Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3468e761d398da63e45d3b84e7dafcbe5bbdba7a09a1a7e428f55c1430d29971
+oid sha256:b588f8a016404d801f6d123b7e0ceb79b40ddf90f516afa3ab6a427f19ed81b6
 size 419475904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e66f8cb76956402db02c2bec1fc2bf11f3a55b2350fe6577f5b20d9212b16337
+oid sha256:5c8306092a9a5b7d4cb37a3202446d898bb8754afb28488ddb0a3b6f6b22caea
 size 213368916

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a974154480f6b5b483655be31f3a20fffb254720aad8de48c7304d71c7fdff60
+oid sha256:96036273dc69d8772050eb416abe30f5c8813a76d1e8f8be692bf5694d44166f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d9346c4fcc90fb1ec8546736583b76a4fae6bc25cb93181337c187d15da94a
+oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0020770456176251173,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.04831306868507931,
+  "best_metric": 0.0015856274403631687,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.07246960302761897,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,135 @@
       "eval_samples_per_second": 9.517,
       "eval_steps_per_second": 2.379,
       "step": 300
+    },
+    {
+      "epoch": 0.04992350430791529,
+      "grad_norm": 0.07601720094680786,
+      "learning_rate": 9.733794785622253e-05,
+      "loss": 0.0104,
+      "step": 310
+    },
+    {
+      "epoch": 0.05153393993075127,
+      "grad_norm": 0.12636294960975647,
+      "learning_rate": 9.202138944469168e-05,
+      "loss": 0.0025,
+      "step": 320
+    },
+    {
+      "epoch": 0.053144375553587246,
+      "grad_norm": 0.021180983632802963,
+      "learning_rate": 8.672744727162781e-05,
+      "loss": 0.0054,
+      "step": 330
+    },
+    {
+      "epoch": 0.054754811176423224,
+      "grad_norm": 0.2496389001607895,
+      "learning_rate": 8.147112759128859e-05,
+      "loss": 0.0063,
+      "step": 340
+    },
+    {
+      "epoch": 0.0563652467992592,
+      "grad_norm": 0.3061932623386383,
+      "learning_rate": 7.626733001288851e-05,
+      "loss": 0.0085,
+      "step": 350
+    },
+    {
+      "epoch": 0.0563652467992592,
+      "eval_loss": 0.0021686903201043606,
+      "eval_runtime": 1099.0821,
+      "eval_samples_per_second": 9.516,
+      "eval_steps_per_second": 2.379,
+      "step": 350
+    },
+    {
+      "epoch": 0.05797568242209518,
+      "grad_norm": 0.06296177953481674,
+      "learning_rate": 7.113080526603792e-05,
+      "loss": 0.006,
+      "step": 360
+    },
+    {
+      "epoch": 0.059586118044931156,
+      "grad_norm": 0.2615507245063782,
+      "learning_rate": 6.607611338819697e-05,
+      "loss": 0.0074,
+      "step": 370
+    },
+    {
+      "epoch": 0.061196553667767134,
+      "grad_norm": 0.07279438525438309,
+      "learning_rate": 6.111758245266794e-05,
+      "loss": 0.0047,
+      "step": 380
+    },
+    {
+      "epoch": 0.0628069892906031,
+      "grad_norm": 0.023239092901349068,
+      "learning_rate": 5.626926795411447e-05,
+      "loss": 0.0069,
+      "step": 390
+    },
+    {
+      "epoch": 0.06441742491343909,
+      "grad_norm": 0.1575266271829605,
+      "learning_rate": 5.1544912966734994e-05,
+      "loss": 0.0095,
+      "step": 400
+    },
+    {
+      "epoch": 0.06441742491343909,
+      "eval_loss": 0.0016576452180743217,
+      "eval_runtime": 1098.7341,
+      "eval_samples_per_second": 9.519,
+      "eval_steps_per_second": 2.38,
+      "step": 400
+    },
+    {
+      "epoch": 0.06602786053627506,
+      "grad_norm": 0.2516278922557831,
+      "learning_rate": 4.695790918802576e-05,
+      "loss": 0.0055,
+      "step": 410
+    },
+    {
+      "epoch": 0.06763829615911104,
+      "grad_norm": 0.2692907750606537,
+      "learning_rate": 4.252125897855932e-05,
+      "loss": 0.0033,
+      "step": 420
+    },
+    {
+      "epoch": 0.06924873178194701,
+      "grad_norm": 0.040723081678152084,
+      "learning_rate": 3.824753850538082e-05,
+      "loss": 0.0032,
+      "step": 430
+    },
+    {
+      "epoch": 0.070859167404783,
+      "grad_norm": 0.030476342886686325,
+      "learning_rate": 3.414886209349615e-05,
+      "loss": 0.0048,
+      "step": 440
+    },
+    {
+      "epoch": 0.07246960302761897,
+      "grad_norm": 0.432902455329895,
+      "learning_rate": 3.0236847886501542e-05,
+      "loss": 0.0079,
+      "step": 450
+    },
+    {
+      "epoch": 0.07246960302761897,
+      "eval_loss": 0.0015856274403631687,
+      "eval_runtime": 1098.3615,
+      "eval_samples_per_second": 9.522,
+      "eval_steps_per_second": 2.381,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -301,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.582279267044557e+17,
+  "total_flos": 1.1370262248082637e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null