Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8c947c49d4902123042f0f415accd554d88286e4871e8c9366b4a34561d8d7
+oid sha256:20d5a055424440ae6c7e5a8b1fb2f6a8907847b0f53bea01aaf73c945d4face9
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0996ccc63abde854ee0dc183fe91f1409cb68edda2a8186c2382bc175196d5cc
+oid sha256:578e4b064638a221186b84c7564dac76a75f260d0d6374847dfd79321808d26f
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0ce1a85378e0d50d06b0cd8040b928bd85ace147bd64f649d7101fbae762a4
+oid sha256:dbbaca1568c7babaf2acd51525de14781ffadfd0063cd816ea46864cea08d9d4
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f09ddbc6e0da830a60621ff658ac405ff583e528d7b3394cc031508da933b6
+oid sha256:e803dfd20381169d6b3a72ff055a5ecb4457019b79e76cad577699a8aa5cb379
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d632f71da5d1bfe3c6a940c00322d709514e7df7fa1b246caa89be7d73199457
+oid sha256:8f5b945344047a8455b0b1d155cd708cfc8b4938238c30ed10695f23b2ce01c6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f60f64d34863817e9b484a7cb797530084f25e09e7e5f4bd46cccc8626e799
+oid sha256:e609012f169b1ed54cd28582fa61f4b4a275b1a2de9dfbd2932f46ced70db2c4
 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": 0.7932476997375488,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.3382663847780127,
+  "best_metric": 0.7787196636199951,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.507399577167019,
   "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": 9.282,
       "eval_steps_per_second": 2.413,
       "step": 50
+    },
+    {
+      "epoch": 0.34503171247357295,
+      "grad_norm": 0.1904909908771515,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.87,
+      "step": 51
+    },
+    {
+      "epoch": 0.3517970401691332,
+      "grad_norm": 0.19124388694763184,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 0.8478,
+      "step": 52
+    },
+    {
+      "epoch": 0.3585623678646934,
+      "grad_norm": 0.19980108737945557,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.8312,
+      "step": 53
+    },
+    {
+      "epoch": 0.3653276955602537,
+      "grad_norm": 0.20743730664253235,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8215,
+      "step": 54
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.19515347480773926,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.8059,
+      "step": 55
+    },
+    {
+      "epoch": 0.3788583509513742,
+      "grad_norm": 0.20205727219581604,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 0.8044,
+      "step": 56
+    },
+    {
+      "epoch": 0.3856236786469345,
+      "grad_norm": 0.21145658195018768,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8261,
+      "step": 57
+    },
+    {
+      "epoch": 0.39238900634249474,
+      "grad_norm": 0.22306717932224274,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 0.7848,
+      "step": 58
+    },
+    {
+      "epoch": 0.39915433403805495,
+      "grad_norm": 0.21222449839115143,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.7658,
+      "step": 59
+    },
+    {
+      "epoch": 0.4059196617336152,
+      "grad_norm": 0.2429528832435608,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7836,
+      "step": 60
+    },
+    {
+      "epoch": 0.4126849894291755,
+      "grad_norm": 0.251037061214447,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.8243,
+      "step": 61
+    },
+    {
+      "epoch": 0.41945031712473574,
+      "grad_norm": 0.27348846197128296,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.7773,
+      "step": 62
+    },
+    {
+      "epoch": 0.426215644820296,
+      "grad_norm": 0.21012000739574432,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8551,
+      "step": 63
+    },
+    {
+      "epoch": 0.4329809725158562,
+      "grad_norm": 0.19766287505626678,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 0.8454,
+      "step": 64
+    },
+    {
+      "epoch": 0.4397463002114165,
+      "grad_norm": 0.21795031428337097,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.8137,
+      "step": 65
+    },
+    {
+      "epoch": 0.44651162790697674,
+      "grad_norm": 0.18766184151172638,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.8081,
+      "step": 66
+    },
+    {
+      "epoch": 0.453276955602537,
+      "grad_norm": 0.20499680936336517,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.812,
+      "step": 67
+    },
+    {
+      "epoch": 0.46004228329809727,
+      "grad_norm": 0.2015526294708252,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 0.8016,
+      "step": 68
+    },
+    {
+      "epoch": 0.46680761099365753,
+      "grad_norm": 0.2130436897277832,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.773,
+      "step": 69
+    },
+    {
+      "epoch": 0.47357293868921774,
+      "grad_norm": 0.20126216113567352,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 0.7987,
+      "step": 70
+    },
+    {
+      "epoch": 0.480338266384778,
+      "grad_norm": 0.2301049381494522,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.7992,
+      "step": 71
+    },
+    {
+      "epoch": 0.48710359408033826,
+      "grad_norm": 0.22262722253799438,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8025,
+      "step": 72
+    },
+    {
+      "epoch": 0.49386892177589853,
+      "grad_norm": 0.2374563217163086,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.7907,
+      "step": 73
+    },
+    {
+      "epoch": 0.5006342494714587,
+      "grad_norm": 0.27033481001853943,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.7869,
+      "step": 74
+    },
+    {
+      "epoch": 0.507399577167019,
+      "grad_norm": 0.39757001399993896,
+      "learning_rate": 1e-05,
+      "loss": 0.8538,
+      "step": 75
+    },
+    {
+      "epoch": 0.507399577167019,
+      "eval_loss": 0.7787196636199951,
+      "eval_runtime": 5.3775,
+      "eval_samples_per_second": 9.298,
+      "eval_steps_per_second": 2.417,
+      "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": 2.654149397184512e+17,
+  "total_flos": 3.981224095776768e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null