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:a615006941a0558bf913e17348dc6fa3d4df16ef1959cc50a79319d31978f35c
+oid sha256:8ae42795da762d57e91bc69f878cd228b0d33d8c7ddef1118343cb5abc278046
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4dea673febd15cb0b141b2cf743de292d642e6db8e761c85e2bc0af9ecaaae
+oid sha256:efdc647c3abc8dd079c58ddea42b3b9101a6889e4a73d8e5963e67058367b062
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b6ab54758d6c72638402e84fae2aad65a221b35640878ae19e43b4230eac2d
+oid sha256:bcd474099de92dc845d40d5927f170b424592df7fa8ed3e362e00c4d62a05861
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b43450b88475bcf098065f8f055f5a22625a79b35c329b2a2da0516bc5608f62
+oid sha256:ea278ffcc402f8731d694a21dbc5a96671a02299dc57c40b61a02431bc8aed26
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0796287059783936,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.27932960893854747,
+  "best_metric": 1.072546362876892,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.31424581005586594,
   "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": 11.683,
       "eval_steps_per_second": 2.926,
       "step": 400
+    },
+    {
+      "epoch": 0.28631284916201116,
+      "grad_norm": 0.40678611397743225,
+      "learning_rate": 2.0721656110318213e-05,
+      "loss": 0.8682,
+      "step": 410
+    },
+    {
+      "epoch": 0.29329608938547486,
+      "grad_norm": 0.38841360807418823,
+      "learning_rate": 1.6486781567027783e-05,
+      "loss": 0.797,
+      "step": 420
+    },
+    {
+      "epoch": 0.30027932960893855,
+      "grad_norm": 0.4177733361721039,
+      "learning_rate": 1.2700186174806422e-05,
+      "loss": 0.7461,
+      "step": 430
+    },
+    {
+      "epoch": 0.30726256983240224,
+      "grad_norm": 0.5100810527801514,
+      "learning_rate": 9.380317845777794e-06,
+      "loss": 0.8731,
+      "step": 440
+    },
+    {
+      "epoch": 0.31424581005586594,
+      "grad_norm": 1.1657980680465698,
+      "learning_rate": 6.543350644728947e-06,
+      "loss": 2.3673,
+      "step": 450
+    },
+    {
+      "epoch": 0.31424581005586594,
+      "eval_loss": 1.072546362876892,
+      "eval_runtime": 51.6984,
+      "eval_samples_per_second": 11.664,
+      "eval_steps_per_second": 2.921,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1268467831341056e+17,
+  "total_flos": 1.2681469712400384e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null