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:a517c60507383dc479eab183d7c953299a68143bdd29781c17bd3c5a46d0c265
+oid sha256:b7f9f2d52f0aed995bbf49800f2806620367bba33dc14cc8d5903a57167a4e6c
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c071802f5f28f0f1950ef5cd7d9ca1c21c6fa44e2e9b75be5f20fe3898447cd
+oid sha256:c7f71545be81d9f7a00bd82ae74b0e31f9d551057bae04179008dd843b0d6292
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8bccb02c4fd4e6c8c34f0a4232e2b2e52997c515bc635e97c60de1fa73c87db
+oid sha256:3b755806378981de9043df7e6fb9040a4956d482785c45c1100277e6bb6b7929
 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": 0.8128843307495117,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.14730252255569876,
+  "best_metric": 0.8024091124534607,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.1657153378751611,
   "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": 10.905,
       "eval_steps_per_second": 2.726,
       "step": 400
+    },
+    {
+      "epoch": 0.15098508561959123,
+      "grad_norm": 0.9193152189254761,
+      "learning_rate": 2.005321559063053e-05,
+      "loss": 1.6275,
+      "step": 410
+    },
+    {
+      "epoch": 0.1546676486834837,
+      "grad_norm": 1.0370545387268066,
+      "learning_rate": 1.5954949903575276e-05,
+      "loss": 1.6423,
+      "step": 420
+    },
+    {
+      "epoch": 0.15835021174737618,
+      "grad_norm": 0.9968223571777344,
+      "learning_rate": 1.2290502749812666e-05,
+      "loss": 1.5805,
+      "step": 430
+    },
+    {
+      "epoch": 0.16203277481126865,
+      "grad_norm": 0.9633427858352661,
+      "learning_rate": 9.077726947526898e-06,
+      "loss": 1.6058,
+      "step": 440
+    },
+    {
+      "epoch": 0.1657153378751611,
+      "grad_norm": 1.313849687576294,
+      "learning_rate": 6.332274817479627e-06,
+      "loss": 1.4868,
+      "step": 450
+    },
+    {
+      "epoch": 0.1657153378751611,
+      "eval_loss": 0.8024091124534607,
+      "eval_runtime": 104.8859,
+      "eval_samples_per_second": 10.907,
+      "eval_steps_per_second": 2.727,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2082564750009958e+17,
+  "total_flos": 1.3587688094642995e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null