Training in progress, epoch 74, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a83e52ef2a0a09610428ae11cc571768905f7860256a9595fd83481602e93fa0
+oid sha256:421852674ee7e5fb884fedde823129400a2a77e2ce9fdcda7248dbe602295e87
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b528e37ccaba2b565274b5b8b973220186ebd02dad5e8a4f4baec2885bf626c8
+oid sha256:885256dbd271d4acdcdc5dd1fe21689d1142647c5cd71cec6d3533802ebff448
 size 330495866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b7e6f767aea18d6d4ac34a2bfb02585dd87a12a52679d2a658a2b56ad7e302
+oid sha256:6000c37f90dc3b850dac3042834ee9dddd756f53ca02164e22124efd3c87f850
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948b3a051b88eb4d3ae3c71089b5c7c6ae711d60bb0c6924fb2c43487f2b5879
+oid sha256:52801c60befa357564462eaa30eb8290d188ee442c2f8c95fd10a63dc3d264df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.31184816360473633,
   "best_model_checkpoint": "chickens-composite-201616161616-150-epochs-wo-transform/checkpoint-35000",
-  "epoch": 73.0,
+  "epoch": 74.0,
   "eval_steps": 500,
-  "global_step": 36500,
+  "global_step": 37000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10417,6 +10417,151 @@
       "eval_samples_per_second": 7.119,
       "eval_steps_per_second": 0.925,
       "step": 36500
+    },
+    {
+      "epoch": 73.02,
+      "grad_norm": 61.354408264160156,
+      "learning_rate": 5.207285692376427e-06,
+      "loss": 0.2531,
+      "step": 36510
+    },
+    {
+      "epoch": 73.08,
+      "grad_norm": 135.92481994628906,
+      "learning_rate": 5.201007746814767e-06,
+      "loss": 0.2641,
+      "step": 36540
+    },
+    {
+      "epoch": 73.14,
+      "grad_norm": 42.83466339111328,
+      "learning_rate": 5.194729483834438e-06,
+      "loss": 0.2872,
+      "step": 36570
+    },
+    {
+      "epoch": 73.2,
+      "grad_norm": 34.50326156616211,
+      "learning_rate": 5.188450913349674e-06,
+      "loss": 0.2668,
+      "step": 36600
+    },
+    {
+      "epoch": 73.26,
+      "grad_norm": 67.49690246582031,
+      "learning_rate": 5.1821720452751945e-06,
+      "loss": 0.2556,
+      "step": 36630
+    },
+    {
+      "epoch": 73.32,
+      "grad_norm": 62.13235092163086,
+      "learning_rate": 5.175892889526189e-06,
+      "loss": 0.2524,
+      "step": 36660
+    },
+    {
+      "epoch": 73.38,
+      "grad_norm": 39.14817428588867,
+      "learning_rate": 5.1696134560183045e-06,
+      "loss": 0.2292,
+      "step": 36690
+    },
+    {
+      "epoch": 73.44,
+      "grad_norm": 62.339149475097656,
+      "learning_rate": 5.16333375466762e-06,
+      "loss": 0.2844,
+      "step": 36720
+    },
+    {
+      "epoch": 73.5,
+      "grad_norm": 92.51763153076172,
+      "learning_rate": 5.157053795390642e-06,
+      "loss": 0.2974,
+      "step": 36750
+    },
+    {
+      "epoch": 73.56,
+      "grad_norm": 57.300418853759766,
+      "learning_rate": 5.150773588104284e-06,
+      "loss": 0.2336,
+      "step": 36780
+    },
+    {
+      "epoch": 73.62,
+      "grad_norm": 58.37376403808594,
+      "learning_rate": 5.144493142725851e-06,
+      "loss": 0.255,
+      "step": 36810
+    },
+    {
+      "epoch": 73.68,
+      "grad_norm": 54.429656982421875,
+      "learning_rate": 5.138212469173022e-06,
+      "loss": 0.3182,
+      "step": 36840
+    },
+    {
+      "epoch": 73.74,
+      "grad_norm": 142.04763793945312,
+      "learning_rate": 5.13193157736384e-06,
+      "loss": 0.2789,
+      "step": 36870
+    },
+    {
+      "epoch": 73.8,
+      "grad_norm": 66.44054412841797,
+      "learning_rate": 5.1256504772166885e-06,
+      "loss": 0.2505,
+      "step": 36900
+    },
+    {
+      "epoch": 73.86,
+      "grad_norm": 67.2595443725586,
+      "learning_rate": 5.119369178650282e-06,
+      "loss": 0.2399,
+      "step": 36930
+    },
+    {
+      "epoch": 73.92,
+      "grad_norm": 67.150146484375,
+      "learning_rate": 5.1130876915836495e-06,
+      "loss": 0.2854,
+      "step": 36960
+    },
+    {
+      "epoch": 73.98,
+      "grad_norm": 74.2684326171875,
+      "learning_rate": 5.1068060259361155e-06,
+      "loss": 0.2582,
+      "step": 36990
+    },
+    {
+      "epoch": 74.0,
+      "eval_loss": 0.31870606541633606,
+      "eval_map": 0.7877,
+      "eval_map_50": 0.9519,
+      "eval_map_75": 0.9094,
+      "eval_map_chicken": 0.7903,
+      "eval_map_duck": 0.7278,
+      "eval_map_large": 0.796,
+      "eval_map_medium": 0.7885,
+      "eval_map_plant": 0.8449,
+      "eval_map_small": 0.3513,
+      "eval_mar_1": 0.3134,
+      "eval_mar_10": 0.8268,
+      "eval_mar_100": 0.829,
+      "eval_mar_100_chicken": 0.8341,
+      "eval_mar_100_duck": 0.7742,
+      "eval_mar_100_plant": 0.8788,
+      "eval_mar_large": 0.8335,
+      "eval_mar_medium": 0.8315,
+      "eval_mar_small": 0.3976,
+      "eval_runtime": 14.3727,
+      "eval_samples_per_second": 6.958,
+      "eval_steps_per_second": 0.904,
+      "step": 37000
     }
   ],
   "logging_steps": 30,
@@ -10436,7 +10581,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.25568436211712e+19,
+  "total_flos": 1.27288551776256e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null