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:d568bbf30866680f2b316648397aaa1eaaeb71aec1cdc8bc3eefbf567b036b67
+oid sha256:435cb9ffb6dba1b1bca47db7df00e5b4a0c86489433192deba7487d14b10440a
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b864e4915debf585f649396d83492cfd3530c10dc0660cc633b93c69abce468a
+oid sha256:35d4a927b1f10c2eb0bcb89348b1ada8098e08a742dbca066edb1b809f494dc0
 size 418094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9733b22e472c583b854a467b7a3050d1ffab341c776cc21a7b78eab5492e85cc
+oid sha256:c44b074319deaa330dbf9fbcc287dd8e1e161bc5b931e9fb7621646bc763b5e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f909eae7da558935f88a00ce26b4da28103d4b055b9a1258f5dcd1e98716dcb2
+oid sha256:18572f0adae215b3259455cf96083d95e78dc1ab7af393890cd3753bf61cc9f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.795702934265137,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.08234325373485472,
+  "best_metric": 6.793699741363525,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.09410657569697682,
   "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": 549.37,
       "eval_steps_per_second": 137.496,
       "step": 350
+    },
+    {
+      "epoch": 0.08469591812727914,
+      "grad_norm": 0.5708802342414856,
+      "learning_rate": 4.7166359328630106e-05,
+      "loss": 6.8333,
+      "step": 360
+    },
+    {
+      "epoch": 0.08704858251970357,
+      "grad_norm": 0.5529999136924744,
+      "learning_rate": 4.112422214015456e-05,
+      "loss": 6.8258,
+      "step": 370
+    },
+    {
+      "epoch": 0.08940124691212799,
+      "grad_norm": 0.6375375390052795,
+      "learning_rate": 3.5403025119602206e-05,
+      "loss": 6.7989,
+      "step": 380
+    },
+    {
+      "epoch": 0.0917539113045524,
+      "grad_norm": 0.974999189376831,
+      "learning_rate": 3.0030641363764346e-05,
+      "loss": 6.751,
+      "step": 390
+    },
+    {
+      "epoch": 0.09410657569697682,
+      "grad_norm": 1.1716803312301636,
+      "learning_rate": 2.5033244586269365e-05,
+      "loss": 6.7699,
+      "step": 400
+    },
+    {
+      "epoch": 0.09410657569697682,
+      "eval_loss": 6.793699741363525,
+      "eval_runtime": 3.2263,
+      "eval_samples_per_second": 554.821,
+      "eval_steps_per_second": 138.86,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 840987033600.0,
+  "total_flos": 961128038400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null