Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9485abd4a845b953b760780b52bf566eba363cae67aaeb4a1caed36245804b8b
+oid sha256:f4b019bc2c60a1a117b7764af1468f4a26966993d26e11b24715645e6e8bfd38
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e9e95d2545ef83ccc81b272bae7faed2f10eeb24dab86cf75499e1920af3d83
+oid sha256:783ea7b92cdbce3da4492609631c00fcecbc5693dbff363f5876fa5942b74c5c
 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:af8c70a94900d9b287ae32cb4f95d47fb8ad712363557219eb89e270f8b96010
+oid sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0803192853927612,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.27932960893854747,
+  "best_metric": 1.0729554891586304,
+  "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": 11.63,
       "eval_steps_per_second": 2.912,
       "step": 400
+    },
+    {
+      "epoch": 0.28631284916201116,
+      "grad_norm": 0.40684303641319275,
+      "learning_rate": 2.005321559063053e-05,
+      "loss": 0.8687,
+      "step": 410
+    },
+    {
+      "epoch": 0.29329608938547486,
+      "grad_norm": 0.3868181109428406,
+      "learning_rate": 1.5954949903575276e-05,
+      "loss": 0.7972,
+      "step": 420
+    },
+    {
+      "epoch": 0.30027932960893855,
+      "grad_norm": 0.415388286113739,
+      "learning_rate": 1.2290502749812666e-05,
+      "loss": 0.7463,
+      "step": 430
+    },
+    {
+      "epoch": 0.30726256983240224,
+      "grad_norm": 0.5129038095474243,
+      "learning_rate": 9.077726947526898e-06,
+      "loss": 0.8726,
+      "step": 440
+    },
+    {
+      "epoch": 0.31424581005586594,
+      "grad_norm": 1.1775633096694946,
+      "learning_rate": 6.332274817479627e-06,
+      "loss": 2.3677,
+      "step": 450
+    },
+    {
+      "epoch": 0.31424581005586594,
+      "eval_loss": 1.0729554891586304,
+      "eval_runtime": 51.7424,
+      "eval_samples_per_second": 11.654,
+      "eval_steps_per_second": 2.918,
+      "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