Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24078c05ffeaae675fa9830d1921165a74963f089d8a8d99c0044b9c37deec5d
+oid sha256:74e097fa368423f449b70f66f4011d11a6df011dbfff5fb31c5326b25bc35cc0
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3782b9b8b6f387c3db7a99eb1e004849ac66770d039faf434deb2736d33d27
+oid sha256:bf83109ed8b89425e851b24c4e8b570f25bd9642ddb5566b08dbe77ef7183c9d
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
+oid sha256:7d54c917256fd085e20e49081e8a953eee303e2ee34f089b2a4112eb45771b1c
 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": 0.2912621359223301,
+  "epoch": 0.3883495145631068,
   "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": 0.3579,
       "step": 75
+    },
+    {
+      "epoch": 0.29514563106796116,
+      "grad_norm": 0.6754430532455444,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.5123,
+      "step": 76
+    },
+    {
+      "epoch": 0.29902912621359223,
+      "grad_norm": 0.5965986251831055,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.4017,
+      "step": 77
+    },
+    {
+      "epoch": 0.3029126213592233,
+      "grad_norm": 0.48246318101882935,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.4715,
+      "step": 78
+    },
+    {
+      "epoch": 0.3067961165048544,
+      "grad_norm": 0.5419760346412659,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.4695,
+      "step": 79
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.45284920930862427,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.4399,
+      "step": 80
+    },
+    {
+      "epoch": 0.3145631067961165,
+      "grad_norm": 0.7130292654037476,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.5745,
+      "step": 81
+    },
+    {
+      "epoch": 0.3145631067961165,
+      "eval_loss": 0.23767226934432983,
+      "eval_runtime": 44.6022,
+      "eval_samples_per_second": 4.865,
+      "eval_steps_per_second": 0.628,
+      "step": 81
+    },
+    {
+      "epoch": 0.31844660194174756,
+      "grad_norm": 0.3817744553089142,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4511,
+      "step": 82
+    },
+    {
+      "epoch": 0.32233009708737864,
+      "grad_norm": 0.634251058101654,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.4383,
+      "step": 83
+    },
+    {
+      "epoch": 0.3262135922330097,
+      "grad_norm": 0.7067334651947021,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.4136,
+      "step": 84
+    },
+    {
+      "epoch": 0.3300970873786408,
+      "grad_norm": 0.5049657225608826,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.554,
+      "step": 85
+    },
+    {
+      "epoch": 0.3339805825242718,
+      "grad_norm": 0.5423300862312317,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.3143,
+      "step": 86
+    },
+    {
+      "epoch": 0.3378640776699029,
+      "grad_norm": 0.4768480360507965,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.3825,
+      "step": 87
+    },
+    {
+      "epoch": 0.341747572815534,
+      "grad_norm": 0.7799291014671326,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.8646,
+      "step": 88
+    },
+    {
+      "epoch": 0.34563106796116505,
+      "grad_norm": 0.41830724477767944,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.4058,
+      "step": 89
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.5093135833740234,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4637,
+      "step": 90
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "eval_loss": 0.23714493215084076,
+      "eval_runtime": 44.6172,
+      "eval_samples_per_second": 4.864,
+      "eval_steps_per_second": 0.628,
+      "step": 90
+    },
+    {
+      "epoch": 0.3533980582524272,
+      "grad_norm": 0.452945351600647,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4256,
+      "step": 91
+    },
+    {
+      "epoch": 0.3572815533980582,
+      "grad_norm": 0.5537383556365967,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.4794,
+      "step": 92
+    },
+    {
+      "epoch": 0.3611650485436893,
+      "grad_norm": 0.4411360025405884,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3774,
+      "step": 93
+    },
+    {
+      "epoch": 0.3650485436893204,
+      "grad_norm": 0.6876885294914246,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.4972,
+      "step": 94
+    },
+    {
+      "epoch": 0.36893203883495146,
+      "grad_norm": 0.49587932229042053,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.5936,
+      "step": 95
+    },
+    {
+      "epoch": 0.37281553398058254,
+      "grad_norm": 0.4395916163921356,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.382,
+      "step": 96
+    },
+    {
+      "epoch": 0.3766990291262136,
+      "grad_norm": 0.4687136709690094,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.3412,
+      "step": 97
+    },
+    {
+      "epoch": 0.38058252427184464,
+      "grad_norm": 0.46291834115982056,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4535,
+      "step": 98
+    },
+    {
+      "epoch": 0.3844660194174757,
+      "grad_norm": 0.4477255940437317,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.3256,
+      "step": 99
+    },
+    {
+      "epoch": 0.3844660194174757,
+      "eval_loss": 0.23691868782043457,
+      "eval_runtime": 44.591,
+      "eval_samples_per_second": 4.866,
+      "eval_steps_per_second": 0.628,
+      "step": 99
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5534548759460449,
+      "learning_rate": 0.0,
+      "loss": 0.3636,
+      "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": 9.5217449435136e+16,
+  "total_flos": 1.26956599246848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null