Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3835ca34fa7332b22358686c574ead09f563fb747b41e516780dd6c4fd41fb3b
+oid sha256:557e23c2bf963651c89d40069e1bf1ea2ffae25eb725537795da21f54a568434
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc0edc33a9c1096f82ceb09e9d28b8fbda3c96ac10e46f4d6998e004f6de816
+oid sha256:e5d088e9abf5cf8ebd528ebdffeebaf9cf0c29176fc4bb1f288310136e106a39
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62acd428d956354759fb7118088aa7b6f3877437638037920c44e024fd787099
+oid sha256:798e5a804c5015a13c256dcddb137fd5521b3a1527698086dacb41e77aa688ca
 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": 2.4349887371063232,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003699593044765076,
+  "best_metric": 2.2063357830047607,
+  "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": 8.144,
       "eval_steps_per_second": 4.075,
       "step": 10
+    },
+    {
+      "epoch": 0.004069552349241583,
+      "grad_norm": 0.683988630771637,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.2553,
+      "step": 11
+    },
+    {
+      "epoch": 0.004439511653718091,
+      "grad_norm": 0.6252261400222778,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.2496,
+      "step": 12
+    },
+    {
+      "epoch": 0.004809470958194599,
+      "grad_norm": 0.5618606805801392,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.1804,
+      "step": 13
+    },
+    {
+      "epoch": 0.005179430262671106,
+      "grad_norm": 0.6698136925697327,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.4199,
+      "step": 14
+    },
+    {
+      "epoch": 0.005549389567147614,
+      "grad_norm": 0.6190295219421387,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.2062,
+      "step": 15
+    },
+    {
+      "epoch": 0.005549389567147614,
+      "eval_loss": 2.2569127082824707,
+      "eval_runtime": 139.8151,
+      "eval_samples_per_second": 8.146,
+      "eval_steps_per_second": 4.077,
+      "step": 15
+    },
+    {
+      "epoch": 0.0059193488716241215,
+      "grad_norm": 0.5969918370246887,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.2917,
+      "step": 16
+    },
+    {
+      "epoch": 0.006289308176100629,
+      "grad_norm": 0.6747704744338989,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.3536,
+      "step": 17
+    },
+    {
+      "epoch": 0.006659267480577136,
+      "grad_norm": 0.6725971102714539,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.1611,
+      "step": 18
+    },
+    {
+      "epoch": 0.007029226785053644,
+      "grad_norm": 0.6665031313896179,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.1477,
+      "step": 19
+    },
+    {
+      "epoch": 0.007399186089530152,
+      "grad_norm": 0.6256259679794312,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.1298,
+      "step": 20
+    },
+    {
+      "epoch": 0.007399186089530152,
+      "eval_loss": 2.2063357830047607,
+      "eval_runtime": 142.6573,
+      "eval_samples_per_second": 7.984,
+      "eval_steps_per_second": 3.996,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 820048664985600.0,
+  "total_flos": 1640097329971200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null