Training in progress, step 150, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ec1a37f0f59fc6a05e9063f15da20a868ccbdb2dafe7ad28de654b4c53e73d
+oid sha256:df1d64c2b7e78cccf52b8fd89561794311c736dd0cf71c94f48717db83624eea
 size 198011252

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:facf61e19608174386a390900e13d0aa47506868d94138ed8774a017c650c68e
+oid sha256:a4eb8a76209844dfdef21bb4b3fbf751bdb9e3846d711e505846df0ae8a9458b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
+oid sha256:7e45926e8bb4228c69b4b56f6b51f1445c0aeb3fb7bb09ed84764ec2b4c3a8ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.07418397626112759,
+  "epoch": 0.11127596439169139,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 30.61,
       "eval_steps_per_second": 7.652,
       "step": 100
+    },
+    {
+      "epoch": 0.08160237388724036,
+      "grad_norm": NaN,
+      "learning_rate": 3.1076923076923076e-06,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.08902077151335312,
+      "grad_norm": NaN,
+      "learning_rate": 2.330769230769231e-06,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.09643916913946587,
+      "grad_norm": NaN,
+      "learning_rate": 1.5538461538461538e-06,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.10385756676557864,
+      "grad_norm": NaN,
+      "learning_rate": 7.769230769230769e-07,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.11127596439169139,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.11127596439169139,
+      "eval_loss": NaN,
+      "eval_runtime": 18.5754,
+      "eval_samples_per_second": 30.578,
+      "eval_steps_per_second": 7.645,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -124,12 +167,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.43327370412032e+16,
+  "total_flos": 2.14991055618048e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null