Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8706dd9f32f31dbef8b52d15a91713597bc2996d51a3292dd09add012a2fa5ff
+oid sha256:be8a396ac79da5c6fe9496c8c539cb4b943c0f59bb95f9c0e5397419ef9c3670
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b70dd99a6a956882dd611bb23abe1f72e81784632ebbbedb6cfff9597020bf5
+oid sha256:91c945e29e7ba612739f657c6dc7652e88550736cd10e69b0701d46db9261f5b
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b6ab54758d6c72638402e84fae2aad65a221b35640878ae19e43b4230eac2d
+oid sha256:bcd474099de92dc845d40d5927f170b424592df7fa8ed3e362e00c4d62a05861
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3090df11bc2445b62bc263a9812782b2cdb94f2d343087e4b12056e17b9122a5
+oid sha256:2e959ae44ed59e1d9df727fe405a413d7ba7165046402e1b6aa379cddd545297
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0796676874160767,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.27932960893854747,
+  "best_metric": 1.0726971626281738,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.31424581005586594,
   "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": 11.598,
       "eval_steps_per_second": 2.904,
       "step": 400
+    },
+    {
+      "epoch": 0.28631284916201116,
+      "grad_norm": 0.40567949414253235,
+      "learning_rate": 2.0148707093443057e-05,
+      "loss": 0.8683,
+      "step": 410
+    },
+    {
+      "epoch": 0.29329608938547486,
+      "grad_norm": 0.3860771656036377,
+      "learning_rate": 1.603092585549706e-05,
+      "loss": 0.7976,
+      "step": 420
+    },
+    {
+      "epoch": 0.30027932960893855,
+      "grad_norm": 0.4146096408367157,
+      "learning_rate": 1.2349028953383204e-05,
+      "loss": 0.7469,
+      "step": 430
+    },
+    {
+      "epoch": 0.30726256983240224,
+      "grad_norm": 0.5146927237510681,
+      "learning_rate": 9.120954218705596e-06,
+      "loss": 0.8733,
+      "step": 440
+    },
+    {
+      "epoch": 0.31424581005586594,
+      "grad_norm": 1.1636193990707397,
+      "learning_rate": 6.362428507086673e-06,
+      "loss": 2.3676,
+      "step": 450
+    },
+    {
+      "epoch": 0.31424581005586594,
+      "eval_loss": 1.0726971626281738,
+      "eval_runtime": 52.9212,
+      "eval_samples_per_second": 11.394,
+      "eval_steps_per_second": 2.853,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1268467831341056e+17,
+  "total_flos": 1.2681469712400384e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null