Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f3e98821c698268f01480d915d377cb12aeea63037cabac8b12379f531bebe2
+oid sha256:15b533718a1864b92ed7049bd091cd653b3d0f91146ba07aa70ddb3b3d27f8c2
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50fc721e0cc231489142a553fe9aa68b8b2bc721861ccec4dcf51c4e51332739
+oid sha256:a50cb74d8de0ebb99d7fa0994ad13327074f5caf9b68d0e145ba3894502bc540
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f60d1a9a29c8b9d0df3785f72eef126f3a90ac8bb7ebe7c0f41f2020f270cac
+oid sha256:7af6e28eb927aaf2ef56158f9c22f00ff891410ff794c1c0879e10a51011c7ec
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da27c36e86fbec616f670eea7cf6f44ac00b01103ba631450b5687f812aaa463
+oid sha256:2661f04b964aebdbfc5fe2d76ad72c51b84450f62ecbdcf121c15876692362c9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.807974100112915,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.020814748736247397,
+  "best_metric": 2.7967422008514404,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.023788284269997028,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 46.666,
       "eval_steps_per_second": 11.666,
       "step": 350
+    },
+    {
+      "epoch": 0.021409455842997322,
+      "grad_norm": 0.6872610449790955,
+      "learning_rate": 4.738676287689473e-05,
+      "loss": 2.8492,
+      "step": 360
+    },
+    {
+      "epoch": 0.02200416294974725,
+      "grad_norm": 0.7925031781196594,
+      "learning_rate": 4.131639140249173e-05,
+      "loss": 2.8009,
+      "step": 370
+    },
+    {
+      "epoch": 0.022598870056497175,
+      "grad_norm": 0.9018983244895935,
+      "learning_rate": 3.5568459816422774e-05,
+      "loss": 2.8143,
+      "step": 380
+    },
+    {
+      "epoch": 0.0231935771632471,
+      "grad_norm": 1.0778685808181763,
+      "learning_rate": 3.017097146359502e-05,
+      "loss": 2.7583,
+      "step": 390
+    },
+    {
+      "epoch": 0.023788284269997028,
+      "grad_norm": 1.6764299869537354,
+      "learning_rate": 2.5150222364709875e-05,
+      "loss": 2.7238,
+      "step": 400
+    },
+    {
+      "epoch": 0.023788284269997028,
+      "eval_loss": 2.7967422008514404,
+      "eval_runtime": 152.1562,
+      "eval_samples_per_second": 46.531,
+      "eval_steps_per_second": 11.633,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3712914649251840.0,
+  "total_flos": 4231100552970240.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null