Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3d9a0d4af70579cc7d416e48094f46e6d792226b735a4ec418fd6a5799b413
+oid sha256:5c9ef9f67966727d16f32ca9c5be184d105af7088daa6a4c11fb6be586d7ccf0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c178c7ba51191e6f979efc088afb7cd77001bc460923ab4598e8fb9b6eb917
+oid sha256:e3fd09e6d376acb967f5c9be06d58122820326d0205b61b3b3065d8224520106
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eae4a00498eae213a9ac94811fd6e10f603c3fc5770db8c2d81ab447acaae8a3
+oid sha256:0572913da76f8383df863a06d8a17389515370cea786a37f627a549c437dda9a
 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": 0.007571168988491823,
+  "epoch": 0.010094891984655765,
   "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": 2.1572,
       "step": 75
+    },
+    {
+      "epoch": 0.007672117908338381,
+      "grad_norm": 0.23516961932182312,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.1657,
+      "step": 76
+    },
+    {
+      "epoch": 0.0077730668281849385,
+      "grad_norm": 0.22615772485733032,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.1423,
+      "step": 77
+    },
+    {
+      "epoch": 0.007874015748031496,
+      "grad_norm": 0.25158652663230896,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.1857,
+      "step": 78
+    },
+    {
+      "epoch": 0.007974964667878054,
+      "grad_norm": 0.24187257885932922,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.155,
+      "step": 79
+    },
+    {
+      "epoch": 0.00807591358772461,
+      "grad_norm": 0.2316223829984665,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.176,
+      "step": 80
+    },
+    {
+      "epoch": 0.00817686250757117,
+      "grad_norm": 0.2663958668708801,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.175,
+      "step": 81
+    },
+    {
+      "epoch": 0.00817686250757117,
+      "eval_loss": 2.1655943393707275,
+      "eval_runtime": 836.7406,
+      "eval_samples_per_second": 9.97,
+      "eval_steps_per_second": 1.247,
+      "step": 81
+    },
+    {
+      "epoch": 0.008277811427417727,
+      "grad_norm": 0.287240207195282,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1805,
+      "step": 82
+    },
+    {
+      "epoch": 0.008378760347264284,
+      "grad_norm": 0.2595893144607544,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.1463,
+      "step": 83
+    },
+    {
+      "epoch": 0.008479709267110842,
+      "grad_norm": 0.23999683558940887,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.1788,
+      "step": 84
+    },
+    {
+      "epoch": 0.008580658186957399,
+      "grad_norm": 0.27363473176956177,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.145,
+      "step": 85
+    },
+    {
+      "epoch": 0.008681607106803957,
+      "grad_norm": 0.2818804979324341,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.1733,
+      "step": 86
+    },
+    {
+      "epoch": 0.008782556026650516,
+      "grad_norm": 0.2009168416261673,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.1748,
+      "step": 87
+    },
+    {
+      "epoch": 0.008883504946497072,
+      "grad_norm": 0.26735901832580566,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.176,
+      "step": 88
+    },
+    {
+      "epoch": 0.00898445386634363,
+      "grad_norm": 0.2693656384944916,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.1828,
+      "step": 89
+    },
+    {
+      "epoch": 0.009085402786190187,
+      "grad_norm": 0.20952469110488892,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.1511,
+      "step": 90
+    },
+    {
+      "epoch": 0.009085402786190187,
+      "eval_loss": 2.1652722358703613,
+      "eval_runtime": 836.531,
+      "eval_samples_per_second": 9.972,
+      "eval_steps_per_second": 1.247,
+      "step": 90
+    },
+    {
+      "epoch": 0.009186351706036745,
+      "grad_norm": 0.21097005903720856,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.1736,
+      "step": 91
+    },
+    {
+      "epoch": 0.009287300625883304,
+      "grad_norm": 0.25543177127838135,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.1668,
+      "step": 92
+    },
+    {
+      "epoch": 0.00938824954572986,
+      "grad_norm": 0.25192975997924805,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.1451,
+      "step": 93
+    },
+    {
+      "epoch": 0.009489198465576418,
+      "grad_norm": 0.2307412028312683,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.1588,
+      "step": 94
+    },
+    {
+      "epoch": 0.009590147385422977,
+      "grad_norm": 0.2313176393508911,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.16,
+      "step": 95
+    },
+    {
+      "epoch": 0.009691096305269533,
+      "grad_norm": 0.23625782132148743,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.1843,
+      "step": 96
+    },
+    {
+      "epoch": 0.009792045225116092,
+      "grad_norm": 0.2403765767812729,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.1836,
+      "step": 97
+    },
+    {
+      "epoch": 0.009892994144962648,
+      "grad_norm": 0.2410961240530014,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.1562,
+      "step": 98
+    },
+    {
+      "epoch": 0.009993943064809207,
+      "grad_norm": 0.2312341183423996,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.1613,
+      "step": 99
+    },
+    {
+      "epoch": 0.009993943064809207,
+      "eval_loss": 2.1652092933654785,
+      "eval_runtime": 836.931,
+      "eval_samples_per_second": 9.967,
+      "eval_steps_per_second": 1.246,
+      "step": 99
+    },
+    {
+      "epoch": 0.010094891984655765,
+      "grad_norm": 0.20589391887187958,
+      "learning_rate": 0.0,
+      "loss": 2.1687,
+      "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": 1.0572077400588288e+17,
+  "total_flos": 1.4244483234476851e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null