Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b3e7a800d94dc707b43d2cff1367b4bf08493d6dcd6f3250acf23515aec58d
+oid sha256:bdf30656975a7ced594f94b07a0f452f9bed705b5e96edcc572d8bdc7909d636
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc7ad86ebf88542c1ba187292a0681d85e46af0282a475393ba46e7c637505bb
+oid sha256:6c59ddd4a6c30e1796d13bac686374e0b10e6cf8bec72d08fd73735c9de4449f
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e224c14664601a8f0eb60590a28a54e325cd887941e1d119e02e8c408128fff3
+oid sha256:2b3ee690ad88b56c8223e3bf83d50e37e8f858cadaf0e44c5eac6f2d3f098a1f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935feb3a63b37324efd90f0473c874080c886e9eea264139d581d13a208d37c1
+oid sha256:56d2b9cd8b76db862d8f36c96267d64ff69a21d07ce7f6eb4a0887810e44a8eb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3324865102767944,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.14713996689350745,
+  "best_metric": 1.3237847089767456,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.16553246275519587,
   "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": 17.446,
       "eval_steps_per_second": 4.373,
       "step": 400
+    },
+    {
+      "epoch": 0.15081846606584515,
+      "grad_norm": 0.7403445839881897,
+      "learning_rate": 1.928928356813032e-05,
+      "loss": 1.4268,
+      "step": 410
+    },
+    {
+      "epoch": 0.15449696523818282,
+      "grad_norm": 0.7790653109550476,
+      "learning_rate": 1.5347142288200977e-05,
+      "loss": 1.3724,
+      "step": 420
+    },
+    {
+      "epoch": 0.1581754644105205,
+      "grad_norm": 0.8011258840560913,
+      "learning_rate": 1.1822293121248375e-05,
+      "loss": 1.3301,
+      "step": 430
+    },
+    {
+      "epoch": 0.1618539635828582,
+      "grad_norm": 0.8102395534515381,
+      "learning_rate": 8.731908778097302e-06,
+      "loss": 1.2836,
+      "step": 440
+    },
+    {
+      "epoch": 0.16553246275519587,
+      "grad_norm": 0.930636465549469,
+      "learning_rate": 6.09104530062326e-06,
+      "loss": 1.2365,
+      "step": 450
+    },
+    {
+      "epoch": 0.16553246275519587,
+      "eval_loss": 1.3237847089767456,
+      "eval_runtime": 65.7933,
+      "eval_samples_per_second": 17.403,
+      "eval_steps_per_second": 4.362,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.1094434267136e+16,
+  "total_flos": 7.9981238550528e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null