Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14a22ee8d61965b8165c8d72bb34f8906bb6a143533937eebab0224cc353ba3b
+oid sha256:128c762501d9c85ec4d860989bb5e692dbdd93a0a63b8223a8618d6c52a0d724
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955b0dc0f9179efa7d1bef8680398c4b21bdcf8cf50376bee91c4f97fd325bee
+oid sha256:21102d928db0bdec16a638d11126d49feb9171f3091b98789684d4778b470973
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27e4d6d645274d5ae44509f7091df2405a6cbc968218f9daa212446edd3115ef
+oid sha256:30838187cba60732fe75efb4676210d3a76674b85cead0a81def209e89730860
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:069742f44c97d0a36ba5c8124966ab84c537c89a2701042293090163885cb3b6
+oid sha256:b8ca7e0801de2b96a0927bad053c693b838719e807e055866a14bb470b67e9f5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:628fdc17afc47c635bf4cbab2c2d9f5b38a88c75f3193e484d433b6ddda42146
+oid sha256:76dd85b93d7a44aca807e33670f1bcaf4164e971bfb99ccd9fdb3ee7d24a5110
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d5e166875503313e24fdf9fa2fc765827787a5049bcdb411e3c1f387afd4b05
+oid sha256:77019ddd25b2f935a50d3e96209434bc20b451f0fa86541261082d61cf690afb
 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": 10.371728897094727,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.645682001614205,
+  "best_metric": 10.365694999694824,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.29136400322841,
   "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": 348.971,
       "eval_steps_per_second": 90.732,
       "step": 25
+    },
+    {
+      "epoch": 0.6715092816787732,
+      "grad_norm": 0.13307611644268036,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3589,
+      "step": 26
+    },
+    {
+      "epoch": 0.6973365617433414,
+      "grad_norm": 0.12787942588329315,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3505,
+      "step": 27
+    },
+    {
+      "epoch": 0.7231638418079096,
+      "grad_norm": 0.17840470373630524,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3771,
+      "step": 28
+    },
+    {
+      "epoch": 0.7489911218724778,
+      "grad_norm": 0.12635862827301025,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3656,
+      "step": 29
+    },
+    {
+      "epoch": 0.774818401937046,
+      "grad_norm": 0.23654264211654663,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.397,
+      "step": 30
+    },
+    {
+      "epoch": 0.8006456820016142,
+      "grad_norm": 0.17520985007286072,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3823,
+      "step": 31
+    },
+    {
+      "epoch": 0.8264729620661824,
+      "grad_norm": 0.16809497773647308,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3763,
+      "step": 32
+    },
+    {
+      "epoch": 0.8523002421307506,
+      "grad_norm": 0.16317372024059296,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3719,
+      "step": 33
+    },
+    {
+      "epoch": 0.8781275221953188,
+      "grad_norm": 0.1540750414133072,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3655,
+      "step": 34
+    },
+    {
+      "epoch": 0.903954802259887,
+      "grad_norm": 0.15551811456680298,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.361,
+      "step": 35
+    },
+    {
+      "epoch": 0.9297820823244553,
+      "grad_norm": 0.14692772924900055,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3512,
+      "step": 36
+    },
+    {
+      "epoch": 0.9556093623890234,
+      "grad_norm": 0.12654046714305878,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3606,
+      "step": 37
+    },
+    {
+      "epoch": 0.9814366424535916,
+      "grad_norm": 0.17960292100906372,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3658,
+      "step": 38
+    },
+    {
+      "epoch": 1.0072639225181599,
+      "grad_norm": 0.19845052063465118,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 14.0463,
+      "step": 39
+    },
+    {
+      "epoch": 1.033091202582728,
+      "grad_norm": 0.2014998197555542,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 8.8616,
+      "step": 40
+    },
+    {
+      "epoch": 1.0589184826472962,
+      "grad_norm": 0.20529989898204803,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.0625,
+      "step": 41
+    },
+    {
+      "epoch": 1.0847457627118644,
+      "grad_norm": 0.19758163392543793,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.6261,
+      "step": 42
+    },
+    {
+      "epoch": 1.1105730427764327,
+      "grad_norm": 0.17450495064258575,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.2504,
+      "step": 43
+    },
+    {
+      "epoch": 1.136400322841001,
+      "grad_norm": 0.16295291483402252,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.2684,
+      "step": 44
+    },
+    {
+      "epoch": 1.162227602905569,
+      "grad_norm": 0.16200117766857147,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3569,
+      "step": 45
+    },
+    {
+      "epoch": 1.1880548829701372,
+      "grad_norm": 0.15267767012119293,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3028,
+      "step": 46
+    },
+    {
+      "epoch": 1.2138821630347054,
+      "grad_norm": 0.13210907578468323,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.4081,
+      "step": 47
+    },
+    {
+      "epoch": 1.2397094430992737,
+      "grad_norm": 0.18460141122341156,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.6767,
+      "step": 48
+    },
+    {
+      "epoch": 1.2655367231638417,
+      "grad_norm": 0.1711810678243637,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.0648,
+      "step": 49
+    },
+    {
+      "epoch": 1.29136400322841,
+      "grad_norm": 0.23405061662197113,
+      "learning_rate": 1e-05,
+      "loss": 9.1647,
+      "step": 50
+    },
+    {
+      "epoch": 1.29136400322841,
+      "eval_loss": 10.365694999694824,
+      "eval_runtime": 0.1505,
+      "eval_samples_per_second": 332.175,
+      "eval_steps_per_second": 86.365,
+      "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": 25326710423552.0,
+  "total_flos": 50807118495744.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null