Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1147614a6e85de1d9e2f4e2376bd177e2d5e85b545e02d0546a24728ad865471
+oid sha256:b46006f366def493f64dd41e5aeb47a8f01cc298fcfeae9f56f2e0ddb2732bc4
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23834ad4384afa286019e44b363892aa9d5cd65b9d6ad431405efbe154ada154
+oid sha256:a1d4b68dd69b2430720c46ded8970426f865420c4fbd77b20adb6f0f03af5ceb
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10bb775aef3634c18e85e482f2921041faaf1e4d5e7d99b1e6c84a306e8c18ef
+oid sha256:c50d55ee2e0ed176cd88b5fd6e7bc517ba61729cccfcf76b92e06a0af3662289
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b310f76db6cae2139466df148f0227fc48a1f83b808fb8b00de82c023094a8aa
+oid sha256:209e16906f8c3c072337b3c0e4092b319899072233e11e16518fd9fe8f4ce6a9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d5866dd1a9e7463ca192b836b0dc525d4faf226ec436020db4e0ed75aecb7c
+oid sha256:609d04d8088cd02a1248e6aea52479ca2cf1b5efb88b60eb128617904ff06514
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c5451d740af91502bd732ba3797883db157e5f3318ace24e5d626cc4a0004a
+oid sha256:3b2dc72f68b2a50ccf41cff4fa89fafc17977e2f742c6390bd04d89b5b3a0297
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.14145001769065857,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7782101167315175,
+  "best_metric": 0.10530552268028259,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.556420233463035,
   "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": 14.294,
       "eval_steps_per_second": 3.716,
       "step": 25
+    },
+    {
+      "epoch": 0.8093385214007782,
+      "grad_norm": 2.2419772148132324,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1745,
+      "step": 26
+    },
+    {
+      "epoch": 0.8404669260700389,
+      "grad_norm": 1.8178470134735107,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1717,
+      "step": 27
+    },
+    {
+      "epoch": 0.8715953307392996,
+      "grad_norm": 1.2768809795379639,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1504,
+      "step": 28
+    },
+    {
+      "epoch": 0.9027237354085603,
+      "grad_norm": 0.9017437696456909,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.159,
+      "step": 29
+    },
+    {
+      "epoch": 0.933852140077821,
+      "grad_norm": 1.263572096824646,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1653,
+      "step": 30
+    },
+    {
+      "epoch": 0.9649805447470817,
+      "grad_norm": 1.1224571466445923,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1611,
+      "step": 31
+    },
+    {
+      "epoch": 0.9961089494163424,
+      "grad_norm": 1.5271551609039307,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1742,
+      "step": 32
+    },
+    {
+      "epoch": 1.027237354085603,
+      "grad_norm": 2.334810733795166,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.228,
+      "step": 33
+    },
+    {
+      "epoch": 1.0583657587548638,
+      "grad_norm": 0.7964612245559692,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1209,
+      "step": 34
+    },
+    {
+      "epoch": 1.0894941634241244,
+      "grad_norm": 0.8177843689918518,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1245,
+      "step": 35
+    },
+    {
+      "epoch": 1.1206225680933852,
+      "grad_norm": 0.7340578436851501,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1294,
+      "step": 36
+    },
+    {
+      "epoch": 1.1517509727626458,
+      "grad_norm": 0.859123170375824,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1388,
+      "step": 37
+    },
+    {
+      "epoch": 1.1828793774319066,
+      "grad_norm": 0.758919358253479,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1088,
+      "step": 38
+    },
+    {
+      "epoch": 1.2140077821011672,
+      "grad_norm": 0.7981888651847839,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1256,
+      "step": 39
+    },
+    {
+      "epoch": 1.245136186770428,
+      "grad_norm": 0.8933906555175781,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1213,
+      "step": 40
+    },
+    {
+      "epoch": 1.2762645914396886,
+      "grad_norm": 0.7495871186256409,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0941,
+      "step": 41
+    },
+    {
+      "epoch": 1.3073929961089494,
+      "grad_norm": 0.6591278910636902,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0954,
+      "step": 42
+    },
+    {
+      "epoch": 1.3385214007782102,
+      "grad_norm": 0.6582584381103516,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0985,
+      "step": 43
+    },
+    {
+      "epoch": 1.3696498054474708,
+      "grad_norm": 0.6135019063949585,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1084,
+      "step": 44
+    },
+    {
+      "epoch": 1.4007782101167314,
+      "grad_norm": 0.857144296169281,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0981,
+      "step": 45
+    },
+    {
+      "epoch": 1.4319066147859922,
+      "grad_norm": 1.0293967723846436,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.1399,
+      "step": 46
+    },
+    {
+      "epoch": 1.463035019455253,
+      "grad_norm": 0.947338879108429,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.1457,
+      "step": 47
+    },
+    {
+      "epoch": 1.4941634241245136,
+      "grad_norm": 1.044509768486023,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1132,
+      "step": 48
+    },
+    {
+      "epoch": 1.5252918287937742,
+      "grad_norm": 0.7475258708000183,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0992,
+      "step": 49
+    },
+    {
+      "epoch": 1.556420233463035,
+      "grad_norm": 0.8056252002716064,
+      "learning_rate": 1e-05,
+      "loss": 0.0983,
+      "step": 50
+    },
+    {
+      "epoch": 1.556420233463035,
+      "eval_loss": 0.10530552268028259,
+      "eval_runtime": 3.4776,
+      "eval_samples_per_second": 14.378,
+      "eval_steps_per_second": 3.738,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null