Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b74e76a70c8aa7378f012d122cf8099505f2ad65b8dc550ef517464e498937
+oid sha256:c3c56500a0ab0e18bd89cc06dd19ac124fef5611e51a625f6eaece9b7f9fb334
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce7cea08c6171e6bc47095a7bb176e7ff500fc05df0451de56aa60cca8acdd60
+oid sha256:7b3104f94caf145e6bb12599ef47f9737f8af4d2890daee6fa622456efa543a4
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b1330565fd27987f801e2d37c9ff5c8a342f0c9f98d1f15ff82badeebeb0b2
+oid sha256:aa475f51346237b604de04dfb5849998c82ad8e092cda930a1bc5b8d1fca410b
 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": 1.1311993598937988,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.01059322033898305,
+  "best_metric": 0.6798481941223145,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0211864406779661,
   "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": 6.655,
       "eval_steps_per_second": 3.327,
       "step": 10
+    },
+    {
+      "epoch": 0.011652542372881356,
+      "grad_norm": 2.957493305206299,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.0912,
+      "step": 11
+    },
+    {
+      "epoch": 0.012711864406779662,
+      "grad_norm": 2.8493051528930664,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.9196,
+      "step": 12
+    },
+    {
+      "epoch": 0.013771186440677966,
+      "grad_norm": 2.804184675216675,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.2003,
+      "step": 13
+    },
+    {
+      "epoch": 0.014830508474576272,
+      "grad_norm": 3.1039199829101562,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.7907,
+      "step": 14
+    },
+    {
+      "epoch": 0.015889830508474576,
+      "grad_norm": 5.297954559326172,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.4727,
+      "step": 15
+    },
+    {
+      "epoch": 0.015889830508474576,
+      "eval_loss": 0.7405627369880676,
+      "eval_runtime": 60.1344,
+      "eval_samples_per_second": 6.619,
+      "eval_steps_per_second": 3.309,
+      "step": 15
+    },
+    {
+      "epoch": 0.01694915254237288,
+      "grad_norm": 3.4782044887542725,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.8036,
+      "step": 16
+    },
+    {
+      "epoch": 0.018008474576271187,
+      "grad_norm": 2.544600248336792,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.4763,
+      "step": 17
+    },
+    {
+      "epoch": 0.019067796610169493,
+      "grad_norm": 4.462560176849365,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.682,
+      "step": 18
+    },
+    {
+      "epoch": 0.020127118644067795,
+      "grad_norm": 2.4938857555389404,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.1245,
+      "step": 19
+    },
+    {
+      "epoch": 0.0211864406779661,
+      "grad_norm": 3.4558427333831787,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.6024,
+      "step": 20
+    },
+    {
+      "epoch": 0.0211864406779661,
+      "eval_loss": 0.6798481941223145,
+      "eval_runtime": 60.5106,
+      "eval_samples_per_second": 6.577,
+      "eval_steps_per_second": 3.289,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3137325131366400.0,
+  "total_flos": 6274650262732800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null