Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c4dcba0fe5f8b04bf1bfa592ebdb9f392a6dbeaf5b7f3ee6a3b04d222febe0
+oid sha256:03849bc18303646a3f77145f4a4ddcb6fb3b948cefb269f92f79db7cc81c5db1
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968fe0f04bacfbe5e7022f082ab50d8381bfd4ca6d37f4aa8d463b60647cdfdd
+oid sha256:20092e539049a0e9cf7fa2ffde4cd372c45eda7b5926fdc3d2d4b789a301ac59
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b480f8f3e9dfce5b6f306908b2a95dad982857b71471e381b9452b23f9f9f99
+oid sha256:d8c714c9fc00e7c6bd0ae32e76d48be082a9d71969bbed20217c992fbb958d4a
 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": 0.29296875,
+  "epoch": 0.390625,
   "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": 0.1133,
       "step": 75
+    },
+    {
+      "epoch": 0.296875,
+      "grad_norm": 0.1122271865606308,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0951,
+      "step": 76
+    },
+    {
+      "epoch": 0.30078125,
+      "grad_norm": 0.0981534868478775,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0696,
+      "step": 77
+    },
+    {
+      "epoch": 0.3046875,
+      "grad_norm": 0.11013442277908325,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0881,
+      "step": 78
+    },
+    {
+      "epoch": 0.30859375,
+      "grad_norm": 0.1381031721830368,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.1089,
+      "step": 79
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.1080598533153534,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0956,
+      "step": 80
+    },
+    {
+      "epoch": 0.31640625,
+      "grad_norm": 0.13694408535957336,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0884,
+      "step": 81
+    },
+    {
+      "epoch": 0.31640625,
+      "eval_loss": 0.0842214897274971,
+      "eval_runtime": 37.6747,
+      "eval_samples_per_second": 5.733,
+      "eval_steps_per_second": 0.717,
+      "step": 81
+    },
+    {
+      "epoch": 0.3203125,
+      "grad_norm": 0.11448404937982559,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0717,
+      "step": 82
+    },
+    {
+      "epoch": 0.32421875,
+      "grad_norm": 0.09915163367986679,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0859,
+      "step": 83
+    },
+    {
+      "epoch": 0.328125,
+      "grad_norm": 0.13431188464164734,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1183,
+      "step": 84
+    },
+    {
+      "epoch": 0.33203125,
+      "grad_norm": 0.1266343742609024,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0907,
+      "step": 85
+    },
+    {
+      "epoch": 0.3359375,
+      "grad_norm": 0.08939848095178604,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0936,
+      "step": 86
+    },
+    {
+      "epoch": 0.33984375,
+      "grad_norm": 0.08177338540554047,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.081,
+      "step": 87
+    },
+    {
+      "epoch": 0.34375,
+      "grad_norm": 0.11731616407632828,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0617,
+      "step": 88
+    },
+    {
+      "epoch": 0.34765625,
+      "grad_norm": 0.14580127596855164,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1243,
+      "step": 89
+    },
+    {
+      "epoch": 0.3515625,
+      "grad_norm": 0.125287264585495,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0565,
+      "step": 90
+    },
+    {
+      "epoch": 0.3515625,
+      "eval_loss": 0.08387485146522522,
+      "eval_runtime": 37.6798,
+      "eval_samples_per_second": 5.733,
+      "eval_steps_per_second": 0.717,
+      "step": 90
+    },
+    {
+      "epoch": 0.35546875,
+      "grad_norm": 0.100253626704216,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0871,
+      "step": 91
+    },
+    {
+      "epoch": 0.359375,
+      "grad_norm": 0.09870755672454834,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0835,
+      "step": 92
+    },
+    {
+      "epoch": 0.36328125,
+      "grad_norm": 0.1428849697113037,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0803,
+      "step": 93
+    },
+    {
+      "epoch": 0.3671875,
+      "grad_norm": 0.09685681015253067,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0927,
+      "step": 94
+    },
+    {
+      "epoch": 0.37109375,
+      "grad_norm": 0.10489041358232498,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0825,
+      "step": 95
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.09282656759023666,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0892,
+      "step": 96
+    },
+    {
+      "epoch": 0.37890625,
+      "grad_norm": 0.1284118890762329,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0695,
+      "step": 97
+    },
+    {
+      "epoch": 0.3828125,
+      "grad_norm": 0.08799555897712708,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0832,
+      "step": 98
+    },
+    {
+      "epoch": 0.38671875,
+      "grad_norm": 0.10245624929666519,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0673,
+      "step": 99
+    },
+    {
+      "epoch": 0.38671875,
+      "eval_loss": 0.08374549448490143,
+      "eval_runtime": 37.6733,
+      "eval_samples_per_second": 5.733,
+      "eval_steps_per_second": 0.717,
+      "step": 99
+    },
+    {
+      "epoch": 0.390625,
+      "grad_norm": 0.1315760463476181,
+      "learning_rate": 0.0,
+      "loss": 0.0925,
+      "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": 8.462004696121344e+16,
+  "total_flos": 1.1271654692880384e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null