Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13822c8f7b8fcc8dfa686dce024d56008178163b6068f7214df483790ac2760d
+oid sha256:d3fe894616f5a0a2ffcec317fc90ef622fb7ab3b320f3597213d77d8e8dc7614
 size 103716484

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa794c9ee865a2d0381358ab301e946d055d76d1bef5d826e3cf1b691a170cf
+oid sha256:6197beae849ae6988a056379e03435ac30956e087d38a5e1c1ebe11fac8f0baf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0a47cc675a5d4ba5fe8c0d42564476e1fe842799977ab67bf2a8317adef53f
+oid sha256:5b782a524e5b57eb023365370accae538ac5e68454bafa53a6dd8b2c51cead56
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.14432617716038246,
+  "epoch": 0.1804077214504781,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -327,6 +327,84 @@
       "eval_samples_per_second": 23.644,
       "eval_steps_per_second": 5.911,
       "step": 400
+    },
+    {
+      "epoch": 0.14793433158939204,
+      "grad_norm": 0.0,
+      "learning_rate": 4.695790918802576e-05,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.1515424860184016,
+      "grad_norm": 0.0,
+      "learning_rate": 4.252125897855932e-05,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.15515064044741114,
+      "grad_norm": 0.0,
+      "learning_rate": 3.824753850538082e-05,
+      "loss": 0.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.15875879487642072,
+      "grad_norm": 0.0,
+      "learning_rate": 3.414886209349615e-05,
+      "loss": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.16236694930543027,
+      "grad_norm": 0.0,
+      "learning_rate": 3.0236847886501542e-05,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.16597510373443983,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 0.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.1695832581634494,
+      "grad_norm": 0.0,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 0.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.17319141259245896,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 0.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.1767995670214685,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 0.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.1804077214504781,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.1804077214504781,
+      "eval_loss": NaN,
+      "eval_runtime": 197.1433,
+      "eval_samples_per_second": 23.678,
+      "eval_steps_per_second": 5.92,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -341,7 +419,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 4
       }
     },
     "TrainerControl": {
@@ -355,7 +433,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.65414936363008e+17,
+  "total_flos": 3.3176867045376e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null