Training in progress, step 145, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bdd9bf1b7ca10ca16931ff7f292abe7c1c96831ff95fcbc0459fd8d83e3408
+oid sha256:e983214b5285287741e582a0f905b2b8365259ff4ffff55cc166b9d7901ba29a
 size 985240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad7f4c40cfca9a0ece3befd2e8a4c0d4b7f2755b0f80f7d335fefb0380673a3a
+oid sha256:a6eb694d1ff514b05f19ad7aab2075e84af4265330d9c1677aa393b0ec9be830
 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 sha256:809b754501ce13d8396f83d601629273b10f255b85892771c16a15f44d55b09c
+oid sha256:4dcac0cb8e15eb817713ccc513f9c4b775fbbd957ef48d20a984b24b6d380d54
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.71052074432373,
   "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": 932.577,
       "eval_steps_per_second": 30.083,
       "step": 100
+    },
+    {
+      "epoch": 2.082474226804124,
+      "grad_norm": 0.8079841732978821,
+      "learning_rate": 2.7359080708034724e-05,
+      "loss": 42.8441,
+      "step": 101
+    },
+    {
+      "epoch": 2.1030927835051547,
+      "grad_norm": 0.8587807416915894,
+      "learning_rate": 2.6234212496763786e-05,
+      "loss": 42.7617,
+      "step": 102
+    },
+    {
+      "epoch": 2.1237113402061856,
+      "grad_norm": 1.0234891176223755,
+      "learning_rate": 2.512600450216744e-05,
+      "loss": 42.6967,
+      "step": 103
+    },
+    {
+      "epoch": 2.1443298969072164,
+      "grad_norm": 0.7730754613876343,
+      "learning_rate": 2.403505683842477e-05,
+      "loss": 42.8832,
+      "step": 104
+    },
+    {
+      "epoch": 2.1649484536082473,
+      "grad_norm": 0.8016390800476074,
+      "learning_rate": 2.29619602729412e-05,
+      "loss": 42.8875,
+      "step": 105
+    },
+    {
+      "epoch": 2.1855670103092786,
+      "grad_norm": 0.7425552010536194,
+      "learning_rate": 2.1907295906437478e-05,
+      "loss": 42.8274,
+      "step": 106
+    },
+    {
+      "epoch": 2.2061855670103094,
+      "grad_norm": 0.8459512591362,
+      "learning_rate": 2.087163485827351e-05,
+      "loss": 42.781,
+      "step": 107
+    },
+    {
+      "epoch": 2.2268041237113403,
+      "grad_norm": 0.8400618433952332,
+      "learning_rate": 1.9855537957177057e-05,
+      "loss": 42.7517,
+      "step": 108
+    },
+    {
+      "epoch": 2.247422680412371,
+      "grad_norm": 0.901757538318634,
+      "learning_rate": 1.88595554375451e-05,
+      "loss": 42.7027,
+      "step": 109
+    },
+    {
+      "epoch": 2.268041237113402,
+      "grad_norm": 0.9196100234985352,
+      "learning_rate": 1.7884226641482193e-05,
+      "loss": 42.789,
+      "step": 110
+    },
+    {
+      "epoch": 2.288659793814433,
+      "grad_norm": 0.8353160619735718,
+      "learning_rate": 1.6930079726737282e-05,
+      "loss": 42.9308,
+      "step": 111
+    },
+    {
+      "epoch": 2.3092783505154637,
+      "grad_norm": 0.7330605387687683,
+      "learning_rate": 1.5997631380696897e-05,
+      "loss": 42.8964,
+      "step": 112
+    },
+    {
+      "epoch": 2.329896907216495,
+      "grad_norm": 0.7792418003082275,
+      "learning_rate": 1.5087386540589772e-05,
+      "loss": 42.8446,
+      "step": 113
+    },
+    {
+      "epoch": 2.350515463917526,
+      "grad_norm": 0.8483313918113708,
+      "learning_rate": 1.4199838120054547e-05,
+      "loss": 42.7767,
+      "step": 114
+    },
+    {
+      "epoch": 2.3711340206185567,
+      "grad_norm": 0.8654447197914124,
+      "learning_rate": 1.333546674221826e-05,
+      "loss": 42.7016,
+      "step": 115
+    },
+    {
+      "epoch": 2.3917525773195876,
+      "grad_norm": 1.0370359420776367,
+      "learning_rate": 1.2494740479430427e-05,
+      "loss": 42.7808,
+      "step": 116
+    },
+    {
+      "epoch": 2.4123711340206184,
+      "grad_norm": 0.8705489635467529,
+      "learning_rate": 1.167811459979367e-05,
+      "loss": 42.9616,
+      "step": 117
+    },
+    {
+      "epoch": 2.4329896907216497,
+      "grad_norm": 0.8204030394554138,
+      "learning_rate": 1.0886031320628002e-05,
+      "loss": 42.8996,
+      "step": 118
+    },
+    {
+      "epoch": 2.4536082474226806,
+      "grad_norm": 0.7885167002677917,
+      "learning_rate": 1.0118919569002249e-05,
+      "loss": 42.846,
+      "step": 119
+    },
+    {
+      "epoch": 2.4742268041237114,
+      "grad_norm": 0.8088667988777161,
+      "learning_rate": 9.377194749462633e-06,
+      "loss": 42.8065,
+      "step": 120
+    },
+    {
+      "epoch": 2.4948453608247423,
