Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59842f2c84ca02b7210aa6a144474e6682c17743b7da95e4e8f63e672c3af33f
+oid sha256:58dd2dd7a31cf38cc48378c11b297b700772d2ae0503ffe823b3a73bd96cb7d2
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:482e890dc5c94ceccd3b5c63ca4922385f65648b84be5f6ebaf36ac6611ed353
+oid sha256:1efb42f87131f42ece2fbb83f6c80814849fc58d36cc62e09e8414a9d263442a
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d18e2b1b9b98e75cf042a7f29b3e190dc725ca8964ebee762fcbe1462eb1549
+oid sha256:dace3653fe0e7343aeff78961da71266f92cc83f6bc7a8561cfa91c303e54dba
 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": 10.3787260055542,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.017543859649122806,
+  "best_metric": 10.377450942993164,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.03508771929824561,
   "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": 307.12,
       "eval_steps_per_second": 153.56,
       "step": 10
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 0.038283903151750565,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.3773,
+      "step": 12
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 0.047764599323272705,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.38,
+      "step": 15
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "eval_loss": 10.378009796142578,
+      "eval_runtime": 0.8122,
+      "eval_samples_per_second": 295.476,
+      "eval_steps_per_second": 147.738,
+      "step": 15
+    },
+    {
+      "epoch": 0.031578947368421054,
+      "grad_norm": 0.03205176070332527,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3795,
+      "step": 18
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "eval_loss": 10.377450942993164,
+      "eval_runtime": 0.8206,
+      "eval_samples_per_second": 292.462,
+      "eval_steps_per_second": 146.231,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 268050038784.0,
+  "total_flos": 542637883392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null