Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ed1a959d8007b175b9b4889ab51e78dece828b975ea7fb2460344a95f49b0c6
+oid sha256:c765adb44001dcaafe5e4fa228a343b596f48419e58cfb4191cb938ad75e7128
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04fc597453c99acc9d62a6a458584722b3fdd5dc4ed7cb9e7e61c01df9e5caf0
+oid sha256:848c3df4e68058a955179856299e857124aa1d1293eaed6decbbed086123a5c5
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab520cc199ab160eef65d5d172aedd6d2987741847f79baf9be3bae2ba3fe17
+oid sha256:67ee7487665d86cc21b2cfe4a7fe232b6a94f2556632e305c35871f10d991211
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:530505d607699f384741067a5f9139d72f043713adb680898a3f1b5714170c97
+oid sha256:5182c64d745614fbc9217a3122cffdaa4b9683ea7cfb2e6909f3ad8f175d0a03
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5775735974311829,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.015969817045783468,
+  "best_metric": 0.520143449306488,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.019962271307229336,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,21 @@
       "eval_samples_per_second": 14.977,
       "eval_steps_per_second": 7.489,
       "step": 200
+    },
+    {
+      "epoch": 0.019163780454940164,
+      "grad_norm": 28.21241569519043,
+      "learning_rate": 5e-05,
+      "loss": 4.1189,
+      "step": 240
+    },
+    {
+      "epoch": 0.019962271307229336,
+      "eval_loss": 0.520143449306488,
+      "eval_runtime": 704.7521,
+      "eval_samples_per_second": 14.966,
+      "eval_steps_per_second": 7.483,
+      "step": 250
     }
   ],
   "logging_steps": 40,
@@ -110,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.076947002025574e+16,
+  "total_flos": 8.845078670239334e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null