Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3e566f56f25d9835919b70a5dbe919c6c26ac4fba2092ecbd43cf48f69f4d7f
+oid sha256:d6c1337bd7851d89c3e3d46012a973367067ce07ef011966b6829c7de08a8cd2
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7fe744484ffb27cac02153474e1d16d40fdd2e37dfca4abc3a31a094f765be
+oid sha256:3672cf6ef73ccd708cc86b99114bed8e68f0f806baa2bbcc0b2574e44a120f99
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c179677d930132ddc61731675ff2de91bdddb6260f135e90a32e5388109f684
+oid sha256:5bda8c7741a8df07c9f7ee19efce756a9eff778140a03fe6222ef5adbe2847c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e3c543dd881d7b92b58f753c91bcd488f8269b3e4ffd67623431c55e782209
+oid sha256:8e4a64d71eed58bad723d1496b310be4dbd45cd96d8ef2f7cd1e195fe59bff7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0014698821154543406,
+  "epoch": 0.0019598428206057876,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 151.855,
       "eval_steps_per_second": 37.964,
       "step": 150
+    },
+    {
+      "epoch": 0.00156787425648463,
+      "grad_norm": 1.955423067556694e-05,
+      "learning_rate": 0.0001779516693350504,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.0016658663975149192,
+      "grad_norm": 4.4300071749603376e-05,
+      "learning_rate": 0.00017275501775814182,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.0017638585385452087,
+      "grad_norm": 9.80212862486951e-05,
+      "learning_rate": 0.00016722096269620562,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.001861850679575498,
+      "grad_norm": 5.2664123359136283e-05,
+      "learning_rate": 0.00016137646550922228,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "grad_norm": 0.00016968519776128232,
+      "learning_rate": 0.00015525,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "eval_loss": 11.5,
+      "eval_runtime": 283.4414,
+      "eval_samples_per_second": 151.594,
+      "eval_steps_per_second": 37.898,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3002180665344.0,
+  "total_flos": 4009556901888.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null