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:d98f52ea9e3b4f5493caa758d4f5fde320b07d26e631a62d06b30efdb375999a
+oid sha256:88c54e31db2504f5ba98ca7a326fcf85dbf5f93bff5ed61f422760c8a6da2b08
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea55249602bec4a7f78154c7173c8d40a8529f23d77824a36381cae980615f5a
+oid sha256:0d9328fe7ac61302449260cfede2e96da43a1f2bc71231ad3924cc331c5ba3d3
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
+oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
 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": 0.0024627306757732973,
+  "epoch": 0.003283640901031063,
   "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": 10.3707,
       "step": 75
+    },
+    {
+      "epoch": 0.0024955670847836083,
+      "grad_norm": 0.05032104626297951,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3751,
+      "step": 76
+    },
+    {
+      "epoch": 0.0025284034937939188,
+      "grad_norm": 0.06600265204906464,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3799,
+      "step": 77
+    },
+    {
+      "epoch": 0.0025612399028042293,
+      "grad_norm": 0.05626071244478226,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3706,
+      "step": 78
+    },
+    {
+      "epoch": 0.0025940763118145397,
+      "grad_norm": 0.04748469963669777,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.369,
+      "step": 79
+    },
+    {
+      "epoch": 0.0026269127208248507,
+      "grad_norm": 0.04868736118078232,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3713,
+      "step": 80
+    },
+    {
+      "epoch": 0.002659749129835161,
+      "grad_norm": 0.04755145311355591,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3695,
+      "step": 81
+    },
+    {
+      "epoch": 0.002659749129835161,
+      "eval_loss": 10.370580673217773,
+      "eval_runtime": 170.173,
+      "eval_samples_per_second": 150.705,
+      "eval_steps_per_second": 18.84,
+      "step": 81
+    },
+    {
+      "epoch": 0.0026925855388454717,
+      "grad_norm": 0.04993366450071335,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3709,
+      "step": 82
+    },
+    {
+      "epoch": 0.0027254219478557826,
+      "grad_norm": 0.047633569687604904,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3658,
+      "step": 83
+    },
+    {
+      "epoch": 0.002758258356866093,
+      "grad_norm": 0.049595627933740616,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3725,
+      "step": 84
+    },
+    {
+      "epoch": 0.0027910947658764036,
+      "grad_norm": 0.04706868901848793,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3715,
+      "step": 85
+    },
+    {
+      "epoch": 0.0028239311748867145,
+      "grad_norm": 0.047884490340948105,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.364,
+      "step": 86
+    },
+    {
+      "epoch": 0.002856767583897025,
+      "grad_norm": 0.04975724220275879,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3678,
+      "step": 87
+    },
+    {
+      "epoch": 0.0028896039929073355,
+      "grad_norm": 0.052582498639822006,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3702,
+      "step": 88
+    },
+    {
+      "epoch": 0.0029224404019176464,
+      "grad_norm": 0.05560288950800896,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3735,
+      "step": 89
+    },
+    {
+      "epoch": 0.002955276810927957,
+      "grad_norm": 0.061860982328653336,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3729,
+      "step": 90
+    },
+    {
+      "epoch": 0.002955276810927957,
+      "eval_loss": 10.370454788208008,
+      "eval_runtime": 170.5443,
+      "eval_samples_per_second": 150.377,
+      "eval_steps_per_second": 18.799,
+      "step": 90
+    },
+    {
+      "epoch": 0.0029881132199382674,
+      "grad_norm": 0.0577683299779892,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3711,
+      "step": 91
+    },
+    {
+      "epoch": 0.0030209496289485783,
+      "grad_norm": 0.05124616622924805,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3703,
+      "step": 92
+    },
+    {
+      "epoch": 0.003053786037958889,
+      "grad_norm": 0.052736300975084305,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3715,
+      "step": 93
+    },
+    {
+      "epoch": 0.0030866224469691993,
+      "grad_norm": 0.05762464180588722,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3688,
+      "step": 94
+    },
+    {
+      "epoch": 0.0031194588559795102,
+      "grad_norm": 0.0635187178850174,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3695,
+      "step": 95
+    },
+    {
+      "epoch": 0.0031522952649898207,
+      "grad_norm": 0.05708334967494011,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.366,
+      "step": 96
+    },
+    {
+      "epoch": 0.003185131674000131,
+      "grad_norm": 0.05262709781527519,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3671,
+      "step": 97
+    },
+    {
+      "epoch": 0.003217968083010442,
+      "grad_norm": 0.06074366718530655,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3769,
+      "step": 98
+    },
+    {
+      "epoch": 0.0032508044920207526,
+      "grad_norm": 0.04959198087453842,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3706,
+      "step": 99
+    },
+    {
+      "epoch": 0.0032508044920207526,
+      "eval_loss": 10.370431900024414,
+      "eval_runtime": 170.5901,
+      "eval_samples_per_second": 150.337,
+      "eval_steps_per_second": 18.794,
+      "step": 99
+    },
+    {
+      "epoch": 0.003283640901031063,
+      "grad_norm": 0.050457920879125595,
+      "learning_rate": 0.0,
+      "loss": 10.375,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null