Training in progress, step 125, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4343dd8d1a3cae2275c1b0775c85aafda99ba00210dc9cbfd6d2effd170b7b85
+oid sha256:2ffdeb5b0c9971fd4bc708ae8ba9d156294e0fa22c2d672c50eadf3ad52077bf
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd42158c3831bab1671ace88d8baad72e71cdec3f442f9320594be4bf179907c
+oid sha256:c0d75bea1f854ccf45211b310ef21c23b2c3e9fe03ada188f67cb3c3c0c507ad
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c172fb92d30a3997e4403c7053678be36d697a289f64f1d5bf73cdcda2e89547
+oid sha256:9ab6246b153f475a1cdde00ee344148098f311283b1adf6e6374b9996f1ca3e4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eefced3cc3821b717603a74ca9084a0add144eee88dcae3a554a7a32cfb5b8c
+oid sha256:7a8648d725732dfec9ae63a9ea715300772f909153c68b13d81e34c831d011f1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f0a25f271ba57cea38506e22ec2fac7b5f3b817d44cfc3220b45decdd324f2
+oid sha256:46af0960f3c906cc2e5bbf35470d236ecdf9c1e2759ca612271f969d9eb4d0f1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62b20abbb823060076b1a3eb033cb16f6b5fc1c0d26dfa41bcc3cd89efd53e2e
+oid sha256:eda6132e8e3a8270c37166f87ddbff25c39b22434f57d397c3401c6ac5e73954
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88cf1ca29131bea6a1c678610dbfd2c6c90cc06115bb015c84ed8386046423a
+oid sha256:72e23a2d1e485599a7b5fae1501ffcbc43db47e90bf1e1f6de6ac821e4368041
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.012017174623906612,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.48869883934025654,
+  "best_metric": 0.006207775324583054,
+  "best_model_checkpoint": "miner_id_24/checkpoint-125",
+  "epoch": 0.6108735491753207,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -747,6 +747,189 @@
       "eval_samples_per_second": 15.522,
       "eval_steps_per_second": 4.036,
       "step": 100
+    },
+    {
+      "epoch": 0.4935858277336591,
+      "grad_norm": 0.24904842674732208,
+      "learning_rate": 3.3355505398627566e-05,
+      "loss": 0.0339,
+      "step": 101
+    },
+    {
+      "epoch": 0.4984728161270617,
+      "grad_norm": 0.2502872347831726,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0348,
+      "step": 102
+    },
+    {
+      "epoch": 0.5033598045204642,
+      "grad_norm": 0.27058976888656616,
+      "learning_rate": 3.165520338277653e-05,
+      "loss": 0.0306,
+      "step": 103
+    },
+    {
+      "epoch": 0.5082467929138669,
+      "grad_norm": 0.16723230481147766,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 0.0215,
+      "step": 104
+    },
+    {
+      "epoch": 0.5131337813072694,
+      "grad_norm": 0.2476491630077362,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0243,
+      "step": 105
+    },
+    {
+      "epoch": 0.518020769700672,
+      "grad_norm": 0.16993577778339386,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.022,
+      "step": 106
+    },
+    {
+      "epoch": 0.5229077580940745,
+      "grad_norm": 0.20630362629890442,
+      "learning_rate": 2.8391065823638806e-05,
+      "loss": 0.0214,
+      "step": 107
+    },
+    {
+      "epoch": 0.527794746487477,
+      "grad_norm": 0.18468116223812103,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0224,
+      "step": 108
+    },
+    {
+      "epoch": 0.5326817348808797,
+      "grad_norm": 0.12725146114826202,
+      "learning_rate": 2.6833443751717347e-05,
+      "loss": 0.0101,
+      "step": 109
+    },
+    {
+      "epoch": 0.5375687232742822,
+      "grad_norm": 0.14481593668460846,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.0165,
+      "step": 110
+    },
+    {
+      "epoch": 0.5424557116676848,
+      "grad_norm": 0.14558053016662598,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0191,
+      "step": 111
+    },
+    {
+      "epoch": 0.5473427000610873,
+      "grad_norm": 0.09826002269983292,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 0.005,
+      "step": 112
+    },
+    {
+      "epoch": 0.5522296884544899,
+      "grad_norm": 0.2601858973503113,
+      "learning_rate": 2.3881912489797885e-05,
+      "loss": 0.0232,
+      "step": 113
+    },
+    {
+      "epoch": 0.5571166768478925,
+      "grad_norm": 0.2997516393661499,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0294,
+      "step": 114
+    },
+    {
+      "epoch": 0.5620036652412951,
+      "grad_norm": 0.2502405345439911,
+      "learning_rate": 2.2493621707311002e-05,
+      "loss": 0.0341,
+      "step": 115
+    },
+    {
+      "epoch": 0.5668906536346976,
+      "grad_norm": 0.21258173882961273,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 0.0251,
+      "step": 116
+    },
+    {
+      "epoch": 0.5717776420281002,
+      "grad_norm": 0.2167203426361084,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0233,
+      "step": 117
+    },
+    {
+      "epoch": 0.5766646304215027,
+      "grad_norm": 0.20736785233020782,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.0238,
+      "step": 118
+    },
+    {
+      "epoch": 0.5815516188149054,
+      "grad_norm": 0.18189823627471924,
+      "learning_rate": 1.9905198260820328e-05,
+      "loss": 0.0239,
+      "step": 119
+    },
+    {
+      "epoch": 0.5864386072083079,
+      "grad_norm": 0.17831675708293915,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0139,
+      "step": 120
+    },
+    {
+      "epoch": 0.5913255956017105,
+      "grad_norm": 0.17311929166316986,
+      "learning_rate": 1.8709992807963285e-05,
+      "loss": 0.0155,
+      "step": 121
+    },
+    {
+      "epoch": 0.596212583995113,
+      "grad_norm": 0.21193860471248627,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.0138,
+      "step": 122
+    },
+    {
+      "epoch": 0.6010995723885155,
+      "grad_norm": 0.12439697980880737,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0081,
+      "step": 123
+    },
+    {
+      "epoch": 0.6059865607819181,
+      "grad_norm": 0.1485549807548523,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.0061,
+      "step": 124
+    },
+    {
+      "epoch": 0.6108735491753207,
+      "grad_norm": 0.0644276961684227,
+      "learning_rate": 1.6528965819717413e-05,
+      "loss": 0.002,
+      "step": 125
+    },
+    {
+      "epoch": 0.6108735491753207,
+      "eval_loss": 0.006207775324583054,
+      "eval_runtime": 3.2392,
+      "eval_samples_per_second": 15.436,
+      "eval_steps_per_second": 4.013,
+      "step": 125
     }
   ],
   "logging_steps": 1,
@@ -775,7 +958,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1248115621298176e+18,
+  "total_flos": 1.406014452662272e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null