Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b363d9b3d34db8babb2c2cd28ff9fcbe150e320d421d670b02824aac3fbbca9
+oid sha256:a0222c0047535996deb8c8cb559888e4d66b3038044de3ae8bf08f3bd010cc02
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58aa446747ed8a047799a4009220bfa51fd93f2d52c03e85d541e5fe0f01c58c
+oid sha256:9677e62c9c2ab535a7409c2bbd60fd7316b6431801418e2a7ba28e522edbfac2
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd78934c835a4a69f293b31361858c5aba532565f0c899d40296121d5cbad7d7
+oid sha256:bd641d2c2a7f8e3282e19ce9e5df14c6531555bf46535a1b63e4e32f7c2a55e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:8f3583f6fb6381489c8d29ab09722642111b0d57df55aa7b4c72ce687a83cdee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9411152005195618,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.5714285714285714,
+  "best_metric": 0.784389317035675,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 1.1428571428571428,
   "eval_steps": 10,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 7.199,
       "eval_steps_per_second": 1.92,
       "step": 10
+    },
+    {
+      "epoch": 0.6285714285714286,
+      "grad_norm": 0.33402150869369507,
+      "learning_rate": 9.986661418317759e-05,
+      "loss": 0.8844,
+      "step": 11
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.31261247396469116,
+      "learning_rate": 9.946716840375551e-05,
+      "loss": 0.8441,
+      "step": 12
+    },
+    {
+      "epoch": 0.7428571428571429,
+      "grad_norm": 0.33552902936935425,
+      "learning_rate": 9.880379387779637e-05,
+      "loss": 0.8498,
+      "step": 13
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.33501139283180237,
+      "learning_rate": 9.78800299954203e-05,
+      "loss": 0.8905,
+      "step": 14
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.33641278743743896,
+      "learning_rate": 9.67008054366274e-05,
+      "loss": 0.8753,
+      "step": 15
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.3439123332500458,
+      "learning_rate": 9.527241187465734e-05,
+      "loss": 0.8292,
+      "step": 16
+    },
+    {
+      "epoch": 0.9714285714285714,
+      "grad_norm": 0.3387420177459717,
+      "learning_rate": 9.360247040719039e-05,
+      "loss": 0.8047,
+      "step": 17
+    },
+    {
+      "epoch": 1.0285714285714285,
+      "grad_norm": 0.35765647888183594,
+      "learning_rate": 9.16998908944939e-05,
+      "loss": 0.8683,
+      "step": 18
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 0.33680498600006104,
+      "learning_rate": 8.957482442146272e-05,
+      "loss": 0.7337,
+      "step": 19
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.32664304971694946,
+      "learning_rate": 8.72386091371891e-05,
+      "loss": 0.7241,
+      "step": 20
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "eval_loss": 0.784389317035675,
+      "eval_runtime": 2.086,
+      "eval_samples_per_second": 7.191,
+      "eval_steps_per_second": 1.918,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -121,7 +199,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3848728247009280.0,
+  "total_flos": 7697456494018560.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null