5fecfdf2219c82b6b7296f5cc6c25f837bd17844eb4b3a72eba7fc38dcda
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04416de135874138de7f6a298b6a3592926ca9becf476bc3796b957675aecb5c
+oid sha256:5de9ccedb7430d22f2e455c209993c0666e09225f8583c1056242611debfa15b
 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": 0.2941422462463379,
   "best_model_checkpoint": "chickens-composite-101818181818-150-epochs-w-transform-metrics-test-shfld/checkpoint-64500",
-  "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": 15.029,
       "eval_steps_per_second": 1.954,
       "step": 74500
+    },
+    {
+      "epoch": 149.04,
+      "grad_norm": 117.0508041381836,
+      "learning_rate": 1.0106134441850712e-09,
+      "loss": 0.3573,
+      "step": 74520
+    },
+    {
+      "epoch": 149.1,
+      "grad_norm": 45.64506530761719,
+      "learning_rate": 8.88238095955174e-10,
+      "loss": 0.3316,
+      "step": 74550
+    },
+    {
+      "epoch": 149.16,
+      "grad_norm": 94.44927978515625,
+      "learning_rate": 7.737570275573314e-10,
+      "loss": 0.3382,
+      "step": 74580
+    },
+    {
+      "epoch": 149.22,
+      "grad_norm": 3.591849599615671e-05,
+      "learning_rate": 6.671704197735995e-10,
+      "loss": 0.342,
+      "step": 74610
+    },
+    {
+      "epoch": 149.28,
+      "grad_norm": 67.9451675415039,
+      "learning_rate": 5.684784409182298e-10,
+      "loss": 0.2873,
+      "step": 74640
+    },
+    {
+      "epoch": 149.34,
+      "grad_norm": 42.688377380371094,
+      "learning_rate": 4.776812468398895e-10,
+      "loss": 0.4223,
+      "step": 74670
+    },
+    {
+      "epoch": 149.4,
+      "grad_norm": 41.38331985473633,
+      "learning_rate": 3.9477898091944135e-10,
+      "loss": 0.3307,
+      "step": 74700
+    },
+    {
+      "epoch": 149.46,
+      "grad_norm": 0.00017890056187752634,
+      "learning_rate": 3.1977177407105376e-10,
+      "loss": 0.3874,
+      "step": 74730
+    },
+    {
+      "epoch": 149.52,
+      "grad_norm": 41.96646499633789,
+      "learning_rate": 2.5265974474109054e-10,
+      "loss": 0.3314,
+      "step": 74760
+    },
+    {
+      "epoch": 149.58,
+      "grad_norm": 103.0324478149414,
+      "learning_rate": 1.9344299890866614e-10,
+      "loss": 0.3076,
+      "step": 74790
+    },
+    {
+      "epoch": 149.64,
+      "grad_norm": 61.15840530395508,
+      "learning_rate": 1.4212163008509028e-10,
+      "loss": 0.3422,
+      "step": 74820
+    },
+    {
+      "epoch": 149.7,
+      "grad_norm": 69.58673095703125,
+      "learning_rate": 9.869571931442334e-11,
+      "loss": 0.4025,
+      "step": 74850
+    },
+    {
+      "epoch": 149.76,
+      "grad_norm": 45.99262619018555,
+      "learning_rate": 6.316533517125578e-11,
+      "loss": 0.3571,
+      "step": 74880
+    },
+    {
+      "epoch": 149.82,
+      "grad_norm": 57.4156379699707,
+      "learning_rate": 3.55305337634837e-11,
+      "loss": 0.344,
+      "step": 74910
+    },
+    {
+      "epoch": 149.88,
+      "grad_norm": 65.1833267211914,
+      "learning_rate": 1.57913587295333e-11,
+      "loss": 0.4197,
+      "step": 74940
+    },
+    {
+      "epoch": 149.94,
+      "grad_norm": 45.26428985595703,
+      "learning_rate": 3.947841241136452e-12,
+      "loss": 0.308,
+      "step": 74970
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 50.627567291259766,
+      "learning_rate": 0.0,
+      "loss": 0.3823,
+      "step": 75000
+    },
+    {
+      "epoch": 150.0,
+      "eval_loss": 0.29592713713645935,
+      "eval_map": 0.7997,
+      "eval_map_50": 0.9529,
+      "eval_map_75": 0.9125,
+      "eval_map_chicken": 0.7961,
+      "eval_map_duck": 0.7392,
+      "eval_map_large": 0.8126,
+      "eval_map_medium": 0.7977,
+      "eval_map_plant": 0.8637,
+      "eval_map_small": 0.2883,
+      "eval_mar_1": 0.3344,
+      "eval_mar_10": 0.8339,
+      "eval_mar_100": 0.8362,
+      "eval_mar_100_chicken": 0.8395,
+      "eval_mar_100_duck": 0.7758,
+      "eval_mar_100_plant": 0.8934,
+      "eval_mar_large": 0.8457,
+      "eval_mar_medium": 0.8343,
+      "eval_mar_small": 0.3111,
+      "eval_runtime": 6.8503,
+      "eval_samples_per_second": 14.598,
+      "eval_steps_per_second": 1.898,
+      "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