Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028d308d2b2975c71a859c1db9eec7b73b4e60cf2d64c6ed4ab844b74612c0e0
+oid sha256:6b184ddf78308c9a0062bdd4ac2aea71dbb59614141f7e670c55eb12205bfd32
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9ffc7737d4f9bb687d2342d640e3f10d15c7b8587c8f6af1a14522dd3f4428
+oid sha256:a792fe7db85f3b298cce69bb327e8b154601ef7fc807d1fa65f61417691df8ad
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5260c8125a24537a0b9406dcd050daa45aa08666d31e6a0297dc30b84741333
+oid sha256:f2b8943e674f8bbdced045cb2530ea33584297335f08ea6bc4a911f482fdfb11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa1bfb19ac7a71e5a662427e7488d4a4d957109537750c19fd28e94a30346c50
+oid sha256:96aa36799c943a9bfefa20f32f650908880b1404c454cf725bf5d9ee2c75343e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.35316547751426697,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.087527352297593,
+  "epoch": 0.13129102844638948,
   "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": 9.928,
       "eval_steps_per_second": 2.497,
       "step": 100
+    },
+    {
+      "epoch": 0.0962800875273523,
+      "grad_norm": 0.5827049612998962,
+      "learning_rate": 0.0002018790457812944,
+      "loss": 0.8235,
+      "step": 110
+    },
+    {
+      "epoch": 0.1050328227571116,
+      "grad_norm": 0.36756134033203125,
+      "learning_rate": 0.0001986509710466168,
+      "loss": 0.6406,
+      "step": 120
+    },
+    {
+      "epoch": 0.1137855579868709,
+      "grad_norm": 0.10399194061756134,
+      "learning_rate": 0.00019496907414450293,
+      "loss": 0.1631,
+      "step": 130
+    },
+    {
+      "epoch": 0.12253829321663019,
+      "grad_norm": 0.05342819169163704,
+      "learning_rate": 0.00019085129290655697,
+      "loss": 0.0033,
+      "step": 140
+    },
+    {
+      "epoch": 0.13129102844638948,
+      "grad_norm": 0.01769879087805748,
+      "learning_rate": 0.00018631768874905217,
+      "loss": 0.001,
+      "step": 150
+    },
+    {
+      "epoch": 0.13129102844638948,
+      "eval_loss": 0.3601878583431244,
+      "eval_runtime": 48.1446,
+      "eval_samples_per_second": 9.991,
+      "eval_steps_per_second": 2.513,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.252570367721472e+16,
+  "total_flos": 4.905515964432384e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null