Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b767e51a2febadff74cea6fd2b6cf4ac88e84b162d74677908d0a93122679db
+oid sha256:ebebc8a19fd7b6d5dd18de5ebb1757251a686bc8736a6d24aa1aebbe285cfd61
 size 2185308216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a221b98d5f5c1da3beb94c0325f261016fcba4c3ad963879f7cf2fd37aa83a1a
+oid sha256:b2faa1236b041a91db75d142c93c7481ce047ed75543d814470a67cfcef9a98e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5909367203712463,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0023559901048415596,
+  "best_metric": 0.542029082775116,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.004711980209683119,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 4.102,
       "eval_steps_per_second": 2.051,
       "step": 10
+    },
+    {
+      "epoch": 0.0025915891153257156,
+      "grad_norm": 0.47473108768463135,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.5654,
+      "step": 11
+    },
+    {
+      "epoch": 0.0028271881258098716,
+      "grad_norm": 0.572853684425354,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.6893,
+      "step": 12
+    },
+    {
+      "epoch": 0.0030627871362940277,
+      "grad_norm": 0.6122471690177917,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.593,
+      "step": 13
+    },
+    {
+      "epoch": 0.0032983861467781837,
+      "grad_norm": 0.7183160781860352,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6515,
+      "step": 14
+    },
+    {
+      "epoch": 0.0035339851572623393,
+      "grad_norm": 0.4755716621875763,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6092,
+      "step": 15
+    },
+    {
+      "epoch": 0.0035339851572623393,
+      "eval_loss": 0.5491443276405334,
+      "eval_runtime": 432.8959,
+      "eval_samples_per_second": 4.13,
+      "eval_steps_per_second": 2.065,
+      "step": 15
+    },
+    {
+      "epoch": 0.0037695841677464954,
+      "grad_norm": 0.3686135709285736,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5829,
+      "step": 16
+    },
+    {
+      "epoch": 0.004005183178230651,
+      "grad_norm": 0.39384743571281433,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.5757,
+      "step": 17
+    },
+    {
+      "epoch": 0.004240782188714807,
+      "grad_norm": 0.3624189794063568,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4607,
+      "step": 18
+    },
+    {
+      "epoch": 0.0044763811991989635,
+      "grad_norm": 0.3992636799812317,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.4785,
+      "step": 19
+    },
+    {
+      "epoch": 0.004711980209683119,
+      "grad_norm": 0.3548687994480133,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4083,
+      "step": 20
+    },
+    {
+      "epoch": 0.004711980209683119,
+      "eval_loss": 0.542029082775116,
+      "eval_runtime": 430.5877,
+      "eval_samples_per_second": 4.152,
+      "eval_steps_per_second": 2.076,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3699130509557760.0,
+  "total_flos": 7398261019115520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null