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:a7eafe47ffc3a6c191194c79651e2f1c838df604fc23b4aa0faaac55d7b8faba
+oid sha256:682be27ece66f9a8a568a0d411cc45f1649bedeedd1049d40a479323daf4bdd2
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fccd049535ed4ff363c7a5a2cef783eb1cb12bd67752e0a87cd6461845ec713
+oid sha256:a348da2defc8052781c60c3f6b93af5b7a9ee00c700a96e5b397ac47453a7b46
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac94bb3cc87c8de208a8b004cce16243d4705e73f1bf6c90367cc51814e90f06
+oid sha256:df18b56402251af5cb25c1ed68581f60ddc2e663f6a9ceb2125ca5db275f495f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3d8ea1c81b1c92b4fec84760ed7716fedf9e67df6053c2dbbbd49667989a3f
+oid sha256:902a5d834fb8986f24d7b2a3c0b413eb45c8229700494fdf3b276b4c77ee46b1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e7f1095bc4d788846282c91edb079bd97f30f3842f750479072f27d9d908aa
+oid sha256:3d5a15361f4e84472b42b0d0cb80062ef308c2bd3e5f15513b166530eb55d616
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c9543f5715cb5c9fb637d47f4d4bf8934beb21e2df91864a6cc72d46cbed4e
+oid sha256:226904ad78c9c0b1dabd5e7db2326c881512e98a08cd73aed76a2320a46c8324
 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": 11.762114524841309,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02463964518910928,
+  "best_metric": 11.758837699890137,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04927929037821856,
   "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": 312.289,
       "eval_steps_per_second": 81.195,
       "step": 25
+    },
+    {
+      "epoch": 0.02562523099667365,
+      "grad_norm": 0.06491614878177643,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.7642,
+      "step": 26
+    },
+    {
+      "epoch": 0.02661081680423802,
+      "grad_norm": 0.06239859759807587,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7607,
+      "step": 27
+    },
+    {
+      "epoch": 0.02759640261180239,
+      "grad_norm": 0.06446800380945206,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7627,
+      "step": 28
+    },
+    {
+      "epoch": 0.028581988419366763,
+      "grad_norm": 0.07301193475723267,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7614,
+      "step": 29
+    },
+    {
+      "epoch": 0.029567574226931133,
+      "grad_norm": 0.06827574968338013,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.7594,
+      "step": 30
+    },
+    {
+      "epoch": 0.030553160034495503,
+      "grad_norm": 0.06913921236991882,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.7581,
+      "step": 31
+    },
+    {
+      "epoch": 0.03153874584205987,
+      "grad_norm": 0.08095534145832062,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.7569,
+      "step": 32
+    },
+    {
+      "epoch": 0.03252433164962425,
+      "grad_norm": 0.07958046346902847,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.7622,
+      "step": 33
+    },
+    {
+      "epoch": 0.033509917457188614,
+      "grad_norm": 0.08830973505973816,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.763,
+      "step": 34
+    },
+    {
+      "epoch": 0.03449550326475299,
+      "grad_norm": 0.09469051659107208,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.7601,
+      "step": 35
+    },
+    {
+      "epoch": 0.03548108907231736,
+      "grad_norm": 0.09495487809181213,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7612,
+      "step": 36
+    },
+    {
+      "epoch": 0.03646667487988173,
+      "grad_norm": 0.09853039681911469,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.7619,
+      "step": 37
+    },
+    {
+      "epoch": 0.0374522606874461,
+      "grad_norm": 0.0928775817155838,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.7562,
+      "step": 38
+    },
+    {
+      "epoch": 0.038437846495010475,
+      "grad_norm": 0.08328034728765488,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.7608,
+      "step": 39
+    },
+    {
+      "epoch": 0.03942343230257484,
+      "grad_norm": 0.08076374232769012,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7634,
+      "step": 40
+    },
+    {
+      "epoch": 0.040409018110139215,
+      "grad_norm": 0.07809954881668091,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.7596,
+      "step": 41
+    },
+    {
+      "epoch": 0.04139460391770358,
+      "grad_norm": 0.09155470132827759,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7622,
+      "step": 42
+    },
+    {
+      "epoch": 0.042380189725267955,
+      "grad_norm": 0.08296317607164383,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.7583,
+      "step": 43
+    },
+    {
+      "epoch": 0.04336577553283233,
+      "grad_norm": 0.08634920418262482,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.7581,
+      "step": 44
+    },
+    {
+      "epoch": 0.044351361340396696,
+      "grad_norm": 0.08652149140834808,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.7608,
+      "step": 45
+    },
+    {
+      "epoch": 0.04533694714796107,
+      "grad_norm": 0.08408989012241364,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.7577,
+      "step": 46
+    },
+    {
+      "epoch": 0.04632253295552544,
+      "grad_norm": 0.09810920059680939,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.7598,
+      "step": 47
+    },
+    {
+      "epoch": 0.04730811876308981,
+      "grad_norm": 0.09459834545850754,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7593,
+      "step": 48
+    },
+    {
+      "epoch": 0.04829370457065418,
+      "grad_norm": 0.11204507201910019,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.758,
+      "step": 49
+    },
+    {
+      "epoch": 0.04927929037821856,
+      "grad_norm": 0.10605693608522415,
+      "learning_rate": 1e-05,
+      "loss": 11.7611,
+      "step": 50
+    },
+    {
+      "epoch": 0.04927929037821856,
+      "eval_loss": 11.758837699890137,
+      "eval_runtime": 0.1569,
+      "eval_samples_per_second": 318.582,
+      "eval_steps_per_second": 82.831,
+      "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": 82045497769984.0,
+  "total_flos": 164193424113664.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null