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:a3e9c60b2503f918950b9a646285fd56b4d0bc0d8cbe126431c8ce2285935dba
+oid sha256:981e2f97524bfa75644fbea7da5632973171be2d061136c796539feb8fd3fcb7
 size 72936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8212a2792235bfed3c3583e6b02b2eb8553aa1a8ce7f6ffc3852057a047861e
+oid sha256:baf556661f1bb9441f53bc29ab65de87ac0ce5c8c6cfa72632c9268ffb2d9912
 size 151106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6674ffdc21f0b79e5063878d8f5bc74d75dc80bb4833c4433d4d084fca87073e
+oid sha256:2374c0ca1ab6a3249a28a31b4796b7290ce35b072aa2dbfa12e964c378056c86
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
+oid sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 12.385225296020508,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.44798407167745147,
+  "epoch": 0.49776007964161273,
   "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": 53.069,
       "eval_steps_per_second": 13.299,
       "step": 450
+    },
+    {
+      "epoch": 0.4579392732702837,
+      "grad_norm": 0.07531358301639557,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 12.3937,
+      "step": 460
+    },
+    {
+      "epoch": 0.46789447486311597,
+      "grad_norm": 0.10366726666688919,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 12.3875,
+      "step": 470
+    },
+    {
+      "epoch": 0.4778496764559482,
+      "grad_norm": 0.10956410318613052,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 12.3875,
+      "step": 480
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.14846912026405334,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 12.3882,
+      "step": 490
+    },
+    {
+      "epoch": 0.49776007964161273,
+      "grad_norm": 0.4386281669139862,
+      "learning_rate": 0.0,
+      "loss": 12.3824,
+      "step": 500
+    },
+    {
+      "epoch": 0.49776007964161273,
+      "eval_loss": 12.385251998901367,
+      "eval_runtime": 8.0591,
+      "eval_samples_per_second": 52.487,
+      "eval_steps_per_second": 13.153,
+      "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": 216937267200.0,
+  "total_flos": 241041408000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null