Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36846934f00f1a43b88f2b423df5c7fb81d806bee717541a5c991361348e938
+oid sha256:23ec1a37f0f59fc6a05e9063f15da20a868ccbdb2dafe7ad28de654b4c53e73d
 size 198011252

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff53100a06c7d9ec5de5d4d36860f8b452a856e09537e514ef940c12752dcb0
+oid sha256:facf61e19608174386a390900e13d0aa47506868d94138ed8774a017c650c68e
 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": 0.037091988130563795,
+  "epoch": 0.07418397626112759,
   "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": 30.608,
       "eval_steps_per_second": 7.652,
       "step": 50
+    },
+    {
+      "epoch": 0.04451038575667656,
+      "grad_norm": NaN,
+      "learning_rate": 6.992307692307692e-06,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.05192878338278932,
+      "grad_norm": NaN,
+      "learning_rate": 6.215384615384615e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.05934718100890208,
+      "grad_norm": NaN,
+      "learning_rate": 5.438461538461538e-06,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.06676557863501484,
+      "grad_norm": NaN,
+      "learning_rate": 4.661538461538462e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.07418397626112759,
+      "grad_norm": NaN,
+      "learning_rate": 3.884615384615385e-06,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.07418397626112759,
+      "eval_loss": NaN,
+      "eval_runtime": 18.5563,
+      "eval_samples_per_second": 30.61,
+      "eval_steps_per_second": 7.652,
+      "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": 7166368520601600.0,
+  "total_flos": 1.43327370412032e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null