Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e8da19d76c382a06fe3bc055f8406ba65f38cbb260ec6b25f5e99be62579e7
+oid sha256:b1fcbfaec0e2fb4bb00886676cd8c01744b44c2212d501fd80fb7af091763722
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ccf27f75fb2a3c8bbac22620f026b824a5524e1ac0c0f2584475e9ef6663413
+oid sha256:772662c5e9fe9b08c01ef6271d4490d3149183f0e092e7530909df4682a0ba2e
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c7f44ec6860003f13de57bd2ad679abc76372e696f0ba64dcb096ad8c2d194
+oid sha256:c6a3bdea21e6ba079ccbba624ec1dfb599a55306a888996d433b7da6e98cbcc2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6efc3cf2283ba2318df09b4fccd81fc2c7c92f336f9b8fbed31252acffe51a
+oid sha256:9a0972cadd551b6d9210f90d9b2e3421a9d27b4b199b21668663b7517dda9ca7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec5a5fa365a025d7b72e73ba5ae61435c717d5192c0a548efd67efffa7d01f8
+oid sha256:052d2643f94d39de729385018900f6560552f49ed10facb0a7531f28b31aadc0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef8374d5b4a7b565c654f01afc3676c24946d4955ee4d27506c6d5576f109d2
+oid sha256:efb31cd55af594dd5a265c5dff7191e1e4857df34d419a4bf8db7fd4e3cef497
 size 15024

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": 0.03259452411994785,
+  "epoch": 0.0434593654932638,
   "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": 10.21,
       "step": 75
+    },
+    {
+      "epoch": 0.03302911777488049,
+      "grad_norm": 1.3915892839431763,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.2071,
+      "step": 76
+    },
+    {
+      "epoch": 0.03346371142981312,
+      "grad_norm": 1.4067327976226807,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.1902,
+      "step": 77
+    },
+    {
+      "epoch": 0.03389830508474576,
+      "grad_norm": 1.4121757745742798,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.192,
+      "step": 78
+    },
+    {
+      "epoch": 0.0343328987396784,
+      "grad_norm": 1.445264220237732,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.2108,
+      "step": 79
+    },
+    {
+      "epoch": 0.034767492394611035,
+      "grad_norm": 1.4060300588607788,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.1989,
+      "step": 80
+    },
+    {
+      "epoch": 0.035202086049543675,
+      "grad_norm": 1.4106123447418213,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.035202086049543675,
+      "eval_loss": 10.19814395904541,
+      "eval_runtime": 4.4149,
+      "eval_samples_per_second": 1755.627,
+      "eval_steps_per_second": 55.04,
+      "step": 81
+    },
+    {
+      "epoch": 0.035636679704476315,
+      "grad_norm": 1.4134420156478882,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.2071,
+      "step": 82
+    },
+    {
+      "epoch": 0.036071273359408955,
+      "grad_norm": 1.3421871662139893,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.199,
+      "step": 83
+    },
+    {
+      "epoch": 0.03650586701434159,
+      "grad_norm": 1.3774632215499878,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.19,
+      "step": 84
+    },
+    {
+      "epoch": 0.03694046066927423,
+      "grad_norm": 1.3491445779800415,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.1879,
+      "step": 85
+    },
+    {
+      "epoch": 0.03737505432420687,
+      "grad_norm": 1.3587225675582886,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.1965,
+      "step": 86
+    },
+    {
+      "epoch": 0.03780964797913951,
+      "grad_norm": 1.3620103597640991,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.1911,
+      "step": 87
+    },
+    {
+      "epoch": 0.03824424163407214,
+      "grad_norm": 1.337594985961914,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.1873,
+      "step": 88
+    },
+    {
+      "epoch": 0.03867883528900478,
+      "grad_norm": 1.3280407190322876,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.2072,
+      "step": 89
+    },
+    {
+      "epoch": 0.03911342894393742,
+      "grad_norm": 1.3855839967727661,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.2045,
+      "step": 90
+    },
+    {
+      "epoch": 0.03911342894393742,
+      "eval_loss": 10.195647239685059,
+      "eval_runtime": 4.3777,
+      "eval_samples_per_second": 1770.565,
+      "eval_steps_per_second": 55.509,
+      "step": 90
+    },
+    {
+      "epoch": 0.03954802259887006,
+      "grad_norm": 1.3364759683609009,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.1887,
+      "step": 91
+    },
+    {
+      "epoch": 0.03998261625380269,
+      "grad_norm": 1.2921222448349,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.1892,
+      "step": 92
+    },
+    {
+      "epoch": 0.04041720990873533,
+      "grad_norm": 1.3389850854873657,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.2107,
+      "step": 93
+    },
+    {
+      "epoch": 0.04085180356366797,
+      "grad_norm": 1.3627759218215942,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.2064,
+      "step": 94
+    },
+    {
+      "epoch": 0.041286397218600605,
+      "grad_norm": 1.3275415897369385,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.1928,
+      "step": 95
+    },
+    {
+      "epoch": 0.041720990873533245,
+      "grad_norm": 1.3738682270050049,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.2054,
+      "step": 96
+    },
+    {
+      "epoch": 0.042155584528465885,
+      "grad_norm": 1.3698922395706177,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.2082,
+      "step": 97
+    },
+    {
+      "epoch": 0.042590178183398525,
+      "grad_norm": 1.3257871866226196,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.1871,
+      "step": 98
+    },
+    {
+      "epoch": 0.04302477183833116,
+      "grad_norm": 1.3610293865203857,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.192,
+      "step": 99
+    },
+    {
+      "epoch": 0.04302477183833116,
+      "eval_loss": 10.195563316345215,
+      "eval_runtime": 4.3766,
+      "eval_samples_per_second": 1771.0,
+      "eval_steps_per_second": 55.522,
+      "step": 99
+    },
+    {
+      "epoch": 0.0434593654932638,
+      "grad_norm": 1.345515251159668,
+      "learning_rate": 0.0,
+      "loss": 10.1928,
+      "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": 15690733977600.0,
+  "total_flos": 20920978636800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null