Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:651cb403146e3bb7ba0b577227371161a04dcf9dbaf7c61180460dced926a62a
+oid sha256:bc884815c126a9bcc057e85b4609aafc0b566add0cf47a55eadbfb55a727803d
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84bcab4eed33d004e8d1d06f0e18eff5e7e9fcff8a9d3c309d28b8bc542185e5
+oid sha256:c52ae7a5fa365f7f694460996c62193712df4fdfad12b35db4105904d2b000d1
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472a802910da1680bf70feab18c4e65613f96d757c027a2ae95f02fb89274fd2
+oid sha256:05803afa19cda5b6abb99394d678e810ac5426335c13e6fdaacfe1b4d370527b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ed6bb1dbbfd44566f2fbe9adc5637e0ba94bef602bf1d3210d3b442a180974
+oid sha256:f6bcfd288976efa04b300ce8dfe3482dedae9984ba25cbd81fd57a72e62a6f94
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4478fe01b2cdb72a2a7f53a49afbaa4b13af4c110a1a8fa020796beb83da19f9
+oid sha256:2ba0d85e29096cba3540854efbe2eb24b0dcb354bd598c9b0442f1a068e97147
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfab690b5170c855d7cf054d8dc90b5b048878528e4a1eb1f923a3f7e795fa72
+oid sha256:bce6c0f85e52f47ca30e0c92d68100127220279776878577c4b7dbbb15af1305
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6187465190887451,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012340346763744061,
+  "best_metric": 1.558501124382019,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.024680693527488123,
   "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": 23.03,
       "eval_steps_per_second": 5.988,
       "step": 25
+    },
+    {
+      "epoch": 0.012833960634293824,
+      "grad_norm": 0.9111001491546631,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 1.643,
+      "step": 26
+    },
+    {
+      "epoch": 0.013327574504843585,
+      "grad_norm": 0.869102418422699,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 1.6734,
+      "step": 27
+    },
+    {
+      "epoch": 0.013821188375393348,
+      "grad_norm": 0.842080295085907,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 1.476,
+      "step": 28
+    },
+    {
+      "epoch": 0.014314802245943111,
+      "grad_norm": 0.835245668888092,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 1.6803,
+      "step": 29
+    },
+    {
+      "epoch": 0.014808416116492874,
+      "grad_norm": 0.7700492739677429,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 1.4141,
+      "step": 30
+    },
+    {
+      "epoch": 0.015302029987042635,
+      "grad_norm": 0.8414303064346313,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 1.5424,
+      "step": 31
+    },
+    {
+      "epoch": 0.015795643857592398,
+      "grad_norm": 0.8434069752693176,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 1.5554,
+      "step": 32
+    },
+    {
+      "epoch": 0.01628925772814216,
+      "grad_norm": 0.8102946877479553,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 1.5322,
+      "step": 33
+    },
+    {
+      "epoch": 0.016782871598691924,
+      "grad_norm": 0.777534544467926,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 1.5407,
+      "step": 34
+    },
+    {
+      "epoch": 0.017276485469241685,
+      "grad_norm": 0.8392916321754456,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 1.5694,
+      "step": 35
+    },
+    {
+      "epoch": 0.01777009933979145,
+      "grad_norm": 0.8198193907737732,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 1.5633,
+      "step": 36
+    },
+    {
+      "epoch": 0.01826371321034121,
+      "grad_norm": 0.8337418437004089,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 1.563,
+      "step": 37
+    },
+    {
+      "epoch": 0.01875732708089097,
+      "grad_norm": 0.7560647130012512,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 1.4525,
+      "step": 38
+    },
+    {
+      "epoch": 0.019250940951440736,
+      "grad_norm": 0.7717271447181702,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 1.5498,
+      "step": 39
+    },
+    {
+      "epoch": 0.019744554821990497,
+      "grad_norm": 0.7649319767951965,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 1.529,
+      "step": 40
+    },
+    {
+      "epoch": 0.020238168692540262,
+      "grad_norm": 0.747653067111969,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 1.388,
+      "step": 41
+    },
+    {
+      "epoch": 0.020731782563090023,
+      "grad_norm": 0.7593997120857239,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 1.4656,
+      "step": 42
+    },
+    {
+      "epoch": 0.021225396433639784,
+      "grad_norm": 0.7581989765167236,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 1.5301,
+      "step": 43
+    },
+    {
+      "epoch": 0.02171901030418955,
+      "grad_norm": 0.8096319437026978,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 1.5115,
+      "step": 44
+    },
+    {
+      "epoch": 0.02221262417473931,
+      "grad_norm": 0.8088666200637817,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 1.5176,
+      "step": 45
+    },
+    {
+      "epoch": 0.02270623804528907,
+      "grad_norm": 0.7563244700431824,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 1.3766,
+      "step": 46
+    },
+    {
+      "epoch": 0.023199851915838836,
+      "grad_norm": 0.8245486617088318,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 1.4407,
+      "step": 47
+    },
+    {
+      "epoch": 0.023693465786388597,
+      "grad_norm": 0.8189464807510376,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 1.4207,
+      "step": 48
+    },
+    {
+      "epoch": 0.02418707965693836,
+      "grad_norm": 0.86505126953125,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5054,
+      "step": 49
+    },
+    {
+      "epoch": 0.024680693527488123,
+      "grad_norm": 0.9769317507743835,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 1.505,
+      "step": 50
+    },
+    {
+      "epoch": 0.024680693527488123,
+      "eval_loss": 1.558501124382019,
+      "eval_runtime": 2.151,
+      "eval_samples_per_second": 23.245,
+      "eval_steps_per_second": 6.044,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null