Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da37c1a0562d46fd08eb2aa1c67262c981ea407256a11a7301cbcc3a56a8eb7
+oid sha256:0796183b56306d91d8a4eeb8848efacf991fc71502af9d50091c01784dbcac35
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d98db4fcbe8c532c61fd9cea6cc05a1d2a34302f8cca0820d9af0e03522b7e2
+oid sha256:e1d108eb4fa0868aa8b0a22e97a779667623e129abb8c840569c3207844dd9b5
 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": 0.8253557085990906,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006595000989250148,
+  "best_metric": 0.7304301857948303,
+  "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": 54.816,
       "eval_steps_per_second": 6.854,
       "step": 25
+    },
+    {
+      "epoch": 0.006858801028820154,
+      "grad_norm": 3.363541841506958,
+      "learning_rate": 5e-05,
+      "loss": 1.1241,
+      "step": 26
+    },
+    {
+      "epoch": 0.00712260106839016,
+      "grad_norm": 3.3168773651123047,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0803,
+      "step": 27
+    },
+    {
+      "epoch": 0.007386401107960166,
+      "grad_norm": 2.484935760498047,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.0032,
+      "step": 28
+    },
+    {
+      "epoch": 0.007650201147530172,
+      "grad_norm": 1.3965139389038086,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9157,
+      "step": 29
+    },
+    {
+      "epoch": 0.007914001187100178,
+      "grad_norm": 0.3380748927593231,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6944,
+      "step": 30
+    },
+    {
+      "epoch": 0.008177801226670185,
+      "grad_norm": 0.3984104096889496,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6846,
+      "step": 31
+    },
+    {
+      "epoch": 0.00844160126624019,
+      "grad_norm": 0.26516708731651306,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6967,
+      "step": 32
+    },
+    {
+      "epoch": 0.008705401305810196,
+      "grad_norm": 0.3935666084289551,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.68,
+      "step": 33
+    },
+    {
+      "epoch": 0.008969201345380201,
+      "grad_norm": 0.43814966082572937,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6795,
+      "step": 34
+    },
+    {
+      "epoch": 0.009233001384950208,
+      "grad_norm": 0.38712698221206665,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6986,
+      "step": 35
+    },
+    {
+      "epoch": 0.009496801424520213,
+      "grad_norm": 0.4240443706512451,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6981,
+      "step": 36
+    },
+    {
+      "epoch": 0.00976060146409022,
+      "grad_norm": 0.2986938953399658,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6801,
+      "step": 37
+    },
+    {
+      "epoch": 0.010024401503660225,
+      "grad_norm": 0.8367800712585449,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8192,
+      "step": 38
+    },
+    {
+      "epoch": 0.010288201543230232,
+      "grad_norm": 1.0442923307418823,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8655,
+      "step": 39
+    },
+    {
+      "epoch": 0.010552001582800237,
+      "grad_norm": 0.9125483632087708,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8298,
+      "step": 40
+    },
+    {
+      "epoch": 0.010815801622370244,
+      "grad_norm": 0.8890961408615112,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8335,
+      "step": 41
+    },
+    {
+      "epoch": 0.011079601661940249,
+      "grad_norm": 0.3978463113307953,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7609,
+      "step": 42
+    },
+    {
+      "epoch": 0.011343401701510256,
+      "grad_norm": 0.41934147477149963,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6892,
+      "step": 43
+    },
+    {
+      "epoch": 0.01160720174108026,
+      "grad_norm": 0.4478147029876709,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6856,
+      "step": 44
+    },
+    {
+      "epoch": 0.011871001780650267,
+      "grad_norm": 0.41898518800735474,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6887,
+      "step": 45
+    },
+    {
+      "epoch": 0.012134801820220273,
+      "grad_norm": 0.4287898540496826,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6916,
+      "step": 46
+    },
+    {
+      "epoch": 0.01239860185979028,
+      "grad_norm": 0.4251207411289215,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6943,
+      "step": 47
+    },
+    {
+      "epoch": 0.012662401899360284,
+      "grad_norm": 0.4728756844997406,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6744,
+      "step": 48
+    },
+    {
+      "epoch": 0.012926201938930291,
+      "grad_norm": 0.43720823526382446,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7,
+      "step": 49
+    },
+    {
+      "epoch": 0.013190001978500296,
+      "grad_norm": 0.4983106255531311,
+      "learning_rate": 0.0,
+      "loss": 0.6954,
+      "step": 50
+    },
+    {
+      "epoch": 0.013190001978500296,
+      "eval_loss": 0.7304301857948303,
+      "eval_runtime": 465.7242,
+      "eval_samples_per_second": 54.835,
+      "eval_steps_per_second": 6.856,
+      "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