Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c026ea4efba98ed56cb5adad07f78e1880606add4e289a557b0dac11a75f5dd
+oid sha256:43dbaf4327f5def640446c1e23d0514f0d1a7f6b878a497433f51dbc54c4c1e6
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:965f99f8378a9a51832b73642938b2b59740754b0c6887a140d2634e6535dd5d
+oid sha256:f311b7cfa26b2f19e49fc19a4804842b104b1b1f2bd8857e296fca7dce899071
 size 588699796

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2a1f1c8603a4b0a143aec6eca9faa19b9e1457fbc1911a6944c8374f7df0f1
+oid sha256:1386eecf1d5a699bebd7880defd66f514848a51dd0b537191a16dbb9647d8719
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa31c55f06bb25adde83cacda21bfe5d59b83dc638bb87ce7519d8ece5781ab5
+oid sha256:bb88bc6ef8dd79b87cb5431ddfce694de6ca4744788e33681ec8db61999eec38
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b6e95119ad2ff45261568a831b29c9440e085591fa169e740d4041005cb3ce
+oid sha256:5c13323716cecc96c0515352728ee0745be6208d9bbf1e3098eaf11c2bea434b
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7cd029da63384fd7b7e526029c5b0ee076c26222e44c19351f29deb70eec18
+oid sha256:00bd101e83529e9b4ad2435c7c7347646e4d6d7ede9debcd18dd7755ca1b5769
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41867356a3938611e010d6b64018b4f05014fbbd1d100a0fa4b9e533d2efc732
+oid sha256:d117b1cbbd4bbe37b704cb80c31e4776cbc4dd9388f4ebef49f4a929e3fd9bb6
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3165a06adbad9731003835ebd2021fbb64cb0dd494042d6f5c74eaefa559ec10
+oid sha256:2030fd5191e4932013cd2649eca0af7485354b591f349aa973a9edfffe6840f5
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a901af50473d7e89db26fd0be3930325a734be9922cf4549a4235b4df84168
+oid sha256:75a592d2c279f5fec67d9b84c9b85a1ca36ce972e1231b5392d7e45b3060397b
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1055278599c75fb21bc7d2065c6e218d0eaaae8bdb3eda872dbf004638cad65
+oid sha256:5069b3efe82a8f545b28087334e068c83caacf67bf327586dbe4138cb9c0744d
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b7e7d044a338e6b420016be2e48e692869df520a6f768a0f5ba8de63e9bb378
+oid sha256:f6b2f615f21faa4fde4442b48613d92f84c55cd5ef4fb4d04d8e3f819305ce14
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6198433637619019,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.06686726847208292,
+  "best_metric": 0.45096904039382935,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.13373453694416584,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,364 @@
       "eval_samples_per_second": 62.369,
       "eval_steps_per_second": 1.95,
       "step": 50
+    },
+    {
+      "epoch": 0.06820461384152457,
+      "grad_norm": 0.7916774153709412,
+      "learning_rate": 7.920526315789474e-05,
+      "loss": 0.5536,
+      "step": 51
+    },
+    {
+      "epoch": 0.06954195921096623,
+      "grad_norm": 0.6397995352745056,
+      "learning_rate": 7.867368421052631e-05,
+      "loss": 0.575,
+      "step": 52
+    },
+    {
+      "epoch": 0.07087930458040789,
+      "grad_norm": 0.8294323086738586,
+      "learning_rate": 7.814210526315789e-05,
+      "loss": 0.5815,
+      "step": 53
+    },
+    {
+      "epoch": 0.07221664994984955,
+      "grad_norm": 0.6827910542488098,
+      "learning_rate": 7.761052631578946e-05,
+      "loss": 0.5574,
+      "step": 54
+    },
+    {
+      "epoch": 0.0735539953192912,
+      "grad_norm": 0.6560467481613159,
+      "learning_rate": 7.707894736842105e-05,
+      "loss": 0.6331,
+      "step": 55
+    },
+    {
+      "epoch": 0.07489134068873286,
+      "grad_norm": 0.6438890695571899,
+      "learning_rate": 7.654736842105264e-05,
+      "loss": 0.6216,
+      "step": 56
+    },
+    {
+      "epoch": 0.07622868605817452,
+      "grad_norm": 0.7472130656242371,
+      "learning_rate": 7.601578947368422e-05,
+      "loss": 0.6165,
+      "step": 57
+    },
+    {
+      "epoch": 0.07756603142761619,
+      "grad_norm": 0.6722190976142883,
+      "learning_rate": 7.548421052631579e-05,
+      "loss": 0.5489,
