Training in progress, step 460, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b78623973eb2794c0a49a2cec63bfb0dd4b26992ffac1dec31ca41cc19e923
+oid sha256:297c40cbc2da5db73511eee36b53e42afb207da29c75ec2eeb3c7a5ff0ce646b
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6feb5a14d31c0796d533286dea3f6e3b3ce9a31fd701942e2cc4f56c02504dd4
+oid sha256:375c8fb1c842bf478a24faad149ade553cc336ab4835462dce843070b2cb474d
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7c724a3e6764e5b735a889ce37cba056b96f3333312e703ca050d56cda9d41
+oid sha256:a155e923e0b4298b8b4229c14dfaf2f68a45b16d8173809b74999eea6f0c1556
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f4240f17505bd53f967c1c31fbb076003c5cff63798cacf8ef30309a9af1de
+oid sha256:bd50cb4f72488d8867b40fc5244626bff4c3ed5a31cd2b76a9d677b834aeddaa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.009457714142627e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-440",
-  "epoch": 2.962962962962963,
+  "best_metric": 2.9283941671565117e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-460",
+  "epoch": 3.0976430976430978,
   "eval_steps": 20,
-  "global_step": 440,
+  "global_step": 460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -219,6 +219,14 @@
       "eval_samples_per_second": 28.419,
       "eval_steps_per_second": 0.909,
       "step": 440
+    },
+    {
+      "epoch": 3.0976430976430978,
+      "eval_loss": 2.9283941671565117e-07,
+      "eval_runtime": 4.4076,
+      "eval_samples_per_second": 28.36,
+      "eval_steps_per_second": 0.908,
+      "step": 460
     }
   ],
   "logging_steps": 100,
@@ -247,7 +255,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8581927371997184e+17,
+  "total_flos": 1.9424160226738176e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null