Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a508200a1f8a6faf886a8e172e018fd5376d906da88e63a82f340283c658614
+oid sha256:e49fac79df062a740613490d8de75f6f6b5b733235585175540be4d04a1e9da4
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3e7d8b6843823a84e7f44b4a2b996159f0df376d07fd5f2d429b446cf272f1
+oid sha256:c021b95308575d15aafb1861a32667149db343ceec304ec547e3f2ad365f60e8
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784b0ed5c586e9c7d21ba8eaaf9e4654d43169c77d6bc77168f9f11248f281ac
+oid sha256:81b15f7a13965e209a2e2b78707aa18f687f540f23be82d8c733fc2ec88cee6e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06a2d9385b181dcd93f708b2eceb4197f29d75402d1d349c152ebf01dc03b80
+oid sha256:b6fe487101b8454200a6b98afce987880f1c044ac9bf48fca459aa6bc90b1681
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4117f58285444eb1f1ee417144821e84c42bec18f9bfa34d9a9d264a82fab4a
+oid sha256:f4df5ad5487779c968a091b073bb50daa437b33a13eb5e0cfa5121fd2cda9a52
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f1e0207ef4936a496ae58b32fe96a33c9c2f3ef135322796f4260be5495134
+oid sha256:989aa7b5f3ee27da8dbdefeb3bb16fad2f537cdda878d90a1c2806604c0edd08
 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": 10.367364883422852,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05391562205148942,
+  "best_metric": 10.357181549072266,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10783124410297884,
   "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": 284.298,
       "eval_steps_per_second": 73.917,
       "step": 25
+    },
+    {
+      "epoch": 0.056072246933548994,
+      "grad_norm": 0.24105389416217804,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3707,
+      "step": 26
+    },
+    {
+      "epoch": 0.058228871815608575,
+      "grad_norm": 0.22713711857795715,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3697,
+      "step": 27
+    },
+    {
+      "epoch": 0.06038549669766815,
+      "grad_norm": 0.2347206324338913,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3692,
+      "step": 28
+    },
+    {
+      "epoch": 0.06254212157972773,
+      "grad_norm": 0.24226069450378418,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3671,
+      "step": 29
+    },
+    {
+      "epoch": 0.0646987464617873,
+      "grad_norm": 0.2433302104473114,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.367,
+      "step": 30
+    },
+    {
+      "epoch": 0.06685537134384688,
+      "grad_norm": 0.23942533135414124,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3671,
+      "step": 31
+    },
+    {
+      "epoch": 0.06901199622590645,
+      "grad_norm": 0.23229525983333588,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.368,
+      "step": 32
+    },
+    {
+      "epoch": 0.07116862110796603,
+      "grad_norm": 0.2230001538991928,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3679,
+      "step": 33
+    },
+    {
+      "epoch": 0.07332524599002561,
+      "grad_norm": 0.233306884765625,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3683,
+      "step": 34
+    },
+    {
+      "epoch": 0.07548187087208519,
+      "grad_norm": 0.23442818224430084,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.366,
+      "step": 35
+    },
+    {
+      "epoch": 0.07763849575414476,
+      "grad_norm": 0.22949644923210144,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3667,
+      "step": 36
+    },
+    {
+      "epoch": 0.07979512063620434,
+      "grad_norm": 0.21760444343090057,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3682,
+      "step": 37
+    },
+    {
+      "epoch": 0.08195174551826391,
+      "grad_norm": 0.2517710328102112,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3608,
+      "step": 38
+    },
+    {
+      "epoch": 0.0841083704003235,
+      "grad_norm": 0.2667182385921478,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3628,
+      "step": 39
+    },
+    {
+      "epoch": 0.08626499528238307,
+      "grad_norm": 0.2659625709056854,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3621,
+      "step": 40
+    },
+    {
+      "epoch": 0.08842162016444265,
+      "grad_norm": 0.2763594090938568,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3643,
+      "step": 41
+    },
+    {
+      "epoch": 0.09057824504650222,
+      "grad_norm": 0.2761751413345337,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3634,
+      "step": 42
+    },
+    {
+      "epoch": 0.0927348699285618,
+      "grad_norm": 0.2660277485847473,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3611,
+      "step": 43
+    },
+    {
+      "epoch": 0.09489149481062138,
+      "grad_norm": 0.27291256189346313,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3632,
+      "step": 44
+    },
+    {
+      "epoch": 0.09704811969268096,
+      "grad_norm": 0.24558402597904205,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3635,
+      "step": 45
+    },
+    {
+      "epoch": 0.09920474457474053,
+      "grad_norm": 0.24723613262176514,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3647,
+      "step": 46
+    },
+    {
+      "epoch": 0.1013613694568001,
+      "grad_norm": 0.23409686982631683,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3641,
+      "step": 47
+    },
+    {
+      "epoch": 0.10351799433885968,
+      "grad_norm": 0.2346973419189453,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.365,
+      "step": 48
+    },
+    {
+      "epoch": 0.10567461922091927,
+      "grad_norm": 0.21328896284103394,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3661,
+      "step": 49
+    },
+    {
+      "epoch": 0.10783124410297884,
+      "grad_norm": 0.24933189153671265,
+      "learning_rate": 1e-05,
+      "loss": 10.3626,
+      "step": 50
+    },
+    {
+      "epoch": 0.10783124410297884,
+      "eval_loss": 10.357181549072266,
+      "eval_runtime": 0.1778,
+      "eval_samples_per_second": 281.248,
+      "eval_steps_per_second": 73.125,
+      "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": 21390712307712.0,
+  "total_flos": 42788107124736.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null