Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00adbe957bd014d78f91efa1819a1ea600a7e4781fc3fe65cd8fe611d595b026
+oid sha256:c13cc74eb7be1fa1d63e249faeaab2f6c4b52fdbf0f5d08f856b241184155b5a
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec0a3a7495a441dcb83bfc889f23f266e2a7ab2a34aed73ee58515535d13354d
+oid sha256:3076b6a5abef09e1b59c3bfff41854ad1a679bf464d4f9e227399d49ac99bf5b
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3fc522e9d8251ad787b712def955c65d6cc43c56ef21de6704fa52066938d9c
+oid sha256:e516c16455de2bbe6230cbf25b455f7a0512969063931d6c3cab39ca6ecdc19c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:543c9aea8ccef00d94a68015b4b0562ca94bcfb6116618056693dc0721358d67
+oid sha256:d1c25f0dca42503edc97f74e8eac6689c459eb98201071c9d158bf05bea1b110
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3b18963f7dcdfad3724556281186cc833f4c0e93115cacbd6bb6829feb98a1
+oid sha256:c53d8b5776244ee4adf885e512cd95311da5cf0c330a02c0c399664314324769
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37986aee71588dc60a019477c959b5c2b7ec2df28e2e3cd86ef3c05d3fe1973a
+oid sha256:2c8a4800319368bda6b2b74cf2922b92f4170dfbcc09940662d64abaf26fc494
 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": 4.555950164794922,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017114495978093443,
+  "best_metric": 4.462329387664795,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03422899195618689,
   "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": 174.618,
       "eval_steps_per_second": 45.401,
       "step": 25
+    },
+    {
+      "epoch": 0.017799075817217184,
+      "grad_norm": 0.6770291924476624,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.8958,
+      "step": 26
+    },
+    {
+      "epoch": 0.01848365565634092,
+      "grad_norm": 0.8567412495613098,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.7047,
+      "step": 27
+    },
+    {
+      "epoch": 0.019168235495464658,
+      "grad_norm": 0.3948538899421692,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.5669,
+      "step": 28
+    },
+    {
+      "epoch": 0.019852815334588398,
+      "grad_norm": 0.39659011363983154,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.4935,
+      "step": 29
+    },
+    {
+      "epoch": 0.020537395173712135,
+      "grad_norm": 0.3679991066455841,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.4412,
+      "step": 30
+    },
+    {
+      "epoch": 0.021221975012835872,
+      "grad_norm": 0.42026281356811523,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.5127,
+      "step": 31
+    },
+    {
+      "epoch": 0.02190655485195961,
+      "grad_norm": 0.38149261474609375,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.5379,
+      "step": 32
+    },
+    {
+      "epoch": 0.02259113469108335,
+      "grad_norm": 0.32174113392829895,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.5225,
+      "step": 33
+    },
+    {
+      "epoch": 0.023275714530207086,
+      "grad_norm": 0.33513426780700684,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.5413,
+      "step": 34
+    },
+    {
+      "epoch": 0.023960294369330823,
+      "grad_norm": 0.34468430280685425,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.4707,
+      "step": 35
+    },
+    {
+      "epoch": 0.02464487420845456,
+      "grad_norm": 0.46181315183639526,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.4974,
+      "step": 36
+    },
+    {
+      "epoch": 0.0253294540475783,
+      "grad_norm": 0.5422366261482239,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.5904,
+      "step": 37
+    },
+    {
+      "epoch": 0.026014033886702037,
+      "grad_norm": 0.676378071308136,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.9106,
+      "step": 38
+    },
+    {
+      "epoch": 0.026698613725825774,
+      "grad_norm": 0.5662744641304016,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.7608,
+      "step": 39
+    },
+    {
+      "epoch": 0.02738319356494951,
+      "grad_norm": 0.3747725486755371,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.5434,
+      "step": 40
+    },
+    {
+      "epoch": 0.02806777340407325,
+      "grad_norm": 0.29015031456947327,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.4867,
+      "step": 41
+    },
+    {
+      "epoch": 0.028752353243196988,
+      "grad_norm": 0.31778571009635925,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.3986,
+      "step": 42
+    },
+    {
+      "epoch": 0.029436933082320725,
+      "grad_norm": 0.27679964900016785,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.4474,
+      "step": 43
+    },
+    {
+      "epoch": 0.030121512921444462,
+      "grad_norm": 0.32700350880622864,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.4121,
+      "step": 44
+    },
+    {
+      "epoch": 0.030806092760568202,
+      "grad_norm": 0.376959890127182,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.4597,
+      "step": 45
+    },
+    {
+      "epoch": 0.03149067259969194,
+      "grad_norm": 0.3510367274284363,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.4553,
+      "step": 46
+    },
+    {
+      "epoch": 0.03217525243881568,
+      "grad_norm": 0.33624082803726196,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.4928,
+      "step": 47
+    },
+    {
+      "epoch": 0.03285983227793941,
+      "grad_norm": 0.3985156714916229,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.4657,
+      "step": 48
+    },
+    {
+      "epoch": 0.03354441211706315,
+      "grad_norm": 0.39452290534973145,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.5377,
+      "step": 49
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "grad_norm": 0.46196067333221436,
+      "learning_rate": 1e-05,
+      "loss": 4.6119,
+      "step": 50
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "eval_loss": 4.462329387664795,
+      "eval_runtime": 0.3165,
+      "eval_samples_per_second": 157.962,
+      "eval_steps_per_second": 41.07,
+      "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": 5981868147081216.0,
+  "total_flos": 1.194596482678784e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null