Training in progress, step 145, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6167510707e747f9e51da35a17815b2a79cb2444f5eb609533196310ee8c6195
+oid sha256:5a679ea933c7505082908a7fe696ddaa8f4abc8442bd664671943add9cec7c90
 size 985240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd62618721d528ae27b2d65163eee0a5c2f37ba810d293164c6cf017927ca468
+oid sha256:68af00b6f8cf8c196e10119f583b251bd3064cecce8f4c1a7030d6d3ab641d2c
 size 520860

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:153edb00d78c10e02a0f8d7caa61bc7efbc127daae56d527df2bc81f8ac36bfe
+oid sha256:131d1ba961a67b13766879469ce94fc21ba30471d9ca60ae6032ceca8d25d5b7
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c7604d2def8c682f9f6afb51eefd19373793659e24fe239209c6fc78f70375
+oid sha256:a93877b69a5a56bbcea27e18c2c28fe9fedcd0c31efb0c41d2fd6cada49caa1b
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af0aa3d9afdb252bbe08bcfcb9ae9ab79c70887018eacee2f3824cad8b91f4a
+oid sha256:0da609f80f32675141bfb82e0e975a1eb342c3a509b86a88a3fd2d74276618d5
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c533e819157cd7da25af24e07e2d3f281ac1856dba8f5f4417b3ecd282c0e09e
+oid sha256:8d5b848dde345ce498023c70f0268ba4cf7d738a9427981145ad3df4a265add9
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:633c26d652c012aae6654f470f65c9efd8e5cc9b63ec5c95928dc6895e58662b
+oid sha256:78e9e0c845ffe0397985c91eb1097340588a2d5849a65dbbcca5e23cb4bb07e8
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae02e8af6afa171bef78c8cdab2a41bec71628b58014cb839dfa182f7d7e6681
+oid sha256:70696bf61cb004d74644c7a522f413a7bf47bc363e1931aa620f0b479a172f88
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdcfe8ccaefd82d507cde989c255721e38ddfbaacf8fe91b1c968547f87927ad
+oid sha256:ee5b23ae45339d14c73b3a4ecb15a3ca5ecb4137ac37c73bff95647c07caf5f0
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f3d2d00841ac6ce4508b6a2d92dfffb0146ce61413bf5cf249d27b8f028c81
+oid sha256:b6d6a3d7d08889449c5ae268ac2101058182b6d0cdee0e9741539b6f9aa5e61a
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd13ebb00e31d8ca00416cf54bd3131088b8317f9edf4b378a41202af38c30b5
+oid sha256:73b73c87c99b8acbaf746ac7d90fa2da2efa50142cb3549fb8be2f67f6c3fe1a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.71790599822998,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 2.0618556701030926,
+  "epoch": 2.9896907216494846,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 145,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -731,6 +731,321 @@
       "eval_samples_per_second": 1139.365,
       "eval_steps_per_second": 36.754,
       "step": 100
+    },
+    {
+      "epoch": 2.082474226804124,
+      "grad_norm": 0.7998151183128357,
+      "learning_rate": 2.471916941164541e-05,
+      "loss": 42.8782,
+      "step": 101
+    },
+    {
+      "epoch": 2.1030927835051547,
+      "grad_norm": 0.8684083223342896,
+      "learning_rate": 2.37028411154971e-05,
+      "loss": 42.8018,
+      "step": 102
+    },
+    {
+      "epoch": 2.1237113402061856,
+      "grad_norm": 1.0473065376281738,
+      "learning_rate": 2.2701565471256545e-05,
+      "loss": 42.7244,
+      "step": 103
+    },
+    {
+      "epoch": 2.1443298969072164,
+      "grad_norm": 0.783116340637207,
+      "learning_rate": 2.1715884687348693e-05,
+      "loss": 42.912,
+      "step": 104
+    },
+    {
+      "epoch": 2.1649484536082473,
+      "grad_norm": 0.8167928457260132,
+      "learning_rate": 2.0746332527306523e-05,
+      "loss": 42.9268,
+      "step": 105
+    },
+    {
+      "epoch": 2.1855670103092786,
+      "grad_norm": 0.752877414226532,
+      "learning_rate": 1.9793434020728596e-05,
