Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a7fffbed11c51c59ca4967e56b55eaf413fb7d85cf3a28331e4a75ff1da7b31
+oid sha256:610ad30acd3e13e218807530d87da618ac6f2750803bf4996a4427420ab91dbf
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a266140111a909acc4cfd80fbf9d71387a9c649d00193dc9a422888ecf518b0d
+oid sha256:ee11ee1e4b046232426342fd86ec0454e48b501e10564fb2867e1cbeb018a9cb
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b2f7e6709b15af8e3316e4948e321f649f623cc242bc72a0ec459ca5d049b2
+oid sha256:ae23d6e3344e80eee1e5f521240d9b543991605b2b3565b0eeba196ec69bfa5a
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff186fe49135608f882516fa7f8019c2e56d31e37e18b7d453edd9a69c0a6662
+oid sha256:265c8ec1457a62a40c68e764e0df615e596963851f08632cbaaf686ba16c5493
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a0a738fb8544babdf1befdd4807153090c938974ef331d44f9837165bb0bff
+oid sha256:c06e1d9799786621014b9723a6b78d1e9771c19da2ceb92cd700a9fbe13ff0ac
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3710648fe4ad7d0348d3024ad72e59c8c5ef4d43f569046aacc84376325b30af
+oid sha256:37ef074e1185e1b49908fda8b5a3840c9f7b965beb14a03449023f6d37621a97
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.22251036763191223,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10706638115631692,
+  "best_metric": 0.14586713910102844,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.21413276231263384,
   "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": 7.897,
       "eval_steps_per_second": 0.989,
       "step": 25
+    },
+    {
+      "epoch": 0.11134903640256959,
+      "grad_norm": 19.137922286987305,
+      "learning_rate": 5e-05,
+      "loss": 3.0908,
+      "step": 26
+    },
+    {
+      "epoch": 0.11563169164882227,
+      "grad_norm": 13.688855171203613,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.3774,
+      "step": 27
+    },
+    {
+      "epoch": 0.11991434689507495,
+      "grad_norm": 6.846719264984131,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.7852,
+      "step": 28
+    },
+    {
+      "epoch": 0.12419700214132762,
+      "grad_norm": 6.931698799133301,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.1304,
+      "step": 29
+    },
+    {
+      "epoch": 0.1284796573875803,
+      "grad_norm": 8.356529235839844,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.1389,
+      "step": 30
+    },
+    {
+      "epoch": 0.13276231263383298,
+      "grad_norm": 13.247598648071289,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.6286,
+      "step": 31
+    },
+    {
+      "epoch": 0.13704496788008566,
+      "grad_norm": 57.86114501953125,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.0856,
+      "step": 32
+    },
+    {
+      "epoch": 0.14132762312633834,
+      "grad_norm": 7.757084846496582,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.2319,
+      "step": 33
+    },
+    {
+      "epoch": 0.145610278372591,
+      "grad_norm": 6.383694171905518,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4734,
+      "step": 34
+    },
+    {
+      "epoch": 0.14989293361884368,
+      "grad_norm": 7.215427875518799,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.2606,
+      "step": 35
+    },
+    {
+      "epoch": 0.15417558886509636,
+      "grad_norm": 9.813756942749023,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.9801,
+      "step": 36
+    },
+    {
+      "epoch": 0.15845824411134904,
+      "grad_norm": 7.98891544342041,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.4118,
+      "step": 37
+    },
+    {
+      "epoch": 0.16274089935760172,
+      "grad_norm": 8.596599578857422,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3784,
+      "step": 38
+    },
+    {
+      "epoch": 0.1670235546038544,
+      "grad_norm": 3.399794578552246,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.9948,
+      "step": 39
+    },
+    {
+      "epoch": 0.17130620985010706,
+      "grad_norm": 3.525446891784668,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3627,
+      "step": 40
+    },
+    {
+      "epoch": 0.17558886509635974,
+      "grad_norm": 4.740527153015137,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.5379,
+      "step": 41
+    },
+    {
+      "epoch": 0.17987152034261242,
+      "grad_norm": 5.45485258102417,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.402,
+      "step": 42
+    },
+    {
+      "epoch": 0.1841541755888651,
+      "grad_norm": 7.981726169586182,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.2083,
+      "step": 43
+    },
+    {
+      "epoch": 0.18843683083511778,
+      "grad_norm": 16.032129287719727,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.695,
+      "step": 44
+    },
+    {
+      "epoch": 0.19271948608137046,
+      "grad_norm": 14.371125221252441,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.4968,
+      "step": 45
+    },
+    {
+      "epoch": 0.19700214132762311,
+      "grad_norm": 5.07935094833374,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9599,
+      "step": 46
+    },
+    {
+      "epoch": 0.2012847965738758,
+      "grad_norm": 6.442592144012451,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.7358,
+      "step": 47
+    },
+    {
+      "epoch": 0.20556745182012848,
+      "grad_norm": 7.287022590637207,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.9093,
+      "step": 48
+    },
+    {
+      "epoch": 0.20985010706638116,
+      "grad_norm": 9.049643516540527,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.0813,
+      "step": 49
+    },
+    {
+      "epoch": 0.21413276231263384,
+      "grad_norm": 16.802932739257812,
+      "learning_rate": 0.0,
+      "loss": 2.601,
+      "step": 50
+    },
+    {
+      "epoch": 0.21413276231263384,
+      "eval_loss": 0.14586713910102844,
+      "eval_runtime": 199.3411,
+      "eval_samples_per_second": 7.891,
+      "eval_steps_per_second": 0.988,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.138258080548782e+17,
+  "total_flos": 8.227212051810877e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null