Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca05b2780b74e4e7d8de280f4b73b0b597a55d49680ce2db5389babfda9df2c
+oid sha256:1bb747da2c9651f4ece573771448013b48ef108437061f62c965925f212beb28
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85dba8cde9be2c87e1236e36bcce50410aafbffc210efd571267c15cb1381eea
+oid sha256:2d76a1cc5e6ef93f22cb294519dd5c8e85e1f41d39bc6973aafcd3c11297e425
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:489b4497ec7f9277cf751a521880c93e5b44897ecfec9448dd231290fcce5ec8
+oid sha256:d9df3c0957eb8a5ef2cbdd9c4268f95ef1f381ee4405e75387c4f68e82bc13a3
 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": 0.02439421044072207,
+  "epoch": 0.03252561392096276,
   "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": 1.012,
       "step": 75
+    },
+    {
+      "epoch": 0.024719466579931695,
+      "grad_norm": 0.4276930093765259,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.0689,
+      "step": 76
+    },
+    {
+      "epoch": 0.025044722719141325,
+      "grad_norm": 0.3671048581600189,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.2221,
+      "step": 77
+    },
+    {
+      "epoch": 0.02536997885835095,
+      "grad_norm": 0.3389880061149597,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.9975,
+      "step": 78
+    },
+    {
+      "epoch": 0.02569523499756058,
+      "grad_norm": 0.3353745639324188,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.9682,
+      "step": 79
+    },
+    {
+      "epoch": 0.026020491136770206,
+      "grad_norm": 0.3157464861869812,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.0898,
+      "step": 80
+    },
+    {
+      "epoch": 0.026345747275979835,
+      "grad_norm": 0.31050676107406616,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.9718,
+      "step": 81
+    },
+    {
+      "epoch": 0.026345747275979835,
+      "eval_loss": 0.5167155265808105,
+      "eval_runtime": 783.7942,
+      "eval_samples_per_second": 3.303,
+      "eval_steps_per_second": 0.413,
+      "step": 81
+    },
+    {
+      "epoch": 0.02667100341518946,
+      "grad_norm": 0.28341951966285706,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9535,
+      "step": 82
+    },
+    {
+      "epoch": 0.02699625955439909,
+      "grad_norm": 0.34261542558670044,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.0475,
+      "step": 83
+    },
+    {
+      "epoch": 0.027321515693608717,
+      "grad_norm": 0.2891163229942322,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.0398,
+      "step": 84
+    },
+    {
+      "epoch": 0.027646771832818346,
+      "grad_norm": 0.30140769481658936,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0461,
+      "step": 85
+    },
+    {
+      "epoch": 0.027972027972027972,
+      "grad_norm": 0.3153305947780609,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0026,
+      "step": 86
+    },
+    {
+      "epoch": 0.028297284111237598,
+      "grad_norm": 0.2923007905483246,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.0061,
+      "step": 87
+    },
+    {
+      "epoch": 0.028622540250447227,
+      "grad_norm": 0.310686856508255,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.0761,
+      "step": 88
+    },
+    {
+      "epoch": 0.028947796389656853,
+      "grad_norm": 0.3076779544353485,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.0248,
+      "step": 89
+    },
+    {
+      "epoch": 0.029273052528866483,
+      "grad_norm": 0.3605354130268097,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.0372,
+      "step": 90
+    },
+    {
+      "epoch": 0.029273052528866483,
+      "eval_loss": 0.5154066681861877,
+      "eval_runtime": 783.8332,
+      "eval_samples_per_second": 3.303,
+      "eval_steps_per_second": 0.413,
+      "step": 90
+    },
+    {
+      "epoch": 0.02959830866807611,
+      "grad_norm": 0.34296754002571106,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.9784,
+      "step": 91
+    },
+    {
+      "epoch": 0.029923564807285738,
+      "grad_norm": 0.283575177192688,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.8804,
+      "step": 92
+    },
+    {
+      "epoch": 0.030248820946495364,
+      "grad_norm": 0.3156563639640808,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.0238,
+      "step": 93
+    },
+    {
+      "epoch": 0.030574077085704993,
+      "grad_norm": 0.30818790197372437,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.9902,
+      "step": 94
+    },
+    {
+      "epoch": 0.03089933322491462,
+      "grad_norm": 0.3115820586681366,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.9174,
+      "step": 95
+    },
+    {
+      "epoch": 0.03122458936412425,
+      "grad_norm": 0.305444598197937,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.9995,
+      "step": 96
+    },
+    {
+      "epoch": 0.031549845503333875,
+      "grad_norm": 0.37256306409835815,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.9834,
+      "step": 97
+    },
+    {
+      "epoch": 0.0318751016425435,
+      "grad_norm": 0.32575827836990356,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.0356,
+      "step": 98
+    },
+    {
+      "epoch": 0.03220035778175313,
+      "grad_norm": 0.4277135133743286,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0836,
+      "step": 99
+    },
+    {
+      "epoch": 0.03220035778175313,
+      "eval_loss": 0.5151550769805908,
+      "eval_runtime": 784.0298,
+      "eval_samples_per_second": 3.302,
+      "eval_steps_per_second": 0.413,
+      "step": 99
+    },
+    {
+      "epoch": 0.03252561392096276,
+      "grad_norm": 0.35957303643226624,
+      "learning_rate": 0.0,
+      "loss": 1.0562,
+      "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": 1.8154793692299264e+17,
+  "total_flos": 2.4502623654641664e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null