Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c765adb44001dcaafe5e4fa228a343b596f48419e58cfb4191cb938ad75e7128
+oid sha256:81fa15356cbdb5fd8158560ba778294881796a36f68f01c33b7567c323fc1094
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848c3df4e68058a955179856299e857124aa1d1293eaed6decbbed086123a5c5
-size 170920084
+oid sha256:8cfb656c68350e00da72ec844c228b5d9c0d0bcf4cd65c61aae1ea515c9a3db6
+size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ee7487665d86cc21b2cfe4a7fe232b6a94f2556632e305c35871f10d991211
+oid sha256:c1efdf732dd61169b2f4e619b05c3fbdc2b1b0b1300f41ecf17dae6d087e8bfa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5182c64d745614fbc9217a3122cffdaa4b9683ea7cfb2e6909f3ad8f175d0a03
+oid sha256:ef9686b06e8feaa36ed10d72ecd8afef7e62f88744e516a900f077a3e6a083d3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.520143449306488,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.019962271307229336,
+  "best_metric": 0.4819493889808655,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.023954725568675204,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -97,6 +97,21 @@
       "eval_samples_per_second": 14.966,
       "eval_steps_per_second": 7.483,
       "step": 250
+    },
+    {
+      "epoch": 0.022357743864096856,
+      "grad_norm": 24.794347763061523,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.9716,
+      "step": 280
+    },
+    {
+      "epoch": 0.023954725568675204,
+      "eval_loss": 0.4819493889808655,
+      "eval_runtime": 704.0197,
+      "eval_samples_per_second": 14.981,
+      "eval_steps_per_second": 7.491,
+      "step": 300
     }
   ],
   "logging_steps": 40,
@@ -125,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.845078670239334e+16,
+  "total_flos": 1.0613210338453094e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null