Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1cf31a0084088a2454ac94f16b348dc89c60b1d770327297de89b54414138f
+oid sha256:361ea9c27136638fc65e2fd4a45ef475f4dd8019914b17050dae329c9c627e0a
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:072dac4e0a9ecd235187a407b340fbe8f18ed468e3b4bfb65ea55a982068dca5
+oid sha256:e0f5c94f1ae113a89a884bbeefacf68a222bd5d64c0a63a32c87b39031ac9ecb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152cf5e1f9adf3dc2c608dbb3e394e09940ab42688cdb5a07d89f1cccb7f89a5
+oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.04409171075837742,
+  "epoch": 0.08818342151675485,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 19.516,
       "eval_steps_per_second": 4.899,
       "step": 50
+    },
+    {
+      "epoch": 0.05291005291005291,
+      "grad_norm": NaN,
+      "learning_rate": 6.992307692307692e-06,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": NaN,
+      "learning_rate": 6.215384615384615e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.07054673721340388,
+      "grad_norm": NaN,
+      "learning_rate": 5.438461538461538e-06,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.07936507936507936,
+      "grad_norm": NaN,
+      "learning_rate": 4.661538461538462e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.08818342151675485,
+      "grad_norm": NaN,
+      "learning_rate": 3.884615384615385e-06,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.08818342151675485,
+      "eval_loss": NaN,
+      "eval_runtime": 24.5008,
+      "eval_samples_per_second": 19.51,
+      "eval_steps_per_second": 4.898,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.78874751123456e+16,
+  "total_flos": 3.57749502246912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null