Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec8af09ea1ab2375872b62219be9333db29fde1e77fb8983403e001f04945252
+oid sha256:6d4afdfdac4abb363a87741a54395752df6c9923fa0fccaf0d49eb1514869301
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a3774a20cf58dce6c8704d494e52999ee482552ef6a2990602964e507df389e
+oid sha256:23e0de8313be14c314f4d8b495fcb1c22f15a58b68e750f8676bb80321b447f7
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35bb90a354ebd23af0a5c0c1246f630c256d6eae0cf735c8f8719f8c325c2b7d
+oid sha256:65d23e71454d91540ca5cae0c13105c0eee7ea182728dcfbee0fe9626c97c693
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31da5a14cc904adc54ea83cca79e784b23d086943331be4291a1b3f48fa9a4d1
+oid sha256:203d649d53933a20ddae1c00fc7d5d4eee081c3469bbba2dc0d5fb090df29ad9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 8.045045433391351e-06,
-  "best_model_checkpoint": "miner_id_24/checkpoint-40",
-  "epoch": 0.26936026936026936,
+  "best_metric": 3.3631840778980404e-06,
+  "best_model_checkpoint": "miner_id_24/checkpoint-60",
+  "epoch": 0.40404040404040403,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -31,6 +31,14 @@
       "eval_samples_per_second": 28.775,
       "eval_steps_per_second": 0.921,
       "step": 40
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "eval_loss": 3.3631840778980404e-06,
+      "eval_runtime": 4.4814,
+      "eval_samples_per_second": 27.893,
+      "eval_steps_per_second": 0.893,
+      "step": 60
     }
   ],
   "logging_steps": 100,
@@ -59,7 +67,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.68974616625152e+16,
+  "total_flos": 2.53461924937728e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null