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:d59c541daad881a2bcf7c3fa2df078c9fee46add5727a0a9d5b906b61ff6de3b
+oid sha256:4bd41d1756d38ccd84aef0735381137e73cb8bef8850c7b27e6059baceae6a1b
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2267d7748a41531488b101470ffa97098788692fcf734acfe416020f1c2ccc
+oid sha256:8723c7c8b81dc4396ff39f6405b11677d7ba1e4e6edc10845bc4f2f10f43fbbb
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
+oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
 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": 0.0015885959988562108,
+  "epoch": 0.0021181279984749477,
   "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": 10.3904,
       "step": 75
+    },
+    {
+      "epoch": 0.0016097772788409603,
+      "grad_norm": 0.33791688084602356,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3546,
+      "step": 76
+    },
+    {
+      "epoch": 0.00163095855882571,
+      "grad_norm": 0.32664117217063904,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3715,
+      "step": 77
+    },
+    {
+      "epoch": 0.0016521398388104594,
+      "grad_norm": 0.3056585192680359,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3574,
+      "step": 78
+    },
+    {
+      "epoch": 0.0016733211187952089,
+      "grad_norm": 0.31749436259269714,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.369,
+      "step": 79
+    },
+    {
+      "epoch": 0.0016945023987799583,
+      "grad_norm": 0.3024196922779083,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3541,
+      "step": 80
+    },
+    {
+      "epoch": 0.0017156836787647078,
+      "grad_norm": 0.31615588068962097,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3619,
+      "step": 81
+    },
+    {
+      "epoch": 0.0017156836787647078,
+      "eval_loss": 10.351547241210938,
+      "eval_runtime": 263.9177,
+      "eval_samples_per_second": 150.645,
+      "eval_steps_per_second": 18.832,
+      "step": 81
+    },
+    {
+      "epoch": 0.0017368649587494573,
+      "grad_norm": 0.302412748336792,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3478,
+      "step": 82
+    },
+    {
+      "epoch": 0.0017580462387342068,
+      "grad_norm": 0.34448879957199097,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.333,
+      "step": 83
+    },
+    {
+      "epoch": 0.0017792275187189562,
+      "grad_norm": 0.2946290075778961,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3425,
+      "step": 84
+    },
+    {
+      "epoch": 0.0018004087987037057,
+      "grad_norm": 0.3481883406639099,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.33,
+      "step": 85
+    },
+    {
+      "epoch": 0.0018215900786884552,
+      "grad_norm": 0.3070729970932007,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3511,
+      "step": 86
+    },
+    {
+      "epoch": 0.0018427713586732046,
+      "grad_norm": 0.3426555395126343,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3715,
+      "step": 87
+    },
+    {
+      "epoch": 0.001863952638657954,
+      "grad_norm": 0.3272855579853058,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3723,
+      "step": 88
+    },
+    {
+      "epoch": 0.0018851339186427036,
+      "grad_norm": 0.3252405524253845,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3478,
+      "step": 89
+    },
+    {
+      "epoch": 0.001906315198627453,
+      "grad_norm": 0.3317711651325226,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3445,
+      "step": 90
+    },
+    {
+      "epoch": 0.001906315198627453,
+      "eval_loss": 10.350534439086914,
+      "eval_runtime": 264.5384,
+      "eval_samples_per_second": 150.292,
+      "eval_steps_per_second": 18.787,
+      "step": 90
+    },
+    {
+      "epoch": 0.0019274964786122025,
+      "grad_norm": 0.3351341187953949,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3455,
+      "step": 91
+    },
+    {
+      "epoch": 0.001948677758596952,
+      "grad_norm": 0.31914907693862915,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3619,
+      "step": 92
+    },
+    {
+      "epoch": 0.0019698590385817017,
+      "grad_norm": 0.31719982624053955,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3511,
+      "step": 93
+    },
+    {
+      "epoch": 0.001991040318566451,
+      "grad_norm": 0.3255273699760437,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3649,
+      "step": 94
+    },
+    {
+      "epoch": 0.0020122215985512006,
+      "grad_norm": 0.3029558062553406,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3522,
+      "step": 95
+    },
+    {
+      "epoch": 0.00203340287853595,
+      "grad_norm": 0.3137965500354767,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.33,
+      "step": 96
+    },
+    {
+      "epoch": 0.0020545841585206995,
+      "grad_norm": 0.3334927558898926,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3613,
+      "step": 97
+    },
+    {
+      "epoch": 0.0020757654385054488,
+      "grad_norm": 0.31634390354156494,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3522,
+      "step": 98
+    },
+    {
+      "epoch": 0.0020969467184901985,
+      "grad_norm": 0.28614795207977295,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3672,
+      "step": 99
+    },
+    {
+      "epoch": 0.0020969467184901985,
+      "eval_loss": 10.350330352783203,
+      "eval_runtime": 264.4391,
+      "eval_samples_per_second": 150.348,
+      "eval_steps_per_second": 18.795,
+      "step": 99
+    },
+    {
+      "epoch": 0.0021181279984749477,
+      "grad_norm": 0.31697142124176025,
+      "learning_rate": 0.0,
+      "loss": 10.3324,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null