Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b4841243f8729a95f8cbf438eaaf0cd378116d0555c896cac461963478bb86
+oid sha256:01c306e0d8eb863fa7f156ce9765ad9b28406303063fca7a89889f37fa3b5b9d
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b99d7592e2217a55adeb6f26dc88e3e72a8e9de69cd170cb827a83d673de29
+oid sha256:5ad7b7027b7c61af8157df28c281203cb6a7ab3fac972e42de97b99c42d2d637
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534fd80f4a36921aa36f02966232895e27318825fe994a2792a763901e8e85a0
+oid sha256:90efee331ac9bcdb2e4f63bae83396c78dd900015159ffa010420c7d94807b3b
 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": 3.267272472381592,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00228741350717676,
+  "best_metric": 1.9547957181930542,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00457482701435352,
   "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": 5.824,
       "eval_steps_per_second": 2.914,
       "step": 10
+    },
+    {
+      "epoch": 0.0025161548578944357,
+      "grad_norm": 7.548186779022217,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 14.214,
+      "step": 11
+    },
+    {
+      "epoch": 0.0027448962086121117,
+      "grad_norm": 10.005125999450684,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 14.8289,
+      "step": 12
+    },
+    {
+      "epoch": 0.0029736375593297877,
+      "grad_norm": 7.77647590637207,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 10.9902,
+      "step": 13
+    },
+    {
+      "epoch": 0.0032023789100474637,
+      "grad_norm": 9.317489624023438,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 11.2201,
+      "step": 14
+    },
+    {
+      "epoch": 0.0034311202607651397,
+      "grad_norm": 8.553632736206055,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.4567,
+      "step": 15
+    },
+    {
+      "epoch": 0.0034311202607651397,
+      "eval_loss": 2.2402334213256836,
+      "eval_runtime": 317.5791,
+      "eval_samples_per_second": 5.797,
+      "eval_steps_per_second": 2.9,
+      "step": 15
+    },
+    {
+      "epoch": 0.0036598616114828157,
+      "grad_norm": 7.3252387046813965,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.2007,
+      "step": 16
+    },
+    {
+      "epoch": 0.0038886029622004917,
+      "grad_norm": 9.066070556640625,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 7.0014,
+      "step": 17
+    },
+    {
+      "epoch": 0.004117344312918168,
+      "grad_norm": 13.760567665100098,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 9.2674,
+      "step": 18
+    },
+    {
+      "epoch": 0.004346085663635844,
+      "grad_norm": 9.562538146972656,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 8.6528,
+      "step": 19
+    },
+    {
+      "epoch": 0.00457482701435352,
+      "grad_norm": 12.553031921386719,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 9.9563,
+      "step": 20
+    },
+    {
+      "epoch": 0.00457482701435352,
+      "eval_loss": 1.9547957181930542,
+      "eval_runtime": 317.0485,
+      "eval_samples_per_second": 5.807,
+      "eval_steps_per_second": 2.905,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3397367365632000.0,
+  "total_flos": 6794734731264000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null