Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9fbd24b4112f26bb557ae7fa5c5212659c63ee3f411b1923d90f65ac70424b
+oid sha256:1758b45549cb650da3d23dcd14b541a174c68a795ec737980018fe43cf01d827
 size 113864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774e53de0cb7f5fe5ec9399de1a0d4f03d2adf804ba8b65bd4c5d4aa4276aba2
+oid sha256:cadfafe431262e0dc452370456f8b039a407a04e10ca8c62a4396d54f78eb254
 size 244554

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee4e4eaeb8904d6cb9f2d79f284644bddfc4d1949103f727557baa7ba138f066
+oid sha256:b84fd65c05bff8eef3a606db8a36ecbd6e5e8b5bde4854a343981bef9f45bc5c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:103e83737f01903af0c786a23c081f2a9d27cb409aae565da21916821485d49d
+oid sha256:b45a698ff6fe7f124609a6e073b121baeb1e1fd099504aabc04003de8aac93d0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1248ef16dd4da439d009664198788e5786f9cdf4f25f1a82c69a79369e90e752
+oid sha256:424a4d5ea86f1785f352a2a961237948cdbe216eca4b48a424975e438774c83f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0024b4b8a24a6d810d55a79e22185568161ff1130e4edb524d8c08bc71b861
+oid sha256:74eac14b42ad58c578c9fa4b223a6066c1051f0aa4010b79b97e559f7878ce19
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.359905242919922,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2777777777777778,
+  "best_metric": 10.351967811584473,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5555555555555556,
   "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": 533.538,
       "eval_steps_per_second": 66.802,
       "step": 25
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 4.7071533203125,
+      "learning_rate": 5e-05,
+      "loss": 165.782,
+      "step": 26
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.890855312347412,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 165.7428,
+      "step": 27
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 4.952169895172119,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 165.7307,
+      "step": 28
+    },
+    {
+      "epoch": 0.32222222222222224,
+      "grad_norm": 5.063704967498779,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 165.7296,
+      "step": 29
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 5.143160820007324,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 165.7075,
+      "step": 30
+    },
+    {
+      "epoch": 0.34444444444444444,
+      "grad_norm": 5.115466117858887,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 165.6855,
+      "step": 31
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 5.136069297790527,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 165.6738,
+      "step": 32
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 5.1304707527160645,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 165.6747,
+      "step": 33
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 5.154939651489258,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 165.6664,
+      "step": 34
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 5.159790992736816,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 165.684,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.0748209953308105,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 165.6955,
+      "step": 36
+    },
+    {
+      "epoch": 0.4111111111111111,
+      "grad_norm": 4.830750465393066,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 165.6902,
+      "step": 37
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 5.073268413543701,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 165.6824,
+      "step": 38
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 5.661942005157471,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 165.6572,
+      "step": 39
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 5.7315754890441895,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 165.6268,
+      "step": 40
+    },
+    {
+      "epoch": 0.45555555555555555,
+      "grad_norm": 5.768131256103516,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 165.652,
+      "step": 41
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 5.762514114379883,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 165.6245,
+      "step": 42
+    },
+    {
+      "epoch": 0.4777777777777778,
+      "grad_norm": 5.732676029205322,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 165.6337,
+      "step": 43
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 5.677743434906006,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 165.6258,
+      "step": 44
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.603147029876709,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 165.6108,
+      "step": 45
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 5.611842155456543,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 165.6401,
+      "step": 46
+    },
+    {
+      "epoch": 0.5222222222222223,
+      "grad_norm": 5.5356245040893555,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 165.6436,
+      "step": 47
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 5.494062900543213,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 165.6397,
+      "step": 48
+    },
+    {
+      "epoch": 0.5444444444444444,
+      "grad_norm": 5.341508388519287,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 165.6567,
+      "step": 49
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 5.405158519744873,
+      "learning_rate": 0.0,
+      "loss": 165.6591,
+      "step": 50
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "eval_loss": 10.351967811584473,
+      "eval_runtime": 1.1256,
+      "eval_samples_per_second": 539.249,
+      "eval_steps_per_second": 67.517,
+      "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": 67369928491008.0,
+  "total_flos": 136048519151616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null