Training in progress, epoch 111, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad2b988d8f0404432c148548cf4bef2c3e459fc5cb3d4b25049082154418178
+oid sha256:292c73693098875692abcb4fe84b6b84cc28407036bb27a962300192d5d9f048
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe570c8a4fa1b73bfe1c715f7f40db03cc6b86d7cb2e76ca103416b45d58494
+oid sha256:c70174351bbc61e80037e803568d9a6f4338016d31c52d7c41f2228630dfa92a
 size 330495866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f7c3a56d7769670ed1811eae3d35cdb7046cabac5d4616921ff952a0230d6c
+oid sha256:0c387bfd9a993f978958650fcc5a25ab904bd56418ed7491f4791553eb1382ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ce54cfb1e1954af7d5a410661038938f3b5da2d5bc8c7db9c67e10ccc637ab7
+oid sha256:91165b4467d36cadf91977e383e5a88c4e25b217f011b6ddd68eb9dee41f87cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2962397336959839,
   "best_model_checkpoint": "chickens-composite-201616161616-150-epochs-wo-transform/checkpoint-45000",
-  "epoch": 110.0,
+  "epoch": 111.0,
   "eval_steps": 500,
-  "global_step": 55000,
+  "global_step": 55500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15698,6 +15698,151 @@
       "eval_samples_per_second": 7.28,
       "eval_steps_per_second": 0.946,
       "step": 55000
+    },
+    {
+      "epoch": 110.04,
+      "grad_norm": 35.87388610839844,
+      "learning_rate": 1.651235264858177e-06,
+      "loss": 0.2443,
+      "step": 55020
+    },
+    {
+      "epoch": 110.1,
+      "grad_norm": 47.754180908203125,
+      "learning_rate": 1.6465721173164e-06,
+      "loss": 0.2129,
+      "step": 55050
+    },
+    {
+      "epoch": 110.16,
+      "grad_norm": 26.22478675842285,
+      "learning_rate": 1.6419142652949793e-06,
+      "loss": 0.1971,
+      "step": 55080
+    },
+    {
+      "epoch": 110.22,
+      "grad_norm": 51.385337829589844,
+      "learning_rate": 1.6372617161493014e-06,
+      "loss": 0.2324,
+      "step": 55110
+    },
+    {
+      "epoch": 110.28,
+      "grad_norm": 54.496002197265625,
+      "learning_rate": 1.6326144772263752e-06,
+      "loss": 0.2315,
+      "step": 55140
+    },
+    {
+      "epoch": 110.34,
+      "grad_norm": 73.95658111572266,
+      "learning_rate": 1.627972555864824e-06,
+      "loss": 0.2268,
+      "step": 55170
+    },
+    {
+      "epoch": 110.4,
+      "grad_norm": 56.15229415893555,
+      "learning_rate": 1.6233359593948777e-06,
+      "loss": 0.1911,
+      "step": 55200
+    },
+    {
+      "epoch": 110.46,
+      "grad_norm": 26.1507511138916,
+      "learning_rate": 1.618704695138353e-06,
+      "loss": 0.2455,
+      "step": 55230
+    },
+    {
+      "epoch": 110.52,
+      "grad_norm": 73.8873291015625,
+      "learning_rate": 1.6140787704086502e-06,
+      "loss": 0.1911,
+      "step": 55260
+    },
+    {
+      "epoch": 110.58,
+      "grad_norm": 101.59705352783203,
+      "learning_rate": 1.6094581925107356e-06,
+      "loss": 0.2273,
+      "step": 55290
+    },
+    {
+      "epoch": 110.64,
+      "grad_norm": 31.966201782226562,
+      "learning_rate": 1.6048429687411294e-06,
+      "loss": 0.2295,
+      "step": 55320
+    },
+    {
+      "epoch": 110.7,
+      "grad_norm": 60.9480094909668,
+      "learning_rate": 1.600233106387904e-06,
+      "loss": 0.2284,
+      "step": 55350
+    },
+    {
+      "epoch": 110.76,
+      "grad_norm": 65.5320816040039,
+      "learning_rate": 1.5956286127306591e-06,
+      "loss": 0.2274,
+      "step": 55380
+    },
+    {
+      "epoch": 110.82,
+      "grad_norm": 67.60034942626953,
+      "learning_rate": 1.591029495040518e-06,
+      "loss": 0.2207,
+      "step": 55410
+    },
+    {
+      "epoch": 110.88,
+      "grad_norm": 134.33175659179688,
+      "learning_rate": 1.586435760580118e-06,
+      "loss": 0.2187,
+      "step": 55440
+    },
+    {
+      "epoch": 110.94,
+      "grad_norm": 66.95919799804688,
+      "learning_rate": 1.5818474166035907e-06,
+      "loss": 0.2397,
+      "step": 55470
+    },
+    {
+      "epoch": 111.0,
+      "grad_norm": 59.430965423583984,
+      "learning_rate": 1.5772644703565564e-06,
+      "loss": 0.2212,
+      "step": 55500
+    },
+    {
+      "epoch": 111.0,
+      "eval_loss": 0.31890785694122314,
+      "eval_map": 0.8013,
+      "eval_map_50": 0.9453,
+      "eval_map_75": 0.8992,
+      "eval_map_chicken": 0.8086,
+      "eval_map_duck": 0.7247,
+      "eval_map_large": 0.7895,
+      "eval_map_medium": 0.8062,
+      "eval_map_plant": 0.8707,
+      "eval_map_small": 0.3336,
+      "eval_mar_1": 0.3229,
+      "eval_mar_10": 0.8357,
+      "eval_mar_100": 0.8399,
+      "eval_mar_100_chicken": 0.8488,
+      "eval_mar_100_duck": 0.7742,
+      "eval_mar_100_plant": 0.8967,
+      "eval_mar_large": 0.8245,
+      "eval_mar_medium": 0.8465,
+      "eval_mar_small": 0.3881,
+      "eval_runtime": 11.8276,
+      "eval_samples_per_second": 8.455,
+      "eval_steps_per_second": 1.099,
+      "step": 55500
     }
   ],
   "logging_steps": 30,
@@ -15717,7 +15862,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8921271209984e+19,
+  "total_flos": 1.90932827664384e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null