Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c816d5ee43afb31ccc46408d2365e4cbc7c1eb8b72186087a31d843c20f755b
+oid sha256:0a6a7d2d6f241d7b191ceba7da340ce6f73393738536ce9a3bcbc2b9c10e60b3
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:990c93a6a97309d91899621b4a0772523c3a347abf1a2828f4e0e16dfbacdb58
+oid sha256:bbf897d2ababa82d1821ae33dcf01997684697f95c347319ca00bf1d8c94a7b8
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec134605e1e781fc705a3279e09b0cbaee66f077da601816e59f2b3169ff7952
+oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
 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": 4.058638095855713,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00019502586530538614,
+  "best_metric": 3.88244366645813,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0003900517306107723,
   "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": 29.322,
       "eval_steps_per_second": 14.661,
       "step": 10
+    },
+    {
+      "epoch": 0.00023403103836646335,
+      "grad_norm": 9.496614456176758,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 16.2777,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002925387979580792,
+      "grad_norm": 9.867759704589844,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 15.7824,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002925387979580792,
+      "eval_loss": 3.9371206760406494,
+      "eval_runtime": 734.2275,
+      "eval_samples_per_second": 29.405,
+      "eval_steps_per_second": 14.703,
+      "step": 15
+    },
+    {
+      "epoch": 0.00035104655754969504,
+      "grad_norm": 9.290112495422363,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 15.3766,
+      "step": 18
+    },
+    {
+      "epoch": 0.0003900517306107723,
+      "eval_loss": 3.88244366645813,
+      "eval_runtime": 735.9882,
+      "eval_samples_per_second": 29.335,
+      "eval_steps_per_second": 14.667,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 151685494210560.0,
+  "total_flos": 303370988421120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null