Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456253c7b47d4b3c8243274d8f1190016149670c15112b9fcc626948b11c7602
+oid sha256:884d5d0091f3b11e10b4398ff67883bd4c133995f4a5b31d07c83797d19b43de
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2fc91c6b00712bbf4e7a0192024ffcb8366e804e7151ebbd3e63f1094526645
+oid sha256:0fe5dbafc9a539578e62f553544222359be9c83d60c82df8a9d74c683bb5738e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f3fac815969f48929052743a5a69cb3dfca2432072712e9113166288361420c
+oid sha256:fde104bab0adc1cc90c60a95e124ce8958368abce247283c13e815fc5610de65
 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": 0.004051535531966615,
+  "epoch": 0.005402047375955487,
   "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": 1.4961,
       "step": 75
+    },
+    {
+      "epoch": 0.00410555600572617,
+      "grad_norm": 1.0231529474258423,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4926,
+      "step": 76
+    },
+    {
+      "epoch": 0.004159576479485725,
+      "grad_norm": 0.9222609400749207,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4712,
+      "step": 77
+    },
+    {
+      "epoch": 0.00421359695324528,
+      "grad_norm": 1.1976020336151123,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5043,
+      "step": 78
+    },
+    {
+      "epoch": 0.004267617427004835,
+      "grad_norm": 1.4451897144317627,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.3476,
+      "step": 79
+    },
+    {
+      "epoch": 0.00432163790076439,
+      "grad_norm": 1.0686806440353394,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.492,
+      "step": 80
+    },
+    {
+      "epoch": 0.004375658374523945,
+      "grad_norm": 0.9768352508544922,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.413,
+      "step": 81
+    },
+    {
+      "epoch": 0.004375658374523945,
+      "eval_loss": 1.4142619371414185,
+      "eval_runtime": 3370.8773,
+      "eval_samples_per_second": 4.625,
+      "eval_steps_per_second": 0.578,
+      "step": 81
+    },
+    {
+      "epoch": 0.004429678848283499,
+      "grad_norm": 0.9269257187843323,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.4816,
+      "step": 82
+    },
+    {
+      "epoch": 0.004483699322043054,
+      "grad_norm": 1.01197350025177,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.4349,
+      "step": 83
+    },
+    {
+      "epoch": 0.0045377197958026095,
+      "grad_norm": 0.8954335451126099,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.4416,
+      "step": 84
+    },
+    {
+      "epoch": 0.004591740269562164,
+      "grad_norm": 0.8160538077354431,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2484,
+      "step": 85
+    },
+    {
+      "epoch": 0.004645760743321719,
+      "grad_norm": 0.9298813343048096,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.479,
+      "step": 86
+    },
+    {
+      "epoch": 0.004699781217081274,
+      "grad_norm": 0.9313685297966003,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.3051,
+      "step": 87
+    },
+    {
+      "epoch": 0.004753801690840828,
+      "grad_norm": 1.6026023626327515,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4277,
+      "step": 88
+    },
+    {
+      "epoch": 0.0048078221646003835,
+      "grad_norm": 0.8113055229187012,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.4505,
+      "step": 89
+    },
+    {
+      "epoch": 0.004861842638359939,
+      "grad_norm": 0.9440635442733765,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.4504,
+      "step": 90
+    },
+    {
+      "epoch": 0.004861842638359939,
+      "eval_loss": 1.4125441312789917,
+      "eval_runtime": 3370.8329,
+      "eval_samples_per_second": 4.625,
+      "eval_steps_per_second": 0.578,
+      "step": 90
+    },
+    {
+      "epoch": 0.004915863112119493,
+      "grad_norm": 0.9242429733276367,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.3518,
+      "step": 91
+    },
+    {
+      "epoch": 0.004969883585879048,
+      "grad_norm": 0.8084946870803833,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3352,
+      "step": 92
+    },
+    {
+      "epoch": 0.005023904059638603,
+      "grad_norm": 0.8405563235282898,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.4091,
+      "step": 93
+    },
+    {
+      "epoch": 0.005077924533398158,
+      "grad_norm": 0.9099767804145813,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5132,
+      "step": 94
+    },
+    {
+      "epoch": 0.0051319450071577125,
+      "grad_norm": 0.9288073182106018,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.3346,
+      "step": 95
+    },
+    {
+      "epoch": 0.005185965480917268,
+      "grad_norm": 0.9403652548789978,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.2107,
+      "step": 96
+    },
+    {
+      "epoch": 0.005239985954676823,
+      "grad_norm": 0.8419960141181946,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.2498,
+      "step": 97
+    },
+    {
+      "epoch": 0.005294006428436377,
+      "grad_norm": 1.1825482845306396,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4782,
+      "step": 98
+    },
+    {
+      "epoch": 0.005348026902195932,
+      "grad_norm": 0.9216974377632141,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.3119,
+      "step": 99
+    },
+    {
+      "epoch": 0.005348026902195932,
+      "eval_loss": 1.4122796058654785,
+      "eval_runtime": 3371.9788,
+      "eval_samples_per_second": 4.623,
+      "eval_steps_per_second": 0.578,
+      "step": 99
+    },
+    {
+      "epoch": 0.005402047375955487,
+      "grad_norm": 1.1032953262329102,
+      "learning_rate": 0.0,
+      "loss": 1.399,
+      "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": 1.1017026160872653e+17,
+  "total_flos": 1.4652273850318848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null