Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:259bc27689b7d9ec67bf3359500e9a45a7635f493aa809d09ee805f3a6ff0b2c
+oid sha256:a20307749b453db8fa0778403258055c3a8943cd6d91c316bed53a3ee43501d1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e4f147e6a1357c7aef5a06932f4ce98f51849225028c0149a27353a69968356
+oid sha256:312d10349af77bc3a72eb91da2b959cae8c93b72554bb31d7ba5d898a219eefc
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d8e7159f674423b11eda337a261f56e630fdd796596032f38f1f25616e32963
+oid sha256:20d011697de24443a1dd9d31199281773164ef93ec2ed691f83a3d193f609d72
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4347b7fb99d7ebaf2c3730c4429ff1607753100711ea4010e264aa025e26fab1
+oid sha256:242acc5c9c8f90c67e4c4cfb842d62c8ba9c192c7d60e41b1b07d1c3104c962b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd703989fb91d13314a9bc6ab7f7a1476972399a2433bd1114d56f54654ebe0b
+oid sha256:360956a15773a04b6bf40f2c5244f7b93aa6d0e1c1d1bcb4898bf0a4635b2627
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1a113a29438f0bf44424645af3900b45bff340572fe3a05be215133aea923e
+oid sha256:f00e86448c87b5ede4a0cd5e5287e31b5da6a841d404528fb01530925c6c08a6
 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": 0.4165439307689667,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22346368715083798,
+  "best_metric": 0.2622641623020172,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.44692737430167595,
   "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": 11.487,
       "eval_steps_per_second": 2.987,
       "step": 25
+    },
+    {
+      "epoch": 0.2324022346368715,
+      "grad_norm": 3.016798496246338,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.707,
+      "step": 26
+    },
+    {
+      "epoch": 0.24134078212290502,
+      "grad_norm": 2.214432716369629,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.4435,
+      "step": 27
+    },
+    {
+      "epoch": 0.25027932960893856,
+      "grad_norm": 1.871042013168335,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3622,
+      "step": 28
+    },
+    {
+      "epoch": 0.25921787709497207,
+      "grad_norm": 1.3092725276947021,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.3011,
+      "step": 29
+    },
+    {
+      "epoch": 0.2681564245810056,
+      "grad_norm": 1.4508849382400513,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.257,
+      "step": 30
+    },
+    {
+      "epoch": 0.2770949720670391,
+      "grad_norm": 1.6570039987564087,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.324,
+      "step": 31
+    },
+    {
+      "epoch": 0.2860335195530726,
+      "grad_norm": 1.6880950927734375,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.2753,
+      "step": 32
+    },
+    {
+      "epoch": 0.29497206703910617,
+      "grad_norm": 2.029897451400757,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.3435,
+      "step": 33
+    },
+    {
+      "epoch": 0.3039106145251397,
+      "grad_norm": 2.708217144012451,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.403,
+      "step": 34
+    },
+    {
+      "epoch": 0.3128491620111732,
+      "grad_norm": 14.175328254699707,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5983,
+      "step": 35
+    },
+    {
+      "epoch": 0.3217877094972067,
+      "grad_norm": 6.837980270385742,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4558,
+      "step": 36
+    },
+    {
+      "epoch": 0.3307262569832402,
+      "grad_norm": 4.484794616699219,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3205,
+      "step": 37
+    },
+    {
+      "epoch": 0.3396648044692737,
+      "grad_norm": 2.619335889816284,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3569,
+      "step": 38
+    },
+    {
+      "epoch": 0.3486033519553073,
+      "grad_norm": 2.7390358448028564,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.381,
+      "step": 39
+    },
+    {
+      "epoch": 0.3575418994413408,
+      "grad_norm": 2.364455223083496,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.3319,
+      "step": 40
+    },
+    {
+      "epoch": 0.3664804469273743,
+      "grad_norm": 2.2109696865081787,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3197,
+      "step": 41
+    },
+    {
+      "epoch": 0.3754189944134078,
+      "grad_norm": 1.8548595905303955,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.2718,
+      "step": 42
+    },
+    {
+      "epoch": 0.3843575418994413,
+      "grad_norm": 2.3461661338806152,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3907,
+      "step": 43
+    },
+    {
+      "epoch": 0.39329608938547483,
+      "grad_norm": 1.327548861503601,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2497,
+      "step": 44
+    },
+    {
+      "epoch": 0.4022346368715084,
+      "grad_norm": 1.4733893871307373,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3123,
+      "step": 45
+    },
+    {
+      "epoch": 0.4111731843575419,
+      "grad_norm": 1.3677797317504883,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3053,
+      "step": 46
+    },
+    {
+      "epoch": 0.4201117318435754,
+      "grad_norm": 1.656186580657959,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3297,
+      "step": 47
+    },
+    {
+      "epoch": 0.42905027932960893,
+      "grad_norm": 1.1715149879455566,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3077,
+      "step": 48
+    },
+    {
+      "epoch": 0.43798882681564244,
+      "grad_norm": 0.7847478985786438,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.1393,
+      "step": 49
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.5844078660011292,
+      "learning_rate": 1e-05,
+      "loss": 0.056,
+      "step": 50
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "eval_loss": 0.2622641623020172,
+      "eval_runtime": 4.3702,
+      "eval_samples_per_second": 11.441,
+      "eval_steps_per_second": 2.975,
+      "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": 2.9989620096486605e+17,
+  "total_flos": 5.991396431364096e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null