Training in progress, step 1350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:308c8112cd436e4e3cf0b4d1c1d899765b81713470eab2d742f0a53f08d8e8fb
+oid sha256:200a88f61a7e88a93fb00c5dc2da4ba537a81cd94444730c2f73356bcb9fa588
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87dbd6589d1029104817f2f43217594eb6430a5218ba1db9e5fb602f538d0ae4
+oid sha256:75023e07d60e4e00600120d9257e00fe03185b56bfc95b72efdb36dd2222933b
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a340e73e7fff823d019deed088bd52f0fc0271528bcd905e694a55cb4ced90
+oid sha256:ddf91ecd669f186faeccc2ddc419b2e245a4aca4accac80b04b3de8a0ea96372
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f130e00059750e08fde0557f1628570250cc11d981d01f55b80e33b935a3162
+oid sha256:6769de87f07ffd3568aa81b9a1fe6ecade894861382192b5a67c276923ba90ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.45658260583877563,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1200",
-  "epoch": 0.4549763033175355,
+  "best_metric": 0.4398421049118042,
+  "best_model_checkpoint": "miner_id_24/checkpoint-1350",
+  "epoch": 0.5118483412322274,
   "eval_steps": 150,
-  "global_step": 1200,
+  "global_step": 1350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -919,6 +919,119 @@
       "eval_samples_per_second": 21.043,
       "eval_steps_per_second": 5.263,
       "step": 1200
+    },
+    {
+      "epoch": 0.45876777251184836,
+      "grad_norm": 0.8443006277084351,
+      "learning_rate": 5.809736120478817e-05,
+      "loss": 0.7046,
+      "step": 1210
+    },
+    {
+      "epoch": 0.46255924170616114,
+      "grad_norm": 0.7299622893333435,
+      "learning_rate": 5.749783770253315e-05,
+      "loss": 0.4708,
+      "step": 1220
+    },
+    {
+      "epoch": 0.4663507109004739,
+      "grad_norm": 0.7422939538955688,
+      "learning_rate": 5.6897209353880885e-05,
+      "loss": 0.4123,
+      "step": 1230
+    },
+    {
+      "epoch": 0.47014218009478675,
+      "grad_norm": 0.723355770111084,
+      "learning_rate": 5.629556466462376e-05,
+      "loss": 0.3656,
+      "step": 1240
+    },
+    {
+      "epoch": 0.47393364928909953,
+      "grad_norm": 0.611301839351654,
+      "learning_rate": 5.5692992290317366e-05,
+      "loss": 0.2865,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4777251184834123,
+      "grad_norm": 0.7408523559570312,
+      "learning_rate": 5.508958102321666e-05,
+      "loss": 0.7044,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4815165876777251,
+      "grad_norm": 0.779376745223999,
+      "learning_rate": 5.448541977919195e-05,
+      "loss": 0.4626,
+      "step": 1270
+    },
+    {
+      "epoch": 0.48530805687203793,
+      "grad_norm": 0.824704110622406,
+      "learning_rate": 5.388059758462658e-05,
+      "loss": 0.4017,
+      "step": 1280
+    },
+    {
+      "epoch": 0.4890995260663507,
+      "grad_norm": 0.7132182717323303,
+      "learning_rate": 5.327520356329853e-05,
+      "loss": 0.3587,
+      "step": 1290
+    },
+    {
+      "epoch": 0.4928909952606635,
+      "grad_norm": 0.6510176062583923,
+      "learning_rate": 5.266932692324747e-05,
+      "loss": 0.2709,
+      "step": 1300
+    },
+    {
+      "epoch": 0.4966824644549763,
+      "grad_norm": 0.8185328245162964,
+      "learning_rate": 5.206305694362959e-05,
+      "loss": 0.6967,
+      "step": 1310
+    },
+    {
+      "epoch": 0.500473933649289,
+      "grad_norm": 0.8479395508766174,
+      "learning_rate": 5.1456482961561656e-05,
+      "loss": 0.4754,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5042654028436019,
+      "grad_norm": 0.7257512211799622,
+      "learning_rate": 5.084969435895691e-05,
+      "loss": 0.4183,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5080568720379147,
+      "grad_norm": 0.6470847725868225,
+      "learning_rate": 5.024278054935403e-05,
+      "loss": 0.3574,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5118483412322274,
+      "grad_norm": 0.5835993885993958,
+      "learning_rate": 4.963583096474159e-05,
+      "loss": 0.2612,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5118483412322274,
+      "eval_loss": 0.4398421049118042,
+      "eval_runtime": 211.1019,
+      "eval_samples_per_second": 21.042,
+      "eval_steps_per_second": 5.263,
+      "step": 1350
     }
   ],
   "logging_steps": 10,
@@ -947,7 +1060,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0646334581998879e+18,
+  "total_flos": 1.197948345721553e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null