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:c2a60ff55fb387f53ad93f46901715fc0a880a7d48cce174a584084c93af97c3
+oid sha256:c5d02a6516e37dd293a88bf10a192a6144fe0bb08647e2dff03646a110717876
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c945e4a3f78c1d950e614d0e66fa0d155a99bee1d03f4f55b782cfe2535fa75c
+oid sha256:e065fbf32c64fff3c1ed39f305989c725e7f52b8385d3cebc4cd3180e2c7e4cb
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e00e749000557b1014539a7bbdab1432f4856d3e423d8a50564c8090e2b3077
+oid sha256:45aa182b328bfe02d781c42616bdb5443d5352aa5d5ba6c53863c2f340c940a8
 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": 2.584866523742676,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003699593044765076,
+  "best_metric": 2.3715481758117676,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.007399186089530152,
   "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": 5.46,
       "eval_steps_per_second": 2.732,
       "step": 10
+    },
+    {
+      "epoch": 0.004069552349241583,
+      "grad_norm": 1.2998981475830078,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.3709,
+      "step": 11
+    },
+    {
+      "epoch": 0.004439511653718091,
+      "grad_norm": 1.5440006256103516,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.4366,
+      "step": 12
+    },
+    {
+      "epoch": 0.004809470958194599,
+      "grad_norm": 1.5911710262298584,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.3136,
+      "step": 13
+    },
+    {
+      "epoch": 0.005179430262671106,
+      "grad_norm": 1.6979089975357056,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.5733,
+      "step": 14
+    },
+    {
+      "epoch": 0.005549389567147614,
+      "grad_norm": 1.5529507398605347,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.4157,
+      "step": 15
+    },
+    {
+      "epoch": 0.005549389567147614,
+      "eval_loss": 2.445035219192505,
+      "eval_runtime": 209.4732,
+      "eval_samples_per_second": 5.437,
+      "eval_steps_per_second": 2.721,
+      "step": 15
+    },
+    {
+      "epoch": 0.0059193488716241215,
+      "grad_norm": 1.7018779516220093,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.5408,
+      "step": 16
+    },
+    {
+      "epoch": 0.006289308176100629,
+      "grad_norm": 1.5621485710144043,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.5183,
+      "step": 17
+    },
+    {
+      "epoch": 0.006659267480577136,
+      "grad_norm": 1.6603797674179077,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.4762,
+      "step": 18
+    },
+    {
+      "epoch": 0.007029226785053644,
+      "grad_norm": 1.3905707597732544,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.348,
+      "step": 19
+    },
+    {
+      "epoch": 0.007399186089530152,
+      "grad_norm": 1.3540409803390503,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.2931,
+      "step": 20
+    },
+    {
+      "epoch": 0.007399186089530152,
+      "eval_loss": 2.3715481758117676,
+      "eval_runtime": 209.4929,
+      "eval_samples_per_second": 5.437,
+      "eval_steps_per_second": 2.721,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 500097330708480.0,
+  "total_flos": 1000194661416960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null