Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09bd95f7fd364b89b2ae4f81d4c4ca5db8f8b034fadc0d7c22d6971663b16b1a
+oid sha256:69c0d0f0165f2e320264b0cbf7a406d8ade6350ee3ddad75d08ab7a097c3d1b7
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e006bb684433eda15f73531a2caf513d8fd48e340ad19b335d95a7347def5c
+oid sha256:5c3419855da5d9fa1454decf9c5559af4499b354f8e3df8d2778fcf7856fbb86
 size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35fc7e171edb891fb3bf2ebbb8252949f7facee3f2a2fec8c75dafd99cbd553c
+oid sha256:44a493c7fd0594ffa7fd7ceee4d682a949a06d6dbea4370ae50c901b5384a7d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0a47cc675a5d4ba5fe8c0d42564476e1fe842799977ab67bf2a8317adef53f
+oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.208735466003418,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.2611818478615736,
+  "best_metric": 1.2068712711334229,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.2938295788442703,
   "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": 61.734,
       "eval_steps_per_second": 15.439,
       "step": 400
+    },
+    {
+      "epoch": 0.26771139405811295,
+      "grad_norm": 0.06299945712089539,
+      "learning_rate": 4.695790918802576e-05,
+      "loss": 1.1717,
+      "step": 410
+    },
+    {
+      "epoch": 0.2742409402546523,
+      "grad_norm": 0.08601243048906326,
+      "learning_rate": 4.252125897855932e-05,
+      "loss": 1.2408,
+      "step": 420
+    },
+    {
+      "epoch": 0.2807704864511916,
+      "grad_norm": 0.14494818449020386,
+      "learning_rate": 3.824753850538082e-05,
+      "loss": 1.2919,
+      "step": 430
+    },
+    {
+      "epoch": 0.28730003264773096,
+      "grad_norm": 0.31678304076194763,
+      "learning_rate": 3.414886209349615e-05,
+      "loss": 1.239,
+      "step": 440
+    },
+    {
+      "epoch": 0.2938295788442703,
+      "grad_norm": 1.0417225360870361,
+      "learning_rate": 3.0236847886501542e-05,
+      "loss": 1.1049,
+      "step": 450
+    },
+    {
+      "epoch": 0.2938295788442703,
+      "eval_loss": 1.2068712711334229,
+      "eval_runtime": 42.7188,
+      "eval_samples_per_second": 60.372,
+      "eval_steps_per_second": 15.099,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.5047797694464e+16,
+  "total_flos": 7.317376872952627e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null