+      "step": 58
+    },
+    {
+      "epoch": 0.07890337679705783,
+      "grad_norm": 0.7682622671127319,
+      "learning_rate": 7.495263157894737e-05,
+      "loss": 0.5283,
+      "step": 59
+    },
+    {
+      "epoch": 0.0802407221664995,
+      "grad_norm": 0.6968657970428467,
+      "learning_rate": 7.442105263157894e-05,
+      "loss": 0.5136,
+      "step": 60
+    },
+    {
+      "epoch": 0.08157806753594116,
+      "grad_norm": 0.705340564250946,
+      "learning_rate": 7.388947368421053e-05,
+      "loss": 0.542,
+      "step": 61
+    },
+    {
+      "epoch": 0.08291541290538282,
+      "grad_norm": 0.7181550860404968,
+      "learning_rate": 7.335789473684211e-05,
+      "loss": 0.6186,
+      "step": 62
+    },
+    {
+      "epoch": 0.08425275827482448,
+      "grad_norm": 0.7151327133178711,
+      "learning_rate": 7.282631578947368e-05,
+      "loss": 0.5627,
+      "step": 63
+    },
+    {
+      "epoch": 0.08559010364426613,
+      "grad_norm": 0.6997770667076111,
+      "learning_rate": 7.229473684210527e-05,
+      "loss": 0.5474,
+      "step": 64
+    },
+    {
+      "epoch": 0.08692744901370779,
+      "grad_norm": 0.6078030467033386,
+      "learning_rate": 7.176315789473685e-05,
+      "loss": 0.5169,
+      "step": 65
+    },
+    {
+      "epoch": 0.08826479438314945,
+      "grad_norm": 0.6001531481742859,
+      "learning_rate": 7.123157894736842e-05,
+      "loss": 0.4925,
+      "step": 66
+    },
+    {
+      "epoch": 0.08960213975259111,
+      "grad_norm": 0.5884681940078735,
+      "learning_rate": 7.07e-05,
+      "loss": 0.517,
+      "step": 67
+    },
+    {
+      "epoch": 0.09093948512203276,
+      "grad_norm": 0.676162600517273,
+      "learning_rate": 7.016842105263159e-05,
+      "loss": 0.6264,
+      "step": 68
+    },
+    {
+      "epoch": 0.09227683049147442,
+      "grad_norm": 0.7076681852340698,
+      "learning_rate": 6.963684210526316e-05,
+      "loss": 0.5951,
+      "step": 69
+    },
+    {
+      "epoch": 0.09361417586091608,
+      "grad_norm": 0.688647985458374,
+      "learning_rate": 6.910526315789474e-05,
+      "loss": 0.5149,
+      "step": 70
+    },
+    {
+      "epoch": 0.09495152123035774,
+      "grad_norm": 0.6269810199737549,
+      "learning_rate": 6.857368421052631e-05,
+      "loss": 0.4786,
+      "step": 71
+    },
+    {
+      "epoch": 0.09628886659979939,
+      "grad_norm": 0.5938174724578857,
+      "learning_rate": 6.80421052631579e-05,
+      "loss": 0.4705,
+      "step": 72
+    },
+    {
+      "epoch": 0.09762621196924105,
+      "grad_norm": 0.5638948678970337,
+      "learning_rate": 6.751052631578948e-05,
+      "loss": 0.4933,
+      "step": 73
+    },
+    {
+      "epoch": 0.09896355733868271,
+      "grad_norm": 0.5896424055099487,
+      "learning_rate": 6.697894736842105e-05,
+      "loss": 0.5242,
+      "step": 74
+    },
+    {
+      "epoch": 0.10030090270812438,
+      "grad_norm": 0.6239397525787354,
+      "learning_rate": 6.644736842105264e-05,
+      "loss": 0.5819,
+      "step": 75
+    },
+    {
+      "epoch": 0.10163824807756604,
+      "grad_norm": 0.6227509379386902,
+      "learning_rate": 6.591578947368422e-05,
+      "loss": 0.4862,
+      "step": 76
+    },
+    {
+      "epoch": 0.10297559344700769,
+      "grad_norm": 0.5637099742889404,
+      "learning_rate": 6.538421052631579e-05,
+      "loss": 0.4858,
+      "step": 77
+    },
+    {
+      "epoch": 0.10431293881644935,
+      "grad_norm": 0.5321072936058044,
+      "learning_rate": 6.485263157894737e-05,
+      "loss": 0.4471,
+      "step": 78
+    },
+    {
+      "epoch": 0.10565028418589101,
+      "grad_norm": 0.5791961550712585,
+      "learning_rate": 6.432105263157894e-05,
+      "loss": 0.4531,
+      "step": 79
+    },
+    {
+      "epoch": 0.10698762955533267,
+      "grad_norm": 0.5246228575706482,
+      "learning_rate": 6.378947368421053e-05,
+      "loss": 0.4812,
+      "step": 80
+    },
+    {
+      "epoch": 0.10832497492477432,
