Training in progress, step 150, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68930c58fce51d88a4b2b15bfcffc20cb8fbfb74f8d06364ec15ff69a6ef79c8
+oid sha256:0618f2eb07d300b9fc05ae2a5365b257f61c4852bd74184e7fd4757f0162d463
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b90f23af62305ba960d6f3da9c8fe5215a78ee5d6503478786db71489b3f020
+oid sha256:a1851c1fda208f0b8fdd03141a67662302756abf898fa5ad966b0637bc8b07cb
 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": 0.05393743257820928,
+  "epoch": 0.08090614886731391,
   "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": 59.225,
       "eval_steps_per_second": 14.863,
       "step": 100
+    },
+    {
+      "epoch": 0.0593311758360302,
+      "grad_norm": NaN,
+      "learning_rate": 3.1076923076923076e-06,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": NaN,
+      "learning_rate": 2.330769230769231e-06,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.07011866235167206,
+      "grad_norm": NaN,
+      "learning_rate": 1.5538461538461538e-06,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.07551240560949299,
+      "grad_norm": NaN,
+      "learning_rate": 7.769230769230769e-07,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.08090614886731391,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.08090614886731391,
+      "eval_loss": NaN,
+      "eval_runtime": 13.194,
+      "eval_samples_per_second": 59.194,
+      "eval_steps_per_second": 14.855,
+      "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": 5054876362997760.0,
+  "total_flos": 7557290404085760.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null