Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c3cca6437ff819b32f53cafd1ff181716acb23e5f8cf2d76f4b3ff1a3f028b
+oid sha256:f7b0fd3c6eb733cf610d18a279f6ac8b53a38bba7c483291a1de7b4476b6491a
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2042d518fedc45dc67cc3f4405da7ffbfb1d9b1adc33857f38e7e7e2ab05603a
+oid sha256:40d8a311099d61f5d37e97230abd57d290f0bcc86ef8429068b1efa61fcf6607
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62577c705b5e0903a8d1b61ec40f0dd9672c14fc3d9beee0560e32a4d664d0c
+oid sha256:29dfce459bfef11512041671bca91604f66b1ddbefa3947517889259b1e8c185
 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": 1.5957446808510638,
+  "epoch": 2.127659574468085,
   "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": 10.323,
       "step": 75
+    },
+    {
+      "epoch": 1.6170212765957448,
+      "grad_norm": 0.49834099411964417,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3294,
+      "step": 76
+    },
+    {
+      "epoch": 1.6382978723404256,
+      "grad_norm": 0.4265074133872986,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3262,
+      "step": 77
+    },
+    {
+      "epoch": 1.6595744680851063,
+      "grad_norm": 0.4176177382469177,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3285,
+      "step": 78
+    },
+    {
+      "epoch": 1.6808510638297873,
+      "grad_norm": 0.3886817693710327,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3125,
+      "step": 79
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.37757551670074463,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.318,
+      "step": 80
+    },
+    {
+      "epoch": 1.7234042553191489,
+      "grad_norm": 0.40319740772247314,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3257,
+      "step": 81
+    },
+    {
+      "epoch": 1.7234042553191489,
+      "eval_loss": 10.324304580688477,
+      "eval_runtime": 0.1631,
+      "eval_samples_per_second": 245.274,
+      "eval_steps_per_second": 30.659,
+      "step": 81
+    },
+    {
+      "epoch": 1.7446808510638299,
+      "grad_norm": 0.41633689403533936,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3251,
+      "step": 82
+    },
+    {
+      "epoch": 1.7659574468085106,
+      "grad_norm": 0.4362964332103729,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3228,
+      "step": 83
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "grad_norm": 0.3783886730670929,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3214,
+      "step": 84
+    },
+    {
+      "epoch": 1.8085106382978724,
+      "grad_norm": 0.41345518827438354,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3228,
+      "step": 85
+    },
+    {
+      "epoch": 1.8297872340425532,
+      "grad_norm": 0.46816903352737427,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3294,
+      "step": 86
+    },
+    {
+      "epoch": 1.851063829787234,
+      "grad_norm": 0.41516950726509094,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3271,
+      "step": 87
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 0.4659665822982788,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3208,
+      "step": 88
+    },
+    {
+      "epoch": 1.8936170212765957,
+      "grad_norm": 0.37368547916412354,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3361,
+      "step": 89
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 0.42361190915107727,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.32,
+      "step": 90
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "eval_loss": 10.322896957397461,
+      "eval_runtime": 0.1794,
+      "eval_samples_per_second": 223.005,
+      "eval_steps_per_second": 27.876,
+      "step": 90
+    },
+    {
+      "epoch": 1.9361702127659575,
+      "grad_norm": 0.38452357053756714,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3245,
+      "step": 91
+    },
+    {
+      "epoch": 1.9574468085106385,
+      "grad_norm": 0.404781699180603,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3272,
+      "step": 92
+    },
+    {
+      "epoch": 1.978723404255319,
+      "grad_norm": 0.3733466565608978,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3191,
+      "step": 93
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.40015843510627747,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.324,
+      "step": 94
+    },
+    {
+      "epoch": 2.021276595744681,
+      "grad_norm": 0.4130217134952545,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3231,
+      "step": 95
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 0.46308839321136475,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3252,
+      "step": 96
+    },
+    {
+      "epoch": 2.0638297872340425,
+      "grad_norm": 0.4061806797981262,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3233,
+      "step": 97
+    },
+    {
+      "epoch": 2.0851063829787235,
+      "grad_norm": 0.46338579058647156,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3277,
+      "step": 98
+    },
+    {
+      "epoch": 2.106382978723404,
+      "grad_norm": 0.4338410794734955,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.321,
+      "step": 99
+    },
+    {
+      "epoch": 2.106382978723404,
+      "eval_loss": 10.322647094726562,
+      "eval_runtime": 0.195,
+      "eval_samples_per_second": 205.084,
+      "eval_steps_per_second": 25.635,
+      "step": 99
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.440590500831604,
+      "learning_rate": 0.0,
+      "loss": 10.3241,
+      "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": 3922683494400.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null