Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566e707db1ec109b7de18f39db0405edea1872dfe6fe7005423b0d53c3c1001b
+oid sha256:323db57466ceb9b4f55da57aec2eb9f4e46381c3c6a3c4f1f4b9e317886fca5c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d15fc0802be07b7fd1276d666f8f4aef0db03976af597a70871fc2e6bcb618b
+oid sha256:0f986297c9426c7b3d52aeb95964c4e4531a32a3d725d640129e1f795e7b3002
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831cb014d734d1a236f43ff0ae6d2fae9843b9526271b8c069d0c080cd61d6bb
+oid sha256:43d3ee90a63e02390da60ec439ae36d8d9b15db2ed71752863edd5f68f794cb9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37593984962406013,
+  "epoch": 0.5012531328320802,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 1.4927,
       "step": 75
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.5334950685501099,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4068,
+      "step": 76
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 1.543641448020935,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4417,
+      "step": 77
+    },
+    {
+      "epoch": 0.39097744360902253,
+      "grad_norm": 1.2889515161514282,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3701,
+      "step": 78
+    },
+    {
+      "epoch": 0.39598997493734334,
+      "grad_norm": 1.4031617641448975,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.3879,
+      "step": 79
+    },
+    {
+      "epoch": 0.40100250626566414,
+      "grad_norm": 2.3280229568481445,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.4804,
+      "step": 80
+    },
+    {
+      "epoch": 0.40601503759398494,
+      "grad_norm": 1.840705394744873,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.4225,
+      "step": 81
+    },
+    {
+      "epoch": 0.40601503759398494,
+      "eval_loss": 0.6867606043815613,
+      "eval_runtime": 28.605,
+      "eval_samples_per_second": 5.873,
+      "eval_steps_per_second": 0.734,
+      "step": 81
+    },
+    {
+      "epoch": 0.41102756892230574,
+      "grad_norm": 1.6926554441452026,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.4528,
+      "step": 82
+    },
+    {
+      "epoch": 0.41604010025062654,
+      "grad_norm": 1.542953372001648,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.422,
+      "step": 83
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.3982118368148804,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.43,
+      "step": 84
+    },
+    {
+      "epoch": 0.42606516290726815,
+      "grad_norm": 1.7478983402252197,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4112,
+      "step": 85
+    },
+    {
+      "epoch": 0.43107769423558895,
+      "grad_norm": 2.144606590270996,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4026,
+      "step": 86
+    },
+    {
+      "epoch": 0.43609022556390975,
+      "grad_norm": 1.515303611755371,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.3563,
+      "step": 87
+    },
+    {
+      "epoch": 0.44110275689223055,
+      "grad_norm": 1.6609570980072021,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4258,
+      "step": 88
+    },
+    {
+      "epoch": 0.44611528822055135,
+      "grad_norm": 1.8882701396942139,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.3771,
+      "step": 89
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "grad_norm": 1.545371174812317,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.3798,
+      "step": 90
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "eval_loss": 0.6865832805633545,
+      "eval_runtime": 28.6158,
+      "eval_samples_per_second": 5.871,
+      "eval_steps_per_second": 0.734,
+      "step": 90
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 2.012698173522949,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.448,
+      "step": 91
+    },
+    {
+      "epoch": 0.46115288220551376,
+      "grad_norm": 2.5337393283843994,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3807,
+      "step": 92
+    },
+    {
+      "epoch": 0.46616541353383456,
+      "grad_norm": 2.5152134895324707,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.42,
+      "step": 93
+    },
+    {
+      "epoch": 0.47117794486215536,
+      "grad_norm": 2.0130863189697266,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.4192,
+      "step": 94
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.2953547239303589,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.3369,
+      "step": 95
+    },
+    {
+      "epoch": 0.48120300751879697,
+      "grad_norm": 7.441637992858887,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.4595,
+      "step": 96
+    },
+    {
+      "epoch": 0.48621553884711777,
+      "grad_norm": 2.2585561275482178,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.4148,
+      "step": 97
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 1.8977596759796143,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4021,
+      "step": 98
+    },
+    {
+      "epoch": 0.49624060150375937,
+      "grad_norm": 1.658085823059082,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.3434,
+      "step": 99
+    },
+    {
+      "epoch": 0.49624060150375937,
+      "eval_loss": 0.686565101146698,
+      "eval_runtime": 28.6385,
+      "eval_samples_per_second": 5.866,
+      "eval_steps_per_second": 0.733,
+      "step": 99
+    },
+    {
+      "epoch": 0.5012531328320802,
+      "grad_norm": 1.2815591096878052,
+      "learning_rate": 0.0,
+      "loss": 1.3255,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.887031545882214e+16,
+  "total_flos": 1.1729574724160717e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null