Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534bacf15ae0120290d041dd787e2172bc885c9f0cdb5fdb1d076ba294acf9ee
+oid sha256:3ae0121c7556edf5c3d39dc68a36ad1e58f74a3050f3cd6875ea40059b7c76d3
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e408c26b84a9b1497a22f374c7ad4dc29f5663c0d5876f6c9ba85cbe637637
+oid sha256:0504a82b9d1462df6794f44fbb8431046ed9c46b7286f7ec8247a50fe9724974
 size 51418452

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9c215bbc9da7782d528c8f06a75c7a0667b8e3c2ca59be19e3fe53b5b30023
+oid sha256:d26b6ca5513429ee6f5da17a80a0dec8462857d45a6714cbe5fe4f29d713d2c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d9346c4fcc90fb1ec8546736583b76a4fae6bc25cb93181337c187d15da94a
+oid sha256:77c9b643e87499abdfb160399a4a6e4965274897c037cf91e4cd5d5d65b2b404
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7667000889778137,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.353045013239188,
+  "best_metric": 0.7572553157806396,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.41188584877905265,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 22.067,
       "eval_steps_per_second": 5.517,
       "step": 300
+    },
+    {
+      "epoch": 0.3648131803471609,
+      "grad_norm": 0.7242693305015564,
+      "learning_rate": 9.733794785622253e-05,
+      "loss": 5.6994,
+      "step": 310
+    },
+    {
+      "epoch": 0.3765813474551339,
+      "grad_norm": 0.810172438621521,
+      "learning_rate": 9.202138944469168e-05,
+      "loss": 4.7286,
+      "step": 320
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.7765442728996277,
+      "learning_rate": 8.672744727162781e-05,
+      "loss": 2.8564,
+      "step": 330
+    },
+    {
+      "epoch": 0.40011768167107975,
+      "grad_norm": 0.7657132744789124,
+      "learning_rate": 8.147112759128859e-05,
+      "loss": 1.3036,
+      "step": 340
+    },
+    {
+      "epoch": 0.41188584877905265,
+      "grad_norm": 1.4623005390167236,
+      "learning_rate": 7.626733001288851e-05,
+      "loss": 1.3171,
+      "step": 350
+    },
+    {
+      "epoch": 0.41188584877905265,
+      "eval_loss": 0.7572553157806396,
+      "eval_runtime": 64.9777,
+      "eval_samples_per_second": 22.038,
+      "eval_steps_per_second": 5.51,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0198533389248102e+17,
+  "total_flos": 2.3560350392018534e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null