Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1469f5dc6aa64365507898c3f70693749ff0673bf76b56b142493948d0336ff6
+oid sha256:32b40a69ed53ce731ecbf58dcacb98f465fbc6d0568f68f80cfe3fb03b4a3185
 size 100690184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c55806ea45e04adbdb3a5310826228a387d59425abc0b3c31d5e4dac576934
+oid sha256:2731d808422ac7bebb3c73d92503f5457b7f2ac3feaf99ef7ef86817b1e675c4
 size 51345082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f689e099e8b551a080ad8b1d535052d398432005a22d166dd01998057344cb
+oid sha256:c1e5a944f30913173a4c67a7e5af43367d84ea71b16fb1705e8f008afc251373
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18572f0adae215b3259455cf96083d95e78dc1ab7af393890cd3753bf61cc9f4
+oid sha256:ac6ee4c7143f9893927b533c972fc3aa0da9526c7e014b3849d291e400a8521c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8595229387283325,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.19111323459149546,
+  "best_metric": 0.837338387966156,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.21500238891543239,
   "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": 72.277,
       "eval_steps_per_second": 18.11,
       "step": 400
+    },
+    {
+      "epoch": 0.19589106545628285,
+      "grad_norm": 24.64581871032715,
+      "learning_rate": 2.0435181601880635e-05,
+      "loss": 1.1874,
+      "step": 410
+    },
+    {
+      "epoch": 0.20066889632107024,
+      "grad_norm": 17.642654418945312,
+      "learning_rate": 1.625885371126242e-05,
+      "loss": 1.5195,
+      "step": 420
+    },
+    {
+      "epoch": 0.20544672718585763,
+      "grad_norm": 17.003334045410156,
+      "learning_rate": 1.2524607564094813e-05,
+      "loss": 1.8292,
+      "step": 430
+    },
+    {
+      "epoch": 0.210224558050645,
+      "grad_norm": 13.311195373535156,
+      "learning_rate": 9.250636032241695e-06,
+      "loss": 1.8517,
+      "step": 440
+    },
+    {
+      "epoch": 0.21500238891543239,
+      "grad_norm": 12.355936050415039,
+      "learning_rate": 6.45288957590781e-06,
+      "loss": 2.2005,
+      "step": 450
+    },
+    {
+      "epoch": 0.21500238891543239,
+      "eval_loss": 0.837338387966156,
+      "eval_runtime": 12.301,
+      "eval_samples_per_second": 71.701,
+      "eval_steps_per_second": 17.966,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3725608982937600.0,
+  "total_flos": 4191310105804800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null