Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d0135e77da24b529f7af236b50ea9d445f0ace489cf1f64aff5c6866db444e4
+oid sha256:6dc75f1da44b43edcf2a138468650eaf0c4a7e47f07d1187ff25ca62e963932d
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffaf3147b59c2c2d5b43d973142461df179f0d7986a90886f2537c508d14d6f1
+oid sha256:ad2b7b9a44c9de2fb84ff41052e7e8afc3918156af77d5e04016319b79c90263
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ac488ce1f441ca1ae6806867cc0d824ea5a04d174d746efdffa5a728cba642
+oid sha256:b0cc465a75681ba50afdecee660968bcd8503a20558be1104c59586aa9b9c2e7
 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": 11.93446159362793,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00022732180811766176,
+  "best_metric": 11.927410125732422,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00045464361623532353,
   "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": 49.582,
       "eval_steps_per_second": 24.792,
       "step": 10
+    },
+    {
+      "epoch": 0.0002727861697411941,
+      "grad_norm": 0.13978028297424316,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 11.9324,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003409827121764927,
+      "grad_norm": 0.0874234288930893,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 11.933,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003409827121764927,
+      "eval_loss": 11.930874824523926,
+      "eval_runtime": 377.4764,
+      "eval_samples_per_second": 49.071,
+      "eval_steps_per_second": 24.537,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004091792546117912,
+      "grad_norm": 0.24752134084701538,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9256,
+      "step": 18
+    },
+    {
+      "epoch": 0.00045464361623532353,
+      "eval_loss": 11.927410125732422,
+      "eval_runtime": 378.2962,
+      "eval_samples_per_second": 48.964,
+      "eval_steps_per_second": 24.483,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2856405565440.0,
+  "total_flos": 5712811130880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null