Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51bd16a73246209a4fbf25696a562c8a905ec9ad4b17888fea8b7b8dfac32d75
+oid sha256:7ed08efe7ca9db72ff0c68e6540036fd62b2d71245c5b5c7534c4d32d93b9a59
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bee346bea5e64e89f61b9fb15d7a24004f23031daaa72f8b48b369250e0e85
+oid sha256:e96672adc90f76710f1231a79729ea7d75b262aa04cd7c4b7e9160a303d0c751
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
+oid sha256:5270a8ad33fa8f4633e4b858b5f92c1fafc05119f07ca49330569eeec336ada6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040b95482c646935022d148ebc91f462fbf2195cfa3365adbbe3bd6ca1f35a74
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007328423289729215,
+  "epoch": 0.01465684657945843,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 115.512,
       "eval_steps_per_second": 57.776,
       "step": 25
+    },
+    {
+      "epoch": 0.007621560221318383,
+      "grad_norm": 0.03293245658278465,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9269,
+      "step": 26
+    },
+    {
+      "epoch": 0.007914697152907551,
+      "grad_norm": 0.027991851791739464,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 11.9285,
+      "step": 27
+    },
+    {
+      "epoch": 0.008207834084496721,
+      "grad_norm": 0.030205611139535904,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 11.9266,
+      "step": 28
+    },
+    {
+      "epoch": 0.008500971016085889,
+      "grad_norm": 0.02978375367820263,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 11.928,
+      "step": 29
+    },
+    {
+      "epoch": 0.008794107947675057,
+      "grad_norm": 0.03635377064347267,
+      "learning_rate": 0.0001,
+      "loss": 11.9275,
+      "step": 30
+    },
+    {
+      "epoch": 0.008794107947675057,
+      "eval_loss": 11.927339553833008,
+      "eval_runtime": 24.8896,
+      "eval_samples_per_second": 115.43,
+      "eval_steps_per_second": 57.735,
+      "step": 30
+    },
+    {
+      "epoch": 0.009087244879264227,
+      "grad_norm": 0.03566306084394455,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 11.9261,
+      "step": 31
+    },
+    {
+      "epoch": 0.009380381810853395,
+      "grad_norm": 0.03900522366166115,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 11.9265,
+      "step": 32
+    },
+    {
+      "epoch": 0.009673518742442563,
+      "grad_norm": 0.04783564433455467,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 11.9261,
+      "step": 33
+    },
+    {
+      "epoch": 0.009966655674031733,
+      "grad_norm": 0.03774084150791168,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 11.9276,
+      "step": 34
+    },
+    {
+      "epoch": 0.010259792605620901,
+      "grad_norm": 0.0395960696041584,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 11.9252,
+      "step": 35
+    },
+    {
+      "epoch": 0.010259792605620901,
+      "eval_loss": 11.926952362060547,
+      "eval_runtime": 24.7995,
+      "eval_samples_per_second": 115.849,
+      "eval_steps_per_second": 57.945,
+      "step": 35
+    },
+    {
+      "epoch": 0.010552929537210069,
+      "grad_norm": 0.031245063990354538,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 11.9256,
+      "step": 36
+    },
+    {
+      "epoch": 0.010846066468799239,
+      "grad_norm": 0.03537562116980553,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 11.9264,
+      "step": 37
+    },
+    {
+      "epoch": 0.011139203400388407,
+      "grad_norm": 0.03238970413804054,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.9279,
+      "step": 38
+    },
+    {
+      "epoch": 0.011432340331977575,
+      "grad_norm": 0.03814040124416351,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 11.9251,
+      "step": 39
+    },
+    {
+      "epoch": 0.011725477263566743,
+      "grad_norm": 0.03654216229915619,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 11.9248,
+      "step": 40
+    },
+    {
+      "epoch": 0.011725477263566743,
+      "eval_loss": 11.926708221435547,
+      "eval_runtime": 24.7998,
+      "eval_samples_per_second": 115.848,
+      "eval_steps_per_second": 57.944,
+      "step": 40
+    },
+    {
+      "epoch": 0.012018614195155913,
+      "grad_norm": 0.04135998338460922,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 11.9255,
+      "step": 41
+    },
+    {
+      "epoch": 0.01231175112674508,
+      "grad_norm": 0.03332056105136871,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 11.9267,
+      "step": 42
+    },
+    {
+      "epoch": 0.012604888058334249,
+      "grad_norm": 0.038812343031167984,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 11.9276,
+      "step": 43
+    },
+    {
+      "epoch": 0.012898024989923419,
+      "grad_norm": 0.04861786961555481,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.9272,
+      "step": 44
+    },
+    {
+      "epoch": 0.013191161921512587,
+      "grad_norm": 0.036478109657764435,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 11.9273,
+      "step": 45
+    },
+    {
+      "epoch": 0.013191161921512587,
+      "eval_loss": 11.926604270935059,
+      "eval_runtime": 24.9172,
+      "eval_samples_per_second": 115.302,
+      "eval_steps_per_second": 57.671,
+      "step": 45
+    },
+    {
+      "epoch": 0.013484298853101755,
+      "grad_norm": 0.047678880393505096,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 11.925,
+      "step": 46
+    },
+    {
+      "epoch": 0.013777435784690924,
+      "grad_norm": 0.03523854911327362,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 11.9267,
+      "step": 47
+    },
+    {
+      "epoch": 0.014070572716280092,
+      "grad_norm": 0.041060738265514374,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 11.9272,
+      "step": 48
+    },
+    {
+      "epoch": 0.01436370964786926,
+      "grad_norm": 0.039238590747117996,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 11.9262,
+      "step": 49
+    },
+    {
+      "epoch": 0.01465684657945843,
+      "grad_norm": 0.03868459165096283,
+      "learning_rate": 0.0,
+      "loss": 11.9278,
+      "step": 50
+    },
+    {
+      "epoch": 0.01465684657945843,
+      "eval_loss": 11.92658519744873,
+      "eval_runtime": 24.9438,
+      "eval_samples_per_second": 115.179,
+      "eval_steps_per_second": 57.61,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 37473484800.0,
+  "total_flos": 74946969600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null