Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5630e083fbc0ff4413abd1515abdd2577d267a0ee4f92e1e16c0ec38ad3a356a
+oid sha256:25a0f27a7e939b8543cd7b4dc96742b9236ef5298fce500072ea1cac7fbcf493
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380673d5b1543936c768b4a902402b2d9cdf594812055d0617bc542fb5f03d2f
+oid sha256:0d28eb87d638daa4377adeac6bad7b3e31c80d4117e9786331105bfd12bb11b2
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888cfa6be73e4b753c797ec50ddbe045c02fe1db04af2c33f52f7522db5da72a
+oid sha256:2be8837dc6f3912dfa18af808ba1e7ff240983347458834b365c04dd5b500cdd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6c8bf99331194b84f2422cb9def86bc3c8183a5569bc905b2bff9414393588c
+oid sha256:545040198f28fd842769e6d6b34834304dfe17089e89e38bf663ed9641febce5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63251887cf2dbfc2c7f5933b0aa92cff6699246fa3790f5a814481a375b0f344
+oid sha256:d41b58184c3adf77913ffc0d293bb23be91b8492030e316ca77b206446cedec5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792b960e8d34e7d8ef115e6f1ed5aea2ed0466d61549de1acab4625a54204ba0
+oid sha256:57c7041b80543d314236ec4c9ce3ffd826fe6cc8006262f0a308932bece91543
 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": 11.9251070022583,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.07140307033202428,
+  "best_metric": 11.923971176147461,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.10710460549803641,
   "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": 422.373,
       "eval_steps_per_second": 109.817,
       "step": 50
+    },
+    {
+      "epoch": 0.07283113173866476,
+      "grad_norm": 0.028324365615844727,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.931,
+      "step": 51
+    },
+    {
+      "epoch": 0.07425919314530526,
+      "grad_norm": 0.024705391377210617,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 11.9304,
+      "step": 52
+    },
+    {
+      "epoch": 0.07568725455194573,
+      "grad_norm": 0.028772857040166855,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 11.9285,
+      "step": 53
+    },
+    {
+      "epoch": 0.07711531595858621,
+      "grad_norm": 0.038632966578006744,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9299,
+      "step": 54
+    },
+    {
+      "epoch": 0.07854337736522671,
+      "grad_norm": 0.03747715428471565,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 11.9281,
+      "step": 55
+    },
+    {
+      "epoch": 0.07997143877186719,
+      "grad_norm": 0.03954080492258072,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 11.9261,
+      "step": 56
+    },
+    {
+      "epoch": 0.08139950017850768,
+      "grad_norm": 0.04532692953944206,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9288,
+      "step": 57
+    },
+    {
+      "epoch": 0.08282756158514816,
+      "grad_norm": 0.04139029607176781,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 11.9292,
+      "step": 58
+    },
+    {
+      "epoch": 0.08425562299178865,
+      "grad_norm": 0.06036078557372093,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 11.9261,
+      "step": 59
+    },
+    {
+      "epoch": 0.08568368439842913,
+      "grad_norm": 0.05277972295880318,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9258,
+      "step": 60
+    },
+    {
+      "epoch": 0.08711174580506961,
+      "grad_norm": 0.05443393439054489,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 11.9258,
+      "step": 61
+    },
+    {
+      "epoch": 0.0885398072117101,
+      "grad_norm": 0.0641714483499527,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 11.9267,
+      "step": 62
+    },
+    {
+      "epoch": 0.08996786861835059,
+      "grad_norm": 0.02531246840953827,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.931,
+      "step": 63
+    },
+    {
+      "epoch": 0.09139593002499108,
+      "grad_norm": 0.032845158129930496,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 11.9303,
+      "step": 64
+    },
+    {
+      "epoch": 0.09282399143163156,
+      "grad_norm": 0.04369133338332176,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 11.9295,
+      "step": 65
+    },
+    {
+      "epoch": 0.09425205283827205,
+      "grad_norm": 0.03401423245668411,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9292,
+      "step": 66
+    },
+    {
+      "epoch": 0.09568011424491253,
+      "grad_norm": 0.04532518982887268,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 11.9285,
+      "step": 67
+    },
+    {
+      "epoch": 0.09710817565155301,
+      "grad_norm": 0.04133721813559532,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 11.9279,
+      "step": 68
+    },
+    {
+      "epoch": 0.0985362370581935,
+      "grad_norm": 0.041920006275177,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9275,
+      "step": 69
+    },
+    {
+      "epoch": 0.09996429846483398,
+      "grad_norm": 0.044887904077768326,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 11.9283,
+      "step": 70
+    },
+    {
+      "epoch": 0.10139235987147448,
+      "grad_norm": 0.04782561585307121,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 11.9258,
+      "step": 71
+    },
+    {
+      "epoch": 0.10282042127811496,
+      "grad_norm": 0.04621487855911255,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9258,
+      "step": 72
+    },
+    {
+      "epoch": 0.10424848268475545,
+      "grad_norm": 0.06691943854093552,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 11.9262,
+      "step": 73
+    },
+    {
+      "epoch": 0.10567654409139593,
+      "grad_norm": 0.06318347901105881,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 11.9244,
+      "step": 74
+    },
+    {
+      "epoch": 0.10710460549803641,
+      "grad_norm": 0.08262067288160324,
+      "learning_rate": 1e-05,
+      "loss": 11.925,
+      "step": 75
+    },
+    {
+      "epoch": 0.10710460549803641,
+      "eval_loss": 11.923971176147461,
+      "eval_runtime": 0.1168,
+      "eval_samples_per_second": 428.033,
+      "eval_steps_per_second": 111.289,
+      "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": 1042494259200.0,
+  "total_flos": 1563741388800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null