Training in progress, step 240, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d015affd6db158bedfd9fd25c50ae0db56683b4af68825771013d0c7f1761e7
+oid sha256:f2ca6f541a9d128a71b52474f12655bf699880f16de2961187b92699c533fb7b
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d780d1844496ddf7c79f7bfe775e1ce1686bb74b6d42ed307c08192fcae54ba8
+oid sha256:ad5670142902563ea66cb6058b04d9c3cd19723cabb474739b676c163e64ddd3
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c8446a0101b92101f9f087b8c34cf04dc6908f0b5cf93c2a4b2014185e0af79
+oid sha256:93f0ec112c9b0167a2c769cccced6910c1decb6450825497553afbf16ac1002d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:628bd7f1457e043dd759d9a2b466e6a3738950f1815b17b82ee8d82f030b600e
+oid sha256:af9a5a02fd2f64af4b394ceffc9ffebe28abc2a4d62808bb3561346ca599f084
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 5.753882987846737e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-220",
-  "epoch": 1.4814814814814814,
+  "best_metric": 5.237209279584931e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-240",
+  "epoch": 1.6161616161616161,
   "eval_steps": 20,
-  "global_step": 220,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -117,6 +117,14 @@
       "eval_samples_per_second": 28.744,
       "eval_steps_per_second": 0.92,
       "step": 220
+    },
+    {
+      "epoch": 1.6161616161616161,
+      "eval_loss": 5.237209279584931e-07,
+      "eval_runtime": 4.3453,
+      "eval_samples_per_second": 28.767,
+      "eval_steps_per_second": 0.921,
+      "step": 240
     }
   ],
   "logging_steps": 100,
@@ -145,7 +153,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.290963685998592e+16,
+  "total_flos": 1.0135836769124352e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null