Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63622b593e81d02a230cbe440c98aa3ffbee4770adb2b5badf6b0a7940fd33aa
+oid sha256:9a3cdb9c488614071cab79a58dd0956c2240dce6881c55c97d087a03320bdcf4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14b49805228d17ca45e8fc83ac243816a15ef14b15e62ed43299103295aae941
+oid sha256:d4aa1c8e9f9d53fcf3e1142c17df9fc0d9e70b60277951dc3a48b0d3249de318
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c2aeb48c97bc17fc16027c087a1f2b9b14a3b5da40e726c4c4179d5382c495
+oid sha256:91f22f8f8c0b9795081b2113cdf6c8de9bf9ffc844eac0cced0355cd972f7187
 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": 0.18404907975460122,
+  "epoch": 0.24539877300613497,
   "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": 0.0593,
       "step": 75
+    },
+    {
+      "epoch": 0.18650306748466258,
+      "grad_norm": 0.1609889268875122,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1074,
+      "step": 76
+    },
+    {
+      "epoch": 0.18895705521472392,
+      "grad_norm": 0.14295519888401031,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0724,
+      "step": 77
+    },
+    {
+      "epoch": 0.19141104294478528,
+      "grad_norm": 0.2733156681060791,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1378,
+      "step": 78
+    },
+    {
+      "epoch": 0.19386503067484662,
+      "grad_norm": 0.19158926606178284,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0873,
+      "step": 79
+    },
+    {
+      "epoch": 0.19631901840490798,
+      "grad_norm": 0.15549211204051971,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0799,
+      "step": 80
+    },
+    {
+      "epoch": 0.19877300613496932,
+      "grad_norm": 0.1473371535539627,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0927,
+      "step": 81
+    },
+    {
+      "epoch": 0.19877300613496932,
+      "eval_loss": 0.08084429800510406,
+      "eval_runtime": 72.2318,
+      "eval_samples_per_second": 4.749,
+      "eval_steps_per_second": 0.595,
+      "step": 81
+    },
+    {
+      "epoch": 0.20122699386503068,
+      "grad_norm": 0.18977564573287964,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0813,
+      "step": 82
+    },
+    {
+      "epoch": 0.20368098159509201,
+      "grad_norm": 0.19046197831630707,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0985,
+      "step": 83
+    },
+    {
+      "epoch": 0.20613496932515338,
+      "grad_norm": 0.2664346992969513,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1368,
+      "step": 84
+    },
+    {
+      "epoch": 0.2085889570552147,
+      "grad_norm": 0.15875068306922913,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0904,
+      "step": 85
+    },
+    {
+      "epoch": 0.21104294478527608,
+      "grad_norm": 0.141635924577713,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0763,
+      "step": 86
+    },
+    {
+      "epoch": 0.2134969325153374,
+      "grad_norm": 0.1432258039712906,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0752,
+      "step": 87
+    },
+    {
+      "epoch": 0.21595092024539878,
+      "grad_norm": 0.1705997735261917,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0682,
+      "step": 88
+    },
+    {
+      "epoch": 0.2184049079754601,
+      "grad_norm": 0.172316774725914,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0725,
+      "step": 89
+    },
+    {
+      "epoch": 0.22085889570552147,
+      "grad_norm": 0.14289115369319916,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.087,
+      "step": 90
+    },
+    {
+      "epoch": 0.22085889570552147,
+      "eval_loss": 0.07996805757284164,
+      "eval_runtime": 72.1848,
+      "eval_samples_per_second": 4.752,
+      "eval_steps_per_second": 0.596,
+      "step": 90
+    },
+    {
+      "epoch": 0.2233128834355828,
+      "grad_norm": 0.18413448333740234,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0918,
+      "step": 91
+    },
+    {
+      "epoch": 0.22576687116564417,
+      "grad_norm": 0.21855594217777252,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1008,
+      "step": 92
+    },
+    {
+      "epoch": 0.2282208588957055,
+      "grad_norm": 0.1916782408952713,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.089,
+      "step": 93
+    },
+    {
+      "epoch": 0.23067484662576687,
+      "grad_norm": 0.15419402718544006,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1061,
+      "step": 94
+    },
+    {
+      "epoch": 0.2331288343558282,
+      "grad_norm": 0.10309912264347076,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0595,
+      "step": 95
+    },
+    {
+      "epoch": 0.23558282208588957,
+      "grad_norm": 0.1862940937280655,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0664,
+      "step": 96
+    },
+    {
+      "epoch": 0.23803680981595093,
+      "grad_norm": 0.15097887814044952,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0872,
+      "step": 97
+    },
+    {
+      "epoch": 0.24049079754601227,
+      "grad_norm": 0.466399222612381,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0873,
+      "step": 98
+    },
+    {
+      "epoch": 0.24294478527607363,
+      "grad_norm": 0.12407394498586655,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0674,
+      "step": 99
+    },
+    {
+      "epoch": 0.24294478527607363,
+      "eval_loss": 0.07985200732946396,
+      "eval_runtime": 72.2547,
+      "eval_samples_per_second": 4.747,
+      "eval_steps_per_second": 0.595,
+      "step": 99
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.13656176626682281,
+      "learning_rate": 0.0,
+      "loss": 0.0659,
+      "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": 9.57034595792978e+16,
+  "total_flos": 1.283465000559575e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null