Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9197206615e98db53ead02018236fa2fae2e9f85816564ad345083efacee7f7d
+oid sha256:857610b6a4567447724792fddcb492383236ee9605648563dfe154f175ea951c
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a88aa40a68a81e9a56064cf3a615673073ee6edbce7d2b725e4500fa4bb6dd
+oid sha256:445785f158c0a40368631a3328c9cd8f8a79db30db58811db9c617a969bcb727
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce5915506840714f2a84d03daad69c91dbfe3b89a182f48455154873d2a04298
+oid sha256:171d5712a2733391374854a2055485cc5f6ef87951411427cfee464c5a4355ba
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af68c7a49e5029d2eec396ab855006a2181b4034ca04f696b84de274a534111a
+oid sha256:dcb3a41570e50cfca90daa7df197273aa1f466d4799bf935f2f2d5ec851f14c6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eccef9403f47d6834ec4aa91d67129c368df94a8fc9b8ba119da433321b6687
+oid sha256:c574ba4479ebc95df441470dd415cf7e5690ccdd2e64d254794e3f617f2d78df
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec253b17000757b4d906d46b16fb9a9b149f009a46fd504eb5d05e0b1671c2a
+oid sha256:deefc2665633aa5f545fcdcc81ae4200ce7db2912d836582e97c1930776329cf
 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": 0.5459790825843811,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12876227265411236,
+  "best_metric": 0.14273174107074738,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2575245453082247,
   "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": 12.121,
       "eval_steps_per_second": 3.152,
       "step": 25
+    },
+    {
+      "epoch": 0.13391276356027684,
+      "grad_norm": 135.01632690429688,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 19.2796,
+      "step": 26
+    },
+    {
+      "epoch": 0.13906325446644133,
+      "grad_norm": 122.40741729736328,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 20.3915,
+      "step": 27
+    },
+    {
+      "epoch": 0.14421374537260584,
+      "grad_norm": 77.29145050048828,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 15.7624,
+      "step": 28
+    },
+    {
+      "epoch": 0.14936423627877032,
+      "grad_norm": 71.43122863769531,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 16.1651,
+      "step": 29
+    },
+    {
+      "epoch": 0.1545147271849348,
+      "grad_norm": 60.62587356567383,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.7429,
+      "step": 30
+    },
+    {
+      "epoch": 0.15966521809109932,
+      "grad_norm": 69.12200927734375,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 14.7872,
+      "step": 31
+    },
+    {
+      "epoch": 0.1648157089972638,
+      "grad_norm": 48.978023529052734,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 8.8029,
+      "step": 32
+    },
+    {
+      "epoch": 0.1699661999034283,
+      "grad_norm": 47.26166534423828,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 9.5402,
+      "step": 33
+    },
+    {
+      "epoch": 0.1751166908095928,
+      "grad_norm": 49.96639633178711,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 8.8643,
+      "step": 34
+    },
+    {
+      "epoch": 0.18026718171575729,
+      "grad_norm": 47.3193359375,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.71,
+      "step": 35
+    },
+    {
+      "epoch": 0.18541767262192177,
+      "grad_norm": 55.040592193603516,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 9.0711,
+      "step": 36
+    },
+    {
+      "epoch": 0.19056816352808628,
+      "grad_norm": 60.64955520629883,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.7455,
+      "step": 37
+    },
+    {
+      "epoch": 0.19571865443425077,
+      "grad_norm": 96.02499389648438,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 14.7612,
+      "step": 38
+    },
+    {
+      "epoch": 0.20086914534041525,
+      "grad_norm": 68.96138763427734,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.6281,
+      "step": 39
+    },
+    {
+      "epoch": 0.20601963624657976,
+      "grad_norm": 78.70532989501953,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 9.8648,
+      "step": 40
+    },
+    {
+      "epoch": 0.21117012715274425,
+      "grad_norm": 73.4675521850586,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 9.5117,
+      "step": 41
+    },
+    {
+      "epoch": 0.21632061805890873,
+      "grad_norm": 60.545936584472656,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 9.5021,
+      "step": 42
+    },
+    {
+      "epoch": 0.22147110896507324,
+      "grad_norm": 47.23418045043945,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 7.5249,
+      "step": 43
+    },
+    {
+      "epoch": 0.22662159987123773,
+      "grad_norm": 33.51955795288086,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 5.3886,
+      "step": 44
+    },
+    {
+      "epoch": 0.2317720907774022,
+      "grad_norm": 40.547977447509766,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 5.9733,
+      "step": 45
+    },
+    {
+      "epoch": 0.23692258168356672,
+      "grad_norm": 34.97176742553711,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 5.6807,
+      "step": 46
+    },
+    {
+      "epoch": 0.2420730725897312,
+      "grad_norm": 79.3729476928711,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.1564,
+      "step": 47
+    },
+    {
+      "epoch": 0.2472235634958957,
+      "grad_norm": 46.89299011230469,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.3804,
+      "step": 48
+    },
+    {
+      "epoch": 0.2523740544020602,
+      "grad_norm": 77.9176025390625,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 8.2541,
+      "step": 49
+    },
+    {
+      "epoch": 0.2575245453082247,
+      "grad_norm": 107.83366394042969,
+      "learning_rate": 1e-05,
+      "loss": 10.4399,
+      "step": 50
+    },
+    {
+      "epoch": 0.2575245453082247,
+      "eval_loss": 0.14273174107074738,
+      "eval_runtime": 4.1412,
+      "eval_samples_per_second": 12.074,
+      "eval_steps_per_second": 3.139,
+      "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": 2.629552387915776e+17,
+  "total_flos": 5.259104775831552e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null