Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb363d52f809e42ba14f4c5fa66d715569ec540d99d2f9059047060d5eb9c48
+oid sha256:6128e193e9fa43283ae504f62daa079868846804c167980a19d9e35052841ffd
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe39e32a61a9c8e2f2e972a4523b0e7386e00d8bd33a6946e65da955afc882f4
+oid sha256:bd8948f68fdd6b2a3f11b629adee6ab4ad449f3ac2ad87a3679a877b6cded44b
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26273becc6a8648e93d80c878bdc8c53b88305e9bd75c42025a44697539acb1c
+oid sha256:bfb5c4960152e0b8acb3e427fe9330c4c6bef2d58760e69b2339fd2ae5587a78
 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": 0.0021892057561516682,
+  "epoch": 0.002918941008202224,
   "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": 2.015,
       "step": 75
+    },
+    {
+      "epoch": 0.0022183951662336906,
+      "grad_norm": 4.182319164276123,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.2588,
+      "step": 76
+    },
+    {
+      "epoch": 0.0022475845763157126,
+      "grad_norm": 4.0956902503967285,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.5251,
+      "step": 77
+    },
+    {
+      "epoch": 0.002276773986397735,
+      "grad_norm": 6.849318504333496,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.9433,
+      "step": 78
+    },
+    {
+      "epoch": 0.0023059633964797573,
+      "grad_norm": 4.243894100189209,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.0968,
+      "step": 79
+    },
+    {
+      "epoch": 0.0023351528065617792,
+      "grad_norm": 4.446126461029053,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.2825,
+      "step": 80
+    },
+    {
+      "epoch": 0.0023643422166438016,
+      "grad_norm": 4.001028060913086,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.0534,
+      "step": 81
+    },
+    {
+      "epoch": 0.0023643422166438016,
+      "eval_loss": 1.1278122663497925,
+      "eval_runtime": 5144.6061,
+      "eval_samples_per_second": 5.608,
+      "eval_steps_per_second": 0.701,
+      "step": 81
+    },
+    {
+      "epoch": 0.002393531626725824,
+      "grad_norm": 4.941494464874268,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.6782,
+      "step": 82
+    },
+    {
+      "epoch": 0.002422721036807846,
+      "grad_norm": 3.429147243499756,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.8928,
+      "step": 83
+    },
+    {
+      "epoch": 0.0024519104468898683,
+      "grad_norm": 4.535146713256836,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.3525,
+      "step": 84
+    },
+    {
+      "epoch": 0.0024810998569718907,
+      "grad_norm": 5.437557697296143,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9063,
+      "step": 85
+    },
+    {
+      "epoch": 0.002510289267053913,
+      "grad_norm": 3.488252878189087,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.8033,
+      "step": 86
+    },
+    {
+      "epoch": 0.002539478677135935,
+      "grad_norm": 3.811572551727295,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.2559,
+      "step": 87
+    },
+    {
+      "epoch": 0.0025686680872179573,
+      "grad_norm": 3.8322970867156982,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.8017,
+      "step": 88
+    },
+    {
+      "epoch": 0.0025978574972999797,
+      "grad_norm": 3.616431951522827,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.8406,
+      "step": 89
+    },
+    {
+      "epoch": 0.0026270469073820016,
+      "grad_norm": 4.430796146392822,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.6601,
+      "step": 90
+    },
+    {
+      "epoch": 0.0026270469073820016,
+      "eval_loss": 1.1228456497192383,
+      "eval_runtime": 5146.2182,
+      "eval_samples_per_second": 5.606,
+      "eval_steps_per_second": 0.701,
+      "step": 90
+    },
+    {
+      "epoch": 0.002656236317464024,
+      "grad_norm": 3.7266006469726562,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.2885,
+      "step": 91
+    },
+    {
+      "epoch": 0.0026854257275460464,
+      "grad_norm": 4.4447102546691895,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.3565,
+      "step": 92
+    },
+    {
+      "epoch": 0.0027146151376280687,
+      "grad_norm": 3.7036726474761963,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.9967,
+      "step": 93
+    },
+    {
+      "epoch": 0.0027438045477100907,
+      "grad_norm": 3.414736032485962,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.7818,
+      "step": 94
+    },
+    {
+      "epoch": 0.002772993957792113,
+      "grad_norm": 3.677932024002075,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.2275,
+      "step": 95
+    },
+    {
+      "epoch": 0.0028021833678741354,
+      "grad_norm": 4.357283592224121,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2058,
+      "step": 96
+    },
+    {
+      "epoch": 0.0028313727779561574,
+      "grad_norm": 4.287678241729736,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.707,
+      "step": 97
+    },
+    {
+      "epoch": 0.0028605621880381797,
+      "grad_norm": 3.559546947479248,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.966,
+      "step": 98
+    },
+    {
+      "epoch": 0.002889751598120202,
+      "grad_norm": 3.653371810913086,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.9594,
+      "step": 99
+    },
+    {
+      "epoch": 0.002889751598120202,
+      "eval_loss": 1.1218863725662231,
+      "eval_runtime": 5144.1382,
+      "eval_samples_per_second": 5.608,
+      "eval_steps_per_second": 0.701,
+      "step": 99
+    },
+    {
+      "epoch": 0.002918941008202224,
+      "grad_norm": 3.8295724391937256,
+      "learning_rate": 0.0,
+      "loss": 1.8266,
+      "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": 1.1108631969792e+17,
+  "total_flos": 1.485382789103616e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null