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:aadb523ac9a656e805050295e238c983a2fc583a2682661ed79041106a6f9112
+oid sha256:a6e51fe0e59648ebf7ada02b614a9b1b33c1180f55ad2452ac0ae942122d21b8
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9010afdf4bc62e97a4bdf1a9124a6e61fb5c30ccb735b25f7d1db9965ab153f6
+oid sha256:ca770457266933279b91d981f8cb79184c3764dadb543d5761f4ac0e0e2bc2c5
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c075c36e3dff0644511b4237e4e7d692d5e4f62c5e496a69eb72a477af39d366
+oid sha256:359c14b230bd1bd5d9aecddbfcb3f385f9588bed72cb4d4843e53c71a74e75e8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ae213283cd07cee78fe1bd2672498c33fcef219a40ff6aa77a7d2cc04c9e10
+oid sha256:4d2915a71bb5959a1f592543213dbfc71f4d9c5223efd5b4526a4c4eb1cb4349
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1e1c7ad46d49425a9a4d8dbe6119837b865b692bc95489036573c6d537a70e7
+oid sha256:eb6b2889a47ed7cb8155c6f7f035340c815509e3199d5ebb0785a93cc331aec5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75954554874032ae54cbaf2a3e035e157d8c08dc9cf8bb437d766c06cc737f44
+oid sha256:e2db539a524facb3f4065b6a7c459160a500904cd49135e91fb5bccd3ccf8af7
 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": 0.21341951191425323,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2597402597402597,
+  "best_metric": 0.11276046931743622,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5194805194805194,
   "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": 39.668,
       "eval_steps_per_second": 10.314,
       "step": 25
+    },
+    {
+      "epoch": 0.2701298701298701,
+      "grad_norm": 1.8199442625045776,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.189,
+      "step": 26
+    },
+    {
+      "epoch": 0.2805194805194805,
+      "grad_norm": 1.7070503234863281,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1914,
+      "step": 27
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 1.6178464889526367,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.221,
+      "step": 28
+    },
+    {
+      "epoch": 0.3012987012987013,
+      "grad_norm": 1.722450613975525,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.2057,
+      "step": 29
+    },
+    {
+      "epoch": 0.3116883116883117,
+      "grad_norm": 1.5822162628173828,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.2006,
+      "step": 30
+    },
+    {
+      "epoch": 0.3220779220779221,
+      "grad_norm": 1.6125823259353638,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.2074,
+      "step": 31
+    },
+    {
+      "epoch": 0.33246753246753247,
+      "grad_norm": 1.8437734842300415,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1725,
+      "step": 32
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 1.5423240661621094,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.1747,
+      "step": 33
+    },
+    {
+      "epoch": 0.35324675324675325,
+      "grad_norm": 1.7353768348693848,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1812,
+      "step": 34
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.5530339479446411,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1674,
+      "step": 35
+    },
+    {
+      "epoch": 0.37402597402597404,
+      "grad_norm": 1.0867341756820679,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1958,
+      "step": 36
+    },
+    {
+      "epoch": 0.38441558441558443,
+      "grad_norm": 1.0079206228256226,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1409,
+      "step": 37
+    },
+    {
+      "epoch": 0.3948051948051948,
+      "grad_norm": 1.1320562362670898,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.142,
+      "step": 38
+    },
+    {
+      "epoch": 0.4051948051948052,
+      "grad_norm": 1.299381971359253,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.187,
+      "step": 39
+    },
+    {
+      "epoch": 0.4155844155844156,
+      "grad_norm": 1.3311715126037598,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.185,
+      "step": 40
+    },
+    {
+      "epoch": 0.42597402597402595,
+      "grad_norm": 1.184550166130066,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1746,
+      "step": 41
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 1.0470242500305176,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1865,
+      "step": 42
+    },
+    {
+      "epoch": 0.44675324675324674,
+      "grad_norm": 1.2727560997009277,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.1466,
+      "step": 43
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 1.119794249534607,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1663,
+      "step": 44
+    },
+    {
+      "epoch": 0.4675324675324675,
+      "grad_norm": 1.0451369285583496,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1812,
+      "step": 45
+    },
+    {
+      "epoch": 0.4779220779220779,
+      "grad_norm": 0.8651501536369324,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.164,
+      "step": 46
+    },
+    {
+      "epoch": 0.4883116883116883,
+      "grad_norm": 1.185897946357727,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.17,
+      "step": 47
+    },
+    {
+      "epoch": 0.4987012987012987,
+      "grad_norm": 1.228886604309082,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1999,
+      "step": 48
+    },
+    {
+      "epoch": 0.509090909090909,
+      "grad_norm": 0.9948132038116455,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.1337,
+      "step": 49
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 1.1506510972976685,
+      "learning_rate": 1e-05,
+      "loss": 0.176,
+      "step": 50
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "eval_loss": 0.11276046931743622,
+      "eval_runtime": 1.2757,
+      "eval_samples_per_second": 39.195,
+      "eval_steps_per_second": 10.191,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null