Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2966f13bd1f98ceffe031e4fb87ebb1a15b6d67016c00e3deb1a3074f24205f8
+oid sha256:71ad751bb04f579e83c7f361233637557f9ddd59cbdbd5ffe1a0191f0321a756
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:198baef8d6cc1475b1c43876159b5eb5c6fa824e60cd5e52385897861feeb06f
+oid sha256:1ae9b683aaea94d9a4d60f5d6303b935b440a36e475603f5cbf7f28652f737ad
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4026bd94dfb661dcdf5dbdbc0e77a87b17c8ae0cb2ac247a5fa4f4e7da532809
+oid sha256:7c63729a20b60e7632088b0a8db0f282e51362d5fc07e8fdb3f5c2f3b27dd538
 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": 1.4789899587631226,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.06755615605472048,
+  "best_metric": 1.4701261520385742,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.07600067556156055,
   "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": 11.075,
       "eval_steps_per_second": 2.771,
       "step": 400
+    },
+    {
+      "epoch": 0.0692450599560885,
+      "grad_norm": 2.2446751594543457,
+      "learning_rate": 1.928928356813032e-05,
+      "loss": 2.6135,
+      "step": 410
+    },
+    {
+      "epoch": 0.07093396385745651,
+      "grad_norm": 2.9616000652313232,
+      "learning_rate": 1.5347142288200977e-05,
+      "loss": 2.8901,
+      "step": 420
+    },
+    {
+      "epoch": 0.07262286775882452,
+      "grad_norm": 2.9250693321228027,
+      "learning_rate": 1.1822293121248375e-05,
+      "loss": 2.8757,
+      "step": 430
+    },
+    {
+      "epoch": 0.07431177166019254,
+      "grad_norm": 2.9157168865203857,
+      "learning_rate": 8.731908778097302e-06,
+      "loss": 3.2046,
+      "step": 440
+    },
+    {
+      "epoch": 0.07600067556156055,
+      "grad_norm": 5.299656867980957,
+      "learning_rate": 6.09104530062326e-06,
+      "loss": 3.061,
+      "step": 450
+    },
+    {
+      "epoch": 0.07600067556156055,
+      "eval_loss": 1.4701261520385742,
+      "eval_runtime": 221.003,
+      "eval_samples_per_second": 11.285,
+      "eval_steps_per_second": 2.823,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.28802361442304e+17,
+  "total_flos": 1.44902656622592e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null