Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7e3337e9a6856284b1c7d6a98d853f4b744699bd31f0286830444e77fd28b1
+oid sha256:544ec3c81baa0939e589bd5c9db1c331a7848cb0fa27183c956f3d50b902b0e7
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5000dadb889399b9836159bf984ffaaa8810568186d44ca02f74f17d961ed599
+oid sha256:8d9c5bd6359a5cc032069d9d32f9c7ae1d8fd2a15719e117e8b1bd584af27f06
 size 111412820

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1323c18b0ac24675ebf582ae0cc6361039c60323aef4e15ee94b7e74df57e44
+oid sha256:9b38c318cc0bbed882a1d1a6a0e872b3052845a17efc867d6760318c2b7f41d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0a47cc675a5d4ba5fe8c0d42564476e1fe842799977ab67bf2a8317adef53f
+oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0921169519424438,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.26130981544994286,
+  "best_metric": 1.085567831993103,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.29397354238118567,
   "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": 18.85,
       "eval_steps_per_second": 4.716,
       "step": 400
+    },
+    {
+      "epoch": 0.2678425608361914,
+      "grad_norm": 0.2013624608516693,
+      "learning_rate": 4.695790918802576e-05,
+      "loss": 0.898,
+      "step": 410
+    },
+    {
+      "epoch": 0.27437530622244,
+      "grad_norm": 0.35071200132369995,
+      "learning_rate": 4.252125897855932e-05,
+      "loss": 0.9476,
+      "step": 420
+    },
+    {
+      "epoch": 0.28090805160868854,
+      "grad_norm": 0.5039893388748169,
+      "learning_rate": 3.824753850538082e-05,
+      "loss": 1.0456,
+      "step": 430
+    },
+    {
+      "epoch": 0.28744079699493713,
+      "grad_norm": 0.9260233640670776,
+      "learning_rate": 3.414886209349615e-05,
+      "loss": 1.1276,
+      "step": 440
+    },
+    {
+      "epoch": 0.29397354238118567,
+      "grad_norm": 3.32053279876709,
+      "learning_rate": 3.0236847886501542e-05,
+      "loss": 1.501,
+      "step": 450
+    },
+    {
+      "epoch": 0.29397354238118567,
+      "eval_loss": 1.085567831993103,
+      "eval_runtime": 136.7334,
+      "eval_samples_per_second": 18.854,
+      "eval_steps_per_second": 4.717,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.487667926943662e+17,
+  "total_flos": 3.9220372617088205e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null