Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c1377fb4a5dd252aa404ea5c5b1200d84b54bcbb288507527b716b7cf25f7c
+oid sha256:df2e89907be3e36dd411cb06ca5c0512bf90a404d764bb3922f715ba99c034de
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0806d8f17fa4f9c46c2702445d12114c2904201a6de24706c45b8c31a81ff0f
+oid sha256:e75d4d817427886f4bcf1c8cc9c38666b1cfad5f56f735a183bd39aa1ef686d0
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1d644a4a39d949387b662bdefaee2232811c755c916d4547d1e6e803c86cf5
+oid sha256:03234c59276a3926e42276e51b5f8ade5ed5a056f62f458d656d76b351955cf2
 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": 0.06315789473684211,
+  "epoch": 0.08421052631578947,
   "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": 0.6147,
       "step": 75
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.3419746458530426,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.6167,
+      "step": 76
+    },
+    {
+      "epoch": 0.0648421052631579,
+      "grad_norm": 0.7516468167304993,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.6367,
+      "step": 77
+    },
+    {
+      "epoch": 0.06568421052631579,
+      "grad_norm": 0.5556538105010986,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6365,
+      "step": 78
+    },
+    {
+      "epoch": 0.06652631578947368,
+      "grad_norm": 0.4769613742828369,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.63,
+      "step": 79
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.4179724454879761,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6188,
+      "step": 80
+    },
+    {
+      "epoch": 0.06821052631578947,
+      "grad_norm": 0.497568279504776,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.6318,
+      "step": 81
+    },
+    {
+      "epoch": 0.06821052631578947,
+      "eval_loss": 0.62742018699646,
+      "eval_runtime": 28.6954,
+      "eval_samples_per_second": 34.849,
+      "eval_steps_per_second": 4.356,
+      "step": 81
+    },
+    {
+      "epoch": 0.06905263157894737,
+      "grad_norm": 0.6568834781646729,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6382,
+      "step": 82
+    },
+    {
+      "epoch": 0.06989473684210526,
+      "grad_norm": 0.44247978925704956,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.6287,
+      "step": 83
+    },
+    {
+      "epoch": 0.07073684210526315,
+      "grad_norm": 0.48621073365211487,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6372,
+      "step": 84
+    },
+    {
+      "epoch": 0.07157894736842105,
+      "grad_norm": 0.493594765663147,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6298,
+      "step": 85
+    },
+    {
+      "epoch": 0.07242105263157894,
+      "grad_norm": 0.47130337357521057,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6161,
+      "step": 86
+    },
+    {
+      "epoch": 0.07326315789473684,
+      "grad_norm": 0.370483934879303,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.6283,
+      "step": 87
+    },
+    {
+      "epoch": 0.07410526315789474,
+      "grad_norm": 0.4378347098827362,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.6229,
+      "step": 88
+    },
+    {
+      "epoch": 0.07494736842105264,
+      "grad_norm": 0.5102152824401855,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.6225,
+      "step": 89
+    },
+    {
+      "epoch": 0.07578947368421053,
+      "grad_norm": 0.4649106562137604,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.6318,
+      "step": 90
+    },
+    {
+      "epoch": 0.07578947368421053,
+      "eval_loss": 0.6250188946723938,
+      "eval_runtime": 28.6886,
+      "eval_samples_per_second": 34.857,
+      "eval_steps_per_second": 4.357,
+      "step": 90
+    },
+    {
+      "epoch": 0.07663157894736843,
+      "grad_norm": 0.4687817692756653,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.6187,
+      "step": 91
+    },
+    {
+      "epoch": 0.07747368421052632,
+      "grad_norm": 0.369341641664505,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.6219,
+      "step": 92
+    },
+    {
+      "epoch": 0.07831578947368421,
+      "grad_norm": 0.41136807203292847,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.6191,
+      "step": 93
+    },
+    {
+      "epoch": 0.07915789473684211,
+      "grad_norm": 0.3214464485645294,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6222,
+      "step": 94
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4911435544490814,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.6334,
+      "step": 95
+    },
+    {
+      "epoch": 0.0808421052631579,
+      "grad_norm": 0.4080554246902466,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6431,
+      "step": 96
+    },
+    {
+      "epoch": 0.08168421052631579,
+      "grad_norm": 0.39761316776275635,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.6264,
+      "step": 97
+    },
+    {
+      "epoch": 0.08252631578947368,
+      "grad_norm": 0.42710548639297485,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.6246,
+      "step": 98
+    },
+    {
+      "epoch": 0.08336842105263158,
+      "grad_norm": 0.4810851812362671,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.6293,
+      "step": 99
+    },
+    {
+      "epoch": 0.08336842105263158,
+      "eval_loss": 0.6246677041053772,
+      "eval_runtime": 28.7191,
+      "eval_samples_per_second": 34.82,
+      "eval_steps_per_second": 4.352,
+      "step": 99
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.27740001678466797,
+      "learning_rate": 0.0,
+      "loss": 0.6241,
+      "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": 7720265790259200.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null