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:b76192e62f55c2240c494f243079f015ae894ea30d7ba15e6369f549cc9a44a1
+oid sha256:ce963fa7f6df1eaecd186e0bae81e62163112896b60fabd05683ec210c2bcc92
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e19f4fcd65f81b30eb91b114c2dc19409927b56b6f5a09752cad885f7ae06a04
+oid sha256:9be0408cb69f3454734b2b62ac0eb0a240bb845b5bc88a5a725a5f3c84f72fd4
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cbf89dc20b129b3d09728afa92ac0c4ecb17713a05600da13e1eb29d6b78396
+oid sha256:0d6d52f14069d471ff4c557520cab5f7d12dcbaa73d56c3c2466fedfacccb7b6
 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": 0.020483408439164276,
+  "epoch": 0.027311211252219036,
   "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": 87.711,
       "eval_steps_per_second": 21.928,
       "step": 150
+    },
+    {
+      "epoch": 0.02184896900177523,
+      "grad_norm": 9.578291792422533e-05,
+      "learning_rate": 0.00018396935863623567,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.02321452956438618,
+      "grad_norm": 0.00012365143629722297,
+      "learning_rate": 0.00017859697488039784,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.024580090126997134,
+      "grad_norm": 3.514682612149045e-05,
+      "learning_rate": 0.00017287577785984542,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.025945650689608083,
+      "grad_norm": 0.0001229763583978638,
+      "learning_rate": 0.0001668336406713699,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.027311211252219036,
+      "grad_norm": 0.00010852934065042064,
+      "learning_rate": 0.0001605,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.027311211252219036,
+      "eval_loss": 11.5,
+      "eval_runtime": 35.0986,
+      "eval_samples_per_second": 87.867,
+      "eval_steps_per_second": 21.967,
+      "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": 5306179780608.0,
+  "total_flos": 7111477788672.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null