Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad7c8da8f869e90bb6529bf734b6265d18e2532c4520ce34a20e94c828ace670
+oid sha256:9c368c0c5fecd655ca2c7e9d4ef21c5d20ccfba1f9bf8bbf57bc131823b6c1bd
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f744d33f60c81fcec6846e333b71636ca5a1246ae19f920fc5d5493ebf229da
+oid sha256:a6d026ec642652df4b233580d2a80471ee7146a3c3b08072ad67ec204cb00fcd
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c34eaffeb97d16d7d5fc3f58d34117373e21f932c97684c4f93e8476b32271d1
+oid sha256:8dacb351634cadf8731b37769aa65f8d189619347a642a1e44a84b8345b1b587
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8c70a94900d9b287ae32cb4f95d47fb8ad712363557219eb89e270f8b96010
+oid sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.1065056249499321,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.2176278563656148,
+  "epoch": 0.24483133841131666,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 5.932,
       "eval_steps_per_second": 1.487,
       "step": 400
+    },
+    {
+      "epoch": 0.22306855277475518,
+      "grad_norm": 0.11437083035707474,
+      "learning_rate": 2.005321559063053e-05,
+      "loss": 0.0697,
+      "step": 410
+    },
+    {
+      "epoch": 0.22850924918389554,
+      "grad_norm": 0.10665331780910492,
+      "learning_rate": 1.5954949903575276e-05,
+      "loss": 0.0688,
+      "step": 420
+    },
+    {
+      "epoch": 0.23394994559303592,
+      "grad_norm": 0.27620697021484375,
+      "learning_rate": 1.2290502749812666e-05,
+      "loss": 0.1334,
+      "step": 430
+    },
+    {
+      "epoch": 0.23939064200217627,
+      "grad_norm": 0.16248451173305511,
+      "learning_rate": 9.077726947526898e-06,
+      "loss": 0.1574,
+      "step": 440
+    },
+    {
+      "epoch": 0.24483133841131666,
+      "grad_norm": 0.19599585235118866,
+      "learning_rate": 6.332274817479627e-06,
+      "loss": 0.1893,
+      "step": 450
+    },
+    {
+      "epoch": 0.24483133841131666,
+      "eval_loss": 0.10668922960758209,
+      "eval_runtime": 65.667,
+      "eval_samples_per_second": 5.893,
+      "eval_steps_per_second": 1.477,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -373,7 +416,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0473242014777344e+17,
+  "total_flos": 1.2083271532806144e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null