Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9d51b81cbc9a30b605c8a130bad4af4c7eb843dfcff35c0acefa3659dc1eb7
+oid sha256:85afb57401fef2ffe001fbd733539f0c9e193a3d9986d9a9dac380460f488389
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84742f93e6a6c79b8abbd480e11e85552d1a19fab95f67d261d2d2c4fad3846e
+oid sha256:475a8dc75bc6b9173a49038ed47904c15f9651f972ce2f2954ef98febf900364
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7b48e906cfa3e580bbca17fc33437a8abc6a94e265d1646eeeb5e213371bec
+oid sha256:899dfa54727969c4bf5d5667a150ece40f05293e491ed37e27aa6f5befc13734
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c85205e74efcdf28bb9a4e53bec1c15a39f84872ee41429a5460c4047bfa5a43
+oid sha256:7483b7b2eef910a669e6189dbbaa2a9217b4210229f67bd79795a30d3437ac60
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50253399bb198706c940b602503a58c29f78114476ce0717aaa4c4cc337fa8e1
+oid sha256:6aa0a813e794ebd13c1dde873e4a38bfd5f40fc6d2c52ceddc3db8870dfafc06
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9048736bcd6dd224dec837acb4e31279c64886894f5a9aa8920f145f1e901d06
+oid sha256:051f2768a56943a0b743bacd33b424d1a3a53b82bc0c5e162f25f3d603c7b82e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8275464177131653,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006595000989250148,
+  "best_metric": 0.7286787033081055,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013190001978500296,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 55.224,
       "eval_steps_per_second": 6.905,
       "step": 25
+    },
+    {
+      "epoch": 0.006858801028820154,
+      "grad_norm": 3.8096213340759277,
+      "learning_rate": 5e-05,
+      "loss": 1.1405,
+      "step": 26
+    },
+    {
+      "epoch": 0.00712260106839016,
+      "grad_norm": 3.760140895843506,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0925,
+      "step": 27
+    },
+    {
+      "epoch": 0.007386401107960166,
+      "grad_norm": 2.723322629928589,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.0105,
+      "step": 28
+    },
+    {
+      "epoch": 0.007650201147530172,
+      "grad_norm": 1.6143128871917725,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.925,
+      "step": 29
+    },
+    {
+      "epoch": 0.007914001187100178,
+      "grad_norm": 0.2784794270992279,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.69,
+      "step": 30
+    },
+    {
+      "epoch": 0.008177801226670185,
+      "grad_norm": 0.36772847175598145,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6823,
+      "step": 31
+    },
+    {
+      "epoch": 0.00844160126624019,
+      "grad_norm": 0.23856256902217865,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6923,
+      "step": 32
+    },
+    {
+      "epoch": 0.008705401305810196,
+      "grad_norm": 0.3167315423488617,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.68,
+      "step": 33
+    },
+    {
+      "epoch": 0.008969201345380201,
+      "grad_norm": 0.2358066588640213,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6755,
+      "step": 34
+    },
+    {
+      "epoch": 0.009233001384950208,
+      "grad_norm": 0.300946980714798,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6979,
+      "step": 35
+    },
+    {
+      "epoch": 0.009496801424520213,
+      "grad_norm": 0.3268861174583435,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6988,
+      "step": 36
+    },
+    {
+      "epoch": 0.00976060146409022,
+      "grad_norm": 0.260076105594635,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6752,
+      "step": 37
+    },
+    {
+      "epoch": 0.010024401503660225,
+      "grad_norm": 0.826528787612915,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8173,
+      "step": 38
+    },
+    {
+      "epoch": 0.010288201543230232,
+      "grad_norm": 1.0106130838394165,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8638,
+      "step": 39
+    },
+    {
+      "epoch": 0.010552001582800237,
+      "grad_norm": 0.8522423505783081,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8284,
+      "step": 40
+    },
+    {
+      "epoch": 0.010815801622370244,
+      "grad_norm": 0.817550778388977,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.831,
+      "step": 41
+    },
+    {
+      "epoch": 0.011079601661940249,
+      "grad_norm": 0.3556511104106903,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7595,
+      "step": 42
+    },
+    {
+      "epoch": 0.011343401701510256,
+      "grad_norm": 0.33497169613838196,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6843,
+      "step": 43
+    },
+    {
+      "epoch": 0.01160720174108026,
+      "grad_norm": 0.36886918544769287,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.681,
+      "step": 44
+    },
+    {
+      "epoch": 0.011871001780650267,
+      "grad_norm": 0.33282706141471863,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6874,
+      "step": 45
+    },
+    {
+      "epoch": 0.012134801820220273,
+      "grad_norm": 0.3662412166595459,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6908,
+      "step": 46
+    },
+    {
+      "epoch": 0.01239860185979028,
+      "grad_norm": 0.3355032205581665,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.694,
+      "step": 47
+    },
+    {
+      "epoch": 0.012662401899360284,
+      "grad_norm": 0.4087969958782196,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6739,
+      "step": 48
+    },
+    {
+      "epoch": 0.012926201938930291,
+      "grad_norm": 0.3180367350578308,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6981,
+      "step": 49
+    },
+    {
+      "epoch": 0.013190001978500296,
+      "grad_norm": 0.3914031684398651,
+      "learning_rate": 0.0,
+      "loss": 0.6933,
+      "step": 50
+    },
+    {
+      "epoch": 0.013190001978500296,
+      "eval_loss": 0.7286787033081055,
+      "eval_runtime": 462.8508,
+      "eval_samples_per_second": 55.175,
+      "eval_steps_per_second": 6.899,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null