Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58460501797c790fa42a6dac359f3a82eec702922ddb2ae8758f766ec563f568
+oid sha256:46e50dc816448479dad5be80bf5066779446b987bd210b529d9a5b963d8b2789
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad1dfe453f6e2a27967e6bcab08462355d39ffd65f9b88468e9cfa0d23c50d29
+oid sha256:dd89190335d6a27b469d5ed907313afb7473297bd04448f97ab46365f41f78d7
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef0bc15308c4e2d7a9d7eb21b7efe66e17ef733cf9c40a47c74490075c4bb179
+oid sha256:a3b004ac384056ba4dbff7f1e6d1d83ec5784badfe5c77abdc6f7df970b12959
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c739a670c495e55cc1154b2d031dd316ccbe5fa2f51e0baae75301344f234379
+oid sha256:21a2eca0d8a94c2dbd77b9da7f6563ac46a4944245d67561c49223c9ba4541f5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc92baf2f6ec86e86cb9b50b13ac850fc5784032dc47cbc6eefb2a0d6b3716e
+oid sha256:62e95f5fbfe890b39fb74027c82cd679cd04d66cf4a31206056ac946ec176cf2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601b22613d2d8a193cfc8f0c3d57f2454c986fca2033fb8e04c5fec07b7e9fec
+oid sha256:4cf34d016cca5bbcd5237c0b6d8b02d6b8f5588ddd96a232c86942a7b5d8d6e1
 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": 11.761113166809082,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.03203972926428772,
+  "best_metric": 11.760108947753906,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.04805959389643157,
   "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": 213.264,
       "eval_steps_per_second": 55.449,
       "step": 50
+    },
+    {
+      "epoch": 0.03268052384957347,
+      "grad_norm": 0.03685550019145012,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.7635,
+      "step": 51
+    },
+    {
+      "epoch": 0.03332131843485923,
+      "grad_norm": 0.04207245260477066,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 11.7628,
+      "step": 52
+    },
+    {
+      "epoch": 0.03396211302014498,
+      "grad_norm": 0.047665830701589584,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 11.7617,
+      "step": 53
+    },
+    {
+      "epoch": 0.034602907605430736,
+      "grad_norm": 0.050436247140169144,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7613,
+      "step": 54
+    },
+    {
+      "epoch": 0.035243702190716486,
+      "grad_norm": 0.04612034186720848,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 11.7613,
+      "step": 55
+    },
+    {
+      "epoch": 0.03588449677600224,
+      "grad_norm": 0.04736921191215515,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 11.7612,
+      "step": 56
+    },
+    {
+      "epoch": 0.036525291361287994,
+      "grad_norm": 0.05022180452942848,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.7604,
+      "step": 57
+    },
+    {
+      "epoch": 0.03716608594657375,
+      "grad_norm": 0.04974595829844475,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 11.76,
+      "step": 58
+    },
+    {
+      "epoch": 0.03780688053185951,
+      "grad_norm": 0.047848932445049286,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 11.7615,
+      "step": 59
+    },
+    {
+      "epoch": 0.03844767511714526,
+      "grad_norm": 0.04960588365793228,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7612,
+      "step": 60
+    },
+    {
+      "epoch": 0.03908846970243102,
+      "grad_norm": 0.05584871768951416,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 11.7601,
+      "step": 61
+    },
+    {
+      "epoch": 0.03972926428771677,
+      "grad_norm": 0.04442853853106499,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 11.7609,
+      "step": 62
+    },
+    {
+      "epoch": 0.040370058873002525,
+      "grad_norm": 0.04721665382385254,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7637,
+      "step": 63
+    },
+    {
+      "epoch": 0.041010853458288275,
+      "grad_norm": 0.04801863431930542,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 11.7612,
+      "step": 64
+    },
+    {
+      "epoch": 0.04165164804357403,
+      "grad_norm": 0.04716704413294792,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 11.7627,
+      "step": 65
+    },
+    {
+      "epoch": 0.04229244262885978,
+      "grad_norm": 0.05011888965964317,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.761,
+      "step": 66
+    },
+    {
+      "epoch": 0.04293323721414554,
+      "grad_norm": 0.04726472124457359,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 11.7608,
+      "step": 67
+    },
+    {
+      "epoch": 0.0435740317994313,
+      "grad_norm": 0.053742505609989166,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 11.76,
+      "step": 68
+    },
+    {
+      "epoch": 0.04421482638471705,
+      "grad_norm": 0.05879789963364601,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.7597,
+      "step": 69
+    },
+    {
+      "epoch": 0.044855620970002806,
+      "grad_norm": 0.05244609713554382,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 11.7611,
+      "step": 70
+    },
+    {
+      "epoch": 0.04549641555528856,
+      "grad_norm": 0.05740131437778473,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 11.7612,
+      "step": 71
+    },
+    {
+      "epoch": 0.046137210140574314,
+      "grad_norm": 0.04920673370361328,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7614,
+      "step": 72
+    },
+    {
+      "epoch": 0.046778004725860065,
+      "grad_norm": 0.05816422030329704,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 11.7607,
+      "step": 73
+    },
+    {
+      "epoch": 0.04741879931114582,
+      "grad_norm": 0.05213126912713051,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 11.7598,
+      "step": 74
+    },
+    {
+      "epoch": 0.04805959389643157,
+      "grad_norm": 0.061734773218631744,
+      "learning_rate": 1e-05,
+      "loss": 11.7597,
+      "step": 75
+    },
+    {
+      "epoch": 0.04805959389643157,
+      "eval_loss": 11.760108947753906,
+      "eval_runtime": 0.2399,
+      "eval_samples_per_second": 208.462,
+      "eval_steps_per_second": 54.2,
+      "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": 164654353481728.0,
+  "total_flos": 246955923210240.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null