Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee0957a5b7e46192855ee55f38fc0e4fbd5d00d9365d2cfc4fa2463bd49002d
+oid sha256:f53058d424952854de753c16ccf54cc78610cde1549772281bf1fa2a21da53f9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd30eced465fdafcc5e39f471f305c21206d4fb7c0ea6e1553be9e7d700041d
+oid sha256:59f41bae733262d9125db89b7983e61d14a556837eed6eaabd90215094e95bb6
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4cf3b2cc7e50f923b1fadf54f9e4504518ac2eea1ca9b58f50df1ec79903d54
+oid sha256:de25ffc97567cae899dde86253d6110eb610fd40635798ce90cc424379441ec7
 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": 0.11355034065102196,
+  "epoch": 0.1514004542013626,
   "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": 0.5487,
       "step": 75
+    },
+    {
+      "epoch": 0.11506434519303559,
+      "grad_norm": 0.4295434355735779,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.5305,
+      "step": 76
+    },
+    {
+      "epoch": 0.1165783497350492,
+      "grad_norm": 0.46621814370155334,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.6412,
+      "step": 77
+    },
+    {
+      "epoch": 0.11809235427706283,
+      "grad_norm": 0.4103274941444397,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6237,
+      "step": 78
+    },
+    {
+      "epoch": 0.11960635881907646,
+      "grad_norm": 0.46474939584732056,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.5917,
+      "step": 79
+    },
+    {
+      "epoch": 0.12112036336109008,
+      "grad_norm": 0.43910786509513855,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6498,
+      "step": 80
+    },
+    {
+      "epoch": 0.12263436790310371,
+      "grad_norm": 0.44320958852767944,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.6044,
+      "step": 81
+    },
+    {
+      "epoch": 0.12263436790310371,
+      "eval_loss": 0.5315753817558289,
+      "eval_runtime": 127.3914,
+      "eval_samples_per_second": 4.365,
+      "eval_steps_per_second": 0.549,
+      "step": 81
+    },
+    {
+      "epoch": 0.12414837244511734,
+      "grad_norm": 0.46327945590019226,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6136,
+      "step": 82
+    },
+    {
+      "epoch": 0.12566237698713095,
+      "grad_norm": 0.421197772026062,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.6935,
+      "step": 83
+    },
+    {
+      "epoch": 0.1271763815291446,
+      "grad_norm": 0.4459386467933655,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.5118,
+      "step": 84
+    },
+    {
+      "epoch": 0.1286903860711582,
+      "grad_norm": 0.4398004710674286,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.616,
+      "step": 85
+    },
+    {
+      "epoch": 0.13020439061317185,
+      "grad_norm": 0.42645105719566345,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6304,
+      "step": 86
+    },
+    {
+      "epoch": 0.13171839515518546,
+      "grad_norm": 0.4002155661582947,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.5812,
+      "step": 87
+    },
+    {
+      "epoch": 0.1332323996971991,
+      "grad_norm": 0.5312856435775757,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5926,
+      "step": 88
+    },
+    {
+      "epoch": 0.13474640423921272,
+      "grad_norm": 0.47034987807273865,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.5159,
+      "step": 89
+    },
+    {
+      "epoch": 0.13626040878122633,
+      "grad_norm": 0.47122740745544434,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.5381,
+      "step": 90
+    },
+    {
+      "epoch": 0.13626040878122633,
+      "eval_loss": 0.5309846997261047,
+      "eval_runtime": 127.4539,
+      "eval_samples_per_second": 4.362,
+      "eval_steps_per_second": 0.549,
+      "step": 90
+    },
+    {
+      "epoch": 0.13777441332323997,
+      "grad_norm": 0.6037063002586365,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4144,
+      "step": 91
+    },
+    {
+      "epoch": 0.1392884178652536,
+      "grad_norm": 0.44338667392730713,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.5655,
+      "step": 92
+    },
+    {
+      "epoch": 0.14080242240726723,
+      "grad_norm": 0.48680365085601807,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.6424,
+      "step": 93
+    },
+    {
+      "epoch": 0.14231642694928084,
+      "grad_norm": 0.469305157661438,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6424,
+      "step": 94
+    },
+    {
+      "epoch": 0.14383043149129449,
+      "grad_norm": 0.42999425530433655,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.521,
+      "step": 95
+    },
+    {
+      "epoch": 0.1453444360333081,
+      "grad_norm": 0.3979586660861969,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6096,
+      "step": 96
+    },
+    {
+      "epoch": 0.1468584405753217,
+      "grad_norm": 0.4476478397846222,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.5375,
+      "step": 97
+    },
+    {
+      "epoch": 0.14837244511733536,
+      "grad_norm": 0.37695378065109253,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.5883,
+      "step": 98
+    },
+    {
+      "epoch": 0.14988644965934897,
+      "grad_norm": 0.5061571598052979,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.5421,
+      "step": 99
+    },
+    {
+      "epoch": 0.14988644965934897,
+      "eval_loss": 0.5308008193969727,
+      "eval_runtime": 127.4561,
+      "eval_samples_per_second": 4.362,
+      "eval_steps_per_second": 0.549,
+      "step": 99
+    },
+    {
+      "epoch": 0.1514004542013626,
+      "grad_norm": 0.45723745226860046,
+      "learning_rate": 0.0,
+      "loss": 0.5256,
+      "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": 1.0571893790736384e+17,
+  "total_flos": 1.405876402347049e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null