Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c84e9cc936663e6c34b3a3e6c931e7e307e89e3d2f455805818ba80ea25bec
+oid sha256:04e9a20845bafe95363997a4b9637a5ae4c1128170320448ad411e8afeaabef2
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e7c2c253c15cc52058dc9311cabc349ea810c722cf581c76e1b08499199643
+oid sha256:7240b0ed19a50c2530325fcc53033cfda0060c485bbec26b3b10c089072d8c6f
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b778f964afdb04441b7ffabc2d4c71842e937185ab90d6759d7e25153973b7b9
+oid sha256:903125fed0a9de29a47f6119f55db3d494a56b3b64b59c1f84927248fb21fd0a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b7a42e4de5a0371ed1cdb9a4ad0dc5b3c36d5df99820c6e294bbce39c952685
+oid sha256:83a0c0bc555ca42eab8053c417988c17d7af364e7c0f092b31a291c4524b2f82
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.863944814635033e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-480",
-  "epoch": 3.2323232323232323,
+  "best_metric": 2.800263985136553e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 3.3670033670033668,
   "eval_steps": 20,
-  "global_step": 480,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -235,6 +235,21 @@
       "eval_samples_per_second": 28.692,
       "eval_steps_per_second": 0.918,
       "step": 480
+    },
+    {
+      "epoch": 3.3670033670033668,
+      "grad_norm": 6.557375400007004e-06,
+      "learning_rate": 7.29623588569039e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 3.3670033670033668,
+      "eval_loss": 2.800263985136553e-07,
+      "eval_runtime": 4.3855,
+      "eval_samples_per_second": 28.503,
+      "eval_steps_per_second": 0.912,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -263,7 +278,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0269033309863936e+17,
+  "total_flos": 2.1113906392989696e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null