Training in progress, epoch 70, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8afc1746185cec16643e581fb9ab5321c6d13ec4eecbac00df77e4a2ef3926cb
+oid sha256:aa812769d7086f7d6e19077f55b8e92cd7d402c7253b4b8e5b162c1020e22881
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:475525798608d625979c7d71f2941abe896d06146dd33aea4d8d715b4e8faefd
+oid sha256:650ddd0fde638547cf9b2a00a224f109876334850aa5fcdf74e8cbf8ca681f89
 size 330495866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11db7bd7e6b331ec7027c1f9a58bac7d1a561357af84f38d3e10be5a0609cf76
+oid sha256:685346e99c461788ef127f10b4458c9a0913ccd9cd3182686a88d0c9875a0b90
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9598ad7b14a1bbfb3ebd21f90fe1eb55454683653bdb0336d16fa0ddbc0fd33b
+oid sha256:3dd2e1f761a5703283541aef2eeade4dd37cc067c721190ff4ee0690c491491b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.3433947265148163,
   "best_model_checkpoint": "chickens-composite-201616161616-150-epochs-w-transform/checkpoint-33000",
-  "epoch": 69.0,
+  "epoch": 70.0,
   "eval_steps": 500,
-  "global_step": 34500,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9851,6 +9851,144 @@
       "eval_samples_per_second": 7.579,
       "eval_steps_per_second": 0.985,
       "step": 34500
+    },
+    {
+      "epoch": 69.06,
+      "grad_norm": 5.733088619308546e-05,
+      "learning_rate": 5.620432034152107e-06,
+      "loss": 0.4275,
+      "step": 34530
+    },
+    {
+      "epoch": 69.12,
+      "grad_norm": 51.50437927246094,
+      "learning_rate": 5.614196920735822e-06,
+      "loss": 0.4622,
+      "step": 34560
+    },
+    {
+      "epoch": 69.18,
+      "grad_norm": 38.773948669433594,
+      "learning_rate": 5.607960837418763e-06,
+      "loss": 0.4583,
+      "step": 34590
+    },
+    {
+      "epoch": 69.24,
+      "grad_norm": 43.785675048828125,
+      "learning_rate": 5.601723794048558e-06,
+      "loss": 0.4097,
+      "step": 34620
+    },
+    {
+      "epoch": 69.3,
+      "grad_norm": 45.26587677001953,
+      "learning_rate": 5.59548580047435e-06,
+      "loss": 0.4097,
+      "step": 34650
+    },
+    {
+      "epoch": 69.36,
+      "grad_norm": 28.66240882873535,
+      "learning_rate": 5.58924686654678e-06,
+      "loss": 0.4591,
+      "step": 34680
+    },
+    {
+      "epoch": 69.42,
+      "grad_norm": 43.78499984741211,
+      "learning_rate": 5.5830070021179785e-06,
+      "loss": 0.4095,
+      "step": 34710
+    },
+    {
+      "epoch": 69.48,
+      "grad_norm": 32.92940139770508,
+      "learning_rate": 5.576766217041541e-06,
+      "loss": 0.4634,
+      "step": 34740
+    },
+    {
+      "epoch": 69.54,
+      "grad_norm": 50.84819793701172,
+      "learning_rate": 5.570524521172523e-06,
+      "loss": 0.4746,
+      "step": 34770
+    },
+    {
+      "epoch": 69.6,
+      "grad_norm": 38.97684097290039,
+      "learning_rate": 5.5642819243674085e-06,
+      "loss": 0.3952,
+      "step": 34800
+    },
+    {
+      "epoch": 69.66,
+      "grad_norm": 100.71194458007812,
+      "learning_rate": 5.558038436484116e-06,
+      "loss": 0.4176,
+      "step": 34830
+    },
+    {
+      "epoch": 69.72,
+      "grad_norm": 33.512420654296875,
+      "learning_rate": 5.551794067381959e-06,
+      "loss": 0.4269,
+      "step": 34860
+    },
+    {
+      "epoch": 69.78,
+      "grad_norm": 54.8726692199707,
+      "learning_rate": 5.545548826921653e-06,
+      "loss": 0.3438,
+      "step": 34890
+    },
+    {
+      "epoch": 69.84,
+      "grad_norm": 0.00013334951654542238,
+      "learning_rate": 5.5393027249652844e-06,
+      "loss": 0.4642,
+      "step": 34920
+    },
+    {
+      "epoch": 69.9,
+      "grad_norm": 9.714184125186875e-05,
+      "learning_rate": 5.5330557713763e-06,
+      "loss": 0.3817,
+      "step": 34950
+    },
+    {
+      "epoch": 69.96,
+      "grad_norm": 55.636146545410156,
+      "learning_rate": 5.526807976019492e-06,
+      "loss": 0.4091,
+      "step": 34980
+    },
+    {
+      "epoch": 70.0,
+      "eval_loss": 0.3745727241039276,
+      "eval_map": 0.7332,
+      "eval_map_50": 0.9476,
+      "eval_map_75": 0.8716,
+      "eval_map_chicken": 0.7196,
+      "eval_map_duck": 0.6808,
+      "eval_map_large": 0.7409,
+      "eval_map_medium": 0.728,
+      "eval_map_plant": 0.7992,
+      "eval_map_small": 0.1368,
+      "eval_mar_1": 0.3026,
+      "eval_mar_10": 0.7781,
+      "eval_mar_100": 0.7825,
+      "eval_mar_100_chicken": 0.7726,
+      "eval_mar_100_duck": 0.7351,
+      "eval_mar_100_plant": 0.8397,
+      "eval_mar_large": 0.7993,
+      "eval_mar_medium": 0.7767,
+      "eval_mar_small": 0.2071,
+      "eval_runtime": 14.4354,
+      "eval_samples_per_second": 6.927,
+      "eval_steps_per_second": 0.901,
+      "step": 35000
     }
   ],
   "logging_steps": 30,
@@ -9870,7 +10008,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.18687973953536e+19,
+  "total_flos": 1.2040808951808e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null