Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55106b2193e7e96cb29be1ff917c68aa09b015696f358032fe14437de80815f9
+oid sha256:433d56dc76083cb059d60ef24f532a1b8012314a670458dfb8310fe1e1591c95
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e00bb8f99b1dd8d3a520d6d77d51622c0a84ed374efd76777ab8511819175a1
+oid sha256:5b92751f4b20e75eaa14da19b90f1ab13480087054428a4c0d401036dfb6ac41
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f072cc679b4591b13343c2f99b073847ce7e3f6b186430a222f04d73655cf2d9
+oid sha256:ef287f4d129e16c1be2a6d9274834361a2314f3e93306e2f68a2038b7df959db
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:103d807a8aa9689d726be76a6c7b722b5b60393fd4668639765cffced2175eb7
+oid sha256:0d852e8f5f81e0cab6890f467096252da1139a278824fe37f3c8942c5eb9770e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c0aeb5969863fdbec01080313f102e53ee36b002fb9383bfa48ce9dc0cb119
+oid sha256:f1d73e7a0ecb30a99cbdfcf5294c035a1607fc9fe8fb9bf248e040f45b1c4ed0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f7493a121accf25f35377a404b720511fa423ee8ba2b2f8561afc5def4838e
+oid sha256:622caafed4311025a250cc617d5ea7d83f8800dd0509bfa4e0512afe18da2242
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e81119d658b18407dc132d7fdb38f3caf7aed57798ea11f920c85dc8964b35
+oid sha256:38b483de1bf1f4ff353f1ec4a8c9df2b2847b745cbf851617486bbe747b1c0c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9231343865394592,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.32070555221487274,
+  "best_metric": 0.880484402179718,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.4810583283223091,
   "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": 49.226,
       "eval_steps_per_second": 12.799,
       "step": 50
+    },
+    {
+      "epoch": 0.3271196632591702,
+      "grad_norm": 0.3813113868236542,
+      "learning_rate": 8.000066048588211e-05,
+      "loss": 0.942,
+      "step": 51
+    },
+    {
+      "epoch": 0.33353377430346764,
+      "grad_norm": 0.3614146411418915,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 0.8877,
+      "step": 52
+    },
+    {
+      "epoch": 0.3399478853477651,
+      "grad_norm": 0.3518458306789398,
+      "learning_rate": 7.834479661722347e-05,
+      "loss": 0.9331,
+      "step": 53
+    },
+    {
+      "epoch": 0.34636199639206255,
+      "grad_norm": 0.36760586500167847,
+      "learning_rate": 7.75e-05,
+      "loss": 0.8761,
+      "step": 54
+    },
+    {
+      "epoch": 0.35277610743636,
+      "grad_norm": 0.4043155908584595,
+      "learning_rate": 7.664449460137245e-05,
+      "loss": 0.8931,
+      "step": 55
+    },
+    {
+      "epoch": 0.35919021848065746,
+      "grad_norm": 0.397081196308136,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 0.8639,
+      "step": 56
+    },
+    {
+      "epoch": 0.3656043295249549,
+      "grad_norm": 0.3925102651119232,
+      "learning_rate": 7.490299105985507e-05,
+      "loss": 0.8433,
+      "step": 57
+    },
+    {
+      "epoch": 0.3720184405692524,
+      "grad_norm": 0.40960493683815,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 0.8634,
+      "step": 58
+    },
+    {
+      "epoch": 0.37843255161354983,
+      "grad_norm": 0.42561712861061096,
+      "learning_rate": 7.312360104364318e-05,
+      "loss": 0.7908,
+      "step": 59
+    },
+    {
+      "epoch": 0.3848466626578473,
+      "grad_norm": 0.4647367298603058,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 0.8468,
+      "step": 60
+    },
+    {
+      "epoch": 0.39126077370214474,
+      "grad_norm": 0.4602052867412567,
+      "learning_rate": 7.130971172276657e-05,
+      "loss": 0.8855,
+      "step": 61
+    },
+    {
+      "epoch": 0.3976748847464422,
+      "grad_norm": 0.5147804617881775,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 0.9345,
+      "step": 62
+    },
+    {
+      "epoch": 0.40408899579073965,
+      "grad_norm": 0.3348015248775482,
+      "learning_rate": 6.946477593864228e-05,
+      "loss": 1.0632,
+      "step": 63
+    },
+    {
+      "epoch": 0.4105031068350371,
+      "grad_norm": 0.3764553368091583,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 0.9961,
+      "step": 64
+    },
+    {
+      "epoch": 0.41691721787933456,
+      "grad_norm": 0.41312095522880554,
+      "learning_rate": 6.759230563139466e-05,
+      "loss": 0.964,
+      "step": 65
+    },
+    {
+      "epoch": 0.423331328923632,
+      "grad_norm": 0.4216284453868866,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 0.8904,
+      "step": 66
+    },
+    {
+      "epoch": 0.42974543996792947,
+      "grad_norm": 0.3816414773464203,
+      "learning_rate": 6.56958651546778e-05,
+      "loss": 0.868,
+      "step": 67
+    },
+    {
+      "epoch": 0.4361595510122269,
+      "grad_norm": 0.35876405239105225,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 0.8476,
+      "step": 68
+    },
+    {
+      "epoch": 0.4425736620565244,
+      "grad_norm": 0.3981570601463318,
+      "learning_rate": 6.377906449072578e-05,
+      "loss": 0.8487,
+      "step": 69
+    },
+    {
+      "epoch": 0.44898777310082183,
+      "grad_norm": 0.44419988989830017,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 0.8494,
+      "step": 70
+    },
+    {
+      "epoch": 0.4554018841451193,
+      "grad_norm": 0.41967856884002686,
+      "learning_rate": 6.184555237854625e-05,
+      "loss": 0.8249,
+      "step": 71
+    },
+    {
+      "epoch": 0.46181599518941674,
+      "grad_norm": 0.460245817899704,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.8508,
+      "step": 72
+    },
+    {
+      "epoch": 0.4682301062337142,
+      "grad_norm": 0.5052414536476135,
+      "learning_rate": 5.989900936833841e-05,
+      "loss": 0.849,
+      "step": 73
+    },
+    {
+      "epoch": 0.47464421727801165,
+      "grad_norm": 0.6499659419059753,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.881,
+      "step": 74
+    },
+    {
+      "epoch": 0.4810583283223091,
+      "grad_norm": 0.6127673983573914,
+      "learning_rate": 5.794314081535644e-05,
+      "loss": 0.9338,
+      "step": 75
+    },
+    {
+      "epoch": 0.4810583283223091,
+      "eval_loss": 0.880484402179718,
+      "eval_runtime": 1.0107,
+      "eval_samples_per_second": 49.469,
+      "eval_steps_per_second": 12.862,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.335466128054682e+16,
+  "total_flos": 1.2502548088461722e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null