Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bbea9b407f1121a8661982d3e2dc79bdbfa42a319f3e1835bb8e6cdaf85b197
+oid sha256:c6414b8d3ed35cad75df38d7ad2a5651e4cb42985ba6db4f38e73824b94237a2
 size 75471860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0660e7456eb0aeaa731586d4d7110e16bcfa1f88b8398c6f0a54d6290e97b3b6
+oid sha256:e3cb4f40c7f153a59f76cb404afb2420c55ec5869a7e776cfe72b6c7d21bf11f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9421260ddc1f7ea3f664c77307a6e5b30037afc5a204c347c827fe3227c8b77
+oid sha256:f7e9f0c2a27af03f3c1874438820d046de94b36aaec3b0cc778f96def4616314
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.05989817310572028,
+  "epoch": 0.11979634621144056,
   "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": 39.525,
       "eval_steps_per_second": 19.791,
       "step": 50
+    },
+    {
+      "epoch": 0.09583707696915245,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.11979634621144056,
+      "eval_loss": NaN,
+      "eval_runtime": 17.5398,
+      "eval_samples_per_second": 40.08,
+      "eval_steps_per_second": 20.069,
+      "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": 3311051105894400.0,
+  "total_flos": 6622102211788800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null