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:c39fa09a1ac8a25c9195401febe4b753e2d5df9eea7d17f49468f3b8927e6f3d
+oid sha256:fa3ee233732b2e98325a6fa2a227c8bbdcd8b5737e403e9f3728028c00d948b3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4689598c0939540f71b8857f12e0ac0b32e1d6014c5e393050aaadecf395fd30
+oid sha256:1170788b443f5e887906b4a06cd00ec95d51bbaff467cdfb52b9c53693088d6a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f136c199f5a732675f6a9f736544ebc5602c94619f3b8e1d710d38a48909063
+oid sha256:fae915255f2c8a15d241894b93fb82d30ded89855294cb3eaa0133acd3c92e81
 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": 0.004571358912626093,
+  "epoch": 0.006095145216834791,
   "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": 0.0,
       "step": 75
+    },
+    {
+      "epoch": 0.004632310364794441,
+      "grad_norm": 0.004577755928039551,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.004693261816962789,
+      "grad_norm": 0.00045730435522273183,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.004754213269131137,
+      "grad_norm": 0.00031118057086132467,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.004815164721299485,
+      "grad_norm": 0.0005092663923278451,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.004876116173467833,
+      "grad_norm": 0.00029153015930205584,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.004937067625636181,
+      "grad_norm": 0.00032549205934628844,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.004937067625636181,
+      "eval_loss": 0.0021451739594340324,
+      "eval_runtime": 2103.3459,
+      "eval_samples_per_second": 6.569,
+      "eval_steps_per_second": 0.821,
+      "step": 81
+    },
+    {
+      "epoch": 0.004998019077804529,
+      "grad_norm": 0.0006757644005119801,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.005058970529972877,
+      "grad_norm": 0.0008024928974919021,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.005119921982141225,
+      "grad_norm": 0.00041792544652707875,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.005180873434309573,
+      "grad_norm": 0.0006066655623726547,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.0052418248864779205,
+      "grad_norm": 0.00035250242217443883,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.0053027763386462685,
+      "grad_norm": 0.00059564906405285,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.0053637277908146165,
+      "grad_norm": 0.0004675053933169693,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.0054246792429829644,
+      "grad_norm": 0.00046611728612333536,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.005485630695151312,
+      "grad_norm": 0.00036150909727439284,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.005485630695151312,
+      "eval_loss": 0.0021452573128044605,
+      "eval_runtime": 2102.0113,
+      "eval_samples_per_second": 6.573,
+      "eval_steps_per_second": 0.822,
+      "step": 90
+    },
+    {
+      "epoch": 0.0055465821473196595,
+      "grad_norm": 0.0003072117397096008,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.0056075335994880075,
+      "grad_norm": 0.04003473371267319,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0001,
+      "step": 92
+    },
+    {
+      "epoch": 0.005668485051656355,
+      "grad_norm": 0.00045625370694324374,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.005729436503824703,
+      "grad_norm": 0.0004790804523508996,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.005790387955993051,
+      "grad_norm": 0.000417745322920382,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.005851339408161399,
+      "grad_norm": 0.000524096074514091,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.005912290860329747,
+      "grad_norm": 0.0004284666501916945,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.005973242312498095,
+      "grad_norm": 0.00031758853583596647,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.006034193764666443,
+      "grad_norm": 0.0005975643871352077,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.006034193764666443,
+      "eval_loss": 0.0021247444674372673,
+      "eval_runtime": 2103.361,
+      "eval_samples_per_second": 6.569,
+      "eval_steps_per_second": 0.821,
+      "step": 99
+    },
+    {
+      "epoch": 0.006095145216834791,
+      "grad_norm": 0.0004037336620967835,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "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": 7.789816477384704e+16,
+  "total_flos": 1.0163855784778138e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null