Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:452b918fd58af590dfecb8a6ef8ae1893936c4047ca760a9d4bf58513fb697f3
+oid sha256:6674f38157deea1f8da47f0e7383ded7e10888f7be70896c89345136a4f7b5f5
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:176f9d20e6c1f120e6ac8440d3126dcaf0f3d11e0d39248481bcfc3e8e97a513
+oid sha256:980067367be4b528be508d8fd0d54166ea5ae5a5e2031d3216766e76d63bf394
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32319360bea69a353b8dbd7cd43c82fa8e161e8d12be7d1c2fde2aec99a9b0d7
+oid sha256:4a5c6aa2884b0b3ab3eea503865660bbaa2e49a678110098485e78de4b178340
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8c70a94900d9b287ae32cb4f95d47fb8ad712363557219eb89e270f8b96010
+oid sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.1496591418981552,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.43501903208265363,
+  "best_metric": 0.1295737773180008,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.4893964110929853,
   "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": 17.167,
       "eval_steps_per_second": 4.292,
       "step": 400
+    },
+    {
+      "epoch": 0.44589450788471996,
+      "grad_norm": 0.5191034078598022,
+      "learning_rate": 2.005321559063053e-05,
+      "loss": 0.1327,
+      "step": 410
+    },
+    {
+      "epoch": 0.4567699836867863,
+      "grad_norm": 0.6500219106674194,
+      "learning_rate": 1.5954949903575276e-05,
+      "loss": 0.1289,
+      "step": 420
+    },
+    {
+      "epoch": 0.4676454594888526,
+      "grad_norm": 0.7300875186920166,
+      "learning_rate": 1.2290502749812666e-05,
+      "loss": 0.0955,
+      "step": 430
+    },
+    {
+      "epoch": 0.478520935290919,
+      "grad_norm": 0.7386441230773926,
+      "learning_rate": 9.077726947526898e-06,
+      "loss": 0.1079,
+      "step": 440
+    },
+    {
+      "epoch": 0.4893964110929853,
+      "grad_norm": 1.8114835023880005,
+      "learning_rate": 6.332274817479627e-06,
+      "loss": 0.1624,
+      "step": 450
+    },
+    {
+      "epoch": 0.4893964110929853,
+      "eval_loss": 0.1295737773180008,
+      "eval_runtime": 22.5929,
+      "eval_samples_per_second": 17.174,
+      "eval_steps_per_second": 4.293,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.207198273830912e+16,
+  "total_flos": 8.104765506453504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null