Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:308f33ad8053cbcc02d0227051ea3026c078a62bb037b7e5abbf349a89bd9491
+oid sha256:14031c653a57d33e7b2b4ff7d51522b10ba7d7046a696abec3cda3edd8f90f84
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960c1541f35e135fd47853f2b869eee8cd36968913f6f5238c0c06fc7be12af7
+oid sha256:58ec429beae1e3a30f70359b5400904ce0660f7831df1cb8a415d339f156d107
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85beaa8ab06d8b11f3c93d6d561d3d052e57d6c7eebec9bffaf3e9025adb2a43
+oid sha256:81a5b53134b063241a2f678dedea3ac5cf592fc2cd2f4de35c80d0b0c3843de9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
+oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5103766918182373,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.3436426116838488,
+  "best_metric": 1.5094099044799805,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.3865979381443299,
   "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": 17.763,
       "eval_steps_per_second": 4.459,
       "step": 400
+    },
+    {
+      "epoch": 0.35223367697594504,
+      "grad_norm": 0.7793974280357361,
+      "learning_rate": 2.081714761313074e-05,
+      "loss": 1.6656,
+      "step": 410
+    },
+    {
+      "epoch": 0.36082474226804123,
+      "grad_norm": 0.9348426461219788,
+      "learning_rate": 1.656275751894957e-05,
+      "loss": 1.5795,
+      "step": 420
+    },
+    {
+      "epoch": 0.3694158075601375,
+      "grad_norm": 1.0919979810714722,
+      "learning_rate": 1.275871237837696e-05,
+      "loss": 1.4984,
+      "step": 430
+    },
+    {
+      "epoch": 0.37800687285223367,
+      "grad_norm": 1.2562652826309204,
+      "learning_rate": 9.423545116956494e-06,
+      "loss": 1.4936,
+      "step": 440
+    },
+    {
+      "epoch": 0.3865979381443299,
+      "grad_norm": 2.6799798011779785,
+      "learning_rate": 6.573504334335994e-06,
+      "loss": 1.2333,
+      "step": 450
+    },
+    {
+      "epoch": 0.3865979381443299,
+      "eval_loss": 1.5094099044799805,
+      "eval_runtime": 27.6177,
+      "eval_samples_per_second": 17.742,
+      "eval_steps_per_second": 4.454,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.1094434267136e+16,
+  "total_flos": 7.9981238550528e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null