Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1c094e2b04c46c936a656de7835e85dbcf14183993b0c8bbe0411df903641f
+oid sha256:efa6f5732f77aa9a784bb8a2ebf5af9841117b3c882e5d63f0fb5be0cd41e1fd
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1a989b37f527b2146802ecf1b0048cb62f261e022e387637a7fbfd210017c65
+oid sha256:400803adf9b6f429f27ba401532c4cf16af1fad64a3c4c50915fbe4fec173d22
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e600d3f88008e73276d99a5b1120d15a4881ba5b50d66a82ac22c9b9e451d1
+oid sha256:bbf266077134fb6ebbf59c69cd2a324ae0d4cae220b2ae6a2823dde2071ecaaa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a5239f249d81d8bfa06ef3de4b500e1ac939798a7dbf67fabb6fdf26f4f0286
+oid sha256:211a284abdb0ef5f9062030192f0ac27c5f458db1d7f81a779a3eb1e56e09f8b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3fb3c75839ecf6ed308f90b9c2940bd609f26e633ef816e3b4989d2302e7d3
+oid sha256:a1675726a1ea11b2b4b1a465ed666a496f813012021b43f983b32c7c4bb3a300
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd14640f5eeb90ec4e386c79cd20d4ed3e7b6616d7a4070b600d64580c4eace
+oid sha256:600f5b8abb911ad132dc63d0b5f3a3e3882435efbf5bcfd7e57eedc7c9a76231
 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": 1.1305104494094849,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.2575245453082247,
+  "best_metric": 1.1020288467407227,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.38628681796233705,
   "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": 12.366,
       "eval_steps_per_second": 3.215,
       "step": 50
+    },
+    {
+      "epoch": 0.2626750362143892,
+      "grad_norm": 0.6626567244529724,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.4105,
+      "step": 51
+    },
+    {
+      "epoch": 0.2678255271205537,
+      "grad_norm": 0.6616899371147156,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 1.2103,
+      "step": 52
+    },
+    {
+      "epoch": 0.27297601802671817,
+      "grad_norm": 0.6504210233688354,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 1.1649,
+      "step": 53
+    },
+    {
+      "epoch": 0.27812650893288265,
+      "grad_norm": 0.6488938331604004,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2075,
+      "step": 54
+    },
+    {
+      "epoch": 0.28327699983904714,
+      "grad_norm": 0.6831638813018799,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 1.238,
+      "step": 55
+    },
+    {
+      "epoch": 0.2884274907452117,
+      "grad_norm": 0.7102789878845215,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 1.1096,
+      "step": 56
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.697617769241333,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.0315,
+      "step": 57
+    },
+    {
+      "epoch": 0.29872847255754065,
+      "grad_norm": 0.789955735206604,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 1.0317,
+      "step": 58
+    },
+    {
+      "epoch": 0.30387896346370513,
+      "grad_norm": 0.8065967559814453,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 1.0469,
+      "step": 59
+    },
+    {
+      "epoch": 0.3090294543698696,
+      "grad_norm": 0.7964063286781311,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9775,
+      "step": 60
+    },
+    {
+      "epoch": 0.3141799452760341,
+      "grad_norm": 0.8694634437561035,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.8733,
+      "step": 61
+    },
+    {
+      "epoch": 0.31933043618219864,
+      "grad_norm": 0.9869593381881714,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.9035,
+      "step": 62
+    },
+    {
+      "epoch": 0.3244809270883631,
+      "grad_norm": 0.5871992707252502,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3583,
+      "step": 63
+    },
+    {
+      "epoch": 0.3296314179945276,
+      "grad_norm": 0.5578927397727966,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 1.3325,
+      "step": 64
+    },
+    {
+      "epoch": 0.3347819089006921,
+      "grad_norm": 0.587887704372406,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 1.3098,
+      "step": 65
+    },
+    {
+      "epoch": 0.3399323998068566,
+      "grad_norm": 0.6099755764007568,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2052,
+      "step": 66
+    },
+    {
+      "epoch": 0.34508289071302106,
+      "grad_norm": 0.6458743810653687,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 1.2037,
+      "step": 67
+    },
+    {
+      "epoch": 0.3502333816191856,
+      "grad_norm": 0.6708971261978149,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 1.1093,
+      "step": 68
+    },
+    {
+      "epoch": 0.3553838725253501,
+      "grad_norm": 0.6868105530738831,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.1062,
+      "step": 69
+    },
+    {
+      "epoch": 0.36053436343151457,
+      "grad_norm": 0.7059977650642395,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 1.1001,
+      "step": 70
+    },
+    {
+      "epoch": 0.36568485433767906,
+      "grad_norm": 0.7179769277572632,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.9938,
+      "step": 71
+    },
+    {
+      "epoch": 0.37083534524384354,
+      "grad_norm": 0.7872999310493469,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0442,
+      "step": 72
+    },
+    {
+      "epoch": 0.375985836150008,
+      "grad_norm": 0.914609968662262,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.8831,
+      "step": 73
+    },
+    {
+      "epoch": 0.38113632705617256,
+      "grad_norm": 0.9258915185928345,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.8793,
+      "step": 74
+    },
+    {
+      "epoch": 0.38628681796233705,
+      "grad_norm": 1.1383943557739258,
+      "learning_rate": 1e-05,
+      "loss": 0.841,
+      "step": 75
+    },
+    {
+      "epoch": 0.38628681796233705,
+      "eval_loss": 1.1020288467407227,
+      "eval_runtime": 4.0849,
+      "eval_samples_per_second": 12.24,
+      "eval_steps_per_second": 3.182,
+      "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": 6.174479344467968e+17,
+  "total_flos": 9.261719016701952e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null