Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd11218273ee3053d63be73aa5789d16270e4374dc614764efe8b1b016a86559
+oid sha256:ced0aae4575f32da894f069a0689f8adfc695305a4161c3476b41484cbac0743
 size 103716100

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f332baa2d72fc2a56d128c8481794ccb6d37b1ba96d757403e140a254bc155
+oid sha256:4874bfff8f48f58dbeacd6424c17544ca4074af0f4864ca33e34f39221c537ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0051c53bcb92b7c913136d782f625b409707ede35cdcc9bbc83a63d788098e04
+oid sha256:d10d0fa96665f6b4af4824faec3d1d9f4e8b4343723a14d86cab932da6ce3225
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.036081544290095614,
+  "epoch": 0.07216308858019123,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 23.662,
       "eval_steps_per_second": 5.915,
       "step": 100
+    },
+    {
+      "epoch": 0.03968969871910518,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001861554081393806,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.04329785314811474,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001833313919082515,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.0469060075771243,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018027116379309638,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.050514162006133866,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017698339834299061,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.054122316435143425,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017347741508630672,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.057730470864152984,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001697631521134985,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.06133862529316255,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016585113790650388,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.06494677972217211,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001617524614946192,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.06855493415118168,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001574787410214407,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.07216308858019123,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015304209081197425,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.07216308858019123,
+      "eval_loss": NaN,
+      "eval_runtime": 197.0795,
+      "eval_samples_per_second": 23.686,
+      "eval_steps_per_second": 5.921,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -107,7 +185,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -121,7 +199,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.6353734090752e+16,
+  "total_flos": 1.32707468181504e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null