Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d11ef5e2f0a512fc82286e9113b7cf3dee0a254ac28ef28b80f02c4d4804e36
+oid sha256:74e2112972ba3b03ef9cba4caff78577895a8f0b26d3e257a357d2067f4c6905
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9136fec5b27da9b62f00fd65e3f6865f61cc067496c8e2e2640b0a89f738a44
+oid sha256:a385fcaab36bce7590a3f5eeec5f1563b08706359e6b75fa531bac45645a3838
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b89dd38db98ad38a01577cdd46c96a298f4583db1a347ee24c5352fb1155451
+oid sha256:fde104bab0adc1cc90c60a95e124ce8958368abce247283c13e815fc5610de65
 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": 0.32397408207343414,
+  "epoch": 0.4319654427645788,
   "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": 0.0049,
       "step": 75
+    },
+    {
+      "epoch": 0.3282937365010799,
+      "grad_norm": 0.0329754464328289,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0014,
+      "step": 76
+    },
+    {
+      "epoch": 0.3326133909287257,
+      "grad_norm": 0.06644655019044876,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.005,
+      "step": 77
+    },
+    {
+      "epoch": 0.3369330453563715,
+      "grad_norm": 0.071534663438797,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0032,
+      "step": 78
+    },
+    {
+      "epoch": 0.3412526997840173,
+      "grad_norm": 0.048516895622015,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0039,
+      "step": 79
+    },
+    {
+      "epoch": 0.34557235421166305,
+      "grad_norm": 0.05907434597611427,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0029,
+      "step": 80
+    },
+    {
+      "epoch": 0.34989200863930886,
+      "grad_norm": 0.04661243036389351,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0039,
+      "step": 81
+    },
+    {
+      "epoch": 0.34989200863930886,
+      "eval_loss": 0.0029163085855543613,
+      "eval_runtime": 42.6384,
+      "eval_samples_per_second": 4.573,
+      "eval_steps_per_second": 0.586,
+      "step": 81
+    },
+    {
+      "epoch": 0.3542116630669546,
+      "grad_norm": 0.04970655217766762,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0035,
+      "step": 82
+    },
+    {
+      "epoch": 0.35853131749460043,
+      "grad_norm": 0.05986812338232994,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0069,
+      "step": 83
+    },
+    {
+      "epoch": 0.36285097192224625,
+      "grad_norm": 0.04365411773324013,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0029,
+      "step": 84
+    },
+    {
+      "epoch": 0.367170626349892,
+      "grad_norm": 0.13277940452098846,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0056,
+      "step": 85
+    },
+    {
+      "epoch": 0.3714902807775378,
+      "grad_norm": 0.05331737548112869,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0032,
+      "step": 86
+    },
+    {
+      "epoch": 0.3758099352051836,
+      "grad_norm": 0.034497883170843124,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0034,
+      "step": 87
+    },
+    {
+      "epoch": 0.3801295896328294,
+      "grad_norm": 0.024258598685264587,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0021,
+      "step": 88
+    },
+    {
+      "epoch": 0.38444924406047515,
+      "grad_norm": 0.06567387282848358,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0071,
+      "step": 89
+    },
+    {
+      "epoch": 0.38876889848812096,
+      "grad_norm": 0.05820886418223381,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.004,
+      "step": 90
+    },
+    {
+      "epoch": 0.38876889848812096,
+      "eval_loss": 0.002866251626983285,
+      "eval_runtime": 42.5996,
+      "eval_samples_per_second": 4.578,
+      "eval_steps_per_second": 0.587,
+      "step": 90
+    },
+    {
+      "epoch": 0.3930885529157667,
+      "grad_norm": 0.07091183215379715,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0051,
+      "step": 91
+    },
+    {
+      "epoch": 0.39740820734341253,
+      "grad_norm": 0.07214067131280899,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0031,
+      "step": 92
+    },
+    {
+      "epoch": 0.4017278617710583,
+      "grad_norm": 0.047936685383319855,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0033,
+      "step": 93
+    },
+    {
+      "epoch": 0.4060475161987041,
+      "grad_norm": 0.04225027561187744,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0041,
+      "step": 94
+    },
+    {
+      "epoch": 0.4103671706263499,
+      "grad_norm": 0.13431866466999054,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0038,
+      "step": 95
+    },
+    {
+      "epoch": 0.4146868250539957,
+      "grad_norm": 0.07035449892282486,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0038,
+      "step": 96
+    },
+    {
+      "epoch": 0.4190064794816415,
+      "grad_norm": 0.05573286861181259,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0036,
+      "step": 97
+    },
+    {
+      "epoch": 0.42332613390928725,
+      "grad_norm": 0.09693485498428345,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0048,
+      "step": 98
+    },
+    {
+      "epoch": 0.42764578833693306,
+      "grad_norm": 0.02684597484767437,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0014,
+      "step": 99
+    },
+    {
+      "epoch": 0.42764578833693306,
+      "eval_loss": 0.002881319960579276,
+      "eval_runtime": 42.5998,
+      "eval_samples_per_second": 4.577,
+      "eval_steps_per_second": 0.587,
+      "step": 99
+    },
+    {
+      "epoch": 0.4319654427645788,
+      "grad_norm": 0.02570461854338646,
+      "learning_rate": 0.0,
+      "loss": 0.0019,
+      "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": 1.097993179669463e+17,
+  "total_flos": 1.4652273850318848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null