Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953324c5e1fd2ec5fd87c589adb9afd3b822f114426f0e213faca00ce7959a26
+oid sha256:9fdf11626b774500ac61b9db4329ac0557b288ba30f980bde93036b4f85de094
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09489f7c01cc739253b2c8c31d8879e9a6c4d51559af8b05846a2dc5848fafb2
+oid sha256:b702dece5eca43c70775d874e6b3597152e4ba87e5e46ff44e0a74d446b65746
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed24157843733a720e9b3d1b006fa11ac517dab21a9d332b9aa678dbbf520076
+oid sha256:53857b31065290226097899a29c43817f42b59cc1033072766ec46b6e8e362ce
 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": 2.685049295425415,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005792903692976104,
+  "best_metric": 2.3354403972625732,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.011585807385952208,
   "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": 7.157,
       "eval_steps_per_second": 3.584,
       "step": 10
+    },
+    {
+      "epoch": 0.006372194062273715,
+      "grad_norm": 3.624699592590332,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 10.4661,
+      "step": 11
+    },
+    {
+      "epoch": 0.0069514844315713255,
+      "grad_norm": 4.032886981964111,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 11.1481,
+      "step": 12
+    },
+    {
+      "epoch": 0.007530774800868936,
+      "grad_norm": 3.667426347732544,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 10.4183,
+      "step": 13
+    },
+    {
+      "epoch": 0.008110065170166545,
+      "grad_norm": 3.7377707958221436,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 10.7956,
+      "step": 14
+    },
+    {
+      "epoch": 0.008689355539464157,
+      "grad_norm": 5.357843399047852,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.9671,
+      "step": 15
+    },
+    {
+      "epoch": 0.008689355539464157,
+      "eval_loss": 2.4640743732452393,
+      "eval_runtime": 101.2592,
+      "eval_samples_per_second": 7.18,
+      "eval_steps_per_second": 3.595,
+      "step": 15
+    },
+    {
+      "epoch": 0.009268645908761766,
+      "grad_norm": 3.6775741577148438,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.4698,
+      "step": 16
+    },
+    {
+      "epoch": 0.009847936278059377,
+      "grad_norm": 4.87345027923584,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 9.1637,
+      "step": 17
+    },
+    {
+      "epoch": 0.010427226647356987,
+      "grad_norm": 5.144161224365234,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 10.2837,
+      "step": 18
+    },
+    {
+      "epoch": 0.011006517016654598,
+      "grad_norm": 4.957813262939453,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 9.8878,
+      "step": 19
+    },
+    {
+      "epoch": 0.011585807385952208,
+      "grad_norm": 4.979409694671631,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 8.0892,
+      "step": 20
+    },
+    {
+      "epoch": 0.011585807385952208,
+      "eval_loss": 2.3354403972625732,
+      "eval_runtime": 101.2972,
+      "eval_samples_per_second": 7.177,
+      "eval_steps_per_second": 3.593,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2852805358387200.0,
+  "total_flos": 5705610716774400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null