Training in progress, step 175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133647ff75619b2ebf4b08b1907148f54f64d50a6540006b8b0cfd3d268e67a7
+oid sha256:87f943437f6682f7ee7de160a0fb0dd7f1a7f9b7c1e5cb4bc2beb7dea62371d6
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b780e0bdd236c892f8c7d0c7d4afe550217aba06b3560dacba4ce990ecece4b
+oid sha256:844a482769f0e2abd40ad13846907ca880baf715442ba45b6595fb1d2992d4c5
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d6427d6aa68c158ad80f76946f6fc44629c698f67492b8fb6d643dbc5eef98
+oid sha256:5eafd79e713363198747e3075dba58fd79e2d3d1300105438732b2e0ee683c97
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2caf50116db0368fab40b4e34ae3b0c9f1a86e9da0bc7a8de5ff785b985711a
+oid sha256:c4a1fd21f28f132126ba0a3c0e9b7867579d24daca77e2d8e14bc16542a7a830
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a955dabcc60ffe276aa50f92c60f21389f3a28e5589c5c081037f1d66876c9a3
+oid sha256:d98523765fbe4ee7d22ab0a5ea68e4b5406a21e1b54e1b37a5358bbc38419dcd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1380d7d4f110826396b67714006bc18fde61d5c81581b3cc018f32e55772014
+oid sha256:1907ecded23c99f86058c3975d42bb30b996a62807a726ac4088c81af5fe16c9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148dc60fce7a98d209219ab65863631c40408a69d4537618751b3440fe762b40
+oid sha256:f9f689e3fd5df575eecb35b5e9b27f49e75a860ed67ef4150a0d2749c11e5d42
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.842964704541373e-06,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.3313315386208325,
+  "best_metric": 2.7154196686751675e-06,
+  "best_model_checkpoint": "miner_id_24/checkpoint-175",
+  "epoch": 0.38655346172430455,
   "eval_steps": 25,
-  "global_step": 150,
+  "global_step": 175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1113,6 +1113,189 @@
       "eval_samples_per_second": 23.771,
       "eval_steps_per_second": 6.18,
       "step": 150
+    },
+    {
+      "epoch": 0.3335404155449714,
+      "grad_norm": 0.000154680063133128,
+      "learning_rate": 2.370508142456748e-05,
+      "loss": 0.0,
+      "step": 151
+    },
+    {
+      "epoch": 0.3357492924691102,
+      "grad_norm": 0.00023134062939789146,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 152
+    },
+    {
+      "epoch": 0.33795816939324913,
+      "grad_norm": 0.00024014056543819606,
+      "learning_rate": 2.2663827199913588e-05,
+      "loss": 0.0,
+      "step": 153
+    },
+    {
+      "epoch": 0.340167046317388,
+      "grad_norm": 0.00021546079369727522,
+      "learning_rate": 2.215611672859741e-05,
+      "loss": 0.0,
+      "step": 154
+    },
+    {
+      "epoch": 0.3423759232415269,
+      "grad_norm": 0.00024820741964504123,
+      "learning_rate": 2.165719935902685e-05,
+      "loss": 0.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.3445848001656658,
+      "grad_norm": 0.00044995194184593856,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 156
+    },
+    {
+      "epoch": 0.34679367708980463,
+      "grad_norm": 0.00015662639634683728,
+      "learning_rate": 2.068627582421254e-05,
+      "loss": 0.0,
+      "step": 157
+    },
+    {
+      "epoch": 0.34900255401394353,
+      "grad_norm": 9.385013981955126e-05,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 0.0,
+      "step": 158
+    },
+    {
+      "epoch": 0.35121143093808244,
+      "grad_norm": 9.166620293399319e-05,
+      "learning_rate": 1.9752096284710738e-05,
+      "loss": 0.0,
+      "step": 159
+    },
+    {
+      "epoch": 0.3534203078622213,
+      "grad_norm": 9.074221452465281e-05,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.3556291847863602,
+      "grad_norm": 9.394592780154198e-05,
+      "learning_rate": 1.8855661083370986e-05,
+      "loss": 0.0,
+      "step": 161
+    },
+    {
+      "epoch": 0.3578380617104991,
+      "grad_norm": 9.24318956094794e-05,
+      "learning_rate": 1.842189919337732e-05,
+      "loss": 0.0,
+      "step": 162
+    },
+    {
+      "epoch": 0.36004693863463794,
+      "grad_norm": 0.00011218286090297624,
+      "learning_rate": 1.7997930145460136e-05,
+      "loss": 0.0,
+      "step": 163
+    },
+    {
+      "epoch": 0.36225581555877684,
+      "grad_norm": 0.00019017797603737563,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 164
+    },
+    {
+      "epoch": 0.36446469248291574,
+      "grad_norm": 0.00019140807853545994,
+      "learning_rate": 1.7179821950750284e-05,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.3666735694070546,
+      "grad_norm": 0.00020481123647186905,
+      "learning_rate": 1.6785901831303956e-05,
+      "loss": 0.0,
+      "step": 166
+    },
+    {
+      "epoch": 0.3688824463311935,
+      "grad_norm": 0.00022451799304690212,
+      "learning_rate": 1.6402212549987762e-05,
+      "loss": 0.0,
+      "step": 167
+    },
+    {
+      "epoch": 0.37109132325533234,
+      "grad_norm": 0.00030974153196439147,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 0.37330020017947124,
+      "grad_norm": 0.00048727114335633814,
+      "learning_rate": 1.566593462679586e-05,
+      "loss": 0.0,
+      "step": 169
+    },
+    {
+      "epoch": 0.37550907710361014,
+      "grad_norm": 9.068298095371574e-05,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.377717954027749,
+      "grad_norm": 9.067923383554444e-05,
+      "learning_rate": 1.4971776606016482e-05,
+      "loss": 0.0,
+      "step": 171
+    },
+    {
+      "epoch": 0.3799268309518879,
+      "grad_norm": 9.05448105186224e-05,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 172
+    },
+    {
+      "epoch": 0.3821357078760268,
+      "grad_norm": 9.20113452593796e-05,
+      "learning_rate": 1.4320481809445051e-05,
+      "loss": 0.0,
+      "step": 173
+    },
+    {
+      "epoch": 0.38434458480016565,
+      "grad_norm": 9.098761074710637e-05,
+      "learning_rate": 1.4011127878547087e-05,
+      "loss": 0.0,
+      "step": 174
+    },
+    {
+      "epoch": 0.38655346172430455,
+      "grad_norm": 9.139224857790396e-05,
+      "learning_rate": 1.3712747659862896e-05,
+      "loss": 0.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.38655346172430455,
+      "eval_loss": 2.7154196686751675e-06,
+      "eval_runtime": 2.0847,
+      "eval_samples_per_second": 23.985,
+      "eval_steps_per_second": 6.236,
+      "step": 175
     }
   ],
   "logging_steps": 1,
@@ -1141,7 +1324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.87442683527168e+17,
+  "total_flos": 5.68683130781696e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null