Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91001afcce286c33437fe8cb781bf2d2e7a68b0c9f27b39387011d68cd0e29e8
+oid sha256:71ffdb8629ce2fe066238cffbf8cea7e4787bfdd9840b2a8751fc175f24431cd
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de70acdfc34cafcdc708216ca3328735ce786773e20f06fa59c970dbb5fd3d1c
+oid sha256:81044b76e6a031e5c98e93b98b4809bd70f97a39c9707b7ca40499561b5e4db5
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b48224e45cb502ee8ecd7dfdbc0c3b2ecf1cb31ae633c1f705b79ed73109c2c
+oid sha256:f0d8a6753bf9eff5b67e540a93f6cf1b00d8cc12cceceee564b133c4134fc898
 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": 1.215065360069275,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.020962712575007206,
+  "best_metric": 1.1930021047592163,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.023583051646883107,
   "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": 16.392,
       "eval_steps_per_second": 4.098,
       "step": 400
+    },
+    {
+      "epoch": 0.021486780389382384,
+      "grad_norm": 1.1142139434814453,
+      "learning_rate": 1.9480266573755372e-05,
+      "loss": 1.0362,
+      "step": 410
+    },
+    {
+      "epoch": 0.022010848203757566,
+      "grad_norm": 1.5296214818954468,
+      "learning_rate": 1.5499094192044554e-05,
+      "loss": 1.038,
+      "step": 420
+    },
+    {
+      "epoch": 0.022534916018132747,
+      "grad_norm": 1.5614051818847656,
+      "learning_rate": 1.1939345528389446e-05,
+      "loss": 1.0573,
+      "step": 430
+    },
+    {
+      "epoch": 0.023058983832507925,
+      "grad_norm": 2.5465171337127686,
+      "learning_rate": 8.818363320454701e-06,
+      "loss": 1.082,
+      "step": 440
+    },
+    {
+      "epoch": 0.023583051646883107,
+      "grad_norm": 12.415629386901855,
+      "learning_rate": 6.1513526798373514e-06,
+      "loss": 1.8403,
+      "step": 450
+    },
+    {
+      "epoch": 0.023583051646883107,
+      "eval_loss": 1.1930021047592163,
+      "eval_runtime": 489.2822,
+      "eval_samples_per_second": 16.422,
+      "eval_steps_per_second": 4.106,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.54256789372928e+16,
+  "total_flos": 8.48538888044544e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null