Training in progress, epoch 112, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292c73693098875692abcb4fe84b6b84cc28407036bb27a962300192d5d9f048
+oid sha256:3877cbb6b950cf4c5843dd0231527a1cc2b3b9bfc2562ccb8c27b7f9627eee3e
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70174351bbc61e80037e803568d9a6f4338016d31c52d7c41f2228630dfa92a
+oid sha256:92131f5675c8cd4e58cc1ba0f6c595c49b93168989163839bb1a382acb0fcadc
 size 330495866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c387bfd9a993f978958650fcc5a25ab904bd56418ed7491f4791553eb1382ae
+oid sha256:c1fc25d09e52d766f0206907f84e9120f0722c8875148317201f5f9e6b824ba3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91165b4467d36cadf91977e383e5a88c4e25b217f011b6ddd68eb9dee41f87cb
+oid sha256:26f9d12f584bdbd40d1e891beaa1bdd169a81c278721be8ba6ce2a5a585b5ca0
 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": 111.0,
+  "epoch": 112.0,
   "eval_steps": 500,
-  "global_step": 55500,
+  "global_step": 56000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15843,6 +15843,144 @@
       "eval_samples_per_second": 8.455,
       "eval_steps_per_second": 1.099,
       "step": 55500
+    },
+    {
+      "epoch": 111.06,
+      "grad_norm": 54.1436882019043,
+      "learning_rate": 1.572686929076116e-06,
+      "loss": 0.2357,
+      "step": 55530
+    },
+    {
+      "epoch": 111.12,
+      "grad_norm": 107.09626007080078,
+      "learning_rate": 1.5681147999908308e-06,
+      "loss": 0.2024,
+      "step": 55560
+    },
+    {
+      "epoch": 111.18,
+      "grad_norm": 40.910980224609375,
+      "learning_rate": 1.5635480903207139e-06,
+      "loss": 0.2048,
+      "step": 55590
+    },
+    {
+      "epoch": 111.24,
+      "grad_norm": 76.96800994873047,
+      "learning_rate": 1.5589868072772279e-06,
+      "loss": 0.2338,
+      "step": 55620
+    },
+    {
+      "epoch": 111.3,
+      "grad_norm": 77.27308654785156,
+      "learning_rate": 1.554430958063259e-06,
+      "loss": 0.2305,
+      "step": 55650
+    },
+    {
+      "epoch": 111.36,
+      "grad_norm": 69.03377532958984,
+      "learning_rate": 1.5498805498731146e-06,
+      "loss": 0.2088,
+      "step": 55680
+    },
+    {
+      "epoch": 111.42,
+      "grad_norm": 39.929359436035156,
+      "learning_rate": 1.5453355898925094e-06,
+      "loss": 0.2164,
+      "step": 55710
+    },
+    {
+      "epoch": 111.48,
+      "grad_norm": 98.23054504394531,
+      "learning_rate": 1.5407960852985582e-06,
+      "loss": 0.2294,
+      "step": 55740
+    },
+    {
+      "epoch": 111.54,
+      "grad_norm": 41.308589935302734,
+      "learning_rate": 1.5362620432597559e-06,
+      "loss": 0.2172,
+      "step": 55770
+    },
+    {
+      "epoch": 111.6,
+      "grad_norm": 42.228031158447266,
+      "learning_rate": 1.531733470935976e-06,
+      "loss": 0.2229,
+      "step": 55800
+    },
+    {
+      "epoch": 111.66,
+      "grad_norm": 44.37253189086914,
+      "learning_rate": 1.5272103754784517e-06,
+      "loss": 0.2366,
+      "step": 55830
+    },
+    {
+      "epoch": 111.72,
+      "grad_norm": 59.920867919921875,
+      "learning_rate": 1.5226927640297663e-06,
+      "loss": 0.2056,
+      "step": 55860
+    },
+    {
+      "epoch": 111.78,
+      "grad_norm": 103.45928955078125,
+      "learning_rate": 1.5181806437238472e-06,
+      "loss": 0.2811,
+      "step": 55890
+    },
+    {
+      "epoch": 111.84,
+      "grad_norm": 31.924144744873047,
+      "learning_rate": 1.5136740216859464e-06,
+      "loss": 0.2208,
+      "step": 55920
+    },
+    {
+      "epoch": 111.9,
+      "grad_norm": 34.80758285522461,
+      "learning_rate": 1.5091729050326376e-06,
+      "loss": 0.2034,
+      "step": 55950
+    },
+    {
+      "epoch": 111.96,
+      "grad_norm": 77.86346435546875,
+      "learning_rate": 1.5046773008717968e-06,
+      "loss": 0.2089,
+      "step": 55980
+    },
+    {
+      "epoch": 112.0,
+      "eval_loss": 0.31037819385528564,
+      "eval_map": 0.8021,
+      "eval_map_50": 0.9514,
+      "eval_map_75": 0.9063,
+      "eval_map_chicken": 0.8105,
+      "eval_map_duck": 0.7278,
+      "eval_map_large": 0.8079,
+      "eval_map_medium": 0.8046,
+      "eval_map_plant": 0.868,
+      "eval_map_small": 0.3474,
+      "eval_mar_1": 0.3175,
+      "eval_mar_10": 0.8374,
+      "eval_mar_100": 0.8407,
+      "eval_mar_100_chicken": 0.8472,
+      "eval_mar_100_duck": 0.7763,
+      "eval_mar_100_plant": 0.8985,
+      "eval_mar_large": 0.8355,
+      "eval_mar_medium": 0.8471,
+      "eval_mar_small": 0.3886,
+      "eval_runtime": 11.3085,
+      "eval_samples_per_second": 8.843,
+      "eval_steps_per_second": 1.15,
+      "step": 56000
     }
   ],
   "logging_steps": 30,
@@ -15862,7 +16000,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.90932827664384e+19,
+  "total_flos": 1.92652943228928e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null