Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fcc0814a06ab50bd9f5bd4ab0d4012bca53db7273965b0000a948275f2cd930
+oid sha256:7aca078171d3e0bf4ca7ce23caf4c1dd4cd9db63033c7bc84ef50bb784d37c9b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2bc204bb074fe3ff52d2564f4ff4155d44288ce464ac0dd02f6b4b3e63f5cf6
+oid sha256:7da16e329eaf82af942b4435d225241258e4a48533c2d4c722280646ef67a96e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e06e459b7c667b4a6e7f8a6a5a204523d051f7ba92ae0b9c5a6c9461a833ce6b
+oid sha256:12d5e215f21fbf0d0fadcba9d9404c63f2d389e7deeb200582435d8a294f7182
 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": 0.06855575868372943,
+  "epoch": 0.09140767824497258,
   "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": 0.3559,
       "step": 75
+    },
+    {
+      "epoch": 0.06946983546617916,
+      "grad_norm": 0.6338186860084534,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.3529,
+      "step": 76
+    },
+    {
+      "epoch": 0.07038391224862889,
+      "grad_norm": 0.5978414416313171,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.3517,
+      "step": 77
+    },
+    {
+      "epoch": 0.0712979890310786,
+      "grad_norm": 0.8812351226806641,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.3446,
+      "step": 78
+    },
+    {
+      "epoch": 0.07221206581352833,
+      "grad_norm": 0.8271844387054443,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.3916,
+      "step": 79
+    },
+    {
+      "epoch": 0.07312614259597806,
+      "grad_norm": 0.7332054972648621,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3595,
+      "step": 80
+    },
+    {
+      "epoch": 0.0740402193784278,
+      "grad_norm": 0.7870144844055176,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.3366,
+      "step": 81
+    },
+    {
+      "epoch": 0.0740402193784278,
+      "eval_loss": 0.3669198155403137,
+      "eval_runtime": 100.9333,
+      "eval_samples_per_second": 9.135,
+      "eval_steps_per_second": 1.149,
+      "step": 81
+    },
+    {
+      "epoch": 0.07495429616087751,
+      "grad_norm": 0.6526699662208557,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3252,
+      "step": 82
+    },
+    {
+      "epoch": 0.07586837294332724,
+      "grad_norm": 0.9464435577392578,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.3584,
+      "step": 83
+    },
+    {
+      "epoch": 0.07678244972577697,
+      "grad_norm": 0.7502279877662659,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3397,
+      "step": 84
+    },
+    {
+      "epoch": 0.07769652650822668,
+      "grad_norm": 0.6392208933830261,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3404,
+      "step": 85
+    },
+    {
+      "epoch": 0.07861060329067641,
+      "grad_norm": 0.6176791787147522,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.354,
+      "step": 86
+    },
+    {
+      "epoch": 0.07952468007312614,
+      "grad_norm": 0.9151353240013123,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.3976,
+      "step": 87
+    },
+    {
+      "epoch": 0.08043875685557587,
+      "grad_norm": 0.6039880514144897,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.3456,
+      "step": 88
+    },
+    {
+      "epoch": 0.08135283363802559,
+      "grad_norm": 0.85297030210495,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.374,
+      "step": 89
+    },
+    {
+      "epoch": 0.08226691042047532,
+      "grad_norm": 0.6658338308334351,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.3806,
+      "step": 90
+    },
+    {
+      "epoch": 0.08226691042047532,
+      "eval_loss": 0.3671875596046448,
+      "eval_runtime": 100.9337,
+      "eval_samples_per_second": 9.135,
+      "eval_steps_per_second": 1.149,
+      "step": 90
+    },
+    {
+      "epoch": 0.08318098720292505,
+      "grad_norm": 0.7526385188102722,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3402,
+      "step": 91
+    },
+    {
+      "epoch": 0.08409506398537477,
+      "grad_norm": 0.7260336875915527,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3694,
+      "step": 92
+    },
+    {
+      "epoch": 0.0850091407678245,
+      "grad_norm": 0.6894639730453491,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3683,
+      "step": 93
+    },
+    {
+      "epoch": 0.08592321755027423,
+      "grad_norm": 0.8361942172050476,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3574,
+      "step": 94
+    },
+    {
+      "epoch": 0.08683729433272395,
+      "grad_norm": 0.6898833513259888,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3611,
+      "step": 95
+    },
+    {
+      "epoch": 0.08775137111517367,
+      "grad_norm": 0.7415781021118164,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.332,
+      "step": 96
+    },
+    {
+      "epoch": 0.0886654478976234,
+      "grad_norm": 0.6163707375526428,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.3423,
+      "step": 97
+    },
+    {
+      "epoch": 0.08957952468007313,
+      "grad_norm": 0.7453762888908386,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4035,
+      "step": 98
+    },
+    {
+      "epoch": 0.09049360146252285,
+      "grad_norm": 0.7190045714378357,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.3708,
+      "step": 99
+    },
+    {
+      "epoch": 0.09049360146252285,
+      "eval_loss": 0.3665288984775543,
+      "eval_runtime": 100.9185,
+      "eval_samples_per_second": 9.136,
+      "eval_steps_per_second": 1.149,
+      "step": 99
+    },
+    {
+      "epoch": 0.09140767824497258,
+      "grad_norm": 0.7005969285964966,
+      "learning_rate": 0.0,
+      "loss": 0.3717,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null