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:c99ec4ac1a32e29589c1bd12bea30c4f62a6ec2f160ce3701dd628f1a8a984df
+oid sha256:881e285f65e9449deba89c6e753dca1c19d4804fcde191acbca4369c7cf8b141
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72baaeadabb66c943626ff6acaacbb2c63edfe86e0ac5c960fc174aa78123d4d
+oid sha256:ba655007a6a4b92606863fbbbd7cedae73f5803aa1416598c7a0df1ac6f58552
 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": 0.0017847794012660035,
+  "epoch": 0.0023797058683546713,
   "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": 0.1936,
       "step": 75
+    },
+    {
+      "epoch": 0.0018085764599495503,
+      "grad_norm": 0.6997938752174377,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.178,
+      "step": 76
+    },
+    {
+      "epoch": 0.001832373518633097,
+      "grad_norm": 0.44665923714637756,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.179,
+      "step": 77
+    },
+    {
+      "epoch": 0.0018561705773166436,
+      "grad_norm": 1.0063934326171875,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1741,
+      "step": 78
+    },
+    {
+      "epoch": 0.0018799676360001904,
+      "grad_norm": 0.8322280645370483,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.1771,
+      "step": 79
+    },
+    {
+      "epoch": 0.001903764694683737,
+      "grad_norm": 0.4578947424888611,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1788,
+      "step": 80
+    },
+    {
+      "epoch": 0.0019275617533672839,
+      "grad_norm": 0.7244126796722412,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.1852,
+      "step": 81
+    },
+    {
+      "epoch": 0.0019275617533672839,
+      "eval_loss": 0.17674638330936432,
+      "eval_runtime": 3851.8927,
+      "eval_samples_per_second": 9.187,
+      "eval_steps_per_second": 1.149,
+      "step": 81
+    },
+    {
+      "epoch": 0.0019513588120508305,
+      "grad_norm": 2.129763126373291,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.19,
+      "step": 82
+    },
+    {
+      "epoch": 0.001975155870734377,
+      "grad_norm": 0.9284147620201111,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.1748,
+      "step": 83
+    },
+    {
+      "epoch": 0.001998952929417924,
+      "grad_norm": 0.26722249388694763,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1716,
+      "step": 84
+    },
+    {
+      "epoch": 0.0020227499881014708,
+      "grad_norm": 0.5134215950965881,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1735,
+      "step": 85
+    },
+    {
+      "epoch": 0.0020465470467850174,
+      "grad_norm": 0.3766758441925049,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1743,
+      "step": 86
+    },
+    {
+      "epoch": 0.002070344105468564,
+      "grad_norm": 0.9653725028038025,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.1776,
+      "step": 87
+    },
+    {
+      "epoch": 0.0020941411641521106,
+      "grad_norm": 1.9916068315505981,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1841,
+      "step": 88
+    },
+    {
+      "epoch": 0.0021179382228356577,
+      "grad_norm": 0.9163305163383484,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.1856,
+      "step": 89
+    },
+    {
+      "epoch": 0.0021417352815192043,
+      "grad_norm": 0.5257497429847717,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1729,
+      "step": 90
+    },
+    {
+      "epoch": 0.0021417352815192043,
+      "eval_loss": 0.17558716237545013,
+      "eval_runtime": 3849.0599,
+      "eval_samples_per_second": 9.194,
+      "eval_steps_per_second": 1.149,
+      "step": 90
+    },
+    {
+      "epoch": 0.002165532340202751,
+      "grad_norm": 1.5954173803329468,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1592,
+      "step": 91
+    },
+    {
+      "epoch": 0.0021893293988862975,
+      "grad_norm": 1.5814809799194336,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1814,
+      "step": 92
+    },
+    {
+      "epoch": 0.0022131264575698446,
+      "grad_norm": 1.5040247440338135,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1619,
+      "step": 93
+    },
+    {
+      "epoch": 0.002236923516253391,
+      "grad_norm": 0.4892219007015228,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1816,
+      "step": 94
+    },
+    {
+      "epoch": 0.002260720574936938,
+      "grad_norm": 0.45594584941864014,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1767,
+      "step": 95
+    },
+    {
+      "epoch": 0.0022845176336204844,
+      "grad_norm": 1.0217349529266357,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1597,
+      "step": 96
+    },
+    {
+      "epoch": 0.002308314692304031,
+      "grad_norm": 0.24473020434379578,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.1728,
+      "step": 97
+    },
+    {
+      "epoch": 0.002332111750987578,
+      "grad_norm": 2.5822603702545166,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.187,
+      "step": 98
+    },
+    {
+      "epoch": 0.0023559088096711247,
+      "grad_norm": 0.20606911182403564,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.1664,
+      "step": 99
+    },
+    {
+      "epoch": 0.0023559088096711247,
+      "eval_loss": 0.17582166194915771,
+      "eval_runtime": 3850.4432,
+      "eval_samples_per_second": 9.19,
+      "eval_steps_per_second": 1.149,
+      "step": 99
+    },
+    {
+      "epoch": 0.0023797058683546713,
+      "grad_norm": 0.9258091449737549,
+      "learning_rate": 0.0,
+      "loss": 0.1737,
+      "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