Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8831358bf45f54756e3ee2363320466f18c85192b2cbdcde06ad096fa9fdb24a
+oid sha256:be7857e7ebce68690e22d9e6fd60714fed7f79a28bf341640b064fc6b936530d
 size 2269195160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa15eae934bb5d69aa6f53eea85e92658da6e9662418e780a1d863c052417b5
+oid sha256:9fabe4486b14232045cd3e18d0d5adcf92a73df8d75031df63e0e4cba73826c3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.14720314033366044,
+  "epoch": 0.19627085377821393,
   "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": 0.076,
       "step": 75
+    },
+    {
+      "epoch": 0.1491658488714426,
+      "grad_norm": 0.7612863183021545,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0628,
+      "step": 76
+    },
+    {
+      "epoch": 0.15112855740922473,
+      "grad_norm": 1.5379414558410645,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0502,
+      "step": 77
+    },
+    {
+      "epoch": 0.15309126594700687,
+      "grad_norm": 0.42116737365722656,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0216,
+      "step": 78
+    },
+    {
+      "epoch": 0.155053974484789,
+      "grad_norm": 0.6533110737800598,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0357,
+      "step": 79
+    },
+    {
+      "epoch": 0.15701668302257116,
+      "grad_norm": 0.4809662401676178,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0267,
+      "step": 80
+    },
+    {
+      "epoch": 0.1589793915603533,
+      "grad_norm": 0.7027826309204102,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0598,
+      "step": 81
+    },
+    {
+      "epoch": 0.1589793915603533,
+      "eval_loss": 0.06062833219766617,
+      "eval_runtime": 51.8646,
+      "eval_samples_per_second": 8.272,
+      "eval_steps_per_second": 1.041,
+      "step": 81
+    },
+    {
+      "epoch": 0.16094210009813542,
+      "grad_norm": 0.9778656363487244,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1188,
+      "step": 82
+    },
+    {
+      "epoch": 0.16290480863591755,
+      "grad_norm": 1.2301158905029297,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0951,
+      "step": 83
+    },
+    {
+      "epoch": 0.1648675171736997,
+      "grad_norm": 0.6400152444839478,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0271,
+      "step": 84
+    },
+    {
+      "epoch": 0.16683022571148184,
+      "grad_norm": 1.310447096824646,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1029,
+      "step": 85
+    },
+    {
+      "epoch": 0.16879293424926398,
+      "grad_norm": 1.2886770963668823,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0809,
+      "step": 86
+    },
+    {
+      "epoch": 0.17075564278704614,
+      "grad_norm": 1.1671074628829956,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0762,
+      "step": 87
+    },
+    {
+      "epoch": 0.17271835132482827,
+      "grad_norm": 0.9179717302322388,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0965,
+      "step": 88
+    },
+    {
+      "epoch": 0.1746810598626104,
+      "grad_norm": 1.4556831121444702,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0608,
+      "step": 89
+    },
+    {
+      "epoch": 0.17664376840039253,
+      "grad_norm": 1.142041802406311,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0428,
+      "step": 90
+    },
+    {
+      "epoch": 0.17664376840039253,
+      "eval_loss": 0.056533679366111755,
+      "eval_runtime": 51.8311,
+      "eval_samples_per_second": 8.277,
+      "eval_steps_per_second": 1.042,
+      "step": 90
+    },
+    {
+      "epoch": 0.1786064769381747,
+      "grad_norm": 0.7308371663093567,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0348,
+      "step": 91
+    },
+    {
+      "epoch": 0.18056918547595682,
+      "grad_norm": 0.7715025544166565,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0448,
+      "step": 92
+    },
+    {
+      "epoch": 0.18253189401373895,
+      "grad_norm": 1.3858311176300049,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1043,
+      "step": 93
+    },
+    {
+      "epoch": 0.1844946025515211,
+      "grad_norm": 0.7281399369239807,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.05,
+      "step": 94
+    },
+    {
+      "epoch": 0.18645731108930325,
+      "grad_norm": 0.9206270575523376,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0612,
+      "step": 95
+    },
+    {
+      "epoch": 0.18842001962708538,
+      "grad_norm": 0.26463988423347473,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0167,
+      "step": 96
+    },
+    {
+      "epoch": 0.1903827281648675,
+      "grad_norm": 0.6293405294418335,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.05,
+      "step": 97
+    },
+    {
+      "epoch": 0.19234543670264967,
+      "grad_norm": 1.3119679689407349,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.1115,
+      "step": 98
+    },
+    {
+      "epoch": 0.1943081452404318,
+      "grad_norm": 0.8040010333061218,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0342,
+      "step": 99
+    },
+    {
+      "epoch": 0.1943081452404318,
+      "eval_loss": 0.05402405560016632,
+      "eval_runtime": 51.836,
+      "eval_samples_per_second": 8.276,
+      "eval_steps_per_second": 1.042,
+      "step": 99
+    },
+    {
+      "epoch": 0.19627085377821393,
+      "grad_norm": 0.733824610710144,
+      "learning_rate": 0.0,
+      "loss": 0.0434,
+      "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": 5.56415764660224e+16,
+  "total_flos": 7.41887686213632e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null