Training in progress, epoch 149, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a47898b6387ef2cfdf4a2494cac6d643001aa350b662f1ca1cff6c6341846cae
+oid sha256:7e9790a957a17076b2fd3e81a46a61514d45e3fd83828e7c71e313b269d2d43c
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd2c0a7bf22601834502a8f53f12a6d808f34646649b87e6eb1f54f7f0d7f05
+oid sha256:bda7aaccfa295b45aedc9af5b9bfb50bc9bb8fdffc88c815357e96fd66ca4fd2
 size 330495866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:622595e15d8d4adca4c438019feffee921460c3fc84414d13543954d20d79148
+oid sha256:7a396222dff59b097bed0889ab42f3d144ca156561494a7c8362451cc383f6f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426b4b133f941dbc1b63fbe118d222c9115fbe2fd29b895828a7fd399389ce5d
+oid sha256:d97cfcad85d9182f57a6d2bdf768ab9899061715a0c3f6d191db6d91a27ccfef
 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": 148.0,
+  "epoch": 149.0,
   "eval_steps": 500,
-  "global_step": 74000,
+  "global_step": 74500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21117,6 +21117,151 @@
       "eval_samples_per_second": 15.103,
       "eval_steps_per_second": 1.963,
       "step": 74000
+    },
+    {
+      "epoch": 148.02,
+      "grad_norm": 43.992610931396484,
+      "learning_rate": 4.298583608501328e-09,
+      "loss": 0.2141,
+      "step": 74010
+    },
+    {
+      "epoch": 148.08,
+      "grad_norm": 37.40137481689453,
+      "learning_rate": 4.042045240927883e-09,
+      "loss": 0.2215,
+      "step": 74040
+    },
+    {
+      "epoch": 148.14,
+      "grad_norm": 64.64765930175781,
+      "learning_rate": 3.793396172895314e-09,
+      "loss": 0.2091,
+      "step": 74070
+    },
+    {
+      "epoch": 148.2,
+      "grad_norm": 88.0441665649414,
+      "learning_rate": 3.5526367970539765e-09,
+      "loss": 0.204,
+      "step": 74100
+    },
+    {
+      "epoch": 148.26,
+      "grad_norm": 53.6719856262207,
+      "learning_rate": 3.31976749359586e-09,
+      "loss": 0.1983,
+      "step": 74130
+    },
+    {
+      "epoch": 148.32,
+      "grad_norm": 64.46839141845703,
+      "learning_rate": 3.094788630254031e-09,
+      "loss": 0.2306,
+      "step": 74160
+    },
+    {
+      "epoch": 148.38,
+      "grad_norm": 34.077728271484375,
+      "learning_rate": 2.8777005622998567e-09,
+      "loss": 0.2127,
+      "step": 74190
+    },
+    {
+      "epoch": 148.44,
+      "grad_norm": 71.48238372802734,
+      "learning_rate": 2.6685036325457826e-09,
+      "loss": 0.1978,
+      "step": 74220
+    },
+    {
+      "epoch": 148.5,
+      "grad_norm": 103.37129974365234,
+      "learning_rate": 2.4671981713420003e-09,
+      "loss": 0.2089,
+      "step": 74250
+    },
+    {
+      "epoch": 148.56,
+      "grad_norm": 31.161420822143555,
+      "learning_rate": 2.2737844965775578e-09,
+      "loss": 0.1992,
+      "step": 74280
+    },
+    {
+      "epoch": 148.62,
+      "grad_norm": 60.29501724243164,
+      "learning_rate": 2.088262913679251e-09,
+      "loss": 0.1955,
+      "step": 74310
+    },
+    {
+      "epoch": 148.68,
+      "grad_norm": 55.193145751953125,
+      "learning_rate": 1.9106337156099553e-09,
+      "loss": 0.2197,
+      "step": 74340
+    },
+    {
+      "epoch": 148.74,
+      "grad_norm": 51.890506744384766,
+      "learning_rate": 1.740897182871404e-09,
+      "loss": 0.2325,
+      "step": 74370
+    },
+    {
+      "epoch": 148.8,
+      "grad_norm": 81.51058197021484,
+      "learning_rate": 1.5790535835003006e-09,
+      "loss": 0.206,
+      "step": 74400
+    },
+    {
+      "epoch": 148.86,
+      "grad_norm": 72.36231231689453,
+      "learning_rate": 1.425103173069986e-09,
+      "loss": 0.2108,
+      "step": 74430
+    },
+    {
+      "epoch": 148.92,
+      "grad_norm": 67.69371795654297,
+      "learning_rate": 1.2790461946887712e-09,
+      "loss": 0.2046,
+      "step": 74460
+    },
+    {
+      "epoch": 148.98,
+      "grad_norm": 54.43954086303711,
+      "learning_rate": 1.1408828790010484e-09,
+      "loss": 0.1978,
+      "step": 74490
+    },
+    {
+      "epoch": 149.0,
+      "eval_loss": 0.30586719512939453,
+      "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": 7.0692,
+      "eval_samples_per_second": 14.146,
+      "eval_steps_per_second": 1.839,
+      "step": 74500
     }
   ],
   "logging_steps": 30,
@@ -21136,7 +21281,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.54577103552512e+19,
+  "total_flos": 2.56297219117056e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null