Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0222c0047535996deb8c8cb559888e4d66b3038044de3ae8bf08f3bd010cc02
+oid sha256:e02bf26d5b2401ec7dc326297f3ee2388f15d11930d5efb6984ae8f6428a10f9
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9677e62c9c2ab535a7409c2bbd60fd7316b6431801418e2a7ba28e522edbfac2
+oid sha256:da94be3ae0a64e853b92443c0a2c39df2e4402a3604ed63a25872c61f1cc51db
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd641d2c2a7f8e3282e19ce9e5df14c6531555bf46535a1b63e4e32f7c2a55e1
+oid sha256:27827d7d71d66eac185d181a061a3fc686c05fceae71aefa31bdc9f272ad8dc6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f3583f6fb6381489c8d29ab09722642111b0d57df55aa7b4c72ce687a83cdee
+oid sha256:2b01233c08a586038ebf1cf3e5cbb4f41b3484fab28bfbbe42cb46fd4e382bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.784389317035675,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 1.1428571428571428,
+  "best_metric": 0.7271688580513,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 1.7142857142857144,
   "eval_steps": 10,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -171,6 +171,84 @@
       "eval_samples_per_second": 7.191,
       "eval_steps_per_second": 1.918,
       "step": 20
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.35325202345848083,
+      "learning_rate": 8.47037097610317e-05,
+      "loss": 0.7718,
+      "step": 21
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.30332982540130615,
+      "learning_rate": 8.198365107794457e-05,
+      "loss": 0.6796,
+      "step": 22
+    },
+    {
+      "epoch": 1.3142857142857143,
+      "grad_norm": 0.365041047334671,
+      "learning_rate": 7.909294577789766e-05,
+      "loss": 0.7059,
+      "step": 23
+    },
+    {
+      "epoch": 1.3714285714285714,
+      "grad_norm": 0.2987039387226105,
+      "learning_rate": 7.604701702439651e-05,
+      "loss": 0.6808,
+      "step": 24
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.3556249141693115,
+      "learning_rate": 7.286211616523193e-05,
+      "loss": 0.7061,
+      "step": 25
+    },
+    {
+      "epoch": 1.4857142857142858,
+      "grad_norm": 0.37903037667274475,
+      "learning_rate": 6.95552360245078e-05,
+      "loss": 0.736,
+      "step": 26
+    },
+    {
+      "epoch": 1.5428571428571427,
+      "grad_norm": 0.36219486594200134,
+      "learning_rate": 6.614402023857232e-05,
+      "loss": 0.7291,
+      "step": 27
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.31098002195358276,
+      "learning_rate": 6.264666911958404e-05,
+      "loss": 0.6836,
+      "step": 28
+    },
+    {
+      "epoch": 1.657142857142857,
+      "grad_norm": 0.3429687023162842,
+      "learning_rate": 5.908184254897182e-05,
+      "loss": 0.7052,
+      "step": 29
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.3376871645450592,
+      "learning_rate": 5.546856041889373e-05,
+      "loss": 0.678,
+      "step": 30
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "eval_loss": 0.7271688580513,
+      "eval_runtime": 2.0876,
+      "eval_samples_per_second": 7.185,
+      "eval_steps_per_second": 1.916,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -199,7 +277,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7697456494018560.0,
+  "total_flos": 1.154618474102784e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null