Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f93a300e3f3b5f25803b84c9e7de73b41cf01a0974beaf422f399d9400a6f20
+oid sha256:94bc70532f88111543bea3970215cfa8b7ffd2664a1c94d671245af059d5ffc0
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a42b541feb92b363bc38c6e7755d5fcd38ab8cd52678647d74c5e2f7ef4dc75
+oid sha256:edffb0bc9e9b8bb38252c69bf8068598a14fde4c3ece95a36a5e5332b6a07dd9
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d974693f1b73d24c115a391c91cb48722102d864f187f886474234f46a38e9
+oid sha256:25f3200988fb0fba169861cb1e034ba16d45e33c697af4f6032e986d05882985
 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": 0.01950331556364582,
+  "epoch": 0.02600442075152776,
   "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": 10.3747,
       "step": 75
+    },
+    {
+      "epoch": 0.019763359771161098,
+      "grad_norm": 0.045965924859046936,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3776,
+      "step": 76
+    },
+    {
+      "epoch": 0.020023403978676375,
+      "grad_norm": 0.04359443113207817,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3771,
+      "step": 77
+    },
+    {
+      "epoch": 0.02028344818619165,
+      "grad_norm": 0.045900508761405945,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.378,
+      "step": 78
+    },
+    {
+      "epoch": 0.02054349239370693,
+      "grad_norm": 0.054575856775045395,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3755,
+      "step": 79
+    },
+    {
+      "epoch": 0.02080353660122221,
+      "grad_norm": 0.04699670523405075,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3778,
+      "step": 80
+    },
+    {
+      "epoch": 0.021063580808737485,
+      "grad_norm": 0.059355478733778,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3729,
+      "step": 81
+    },
+    {
+      "epoch": 0.021063580808737485,
+      "eval_loss": 10.377110481262207,
+      "eval_runtime": 25.0267,
+      "eval_samples_per_second": 129.422,
+      "eval_steps_per_second": 16.183,
+      "step": 81
+    },
+    {
+      "epoch": 0.021323625016252762,
+      "grad_norm": 0.05459514260292053,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3779,
+      "step": 82
+    },
+    {
+      "epoch": 0.021583669223768042,
+      "grad_norm": 0.04532025381922722,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3779,
+      "step": 83
+    },
+    {
+      "epoch": 0.02184371343128332,
+      "grad_norm": 0.051146797835826874,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3819,
+      "step": 84
+    },
+    {
+      "epoch": 0.022103757638798596,
+      "grad_norm": 0.05978747457265854,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.375,
+      "step": 85
+    },
+    {
+      "epoch": 0.022363801846313872,
+      "grad_norm": 0.04381445050239563,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3791,
+      "step": 86
+    },
+    {
+      "epoch": 0.022623846053829152,
+      "grad_norm": 0.059307560324668884,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.376,
+      "step": 87
+    },
+    {
+      "epoch": 0.02288389026134443,
+      "grad_norm": 0.0550258494913578,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.377,
+      "step": 88
+    },
+    {
+      "epoch": 0.023143934468859706,
+      "grad_norm": 0.04555179178714752,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3759,
+      "step": 89
+    },
+    {
+      "epoch": 0.023403978676374983,
+      "grad_norm": 0.05648469924926758,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3772,
+      "step": 90
+    },
+    {
+      "epoch": 0.023403978676374983,
+      "eval_loss": 10.376992225646973,
+      "eval_runtime": 25.6416,
+      "eval_samples_per_second": 126.318,
+      "eval_steps_per_second": 15.795,
+      "step": 90
+    },
+    {
+      "epoch": 0.023664022883890263,
+      "grad_norm": 0.050564419478178024,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3792,
+      "step": 91
+    },
+    {
+      "epoch": 0.02392406709140554,
+      "grad_norm": 0.05184341222047806,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3734,
+      "step": 92
+    },
+    {
+      "epoch": 0.024184111298920816,
+      "grad_norm": 0.04729103296995163,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3784,
+      "step": 93
+    },
+    {
+      "epoch": 0.024444155506436093,
+      "grad_norm": 0.04831608757376671,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3771,
+      "step": 94
+    },
+    {
+      "epoch": 0.024704199713951373,
+      "grad_norm": 0.055237192660570145,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3786,
+      "step": 95
+    },
+    {
+      "epoch": 0.02496424392146665,
+      "grad_norm": 0.051754217594861984,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3785,
+      "step": 96
+    },
+    {
+      "epoch": 0.025224288128981927,
+      "grad_norm": 0.048474401235580444,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3787,
+      "step": 97
+    },
+    {
+      "epoch": 0.025484332336497204,
+      "grad_norm": 0.04937809333205223,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3745,
+      "step": 98
+    },
+    {
+      "epoch": 0.025744376544012484,
+      "grad_norm": 0.04878290742635727,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3776,
+      "step": 99
+    },
+    {
+      "epoch": 0.025744376544012484,
+      "eval_loss": 10.376970291137695,
+      "eval_runtime": 25.8552,
+      "eval_samples_per_second": 125.275,
+      "eval_steps_per_second": 15.664,
+      "step": 99
+    },
+    {
+      "epoch": 0.02600442075152776,
+      "grad_norm": 0.0496150404214859,
+      "learning_rate": 0.0,
+      "loss": 10.3777,
+      "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": 4288800620544.0,
+  "total_flos": 5727117901824.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null