Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21db67b617bd0c63f02c2f0ce77952934a30c9defd8696c7cf82e411af0f50c1
+oid sha256:816b1a5e34c5cb5b663539e47906f4e5fc96b376e034c9a561a2789699c75b24
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905ef19be6dfb4decbe467bfe5bda65c31d645be15bc6cae7683d6f570fc70af
+oid sha256:a26e8a7fac6a8be9c9a7e13b9a15c51b166bdd47d82ebecf21b243d15ca3e538
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c5cddd493a4b86230f04b497049be55914d9d05da0f27259601800cf135f64
+oid sha256:013561f3e34c965d8030bf7c9709f234458212ee672ae1308999321f0a81a373
 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": 0.006743088334457181,
+  "epoch": 0.00899078444594291,
   "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": 9.1882,
       "step": 75
+    },
+    {
+      "epoch": 0.006832996178916611,
+      "grad_norm": 1.63014554977417,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 9.2502,
+      "step": 76
+    },
+    {
+      "epoch": 0.0069229040233760395,
+      "grad_norm": 1.7437061071395874,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 9.1878,
+      "step": 77
+    },
+    {
+      "epoch": 0.007012811867835468,
+      "grad_norm": 1.6178125143051147,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 9.2569,
+      "step": 78
+    },
+    {
+      "epoch": 0.007102719712294898,
+      "grad_norm": 1.6040529012680054,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 9.1846,
+      "step": 79
+    },
+    {
+      "epoch": 0.007192627556754327,
+      "grad_norm": 1.8354942798614502,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 9.1776,
+      "step": 80
+    },
+    {
+      "epoch": 0.0072825354012137555,
+      "grad_norm": 1.4767147302627563,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 9.1402,
+      "step": 81
+    },
+    {
+      "epoch": 0.0072825354012137555,
+      "eval_loss": 9.192564010620117,
+      "eval_runtime": 277.7377,
+      "eval_samples_per_second": 33.726,
+      "eval_steps_per_second": 4.216,
+      "step": 81
+    },
+    {
+      "epoch": 0.007372443245673185,
+      "grad_norm": 1.559671401977539,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 9.1816,
+      "step": 82
+    },
+    {
+      "epoch": 0.007462351090132614,
+      "grad_norm": 1.6311486959457397,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 9.1622,
+      "step": 83
+    },
+    {
+      "epoch": 0.007552258934592044,
+      "grad_norm": 1.6624658107757568,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 9.1878,
+      "step": 84
+    },
+    {
+      "epoch": 0.007642166779051472,
+      "grad_norm": 1.9123471975326538,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 9.2446,
+      "step": 85
+    },
+    {
+      "epoch": 0.007732074623510901,
+      "grad_norm": 1.486377477645874,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 9.1884,
+      "step": 86
+    },
+    {
+      "epoch": 0.00782198246797033,
+      "grad_norm": 1.8167918920516968,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 9.24,
+      "step": 87
+    },
+    {
+      "epoch": 0.007911890312429759,
+      "grad_norm": 1.5486295223236084,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 9.1895,
+      "step": 88
+    },
+    {
+      "epoch": 0.008001798156889188,
+      "grad_norm": 1.4490200281143188,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 9.1647,
+      "step": 89
+    },
+    {
+      "epoch": 0.008091706001348618,
+      "grad_norm": 2.019087314605713,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 9.2139,
+      "step": 90
+    },
+    {
+      "epoch": 0.008091706001348618,
+      "eval_loss": 9.17447566986084,
+      "eval_runtime": 276.6487,
+      "eval_samples_per_second": 33.859,
+      "eval_steps_per_second": 4.233,
+      "step": 90
+    },
+    {
+      "epoch": 0.008181613845808046,
+      "grad_norm": 1.5200148820877075,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 9.1678,
+      "step": 91
+    },
+    {
+      "epoch": 0.008271521690267476,
+      "grad_norm": 1.5171585083007812,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 9.1463,
+      "step": 92
+    },
+    {
+      "epoch": 0.008361429534726905,
+      "grad_norm": 1.630756139755249,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 9.1325,
+      "step": 93
+    },
+    {
+      "epoch": 0.008451337379186335,
+      "grad_norm": 1.8901387453079224,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 9.2067,
+      "step": 94
+    },
+    {
+      "epoch": 0.008541245223645763,
+      "grad_norm": 1.8213433027267456,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 9.1878,
+      "step": 95
+    },
+    {
+      "epoch": 0.008631153068105192,
+      "grad_norm": 1.5106817483901978,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 9.1789,
+      "step": 96
+    },
+    {
+      "epoch": 0.008721060912564622,
+      "grad_norm": 1.5052330493927002,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 9.1815,
+      "step": 97
+    },
+    {
+      "epoch": 0.00881096875702405,
+      "grad_norm": 1.592929482460022,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 9.201,
+      "step": 98
+    },
+    {
+      "epoch": 0.00890087660148348,
+      "grad_norm": 1.4926317930221558,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 9.1714,
+      "step": 99
+    },
+    {
+      "epoch": 0.00890087660148348,
+      "eval_loss": 9.171258926391602,
+      "eval_runtime": 277.9334,
+      "eval_samples_per_second": 33.702,
+      "eval_steps_per_second": 4.213,
+      "step": 99
+    },
+    {
+      "epoch": 0.00899078444594291,
+      "grad_norm": 1.5409609079360962,
+      "learning_rate": 0.0,
+      "loss": 9.153,
+      "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": 39909794512896.0,
+  "total_flos": 53348806950912.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null