Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d937d8123516983499d27dafb6fb7e797c9f42a3f7b6b8037fc9bb0976bc9aa
+oid sha256:f33da1e566ee39c7bbf630f981a99ba18bf61398257f0c070cde9e68e3c3c2a2
 size 1163996488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a7582284b90f20e8f0f60555c4bfc4d10bb96a7870a4eac0fe2481c71ba2d6
+oid sha256:97c05788ad8a48b7585ed7328708c7591371689f839920411031661a31c0d1ed
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47bcdf6f5ed49c41364b0c3822a6a097292560e5bb9d4f7a840e279c181e8096
+oid sha256:ba45e5ef4c7100bc7e600e9cb437f8a33618941eb488974e537090f9eea97cf9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
+oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.30848589539527893,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.01460786998995709,
+  "best_metric": 0.30705726146698,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.016433853738701727,
   "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": 11.639,
       "eval_steps_per_second": 2.91,
       "step": 400
+    },
+    {
+      "epoch": 0.014973066739706017,
+      "grad_norm": 0.14570221304893494,
+      "learning_rate": 2.081714761313074e-05,
+      "loss": 0.1041,
+      "step": 410
+    },
+    {
+      "epoch": 0.015338263489454943,
+      "grad_norm": 0.24520431458950043,
+      "learning_rate": 1.656275751894957e-05,
+      "loss": 0.1525,
+      "step": 420
+    },
+    {
+      "epoch": 0.01570346023920387,
+      "grad_norm": 0.35061249136924744,
+      "learning_rate": 1.275871237837696e-05,
+      "loss": 0.5399,
+      "step": 430
+    },
+    {
+      "epoch": 0.0160686569889528,
+      "grad_norm": 0.5372488498687744,
+      "learning_rate": 9.423545116956494e-06,
+      "loss": 0.424,
+      "step": 440
+    },
+    {
+      "epoch": 0.016433853738701727,
+      "grad_norm": 0.8911713361740112,
+      "learning_rate": 6.573504334335994e-06,
+      "loss": 0.5111,
+      "step": 450
+    },
+    {
+      "epoch": 0.016433853738701727,
+      "eval_loss": 0.30705726146698,
+      "eval_runtime": 991.6107,
+      "eval_samples_per_second": 11.628,
+      "eval_steps_per_second": 2.907,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0485976167717274e+17,
+  "total_flos": 1.17832103327957e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null