Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0081c90ffc4ba7dcfbce92cb0d12ce7c704347f2cafd3d533d4f98f8627b07b5
+oid sha256:6a7eca6b3cf102bafc5cdda02c684de85bb85ca5d92cc42494e737b32e051cf3
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ca59dde8a69567bf35fbfa7a1599aa35b7d9a58e9024e411eef030f7f44e4c
+oid sha256:a12d4a193d96e2e0d0064a9188ab3d14d58bf415fc516b9ac9e08307e43b0d9c
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8521eb5d5bfac317787fe4384c658a815f854ede64df988fdc985a1e182012
+oid sha256:0e14b1eb85d0d3d024790a2cd09103206710e027e8e5f401eba239f194aaa8b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b96469db93d698ee2179ef5118ada6cd19a5d64b9fa51e2e13a417bf8f9992f2
+oid sha256:20b846236f686f34a315088700cd866bd66ffc165610b7eec245275ac6103428
 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": 151.482,
       "eval_steps_per_second": 37.87,
       "step": 150
+    },
+    {
+      "epoch": 0.00156787425648463,
+      "grad_norm": 4.491434810915962e-05,
+      "learning_rate": 0.00018396935863623567,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.0016658663975149192,
+      "grad_norm": 3.40402293659281e-05,
+      "learning_rate": 0.00017859697488039784,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.0017638585385452087,
+      "grad_norm": 5.6449909607181326e-05,
+      "learning_rate": 0.00017287577785984542,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.001861850679575498,
+      "grad_norm": 7.428977551171556e-05,
+      "learning_rate": 0.0001668336406713699,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "grad_norm": 0.00018914949032478034,
+      "learning_rate": 0.0001605,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "eval_loss": 11.5,
+      "eval_runtime": 283.6858,
+      "eval_samples_per_second": 151.463,
+      "eval_steps_per_second": 37.866,
+      "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": 3012154687488.0,
+  "total_flos": 4019530924032.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null