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:ef14581cfc0e32625110beec8a4a65f7ed1eedab61002c36c6e04c4ac3f4c0be
+oid sha256:8206f4492acebb918c855dc08a1479e57f3d191ecc32919cc21fd48d56dde792
 size 377528296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e54d3b2673814aebd4e0edbc8431a422ae8ed98683876865c9565675cf3bf31
+oid sha256:06643b76c2431e767f32b5febcbe694ff755f8c15310de750555be39906941bb
 size 755217530

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f1e0f029b1dfa712a54d94d6e45fb695d174f80a9d7d5c23e7058b1ddca9d12
+oid sha256:14bdb1224fa3866ffd929a3755f37202aa4fd2c1c9f8c13adf5f5d9591bb6f77
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b6afed0b84f1936100f97590220e4446f2a47da9ae77868bcf01527f6b2b626
+oid sha256:b74ef7ec5e0c2da78d904c39d77afaad3eb387232b4e4947db30ba01b8efdc80
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ab60c497acb62a3282c99b7162dcde7a0d78ff0d672cde149f8dc8e397d339
+oid sha256:11f00ab22e8ed6d25fe102582e9c3aee37c046655c457e51713ad83a19e3fa87
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66990d24a1cd5d98a3b004f90ad0b18546206ce39e659f6385a60b75b1f3ba8e
+oid sha256:9151e0da569f7770085ccf7a5880110bd2e27599544cfa1e34f30158e39aa9bb
 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": 0.2917022407054901,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.032859607327692435,
+  "best_metric": 0.25369930267333984,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06571921465538487,
   "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": 27.454,
       "eval_steps_per_second": 3.433,
       "step": 25
+    },
+    {
+      "epoch": 0.034173991620800134,
+      "grad_norm": 39.145835876464844,
+      "learning_rate": 5e-05,
+      "loss": 0.2671,
+      "step": 26
+    },
+    {
+      "epoch": 0.03548837591390783,
+      "grad_norm": 13.07092571258545,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2708,
+      "step": 27
+    },
+    {
+      "epoch": 0.03680276020701553,
+      "grad_norm": 13.324690818786621,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2022,
+      "step": 28
+    },
+    {
+      "epoch": 0.038117144500123226,
+      "grad_norm": 7.191089153289795,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1898,
+      "step": 29
+    },
+    {
+      "epoch": 0.03943152879323092,
+      "grad_norm": 19.806900024414062,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2829,
+      "step": 30
+    },
+    {
+      "epoch": 0.04074591308633862,
+      "grad_norm": 36.52785873413086,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4437,
+      "step": 31
+    },
+    {
+      "epoch": 0.04206029737944632,
+      "grad_norm": 32.967159271240234,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4069,
+      "step": 32
+    },
+    {
+      "epoch": 0.04337468167255401,
+      "grad_norm": 28.414072036743164,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3775,
+      "step": 33
+    },
+    {
+      "epoch": 0.04468906596566171,
+      "grad_norm": 23.762981414794922,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3371,
+      "step": 34
+    },
+    {
+      "epoch": 0.04600345025876941,
+      "grad_norm": 20.14028549194336,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3427,
+      "step": 35
+    },
+    {
+      "epoch": 0.0473178345518771,
+      "grad_norm": 13.396416664123535,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3186,
+      "step": 36
+    },
+    {
+      "epoch": 0.0486322188449848,
+      "grad_norm": 17.807111740112305,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2514,
+      "step": 37
+    },
+    {
+      "epoch": 0.0499466031380925,
+      "grad_norm": 26.70073890686035,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2482,
+      "step": 38
+    },
+    {
+      "epoch": 0.051260987431200195,
+      "grad_norm": 27.880258560180664,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.268,
+      "step": 39
+    },
+    {
+      "epoch": 0.052575371724307894,
+      "grad_norm": 24.239660263061523,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2833,
+      "step": 40
+    },
+    {
+      "epoch": 0.053889756017415594,
+      "grad_norm": 29.972881317138672,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2505,
+      "step": 41
+    },
+    {
+      "epoch": 0.055204140310523286,
+      "grad_norm": 20.25796127319336,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2796,
+      "step": 42
+    },
+    {
+      "epoch": 0.056518524603630986,
+      "grad_norm": 12.335623741149902,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2809,
+      "step": 43
+    },
+    {
+      "epoch": 0.057832908896738686,
+      "grad_norm": 16.632577896118164,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2659,
+      "step": 44
+    },
+    {
+      "epoch": 0.05914729318984638,
+      "grad_norm": 12.694944381713867,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2621,
+      "step": 45
+    },
+    {
+      "epoch": 0.06046167748295408,
+      "grad_norm": 7.574565887451172,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.296,
+      "step": 46
+    },
+    {
+      "epoch": 0.06177606177606178,
+      "grad_norm": 7.663303375244141,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3015,
+      "step": 47
+    },
+    {
+      "epoch": 0.06309044606916947,
+      "grad_norm": 7.7631049156188965,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3052,
+      "step": 48
+    },
+    {
+      "epoch": 0.06440483036227718,
+      "grad_norm": 8.332027435302734,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2844,
+      "step": 49
+    },
+    {
+      "epoch": 0.06571921465538487,
+      "grad_norm": 6.904819965362549,
+      "learning_rate": 0.0,
+      "loss": 0.2775,
+      "step": 50
+    },
+    {
+      "epoch": 0.06571921465538487,
+      "eval_loss": 0.25369930267333984,
+      "eval_runtime": 186.8409,
+      "eval_samples_per_second": 27.435,
+      "eval_steps_per_second": 3.431,
+      "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": 4.592319693062144e+17,
+  "total_flos": 9.184639386124288e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null