Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93fa75ef15900d1850ea8219d8085af62f39acb411fcee165a4cc11362457b0f
+oid sha256:e8bcf46e8273fdd9e6a39d172604b262358ca5acc917132c993e726f06d682d7
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aed5a7015ab8bcd7d18eaddb55830f29ac6633fd1c31a7be6231fc0a76c86db
+oid sha256:1864e57bcb997745217395bd9f3793e8ad1ebb369000e11b9bd13ef72dce50ad
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd1de999b91ee89daffea3abb7af5fd0931130409c833b7b8d20a8b39861c5d
+oid sha256:0fbdf3c563e47901060c8a0a1969c7b40974ea2772ee3fd006b4c4488361a030
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5706849098205566,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008592910848549946,
+  "best_metric": 2.5436248779296875,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.017185821697099892,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 17.915,
       "eval_steps_per_second": 8.958,
       "step": 10
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 3.4153363704681396,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.8795,
+      "step": 12
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": 3.5653088092803955,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.4435,
+      "step": 15
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "eval_loss": 2.552823066711426,
+      "eval_runtime": 27.2962,
+      "eval_samples_per_second": 17.951,
+      "eval_steps_per_second": 8.976,
+      "step": 15
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": 2.5528149604797363,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3373,
+      "step": 18
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "eval_loss": 2.5436248779296875,
+      "eval_runtime": 27.2804,
+      "eval_samples_per_second": 17.962,
+      "eval_steps_per_second": 8.981,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 931565823590400.0,
+  "total_flos": 1893182157619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null