Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369a9fc237a5c7f6cc1f54de33d98f41238e58f2c3eb5548a8ec14c776a841bd
+oid sha256:a0a7edb94196091d8a10d824661f7ea71ff713f7b15ddce3438f7fa7f3998616
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e5a48ca90eefbb8355aa35d3835606ae62005ee672a04e3c9be2d3013ef078
+oid sha256:3fcdfb23c785e7a941fbece28d914bc3f5dd033b7b2c8d73f9ac90879f11bc97
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e81497461b7eddb6cf48b4fb01e48dcac128bf74d88043318d66719e95e04e
+oid sha256:20e61bca42eb5141e64d65b5c0909b4ba98b55dfcfc5f5a633461dab73519204
 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": 0.2086230876216968,
+  "epoch": 0.27816411682892905,
   "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": 0.0,
       "step": 75
+    },
+    {
+      "epoch": 0.2114047287899861,
+      "grad_norm": 1.0794195986818522e-05,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.2141863699582754,
+      "grad_norm": 6.09993512625806e-05,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.21696801112656466,
+      "grad_norm": 1.4044430827198084e-05,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.21974965229485396,
+      "grad_norm": 1.1747451026167255e-05,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.22253129346314326,
+      "grad_norm": 1.2638842235901393e-05,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.22531293463143254,
+      "grad_norm": 1.3892581591790076e-05,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.22531293463143254,
+      "eval_loss": 0.003094213781878352,
+      "eval_runtime": 65.5512,
+      "eval_samples_per_second": 4.622,
+      "eval_steps_per_second": 0.58,
+      "step": 81
+    },
+    {
+      "epoch": 0.22809457579972184,
+      "grad_norm": 0.00011207773059140891,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.23087621696801114,
+      "grad_norm": 3.354518048581667e-05,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.2336578581363004,
+      "grad_norm": 5.909705214435235e-05,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.2364394993045897,
+      "grad_norm": 6.752560148015618e-05,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.23922114047287898,
+      "grad_norm": 5.754792709922185e-06,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.24200278164116829,
+      "grad_norm": 1.0329221368010622e-05,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.24478442280945759,
+      "grad_norm": 1.6644171410007402e-05,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.24756606397774686,
+      "grad_norm": 2.0343353753560223e-05,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.25034770514603616,
+      "grad_norm": 1.7435373592888936e-05,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.25034770514603616,
+      "eval_loss": 0.002837944542989135,
+      "eval_runtime": 65.51,
+      "eval_samples_per_second": 4.625,
+      "eval_steps_per_second": 0.58,
+      "step": 90
+    },
+    {
+      "epoch": 0.25312934631432543,
+      "grad_norm": 3.190342613379471e-05,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.25591098748261476,
+      "grad_norm": 1.1693891792674549e-05,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.25869262865090403,
+      "grad_norm": 2.0059831513208337e-05,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.2614742698191933,
+      "grad_norm": 0.00017091452900785953,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.26425591098748263,
+      "grad_norm": 10.93679141998291,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1123,
+      "step": 95
+    },
+    {
+      "epoch": 0.2670375521557719,
+      "grad_norm": 1.3947700608696323e-05,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.2698191933240612,
+      "grad_norm": 0.3040238618850708,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0006,
+      "step": 97
+    },
+    {
+      "epoch": 0.2726008344923505,
+      "grad_norm": 0.0006167896208353341,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.2753824756606398,
+      "grad_norm": 0.04959489405155182,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0001,
+      "step": 99
+    },
+    {
+      "epoch": 0.2753824756606398,
+      "eval_loss": 0.002340545877814293,
+      "eval_runtime": 65.5113,
+      "eval_samples_per_second": 4.625,
+      "eval_steps_per_second": 0.58,
+      "step": 99
+    },
+    {
+      "epoch": 0.27816411682892905,
+      "grad_norm": 8.745052582526114e-06,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "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": 1.0905743068338586e+17,
+  "total_flos": 1.4466802029428736e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null