Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8885d91a95fa77d3c6646030172887b1a26b677a50d0d1f1e30e6485c8047edd
+oid sha256:7ee231ccffe274d7bc28eea9791fdc03a3bb986ec859349096c498adb08f4b57
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3884ca904634b94242af0d46c51cc1f607ec0572e51ad802373a21d5818d7cdf
+oid sha256:170ef4317b3e7d235e3b4e3d8c650f0fcf31df753fbec3f1426a19de448d48d3
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1dbcfd47355e87ec2a9bb8e4c3080db99e70e44c401bc614a6bfd3faa9f87cb
+oid sha256:6f7fd2258525f26bc8b7197850b481171e97c4aed36a96c3fe30979a63490aab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77bd4c9c5476c2fb8948124b053923e74843853568788f989a0647069412fddc
+oid sha256:6702a59dbb38f1dead7c7bb36fa6389d08e85c7d5135d08db2010aa858718231
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7698ebc92175e12a6e9c3234eef10eb28ed8fa22d75b5bd87eb1db52ee8eb7a2
+oid sha256:b9b827d7c3dcde23cd0609adb39f39b5a8ffcde4f30f48806775aa8f53db458a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:078d8f098f163c35128c223272adb544aa08272ea4b1f360bf412bba6fffdfc1
+oid sha256:84e496bb76adef46112e26a26685afa14d7066a9407fc9170207c33259522626
 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": 0.5379838347434998,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7575757575757576,
+  "best_metric": 0.3421801030635834,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.5151515151515151,
   "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": 17.189,
       "eval_steps_per_second": 4.469,
       "step": 25
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 7.8287858963012695,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 7.0069,
+      "step": 26
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 6.974181175231934,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 7.1145,
+      "step": 27
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 7.5937042236328125,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 7.1062,
+      "step": 28
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 7.260517120361328,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.4217,
+      "step": 29
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 8.329216003417969,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.5431,
+      "step": 30
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 10.283854484558105,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.9686,
+      "step": 31
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 14.778830528259277,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 7.7959,
+      "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.504195213317871,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.2998,
+      "step": 33
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 8.065375328063965,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 5.3917,
+      "step": 34
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 6.932098865509033,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 5.1002,
+      "step": 35
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 6.426107883453369,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 5.1781,
+      "step": 36
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 6.368813514709473,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 5.3515,
+      "step": 37
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 7.844695091247559,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 5.2342,
+      "step": 38
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 6.590551853179932,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.9267,
+      "step": 39
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 7.364800930023193,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.9535,
+      "step": 40
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 9.986160278320312,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 5.5483,
+      "step": 41
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 6.83111572265625,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.6277,
+      "step": 42
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 7.230846405029297,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.6809,
+      "step": 43
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 6.264194488525391,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.6497,
+      "step": 44
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 5.941837787628174,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.6859,
+      "step": 45
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 7.431611061096191,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.8694,
+      "step": 46
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 7.033977031707764,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.5204,
+      "step": 47
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 8.80021858215332,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.8541,
+      "step": 48
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 14.710296630859375,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 5.174,
+      "step": 49
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 5.271395683288574,
+      "learning_rate": 1e-05,
+      "loss": 4.0463,
+      "step": 50
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "eval_loss": 0.3421801030635834,
+      "eval_runtime": 2.9426,
+      "eval_samples_per_second": 16.992,
+      "eval_steps_per_second": 4.418,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null