+      "loss": 42.87,
+      "step": 106
+    },
+    {
+      "epoch": 2.2061855670103094,
+      "grad_norm": 0.8826267123222351,
+      "learning_rate": 1.8857705178966414e-05,
+      "loss": 42.8111,
+      "step": 107
+    },
+    {
+      "epoch": 2.2268041237113403,
+      "grad_norm": 0.8208662271499634,
+      "learning_rate": 1.793965271569506e-05,
+      "loss": 42.7879,
+      "step": 108
+    },
+    {
+      "epoch": 2.247422680412371,
+      "grad_norm": 0.8979811072349548,
+      "learning_rate": 1.7039773772518817e-05,
+      "loss": 42.7306,
+      "step": 109
+    },
+    {
+      "epoch": 2.268041237113402,
+      "grad_norm": 0.9514249563217163,
+      "learning_rate": 1.6158555649760226e-05,
+      "loss": 42.8129,
+      "step": 110
+    },
+    {
+      "epoch": 2.288659793814433,
+      "grad_norm": 0.8805590271949768,
+      "learning_rate": 1.529647554257842e-05,
+      "loss": 42.9622,
+      "step": 111
+    },
+    {
+      "epoch": 2.3092783505154637,
+      "grad_norm": 0.7457385659217834,
+      "learning_rate": 1.4454000282559474e-05,
+      "loss": 42.9212,
+      "step": 112
+    },
+    {
+      "epoch": 2.329896907216495,
+      "grad_norm": 0.7977012991905212,
+      "learning_rate": 1.3631586084918827e-05,
+      "loss": 42.8719,
+      "step": 113
+    },
+    {
+      "epoch": 2.350515463917526,
+      "grad_norm": 0.8746123313903809,
+      "learning_rate": 1.2829678301452792e-05,
+      "loss": 42.8256,
+      "step": 114
+    },
+    {
+      "epoch": 2.3711340206185567,
+      "grad_norm": 0.8957396745681763,
+      "learning_rate": 1.2048711179372637e-05,
+      "loss": 42.7459,
+      "step": 115
+    },
+    {
+      "epoch": 2.3917525773195876,
+      "grad_norm": 1.091923713684082,
+      "learning_rate": 1.1289107626152051e-05,
+      "loss": 42.8029,
+      "step": 116
+    },
+    {
+      "epoch": 2.4123711340206184,
+      "grad_norm": 0.8746165633201599,
+      "learning_rate": 1.0551278980515333e-05,
+      "loss": 43.0006,
+      "step": 117
+    },
+    {
+      "epoch": 2.4329896907216497,
+      "grad_norm": 0.8317185640335083,
+      "learning_rate": 9.835624789690211e-06,
+      "loss": 42.9392,
+      "step": 118
+    },
+    {
+      "epoch": 2.4536082474226806,
+      "grad_norm": 0.8299346566200256,
+      "learning_rate": 9.14253259304589e-06,
+      "loss": 42.8871,
+      "step": 119
+    },
+    {
+      "epoch": 2.4742268041237114,
+      "grad_norm": 0.8369458913803101,
+      "learning_rate": 8.472377712233782e-06,
+      "loss": 42.8447,
+      "step": 120
+    },
+    {
+      "epoch": 2.4948453608247423,
+      "grad_norm": 0.8657093048095703,
+      "learning_rate": 7.825523047944063e-06,
+      "loss": 42.796,
+      "step": 121
+    },
+    {
+      "epoch": 2.515463917525773,
+      "grad_norm": 1.1348730325698853,
+      "learning_rate": 7.20231888338869e-06,
+      "loss": 42.7148,
+      "step": 122
+    },
+    {
+      "epoch": 2.536082474226804,
+      "grad_norm": 0.8692322969436646,
+      "learning_rate": 6.603102694616742e-06,
+      "loss": 42.9547,
+      "step": 123
+    },
+    {
+      "epoch": 2.556701030927835,
+      "grad_norm": 0.854466438293457,
+      "learning_rate": 6.02819896776526e-06,
+      "loss": 42.9137,
+      "step": 124
+    },
+    {
+      "epoch": 2.5773195876288657,
+      "grad_norm": 0.7972310781478882,
+      "learning_rate": 5.477919023344274e-06,
+      "loss": 42.9149,
+      "step": 125
+    },
+    {
+      "epoch": 2.597938144329897,
+      "grad_norm": 0.8045434951782227,
+      "learning_rate": 4.9525608476511945e-06,
+      "loss": 42.8355,
