Training in progress, epoch 150, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7aa24f0dac48e205c83eb7ea76da5d152bc8bb1192459297bc7bb540f56eb69
+oid sha256:eb11c17e7dde9d73270107d795749e28efd59c4ab5c621578c9356a83f3aa86c
 size 166496880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ec08a7251d93dc8eb88acf8f1fa5b8f1143c54698f9f4788304288be1b35fe
+oid sha256:43579d5b9bffd05f689acc0413af950c5e356541beb78a02919b7c9eae61f35d
 size 330495866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a396222dff59b097bed0889ab42f3d144ca156561494a7c8362451cc383f6f2
+oid sha256:37ba61eb21dd151ab9b4feb5d400cf275fed96c693759a03f3af4b2aaa247d58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d97cfcad85d9182f57a6d2bdf768ab9899061715a0c3f6d191db6d91a27ccfef
+oid sha256:96205cabb1588b7cd4f382979691c79dabb654b1f45a221ef5567a570af3df90
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.22317980229854584,
   "best_model_checkpoint": "chickens-composite-8044444-150-epochs-wo-transform-metrics-test/checkpoint-59500",
-  "epoch": 149.0,
+  "epoch": 150.0,
   "eval_steps": 500,
-  "global_step": 74500,
+  "global_step": 75000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21262,6 +21262,151 @@
       "eval_samples_per_second": 16.282,
       "eval_steps_per_second": 2.117,
       "step": 74500
+    },
+    {
+      "epoch": 149.04,
+      "grad_norm": 224.63658142089844,
+      "learning_rate": 1.0106134441850712e-09,
+      "loss": 0.2104,
+      "step": 74520
+    },
+    {
+      "epoch": 149.1,
+      "grad_norm": 44.2706298828125,
+      "learning_rate": 8.88238095955174e-10,
+      "loss": 0.1973,
+      "step": 74550
+    },
+    {
+      "epoch": 149.16,
+      "grad_norm": 99.53861236572266,
+      "learning_rate": 7.737570275573314e-10,
+      "loss": 0.2129,
+      "step": 74580
+    },
+    {
+      "epoch": 149.22,
+      "grad_norm": 96.69844818115234,
+      "learning_rate": 6.671704197735995e-10,
+      "loss": 0.2126,
+      "step": 74610
+    },
+    {
+      "epoch": 149.28,
+      "grad_norm": 65.76350402832031,
+      "learning_rate": 5.684784409182298e-10,
+      "loss": 0.2165,
+      "step": 74640
+    },
+    {
+      "epoch": 149.34,
+      "grad_norm": 58.61651611328125,
+      "learning_rate": 4.776812468398895e-10,
+      "loss": 0.2249,
+      "step": 74670
+    },
+    {
+      "epoch": 149.4,
+      "grad_norm": 48.4800910949707,
+      "learning_rate": 3.9477898091944135e-10,
+      "loss": 0.2079,
+      "step": 74700
+    },
+    {
+      "epoch": 149.46,
+      "grad_norm": 25.470163345336914,
+      "learning_rate": 3.1977177407105376e-10,
+      "loss": 0.2202,
+      "step": 74730
+    },
+    {
+      "epoch": 149.52,
+      "grad_norm": 46.69743347167969,
+      "learning_rate": 2.5265974474109054e-10,
+      "loss": 0.1829,
+      "step": 74760
+    },
+    {
+      "epoch": 149.58,
+      "grad_norm": 128.72329711914062,
+      "learning_rate": 1.9344299890866614e-10,
+      "loss": 0.2119,
+      "step": 74790
+    },
+    {
+      "epoch": 149.64,
+      "grad_norm": 34.3425407409668,
+      "learning_rate": 1.4212163008509028e-10,
+      "loss": 0.2146,
+      "step": 74820
+    },
+    {
+      "epoch": 149.7,
+      "grad_norm": 42.00620651245117,
+      "learning_rate": 9.869571931442334e-11,
+      "loss": 0.1972,
+      "step": 74850
+    },
+    {
+      "epoch": 149.76,
+      "grad_norm": 41.06703186035156,
+      "learning_rate": 6.316533517125578e-11,
+      "loss": 0.2033,
+      "step": 74880
+    },
+    {
+      "epoch": 149.82,
+      "grad_norm": 32.280738830566406,
+      "learning_rate": 3.55305337634837e-11,
+      "loss": 0.1933,
+      "step": 74910
+    },
+    {
+      "epoch": 149.88,
+      "grad_norm": 37.603878021240234,
+      "learning_rate": 1.57913587295333e-11,
+      "loss": 0.2181,
+      "step": 74940
+    },
+    {
+      "epoch": 149.94,
+      "grad_norm": 42.75212860107422,
+      "learning_rate": 3.947841241136452e-12,
+      "loss": 0.2386,
+      "step": 74970
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 43.60305404663086,
+      "learning_rate": 0.0,
+      "loss": 0.2152,
+      "step": 75000
+    },
+    {
+      "epoch": 150.0,
+      "eval_loss": 0.22922895848751068,
+      "eval_map": 0.8325,
+      "eval_map_50": 0.9667,
+      "eval_map_75": 0.9216,
+      "eval_map_chicken": 0.821,
+      "eval_map_duck": 0.7881,
+      "eval_map_large": 0.8697,
+      "eval_map_medium": 0.8475,
+      "eval_map_plant": 0.8885,
+      "eval_map_small": 0.3829,
+      "eval_mar_1": 0.3088,
+      "eval_mar_10": 0.862,
+      "eval_mar_100": 0.8694,
+      "eval_mar_100_chicken": 0.8702,
+      "eval_mar_100_duck": 0.8196,
+      "eval_mar_100_plant": 0.9185,
+      "eval_mar_large": 0.898,
+      "eval_mar_medium": 0.8815,
+      "eval_mar_small": 0.4616,
+      "eval_runtime": 6.4295,
+      "eval_samples_per_second": 15.553,
+      "eval_steps_per_second": 2.022,
+      "step": 75000
     }
   ],
   "logging_steps": 30,
@@ -21276,12 +21421,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.56297219117056e+19,
+  "total_flos": 2.580173346816e+19,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null