Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923e092b04b7993c38e5965ba3a9daa9a9106f64cf13ef8f5624c961d41f2819
+oid sha256:761fac6e5e455aed1a9f06c84188523ca841993e1d35f4998dd13edf8fcadf59
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d53e2215151a779b3510d02929cc59f83098dd407fe0df8076ecc025d7aa6a
+oid sha256:df8091890776db15a54d2723b9490119a024b0923a609f10847f33da68804213
 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": 0.6097560975609756,
+  "epoch": 0.8130081300813008,
   "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": 10.3638,
       "step": 75
+    },
+    {
+      "epoch": 0.6178861788617886,
+      "grad_norm": 0.19670933485031128,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3652,
+      "step": 76
+    },
+    {
+      "epoch": 0.6260162601626016,
+      "grad_norm": 0.1680048257112503,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3691,
+      "step": 77
+    },
+    {
+      "epoch": 0.6341463414634146,
+      "grad_norm": 0.18312686681747437,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3639,
+      "step": 78
+    },
+    {
+      "epoch": 0.6422764227642277,
+      "grad_norm": 0.19759897887706757,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3654,
+      "step": 79
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 0.18835864961147308,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3626,
+      "step": 80
+    },
+    {
+      "epoch": 0.6585365853658537,
+      "grad_norm": 0.19441981613636017,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.363,
+      "step": 81
+    },
+    {
+      "epoch": 0.6585365853658537,
+      "eval_loss": 10.365053176879883,
+      "eval_runtime": 0.4647,
+      "eval_samples_per_second": 893.116,
+      "eval_steps_per_second": 27.977,
+      "step": 81
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.19026274979114532,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.364,
+      "step": 82
+    },
+    {
+      "epoch": 0.6747967479674797,
+      "grad_norm": 0.19429843127727509,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3648,
+      "step": 83
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 0.19045278429985046,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3653,
+      "step": 84
+    },
+    {
+      "epoch": 0.6910569105691057,
+      "grad_norm": 0.16659685969352722,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3641,
+      "step": 85
+    },
+    {
+      "epoch": 0.6991869918699187,
+      "grad_norm": 0.20563609898090363,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.364,
+      "step": 86
+    },
+    {
+      "epoch": 0.7073170731707317,
+      "grad_norm": 0.18013019859790802,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3668,
+      "step": 87
+    },
+    {
+      "epoch": 0.7154471544715447,
+      "grad_norm": 0.1857130080461502,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3632,
+      "step": 88
+    },
+    {
+      "epoch": 0.7235772357723578,
+      "grad_norm": 0.17810818552970886,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3671,
+      "step": 89
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.19361822307109833,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3636,
+      "step": 90
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "eval_loss": 10.364516258239746,
+      "eval_runtime": 0.4622,
+      "eval_samples_per_second": 897.889,
+      "eval_steps_per_second": 28.127,
+      "step": 90
+    },
+    {
+      "epoch": 0.7398373983739838,
+      "grad_norm": 0.18621030449867249,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3638,
+      "step": 91
+    },
+    {
+      "epoch": 0.7479674796747967,
+      "grad_norm": 0.18979115784168243,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3639,
+      "step": 92
+    },
+    {
+      "epoch": 0.7560975609756098,
+      "grad_norm": 0.15834961831569672,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3646,
+      "step": 93
+    },
+    {
+      "epoch": 0.7642276422764228,
+      "grad_norm": 0.19409507513046265,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3626,
+      "step": 94
+    },
+    {
+      "epoch": 0.7723577235772358,
+      "grad_norm": 0.18269585072994232,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3662,
+      "step": 95
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.194476917386055,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3649,
+      "step": 96
+    },
+    {
+      "epoch": 0.7886178861788617,
+      "grad_norm": 0.18111790716648102,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3666,
+      "step": 97
+    },
+    {
+      "epoch": 0.7967479674796748,
+      "grad_norm": 0.18669374287128448,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3651,
+      "step": 98
+    },
+    {
+      "epoch": 0.8048780487804879,
+      "grad_norm": 0.1975618600845337,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3624,
+      "step": 99
+    },
+    {
+      "epoch": 0.8048780487804879,
+      "eval_loss": 10.364422798156738,
+      "eval_runtime": 0.4591,
+      "eval_samples_per_second": 904.003,
+      "eval_steps_per_second": 28.318,
+      "step": 99
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 0.21033941209316254,
+      "learning_rate": 0.0,
+      "loss": 10.3612,
+      "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": 31119955722240.0,
+  "total_flos": 41475840147456.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null