Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6cccfc9518afa0fdc33a7ea0aaaef064c976c628408a5a2b59dc210fc1c161
+oid sha256:7f7600b18bc8dc264c8df33d9f594711f6b1fa371c50b1f37d642784ff7f76dd
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54cfa3242ed178d00bf7e0e3fc3ec8ee0289f082799ba2db53b5fd90088d3dda
+oid sha256:a998b4a67e8ae554e22b0a0e22cbf45531e77ca77f7bb4e48310262f9dde646a
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20bd7f9e98977739901deb4ac065306087d350d274dcb68e6b2fdb27bdb7adc
+oid sha256:cf565884214ee278bbefbf6bc5a913933f13b1065cb796aba188d64236b6fe21
 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": 0.013501350135013501,
+  "epoch": 0.018001800180018002,
   "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": 8.8277,
       "step": 75
+    },
+    {
+      "epoch": 0.013681368136813681,
+      "grad_norm": 4.766935348510742,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 9.1841,
+      "step": 76
+    },
+    {
+      "epoch": 0.013861386138613862,
+      "grad_norm": 3.851850986480713,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 9.1235,
+      "step": 77
+    },
+    {
+      "epoch": 0.014041404140414042,
+      "grad_norm": 4.168645858764648,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 8.9935,
+      "step": 78
+    },
+    {
+      "epoch": 0.014221422142214222,
+      "grad_norm": 4.831826210021973,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 8.9272,
+      "step": 79
+    },
+    {
+      "epoch": 0.0144014401440144,
+      "grad_norm": 4.024872779846191,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 9.0397,
+      "step": 80
+    },
+    {
+      "epoch": 0.014581458145814581,
+      "grad_norm": 4.845215797424316,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 9.3672,
+      "step": 81
+    },
+    {
+      "epoch": 0.014581458145814581,
+      "eval_loss": 9.021185874938965,
+      "eval_runtime": 41.5093,
+      "eval_samples_per_second": 112.698,
+      "eval_steps_per_second": 14.093,
+      "step": 81
+    },
+    {
+      "epoch": 0.014761476147614761,
+      "grad_norm": 4.619018077850342,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 8.9587,
+      "step": 82
+    },
+    {
+      "epoch": 0.014941494149414942,
+      "grad_norm": 4.925379276275635,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 9.0123,
+      "step": 83
+    },
+    {
+      "epoch": 0.015121512151215122,
+      "grad_norm": 4.891155242919922,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 9.1269,
+      "step": 84
+    },
+    {
+      "epoch": 0.0153015301530153,
+      "grad_norm": 5.3043365478515625,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 9.0393,
+      "step": 85
+    },
+    {
+      "epoch": 0.015481548154815481,
+      "grad_norm": 4.2021026611328125,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 9.1264,
+      "step": 86
+    },
+    {
+      "epoch": 0.015661566156615663,
+      "grad_norm": 4.361050605773926,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 8.5332,
+      "step": 87
+    },
+    {
+      "epoch": 0.015841584158415842,
+      "grad_norm": 4.473583221435547,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 9.0751,
+      "step": 88
+    },
+    {
+      "epoch": 0.01602160216021602,
+      "grad_norm": 4.596582412719727,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 8.8596,
+      "step": 89
+    },
+    {
+      "epoch": 0.016201620162016202,
+      "grad_norm": 4.931702613830566,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 9.0441,
+      "step": 90
+    },
+    {
+      "epoch": 0.016201620162016202,
+      "eval_loss": 9.001091003417969,
+      "eval_runtime": 41.4597,
+      "eval_samples_per_second": 112.832,
+      "eval_steps_per_second": 14.11,
+      "step": 90
+    },
+    {
+      "epoch": 0.01638163816381638,
+      "grad_norm": 5.500175952911377,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 9.2136,
+      "step": 91
+    },
+    {
+      "epoch": 0.016561656165616563,
+      "grad_norm": 5.783007621765137,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 9.234,
+      "step": 92
+    },
+    {
+      "epoch": 0.01674167416741674,
+      "grad_norm": 4.667166233062744,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 9.107,
+      "step": 93
+    },
+    {
+      "epoch": 0.01692169216921692,
+      "grad_norm": 4.6480712890625,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 8.7428,
+      "step": 94
+    },
+    {
+      "epoch": 0.017101710171017102,
+      "grad_norm": 4.516505241394043,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 8.8254,
+      "step": 95
+    },
+    {
+      "epoch": 0.01728172817281728,
+      "grad_norm": 4.1551103591918945,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 8.9528,
+      "step": 96
+    },
+    {
+      "epoch": 0.017461746174617463,
+      "grad_norm": 4.877590656280518,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 9.1006,
+      "step": 97
+    },
+    {
+      "epoch": 0.01764176417641764,
+      "grad_norm": 5.414852619171143,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 9.0552,
+      "step": 98
+    },
+    {
+      "epoch": 0.01782178217821782,
+      "grad_norm": 5.404477596282959,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 9.08,
+      "step": 99
+    },
+    {
+      "epoch": 0.01782178217821782,
+      "eval_loss": 8.99763298034668,
+      "eval_runtime": 41.4635,
+      "eval_samples_per_second": 112.822,
+      "eval_steps_per_second": 14.109,
+      "step": 99
+    },
+    {
+      "epoch": 0.018001800180018002,
+      "grad_norm": 5.185412406921387,
+      "learning_rate": 0.0,
+      "loss": 9.0785,
+      "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": 20362140057600.0,
+  "total_flos": 27149520076800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null