Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6455d4b7af10d1445a14b73e3fe3ec2e8292ab3064f86bf736405cf0884354bd
+oid sha256:cb3ea876a7fe85fca40c5023bd730c54c0df2a7314193d9605599f1a422c60ad
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5937866af6baa7d285fd2ad82fcec11748b41fa822dd3ed9ab7124df3ab1ec
+oid sha256:607d068de53dd73ec39a6769e13c3680815b15df620291b5733eaea29d49f77b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ea5395be9f3770f7d0e563c3e4fee06b4570ed277072c3eacc3ff5b4a8799d3
+oid sha256:4b27ec6d313848d7f46276ecd0ba150ca6b07f29b12cf2bbd5620c9f4a819644
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c22ab587f148e086318213ddb462011853925e47b27a2e90d9c4fb549c894eb
+oid sha256:5ce6cab51d99c210bfad42a6e2c47702db9f85bcb4a0198d5cc71e0e655a4578
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5370ea3231d546738e2622fea4c71b80e31fcaf1c8918230c012c21860f89b99
+oid sha256:a11305ae74fe5c7fad4abc119227840c09e7979297322b0205372ffbba91942b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d4a6e460aeb8829c65826656dcc5d7dcbeabcebf5e3fe8cda40b200bc81fd8
+oid sha256:17824de924a6432b0997131923cf03e279c6d4e8151b0fb66fc9597b1ae59e46
 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": 0.7294516563415527,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07809449433814916,
+  "best_metric": 0.6960844397544861,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15618898867629832,
   "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": 34.547,
       "eval_steps_per_second": 4.324,
       "step": 25
+    },
+    {
+      "epoch": 0.08121827411167512,
+      "grad_norm": 20.791725158691406,
+      "learning_rate": 5e-05,
+      "loss": 0.6133,
+      "step": 26
+    },
+    {
+      "epoch": 0.0843420538852011,
+      "grad_norm": 25.42897605895996,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6555,
+      "step": 27
+    },
+    {
+      "epoch": 0.08746583365872707,
+      "grad_norm": 24.95623779296875,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7177,
+      "step": 28
+    },
+    {
+      "epoch": 0.09058961343225302,
+      "grad_norm": 25.04736328125,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6268,
+      "step": 29
+    },
+    {
+      "epoch": 0.093713393205779,
+      "grad_norm": 25.7648983001709,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6801,
+      "step": 30
+    },
+    {
+      "epoch": 0.09683717297930496,
+      "grad_norm": 21.772857666015625,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6209,
+      "step": 31
+    },
+    {
+      "epoch": 0.09996095275283093,
+      "grad_norm": 23.983652114868164,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6367,
+      "step": 32
+    },
+    {
+      "epoch": 0.10308473252635689,
+      "grad_norm": 25.340946197509766,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6879,
+      "step": 33
+    },
+    {
+      "epoch": 0.10620851229988286,
+      "grad_norm": 27.262245178222656,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.82,
+      "step": 34
+    },
+    {
+      "epoch": 0.10933229207340882,
+      "grad_norm": 29.177738189697266,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7947,
+      "step": 35
+    },
+    {
+      "epoch": 0.11245607184693479,
+      "grad_norm": 29.051311492919922,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7873,
+      "step": 36
+    },
+    {
+      "epoch": 0.11557985162046076,
+      "grad_norm": 31.636856079101562,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.809,
+      "step": 37
+    },
+    {
+      "epoch": 0.11870363139398672,
+      "grad_norm": 23.124906539916992,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6913,
+      "step": 38
+    },
+    {
+      "epoch": 0.1218274111675127,
+      "grad_norm": 15.812859535217285,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4575,
+      "step": 39
+    },
+    {
+      "epoch": 0.12495119094103865,
+      "grad_norm": 19.333393096923828,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5977,
+      "step": 40
+    },
+    {
+      "epoch": 0.1280749707145646,
+      "grad_norm": 20.976985931396484,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6742,
+      "step": 41
+    },
+    {
+      "epoch": 0.1311987504880906,
+      "grad_norm": 23.88761329650879,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.654,
+      "step": 42
+    },
+    {
+      "epoch": 0.13432253026161656,
+      "grad_norm": 26.551042556762695,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6539,
+      "step": 43
+    },
+    {
+      "epoch": 0.13744631003514252,
+      "grad_norm": 25.536396026611328,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7266,
+      "step": 44
+    },
+    {
+      "epoch": 0.1405700898086685,
+      "grad_norm": 27.101118087768555,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7213,
+      "step": 45
+    },
+    {
+      "epoch": 0.14369386958219446,
+      "grad_norm": 23.394760131835938,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6518,
+      "step": 46
+    },
+    {
+      "epoch": 0.14681764935572042,
+      "grad_norm": 27.829160690307617,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7054,
+      "step": 47
+    },
+    {
+      "epoch": 0.14994142912924638,
+      "grad_norm": 26.184154510498047,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6976,
+      "step": 48
+    },
+    {
+      "epoch": 0.15306520890277237,
+      "grad_norm": 28.922327041625977,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7447,
+      "step": 49
+    },
+    {
+      "epoch": 0.15618898867629832,
+      "grad_norm": 30.464828491210938,
+      "learning_rate": 0.0,
+      "loss": 0.8527,
+      "step": 50
+    },
+    {
+      "epoch": 0.15618898867629832,
+      "eval_loss": 0.6960844397544861,
+      "eval_runtime": 62.4671,
+      "eval_samples_per_second": 34.53,
+      "eval_steps_per_second": 4.322,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null