+      "step": 126
+    },
+    {
+      "epoch": 2.618556701030928,
+      "grad_norm": 0.8683797717094421,
+      "learning_rate": 4.452408931406049e-06,
+      "loss": 42.7995,
+      "step": 127
+    },
+    {
+      "epoch": 2.6391752577319587,
+      "grad_norm": 1.0242929458618164,
+      "learning_rate": 3.977734115694721e-06,
+      "loss": 42.7184,
+      "step": 128
+    },
+    {
+      "epoch": 2.6597938144329896,
+      "grad_norm": 0.854243814945221,
+      "learning_rate": 3.528793445303664e-06,
+      "loss": 42.9113,
+      "step": 129
+    },
+    {
+      "epoch": 2.680412371134021,
+      "grad_norm": 0.8261354565620422,
+      "learning_rate": 3.1058300295257215e-06,
+      "loss": 42.9279,
+      "step": 130
+    },
+    {
+      "epoch": 2.7010309278350517,
+      "grad_norm": 0.7675247192382812,
+      "learning_rate": 2.709072910512046e-06,
+      "loss": 42.9658,
+      "step": 131
+    },
+    {
+      "epoch": 2.7216494845360826,
+      "grad_norm": 0.7673724889755249,
+      "learning_rate": 2.3387369392418067e-06,
+      "loss": 42.8263,
+      "step": 132
+    },
+    {
+      "epoch": 2.7422680412371134,
+      "grad_norm": 0.7968787550926208,
+      "learning_rate": 1.995022659176577e-06,
+      "loss": 42.7893,
+      "step": 133
+    },
+    {
+      "epoch": 2.7628865979381443,
+      "grad_norm": 0.9644841551780701,
+      "learning_rate": 1.6781161976625145e-06,
+      "loss": 42.7534,
+      "step": 134
+    },
+    {
+      "epoch": 2.783505154639175,
+      "grad_norm": 0.8922263383865356,
+      "learning_rate": 1.388189165139074e-06,
+      "loss": 42.7949,
+      "step": 135
+    },
+    {
+      "epoch": 2.804123711340206,
+      "grad_norm": 0.8287817239761353,
+      "learning_rate": 1.125398562209007e-06,
+      "loss": 42.9187,
+      "step": 136
+    },
+    {
+      "epoch": 2.824742268041237,
+      "grad_norm": 0.7730743885040283,
+      "learning_rate": 8.898866946197183e-07,
+      "loss": 42.9251,
+      "step": 137
+    },
+    {
+      "epoch": 2.845360824742268,
+      "grad_norm": 0.7981364130973816,
+      "learning_rate": 6.817810962021702e-07,
+      "loss": 42.8825,
+      "step": 138
+    },
+    {
+      "epoch": 2.865979381443299,
+      "grad_norm": 0.8180574774742126,
+      "learning_rate": 5.011944598091263e-07,
+      "loss": 42.828,
+      "step": 139
+    },
+    {
+      "epoch": 2.88659793814433,
+      "grad_norm": 0.9098818898200989,
+      "learning_rate": 3.482245762899343e-07,
+      "loss": 42.801,
+      "step": 140
+    },
+    {
+      "epoch": 2.9072164948453607,
+      "grad_norm": 1.2186717987060547,
+      "learning_rate": 2.2295428153507602e-07,
+      "loss": 42.7891,
+      "step": 141
+    },
+    {
+      "epoch": 2.927835051546392,
+      "grad_norm": 0.8600121140480042,
+      "learning_rate": 1.2545141161905383e-07,
+      "loss": 42.9378,
+      "step": 142
+    },
+    {
+      "epoch": 2.948453608247423,
+      "grad_norm": 0.8009682297706604,
+      "learning_rate": 5.576876606598485e-08,
+      "loss": 42.8841,
+      "step": 143
+    },
+    {
+      "epoch": 2.9690721649484537,
+      "grad_norm": 0.8298251628875732,
+      "learning_rate": 1.3944079257721731e-08,
+      "loss": 42.7618,
+      "step": 144
+    },
+    {
+      "epoch": 2.9896907216494846,
+      "grad_norm": 0.93776535987854,
+      "learning_rate": 0.0,
+      "loss": 42.7531,
+      "step": 145
     }
   ],
   "logging_steps": 1,
@@ -754,12 +1069,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 98834118082560.0,
+  "total_flos": 143055667593216.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null