Training in progress, step 41, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e800c35b11bfe1a08f96f05b791883d39e163009abc37ebeb8e92ff69b34f0
+oid sha256:61cede1e185ec7dbf624104fb40eb9fc0bc03a895e60dbede0c8424afa307e97
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:450b130cb7a2541a409ea797a151003a331b93d7d141da66fa847940f03534d6
+oid sha256:119de6ebbe444568eb36723df3a483c1d702c8540c9fd99672a4810e73669d70
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410e2e49b2a3df2460526fdb53ed937cecd126897972ff2f8737560e70bfe1cf
+oid sha256:dcb0eaa78b52c694c4941dc594e523bb92074f050c8e5b75b886bbdbc029cf8c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba1bb77e54d811be9e2894d17f12d5cb8eb4d1271696e61997d71cdeeb70690
+oid sha256:4d19f5db0b5ed7101391ecc181bbc7740a892ec2d257f4fb3a05a75fb2983ffc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f02f2c1321c3583d30f05af9c0b644720d402ddd65eaa5cc01bebd3e70b05d1f
+oid sha256:e4f4bdf438cca51a87dc2daf2aeb8c9a8957897ddaddf4f5c2677f7a21a1a4b0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e70944ff7fd3a11ea61949dbae7aa37388d84cd2c47931ef61cc9c9ed2b0233
+oid sha256:b591e0c41c4e20d058a924efcc112547252452a6f6cf09b413b46484fa398053
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935c3511559349a68e0c75c3b87066ca7d4af7863dcb94ee59a533b76c75ad0c
+oid sha256:9a58533f5e61baaf0d295b9a19b1c4d2a6e1e9d96b361593f4d95a0f3cb76170
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7650135159492493,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8648018648018647,
+  "epoch": 3.058275058275058,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 41,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,118 @@
       "eval_samples_per_second": 11.419,
       "eval_steps_per_second": 2.969,
       "step": 25
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 13.958155632019043,
+      "learning_rate": 3.904278008308589e-05,
+      "loss": 23.0799,
+      "step": 26
+    },
+    {
+      "epoch": 2.013986013986014,
+      "grad_norm": 13.080740928649902,
+      "learning_rate": 3.570883473686256e-05,
+      "loss": 22.7616,
+      "step": 27
+    },
+    {
+      "epoch": 2.0885780885780885,
+      "grad_norm": 9.918713569641113,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 22.2095,
+      "step": 28
+    },
+    {
+      "epoch": 2.163170163170163,
+      "grad_norm": 12.069844245910645,
+      "learning_rate": 2.9437086397097995e-05,
+      "loss": 21.0234,
+      "step": 29
+    },
+    {
+      "epoch": 2.237762237762238,
+      "grad_norm": 14.520157814025879,
+      "learning_rate": 2.6539958098208027e-05,
+      "loss": 21.4936,
+      "step": 30
+    },
+    {
+      "epoch": 2.312354312354312,
+      "grad_norm": 9.91746711730957,
+      "learning_rate": 2.3827404092068032e-05,
+      "loss": 20.1627,
+      "step": 31
+    },
+    {
+      "epoch": 2.386946386946387,
+      "grad_norm": 11.826277732849121,
+      "learning_rate": 2.1317016332300447e-05,
+      "loss": 21.355,
+      "step": 32
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 13.523852348327637,
+      "learning_rate": 1.902507564684246e-05,
+      "loss": 20.8342,
+      "step": 33
+    },
+    {
+      "epoch": 2.5361305361305364,
+      "grad_norm": 11.003284454345703,
+      "learning_rate": 1.6966446150529244e-05,
+      "loss": 20.2875,
+      "step": 34
+    },
+    {
+      "epoch": 2.6107226107226107,
+      "grad_norm": 11.648452758789062,
+      "learning_rate": 1.515447884560556e-05,
+      "loss": 21.3661,
+      "step": 35
+    },
+    {
+      "epoch": 2.6853146853146854,
+      "grad_norm": 13.226274490356445,
+      "learning_rate": 1.3600925035352913e-05,
+      "loss": 20.4063,
+      "step": 36
+    },
+    {
+      "epoch": 2.7599067599067597,
+      "grad_norm": 12.421295166015625,
+      "learning_rate": 1.2315860112378455e-05,
+      "loss": 20.5653,
+      "step": 37
+    },
+    {
+      "epoch": 2.8344988344988344,
+      "grad_norm": 11.139906883239746,
+      "learning_rate": 1.130761821582766e-05,
+      "loss": 21.522,
+      "step": 38
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 12.317776679992676,
+      "learning_rate": 1.0582738181293923e-05,
+      "loss": 21.0642,
+      "step": 39
+    },
+    {
+      "epoch": 2.983682983682984,
+      "grad_norm": 13.74180793762207,
+      "learning_rate": 1.0145921133960554e-05,
+      "loss": 20.5685,
+      "step": 40
+    },
+    {
+      "epoch": 3.058275058275058,
+      "grad_norm": 10.381887435913086,
+      "learning_rate": 1e-05,
+      "loss": 21.0001,
+      "step": 41
     }
   ],
   "logging_steps": 1,
@@ -221,12 +333,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.829013890367488e+17,
+  "total_flos": 4.63958278020268e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null