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:b7ee347b2dc7cd45c9583c2e598545f46b35fa1f3489d24c0013dfb8c4e8ca81
+oid sha256:10a0f310968926c89e0c7700eef6912b4ef62b6d7d9295ad3dfe59eb152f1fcc
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c275c2fa39cb3c8aa00efab31922ece721c9e2452a803fced4de445911e4f962
+oid sha256:05a95c0b6ce65775592f65f4aec44e0ca251920a6b756f9e8cc9441f4672b1b2
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8cb3edd1e8f6eb1ec1a0c608cf4768dbd71f659ad06583c14db36cedce31801
+oid sha256:362f3d76bee51dd39bf301fc77818e5a0d2c6aae514d92d0812773060c2b2811
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11bec62294e31259bc6fdb36fdb57ca57f460e558fe49499ee8328c64c6daad8
+oid sha256:10f6b7ed88e6fc3c0b1895faa9671f3f60aff7bb8559c6855b4907735946cce5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42f3df0e9df3524680fae05c5f5e263cc39b34801c05dcb213d504b7d50d5b2
+oid sha256:b7394a521f8fef745603ee895dbd1e6b8bc3a5ff8d2213120e6a8f8340e79ffc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7aaffba6771ee03507e31137d46572fad74a844e2499c5321a67bb0c1552e8
+oid sha256:caf5ec184b1cde633d4720e23f6c1df0b944d9be30c04941e4321451988fa73a
 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": 10.369172096252441,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1398112548060119,
+  "best_metric": 10.362602233886719,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2796225096120238,
   "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": 534.565,
       "eval_steps_per_second": 138.987,
       "step": 25
+    },
+    {
+      "epoch": 0.14540370499825236,
+      "grad_norm": 0.18515342473983765,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3706,
+      "step": 26
+    },
+    {
+      "epoch": 0.15099615519049284,
+      "grad_norm": 0.17940200865268707,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3699,
+      "step": 27
+    },
+    {
+      "epoch": 0.1565886053827333,
+      "grad_norm": 0.17424097657203674,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3697,
+      "step": 28
+    },
+    {
+      "epoch": 0.16218105557497378,
+      "grad_norm": 0.16775143146514893,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3678,
+      "step": 29
+    },
+    {
+      "epoch": 0.16777350576721425,
+      "grad_norm": 0.16442053020000458,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3684,
+      "step": 30
+    },
+    {
+      "epoch": 0.17336595595945473,
+      "grad_norm": 0.15736381709575653,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3697,
+      "step": 31
+    },
+    {
+      "epoch": 0.1789584061516952,
+      "grad_norm": 0.15212076902389526,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3699,
+      "step": 32
+    },
+    {
+      "epoch": 0.1845508563439357,
+      "grad_norm": 0.15667906403541565,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.37,
+      "step": 33
+    },
+    {
+      "epoch": 0.19014330653617617,
+      "grad_norm": 0.15856710076332092,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.369,
+      "step": 34
+    },
+    {
+      "epoch": 0.19573575672841664,
+      "grad_norm": 0.15956778824329376,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3678,
+      "step": 35
+    },
+    {
+      "epoch": 0.20132820692065712,
+      "grad_norm": 0.15860746800899506,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3644,
+      "step": 36
+    },
+    {
+      "epoch": 0.2069206571128976,
+      "grad_norm": 0.16222454607486725,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3621,
+      "step": 37
+    },
+    {
+      "epoch": 0.21251310730513806,
+      "grad_norm": 0.21722282469272614,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3658,
+      "step": 38
+    },
+    {
+      "epoch": 0.21810555749737853,
+      "grad_norm": 0.21604430675506592,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3655,
+      "step": 39
+    },
+    {
+      "epoch": 0.223698007689619,
+      "grad_norm": 0.20557966828346252,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3654,
+      "step": 40
+    },
+    {
+      "epoch": 0.22929045788185948,
+      "grad_norm": 0.20266205072402954,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3643,
+      "step": 41
+    },
+    {
+      "epoch": 0.23488290807409998,
+      "grad_norm": 0.18894320726394653,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3643,
+      "step": 42
+    },
+    {
+      "epoch": 0.24047535826634045,
+      "grad_norm": 0.18438370525836945,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3655,
+      "step": 43
+    },
+    {
+      "epoch": 0.24606780845858092,
+      "grad_norm": 0.18429425358772278,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3658,
+      "step": 44
+    },
+    {
+      "epoch": 0.25166025865082137,
+      "grad_norm": 0.1751224398612976,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.366,
+      "step": 45
+    },
+    {
+      "epoch": 0.25725270884306184,
+      "grad_norm": 0.17902234196662903,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3659,
+      "step": 46
+    },
+    {
+      "epoch": 0.26284515903530237,
+      "grad_norm": 0.17663754522800446,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.365,
+      "step": 47
+    },
+    {
+      "epoch": 0.26843760922754284,
+      "grad_norm": 0.17328204214572906,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3631,
+      "step": 48
+    },
+    {
+      "epoch": 0.2740300594197833,
+      "grad_norm": 0.1784089356660843,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3607,
+      "step": 49
+    },
+    {
+      "epoch": 0.2796225096120238,
+      "grad_norm": 0.19091790914535522,
+      "learning_rate": 1e-05,
+      "loss": 10.3588,
+      "step": 50
+    },
+    {
+      "epoch": 0.2796225096120238,
+      "eval_loss": 10.362602233886719,
+      "eval_runtime": 0.0947,
+      "eval_samples_per_second": 527.983,
+      "eval_steps_per_second": 137.275,
+      "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": 21504314966016.0,
+  "total_flos": 43075455025152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null