Training in progress, step 480, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297c40cbc2da5db73511eee36b53e42afb207da29c75ec2eeb3c7a5ff0ce646b
+oid sha256:22c84e9cc936663e6c34b3a3e6c931e7e307e89e3d2f455805818ba80ea25bec
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375c8fb1c842bf478a24faad149ade553cc336ab4835462dce843070b2cb474d
+oid sha256:71e7c2c253c15cc52058dc9311cabc349ea810c722cf581c76e1b08499199643
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a155e923e0b4298b8b4229c14dfaf2f68a45b16d8173809b74999eea6f0c1556
+oid sha256:b778f964afdb04441b7ffabc2d4c71842e937185ab90d6759d7e25153973b7b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd50cb4f72488d8867b40fc5244626bff4c3ed5a31cd2b76a9d677b834aeddaa
+oid sha256:9b7a42e4de5a0371ed1cdb9a4ad0dc5b3c36d5df99820c6e294bbce39c952685
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.9283941671565117e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-460",
-  "epoch": 3.0976430976430978,
+  "best_metric": 2.863944814635033e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-480",
+  "epoch": 3.2323232323232323,
   "eval_steps": 20,
-  "global_step": 460,
+  "global_step": 480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -227,6 +227,14 @@
       "eval_samples_per_second": 28.36,
       "eval_steps_per_second": 0.908,
       "step": 460
+    },
+    {
+      "epoch": 3.2323232323232323,
+      "eval_loss": 2.863944814635033e-07,
+      "eval_runtime": 4.3566,
+      "eval_samples_per_second": 28.692,
+      "eval_steps_per_second": 0.918,
+      "step": 480
     }
   ],
   "logging_steps": 100,
@@ -255,7 +263,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9424160226738176e+17,
+  "total_flos": 2.0269033309863936e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null