Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9446bd8c5faeb76cd8dec0d8b5ce4ff04b379d0e8a9389193606f36cef04d250
+oid sha256:382c82dc1bbd311cb54678e17905670352857a4204e7ab448a34324dcb54205b
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733bd4f75355bee326788cdb90af278a83f16ee7cd962c7eaffba859c7bf7bad
+oid sha256:951c295c90371f2a40a2f88d2538ec432c216e9d772974a70cb1a1c7e8f8977c
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa008a4be23558a50880bc63e17f5669b469ca29e27c6cf3cefb7a528b449f48
+oid sha256:b4cba2ba703998e79c2705f01bf7987104acc0b3c406f646a3b67faf2e759794
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79475b4c75c2433139d5dbc56469509af1ea9e7cde892de33e8b508a0f145e3d
+oid sha256:8d4416e6288283858a2ebc6283f750b0c1ca185b868cb0c5d929eae92ab68da7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37a2d5076e93e3093698a2c0b91f162fbc60151a710332c748297496d2c886d
+oid sha256:8e37b331b254b1983a45f20be5a39ff7b95a254da1d9c6b93c99664a728b44c7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d39c93f1e283522d34142b2b6d519696f7eb4b96fbcaf580fdc4638967adf81
+oid sha256:18f3a7463ed43d9881f4e4aa019a1702b56cd68c50cdb967e8f2bbbe5e66c32b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.405816078186035,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.1245136186770428,
+  "best_metric": 6.368386268615723,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.1867704280155642,
   "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": 102.322,
       "eval_steps_per_second": 26.604,
       "step": 50
+    },
+    {
+      "epoch": 0.12700389105058366,
+      "grad_norm": 0.8649512529373169,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.7933,
+      "step": 51
+    },
+    {
+      "epoch": 0.1294941634241245,
+      "grad_norm": 0.8127966523170471,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 6.8069,
+      "step": 52
+    },
+    {
+      "epoch": 0.13198443579766536,
+      "grad_norm": 0.8927196264266968,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 6.707,
+      "step": 53
+    },
+    {
+      "epoch": 0.13447470817120621,
+      "grad_norm": 0.7540999054908752,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.8266,
+      "step": 54
+    },
+    {
+      "epoch": 0.1369649805447471,
+      "grad_norm": 0.7092488408088684,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 6.7882,
+      "step": 55
+    },
+    {
+      "epoch": 0.13945525291828795,
+      "grad_norm": 0.6673146486282349,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 6.7766,
+      "step": 56
+    },
+    {
+      "epoch": 0.1419455252918288,
+      "grad_norm": 0.7161771655082703,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.821,
+      "step": 57
+    },
+    {
+      "epoch": 0.14443579766536965,
+      "grad_norm": 0.8523626327514648,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 6.6849,
+      "step": 58
+    },
+    {
+      "epoch": 0.1469260700389105,
+      "grad_norm": 1.0966269969940186,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 6.6321,
+      "step": 59
+    },
+    {
+      "epoch": 0.14941634241245136,
+      "grad_norm": 1.2441387176513672,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.4888,
+      "step": 60
+    },
+    {
+      "epoch": 0.1519066147859922,
+      "grad_norm": 1.6971194744110107,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 6.4694,
+      "step": 61
+    },
+    {
+      "epoch": 0.15439688715953306,
+      "grad_norm": 2.2189457416534424,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 6.4204,
+      "step": 62
+    },
+    {
+      "epoch": 0.15688715953307392,
+      "grad_norm": 1.4777802228927612,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.7514,
+      "step": 63
+    },
+    {
+      "epoch": 0.1593774319066148,
+      "grad_norm": 1.0032076835632324,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 6.4532,
+      "step": 64
+    },
+    {
+      "epoch": 0.16186770428015565,
+      "grad_norm": 0.8604456186294556,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 6.7384,
+      "step": 65
+    },
+    {
+      "epoch": 0.1643579766536965,
+      "grad_norm": 0.8361185789108276,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.7395,
+      "step": 66
+    },
+    {
+      "epoch": 0.16684824902723736,
+      "grad_norm": 0.7592188119888306,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 6.7701,
+      "step": 67
+    },
+    {
+      "epoch": 0.1693385214007782,
+      "grad_norm": 0.6846341490745544,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 6.8228,
+      "step": 68
+    },
+    {
+      "epoch": 0.17182879377431906,
+      "grad_norm": 0.7539795637130737,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.8373,
+      "step": 69
+    },
+    {
+      "epoch": 0.1743190661478599,
+      "grad_norm": 0.7585219740867615,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 6.7546,
+      "step": 70
+    },
+    {
+      "epoch": 0.17680933852140077,
+      "grad_norm": 0.9256238341331482,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 6.6777,
+      "step": 71
+    },
+    {
+      "epoch": 0.17929961089494165,
+      "grad_norm": 1.067570686340332,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.5155,
+      "step": 72
+    },
+    {
+      "epoch": 0.1817898832684825,
+      "grad_norm": 1.4094899892807007,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 6.5212,
+      "step": 73
+    },
+    {
+      "epoch": 0.18428015564202335,
+      "grad_norm": 1.8948956727981567,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 6.3666,
+      "step": 74
+    },
+    {
+      "epoch": 0.1867704280155642,
+      "grad_norm": 2.406057834625244,
+      "learning_rate": 1e-05,
+      "loss": 6.5367,
+      "step": 75
+    },
+    {
+      "epoch": 0.1867704280155642,
+      "eval_loss": 6.368386268615723,
+      "eval_runtime": 0.4803,
+      "eval_samples_per_second": 104.107,
+      "eval_steps_per_second": 27.068,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 232050050203648.0,
+  "total_flos": 348056949096448.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null