Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd3c1da81c14a0db55be0c24ecd79049b791440c9aa7efb2574a0640ec52a35c
+oid sha256:ea9950dffcfbb4d3b1ee8d4253efbb1337c7593f8d59b870ad6983ecacebd0f3
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff858ec7126944f018edd4f087d64e9b28884c9feda06ffc5fb381681f173fb
+oid sha256:755f0ea7ae61c6d5fa9fa23eb9eb1e43dfca03ea61dfe87d97b6e1ee10296f8d
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0de0c32bf94efe74fce56eafc87e41e69cc5016d5c33867cf1c8934b8875ce
+oid sha256:02ae481c8002fa1263f712f930a5df4f2c49037e33af7892692f742d795e7bee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292f236c37f22c287cc737dd1428bf82b9a9008a84eb2f517544aab166f8a97f
+oid sha256:2a83bfe9ce791ae9422d624a37c23887da722084404f306517a014ce665484f8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2006936073303223,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.13966480446927373,
+  "best_metric": 1.151829481124878,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.17458100558659218,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 11.636,
       "eval_steps_per_second": 2.914,
       "step": 200
+    },
+    {
+      "epoch": 0.14664804469273743,
+      "grad_norm": 0.45036932826042175,
+      "learning_rate": 0.0001560632694266149,
+      "loss": 0.9129,
+      "step": 210
+    },
+    {
+      "epoch": 0.15363128491620112,
+      "grad_norm": 0.4322090446949005,
+      "learning_rate": 0.00014914481538562646,
+      "loss": 0.9577,
+      "step": 220
+    },
+    {
+      "epoch": 0.16061452513966482,
+      "grad_norm": 0.4544154703617096,
+      "learning_rate": 0.0001420283438896818,
+      "loss": 0.7483,
+      "step": 230
+    },
+    {
+      "epoch": 0.16759776536312848,
+      "grad_norm": 0.6254767179489136,
+      "learning_rate": 0.00013474852567256393,
+      "loss": 0.961,
+      "step": 240
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "grad_norm": 1.0982528924942017,
+      "learning_rate": 0.00012734082727686196,
+      "loss": 2.2834,
+      "step": 250
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "eval_loss": 1.151829481124878,
+      "eval_runtime": 51.8371,
+      "eval_samples_per_second": 11.633,
+      "eval_steps_per_second": 2.913,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.652007524237312e+16,
+  "total_flos": 7.06500940529664e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null