Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87d9e62884d36a30d3a0b94c07899bc4c819634aa9d2810ed1fe13ebe5842a7f
+oid sha256:57e1bb167e00fb076d1c9baf78e126476918b82fc886f55772ca001bd8341ccf
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3997a81ff300eeab5bfe1b4ddde2860fa5e28713f448725ff7e8de95c474628
+oid sha256:718f8235bb907342e858ed5e19ab8b037a85cd68d9baf55c866f7344ef94af97
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7390d69c035960909a3614dd1bb0738527d72c78eaafed1ea04f6c83d7885b4d
+oid sha256:9842831702632f624f0d8eca81553d1ceb1a47fa6fd1c3fa71fed9b149a9b02d
 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": 0.021413276231263382,
+  "epoch": 0.028551034975017844,
   "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": 10.3766,
       "step": 75
+    },
+    {
+      "epoch": 0.02169878658101356,
+      "grad_norm": 0.045716289430856705,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3765,
+      "step": 76
+    },
+    {
+      "epoch": 0.02198429693076374,
+      "grad_norm": 0.03734461963176727,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3785,
+      "step": 77
+    },
+    {
+      "epoch": 0.02226980728051392,
+      "grad_norm": 0.04922715947031975,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3738,
+      "step": 78
+    },
+    {
+      "epoch": 0.022555317630264096,
+      "grad_norm": 0.0455390103161335,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3762,
+      "step": 79
+    },
+    {
+      "epoch": 0.022840827980014276,
+      "grad_norm": 0.05522376298904419,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3761,
+      "step": 80
+    },
+    {
+      "epoch": 0.023126338329764455,
+      "grad_norm": 0.057012733072042465,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3756,
+      "step": 81
+    },
+    {
+      "epoch": 0.023126338329764455,
+      "eval_loss": 10.37621784210205,
+      "eval_runtime": 42.2897,
+      "eval_samples_per_second": 69.757,
+      "eval_steps_per_second": 8.726,
+      "step": 81
+    },
+    {
+      "epoch": 0.02341184867951463,
+      "grad_norm": 0.04108881205320358,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3794,
+      "step": 82
+    },
+    {
+      "epoch": 0.02369735902926481,
+      "grad_norm": 0.05184043198823929,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3757,
+      "step": 83
+    },
+    {
+      "epoch": 0.02398286937901499,
+      "grad_norm": 0.047809191048145294,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3774,
+      "step": 84
+    },
+    {
+      "epoch": 0.02426837972876517,
+      "grad_norm": 0.0556231252849102,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3776,
+      "step": 85
+    },
+    {
+      "epoch": 0.024553890078515345,
+      "grad_norm": 0.05997423455119133,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.377,
+      "step": 86
+    },
+    {
+      "epoch": 0.024839400428265525,
+      "grad_norm": 0.04223267361521721,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3754,
+      "step": 87
+    },
+    {
+      "epoch": 0.025124910778015704,
+      "grad_norm": 0.03968475013971329,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3768,
+      "step": 88
+    },
+    {
+      "epoch": 0.02541042112776588,
+      "grad_norm": 0.04777388647198677,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3758,
+      "step": 89
+    },
+    {
+      "epoch": 0.02569593147751606,
+      "grad_norm": 0.0410679392516613,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3768,
+      "step": 90
+    },
+    {
+      "epoch": 0.02569593147751606,
+      "eval_loss": 10.376099586486816,
+      "eval_runtime": 42.2507,
+      "eval_samples_per_second": 69.821,
+      "eval_steps_per_second": 8.734,
+      "step": 90
+    },
+    {
+      "epoch": 0.02598144182726624,
+      "grad_norm": 0.0462864451110363,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.377,
+      "step": 91
+    },
+    {
+      "epoch": 0.02626695217701642,
+      "grad_norm": 0.06622043251991272,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3771,
+      "step": 92
+    },
+    {
+      "epoch": 0.026552462526766595,
+      "grad_norm": 0.04779757559299469,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3794,
+      "step": 93
+    },
+    {
+      "epoch": 0.026837972876516774,
+      "grad_norm": 0.05168018862605095,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3778,
+      "step": 94
+    },
+    {
+      "epoch": 0.027123483226266953,
+      "grad_norm": 0.051283229142427444,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3764,
+      "step": 95
+    },
+    {
+      "epoch": 0.02740899357601713,
+      "grad_norm": 0.05247614160180092,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3779,
+      "step": 96
+    },
+    {
+      "epoch": 0.02769450392576731,
+      "grad_norm": 0.05288613587617874,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3728,
+      "step": 97
+    },
+    {
+      "epoch": 0.027980014275517488,
+      "grad_norm": 0.057692740112543106,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3739,
+      "step": 98
+    },
+    {
+      "epoch": 0.028265524625267664,
+      "grad_norm": 0.04921926185488701,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.378,
+      "step": 99
+    },
+    {
+      "epoch": 0.028265524625267664,
+      "eval_loss": 10.376075744628906,
+      "eval_runtime": 42.1901,
+      "eval_samples_per_second": 69.922,
+      "eval_steps_per_second": 8.746,
+      "step": 99
+    },
+    {
+      "epoch": 0.028551034975017844,
+      "grad_norm": 0.046121589839458466,
+      "learning_rate": 0.0,
+      "loss": 10.3787,
+      "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": 7845366988800.0,
+  "total_flos": 10460489318400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null