Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9027a2302979f3b05064e7e3df81289b44105971da55ecb69ada68d2c7d4d571
+oid sha256:57fd458df2ab8a1cc7d9875bef82b6f5d6d55f8118f7a2e6f08a05162fe18fb2
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e152533a5df1711f4d6f0060f13a6f25dbfe3e02eb99b459230676fbf86c8834
+oid sha256:2133e6022db3d0af6bfe62de6f6e1febf1f18195aa2f7aaf11788d1629f7f7a2
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f2d5a1f4be87966729e791c26915ff5eaa0a4f40dc60925b391fb853059c2d
+oid sha256:9610de6acc9c8d87cb2fa71bdaa9df7f969b149a16bd9c65600e9377c19c82cc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ad250d1afca7c73828dc9d424e4a8161613e55298935612b41a5ba8bbdc9e6
+oid sha256:9e4c637cb8fd51463926423b49dfd1dad9ec1d4e25ba4564d8db51c9cd8e199b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f50572a766a759b3384985e5553c20deb283faf37f1315e5dc1c00c50ade9052
+oid sha256:bedfcbe15fa4ce3116a656a934f2e3c1768696b0f68618c1564ec719b7648a7d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3346ded1c115353968f12e04330b11ad7f499d713e6d49c9411d0c4187d98617
+oid sha256:ea0caadbfc39d3f22e74593429461783f46a45fd6b6119d1ddefc0169aaa77c8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7746735215187073,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6808510638297872,
+  "best_metric": 0.6847261190414429,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.3617021276595744,
   "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": 37.248,
       "eval_steps_per_second": 9.684,
       "step": 25
+    },
+    {
+      "epoch": 0.7080851063829787,
+      "grad_norm": 0.5276378989219666,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.593,
+      "step": 26
+    },
+    {
+      "epoch": 0.7353191489361702,
+      "grad_norm": 0.8821616172790527,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.584,
+      "step": 27
+    },
+    {
+      "epoch": 0.7625531914893617,
+      "grad_norm": 0.4622693359851837,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0539,
+      "step": 28
+    },
+    {
+      "epoch": 0.7897872340425532,
+      "grad_norm": 0.3739181160926819,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.936,
+      "step": 29
+    },
+    {
+      "epoch": 0.8170212765957446,
+      "grad_norm": 0.299220472574234,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.8822,
+      "step": 30
+    },
+    {
+      "epoch": 0.8442553191489361,
+      "grad_norm": 0.23052352666854858,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7687,
+      "step": 31
+    },
+    {
+      "epoch": 0.8714893617021277,
+      "grad_norm": 0.2283187210559845,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.7128,
+      "step": 32
+    },
+    {
+      "epoch": 0.8987234042553192,
+      "grad_norm": 0.2674626410007477,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.6432,
+      "step": 33
+    },
+    {
+      "epoch": 0.9259574468085107,
+      "grad_norm": 0.3239516317844391,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5833,
+      "step": 34
+    },
+    {
+      "epoch": 0.9531914893617022,
+      "grad_norm": 0.3706875741481781,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5271,
+      "step": 35
+    },
+    {
+      "epoch": 0.9804255319148936,
+      "grad_norm": 0.881801962852478,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4949,
+      "step": 36
+    },
+    {
+      "epoch": 1.0076595744680852,
+      "grad_norm": 0.4072082042694092,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1854,
+      "step": 37
+    },
+    {
+      "epoch": 1.0348936170212766,
+      "grad_norm": 0.4009636342525482,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9146,
+      "step": 38
+    },
+    {
+      "epoch": 1.0621276595744682,
+      "grad_norm": 0.3346448838710785,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.8672,
+      "step": 39
+    },
+    {
+      "epoch": 1.0893617021276596,
+      "grad_norm": 0.2951935827732086,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7999,
+      "step": 40
+    },
+    {
+      "epoch": 1.116595744680851,
+      "grad_norm": 0.26479867100715637,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7479,
+      "step": 41
+    },
+    {
+      "epoch": 1.1438297872340426,
+      "grad_norm": 0.22193463146686554,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6952,
+      "step": 42
+    },
+    {
+      "epoch": 1.171063829787234,
+      "grad_norm": 0.23646961152553558,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5897,
+      "step": 43
+    },
+    {
+      "epoch": 1.1982978723404256,
+      "grad_norm": 0.2977546155452728,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5304,
+      "step": 44
+    },
+    {
+      "epoch": 1.225531914893617,
+      "grad_norm": 0.49887388944625854,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.5922,
+      "step": 45
+    },
+    {
+      "epoch": 1.2527659574468086,
+      "grad_norm": 0.6899640560150146,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6907,
+      "step": 46
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3451332449913025,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8937,
+      "step": 47
+    },
+    {
+      "epoch": 1.3072340425531914,
+      "grad_norm": 0.28191307187080383,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.862,
+      "step": 48
+    },
+    {
+      "epoch": 1.334468085106383,
+      "grad_norm": 0.2290133684873581,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.7711,
+      "step": 49
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.2115873247385025,
+      "learning_rate": 1e-05,
+      "loss": 0.674,
+      "step": 50
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "eval_loss": 0.6847261190414429,
+      "eval_runtime": 1.3587,
+      "eval_samples_per_second": 36.799,
+      "eval_steps_per_second": 9.568,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null