Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1a32fbfe4f9fcfdac2520dceea6e9188182cf953ce1eebcf91ccd4ec690f12
+oid sha256:18faf378cc83306823012fe8b50a3846b2466dfc2ac837b3ec050873f82c43fa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355892675ec61ce6ed077b6521dd0f1e155d6ed3aac2f57e2539d2e8c3e22264
+oid sha256:e6ec3b24a3dca01594a2d4f6be6e85d0f2e69f9d5d0e2cd5548fd0822f1aeb37
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e911f73debba3b869b165b24dbe530d381875b3d2ae0860bff90c1dd80e107
+oid sha256:dc6c8c8005f761597275404d272c3e4a41cab724899a67a64511d3b2eee6db9b
 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": 4.757584571838379,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.001554001554001554,
+  "best_metric": 3.67405366897583,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.003108003108003108,
   "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": 5.689,
       "eval_steps_per_second": 2.844,
       "step": 10
+    },
+    {
+      "epoch": 0.0017094017094017094,
+      "grad_norm": 4.928085803985596,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.2605,
+      "step": 11
+    },
+    {
+      "epoch": 0.0018648018648018648,
+      "grad_norm": 3.8864288330078125,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.1881,
+      "step": 12
+    },
+    {
+      "epoch": 0.00202020202020202,
+      "grad_norm": 5.182751655578613,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.6251,
+      "step": 13
+    },
+    {
+      "epoch": 0.0021756021756021756,
+      "grad_norm": 6.373917102813721,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.051,
+      "step": 14
+    },
+    {
+      "epoch": 0.002331002331002331,
+      "grad_norm": 7.264593124389648,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.6214,
+      "step": 15
+    },
+    {
+      "epoch": 0.002331002331002331,
+      "eval_loss": 3.908417224884033,
+      "eval_runtime": 476.9646,
+      "eval_samples_per_second": 5.682,
+      "eval_steps_per_second": 2.841,
+      "step": 15
+    },
+    {
+      "epoch": 0.0024864024864024864,
+      "grad_norm": 7.405270099639893,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.8455,
+      "step": 16
+    },
+    {
+      "epoch": 0.002641802641802642,
+      "grad_norm": 5.975386142730713,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.7157,
+      "step": 17
+    },
+    {
+      "epoch": 0.002797202797202797,
+      "grad_norm": 6.4273881912231445,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.7263,
+      "step": 18
+    },
+    {
+      "epoch": 0.0029526029526029526,
+      "grad_norm": 5.193171501159668,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.7786,
+      "step": 19
+    },
+    {
+      "epoch": 0.003108003108003108,
+      "grad_norm": 6.251737594604492,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.4756,
+      "step": 20
+    },
+    {
+      "epoch": 0.003108003108003108,
+      "eval_loss": 3.67405366897583,
+      "eval_runtime": 472.2966,
+      "eval_samples_per_second": 5.738,
+      "eval_steps_per_second": 2.869,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2728107266015232.0,
+  "total_flos": 5456214532030464.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null