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:e61b8dce405807895355ff3f59c36e297a912c7cbd0dc69ac00018a052be67e2
+oid sha256:5d73fbd520c5576bc2e439d68a3fd67f45d9ce70c105243188fb4617a1b1617e
 size 37352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42ed7524d9098e2f0342e343dffd6a09b69ad10bb2c7b9fdd2d6a5ebee07240
+oid sha256:1e05481a3ae9dd24308f17327cef018541956eaa2645d490ca17c2580e259763
 size 83444

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d9c839752ea44ed0d4878c8c6176e146face5563574e774fc0732bfaf938868
+oid sha256:4d57bdefdd30eeb90feb1309b5de38ffbfe925ce3c869f834ca81ae1e2497b02
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011042f21de94a771b39db8edb65345fb57be6acd97575fec42b80511d52ba13
+oid sha256:83c12a149d89394c4763c466e44e84659ab8a00b7f9ca96f975faec1d032a95d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e5b68357e797be945bb4145e1f71ab52a3f0ff922dbb60fb23449d03e5ece5
+oid sha256:0e709bce238b509edda5b8ad1ff45fd8d100222fedcecb14dd018a11e7a6e000
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f241a988c2bbd30a4b5bfd27ff45622231ef219717fcbafd40dc3786d5007f5
+oid sha256:add8b94d004921a7e4bb823615817c79baf0d73496bf3a9f38fb17a0e16aece5
 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": 12.441329956054688,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.027582402427251414,
+  "best_metric": 12.439943313598633,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05516480485450283,
   "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": 265.435,
       "eval_steps_per_second": 33.207,
       "step": 25
+    },
+    {
+      "epoch": 0.02868569852434147,
+      "grad_norm": 0.06623788177967072,
+      "learning_rate": 5e-05,
+      "loss": 12.451,
+      "step": 26
+    },
+    {
+      "epoch": 0.029788994621431527,
+      "grad_norm": 0.06605786830186844,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 12.4423,
+      "step": 27
+    },
+    {
+      "epoch": 0.030892290718521582,
+      "grad_norm": 0.07120940089225769,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 12.4352,
+      "step": 28
+    },
+    {
+      "epoch": 0.03199558681561164,
+      "grad_norm": 0.06746616214513779,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 12.439,
+      "step": 29
+    },
+    {
+      "epoch": 0.033098882912701695,
+      "grad_norm": 0.06748634576797485,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 12.4343,
+      "step": 30
+    },
+    {
+      "epoch": 0.03420217900979175,
+      "grad_norm": 0.07837369292974472,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 12.4397,
+      "step": 31
+    },
+    {
+      "epoch": 0.03530547510688181,
+      "grad_norm": 0.07359171658754349,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 12.4358,
+      "step": 32
+    },
+    {
+      "epoch": 0.03640877120397187,
+      "grad_norm": 0.07818469405174255,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 12.4377,
+      "step": 33
+    },
+    {
+      "epoch": 0.03751206730106192,
+      "grad_norm": 0.0786893218755722,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 12.4428,
+      "step": 34
+    },
+    {
+      "epoch": 0.038615363398151976,
+      "grad_norm": 0.0806044265627861,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 12.4377,
+      "step": 35
+    },
+    {
+      "epoch": 0.03971865949524204,
+      "grad_norm": 0.08134198188781738,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 12.4507,
+      "step": 36
+    },
+    {
+      "epoch": 0.04082195559233209,
+      "grad_norm": 0.08251143246889114,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 12.4369,
+      "step": 37
+    },
+    {
+      "epoch": 0.04192525168942215,
+      "grad_norm": 0.077778659760952,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 12.4453,
+      "step": 38
+    },
+    {
+      "epoch": 0.0430285477865122,
+      "grad_norm": 0.07704219222068787,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 12.4409,
+      "step": 39
+    },
+    {
+      "epoch": 0.044131843883602265,
+      "grad_norm": 0.07569456845521927,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 12.4331,
+      "step": 40
+    },
+    {
+      "epoch": 0.04523513998069232,
+      "grad_norm": 0.0804419070482254,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 12.4375,
+      "step": 41
+    },
+    {
+      "epoch": 0.046338436077782375,
+      "grad_norm": 0.07967319339513779,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 12.4464,
+      "step": 42
+    },
+    {
+      "epoch": 0.04744173217487243,
+      "grad_norm": 0.08038902282714844,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 12.4403,
+      "step": 43
+    },
+    {
+      "epoch": 0.04854502827196249,
+      "grad_norm": 0.08977244794368744,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 12.4376,
+      "step": 44
+    },
+    {
+      "epoch": 0.049648324369052546,
+      "grad_norm": 0.08467917889356613,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 12.4467,
+      "step": 45
+    },
+    {
+      "epoch": 0.0507516204661426,
+      "grad_norm": 0.08082818239927292,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 12.4352,
+      "step": 46
+    },
+    {
+      "epoch": 0.051854916563232656,
+      "grad_norm": 0.08253849297761917,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 12.4422,
+      "step": 47
+    },
+    {
+      "epoch": 0.05295821266032271,
+      "grad_norm": 0.0832681804895401,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 12.4337,
+      "step": 48
+    },
+    {
+      "epoch": 0.05406150875741277,
+      "grad_norm": 0.0880957767367363,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 12.4331,
+      "step": 49
+    },
+    {
+      "epoch": 0.05516480485450283,
+      "grad_norm": 0.08951980620622635,
+      "learning_rate": 0.0,
+      "loss": 12.431,
+      "step": 50
+    },
+    {
+      "epoch": 0.05516480485450283,
+      "eval_loss": 12.439943313598633,
+      "eval_runtime": 23.0018,
+      "eval_samples_per_second": 265.501,
+      "eval_steps_per_second": 33.215,
+      "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": 440496291840.0,
+  "total_flos": 881519493120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null