Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa88daf97c624e3ca97a7f74c66e496ec848fb50121eebad9dd06356669e16a5
+oid sha256:d25476df6e2de9fe2e30cc72546495e8c2cf8580a9f9126cd2a1b53d4caaa685
 size 294753940

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839f5feb6bec8bb1299de663912874684658e3407d13b5f8a3dd11d3dd37a5a6
+oid sha256:5fff0db1c0c3f5d850eadae4f8eab4641ae945a67656ea86617217f45866f728
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9421260ddc1f7ea3f664c77307a6e5b30037afc5a204c347c827fe3227c8b77
+oid sha256:fa172a67b17733f4f4576524fa7afa573b19fcbf0bf4ea9f180757ed71fc81e7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.018902698360190918,
+  "epoch": 0.037805396720381836,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 8.996,
       "eval_steps_per_second": 4.498,
       "step": 50
+    },
+    {
+      "epoch": 0.03024431737630547,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.037805396720381836,
+      "eval_loss": NaN,
+      "eval_runtime": 248.6322,
+      "eval_samples_per_second": 8.961,
+      "eval_steps_per_second": 4.481,
+      "step": 100
     }
   ],
   "logging_steps": 40,
@@ -44,7 +59,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -58,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2817493064024064e+16,
+  "total_flos": 6.55533505731625e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null