+      "grad_norm": 0.5978341698646545,
+      "learning_rate": 6.32578947368421e-05,
+      "loss": 0.5496,
+      "step": 81
+    },
+    {
+      "epoch": 0.10966232029421598,
+      "grad_norm": 0.6050398945808411,
+      "learning_rate": 6.27263157894737e-05,
+      "loss": 0.4998,
+      "step": 82
+    },
+    {
+      "epoch": 0.11099966566365764,
+      "grad_norm": 0.5705775618553162,
+      "learning_rate": 6.219473684210527e-05,
+      "loss": 0.4493,
+      "step": 83
+    },
+    {
+      "epoch": 0.1123370110330993,
+      "grad_norm": 0.5693026781082153,
+      "learning_rate": 6.166315789473685e-05,
+      "loss": 0.4627,
+      "step": 84
+    },
+    {
+      "epoch": 0.11367435640254096,
+      "grad_norm": 0.6199223399162292,
+      "learning_rate": 6.113157894736842e-05,
+      "loss": 0.4128,
+      "step": 85
+    },
+    {
+      "epoch": 0.11501170177198261,
+      "grad_norm": 0.7600672841072083,
+      "learning_rate": 6.0599999999999996e-05,
+      "loss": 0.4716,
+      "step": 86
+    },
+    {
+      "epoch": 0.11634904714142427,
+      "grad_norm": 0.6081468462944031,
+      "learning_rate": 6.006842105263158e-05,
+      "loss": 0.5161,
+      "step": 87
+    },
+    {
+      "epoch": 0.11768639251086593,
+      "grad_norm": 0.6899324655532837,
+      "learning_rate": 5.953684210526315e-05,
+      "loss": 0.5071,
+      "step": 88
+    },
+    {
+      "epoch": 0.1190237378803076,
+      "grad_norm": 0.618345320224762,
+      "learning_rate": 5.900526315789474e-05,
+      "loss": 0.49,
+      "step": 89
+    },
+    {
+      "epoch": 0.12036108324974924,
+      "grad_norm": 0.5444545149803162,
+      "learning_rate": 5.847368421052632e-05,
+      "loss": 0.4405,
+      "step": 90
+    },
+    {
+      "epoch": 0.1216984286191909,
+      "grad_norm": 0.60733562707901,
+      "learning_rate": 5.79421052631579e-05,
+      "loss": 0.4539,
+      "step": 91
+    },
+    {
+      "epoch": 0.12303577398863257,
+      "grad_norm": 0.5278117060661316,
+      "learning_rate": 5.7410526315789475e-05,
+      "loss": 0.4333,
+      "step": 92
+    },
+    {
+      "epoch": 0.12437311935807423,
+      "grad_norm": 0.6142237782478333,
+      "learning_rate": 5.687894736842105e-05,
+      "loss": 0.5313,
+      "step": 93
+    },
+    {
+      "epoch": 0.12571046472751587,
+      "grad_norm": 0.5651121735572815,
+      "learning_rate": 5.6347368421052625e-05,
+      "loss": 0.4827,
+      "step": 94
+    },
+    {
+      "epoch": 0.12704781009695754,
+      "grad_norm": 0.5625864863395691,
+      "learning_rate": 5.5815789473684214e-05,
+      "loss": 0.4306,
+      "step": 95
+    },
+    {
+      "epoch": 0.1283851554663992,
+      "grad_norm": 0.5742880702018738,
+      "learning_rate": 5.5284210526315796e-05,
+      "loss": 0.4486,
+      "step": 96
+    },
+    {
+      "epoch": 0.12972250083584086,
+      "grad_norm": 0.5653654932975769,
+      "learning_rate": 5.475263157894737e-05,
+      "loss": 0.4327,
+      "step": 97
+    },
+    {
+      "epoch": 0.13105984620528252,
+      "grad_norm": 0.6067980527877808,
+      "learning_rate": 5.422105263157895e-05,
+      "loss": 0.4323,
+      "step": 98
+    },
+    {
+      "epoch": 0.13239719157472418,
+      "grad_norm": 0.5677730441093445,
+      "learning_rate": 5.368947368421053e-05,
+      "loss": 0.4826,
+      "step": 99
+    },
+    {
+      "epoch": 0.13373453694416584,
+      "grad_norm": 0.5298727750778198,
+      "learning_rate": 5.3157894736842104e-05,
+      "loss": 0.5075,
+      "step": 100
+    },
+    {
+      "epoch": 0.13373453694416584,
+      "eval_loss": 0.45096904039382935,
+      "eval_runtime": 163.4922,
+      "eval_samples_per_second": 61.624,
+      "eval_steps_per_second": 1.927,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -401,7 +759,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0576356021507195e+18,
+  "total_flos": 2.1146110076985016e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null