Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e6e1f47a7c01ef37762658f2562a130b4969acfdc6cdaeae0892faccf6e306
+oid sha256:53deb37127a125a516c24cfecfdd95a0fb7fc40ab6c678b3e447de72c46a15b1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af035ac60441adec8aaf248768c8462992cd4faa60bcfff3cfd45ad8a1bb7ca0
+oid sha256:2cb9219fd50bae67a66f358153b9ba5347e34cee1d0f032ed123d3d4d8db8a6c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02cb420ffbe4bfa74ec929339f92e110525992fececf073c0ca01e03bfa1c21
+oid sha256:c3e51f0892642659ee075abf30df87bb913beb2a496960de104ce5ee219bf24b
 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": 0.5681818181818182,
+  "epoch": 0.7575757575757576,
   "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": 2.2534,
       "step": 75
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 0.800731897354126,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.1962,
+      "step": 76
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 1.328644871711731,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.9807,
+      "step": 77
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 0.8191350102424622,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.4639,
+      "step": 78
+    },
+    {
+      "epoch": 0.5984848484848485,
+      "grad_norm": 0.5501161813735962,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.1417,
+      "step": 79
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.7732625603675842,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2572,
+      "step": 80
+    },
+    {
+      "epoch": 0.6136363636363636,
+      "grad_norm": 0.6892921924591064,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.7751,
+      "step": 81
+    },
+    {
+      "epoch": 0.6136363636363636,
+      "eval_loss": 1.369916319847107,
+      "eval_runtime": 19.3375,
+      "eval_samples_per_second": 5.74,
+      "eval_steps_per_second": 0.724,
+      "step": 81
+    },
+    {
+      "epoch": 0.6212121212121212,
+      "grad_norm": 1.181936264038086,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2691,
+      "step": 82
+    },
+    {
+      "epoch": 0.6287878787878788,
+      "grad_norm": 0.7323097586631775,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.6584,
+      "step": 83
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 0.7199958562850952,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.7934,
+      "step": 84
+    },
+    {
+      "epoch": 0.6439393939393939,
+      "grad_norm": 0.8555872440338135,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1115,
+      "step": 85
+    },
+    {
+      "epoch": 0.6515151515151515,
+      "grad_norm": 2.019829273223877,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.8878,
+      "step": 86
+    },
+    {
+      "epoch": 0.6590909090909091,
+      "grad_norm": 0.8559478521347046,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5928,
+      "step": 87
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.7166076898574829,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.0765,
+      "step": 88
+    },
+    {
+      "epoch": 0.6742424242424242,
+      "grad_norm": 1.0768568515777588,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.433,
+      "step": 89
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 0.49354344606399536,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5407,
+      "step": 90
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "eval_loss": 1.3689146041870117,
+      "eval_runtime": 19.357,
+      "eval_samples_per_second": 5.734,
+      "eval_steps_per_second": 0.723,
+      "step": 90
+    },
+    {
+      "epoch": 0.6893939393939394,
+      "grad_norm": 0.9388372898101807,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.7335,
+      "step": 91
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 0.6668951511383057,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.2305,
+      "step": 92
+    },
+    {
+      "epoch": 0.7045454545454546,
+      "grad_norm": 0.8792560696601868,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.6706,
+      "step": 93
+    },
+    {
+      "epoch": 0.7121212121212122,
+      "grad_norm": 2.2188658714294434,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.3394,
+      "step": 94
+    },
+    {
+      "epoch": 0.7196969696969697,
+      "grad_norm": 0.9161637425422668,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.4869,
+      "step": 95
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.8342282176017761,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.2971,
+      "step": 96
+    },
+    {
+      "epoch": 0.7348484848484849,
+      "grad_norm": 0.7071769833564758,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.9304,
+      "step": 97
+    },
+    {
+      "epoch": 0.7424242424242424,
+      "grad_norm": 0.7601919174194336,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.2886,
+      "step": 98
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.9548859596252441,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.6156,
+      "step": 99
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.368682861328125,
+      "eval_runtime": 19.3511,
+      "eval_samples_per_second": 5.736,
+      "eval_steps_per_second": 0.723,
+      "step": 99
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 0.7403035759925842,
+      "learning_rate": 0.0,
+      "loss": 1.2176,
+      "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": 9.90419523553198e+16,
+  "total_flos": 1.327978237573202e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null