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:c8bd6fb0b81e0831c1d77d1f5a192da05a7e5ae7b7d7fa7a19218442c50c3405
+oid sha256:84dc68d1ac6c495e1a36010bb36478b56578c5cdbfd3293f9da0b030c03dfbdf
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d821f17509d4a39f0a93d5f7ba9a7717ac77e8c557790c969cee39e56c58f292
+oid sha256:4ae94009e4b7d8d4ad3872bd5c42087f46995e2c65418ccdade58c39e19cc695
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f78fb2c1ff49d05aff2689d9e50fed3440933cfd2dce2c015ac44212dc7f363c
+oid sha256:21b19e0b98a8cf394e84b0be59836c9df7fe9876e7ba835b62ec1ad2a83b2819
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612bf804dfa8bdf69a9251163e05b653c00beaf4786384e9df27365ab47861fc
+oid sha256:2d557ee65104cb3c595f3d7306761dfe92a950aecff7c885918609c8d3260ddd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf2ff8cb8706e3c800045714dd2c50644a2c233d373e6694013daaaa9f054e2
+oid sha256:c7459d679b740c24f079640284826983d09cf54e14b489b72518d6193c128735
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d987322515230a68c584da092bf679944a9da2ee503468eee487b74152b01f
+oid sha256:c754773080fe45665f49901074beb25e8bca239900ec9fab6765e0c0ec812d53
 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": 0.19903014600276947,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.6430868167202572,
+  "best_metric": 0.1474793553352356,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.9646302250803859,
   "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": 78.995,
       "eval_steps_per_second": 4.975,
       "step": 50
+    },
+    {
+      "epoch": 0.6559485530546624,
+      "grad_norm": 0.30935201048851013,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 0.1668,
+      "step": 51
+    },
+    {
+      "epoch": 0.6688102893890675,
+      "grad_norm": 0.29703548550605774,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 0.1548,
+      "step": 52
+    },
+    {
+      "epoch": 0.6816720257234726,
+      "grad_norm": 0.2632124125957489,
+      "learning_rate": 4.917330276168208e-05,
+      "loss": 0.1155,
+      "step": 53
+    },
+    {
+      "epoch": 0.6945337620578779,
+      "grad_norm": 0.3463415801525116,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 0.1157,
+      "step": 54
+    },
+    {
+      "epoch": 0.707395498392283,
+      "grad_norm": 0.4073414206504822,
+      "learning_rate": 4.5871032726383386e-05,
+      "loss": 0.1667,
+      "step": 55
+    },
+    {
+      "epoch": 0.7202572347266881,
+      "grad_norm": 0.6212286353111267,
+      "learning_rate": 4.4225768151520694e-05,
+      "loss": 0.2416,
+      "step": 56
+    },
+    {
+      "epoch": 0.7331189710610932,
+      "grad_norm": 0.5285773277282715,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 0.2056,
+      "step": 57
+    },
+    {
+      "epoch": 0.7459807073954984,
+      "grad_norm": 0.4094732403755188,
+      "learning_rate": 4.095597328339452e-05,
+      "loss": 0.1692,
+      "step": 58
+    },
+    {
+      "epoch": 0.7588424437299035,
+      "grad_norm": 0.4649737775325775,
+      "learning_rate": 3.933501846281267e-05,
+      "loss": 0.1719,
+      "step": 59
+    },
+    {
+      "epoch": 0.7717041800643086,
+      "grad_norm": 0.49657511711120605,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.2085,
+      "step": 60
+    },
+    {
+      "epoch": 0.7845659163987139,
+      "grad_norm": 0.5126468539237976,
+      "learning_rate": 3.612985456190778e-05,
+      "loss": 0.1658,
+      "step": 61
+    },
+    {
+      "epoch": 0.797427652733119,
+      "grad_norm": 0.503258228302002,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.123,
+      "step": 62
+    },
+    {
+      "epoch": 0.8102893890675241,
+      "grad_norm": 0.29781374335289,
+      "learning_rate": 3.298534127791785e-05,
+      "loss": 0.1707,
+      "step": 63
+    },
+    {
+      "epoch": 0.8231511254019293,
+      "grad_norm": 0.24223004281520844,
+      "learning_rate": 3.144013755408895e-05,
+      "loss": 0.1478,
+      "step": 64
+    },
+    {
+      "epoch": 0.8360128617363344,
+      "grad_norm": 0.2178749293088913,
+      "learning_rate": 2.991522876735154e-05,
+      "loss": 0.1198,
+      "step": 65
+    },
+    {
+      "epoch": 0.8488745980707395,
+      "grad_norm": 0.32112425565719604,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 0.0997,
+      "step": 66
+    },
+    {
+      "epoch": 0.8617363344051447,
+      "grad_norm": 0.4156148135662079,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 0.1173,
+      "step": 67
+    },
+    {
+      "epoch": 0.8745980707395499,
+      "grad_norm": 0.608623206615448,
+      "learning_rate": 2.547882480847461e-05,
+      "loss": 0.1976,
+      "step": 68
+    },
+    {
+      "epoch": 0.887459807073955,
+      "grad_norm": 0.5557019114494324,
+      "learning_rate": 2.405152131093926e-05,
+      "loss": 0.2075,
+      "step": 69
+    },
+    {
+      "epoch": 0.9003215434083601,
+      "grad_norm": 0.5011090040206909,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.183,
+      "step": 70
+    },
+    {
+      "epoch": 0.9131832797427653,
+      "grad_norm": 0.43509817123413086,
+      "learning_rate": 2.128356686585282e-05,
+      "loss": 0.1857,
+      "step": 71
+    },
+    {
+      "epoch": 0.9260450160771704,
+      "grad_norm": 0.4756283462047577,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 0.187,
+      "step": 72
+    },
+    {
+      "epoch": 0.9389067524115756,
+      "grad_norm": 0.46354904770851135,
+      "learning_rate": 1.8641182076323148e-05,
+      "loss": 0.1792,
+      "step": 73
+    },
+    {
+      "epoch": 0.9517684887459807,
+      "grad_norm": 0.347188800573349,
+      "learning_rate": 1.7370711923791567e-05,
+      "loss": 0.137,
+      "step": 74
+    },
+    {
+      "epoch": 0.9646302250803859,
+      "grad_norm": 0.4456610083580017,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 0.1723,
+      "step": 75
+    },
+    {
+      "epoch": 0.9646302250803859,
+      "eval_loss": 0.1474793553352356,
+      "eval_runtime": 13.2804,
+      "eval_samples_per_second": 78.913,
+      "eval_steps_per_second": 4.97,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.178927560327168e+17,
+  "total_flos": 4.768391340490752e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null