Training in progress, step 121, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9787ea70d0bb51540ee598c7368600f34290d02c53ca2921c3887711479e2893
+oid sha256:48f8f4560c354d0e7aa07e5f56a3c9b0d4c0e48599aff6231cf6f0a7f32bb962
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9586107f1c27f21b84be0584a07eee3b5891b1c6f4bff5f64c9101ee34d3a270
+oid sha256:bc7e86321b6a656f7a69ba261de0362540f03358f7a25ba10eb11f710fbaa97a
 size 68874

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0be6c38cf48b13184fe849738a078de15ec2edd6097be2b958c6ba32cc7ff19b
+oid sha256:a8a533cd1da8c22dbf6b76275aef753460ed9ec26a136383c034c508871fc8a5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a609aeb5e0af0c728ee288597ad43e60df38181bb605a0d3f97d48fae04bded
+oid sha256:dfbabeead774392b7faf646beaeefeb508008ced8065f58d37fabff8851bf3c4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b73e868476fa295a18b44a54dc870e2eeadc84ae562851a34ead4dea923d32cc
+oid sha256:1aa9c8416303e272c351f0f557dba3ea4eab9062fdbf796dc9a49acefcf50184
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85a35df15d7814e422dc17f1d106cf160169c9ed5f927f51a2cef8a81538696
+oid sha256:5eb7bb2a2b3474a8834b98d5e30032b0b495e64c248cfafe3508507e40ca4090
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f67707e0f0373ebe313e8f5199de173ded200232e4aaa3b673734f47586747
+oid sha256:4a7dcab05a29e905b6cb2f53c860067a0e023d2f45787fc8408b4d79acc2c8a7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.921277046203613,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 1.6597510373443982,
+  "epoch": 2.008298755186722,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 121,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -747,6 +747,153 @@
       "eval_samples_per_second": 739.82,
       "eval_steps_per_second": 29.593,
       "step": 100
+    },
+    {
+      "epoch": 1.6763485477178424,
+      "grad_norm": 0.01629016175866127,
+      "learning_rate": 2.3396327395507448e-05,
+      "loss": 11.9071,
+      "step": 101
+    },
+    {
+      "epoch": 1.6929460580912863,
+      "grad_norm": 0.015467053279280663,
+      "learning_rate": 2.117050991693609e-05,
+      "loss": 11.8865,
+      "step": 102
+    },
+    {
+      "epoch": 1.7095435684647304,
+      "grad_norm": 0.01504999864846468,
+      "learning_rate": 1.9047883025821774e-05,
+      "loss": 11.9293,
+      "step": 103
+    },
+    {
+      "epoch": 1.7261410788381744,
+      "grad_norm": 0.01039854995906353,
+      "learning_rate": 1.7030146916085185e-05,
+      "loss": 11.8954,
+      "step": 104
+    },
+    {
+      "epoch": 1.7427385892116183,
+      "grad_norm": 0.011301021091639996,
+      "learning_rate": 1.5118917765624467e-05,
+      "loss": 11.9575,
+      "step": 105
+    },
+    {
+      "epoch": 1.7593360995850622,
+      "grad_norm": 0.009601314552128315,
+      "learning_rate": 1.3315726441779629e-05,
+      "loss": 11.9122,
+      "step": 106
+    },
+    {
+      "epoch": 1.7759336099585061,
+      "grad_norm": 0.011440463364124298,
+      "learning_rate": 1.1622017275129708e-05,
+      "loss": 11.9329,
+      "step": 107
+    },
+    {
+      "epoch": 1.79253112033195,
+      "grad_norm": 0.013274903409183025,
+      "learning_rate": 1.00391469026044e-05,
+      "loss": 11.9641,
+      "step": 108
+    },
+    {
+      "epoch": 1.8091286307053942,
+      "grad_norm": 0.013196711428463459,
+      "learning_rate": 8.568383180837368e-06,
+      "loss": 12.013,
+      "step": 109
+    },
+    {
+      "epoch": 1.8257261410788381,
+      "grad_norm": 0.022849783301353455,
+      "learning_rate": 7.210904170631021e-06,
+      "loss": 12.3974,
+      "step": 110
+    },
+    {
+      "epoch": 1.8423236514522823,
+      "grad_norm": 0.015286913141608238,
+      "learning_rate": 5.967797193346574e-06,
+      "loss": 11.7548,
+      "step": 111
+    },
+    {
+      "epoch": 1.8589211618257262,
+      "grad_norm": 0.012541989795863628,
+      "learning_rate": 4.840057959975169e-06,
+      "loss": 11.5806,
+      "step": 112
+    },
+    {
+      "epoch": 1.8755186721991701,
+      "grad_norm": 0.013375689275562763,
+      "learning_rate": 3.828589773587515e-06,
+      "loss": 11.8641,
+      "step": 113
+    },
+    {
+      "epoch": 1.892116182572614,
+      "grad_norm": 0.01497753243893385,
+      "learning_rate": 2.934202805800989e-06,
+      "loss": 11.8974,
+      "step": 114
+    },
+    {
+      "epoch": 1.908713692946058,
+      "grad_norm": 0.010004348121583462,
+      "learning_rate": 2.1576134478437313e-06,
+      "loss": 11.8974,
+      "step": 115
+    },
+    {
+      "epoch": 1.9253112033195021,
+      "grad_norm": 0.009814193472266197,
+      "learning_rate": 1.4994437367354339e-06,
+      "loss": 11.9167,
+      "step": 116
+    },
+    {
+      "epoch": 1.941908713692946,
+      "grad_norm": 0.008285530842840672,
+      "learning_rate": 9.602208570445636e-07,
+      "loss": 12.0253,
+      "step": 117
+    },
+    {
+      "epoch": 1.9585062240663902,
+      "grad_norm": 0.01668418012559414,
+      "learning_rate": 5.403767186210218e-07,
+      "loss": 11.8426,
+      "step": 118
+    },
+    {
+      "epoch": 1.9751037344398341,
+      "grad_norm": 0.014265616424381733,
+      "learning_rate": 2.402476106425466e-07,
+      "loss": 12.0079,
+      "step": 119
+    },
+    {
+      "epoch": 1.991701244813278,
+      "grad_norm": 0.016387728974223137,
+      "learning_rate": 6.007393225176404e-08,
+      "loss": 12.1605,
+      "step": 120
+    },
+    {
+      "epoch": 2.008298755186722,
+      "grad_norm": 0.04243115335702896,
+      "learning_rate": 0.0,
+      "loss": 20.6424,
+      "step": 121
     }
   ],
   "logging_steps": 1,
@@ -770,12 +917,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 639438176256.0,
+  "total_flos": 774412984320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null