Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbdc6e5c96b4a26d1191704692d3101b148625951c3d71f617360d55dcfdf6a
+oid sha256:d6d8b9f1ed1e4344fb1a8bd6fa6b85410782d57a9346e833edb8dedc9ca2fd9a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6442c748ccc11aad01b095a6dcc4e2b486bd920a066c464c5283239c0e7227cc
+oid sha256:a654dfc37d33057c45051f9f816b84e4eb23821afb15aa191df382bbf4c021a6
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5e83a8d68021f72aa7f6ac24182160a7f72af908d654599ef0c0306176510d
+oid sha256:f5016d318ca8e3d6b8ca4b2a60622ca780cb9ab30c6b1c3967b8626d3aa409c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4024550914764404,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0002139483635624542,
+  "best_metric": 2.105510950088501,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0004278967271249084,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 3.898,
       "eval_steps_per_second": 1.949,
       "step": 10
+    },
+    {
+      "epoch": 0.000256738036274945,
+      "grad_norm": 2.3049252033233643,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 2.5073,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003209225453436813,
+      "grad_norm": 2.5028700828552246,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.2915,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003209225453436813,
+      "eval_loss": 2.176945924758911,
+      "eval_runtime": 5038.5523,
+      "eval_samples_per_second": 3.906,
+      "eval_steps_per_second": 1.953,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003851070544124176,
+      "grad_norm": 2.0715272426605225,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 2.2345,
+      "step": 18
+    },
+    {
+      "epoch": 0.0004278967271249084,
+      "eval_loss": 2.105510950088501,
+      "eval_runtime": 5039.1582,
+      "eval_samples_per_second": 3.906,
+      "eval_steps_per_second": 1.953,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 1.483774567120896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null