Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d6f119d4e9b8e23cf58928dcc02f23bf0d2daaa031b56615e40b9dbc7b74998
+oid sha256:9b1149dd9a6283afe62fd6a5435ee2e45e45334cc32625902c52b02e76811a99
 size 58680

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1a64da15ec1bef708822fb26072490acb1b79cdbc7e51f6bd2bccb99c78ea35
+oid sha256:821aeba1618a4c6ea1f02f73ae01dfffb923411fd07e313df87fa264da97423b
 size 127270

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0636b5dcd4828e7b93aeee92e295cba33d5a09518e59150e0fd50893d80f575a
+oid sha256:6f9214c7106f65d75a1a0e44277060eea7ca60dc6107b276ad73b95692d7abf5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303e83c678e93581d63a3650d04963a2cf914298a9658799e3e1f49cf7c8604f
+oid sha256:f03fffc232f1b8a6305d6fa9076c1e1bca28e4d7666df088caa1812431cf9135
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.301532745361328,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.011239270009412888,
+  "best_metric": 10.30145263671875,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.0126441787605895,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 251.326,
       "eval_steps_per_second": 62.844,
       "step": 400
+    },
+    {
+      "epoch": 0.011520251759648211,
+      "grad_norm": 0.15768560767173767,
+      "learning_rate": 1.9384775070942844e-05,
+      "loss": 20.6082,
+      "step": 410
+    },
+    {
+      "epoch": 0.011801233509883532,
+      "grad_norm": 0.19848321378231049,
+      "learning_rate": 1.5423118240122765e-05,
+      "loss": 20.5956,
+      "step": 420
+    },
+    {
+      "epoch": 0.012082215260118856,
+      "grad_norm": 0.14942528307437897,
+      "learning_rate": 1.188081932481891e-05,
+      "loss": 20.6074,
+      "step": 430
+    },
+    {
+      "epoch": 0.012363197010354177,
+      "grad_norm": 0.21457645297050476,
+      "learning_rate": 8.775136049276001e-06,
+      "loss": 20.5856,
+      "step": 440
+    },
+    {
+      "epoch": 0.0126441787605895,
+      "grad_norm": 0.3364667296409607,
+      "learning_rate": 6.121198990230306e-06,
+      "loss": 20.5984,
+      "step": 450
+    },
+    {
+      "epoch": 0.0126441787605895,
+      "eval_loss": 10.30145263671875,
+      "eval_runtime": 60.1852,
+      "eval_samples_per_second": 248.982,
+      "eval_steps_per_second": 62.258,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 17205637939200.0,
+  "total_flos": 19336966963200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null