Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd88304d2a13c205e60c03cf59634fd7c160e88cb9c5db1f940462640a7e59a
+oid sha256:60637391729df9e656b156a241dec7c1e925bbe14b079ec990ae769c77461a01
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575f5f247dcb7698ba12c3e86ff441bf69fa753f2ca8969c82779c27d5b31461
+oid sha256:23bfc74d86c2bbd6fc7e41e1a3182ab7b4a9a29e66c4794d0be48e2f065cd811
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f490ce0e05cb1ce4d372f0f73d384cb3c5e161d4cf27dfcb68db46977a7c7444
+oid sha256:ba40e84e991758419f82ccf5f7a8e9bbb6a30417ff7897a5638663d5a7264007
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf520a628e41e61266bf94e40b1e2d6b014291f6ee1392360bc12ca17689783f
+oid sha256:5aa365110780f12edfe54751fa123785ae60819def704e87e3c35ec31663f554
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57adae6defcd61ecf6e7ccc8b83ab430f9f27dcca4e6d866af8c17ecbd77812d
+oid sha256:2f23a7eb8010a262826dd3f54f5e41025aae2374c9a7273de5fb4db8b8948d20
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab32244f72d2e219a79d8144a921a4f9e4f9d7acdd093d06091f58961b985b16
+oid sha256:75bec37b27a29ce04cc68bbfd89a8339927f93b8cf9c91c52bcd30fb9e9e5fe0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8483147621154785,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3109211037699184,
+  "best_metric": 1.5857478380203247,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6218422075398368,
   "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": 11.171,
       "eval_steps_per_second": 2.905,
       "step": 25
+    },
+    {
+      "epoch": 0.3233579479207151,
+      "grad_norm": 3.4082753658294678,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 2.41,
+      "step": 26
+    },
+    {
+      "epoch": 0.33579479207151186,
+      "grad_norm": 3.109001874923706,
+      "learning_rate": 7.75e-05,
+      "loss": 2.3198,
+      "step": 27
+    },
+    {
+      "epoch": 0.34823163622230857,
+      "grad_norm": 2.304497718811035,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 2.0177,
+      "step": 28
+    },
+    {
+      "epoch": 0.36066848037310534,
+      "grad_norm": 1.9224731922149658,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 2.0373,
+      "step": 29
+    },
+    {
+      "epoch": 0.37310532452390205,
+      "grad_norm": 1.6497129201889038,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 1.807,
+      "step": 30
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 1.6339839696884155,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 1.8076,
+      "step": 31
+    },
+    {
+      "epoch": 0.3979790128254955,
+      "grad_norm": 1.8460805416107178,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 1.907,
+      "step": 32
+    },
+    {
+      "epoch": 0.4104158569762923,
+      "grad_norm": 1.7650914192199707,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 1.8927,
+      "step": 33
+    },
+    {
+      "epoch": 0.422852701127089,
+      "grad_norm": 1.8454054594039917,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 1.5441,
+      "step": 34
+    },
+    {
+      "epoch": 0.4352895452778857,
+      "grad_norm": 1.8942859172821045,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 1.5689,
+      "step": 35
+    },
+    {
+      "epoch": 0.4477263894286825,
+      "grad_norm": 2.334362268447876,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 1.2838,
+      "step": 36
+    },
+    {
+      "epoch": 0.4601632335794792,
+      "grad_norm": 2.4197657108306885,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 0.9639,
+      "step": 37
+    },
+    {
+      "epoch": 0.47260007773027596,
+      "grad_norm": 1.9846646785736084,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 1.8122,
+      "step": 38
+    },
+    {
+      "epoch": 0.48503692188107267,
+      "grad_norm": 1.9487015008926392,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.0742,
+      "step": 39
+    },
+    {
+      "epoch": 0.49747376603186944,
+      "grad_norm": 2.0693061351776123,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 1.9641,
+      "step": 40
+    },
+    {
+      "epoch": 0.5099106101826661,
+      "grad_norm": 1.666406273841858,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 1.7359,
+      "step": 41
+    },
+    {
+      "epoch": 0.5223474543334629,
+      "grad_norm": 1.9289875030517578,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.887,
+      "step": 42
+    },
+    {
+      "epoch": 0.5347842984842596,
+      "grad_norm": 1.6595007181167603,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 1.7954,
+      "step": 43
+    },
+    {
+      "epoch": 0.5472211426350564,
+      "grad_norm": 1.7720122337341309,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 1.7259,
+      "step": 44
+    },
+    {
+      "epoch": 0.5596579867858531,
+      "grad_norm": 1.9382787942886353,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.7288,
+      "step": 45
+    },
+    {
+      "epoch": 0.5720948309366498,
+      "grad_norm": 1.5037600994110107,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 1.5281,
+      "step": 46
+    },
+    {
+      "epoch": 0.5845316750874465,
+      "grad_norm": 1.6816551685333252,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 1.5025,
+      "step": 47
+    },
+    {
+      "epoch": 0.5969685192382433,
+      "grad_norm": 1.8008204698562622,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3675,
+      "step": 48
+    },
+    {
+      "epoch": 0.6094053633890401,
+      "grad_norm": 1.7607805728912354,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.9439,
+      "step": 49
+    },
+    {
+      "epoch": 0.6218422075398368,
+      "grad_norm": 8.726191520690918,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.7328,
+      "step": 50
+    },
+    {
+      "epoch": 0.6218422075398368,
+      "eval_loss": 1.5857478380203247,
+      "eval_runtime": 4.4715,
+      "eval_samples_per_second": 11.182,
+      "eval_steps_per_second": 2.907,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null