Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94fc3cef370f490431ed1c5e986456245ce34b4b4c1c334d19ffa8e5e48deb7a
+oid sha256:437aff9106a6e5a7771edd4334e52c41e96ec6493f2720470dc60dc0b2d7388b
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:837bda165dafca792898b682d37cd328e3cc838973e867dd3169e4a11c20de74
+oid sha256:0ff24b920611c443289ccfa5ee00c39244c02e39cbce2f4c01547f6e6daa4f19
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b96fd3015aa4f507daff39a88b3149e32f8b490274439d7bb1f334bfbd1885a2
+oid sha256:22765a439d32d57db97a36543eb6c7bceff308abeeed2ac97feb23116cd8acd3
 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": 0.012656091798852515,
+  "epoch": 0.016874789065136685,
   "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": 0.8245,
       "step": 75
+    },
+    {
+      "epoch": 0.01282483968950388,
+      "grad_norm": 0.261058509349823,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.7754,
+      "step": 76
+    },
+    {
+      "epoch": 0.012993587580155248,
+      "grad_norm": 0.272770494222641,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.758,
+      "step": 77
+    },
+    {
+      "epoch": 0.013162335470806615,
+      "grad_norm": 0.20555861294269562,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.661,
+      "step": 78
+    },
+    {
+      "epoch": 0.013331083361457982,
+      "grad_norm": 0.27304545044898987,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.6893,
+      "step": 79
+    },
+    {
+      "epoch": 0.01349983125210935,
+      "grad_norm": 0.26374804973602295,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6545,
+      "step": 80
+    },
+    {
+      "epoch": 0.013668579142760715,
+      "grad_norm": 0.24898526072502136,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.8405,
+      "step": 81
+    },
+    {
+      "epoch": 0.013668579142760715,
+      "eval_loss": 0.7369834184646606,
+      "eval_runtime": 672.429,
+      "eval_samples_per_second": 7.421,
+      "eval_steps_per_second": 0.928,
+      "step": 81
+    },
+    {
+      "epoch": 0.013837327033412082,
+      "grad_norm": 0.2206796407699585,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.748,
+      "step": 82
+    },
+    {
+      "epoch": 0.01400607492406345,
+      "grad_norm": 0.2410127967596054,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.8175,
+      "step": 83
+    },
+    {
+      "epoch": 0.014174822814714817,
+      "grad_norm": 0.2583429217338562,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6929,
+      "step": 84
+    },
+    {
+      "epoch": 0.014343570705366182,
+      "grad_norm": 0.22913764417171478,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6919,
+      "step": 85
+    },
+    {
+      "epoch": 0.01451231859601755,
+      "grad_norm": 0.2943527102470398,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.8743,
+      "step": 86
+    },
+    {
+      "epoch": 0.014681066486668917,
+      "grad_norm": 0.22609929740428925,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.7479,
+      "step": 87
+    },
+    {
+      "epoch": 0.014849814377320284,
+      "grad_norm": 0.21955016255378723,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.6898,
+      "step": 88
+    },
+    {
+      "epoch": 0.015018562267971651,
+      "grad_norm": 0.22741229832172394,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.7654,
+      "step": 89
+    },
+    {
+      "epoch": 0.015187310158623017,
+      "grad_norm": 0.21667438745498657,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.6732,
+      "step": 90
+    },
+    {
+      "epoch": 0.015187310158623017,
+      "eval_loss": 0.7360543012619019,
+      "eval_runtime": 672.0453,
+      "eval_samples_per_second": 7.425,
+      "eval_steps_per_second": 0.929,
+      "step": 90
+    },
+    {
+      "epoch": 0.015356058049274384,
+      "grad_norm": 0.24503310024738312,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.7076,
+      "step": 91
+    },
+    {
+      "epoch": 0.015524805939925751,
+      "grad_norm": 0.3187081217765808,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.8483,
+      "step": 92
+    },
+    {
+      "epoch": 0.015693553830577116,
+      "grad_norm": 0.25870633125305176,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.645,
+      "step": 93
+    },
+    {
+      "epoch": 0.015862301721228485,
+      "grad_norm": 0.2800111472606659,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.7773,
+      "step": 94
+    },
+    {
+      "epoch": 0.01603104961187985,
+      "grad_norm": 0.24954961240291595,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.7345,
+      "step": 95
+    },
+    {
+      "epoch": 0.01619979750253122,
+      "grad_norm": 0.2462889552116394,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.7016,
+      "step": 96
+    },
+    {
+      "epoch": 0.016368545393182585,
+      "grad_norm": 0.2462126463651657,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.7157,
+      "step": 97
+    },
+    {
+      "epoch": 0.01653729328383395,
+      "grad_norm": 0.23672252893447876,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.8213,
+      "step": 98
+    },
+    {
+      "epoch": 0.01670604117448532,
+      "grad_norm": 0.23794856667518616,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.6336,
+      "step": 99
+    },
+    {
+      "epoch": 0.01670604117448532,
+      "eval_loss": 0.7358615398406982,
+      "eval_runtime": 672.0258,
+      "eval_samples_per_second": 7.425,
+      "eval_steps_per_second": 0.929,
+      "step": 99
+    },
+    {
+      "epoch": 0.016874789065136685,
+      "grad_norm": 0.2128089815378189,
+      "learning_rate": 0.0,
+      "loss": 0.6105,
+      "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": 6.181229992869888e+16,
+  "total_flos": 8.296731166900224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null