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:ee973b61fb6827b54356447d901e570efdcbca7180e20d6ae56614bde4b35533
+oid sha256:7306fa4fc1b3f84898869db9c1d22bd0ee7e74f0a70eb98be9a20567d7945992
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2794508ae46cf73d24cd868783910af8465280cccf4dc02ce60d7a6608e2c8e3
+oid sha256:6193c0abd8342b55a9ff075c3818413d75d841c424140247ab453a8f38516863
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b1a2d570362d5fe7bbb15687da3c63cd96031cb350ed30b48bd64ead1a0b67
+oid sha256:1a7c2c029217cb593dab8e49e32321920b802b5b5eb32549e28ab93bc28e0aaa
 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": 0.12510425354462051,
+  "epoch": 0.16680567139282734,
   "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": 1.0819,
       "step": 75
+    },
+    {
+      "epoch": 0.1267723102585488,
+      "grad_norm": 3.2596352100372314,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4257,
+      "step": 76
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 3.483473777770996,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.3465,
+      "step": 77
+    },
+    {
+      "epoch": 0.13010842368640535,
+      "grad_norm": 2.079091787338257,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.0071,
+      "step": 78
+    },
+    {
+      "epoch": 0.1317764804003336,
+      "grad_norm": 2.954646587371826,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.2336,
+      "step": 79
+    },
+    {
+      "epoch": 0.13344453711426188,
+      "grad_norm": 3.4457616806030273,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.4788,
+      "step": 80
+    },
+    {
+      "epoch": 0.13511259382819016,
+      "grad_norm": 1.9960256814956665,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.0899,
+      "step": 81
+    },
+    {
+      "epoch": 0.13511259382819016,
+      "eval_loss": 1.0880334377288818,
+      "eval_runtime": 4.4371,
+      "eval_samples_per_second": 113.813,
+      "eval_steps_per_second": 14.424,
+      "step": 81
+    },
+    {
+      "epoch": 0.13678065054211844,
+      "grad_norm": 2.532301187515259,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.021,
+      "step": 82
+    },
+    {
+      "epoch": 0.13844870725604672,
+      "grad_norm": 2.122875690460205,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.97,
+      "step": 83
+    },
+    {
+      "epoch": 0.14011676396997497,
+      "grad_norm": 1.9642120599746704,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.9546,
+      "step": 84
+    },
+    {
+      "epoch": 0.14178482068390325,
+      "grad_norm": 2.8794195652008057,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.179,
+      "step": 85
+    },
+    {
+      "epoch": 0.14345287739783152,
+      "grad_norm": 2.5818090438842773,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.076,
+      "step": 86
+    },
+    {
+      "epoch": 0.1451209341117598,
+      "grad_norm": 2.238755702972412,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.968,
+      "step": 87
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 2.656874179840088,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.9599,
+      "step": 88
+    },
+    {
+      "epoch": 0.14845704753961636,
+      "grad_norm": 2.070028305053711,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.0208,
+      "step": 89
+    },
+    {
+      "epoch": 0.1501251042535446,
+      "grad_norm": 2.119825601577759,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.0384,
+      "step": 90
+    },
+    {
+      "epoch": 0.1501251042535446,
+      "eval_loss": 1.014533519744873,
+      "eval_runtime": 4.3775,
+      "eval_samples_per_second": 115.364,
+      "eval_steps_per_second": 14.62,
+      "step": 90
+    },
+    {
+      "epoch": 0.1517931609674729,
+      "grad_norm": 2.214562177658081,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.9634,
+      "step": 91
+    },
+    {
+      "epoch": 0.15346121768140117,
+      "grad_norm": 4.23738956451416,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9777,
+      "step": 92
+    },
+    {
+      "epoch": 0.15512927439532945,
+      "grad_norm": 4.1537628173828125,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.0151,
+      "step": 93
+    },
+    {
+      "epoch": 0.15679733110925773,
+      "grad_norm": 5.1043500900268555,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.0603,
+      "step": 94
+    },
+    {
+      "epoch": 0.15846538782318598,
+      "grad_norm": 2.0667572021484375,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.9537,
+      "step": 95
+    },
+    {
+      "epoch": 0.16013344453711426,
+      "grad_norm": 2.5994327068328857,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.9878,
+      "step": 96
+    },
+    {
+      "epoch": 0.16180150125104253,
+      "grad_norm": 2.356971502304077,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.9275,
+      "step": 97
+    },
+    {
+      "epoch": 0.1634695579649708,
+      "grad_norm": 2.4719834327697754,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.0936,
+      "step": 98
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 1.9262813329696655,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.8934,
+      "step": 99
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "eval_loss": 1.00246000289917,
+      "eval_runtime": 4.3721,
+      "eval_samples_per_second": 115.505,
+      "eval_steps_per_second": 14.638,
+      "step": 99
+    },
+    {
+      "epoch": 0.16680567139282734,
+      "grad_norm": 2.25650691986084,
+      "learning_rate": 0.0,
+      "loss": 0.9096,
+      "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": 1041281895628800.0,
+  "total_flos": 1388375860838400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null