Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de0505d7b1bab48fa6d5d209f24f724b1b69f8404cc69d8079af060d6ea306f
+oid sha256:b769747a74fd9d2d86e8ea404f0d489c34c6f073d1ca157ffeb1dac98b652265
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77480fc1a2e5685f4c3a7202ec081f943cad02acd92f68b0ef4f756df27e3d65
+oid sha256:31dd367d889138edfcbcbc95481b5bdc4b2ab6d9f1d8cb42eb61ef591b29f1fe
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be19397c2d522bad39dd4c7c3729e0d990c82da1398aaf0fcac6828f4c865c0c
+oid sha256:c59a811e523d0eb6206332e9cf074e75688ff34eb1b98ab1b011ac2cea64844e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9cd5dab2e3e3a8cd9cc39773bc47067c5c7960b53f19bb66ee1ab40d6cb861
+oid sha256:c3f77c4477d49e466342ef1cb86ac4667de070ca871dfbb0c2ea687b423ac099
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3630b7b1170aca1b5399ec3b798eb13ff75868fc5da3814ce75a32427846d8ac
+oid sha256:1b3061a3333edb02076417c592118c5b105dd36efc20ef5f78cc0ea2108f2830
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d12e0a1c66eccdba9aa6bbca0a493ede43bf9373f52ced2d586fcc578f8acfd9
+oid sha256:f2a6c42cf0cc5b193c69bd67346e4e3b9da3e2c713e36d10a4e30d39dd3f1102
 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": 11.929944038391113,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7575757575757576,
+  "best_metric": 11.926763534545898,
+  "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": 332.811,
       "eval_steps_per_second": 86.531,
       "step": 25
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.1273133009672165,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9205,
+      "step": 26
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.10962895303964615,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9237,
+      "step": 27
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.12553489208221436,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9252,
+      "step": 28
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 0.1279001533985138,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9228,
+      "step": 29
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.1351960301399231,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9208,
+      "step": 30
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.12530995905399323,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9252,
+      "step": 31
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.14163988828659058,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.922,
+      "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13867436349391937,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9221,
+      "step": 33
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 0.15008845925331116,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9209,
+      "step": 34
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.15957288444042206,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9171,
+      "step": 35
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.14019732177257538,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9241,
+      "step": 36
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.14304937422275543,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.921,
+      "step": 37
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 0.15103910863399506,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9189,
+      "step": 38
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.15454430878162384,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9222,
+      "step": 39
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.1565762460231781,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.919,
+      "step": 40
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 0.16164128482341766,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9206,
+      "step": 41
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.14624446630477905,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9241,
+      "step": 42
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 0.16123437881469727,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9206,
+      "step": 43
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.15028682351112366,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9227,
+      "step": 44
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.16800500452518463,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.921,
+      "step": 45
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 0.15440353751182556,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.923,
+      "step": 46
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 0.18006780743598938,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9169,
+      "step": 47
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.1780731976032257,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9175,
+      "step": 48
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 0.16222211718559265,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9235,
+      "step": 49
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.16308805346488953,
+      "learning_rate": 1e-05,
+      "loss": 11.9198,
+      "step": 50
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "eval_loss": 11.926763534545898,
+      "eval_runtime": 0.1448,
+      "eval_samples_per_second": 345.406,
+      "eval_steps_per_second": 89.806,
+      "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": 523527585792.0,
+  "total_flos": 1047055171584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null