Training in progress, step 180, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f1bc393f158c0476cd310d9b601ee5f0abf0ae023763e7fc3bfe9445af3b399
+oid sha256:773ecf925e3044fd8e5bfc79ace12f68a0a750cd0846c60a1995fa9d67197b62
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:442fe0c9cc17e80d36f80b18b6879bd1936c2de80e95575f823ca863fd4741d0
+oid sha256:f5e09c0c9d48ed41f72eefb6b130c9ac4a29d8c7871775dbfb92b640a067ff34
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e637d1febac15aa0ae018e2cdb7f5360162c83d19419303b1c4b013885e8c2c5
+oid sha256:c0e0eb92ee6ab96887c644deef91a3595acf08b4870f007cade3903676b790b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1d9ce382daca2647544897c246240c974b24aa3059027cee78bb529d4c50d9b
+oid sha256:8dedc0c3bbca075b4105f7402c2edc664ae2d3638630e3ba98fe9e0e08614cf6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 8.15467842585349e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-160",
-  "epoch": 1.0774410774410774,
+  "best_metric": 7.171624929469544e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-180",
+  "epoch": 1.2121212121212122,
   "eval_steps": 20,
-  "global_step": 160,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -86,6 +86,14 @@
       "eval_samples_per_second": 28.559,
       "eval_steps_per_second": 0.914,
       "step": 160
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "eval_loss": 7.171624929469544e-07,
+      "eval_runtime": 4.3662,
+      "eval_samples_per_second": 28.629,
+      "eval_steps_per_second": 0.916,
+      "step": 180
     }
   ],
   "logging_steps": 100,
@@ -114,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.756344436621312e+16,
+  "total_flos": 7.601217519747072e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null