Training in progress, step 360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7384e6e0afd8f05180f65c96007714d18e0e6fb36424c6547b4ec71902d11c5
+oid sha256:27dcec798f401aea531332fd52d47af4e2e2052534e106a38738f74d8310f559
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c01ec9d1f8083459f22d7eb7f74be826665564bff8cfff1031d1dd0d4707690e
+oid sha256:f5f75e289bb3450e55503e27675a790d9ae74e663bd5176ca0036dc79eed1f7f
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75b81576a953c126a70feb1037e15d1536a41145956ed969eb430642c3a082d6
+oid sha256:9f464ee492959ca51f31ddd6c918f5e6ed3b897ddaa5bd27211176d3e42d4533
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f554738d4c98e192859c545795d9bad33dffcf55dc2610937bb10f054a491a5
+oid sha256:96a1a67751ef8c6e878b8ba1ee8cfd48efab59bef2ad58f80bf89ebc2ab37857
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.6971795225326787e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-340",
-  "epoch": 2.28956228956229,
+  "best_metric": 3.503983521113696e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-360",
+  "epoch": 2.4242424242424243,
   "eval_steps": 20,
-  "global_step": 340,
+  "global_step": 360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -172,6 +172,14 @@
       "eval_samples_per_second": 28.424,
       "eval_steps_per_second": 0.91,
       "step": 340
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "eval_loss": 3.503983521113696e-07,
+      "eval_runtime": 4.387,
+      "eval_samples_per_second": 28.493,
+      "eval_steps_per_second": 0.912,
+      "step": 360
     }
   ],
   "logging_steps": 100,
@@ -200,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4357561956368384e+17,
+  "total_flos": 1.5202435039494144e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null