Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2e7181fdb5dbecf18242fb22424bbc07856257f9de737b936d98301296d299
+oid sha256:2f1bc393f158c0476cd310d9b601ee5f0abf0ae023763e7fc3bfe9445af3b399
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3a54c951b9e9ea5a3802159c524322c386f6d9e0ca39efb9d7e050ec181eab
+oid sha256:442fe0c9cc17e80d36f80b18b6879bd1936c2de80e95575f823ca863fd4741d0
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5b1b05889a1e7d8b727960030ff6f9c4906014166967f0dfe8b8ca71d0a4b0
+oid sha256:e637d1febac15aa0ae018e2cdb7f5360162c83d19419303b1c4b013885e8c2c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd73ab0fa36296fbe3783fb468aea0cd12510bf37814f4ec18ccbf6aa8715528
+oid sha256:b1d9ce382daca2647544897c246240c974b24aa3059027cee78bb529d4c50d9b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 9.559958016325254e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-140",
-  "epoch": 0.9427609427609428,
+  "best_metric": 8.15467842585349e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-160",
+  "epoch": 1.0774410774410774,
   "eval_steps": 20,
-  "global_step": 140,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,6 +78,14 @@
       "eval_samples_per_second": 28.616,
       "eval_steps_per_second": 0.916,
       "step": 140
+    },
+    {
+      "epoch": 1.0774410774410774,
+      "eval_loss": 8.15467842585349e-07,
+      "eval_runtime": 4.377,
+      "eval_samples_per_second": 28.559,
+      "eval_steps_per_second": 0.914,
+      "step": 160
     }
   ],
   "logging_steps": 100,
@@ -106,7 +114,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.91411158188032e+16,
+  "total_flos": 6.756344436621312e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null