Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e9ba1929ee972b77bcd72d468a37fe2ae415207ef7e59323b5fbe61463f4e4
+oid sha256:daaff03669a032b7c022a482789b2f3c995b01f72ad79b3cc8068b8f1e434c60
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af29e74f68512be973befebf6448552f1b28a5dcab1e75907db8bfa13fa2ff3
+oid sha256:3c0ce3f9ee64b0c869751a3b334d7eed8318d1c81a574dbeacadb98868be199f
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab3d18275216c730a64e666d0a0b15c9be1210bce446ef49cbf8dbc3a28973b2
+oid sha256:8a5b7fc8ba333afed8a1a8bd04eb95e00d2bd168f67ada07b2962cd70cb734ce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a64b03d0773f91f522e81c4f703747e71530a9ddde23207251d238f2ace6db2
+oid sha256:02db3dbfb390a8f0700b2ea5550de43719bf1ee696229ad5e263b02923655626
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.30838942527771,
   "best_model_checkpoint": "miner_id_24/checkpoint-500",
-  "epoch": 0.06826404532732609,
+  "epoch": 0.08191685439279131,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,28 @@
       "eval_samples_per_second": 35.116,
       "eval_steps_per_second": 8.779,
       "step": 500
+    },
+    {
+      "epoch": 0.07509044986005871,
+      "grad_norm": 115.34134674072266,
+      "learning_rate": 0.00025,
+      "loss": 8.8665,
+      "step": 550
+    },
+    {
+      "epoch": 0.08191685439279131,
+      "grad_norm": 85.31719207763672,
+      "learning_rate": 0.00025,
+      "loss": 9.0255,
+      "step": 600
+    },
+    {
+      "epoch": 0.08191685439279131,
+      "eval_loss": 2.3584725856781006,
+      "eval_runtime": 175.5365,
+      "eval_samples_per_second": 35.138,
+      "eval_steps_per_second": 8.784,
+      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -139,7 +161,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -153,7 +175,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.76813166821376e+17,
+  "total_flos": 2.121758001856512e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null