Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01411e698d9319ad8f4eb5f0833deaeef9cb011b9e73b5a137b2191652b55e6c
+oid sha256:a317b184ec9c59e5718de6e47e179a25f2df3c4ea696be2cd2889c34ab953e7b
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ed698dcfa8a612fb25c8e8cb83c595b3194ca1b0c3dd4e7a1592b8ff3e9f22
+oid sha256:35b9a66196538b96741ad3c533152ac689a4f2fb0d36c8d16acbc1c6d3e79935
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e71b85501124bda69e5fcbe95cdefff64271b626060f51f48dec18cc8003812f
+oid sha256:58025aec3c37f3f418266819e41ca997b6525c066ead1dda10e63fee963f3e06
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.38192471861839294,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2222222222222222,
+  "best_metric": 0.3696126937866211,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4444444444444444,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 13.879,
       "eval_steps_per_second": 6.94,
       "step": 25
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 2.0117669105529785,
+      "learning_rate": 0.0001,
+      "loss": 0.3888,
+      "step": 26
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 6.946228504180908,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.5364,
+      "step": 27
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 2.2014853954315186,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.3977,
+      "step": 28
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 4.625939846038818,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.366,
+      "step": 29
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 2.8562731742858887,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.4198,
+      "step": 30
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 0.6394229531288147,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.3234,
+      "step": 31
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 2.782531976699829,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.2482,
+      "step": 32
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 5.685042858123779,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.5143,
+      "step": 33
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 2.0438950061798096,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.3339,
+      "step": 34
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 3.337780237197876,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.4482,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.1531790494918823,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.3529,
+      "step": 36
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 1.931061863899231,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.3628,
+      "step": 37
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 1.7695353031158447,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.3906,
+      "step": 38
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 2.8632524013519287,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.3458,
+      "step": 39
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 2.9647114276885986,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.334,
+      "step": 40
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 0.7860206961631775,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.345,
+      "step": 41
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.9671415686607361,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.3785,
+      "step": 42
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 2.243291139602661,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.3267,
+      "step": 43
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.4092743396759033,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.3687,
+      "step": 44
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.9342949390411377,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.3915,
+      "step": 45
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.2684597969055176,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.3857,
+      "step": 46
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 0.8089708089828491,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.3436,
+      "step": 47
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.3409976959228516,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.3426,
+      "step": 48
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 2.8692626953125,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.3069,
+      "step": 49
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.4735819101333618,
+      "learning_rate": 0.0,
+      "loss": 0.368,
+      "step": 50
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_loss": 0.3696126937866211,
+      "eval_runtime": 3.4698,
+      "eval_samples_per_second": 13.834,
+      "eval_steps_per_second": 6.917,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5146843860172800.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null