Training in progress, step 150, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05860e7d6ab3c4042e0fec969abde0cc4477f38601f1d6407ebbd26770ad1ce
+oid sha256:88897aae948a7f1aa08a2b65863577cd1c611b91bf994f2be1f2746d1654a8f3
 size 61297812

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea920a7a47e5fbf8d353b6e7761af480cba34acd8e11fe7d521446efefb043c4
+oid sha256:8aaa29f442def983c1291d91388d8c8fdd7bfd52d12d6fef8e31698ba0d71810
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa172a67b17733f4f4576524fa7afa573b19fcbf0bf4ea9f180757ed71fc81e7
+oid sha256:321052ad5e93c8a107bd6c10f372f50285d863120fc0088befc39ec2733238fb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.018060729201941527,
+  "epoch": 0.027091093802912292,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 37.351,
       "eval_steps_per_second": 18.68,
       "step": 100
+    },
+    {
+      "epoch": 0.021672875042329835,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.027091093802912292,
+      "eval_loss": NaN,
+      "eval_runtime": 118.5263,
+      "eval_samples_per_second": 39.341,
+      "eval_steps_per_second": 19.675,
+      "step": 150
     }
   ],
   "logging_steps": 40,
@@ -59,7 +74,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -73,7 +88,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6438273417216000.0,
+  "total_flos": 9657410125824000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null