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:d89ef3fb1a8c75c0dc08a6efc853c74a58e61fc0681127eb9e819aded96aa8ed
+oid sha256:6659e2f3a02d0994c581d48195a663b4169b14112934f8267e56a3df7d8fd091
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e399281e2e551cfc56d79bf5c5c718e10523406f9a34d49f5aaee41e438412e
+oid sha256:04d9bcbf6e771c757fae5c4c49136a300acee106c8ec03ca8031cb22c5e42ef3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.0929944203347799,
+  "epoch": 0.12399256044637322,
   "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": 0.4982,
       "step": 75
+    },
+    {
+      "epoch": 0.09423434593924365,
+      "grad_norm": 2.7212040424346924,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2379,
+      "step": 76
+    },
+    {
+      "epoch": 0.09547427154370738,
+      "grad_norm": 3.9562039375305176,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.5157,
+      "step": 77
+    },
+    {
+      "epoch": 0.09671419714817112,
+      "grad_norm": 4.127841472625732,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.7147,
+      "step": 78
+    },
+    {
+      "epoch": 0.09795412275263485,
+      "grad_norm": 2.836074113845825,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.285,
+      "step": 79
+    },
+    {
+      "epoch": 0.09919404835709858,
+      "grad_norm": 4.456368446350098,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.2177,
+      "step": 80
+    },
+    {
+      "epoch": 0.10043397396156231,
+      "grad_norm": 2.3970136642456055,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.1053,
+      "step": 81
+    },
+    {
+      "epoch": 0.10043397396156231,
+      "eval_loss": 0.3661847710609436,
+      "eval_runtime": 74.5661,
+      "eval_samples_per_second": 9.106,
+      "eval_steps_per_second": 1.14,
+      "step": 81
+    },
+    {
+      "epoch": 0.10167389956602604,
+      "grad_norm": 2.0069854259490967,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2474,
+      "step": 82
+    },
+    {
+      "epoch": 0.10291382517048978,
+      "grad_norm": 3.5164527893066406,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.6209,
+      "step": 83
+    },
+    {
+      "epoch": 0.10415375077495351,
+      "grad_norm": 3.549330234527588,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3775,
+      "step": 84
+    },
+    {
+      "epoch": 0.10539367637941724,
+      "grad_norm": 3.223816394805908,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2977,
+      "step": 85
+    },
+    {
+      "epoch": 0.10663360198388097,
+      "grad_norm": 3.326846122741699,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.3848,
+      "step": 86
+    },
+    {
+      "epoch": 0.1078735275883447,
+      "grad_norm": 2.9460747241973877,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.224,
+      "step": 87
+    },
+    {
+      "epoch": 0.10911345319280844,
+      "grad_norm": 3.0875232219696045,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.2752,
+      "step": 88
+    },
+    {
+      "epoch": 0.11035337879727217,
+      "grad_norm": 4.651269435882568,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2754,
+      "step": 89
+    },
+    {
+      "epoch": 0.1115933044017359,
+      "grad_norm": 3.0588595867156982,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4322,
+      "step": 90
+    },
+    {
+      "epoch": 0.1115933044017359,
+      "eval_loss": 0.362551748752594,
+      "eval_runtime": 74.5244,
+      "eval_samples_per_second": 9.111,
+      "eval_steps_per_second": 1.141,
+      "step": 90
+    },
+    {
+      "epoch": 0.11283323000619963,
+      "grad_norm": 2.9374754428863525,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3,
+      "step": 91
+    },
+    {
+      "epoch": 0.11407315561066336,
+      "grad_norm": 2.171053171157837,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1882,
+      "step": 92
+    },
+    {
+      "epoch": 0.1153130812151271,
+      "grad_norm": 2.6169354915618896,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3603,
+      "step": 93
+    },
+    {
+      "epoch": 0.11655300681959083,
+      "grad_norm": 2.496931791305542,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3489,
+      "step": 94
+    },
+    {
+      "epoch": 0.11779293242405456,
+      "grad_norm": 1.8905479907989502,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1084,
+      "step": 95
+    },
+    {
+      "epoch": 0.11903285802851829,
+      "grad_norm": 3.700955390930176,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.458,
+      "step": 96
+    },
+    {
+      "epoch": 0.12027278363298202,
+      "grad_norm": 5.287838935852051,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.2966,
+      "step": 97
+    },
+    {
+      "epoch": 0.12151270923744575,
+      "grad_norm": 2.670868158340454,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4348,
+      "step": 98
+    },
+    {
+      "epoch": 0.12275263484190949,
+      "grad_norm": 2.351815938949585,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.3598,
+      "step": 99
+    },
+    {
+      "epoch": 0.12275263484190949,
+      "eval_loss": 0.36131006479263306,
+      "eval_runtime": 74.5619,
+      "eval_samples_per_second": 9.107,
+      "eval_steps_per_second": 1.14,
+      "step": 99
+    },
+    {
+      "epoch": 0.12399256044637322,
+      "grad_norm": 2.446971893310547,
+      "learning_rate": 0.0,
+      "loss": 0.2263,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null