Training in progress, epoch 148, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0075c09765f4217cb4598585d60460dff05ad3e0e7e110b00dcc6cc35df35f
+oid sha256:a47898b6387ef2cfdf4a2494cac6d643001aa350b662f1ca1cff6c6341846cae
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae21a489ed46c86157d9abebc2ebce7ee2cf5d70cc339aa20c63463b1dec1a1c
+oid sha256:9fd2c0a7bf22601834502a8f53f12a6d808f34646649b87e6eb1f54f7f0d7f05
 size 330495866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c307610f491951f0cf2efdd73180e72af7240ce4aa6a43b10a13ac774ffd0e4
+oid sha256:622595e15d8d4adca4c438019feffee921460c3fc84414d13543954d20d79148
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85f02b07cdec64767b23910029cd704b2c6b794d3aac44d543a26849f5211b68
+oid sha256:426b4b133f941dbc1b63fbe118d222c9115fbe2fd29b895828a7fd399389ce5d
 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": 147.0,
+  "epoch": 148.0,
   "eval_steps": 500,
-  "global_step": 73500,
+  "global_step": 74000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -20979,6 +20979,144 @@
       "eval_samples_per_second": 15.477,
       "eval_steps_per_second": 2.012,
       "step": 73500
+    },
+    {
+      "epoch": 147.06,
+      "grad_norm": 48.93723678588867,
+      "learning_rate": 9.475773543818345e-09,
+      "loss": 0.2219,
+      "step": 73530
+    },
+    {
+      "epoch": 147.12,
+      "grad_norm": 57.43806076049805,
+      "learning_rate": 9.09306994793635e-09,
+      "loss": 0.2339,
+      "step": 73560
+    },
+    {
+      "epoch": 147.18,
+      "grad_norm": 73.41053009033203,
+      "learning_rate": 8.718247675337243e-09,
+      "loss": 0.1919,
+      "step": 73590
+    },
+    {
+      "epoch": 147.24,
+      "grad_norm": 77.83393096923828,
+      "learning_rate": 8.351307317917002e-09,
+      "loss": 0.204,
+      "step": 73620
+    },
+    {
+      "epoch": 147.3,
+      "grad_norm": 54.583885192871094,
+      "learning_rate": 7.992249455124889e-09,
+      "loss": 0.2176,
+      "step": 73650
+    },
+    {
+      "epoch": 147.36,
+      "grad_norm": 33.40181350708008,
+      "learning_rate": 7.641074653961244e-09,
+      "loss": 0.2189,
+      "step": 73680
+    },
+    {
+      "epoch": 147.42,
+      "grad_norm": 16.970766067504883,
+      "learning_rate": 7.297783468980246e-09,
+      "loss": 0.2093,
+      "step": 73710
+    },
+    {
+      "epoch": 147.48,
+      "grad_norm": 48.121337890625,
+      "learning_rate": 6.962376442284368e-09,
+      "loss": 0.2144,
+      "step": 73740
+    },
+    {
+      "epoch": 147.54,
+      "grad_norm": 57.12207794189453,
+      "learning_rate": 6.63485410352771e-09,
+      "loss": 0.2085,
+      "step": 73770
+    },
+    {
+      "epoch": 147.6,
+      "grad_norm": 92.21527099609375,
+      "learning_rate": 6.315216969912663e-09,
+      "loss": 0.1927,
+      "step": 73800
+    },
+    {
+      "epoch": 147.66,
+      "grad_norm": 33.92885208129883,
+      "learning_rate": 6.003465546189358e-09,
+      "loss": 0.2022,
+      "step": 73830
+    },
+    {
+      "epoch": 147.72,
+      "grad_norm": 45.98738479614258,
+      "learning_rate": 5.699600324657328e-09,
+      "loss": 0.1957,
+      "step": 73860
+    },
+    {
+      "epoch": 147.78,
+      "grad_norm": 80.80580139160156,
+      "learning_rate": 5.403621785159407e-09,
+      "loss": 0.2206,
+      "step": 73890
+    },
+    {
+      "epoch": 147.84,
+      "grad_norm": 38.10297393798828,
+      "learning_rate": 5.115530395087276e-09,
+      "loss": 0.211,
+      "step": 73920
+    },
+    {
+      "epoch": 147.9,
+      "grad_norm": 61.57286071777344,
+      "learning_rate": 4.835326609376468e-09,
+      "loss": 0.2167,
+      "step": 73950
+    },
+    {
+      "epoch": 147.96,
+      "grad_norm": 37.9475212097168,
+      "learning_rate": 4.5630108705063684e-09,
+      "loss": 0.19,
+      "step": 73980
+    },
+    {
+      "epoch": 148.0,
+      "eval_loss": 0.3058013916015625,
+      "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": 6.6213,
+      "eval_samples_per_second": 15.103,
+      "eval_steps_per_second": 1.963,
+      "step": 74000
     }
   ],
   "logging_steps": 30,
@@ -20998,7 +21136,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.52856987987968e+19,
+  "total_flos": 2.54577103552512e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null