Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a1786e7ac229da48fb4912b2f0f2bc74971d41b7345e8e04f6b684e8a1c41f
+oid sha256:c9f0db7ef55411d6f1f51f0d711849a26eaac16055651f8a41942133ec7a5cd6
 size 139313234

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835706e2a839abe4c467d46fa9b82669b706f8db1ec8ccbfb61ec2d63ba1e3be
+oid sha256:d1896e726ea618bfe6cef8eb4da9b3414c4f91428549ebd60ee23b2836be50d0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f46d1866da75894bb192904d9336f5b7bceb9ce2edba740a228cea4104230bd
+oid sha256:121d0daaf1acb5819977fc9ac057545cfc4b11763f09d7c2a5ed9ce4c5dea9b0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fff97328081b55e1cfa2db4e8deb8e3b68f1c2df921852c4bd3f09067dbf45f
+oid sha256:01261bdf0e73ba818430e2478fa7c4f2bb0b856228c0a911f69b7051bd0e8d4b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1236e9838ace6e62dc62947277686c85717a90df611e241d6e2f5d0d9f3619b2
+oid sha256:cc434a8a918ae1e5aadc9c7a055810b2eebb97503c75bd5a33839c178c3de3a8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d490043b81d92f2523c5e5743bd899586cd05324668f1c6287fc78466d4341
+oid sha256:83bde02f2e7b736ca94b9c51f0320881be685bc5601886de1775bb4eb0e0862b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.141361256544503,
+  "epoch": 3.086387434554974,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,83 @@
       "eval_samples_per_second": 28.301,
       "eval_steps_per_second": 7.358,
       "step": 25
+    },
+    {
+      "epoch": 2.225130890052356,
+      "grad_norm": NaN,
+      "learning_rate": 2.7881441362933468e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.3089005235602094,
+      "grad_norm": NaN,
+      "learning_rate": 2.4683696035904928e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.392670157068063,
+      "grad_norm": NaN,
+      "learning_rate": 2.1744598725070347e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.4764397905759163,
+      "grad_norm": NaN,
+      "learning_rate": 1.9089224772389225e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.5602094240837694,
+      "grad_norm": NaN,
+      "learning_rate": 1.674022889216737e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.643979057591623,
+      "grad_norm": NaN,
+      "learning_rate": 1.4717651889022202e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.7277486910994764,
+      "grad_norm": NaN,
+      "learning_rate": 1.3038749676803994e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.81151832460733,
+      "grad_norm": NaN,
+      "learning_rate": 1.1717846057223144e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.8952879581151834,
+      "grad_norm": NaN,
+      "learning_rate": 1.076621051422442e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 3.0026178010471205,
+      "grad_norm": NaN,
+      "learning_rate": 1.019196206672345e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 3.086387434554974,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -221,12 +298,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.3054859280384e+16,
+  "total_flos": 1.879899736375296e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null