Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb19aac7ef984d7e44a6233f0c5e6a424b5312f03e657a9e6557d70929c284d
+oid sha256:20bd2b367d0321db00eff6c5e2e74d125d158469b25dcdbae7ec9015e44098e8
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd234be897e177d3710b3c84c9de610a4a1790316ed65887e8a717dff6f48104
+oid sha256:5e07d56c4e4cd7bc38a0f79b9c257290d524e255ad0fa683e8b16b43d1c256a6
 size 1324282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe3e27de9842c68ada3445a07d3149baffe34848ad77f4e3818d2e8813c7371
+oid sha256:87af8c36557c1ff4530edcba1720f7836195d70b35bc70a7a5c483f2635b2010
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
+oid sha256:673699a33c258fc5668f5919a0c3d2b61b77874f7dbb4fb806a02e77a15f3cef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.848329544067383,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.24200053777897285,
+  "epoch": 0.26888948642108096,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 75.231,
       "eval_steps_per_second": 18.832,
       "step": 450
+    },
+    {
+      "epoch": 0.24737832750739447,
+      "grad_norm": 0.16334249079227448,
+      "learning_rate": 3.893199558198952e-06,
+      "loss": 11.8567,
+      "step": 460
+    },
+    {
+      "epoch": 0.2527561172358161,
+      "grad_norm": 0.12637721002101898,
+      "learning_rate": 2.1961661262525285e-06,
+      "loss": 11.8522,
+      "step": 470
+    },
+    {
+      "epoch": 0.2581339069642377,
+      "grad_norm": 0.14183366298675537,
+      "learning_rate": 9.780590914721787e-07,
+      "loss": 11.8507,
+      "step": 480
+    },
+    {
+      "epoch": 0.26351169669265934,
+      "grad_norm": 0.1395043432712555,
+      "learning_rate": 2.4481294888766817e-07,
+      "loss": 11.8474,
+      "step": 490
+    },
+    {
+      "epoch": 0.26888948642108096,
+      "grad_norm": 0.1393822580575943,
+      "learning_rate": 0.0,
+      "loss": 11.8383,
+      "step": 500
+    },
+    {
+      "epoch": 0.26888948642108096,
+      "eval_loss": 11.848384857177734,
+      "eval_runtime": 10.3824,
+      "eval_samples_per_second": 75.416,
+      "eval_steps_per_second": 18.878,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 57635916742656.0,
+  "total_flos": 63983484665856.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null