Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b0050213bb85c5407866035534d4eb9c1fe57a5ae0e7b73f6b7494e0d81ecf
+oid sha256:099fab206d486b7a172deedb626fea09cafd6e074b69788e4ace6d7dce7eb45f
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:394a77afe54ee63806cffea0fbc63fe915bd813b39c218b4b3692dc988973220
+oid sha256:ed64bdfacf51c24158ec699e35f49f01492c72cf1a997ee7a02a15d2a7a2504c
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1621d6c271412bae68a0eb84d7a35437841f80402d3f1f868ba44c05bcc41f
+oid sha256:568e038bdb6de90d564d2f05f58731342f416cc9b01df05959e41e2abecc422f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47c572929b37d598d5524c3fc24b1d8a1cfe3d048c7612de921d6f8374edff9d
+oid sha256:f271512b9e2a71f1d987d40356f758428f8be552aa0689e821b9335dac934e51
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd7d5ec911b47675100a38d7fd767fb6f2f843b97212c7bca6afbc61725eb1e0
+oid sha256:3b4b1468a6ca6b932fec0b30e7ba50f46aa51e058a736233e88fce11c92f3194
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e098fb865602bc5d9c49ef08e0b579674b199b3ade815eb1d6a7d5b3e441fa01
+oid sha256:67cdf104179b5743b186c7fd576042facf7e25e2fe6b79a92eea383934b808e3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3192059420211edc26748a07e2699e00ee3be65f92a2cf84ef56d22611d9eb5c
+oid sha256:a8d5f446d81df8b8e6d5d3423a874831fec3d08bffbe4980db71b54ceb3e7bd4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.05686701834201813,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.9987515605493134,
+  "best_metric": 0.05315978825092316,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 1.4981273408239701,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 99.142,
       "eval_steps_per_second": 6.325,
       "step": 50
+    },
+    {
+      "epoch": 1.0187265917602997,
+      "grad_norm": 0.6444295048713684,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 0.0721,
+      "step": 51
+    },
+    {
+      "epoch": 1.038701622971286,
+      "grad_norm": 0.356772780418396,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 0.0615,
+      "step": 52
+    },
+    {
+      "epoch": 1.058676654182272,
+      "grad_norm": 0.42914852499961853,
+      "learning_rate": 4.917330276168208e-05,
+      "loss": 0.0448,
+      "step": 53
+    },
+    {
+      "epoch": 1.0786516853932584,
+      "grad_norm": 0.45043033361434937,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 0.0495,
+      "step": 54
+    },
+    {
+      "epoch": 1.0986267166042447,
+      "grad_norm": 0.3365642726421356,
+      "learning_rate": 4.5871032726383386e-05,
+      "loss": 0.0594,
+      "step": 55
+    },
+    {
+      "epoch": 1.118601747815231,
+      "grad_norm": 0.2681638300418854,
+      "learning_rate": 4.4225768151520694e-05,
+      "loss": 0.0334,
+      "step": 56
+    },
+    {
+      "epoch": 1.1385767790262173,
+      "grad_norm": 0.38356465101242065,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 0.0523,
+      "step": 57
+    },
+    {
+      "epoch": 1.1585518102372034,
+      "grad_norm": 0.40522027015686035,
+      "learning_rate": 4.095597328339452e-05,
+      "loss": 0.0413,
+      "step": 58
+    },
+    {
+      "epoch": 1.1785268414481898,
+      "grad_norm": 0.22131456434726715,
+      "learning_rate": 3.933501846281267e-05,
+      "loss": 0.0239,
+      "step": 59
+    },
+    {
+      "epoch": 1.198501872659176,
+      "grad_norm": 0.3389541208744049,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.0372,
+      "step": 60
+    },
+    {
+      "epoch": 1.2184769038701624,
+      "grad_norm": 0.29863250255584717,
+      "learning_rate": 3.612985456190778e-05,
+      "loss": 0.0212,
+      "step": 61
+    },
+    {
+      "epoch": 1.2384519350811485,
+      "grad_norm": 0.22949916124343872,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0169,
+      "step": 62
+    },
+    {
+      "epoch": 1.2584269662921348,
+      "grad_norm": 0.28763681650161743,
+      "learning_rate": 3.298534127791785e-05,
+      "loss": 0.0261,
+      "step": 63
+    },
+    {
+      "epoch": 1.2784019975031211,
+      "grad_norm": 0.37180131673812866,
+      "learning_rate": 3.144013755408895e-05,
+      "loss": 0.0322,
+      "step": 64
+    },
+    {
+      "epoch": 1.2983770287141074,
+      "grad_norm": 0.3311071991920471,
+      "learning_rate": 2.991522876735154e-05,
+      "loss": 0.0346,
+      "step": 65
+    },
+    {
+      "epoch": 1.3183520599250937,
+      "grad_norm": 0.3131641149520874,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 0.0391,
+      "step": 66
+    },
+    {
+      "epoch": 1.3383270911360798,
+      "grad_norm": 0.3434888422489166,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 0.0433,
+      "step": 67
+    },
+    {
+      "epoch": 1.3583021223470662,
+      "grad_norm": 0.35058820247650146,
+      "learning_rate": 2.547882480847461e-05,
+      "loss": 0.0353,
+      "step": 68
+    },
+    {
+      "epoch": 1.3782771535580525,
+      "grad_norm": 0.23418645560741425,
+      "learning_rate": 2.405152131093926e-05,
+      "loss": 0.0217,
+      "step": 69
+    },
+    {
+      "epoch": 1.3982521847690386,
+      "grad_norm": 0.2888217866420746,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.0274,
+      "step": 70
+    },
+    {
+      "epoch": 1.4182272159800249,
+      "grad_norm": 0.39486294984817505,
+      "learning_rate": 2.128356686585282e-05,
+      "loss": 0.0554,
+      "step": 71
+    },
+    {
+      "epoch": 1.4382022471910112,
+      "grad_norm": 0.23438122868537903,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 0.0198,
+      "step": 72
+    },
+    {
+      "epoch": 1.4581772784019975,
+      "grad_norm": 0.29288169741630554,
+      "learning_rate": 1.8641182076323148e-05,
+      "loss": 0.0312,
+      "step": 73
+    },
+    {
+      "epoch": 1.4781523096129838,
+      "grad_norm": 0.23595376312732697,
+      "learning_rate": 1.7370711923791567e-05,
+      "loss": 0.0211,
+      "step": 74
+    },
+    {
+      "epoch": 1.4981273408239701,
+      "grad_norm": 0.3430394232273102,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 0.0217,
+      "step": 75
+    },
+    {
+      "epoch": 1.4981273408239701,
+      "eval_loss": 0.05315978825092316,
+      "eval_runtime": 6.797,
+      "eval_samples_per_second": 99.162,
+      "eval_steps_per_second": 6.326,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.119072707772416e+17,
+  "total_flos": 3.178609061658624e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null