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:aeb4c70d0eb54db30135f9e1181d3f60ef363e7554f594d3aff36f5332327f77
+oid sha256:c79d6a4ba5a7dc69e09d618b9eda2944a935b5263f02386f461f3dc740c44ee1
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12ce5ff0caf4b3c5b30e1697d042e35909ab085e1846099cf7133e73c04fb15f
+oid sha256:a35164be0457201e94eaffcdd8493ac848ce5af279f5aa0d113607a8c537255e
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad1d524fc47db40541de4bb31ebd2dbf7fbe2adb11e5083bb2c6cc16b4b3293
+oid sha256:7889ed95f85fdfab63ac4fc238f404b76d5465858d722702d06fd462019844e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a29a98d7724cf179d3beb2d49a34c568e23cf47a86cb77f3cd39efdcdbcc2de
+oid sha256:110c23ba7ac9436ac98f0e4bb88f393b7c16138e63fbbb47259fe31aa44af728
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.20021717250347137,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.0850520944078248,
+  "best_metric": 0.1977642923593521,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.106315118009781,
   "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": 13.635,
       "eval_steps_per_second": 3.416,
       "step": 200
+    },
+    {
+      "epoch": 0.08930469912821604,
+      "grad_norm": 0.5776247978210449,
+      "learning_rate": 0.00015318652713303674,
+      "loss": 0.16,
+      "step": 210
+    },
+    {
+      "epoch": 0.09355730384860728,
+      "grad_norm": 0.5547011494636536,
+      "learning_rate": 0.00014639560219879464,
+      "loss": 0.1446,
+      "step": 220
+    },
+    {
+      "epoch": 0.09780990856899852,
+      "grad_norm": 0.702063798904419,
+      "learning_rate": 0.0001394103099009319,
+      "loss": 0.1747,
+      "step": 230
+    },
+    {
+      "epoch": 0.10206251328938976,
+      "grad_norm": 0.9604615569114685,
+      "learning_rate": 0.0001322646818813646,
+      "loss": 0.2264,
+      "step": 240
+    },
+    {
+      "epoch": 0.106315118009781,
+      "grad_norm": 2.0104331970214844,
+      "learning_rate": 0.0001249935309215281,
+      "loss": 0.254,
+      "step": 250
+    },
+    {
+      "epoch": 0.106315118009781,
+      "eval_loss": 0.1977642923593521,
+      "eval_runtime": 72.6924,
+      "eval_samples_per_second": 13.619,
+      "eval_steps_per_second": 3.412,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.47839968690176e+16,
+  "total_flos": 5.60035666109399e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null