Training in progress, step 520, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e9a20845bafe95363997a4b9637a5ae4c1128170320448ad411e8afeaabef2
+oid sha256:eb75e239f10807cc7b833760bc31a51b22bc6472ab1bb46c2837715efb33cec3
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7240b0ed19a50c2530325fcc53033cfda0060c485bbec26b3b10c089072d8c6f
+oid sha256:8541d815dc555651c8e8b8e632021551adb6006014154fc79bfb427778e96952
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:903125fed0a9de29a47f6119f55db3d494a56b3b64b59c1f84927248fb21fd0a
+oid sha256:91e8336c07f948150ff8156eb2dab171aaabcf51a63b33cea3cf6c8b02c7f21a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a0c0bc555ca42eab8053c417988c17d7af364e7c0f092b31a291c4524b2f82
+oid sha256:f3d8326679ee33cb66e7917979ef316425684ef1f6170b9c9d9735cbe157e239
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.800263985136553e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-500",
-  "epoch": 3.3670033670033668,
+  "best_metric": 2.736429962624243e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-520",
+  "epoch": 3.5016835016835017,
   "eval_steps": 20,
-  "global_step": 500,
+  "global_step": 520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -250,6 +250,14 @@
       "eval_samples_per_second": 28.503,
       "eval_steps_per_second": 0.912,
       "step": 500
+    },
+    {
+      "epoch": 3.5016835016835017,
+      "eval_loss": 2.736429962624243e-07,
+      "eval_runtime": 4.3648,
+      "eval_samples_per_second": 28.638,
+      "eval_steps_per_second": 0.916,
+      "step": 520
     }
   ],
   "logging_steps": 100,
@@ -278,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1113906392989696e+17,
+  "total_flos": 2.1958779476115456e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null