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:ddbea23fc692ada10a7c4a1dadd0ca03fc7f0c32566afb386439f690a6767c79
+oid sha256:42c2a5e8f9c7d0598c2c0f182980ce9b60b7e21d39cc84e412a8189667e1a99a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:994b544f5220ea4864750175b2ca55b2d26dcadeaccb7af24dc7f2f613306f5a
+oid sha256:3ba310e626d0b0862994eb72035c977a4789d9902b762e6647b7939c10f64ed1
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7ac41c92e00e6961fbf45d5a99d8298611815320bdf80a5f802ea50a5c3fc4
+oid sha256:3a7caefadf438d41c59ad8d0faf967b1312777403e79a3568ab308de998cceb6
 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": 0.02642240620045799,
+  "epoch": 0.035229874933943986,
   "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": 0.1668,
       "step": 75
+    },
+    {
+      "epoch": 0.026774704949797428,
+      "grad_norm": 0.4307248890399933,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1825,
+      "step": 76
+    },
+    {
+      "epoch": 0.027127003699136867,
+      "grad_norm": 0.5884014964103699,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.1886,
+      "step": 77
+    },
+    {
+      "epoch": 0.02747930244847631,
+      "grad_norm": 0.4084033668041229,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1692,
+      "step": 78
+    },
+    {
+      "epoch": 0.027831601197815747,
+      "grad_norm": 0.29296913743019104,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.1631,
+      "step": 79
+    },
+    {
+      "epoch": 0.028183899947155186,
+      "grad_norm": 0.29117217659950256,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1875,
+      "step": 80
+    },
+    {
+      "epoch": 0.028536198696494628,
+      "grad_norm": 0.24767440557479858,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.177,
+      "step": 81
+    },
+    {
+      "epoch": 0.028536198696494628,
+      "eval_loss": 0.17174069583415985,
+      "eval_runtime": 513.728,
+      "eval_samples_per_second": 4.654,
+      "eval_steps_per_second": 0.582,
+      "step": 81
+    },
+    {
+      "epoch": 0.028888497445834067,
+      "grad_norm": 0.2397385835647583,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1677,
+      "step": 82
+    },
+    {
+      "epoch": 0.02924079619517351,
+      "grad_norm": 0.3177073299884796,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.1818,
+      "step": 83
+    },
+    {
+      "epoch": 0.029593094944512947,
+      "grad_norm": 0.40429046750068665,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1904,
+      "step": 84
+    },
+    {
+      "epoch": 0.029945393693852386,
+      "grad_norm": 0.3296579420566559,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.155,
+      "step": 85
+    },
+    {
+      "epoch": 0.030297692443191828,
+      "grad_norm": 0.2939475476741791,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1764,
+      "step": 86
+    },
+    {
+      "epoch": 0.030649991192531267,
+      "grad_norm": 0.2700442671775818,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.1719,
+      "step": 87
+    },
+    {
+      "epoch": 0.031002289941870705,
+      "grad_norm": 0.27427229285240173,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1837,
+      "step": 88
+    },
+    {
+      "epoch": 0.03135458869121015,
+      "grad_norm": 0.2285013496875763,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1587,
+      "step": 89
+    },
+    {
+      "epoch": 0.031706887440549586,
+      "grad_norm": 0.25230032205581665,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.185,
+      "step": 90
+    },
+    {
+      "epoch": 0.031706887440549586,
+      "eval_loss": 0.17110635340213776,
+      "eval_runtime": 513.5332,
+      "eval_samples_per_second": 4.656,
+      "eval_steps_per_second": 0.582,
+      "step": 90
+    },
+    {
+      "epoch": 0.032059186189889025,
+      "grad_norm": 0.42755863070487976,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1821,
+      "step": 91
+    },
+    {
+      "epoch": 0.03241148493922846,
+      "grad_norm": 0.23349186778068542,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.158,
+      "step": 92
+    },
+    {
+      "epoch": 0.03276378368856791,
+      "grad_norm": 0.31822070479393005,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1498,
+      "step": 93
+    },
+    {
+      "epoch": 0.03311608243790735,
+      "grad_norm": 0.257592111825943,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1809,
+      "step": 94
+    },
+    {
+      "epoch": 0.033468381187246786,
+      "grad_norm": 0.3682272434234619,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2006,
+      "step": 95
+    },
+    {
+      "epoch": 0.033820679936586225,
+      "grad_norm": 0.25005558133125305,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1924,
+      "step": 96
+    },
+    {
+      "epoch": 0.03417297868592566,
+      "grad_norm": 0.23438604176044464,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.1602,
+      "step": 97
+    },
+    {
+      "epoch": 0.0345252774352651,
+      "grad_norm": 0.2923586666584015,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.1988,
+      "step": 98
+    },
+    {
+      "epoch": 0.03487757618460455,
+      "grad_norm": 0.652924656867981,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.1429,
+      "step": 99
+    },
+    {
+      "epoch": 0.03487757618460455,
+      "eval_loss": 0.1709044873714447,
+      "eval_runtime": 513.0575,
+      "eval_samples_per_second": 4.66,
+      "eval_steps_per_second": 0.583,
+      "step": 99
+    },
+    {
+      "epoch": 0.035229874933943986,
+      "grad_norm": 0.28639668226242065,
+      "learning_rate": 0.0,
+      "loss": 0.1806,
+      "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": 1.083155433998254e+17,
+  "total_flos": 1.4392613301072691e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null