Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df15b5d017c655dcc53f769a573f68e743f57472aec092b2cfebdf79c4b233f
+oid sha256:7ee93c022f8ffc3acce2277304bf58df4df22be26d6abf74a5f3c20bafe90046
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea59b6c0f2e53cd901c8ce6f3413b1f6907dfa9edf465c65d1e14d981c158b4
+oid sha256:58e6129f935b6e1eb106a4d35b353cecba548d9909665a3ed5a8128bafce50d7
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a2e2e612d77d97a4b0242765fede790a34f933ba010ba697d2e1fc9aa07c4b
+oid sha256:2e33ec2d279a54b31bcbd59efbda4ed3412f13129417ee23eb1d555b2fb4c15c
 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": 0.6284367635506677,
+  "epoch": 0.8379156847342236,
   "eval_steps": 50,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -548,6 +548,189 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 2.5932,
       "step": 75
+    },
+    {
+      "epoch": 0.6368159203980099,
+      "grad_norm": 0.42463499307632446,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.4165,
+      "step": 76
+    },
+    {
+      "epoch": 0.6451950772453522,
+      "grad_norm": 0.5442836284637451,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.5349,
+      "step": 77
+    },
+    {
+      "epoch": 0.6535742340926944,
+      "grad_norm": 0.40604889392852783,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.4106,
+      "step": 78
+    },
+    {
+      "epoch": 0.6619533909400367,
+      "grad_norm": 0.4163293242454529,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.3373,
+      "step": 79
+    },
+    {
+      "epoch": 0.6703325477873789,
+      "grad_norm": 0.48656710982322693,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.5337,
+      "step": 80
+    },
+    {
+      "epoch": 0.6787117046347211,
+      "grad_norm": 0.4434641897678375,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.4307,
+      "step": 81
+    },
+    {
+      "epoch": 0.6870908614820633,
+      "grad_norm": 0.4347304105758667,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.3949,
+      "step": 82
+    },
+    {
+      "epoch": 0.6954700183294056,
+      "grad_norm": 0.4212183952331543,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.3767,
+      "step": 83
+    },
+    {
+      "epoch": 0.7038491751767478,
+      "grad_norm": 0.44238415360450745,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.612,
+      "step": 84
+    },
+    {
+      "epoch": 0.7122283320240901,
+      "grad_norm": 0.44845736026763916,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2322,
+      "step": 85
+    },
+    {
+      "epoch": 0.7206074888714323,
+      "grad_norm": 0.4716636836528778,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.5347,
+      "step": 86
+    },
+    {
+      "epoch": 0.7289866457187746,
+      "grad_norm": 0.5085580945014954,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.4772,
+      "step": 87
+    },
+    {
+      "epoch": 0.7373658025661168,
+      "grad_norm": 0.455152302980423,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.3143,
+      "step": 88
+    },
+    {
+      "epoch": 0.745744959413459,
+      "grad_norm": 0.48934170603752136,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.3811,
+      "step": 89
+    },
+    {
+      "epoch": 0.7541241162608012,
+      "grad_norm": 0.4595421552658081,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.4414,
+      "step": 90
+    },
+    {
+      "epoch": 0.7625032731081435,
+      "grad_norm": 0.5183727741241455,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.5257,
+      "step": 91
+    },
+    {
+      "epoch": 0.7708824299554857,
+      "grad_norm": 0.42374536395072937,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.4218,
+      "step": 92
+    },
+    {
+      "epoch": 0.779261586802828,
+      "grad_norm": 0.45261675119400024,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.4601,
+      "step": 93
+    },
+    {
+      "epoch": 0.7876407436501702,
+      "grad_norm": 0.4387091100215912,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.5303,
+      "step": 94
+    },
+    {
+      "epoch": 0.7960199004975125,
+      "grad_norm": 0.42841577529907227,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.3097,
+      "step": 95
+    },
+    {
+      "epoch": 0.8043990573448547,
+      "grad_norm": 0.47183293104171753,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.4747,
+      "step": 96
+    },
+    {
+      "epoch": 0.8127782141921969,
+      "grad_norm": 0.5696967840194702,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.4984,
+      "step": 97
+    },
+    {
+      "epoch": 0.8211573710395391,
+      "grad_norm": 0.4509386718273163,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.2953,
+      "step": 98
+    },
+    {
+      "epoch": 0.8295365278868814,
+      "grad_norm": 0.5444111227989197,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.5414,
+      "step": 99
+    },
+    {
+      "epoch": 0.8379156847342236,
+      "grad_norm": 0.4556747078895569,
+      "learning_rate": 0.0,
+      "loss": 2.4252,
+      "step": 100
+    },
+    {
+      "epoch": 0.8379156847342236,
+      "eval_loss": 2.5602805614471436,
+      "eval_runtime": 45.2034,
+      "eval_samples_per_second": 4.469,
+      "eval_steps_per_second": 4.469,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -562,12 +745,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.88624772612096e+16,
+  "total_flos": 6.51499696816128e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null