Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8b635e51da661003e3906fc8905a025b6fd44f77bfc78d1e9e1498e5999489
+oid sha256:adc73abdb1ab33a9de8a75d372fd2089045118120b9f1550f073edc6b2c89ffd
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7aaf12cdfa04d0ae2999f6d0b30db76c5e2d862ed3d28f7ceaafa20e82ef86f
+oid sha256:dc2309cdcb10bc44c3fb0f04419a1a37da55d9671d66186af0b9b3e8ffde89d0
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a797e4556a00e672702ff04c6ecce740fabaca58e7ff5b6ddf14351f843364
+oid sha256:c659e4505005131eab7ea0ee74ff9e2fee448c1f7e5a9dc766af93a6f64c72a6
 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": 0.26501766784452296,
+  "epoch": 0.35335689045936397,
   "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": 2.7848,
       "step": 75
+    },
+    {
+      "epoch": 0.26855123674911663,
+      "grad_norm": 3.0067617893218994,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.8053,
+      "step": 76
+    },
+    {
+      "epoch": 0.27208480565371024,
+      "grad_norm": 2.957212448120117,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.995,
+      "step": 77
+    },
+    {
+      "epoch": 0.2756183745583039,
+      "grad_norm": 3.0443437099456787,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.8389,
+      "step": 78
+    },
+    {
+      "epoch": 0.2791519434628975,
+      "grad_norm": 2.926431894302368,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.6296,
+      "step": 79
+    },
+    {
+      "epoch": 0.2826855123674912,
+      "grad_norm": 3.1932590007781982,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.9584,
+      "step": 80
+    },
+    {
+      "epoch": 0.2862190812720848,
+      "grad_norm": 2.9129207134246826,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.5164,
+      "step": 81
+    },
+    {
+      "epoch": 0.2862190812720848,
+      "eval_loss": 2.7381513118743896,
+      "eval_runtime": 7.0581,
+      "eval_samples_per_second": 33.862,
+      "eval_steps_per_second": 4.25,
+      "step": 81
+    },
+    {
+      "epoch": 0.28975265017667845,
+      "grad_norm": 3.224900722503662,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.9491,
+      "step": 82
+    },
+    {
+      "epoch": 0.29328621908127206,
+      "grad_norm": 3.0550365447998047,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.8272,
+      "step": 83
+    },
+    {
+      "epoch": 0.2968197879858657,
+      "grad_norm": 2.987809181213379,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.8986,
+      "step": 84
+    },
+    {
+      "epoch": 0.3003533568904594,
+      "grad_norm": 3.203158378601074,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.6763,
+      "step": 85
+    },
+    {
+      "epoch": 0.303886925795053,
+      "grad_norm": 3.269944906234741,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.9629,
+      "step": 86
+    },
+    {
+      "epoch": 0.30742049469964666,
+      "grad_norm": 2.876873254776001,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.4068,
+      "step": 87
+    },
+    {
+      "epoch": 0.31095406360424027,
+      "grad_norm": 3.159451723098755,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.7699,
+      "step": 88
+    },
+    {
+      "epoch": 0.31448763250883394,
+      "grad_norm": 3.1819095611572266,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.6741,
+      "step": 89
+    },
+    {
+      "epoch": 0.31802120141342755,
+      "grad_norm": 3.118530035018921,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.8377,
+      "step": 90
+    },
+    {
+      "epoch": 0.31802120141342755,
+      "eval_loss": 2.7339930534362793,
+      "eval_runtime": 7.0557,
+      "eval_samples_per_second": 33.873,
+      "eval_steps_per_second": 4.252,
+      "step": 90
+    },
+    {
+      "epoch": 0.3215547703180212,
+      "grad_norm": 3.266756772994995,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.7838,
+      "step": 91
+    },
+    {
+      "epoch": 0.3250883392226148,
+      "grad_norm": 3.0559535026550293,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.8555,
+      "step": 92
+    },
+    {
+      "epoch": 0.3286219081272085,
+      "grad_norm": 3.6161367893218994,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 3.0234,
+      "step": 93
+    },
+    {
+      "epoch": 0.3321554770318021,
+      "grad_norm": 3.071720838546753,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.7395,
+      "step": 94
+    },
+    {
+      "epoch": 0.33568904593639576,
+      "grad_norm": 2.7411324977874756,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.4974,
+      "step": 95
+    },
+    {
+      "epoch": 0.3392226148409894,
+      "grad_norm": 2.9565789699554443,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.521,
+      "step": 96
+    },
+    {
+      "epoch": 0.34275618374558303,
+      "grad_norm": 3.2165133953094482,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.8127,
+      "step": 97
+    },
+    {
+      "epoch": 0.3462897526501767,
+      "grad_norm": 2.9913384914398193,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.611,
+      "step": 98
+    },
+    {
+      "epoch": 0.3498233215547703,
+      "grad_norm": 3.2526886463165283,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.7723,
+      "step": 99
+    },
+    {
+      "epoch": 0.3498233215547703,
+      "eval_loss": 2.73214054107666,
+      "eval_runtime": 7.0659,
+      "eval_samples_per_second": 33.824,
+      "eval_steps_per_second": 4.246,
+      "step": 99
+    },
+    {
+      "epoch": 0.35335689045936397,
+      "grad_norm": 2.9997904300689697,
+      "learning_rate": 0.0,
+      "loss": 2.8974,
+      "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": 7257919271731200.0,
+  "total_flos": 9677225695641600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null