Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d97b6b62ead56b86ec17fa83afaf62b79ed1939d43859f4ba0398908dba4dca8
+oid sha256:534bacf15ae0120290d041dd787e2172bc885c9f0cdb5fdb1d076ba294acf9ee
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeecebb300ade4a384deba2ac136a84a850d99aa7e089cef62903fbdb8c1857f
-size 51418196
+oid sha256:c1e408c26b84a9b1497a22f374c7ad4dc29f5663c0d5876f6c9ba85cbe637637
+size 51418452

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1916266e5d8c733d88e89ea7c6174486a4c857e0f94cd7c34aefcb7617bed5a
+oid sha256:3d9c215bbc9da7782d528c8f06a75c7a0667b8e3c2ca59be19e3fe53b5b30023
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e4a8d9505ab5e0891e71b89f41010a5997ec96d8f1c5ec4c12ce973f5bf2fa
+oid sha256:a8d9346c4fcc90fb1ec8546736583b76a4fae6bc25cb93181337c187d15da94a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7788119912147522,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.29420417769932333,
+  "best_metric": 0.7667000889778137,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.353045013239188,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 22.007,
       "eval_steps_per_second": 5.502,
       "step": 250
+    },
+    {
+      "epoch": 0.30597234480729624,
+      "grad_norm": 0.7562018632888794,
+      "learning_rate": 0.0001237326699871115,
+      "loss": 5.6205,
+      "step": 260
+    },
+    {
+      "epoch": 0.3177405119152692,
+      "grad_norm": 0.7738041281700134,
+      "learning_rate": 0.00011852887240871145,
+      "loss": 4.6291,
+      "step": 270
+    },
+    {
+      "epoch": 0.32950867902324216,
+      "grad_norm": 1.0495797395706177,
+      "learning_rate": 0.00011327255272837221,
+      "loss": 2.5666,
+      "step": 280
+    },
+    {
+      "epoch": 0.34127684613121506,
+      "grad_norm": 0.8168486952781677,
+      "learning_rate": 0.00010797861055530831,
+      "loss": 1.2404,
+      "step": 290
+    },
+    {
+      "epoch": 0.353045013239188,
+      "grad_norm": 1.7189139127731323,
+      "learning_rate": 0.00010266205214377748,
+      "loss": 1.3585,
+      "step": 300
+    },
+    {
+      "epoch": 0.353045013239188,
+      "eval_loss": 0.7667000889778137,
+      "eval_runtime": 64.8942,
+      "eval_samples_per_second": 22.067,
+      "eval_steps_per_second": 5.517,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6845926844019507e+17,
+  "total_flos": 2.0198533389248102e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null