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:fa1344b0e95a0967cf070a979f420ba519d227f0b1ee7f0ef2d8f0a983c33a19
+oid sha256:f867d73a1a28bc05d4a0d26284f369667dc00e712c365434e7a2d3da3c2f8a79
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03fa58e010f7b9af7b49785d41ef310f86315539227b23afbfbca613c1a2d728
+oid sha256:639787d9f2ec51cd393f5f1173e6d977f245d47c27192eb1365da20c845a6d8b
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e68bcc2fd844f5c66f96facda8d6a4a996996e77152128e133a8df8e92cc891
+oid sha256:91db5e182392cc56bd90e233c5b4cf215294e7e16e74dc351dd54b04a6f0b448
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7c1078eb5a1a7c3016e3bc1b27b5075c61ea30d4750bf448abc31716e92a9c
+oid sha256:1164ae497156bc73ad6aea2c09c8b9bf103d80abc111b82a8d3df6753edffe06
 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": 88.06,
       "eval_steps_per_second": 22.015,
       "step": 150
+    },
+    {
+      "epoch": 0.02184896900177523,
+      "grad_norm": 0.00021085802291054279,
+      "learning_rate": 0.00017709199943488106,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.02321452956438618,
+      "grad_norm": 0.00017776116146706045,
+      "learning_rate": 0.00017192045245496238,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.024580090126997134,
+      "grad_norm": 7.381874456768855e-05,
+      "learning_rate": 0.00016641313195854277,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.025945650689608083,
+      "grad_norm": 0.0005210270173847675,
+      "learning_rate": 0.0001605968690574869,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.027311211252219036,
+      "grad_norm": 0.0003010142536368221,
+      "learning_rate": 0.0001545,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.027311211252219036,
+      "eval_loss": 11.5,
+      "eval_runtime": 35.0475,
+      "eval_samples_per_second": 87.995,
+      "eval_steps_per_second": 21.999,
+      "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": 5296205758464.0,
+  "total_flos": 7101503766528.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null