Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b533718a1864b92ed7049bd091cd653b3d0f91146ba07aa70ddb3b3d27f8c2
+oid sha256:ddf15abe4d0fdf0398c4c07739d8c8a1a4efc666c2d0c6eef72b169c884d25d3
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50cb74d8de0ebb99d7fa0994ad13327074f5caf9b68d0e145ba3894502bc540
+oid sha256:4c5f64b3873bc17417159fb5f2ff141d2a4d3a2f7a56a5679cb151dc5196be98
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af6e28eb927aaf2ef56158f9c22f00ff891410ff794c1c0879e10a51011c7ec
+oid sha256:7923881f8c8224151111022035a3364293966e66e8837eaed7399558296e3941
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2661f04b964aebdbfc5fe2d76ad72c51b84450f62ecbdcf121c15876692362c9
+oid sha256:275a3f467a10238121d3751994e96dac39b01caeff52940c5c443f8040986af4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.7967422008514404,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.023788284269997028,
+  "best_metric": 2.79083251953125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.026761819803746655,
   "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": 46.531,
       "eval_steps_per_second": 11.633,
       "step": 400
+    },
+    {
+      "epoch": 0.024382991376746953,
+      "grad_norm": 0.7588967084884644,
+      "learning_rate": 2.053067310469316e-05,
+      "loss": 2.855,
+      "step": 410
+    },
+    {
+      "epoch": 0.024977698483496878,
+      "grad_norm": 0.7385247945785522,
+      "learning_rate": 1.633482966318421e-05,
+      "loss": 2.7904,
+      "step": 420
+    },
+    {
+      "epoch": 0.025572405590246802,
+      "grad_norm": 0.8757428526878357,
+      "learning_rate": 1.2583133767665349e-05,
+      "loss": 2.7639,
+      "step": 430
+    },
+    {
+      "epoch": 0.02616711269699673,
+      "grad_norm": 1.0848084688186646,
+      "learning_rate": 9.293863303420395e-06,
+      "loss": 2.7639,
+      "step": 440
+    },
+    {
+      "epoch": 0.026761819803746655,
+      "grad_norm": 2.063558578491211,
+      "learning_rate": 6.483043265514856e-06,
+      "loss": 2.8008,
+      "step": 450
+    },
+    {
+      "epoch": 0.026761819803746655,
+      "eval_loss": 2.79083251953125,
+      "eval_runtime": 153.2642,
+      "eval_samples_per_second": 46.195,
+      "eval_steps_per_second": 11.549,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4231100552970240.0,
+  "total_flos": 4744780492308480.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null