Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c2c532e63fd3dcaf8d658fa45f0e0cd636c9d76a52727bd1da269f19f5f7d2
+oid sha256:c2870d7bf193f4d78d07dd25d3ccd9bc257243aae4d21be4c686a36367472657
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5770d4b5bd718c39150b9058564e7a4249f05c090d0bbf474385abb508a4ee6e
+oid sha256:7397ff01cf99f79a43cae947e46b77f919d4710f34c45b5590c4838fac4d1f19
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:569272a7d60a8f44bfc7b4fedb92ea4a457709206e3d83d72b2990c4afb19bba
+oid sha256:eda283ba932b27c01320094708b64d1289d757c39fdfb3785e861d8b1f4370c9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddd5caac621696a4b97ed434be44ff035c502226c7d9ae3c95de3a11a9fed74
+oid sha256:e55fd03773de1c089633e4188590299adf47ca67a89c6b90a6ed857dfeb76d77
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea3e7c08faa5b76a7254ae6e7162e83473cb4cdfd415d851ba0e7b932222be6
+oid sha256:adb32590666e2992157ea71b3bc261dfcc5ee10e088bb873c2e66cddd5963f26
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968ff4063ee2ede3e11bd3bb9062e50207ac3235567c9536cddc26e68cd86036
+oid sha256:c27fc0bfac625be9324a27ed1288586c49bf986cbc0328cbbb1f700ec6be7947
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.05434239283204079,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008809505456387442,
+  "best_metric": 0.05016423761844635,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.017619010912774884,
   "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": 8.569,
       "eval_steps_per_second": 2.228,
       "step": 25
+    },
+    {
+      "epoch": 0.00916188567464294,
+      "grad_norm": 0.1138065904378891,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.0288,
+      "step": 26
+    },
+    {
+      "epoch": 0.009514265892898437,
+      "grad_norm": 0.13079240918159485,
+      "learning_rate": 7.75e-05,
+      "loss": 0.0152,
+      "step": 27
+    },
+    {
+      "epoch": 0.009866646111153935,
+      "grad_norm": 0.16374854743480682,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.0212,
+      "step": 28
+    },
+    {
+      "epoch": 0.010219026329409433,
+      "grad_norm": 0.09367111325263977,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.0222,
+      "step": 29
+    },
+    {
+      "epoch": 0.010571406547664931,
+      "grad_norm": 0.027064498513936996,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.0222,
+      "step": 30
+    },
+    {
+      "epoch": 0.010923786765920427,
+      "grad_norm": 0.12557287514209747,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.0284,
+      "step": 31
+    },
+    {
+      "epoch": 0.011276166984175925,
+      "grad_norm": 0.14048165082931519,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.0319,
+      "step": 32
+    },
+    {
+      "epoch": 0.011628547202431424,
+      "grad_norm": 0.1092550978064537,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.0327,
+      "step": 33
+    },
+    {
+      "epoch": 0.011980927420686922,
+      "grad_norm": 0.05221077799797058,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.037,
+      "step": 34
+    },
+    {
+      "epoch": 0.012333307638942418,
+      "grad_norm": 0.04570182412862778,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.0403,
+      "step": 35
+    },
+    {
+      "epoch": 0.012685687857197916,
+      "grad_norm": 0.12411309778690338,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.0467,
+      "step": 36
+    },
+    {
+      "epoch": 0.013038068075453414,
+      "grad_norm": 0.09028882533311844,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.0558,
+      "step": 37
+    },
+    {
+      "epoch": 0.013390448293708912,
+      "grad_norm": 0.20290955901145935,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.0216,
+      "step": 38
+    },
+    {
+      "epoch": 0.01374282851196441,
+      "grad_norm": 0.040300991386175156,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0202,
+      "step": 39
+    },
+    {
+      "epoch": 0.014095208730219907,
+      "grad_norm": 0.014306614175438881,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.0137,
+      "step": 40
+    },
+    {
+      "epoch": 0.014447588948475405,
+      "grad_norm": 0.02834320440888405,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.0183,
+      "step": 41
+    },
+    {
+      "epoch": 0.014799969166730903,
+      "grad_norm": 0.01949421875178814,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0196,
+      "step": 42
+    },
+    {
+      "epoch": 0.015152349384986401,
+      "grad_norm": 0.03610558062791824,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.024,
+      "step": 43
+    },
+    {
+      "epoch": 0.015504729603241897,
+      "grad_norm": 0.039888154715299606,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.0262,
+      "step": 44
+    },
+    {
+      "epoch": 0.015857109821497396,
+      "grad_norm": 0.0371965691447258,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0282,
+      "step": 45
+    },
+    {
+      "epoch": 0.016209490039752892,
+      "grad_norm": 0.038961343467235565,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.0355,
+      "step": 46
+    },
+    {
+      "epoch": 0.016561870258008392,
+      "grad_norm": 0.045494209975004196,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.0383,
+      "step": 47
+    },
+    {
+      "epoch": 0.016914250476263888,
+      "grad_norm": 0.05365985259413719,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.044,
+      "step": 48
+    },
+    {
+      "epoch": 0.017266630694519388,
+      "grad_norm": 0.0467500165104866,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.0511,
+      "step": 49
+    },
+    {
+      "epoch": 0.017619010912774884,
+      "grad_norm": 0.07677899301052094,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.0697,
+      "step": 50
+    },
+    {
+      "epoch": 0.017619010912774884,
+      "eval_loss": 0.05016423761844635,
+      "eval_runtime": 5.5589,
+      "eval_samples_per_second": 8.995,
+      "eval_steps_per_second": 2.339,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1826670702401946e+17,
+  "total_flos": 6.379321871858401e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null