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:fdaf0f1ec51eefb3a8d11919a18eca5662d8d7213a8a2c658cef52430bf20aa7
+oid sha256:e60d9cfd66fb63ba0ef4f5d1db7447d24a6492299b9c4e41dabbd248fac86f27
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e027883f08c479f12100e29c8b89ad916939eadc70778fa8a4473e1460023fdb
+oid sha256:dc3b8a925a805a214f80927ac08953b98f2350cb8bbdfc6549774cd741409b1b
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5384c868ad4f5eba08060c410e7ba96c949c8f1932d335231a37a2203cd8d3d8
+oid sha256:f1c42c5533b631e30616c09bafafff6d5dd44c37f3ea17757c3363a8fc82a396
 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": 3.690568685531616,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005128205128205128,
+  "best_metric": 2.6909339427948,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.010256410256410256,
   "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": 12.345,
       "eval_steps_per_second": 6.173,
       "step": 10
+    },
+    {
+      "epoch": 0.0056410256410256415,
+      "grad_norm": 22.763395309448242,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 13.9442,
+      "step": 11
+    },
+    {
+      "epoch": 0.006153846153846154,
+      "grad_norm": 22.979591369628906,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 14.4218,
+      "step": 12
+    },
+    {
+      "epoch": 0.006666666666666667,
+      "grad_norm": 17.942583084106445,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 12.9257,
+      "step": 13
+    },
+    {
+      "epoch": 0.0071794871794871795,
+      "grad_norm": 23.007564544677734,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 14.753,
+      "step": 14
+    },
+    {
+      "epoch": 0.007692307692307693,
+      "grad_norm": 20.036060333251953,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 11.9054,
+      "step": 15
+    },
+    {
+      "epoch": 0.007692307692307693,
+      "eval_loss": 2.848227024078369,
+      "eval_runtime": 68.2509,
+      "eval_samples_per_second": 12.044,
+      "eval_steps_per_second": 6.022,
+      "step": 15
+    },
+    {
+      "epoch": 0.008205128205128205,
+      "grad_norm": 22.43932342529297,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.8376,
+      "step": 16
+    },
+    {
+      "epoch": 0.008717948717948718,
+      "grad_norm": 24.600799560546875,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 11.0014,
+      "step": 17
+    },
+    {
+      "epoch": 0.009230769230769232,
+      "grad_norm": 22.357858657836914,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 11.8771,
+      "step": 18
+    },
+    {
+      "epoch": 0.009743589743589744,
+      "grad_norm": 20.887723922729492,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 11.0594,
+      "step": 19
+    },
+    {
+      "epoch": 0.010256410256410256,
+      "grad_norm": 22.963176727294922,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 11.1411,
+      "step": 20
+    },
+    {
+      "epoch": 0.010256410256410256,
+      "eval_loss": 2.6909339427948,
+      "eval_runtime": 68.7322,
+      "eval_samples_per_second": 11.959,
+      "eval_steps_per_second": 5.98,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 298765642629120.0,
+  "total_flos": 597531285258240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null