Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cec129b4f8a0920ac329e841d136fb13fa3a4dac2472fd85bddb6c8aa2c9c35
+oid sha256:ec8af09ea1ab2375872b62219be9333db29fde1e77fb8983403e001f04945252
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a73fac7d3563437a76adbea0f9aedc23cf5ae54325ae15fbd01e23eb98052f6
+oid sha256:8a3774a20cf58dce6c8704d494e52999ee482552ef6a2990602964e507df389e
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:115f8b8ce45ad51489027f59416f2021c410ae7004969287814b0dde5c3cc44f
+oid sha256:35bb90a354ebd23af0a5c0c1246f630c256d6eae0cf735c8f8719f8c325c2b7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7df70caaedac0c234c7f5937694a04d6ee70bc0b2ef988bc747140f852d79a1
+oid sha256:31da5a14cc904adc54ea83cca79e784b23d086943331be4291a1b3f48fa9a4d1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 5.0069978897226974e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.13468013468013468,
+  "best_metric": 8.045045433391351e-06,
+  "best_model_checkpoint": "miner_id_24/checkpoint-40",
+  "epoch": 0.26936026936026936,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,14 @@
       "eval_samples_per_second": 28.585,
       "eval_steps_per_second": 0.915,
       "step": 20
+    },
+    {
+      "epoch": 0.26936026936026936,
+      "eval_loss": 8.045045433391351e-06,
+      "eval_runtime": 4.3441,
+      "eval_samples_per_second": 28.775,
+      "eval_steps_per_second": 0.921,
+      "step": 40
     }
   ],
   "logging_steps": 100,
@@ -51,7 +59,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8448730831257600.0,
+  "total_flos": 1.68974616625152e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null