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:a896b28d2c48c3038c46acff9fd46a341522fec135f1005a6c82554746baa800
+oid sha256:d5cfe19eb578c5e36e98e3a553a3f58f13be5a6b5e7834e6cb540901e6eef548
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a978c39dc4fa51df42c10a3bbc2b948e39c507366c9f3ff2b77f2e3d01026af
+oid sha256:f987f6fd78f5694f4f2fea6fd17ab10f96dbf9e37025ec5e5bdfb4a5843b4a33
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c1f8c7575b19820685f295b8909f2be86a865c8795f90be7d5d672983652f7
+oid sha256:131047f8afdb4f57f098afb2a3ed1d93cc409cc90a986978ed3ae1808be20a82
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f83d259563f490ff1ff7e4916ac178dc618734e66d8ea8288665df23ceab41
+oid sha256:5fa0f7e2faaa98aa485e5dc42922e1b1819381507fa6961c3be50a0b49af04c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2847579717636108,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.018821757952192736,
+  "best_metric": 1.2806880474090576,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.021174477696216828,
   "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": 8.501,
       "eval_steps_per_second": 2.126,
       "step": 400
+    },
+    {
+      "epoch": 0.019292301900997552,
+      "grad_norm": 0.3955267369747162,
+      "learning_rate": 2.024419859625558e-05,
+      "loss": 1.9078,
+      "step": 410
+    },
+    {
+      "epoch": 0.019762845849802372,
+      "grad_norm": 0.4896032512187958,
+      "learning_rate": 1.610690180741885e-05,
+      "loss": 2.5107,
+      "step": 420
+    },
+    {
+      "epoch": 0.020233389798607188,
+      "grad_norm": 0.688621461391449,
+      "learning_rate": 1.240755515695374e-05,
+      "loss": 3.0001,
+      "step": 430
+    },
+    {
+      "epoch": 0.020703933747412008,
+      "grad_norm": 0.7938734292984009,
+      "learning_rate": 9.164181489884296e-06,
+      "loss": 2.5139,
+      "step": 440
+    },
+    {
+      "epoch": 0.021174477696216828,
+      "grad_norm": 1.0540862083435059,
+      "learning_rate": 6.392582196693718e-06,
+      "loss": 2.7921,
+      "step": 450
+    },
+    {
+      "epoch": 0.021174477696216828,
+      "eval_loss": 1.2806880474090576,
+      "eval_runtime": 1054.9988,
+      "eval_samples_per_second": 8.482,
+      "eval_steps_per_second": 2.121,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.706631289110528e+17,
+  "total_flos": 1.9223752445263872e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null