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:a4763ba34d0ebe9925e21765b4758b11bf875f1c9c13ca9a97820db1859b76eb
+oid sha256:1df2f6f9658eb05e4d94ae92d672dea701a6ef6dc48973e91f6c6494fab7fffb
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c10300386e8448c8c8a27ba03a48e1f89cf2a378c775dfda89eb545878d64f59
+oid sha256:69eab6c34b483ba1ab98ab812cef34cbc272d7abdd4d01c486eae94945730dae
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe546c088a904c9148936fe061003215771900528105cd3fd79a6e7e85aee3a2
+oid sha256:3f8edb692b98d6fe2c463c8560c620326c771fab8f467558be234bddefb8f5bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f69d9f90a0d5ce8ac61f1f875459a761943b0c4252d8391ecd4046776d8753
+oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2882494032382965,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.012419853135236676,
+  "best_metric": 0.2871423065662384,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.01397233477714126,
   "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": 11.674,
       "eval_steps_per_second": 2.919,
       "step": 400
+    },
+    {
+      "epoch": 0.012730349463617592,
+      "grad_norm": 0.4869549572467804,
+      "learning_rate": 1.9480266573755372e-05,
+      "loss": 0.3046,
+      "step": 410
+    },
+    {
+      "epoch": 0.013040845791998509,
+      "grad_norm": 1.2998945713043213,
+      "learning_rate": 1.5499094192044554e-05,
+      "loss": 0.2766,
+      "step": 420
+    },
+    {
+      "epoch": 0.013351342120379427,
+      "grad_norm": 1.5833019018173218,
+      "learning_rate": 1.1939345528389446e-05,
+      "loss": 0.3613,
+      "step": 430
+    },
+    {
+      "epoch": 0.013661838448760344,
+      "grad_norm": 0.3303629159927368,
+      "learning_rate": 8.818363320454701e-06,
+      "loss": 0.2713,
+      "step": 440
+    },
+    {
+      "epoch": 0.01397233477714126,
+      "grad_norm": 0.5843662619590759,
+      "learning_rate": 6.1513526798373514e-06,
+      "loss": 0.2793,
+      "step": 450
+    },
+    {
+      "epoch": 0.01397233477714126,
+      "eval_loss": 0.2871423065662384,
+      "eval_runtime": 1162.0849,
+      "eval_samples_per_second": 11.67,
+      "eval_steps_per_second": 2.918,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1158405142229811e+17,
+  "total_flos": 1.2565220512550093e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null