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:f5a9a9e5917dc3084485bc4577b59fa1cb5e103f43f3173d46749d51fef2d564
+oid sha256:285396dcfd59b27426e4509c7b4a5b7f323052389580c9a7302bae7a87b10aba
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b1e7decb6cc940967b2eceff55de68780bc7b82d785cc777ef92ae358928fb
+oid sha256:4ff942978abf391966946aef96bc1e30feba0a0fbf2771fbabb87d63a416432e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba66ccf8aa3678f61a575e4dbc972d7be3e630cbbbff4ed91f3e27f85b2cb130
+oid sha256:d94dca5b824fcd9bb8fe66f63be2bd729c38587db70e8209c7863dcf5e22a61e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33f82013f3ef43317641fe82cd0019efb0c65b0da7d8945627209d84bf8085b
+oid sha256:ee7872dcba56e23c097e8ed3bf9787eae538c39bd23188def6f6de5509cdec89
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22b63e4c10d179cb0ce7126f5ee72c79b61bef8d7b5bba6b01fc70889897313
+oid sha256:515de67eab54c7b107a0a4e4cb42a0f63c8d6eaf495dddbb5a8713f722b9255e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:029d80fe76ea0a20efe12d2cf109fd840bc79ef24f7c7e1c9728d97a2cdb5181
+oid sha256:3adb35d3a552fae9d2eeb99843c86bb4a606ed8fd9634fa494cf24240cfbd92a
 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": 0.5643110275268555,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14657383657017223,
+  "best_metric": 0.5524216890335083,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.29314767314034446,
   "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": 19.454,
       "eval_steps_per_second": 2.436,
       "step": 25
+    },
+    {
+      "epoch": 0.1524367900329791,
+      "grad_norm": 2.8844926357269287,
+      "learning_rate": 5e-05,
+      "loss": 0.3593,
+      "step": 26
+    },
+    {
+      "epoch": 0.158299743495786,
+      "grad_norm": 2.7052319049835205,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4142,
+      "step": 27
+    },
+    {
+      "epoch": 0.1641626969585929,
+      "grad_norm": 2.585421085357666,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4299,
+      "step": 28
+    },
+    {
+      "epoch": 0.17002565042139978,
+      "grad_norm": 2.434501886367798,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4347,
+      "step": 29
+    },
+    {
+      "epoch": 0.17588860388420666,
+      "grad_norm": 2.5646467208862305,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4853,
+      "step": 30
+    },
+    {
+      "epoch": 0.18175155734701356,
+      "grad_norm": 2.898298740386963,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5326,
+      "step": 31
+    },
+    {
+      "epoch": 0.18761451080982045,
+      "grad_norm": 3.0445826053619385,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5938,
+      "step": 32
+    },
+    {
+      "epoch": 0.19347746427262733,
+      "grad_norm": 3.08903431892395,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6085,
+      "step": 33
+    },
+    {
+      "epoch": 0.19934041773543423,
+      "grad_norm": 3.1981983184814453,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6151,
+      "step": 34
+    },
+    {
+      "epoch": 0.2052033711982411,
+      "grad_norm": 3.186462163925171,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6629,
+      "step": 35
+    },
+    {
+      "epoch": 0.211066324661048,
+      "grad_norm": 3.430967092514038,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6638,
+      "step": 36
+    },
+    {
+      "epoch": 0.2169292781238549,
+      "grad_norm": 3.725010395050049,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.743,
+      "step": 37
+    },
+    {
+      "epoch": 0.22279223158666178,
+      "grad_norm": 4.150148391723633,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6477,
+      "step": 38
+    },
+    {
+      "epoch": 0.22865518504946866,
+      "grad_norm": 2.6251025199890137,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4256,
+      "step": 39
+    },
+    {
+      "epoch": 0.23451813851227557,
+      "grad_norm": 2.48233962059021,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3879,
+      "step": 40
+    },
+    {
+      "epoch": 0.24038109197508245,
+      "grad_norm": 2.504904270172119,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4267,
+      "step": 41
+    },
+    {
+      "epoch": 0.24624404543788933,
+      "grad_norm": 2.4927873611450195,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4366,
+      "step": 42
+    },
+    {
+      "epoch": 0.2521069989006962,
+      "grad_norm": 2.559534788131714,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5019,
+      "step": 43
+    },
+    {
+      "epoch": 0.2579699523635031,
+      "grad_norm": 2.7358570098876953,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6335,
+      "step": 44
+    },
+    {
+      "epoch": 0.26383290582631,
+      "grad_norm": 2.759261131286621,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6043,
+      "step": 45
+    },
+    {
+      "epoch": 0.2696958592891169,
+      "grad_norm": 3.009692430496216,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6303,
+      "step": 46
+    },
+    {
+      "epoch": 0.2755588127519238,
+      "grad_norm": 3.053942918777466,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6556,
+      "step": 47
+    },
+    {
+      "epoch": 0.2814217662147307,
+      "grad_norm": 3.200474739074707,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6752,
+      "step": 48
+    },
+    {
+      "epoch": 0.28728471967753755,
+      "grad_norm": 3.4686524868011475,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6942,
+      "step": 49
+    },
+    {
+      "epoch": 0.29314767314034446,
+      "grad_norm": 4.90553092956543,
+      "learning_rate": 0.0,
+      "loss": 0.8439,
+      "step": 50
+    },
+    {
+      "epoch": 0.29314767314034446,
+      "eval_loss": 0.5524216890335083,
+      "eval_runtime": 59.4099,
+      "eval_samples_per_second": 19.357,
+      "eval_steps_per_second": 2.424,
+      "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": 4.4769093798907085e+17,
+  "total_flos": 8.911383602428641e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null