Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e23173ae6701db4d169e3856983aa161251e28d7f04b59986f44cb65a1682ac9
+oid sha256:113f706992506cea8c8e085086b48f49b7d342c64975086f3f07e6a7b37dac48
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fab165051e5a811ad823cc1bacbda73c2760f1b6c04aca17f5e5dd5aaeceba3
+oid sha256:f7d5645ae36a260b67156dffdc78186e268372589eef63e2892a62eb1f7a75b8
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd5f96a0c54d9c7fc696cd2de657ab87643082dd5b551287b669ca224896764
+oid sha256:68d8240f8b64502e023794a3da2d8c6aa526ac0f753e37b389fdd87097fabd55
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b163f39dfe27dc2b3dbffe608a672c5c24782a59c01d78ba19fb42e537b1c880
+oid sha256:f117663bca47e6dbbfa0c77eb3eb3ed1ed85a3dd0c9f866227e737a73eb5c422
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c2e9f653665898599ba92c14fead2834af70cd76abf31d5deed9f0b6254a84
+oid sha256:7a7d87a0b1f18c774b632725605bde69fd2b07215dcf9ac48e19e6caa47a6c61
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b04fb1bf3df1d2f6147ab7478673cead0a366e5db2e2dbeb350bb77196eaef95
+oid sha256:f3daeca24213bd8e7f686bd89b9bb6ba8b6995471fd68b15febf485beb753100
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2032520325203252,
+  "epoch": 0.4065040650406504,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 10.3812,
       "step": 25
+    },
+    {
+      "epoch": 0.21138211382113822,
+      "grad_norm": 0.11849161982536316,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3872,
+      "step": 26
+    },
+    {
+      "epoch": 0.21951219512195122,
+      "grad_norm": 0.10534635931253433,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3801,
+      "step": 27
+    },
+    {
+      "epoch": 0.21951219512195122,
+      "eval_loss": 10.382162094116211,
+      "eval_runtime": 0.4726,
+      "eval_samples_per_second": 878.139,
+      "eval_steps_per_second": 27.508,
+      "step": 27
+    },
+    {
+      "epoch": 0.22764227642276422,
+      "grad_norm": 0.11179977655410767,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3798,
+      "step": 28
+    },
+    {
+      "epoch": 0.23577235772357724,
+      "grad_norm": 0.12225475907325745,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3798,
+      "step": 29
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 0.10354068130254745,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3823,
+      "step": 30
+    },
+    {
+      "epoch": 0.25203252032520324,
+      "grad_norm": 0.12544958293437958,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3814,
+      "step": 31
+    },
+    {
+      "epoch": 0.2601626016260163,
+      "grad_norm": 0.09698833525180817,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3784,
+      "step": 32
+    },
+    {
+      "epoch": 0.2682926829268293,
+      "grad_norm": 0.12711447477340698,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3771,
+      "step": 33
+    },
+    {
+      "epoch": 0.2764227642276423,
+      "grad_norm": 0.14151258766651154,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.3822,
+      "step": 34
+    },
+    {
+      "epoch": 0.2845528455284553,
+      "grad_norm": 0.10767289996147156,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3796,
+      "step": 35
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.11947591602802277,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3768,
+      "step": 36
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "eval_loss": 10.37866497039795,
+      "eval_runtime": 0.4767,
+      "eval_samples_per_second": 870.534,
+      "eval_steps_per_second": 27.27,
+      "step": 36
+    },
+    {
+      "epoch": 0.3008130081300813,
+      "grad_norm": 0.1273428201675415,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3778,
+      "step": 37
+    },
+    {
+      "epoch": 0.3089430894308943,
+      "grad_norm": 0.12440553307533264,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3797,
+      "step": 38
+    },
+    {
+      "epoch": 0.3170731707317073,
+      "grad_norm": 0.12360162287950516,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.3798,
+      "step": 39
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "grad_norm": 0.13339215517044067,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3789,
+      "step": 40
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.13511091470718384,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.3775,
+      "step": 41
+    },
+    {
+      "epoch": 0.34146341463414637,
+      "grad_norm": 0.12715180218219757,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3757,
+      "step": 42
+    },
+    {
+      "epoch": 0.34959349593495936,
+      "grad_norm": 0.138566792011261,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.3778,
+      "step": 43
+    },
+    {
+      "epoch": 0.35772357723577236,
+      "grad_norm": 0.13547790050506592,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3783,
+      "step": 44
+    },
+    {
+      "epoch": 0.36585365853658536,
+      "grad_norm": 0.1451762467622757,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3737,
+      "step": 45
+    },
+    {
+      "epoch": 0.36585365853658536,
+      "eval_loss": 10.375040054321289,
+      "eval_runtime": 0.4647,
+      "eval_samples_per_second": 893.093,
+      "eval_steps_per_second": 27.976,
+      "step": 45
+    },
+    {
+      "epoch": 0.37398373983739835,
+      "grad_norm": 0.14544105529785156,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3762,
+      "step": 46
+    },
+    {
+      "epoch": 0.3821138211382114,
+      "grad_norm": 0.15613853931427002,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.3718,
+      "step": 47
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.15438242256641388,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.375,
+      "step": 48
+    },
+    {
+      "epoch": 0.3983739837398374,
+      "grad_norm": 0.14396223425865173,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.3695,
+      "step": 49
+    },
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 0.15646320581436157,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3728,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10434338095104.0,
+  "total_flos": 20790222520320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null