Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2870d7bf193f4d78d07dd25d3ccd9bc257243aae4d21be4c686a36367472657
+oid sha256:2f6262a4f679d00b797a98674a789e79866cf19411c132145b9cfe111633252d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7397ff01cf99f79a43cae947e46b77f919d4710f34c45b5590c4838fac4d1f19
+oid sha256:8d81f61164817d5f13e855eb30b30b5be5546ee023bc3527220cac24488ef923
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eda283ba932b27c01320094708b64d1289d757c39fdfb3785e861d8b1f4370c9
+oid sha256:6efacf0026f65d3673f74f27a0c79b4ce335861e525252877ac5133ef1452acb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e55fd03773de1c089633e4188590299adf47ca67a89c6b90a6ed857dfeb76d77
+oid sha256:cf964797b935a97c4e438f67fd0564fe223bdb44ba0f0ec9aa512d3037083c7e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb32590666e2992157ea71b3bc261dfcc5ee10e088bb873c2e66cddd5963f26
+oid sha256:8881211d14d4127f4bf1250b06c1a9b37c44b38e24299f8a658c3376c53d8a7e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27fc0bfac625be9324a27ed1288586c49bf986cbc0328cbbb1f700ec6be7947
+oid sha256:1961cf4cac949368121c5617cf869bfaefb2b387a0c95c683dc6337501096dd4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.05016423761844635,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.017619010912774884,
+  "best_metric": 0.04871680587530136,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.026428516369162325,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 8.995,
       "eval_steps_per_second": 2.339,
       "step": 50
+    },
+    {
+      "epoch": 0.01797139113103038,
+      "grad_norm": 0.05385514348745346,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0233,
+      "step": 51
+    },
+    {
+      "epoch": 0.01832377134928588,
+      "grad_norm": 0.05782073363661766,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 0.0122,
+      "step": 52
+    },
+    {
+      "epoch": 0.018676151567541377,
+      "grad_norm": 0.0645056962966919,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.0168,
+      "step": 53
+    },
+    {
+      "epoch": 0.019028531785796873,
+      "grad_norm": 0.07855939865112305,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0207,
+      "step": 54
+    },
+    {
+      "epoch": 0.019380912004052373,
+      "grad_norm": 0.07800403237342834,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.0227,
+      "step": 55
+    },
+    {
+      "epoch": 0.01973329222230787,
+      "grad_norm": 0.060954831540584564,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 0.0237,
+      "step": 56
+    },
+    {
+      "epoch": 0.02008567244056337,
+      "grad_norm": 0.04431851580739021,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0264,
+      "step": 57
+    },
+    {
+      "epoch": 0.020438052658818866,
+      "grad_norm": 0.033269140869379044,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 0.0316,
+      "step": 58
+    },
+    {
+      "epoch": 0.020790432877074362,
+      "grad_norm": 0.01977214589715004,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.0318,
+      "step": 59
+    },
+    {
+      "epoch": 0.021142813095329862,
+      "grad_norm": 0.03904677554965019,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0402,
+      "step": 60
+    },
+    {
+      "epoch": 0.02149519331358536,
+      "grad_norm": 0.10086186975240707,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.0493,
+      "step": 61
+    },
+    {
+      "epoch": 0.021847573531840855,
+      "grad_norm": 0.1489732712507248,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.0598,
+      "step": 62
+    },
+    {
+      "epoch": 0.022199953750096355,
+      "grad_norm": 0.06647814810276031,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0266,
+      "step": 63
+    },
+    {
+      "epoch": 0.02255233396835185,
+      "grad_norm": 0.033716265112161636,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 0.0177,
+      "step": 64
+    },
+    {
+      "epoch": 0.02290471418660735,
+      "grad_norm": 0.01775234565138817,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.0125,
+      "step": 65
+    },
+    {
+      "epoch": 0.023257094404862847,
+      "grad_norm": 0.013323824852705002,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0178,
+      "step": 66
+    },
+    {
+      "epoch": 0.023609474623118343,
+      "grad_norm": 0.02086944319307804,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.0187,
+      "step": 67
+    },
+    {
+      "epoch": 0.023961854841373843,
+      "grad_norm": 0.019485145807266235,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 0.0246,
+      "step": 68
+    },
+    {
+      "epoch": 0.02431423505962934,
+      "grad_norm": 0.00897766649723053,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0277,
+      "step": 69
+    },
+    {
+      "epoch": 0.024666615277884836,
+      "grad_norm": 0.014582326635718346,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 0.0299,
+      "step": 70
+    },
+    {
+      "epoch": 0.025018995496140336,
+      "grad_norm": 0.029548194259405136,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.0331,
+      "step": 71
+    },
+    {
+      "epoch": 0.025371375714395832,
+      "grad_norm": 0.03517298772931099,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0361,
+      "step": 72
+    },
+    {
+      "epoch": 0.025723755932651332,
+      "grad_norm": 0.026599425822496414,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.0432,
+      "step": 73
+    },
+    {
+      "epoch": 0.02607613615090683,
+      "grad_norm": 0.022014496847987175,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.0471,
+      "step": 74
+    },
+    {
+      "epoch": 0.026428516369162325,
+      "grad_norm": 0.07925083488225937,
+      "learning_rate": 1e-05,
+      "loss": 0.0657,
+      "step": 75
+    },
+    {
+      "epoch": 0.026428516369162325,
+      "eval_loss": 0.04871680587530136,
+      "eval_runtime": 5.8192,
+      "eval_samples_per_second": 8.592,
+      "eval_steps_per_second": 2.234,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.379321871858401e+17,
+  "total_flos": 9.559191436625183e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null