+      "grad_norm": 0.8490159511566162,
+      "learning_rate": 8.661258519083721e-06,
+      "loss": 42.7731,
+      "step": 121
+    },
+    {
+      "epoch": 2.515463917525773,
+      "grad_norm": 1.103000283241272,
+      "learning_rate": 7.971498569964182e-06,
+      "loss": 42.6825,
+      "step": 122
+    },
+    {
+      "epoch": 2.536082474226804,
+      "grad_norm": 0.8642274737358093,
+      "learning_rate": 7.308288419284549e-06,
+      "loss": 42.9307,
+      "step": 123
+    },
+    {
+      "epoch": 2.556701030927835,
+      "grad_norm": 0.8247718214988708,
+      "learning_rate": 6.671987207041162e-06,
+      "loss": 42.8852,
+      "step": 124
+    },
+    {
+      "epoch": 2.5773195876288657,
+      "grad_norm": 0.7806307673454285,
+      "learning_rate": 6.062939501565507e-06,
+      "loss": 42.877,
+      "step": 125
+    },
+    {
+      "epoch": 2.597938144329897,
+      "grad_norm": 0.7737009525299072,
+      "learning_rate": 5.481475112934332e-06,
+      "loss": 42.7929,
+      "step": 126
+    },
+    {
+      "epoch": 2.618556701030928,
+      "grad_norm": 0.834900975227356,
+      "learning_rate": 4.927908914371745e-06,
+      "loss": 42.7624,
+      "step": 127
+    },
+    {
+      "epoch": 2.6391752577319587,
+      "grad_norm": 1.0103235244750977,
+      "learning_rate": 4.402540671739789e-06,
+      "loss": 42.6752,
+      "step": 128
+    },
+    {
+      "epoch": 2.6597938144329896,
+      "grad_norm": 0.8368192911148071,
+      "learning_rate": 3.905654881209881e-06,
+      "loss": 42.8822,
+      "step": 129
+    },
+    {
+      "epoch": 2.680412371134021,
+      "grad_norm": 0.8019142746925354,
+      "learning_rate": 3.437520615203226e-06,
+      "loss": 42.8965,
+      "step": 130
+    },
+    {
+      "epoch": 2.7010309278350517,
+      "grad_norm": 0.7503296732902527,
+      "learning_rate": 2.998391376683236e-06,
+      "loss": 42.9299,
+      "step": 131
+    },
+    {
+      "epoch": 2.7216494845360826,
+      "grad_norm": 0.7759463787078857,
+      "learning_rate": 2.588504961879281e-06,
+      "loss": 42.8007,
+      "step": 132
+    },
+    {
+      "epoch": 2.7422680412371134,
+      "grad_norm": 0.7962337136268616,
+      "learning_rate": 2.208083331515823e-06,
+      "loss": 42.7575,
+      "step": 133
+    },
+    {
+      "epoch": 2.7628865979381443,
+      "grad_norm": 0.9318565726280212,
+      "learning_rate": 1.8573324906167638e-06,
+      "loss": 42.7194,
+      "step": 134
+    },
+    {
+      "epoch": 2.783505154639175,
+      "grad_norm": 0.8853210806846619,
+      "learning_rate": 1.5364423769500432e-06,
+      "loss": 42.7636,
+      "step": 135
+    },
+    {
+      "epoch": 2.804123711340206,
+      "grad_norm": 0.8054129481315613,
+      "learning_rate": 1.2455867581730757e-06,
+      "loss": 42.8866,
+      "step": 136
+    },
+    {
+      "epoch": 2.824742268041237,
+      "grad_norm": 0.7635054588317871,
+      "learning_rate": 9.849231377344456e-07,
+      "loss": 42.8983,
+      "step": 137
+    },
+    {
+      "epoch": 2.845360824742268,
+      "grad_norm": 0.7808680534362793,
+      "learning_rate": 7.545926695829844e-07,
+      "loss": 42.8582,
+      "step": 138
+    },
+    {
+      "epoch": 2.865979381443299,
+      "grad_norm": 0.8024100661277771,
+      "learning_rate": 5.547200817304894e-07,
+      "loss": 42.8089,
+      "step": 139
+    },
+    {
+      "epoch": 2.88659793814433,
+      "grad_norm": 0.8927075266838074,
+      "learning_rate": 3.854136087092477e-07,
+      "loss": 42.7882,
+      "step": 140
+    },
+    {
+      "epoch": 2.9072164948453607,
+      "grad_norm": 1.1699692010879517,
+      "learning_rate": 2.467649329611521e-07,
+      "loss": 42.7566,
+      "step": 141
+    },
+    {
+      "epoch": 2.927835051546392,
+      "grad_norm": 0.8278796076774597,
+      "learning_rate": 1.3884913519002074e-07,
+      "loss": 42.9036,
+      "step": 142
+    },
+    {
+      "epoch": 2.948453608247423,
+      "grad_norm": 0.7831672430038452,
+      "learning_rate": 6.172465370409974e-08,
+      "loss": 42.8563,
+      "step": 143
+    },
+    {
+      "epoch": 2.9690721649484537,
+      "grad_norm": 0.8065726161003113,
+      "learning_rate": 1.5433252770682305e-08,
+      "loss": 42.7297,
+      "step": 144
+    },
+    {
+      "epoch": 2.9896907216494846,
+      "grad_norm": 0.9205412864685059,
+      "learning_rate": 0.0,
+      "loss": 42.7212,
+      "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