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:efa4d4726974ff1da8bbe3364ba0551164bc8e3271eab228d2fecf87d253214c
+oid sha256:8696ee1d102a7631dc05b3f503cce1ca4d6c75bf3b11ac897c4e9fdec9665132
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c463e5f2beb9b34079bb414c9f4a3dad36873d18db2fa180b2b19ed61d08f4ce
+oid sha256:ce5f6288b74d8ff127077c95faf045cfc7cc25361de06114a888b16a8cfdb448
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
+oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
 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": 0.02031969655919805,
+  "epoch": 0.0270929287455974,
   "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": 11.76,
       "step": 75
+    },
+    {
+      "epoch": 0.020590625846654022,
+      "grad_norm": 0.0818638727068901,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 11.7632,
+      "step": 76
+    },
+    {
+      "epoch": 0.020861555134109998,
+      "grad_norm": 0.07441042363643646,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 11.7585,
+      "step": 77
+    },
+    {
+      "epoch": 0.02113248442156597,
+      "grad_norm": 0.10154496878385544,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 11.753,
+      "step": 78
+    },
+    {
+      "epoch": 0.021403413709021945,
+      "grad_norm": 0.10243283957242966,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 11.7583,
+      "step": 79
+    },
+    {
+      "epoch": 0.02167434299647792,
+      "grad_norm": 0.049746040254831314,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 11.7589,
+      "step": 80
+    },
+    {
+      "epoch": 0.021945272283933892,
+      "grad_norm": 0.12136776000261307,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 11.7466,
+      "step": 81
+    },
+    {
+      "epoch": 0.021945272283933892,
+      "eval_loss": 11.755950927734375,
+      "eval_runtime": 74.6606,
+      "eval_samples_per_second": 41.628,
+      "eval_steps_per_second": 5.21,
+      "step": 81
+    },
+    {
+      "epoch": 0.022216201571389867,
+      "grad_norm": 0.0862363949418068,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.7668,
+      "step": 82
+    },
+    {
+      "epoch": 0.022487130858845843,
+      "grad_norm": 0.06779694557189941,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 11.7611,
+      "step": 83
+    },
+    {
+      "epoch": 0.022758060146301815,
+      "grad_norm": 0.10687223821878433,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 11.7516,
+      "step": 84
+    },
+    {
+      "epoch": 0.02302898943375779,
+      "grad_norm": 0.13849890232086182,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.7537,
+      "step": 85
+    },
+    {
+      "epoch": 0.02329991872121376,
+      "grad_norm": 0.07643585652112961,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 11.7572,
+      "step": 86
+    },
+    {
+      "epoch": 0.023570848008669737,
+      "grad_norm": 0.06562468409538269,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 11.7595,
+      "step": 87
+    },
+    {
+      "epoch": 0.023841777296125712,
+      "grad_norm": 0.05346398055553436,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 11.7635,
+      "step": 88
+    },
+    {
+      "epoch": 0.024112706583581684,
+      "grad_norm": 0.11879397928714752,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 11.7538,
+      "step": 89
+    },
+    {
+      "epoch": 0.02438363587103766,
+      "grad_norm": 0.14324668049812317,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.7448,
+      "step": 90
+    },
+    {
+      "epoch": 0.02438363587103766,
+      "eval_loss": 11.755816459655762,
+      "eval_runtime": 74.7138,
+      "eval_samples_per_second": 41.599,
+      "eval_steps_per_second": 5.207,
+      "step": 90
+    },
+    {
+      "epoch": 0.024654565158493635,
+      "grad_norm": 0.08946627378463745,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.7588,
+      "step": 91
+    },
+    {
+      "epoch": 0.024925494445949607,
+      "grad_norm": 0.11015325784683228,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 11.7442,
+      "step": 92
+    },
+    {
+      "epoch": 0.025196423733405582,
+      "grad_norm": 0.07804310321807861,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 11.7548,
+      "step": 93
+    },
+    {
+      "epoch": 0.025467353020861554,
+      "grad_norm": 0.13722215592861176,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 11.7452,
+      "step": 94
+    },
+    {
+      "epoch": 0.02573828230831753,
+      "grad_norm": 0.06574387848377228,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 11.7621,
+      "step": 95
+    },
+    {
+      "epoch": 0.026009211595773504,
+      "grad_norm": 0.08705904334783554,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 11.7529,
+      "step": 96
+    },
+    {
+      "epoch": 0.026280140883229476,
+      "grad_norm": 0.09055496007204056,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 11.752,
+      "step": 97
+    },
+    {
+      "epoch": 0.02655107017068545,
+      "grad_norm": 0.06037510558962822,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 11.7606,
+      "step": 98
+    },
+    {
+      "epoch": 0.026821999458141427,
+      "grad_norm": 0.0861784890294075,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 11.7525,
+      "step": 99
+    },
+    {
+      "epoch": 0.026821999458141427,
+      "eval_loss": 11.755788803100586,
+      "eval_runtime": 74.7195,
+      "eval_samples_per_second": 41.596,
+      "eval_steps_per_second": 5.206,
+      "step": 99
+    },
+    {
+      "epoch": 0.0270929287455974,
+      "grad_norm": 0.09977780282497406,
+      "learning_rate": 0.0,
+      "loss": 11.7579,
+      "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": 15277503283200.0,
+  "total_flos": 20370004377600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null