Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc55a046e9ec2d2a299511af6449a467b3453e165ea3a36353bebe06baae996
+oid sha256:f5f12a10a6d1ec0c9fe58218adb998a7e0f582271a5bf85564e2120b728b7a3d
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7d6dbcc0b56044d7e0341dcdb174562efde8e77f355845bc914bef174f6daa
+oid sha256:95a7b7f6af2ba2939c2a7facf3095e254a631da6cc702b96f9cefc8f150826fc
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60653680dde09c64e0476c7cc3736a29a14786c5445eca158859f54121902306
+oid sha256:2b43a8fab89b180c95bce726892068b7e22e5f8a8974afd65dcc1f410b7635a3
 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": 0.08522727272727272,
+  "epoch": 0.11363636363636363,
   "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": 1.1458,
       "step": 75
+    },
+    {
+      "epoch": 0.08636363636363636,
+      "grad_norm": 0.6192647218704224,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.3072,
+      "step": 76
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 0.555339515209198,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.7459,
+      "step": 77
+    },
+    {
+      "epoch": 0.08863636363636364,
+      "grad_norm": 0.402619868516922,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3941,
+      "step": 78
+    },
+    {
+      "epoch": 0.08977272727272727,
+      "grad_norm": 0.4111030697822571,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.1667,
+      "step": 79
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 0.6310803294181824,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.5854,
+      "step": 80
+    },
+    {
+      "epoch": 0.09204545454545454,
+      "grad_norm": 0.4028031527996063,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.4636,
+      "step": 81
+    },
+    {
+      "epoch": 0.09204545454545454,
+      "eval_loss": 1.3986175060272217,
+      "eval_runtime": 87.4361,
+      "eval_samples_per_second": 8.475,
+      "eval_steps_per_second": 1.064,
+      "step": 81
+    },
+    {
+      "epoch": 0.09318181818181819,
+      "grad_norm": 0.5828585624694824,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.9201,
+      "step": 82
+    },
+    {
+      "epoch": 0.09431818181818181,
+      "grad_norm": 0.5383720397949219,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.3849,
+      "step": 83
+    },
+    {
+      "epoch": 0.09545454545454546,
+      "grad_norm": 0.5691014528274536,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.9816,
+      "step": 84
+    },
+    {
+      "epoch": 0.09659090909090909,
+      "grad_norm": 0.4643211364746094,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5215,
+      "step": 85
+    },
+    {
+      "epoch": 0.09772727272727273,
+      "grad_norm": 0.5514132380485535,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0381,
+      "step": 86
+    },
+    {
+      "epoch": 0.09886363636363636,
+      "grad_norm": 0.3321930766105652,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.0676,
+      "step": 87
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.7636975646018982,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4628,
+      "step": 88
+    },
+    {
+      "epoch": 0.10113636363636364,
+      "grad_norm": 0.6969127655029297,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.4346,
+      "step": 89
+    },
+    {
+      "epoch": 0.10227272727272728,
+      "grad_norm": 0.6535035371780396,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.2264,
+      "step": 90
+    },
+    {
+      "epoch": 0.10227272727272728,
+      "eval_loss": 1.3976737260818481,
+      "eval_runtime": 87.4171,
+      "eval_samples_per_second": 8.477,
+      "eval_steps_per_second": 1.064,
+      "step": 90
+    },
+    {
+      "epoch": 0.10340909090909091,
+      "grad_norm": 0.4957861006259918,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.5694,
+      "step": 91
+    },
+    {
+      "epoch": 0.10454545454545454,
+      "grad_norm": 0.5834468007087708,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.157,
+      "step": 92
+    },
+    {
+      "epoch": 0.10568181818181818,
+      "grad_norm": 0.6812298893928528,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.6588,
+      "step": 93
+    },
+    {
+      "epoch": 0.10681818181818181,
+      "grad_norm": 0.46779105067253113,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.7968,
+      "step": 94
+    },
+    {
+      "epoch": 0.10795454545454546,
+      "grad_norm": 0.5582041144371033,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.7294,
+      "step": 95
+    },
+    {
+      "epoch": 0.10909090909090909,
+      "grad_norm": 0.5326647758483887,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.5638,
+      "step": 96
+    },
+    {
+      "epoch": 0.11022727272727273,
+      "grad_norm": 0.5757723450660706,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.5188,
+      "step": 97
+    },
+    {
+      "epoch": 0.11136363636363636,
+      "grad_norm": 0.8716908693313599,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.819,
+      "step": 98
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 0.588882327079773,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.8313,
+      "step": 99
+    },
+    {
+      "epoch": 0.1125,
+      "eval_loss": 1.3972293138504028,
+      "eval_runtime": 87.4494,
+      "eval_samples_per_second": 8.473,
+      "eval_steps_per_second": 1.063,
+      "step": 99
+    },
+    {
+      "epoch": 0.11363636363636363,
+      "grad_norm": 0.522475004196167,
+      "learning_rate": 0.0,
+      "loss": 1.5229,
+      "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": 5.718464111050752e+16,
+  "total_flos": 7.470363520794624e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null