Training in progress, step 540, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb75e239f10807cc7b833760bc31a51b22bc6472ab1bb46c2837715efb33cec3
+oid sha256:eb6cdf5d8b6226f6a41ae33f3f79fa018f920f25a94ad2acaf9fd20aabddde03
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8541d815dc555651c8e8b8e632021551adb6006014154fc79bfb427778e96952
+oid sha256:5d87b2845003ad9c26f85337961d9910d627941cfca2166b4fd830e4304e7a5d
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e8336c07f948150ff8156eb2dab171aaabcf51a63b33cea3cf6c8b02c7f21a
+oid sha256:c7aafa5db1b56a982de2d1a0e669dfa9a2ace2d844876b7ab6c68d2ae587a2e2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d8326679ee33cb66e7917979ef316425684ef1f6170b9c9d9735cbe157e239
+oid sha256:fdc990d65d20244e2fe8b10836667fc181b3d1910eff3fd20bd309d901a413a6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.736429962624243e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-520",
-  "epoch": 3.5016835016835017,
+  "best_metric": 2.6893604854194564e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-540",
+  "epoch": 3.6363636363636362,
   "eval_steps": 20,
-  "global_step": 520,
+  "global_step": 540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -258,6 +258,14 @@
       "eval_samples_per_second": 28.638,
       "eval_steps_per_second": 0.916,
       "step": 520
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "eval_loss": 2.6893604854194564e-07,
+      "eval_runtime": 4.3884,
+      "eval_samples_per_second": 28.484,
+      "eval_steps_per_second": 0.912,
+      "step": 540
     }
   ],
   "logging_steps": 100,
@@ -286,7 +294,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1958779476115456e+17,
+  "total_flos": 2.2803652559241216e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null