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:e8de870f14b9b55121002d3a5fa26711a08b387eac635abae02d0f7fa35f1d7c
+oid sha256:f50c439f0f7f88a4a692a8c927131c42b266be427c25aa1531f4e117487c8252
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0cf48d4625d65f0ce43607e14a238e3f3e2c365aae80c3c10f8315aef64b37b
+oid sha256:50a9a6cf88a0bbda095da15ad5402fe8d96b214ca4d878b60dc344cded6ca6a4
 size 1279641042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:258a74b0d1a7358be05d4768f42a506876926a0bdef94a1d7d492c6d84436515
+oid sha256:3afbbeff9c2106aa6747a9a6b6d1f2974325978cb30b288d183425c5cf2062c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.014856944791972637,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.18181818181818182,
+  "best_metric": 0.008380405604839325,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.36363636363636365,
   "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": 15.508,
       "eval_steps_per_second": 1.939,
       "step": 25
+    },
+    {
+      "epoch": 0.1890909090909091,
+      "grad_norm": 3.340867042541504,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0748,
+      "step": 26
+    },
+    {
+      "epoch": 0.19636363636363635,
+      "grad_norm": 4.756340980529785,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0569,
+      "step": 27
+    },
+    {
+      "epoch": 0.20363636363636364,
+      "grad_norm": 2.0056493282318115,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0392,
+      "step": 28
+    },
+    {
+      "epoch": 0.2109090909090909,
+      "grad_norm": 1.7935372591018677,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0728,
+      "step": 29
+    },
+    {
+      "epoch": 0.21818181818181817,
+      "grad_norm": 3.992663860321045,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0897,
+      "step": 30
+    },
+    {
+      "epoch": 0.22545454545454546,
+      "grad_norm": 2.0212645530700684,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0439,
+      "step": 31
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 1.1357940435409546,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0609,
+      "step": 32
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.6464401483535767,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0382,
+      "step": 33
+    },
+    {
+      "epoch": 0.24727272727272728,
+      "grad_norm": 1.2237344980239868,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.0718,
+      "step": 34
+    },
+    {
+      "epoch": 0.2545454545454545,
+      "grad_norm": 2.4357638359069824,
+      "learning_rate": 5e-05,
+      "loss": 0.0566,
+      "step": 35
+    },
+    {
+      "epoch": 0.26181818181818184,
+      "grad_norm": 1.897200584411621,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1047,
+      "step": 36
+    },
+    {
+      "epoch": 0.2690909090909091,
+      "grad_norm": 1.4117827415466309,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.0423,
+      "step": 37
+    },
+    {
+      "epoch": 0.27636363636363637,
+      "grad_norm": 1.0462509393692017,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.04,
+      "step": 38
+    },
+    {
+      "epoch": 0.28363636363636363,
+      "grad_norm": 1.4082738161087036,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0524,
+      "step": 39
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 1.5846432447433472,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0752,
+      "step": 40
+    },
+    {
+      "epoch": 0.29818181818181816,
+      "grad_norm": 2.12044095993042,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0367,
+      "step": 41
+    },
+    {
+      "epoch": 0.3054545454545455,
+      "grad_norm": 0.6483519077301025,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0364,
+      "step": 42
+    },
+    {
+      "epoch": 0.31272727272727274,
+      "grad_norm": 0.7130972146987915,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0174,
+      "step": 43
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.9654887318611145,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0556,
+      "step": 44
+    },
+    {
+      "epoch": 0.32727272727272727,
+      "grad_norm": 2.261229991912842,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0579,
+      "step": 45
+    },
+    {
+      "epoch": 0.33454545454545453,
+      "grad_norm": 1.1127955913543701,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0171,
+      "step": 46
+    },
+    {
+      "epoch": 0.3418181818181818,
+      "grad_norm": 0.7904780507087708,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0358,
+      "step": 47
+    },
+    {
+      "epoch": 0.3490909090909091,
+      "grad_norm": 1.2277880907058716,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0484,
+      "step": 48
+    },
+    {
+      "epoch": 0.3563636363636364,
+      "grad_norm": 0.925501823425293,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.013,
+      "step": 49
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.3169645071029663,
+      "learning_rate": 0.0,
+      "loss": 0.0447,
+      "step": 50
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "eval_loss": 0.008380405604839325,
+      "eval_runtime": 14.9451,
+      "eval_samples_per_second": 15.523,
+      "eval_steps_per_second": 1.94,
+      "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": 3.32623943565312e+16,
+  "total_flos": 6.65247887130624e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null