Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7c4e406b6b492e5b1cd44134448ffe93a128d82c3fe83e24d35b3488a4113f
+oid sha256:06d63e1cb1fdb0b6ca5fecb1669687ba0a79fff92708ed2efb572d77f306c1bb
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df340a64944e8a232195ab8c6c7bdf8deeaf83b8b70e6c98c874309b57771ba
+oid sha256:e4f0ba882b4b5a3d2c9b16f849d82d52936054968a9dfe94e1efc2955ffebc38
 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": 0.1366120218579235,
+  "epoch": 0.273224043715847,
   "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": 10.3781,
       "step": 25
+    },
+    {
+      "epoch": 0.14207650273224043,
+      "grad_norm": 0.02928001433610916,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3773,
+      "step": 26
+    },
+    {
+      "epoch": 0.14754098360655737,
+      "grad_norm": 0.027695804834365845,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3766,
+      "step": 27
+    },
+    {
+      "epoch": 0.14754098360655737,
+      "eval_loss": 10.377593994140625,
+      "eval_runtime": 0.8333,
+      "eval_samples_per_second": 739.27,
+      "eval_steps_per_second": 24.002,
+      "step": 27
+    },
+    {
+      "epoch": 0.15300546448087432,
+      "grad_norm": 0.0281513761729002,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3775,
+      "step": 28
+    },
+    {
+      "epoch": 0.15846994535519127,
+      "grad_norm": 0.028438687324523926,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3773,
+      "step": 29
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 0.02885403297841549,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3769,
+      "step": 30
+    },
+    {
+      "epoch": 0.16939890710382513,
+      "grad_norm": 0.02971421554684639,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3776,
+      "step": 31
+    },
+    {
+      "epoch": 0.17486338797814208,
+      "grad_norm": 0.033431265503168106,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3759,
+      "step": 32
+    },
+    {
+      "epoch": 0.18032786885245902,
+      "grad_norm": 0.03296530991792679,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3772,
+      "step": 33
+    },
+    {
+      "epoch": 0.18579234972677597,
+      "grad_norm": 0.03332926705479622,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.377,
+      "step": 34
+    },
+    {
+      "epoch": 0.1912568306010929,
+      "grad_norm": 0.03217661380767822,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3761,
+      "step": 35
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "grad_norm": 0.033675920218229294,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3767,
+      "step": 36
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "eval_loss": 10.376678466796875,
+      "eval_runtime": 0.8446,
+      "eval_samples_per_second": 729.317,
+      "eval_steps_per_second": 23.679,
+      "step": 36
+    },
+    {
+      "epoch": 0.20218579234972678,
+      "grad_norm": 0.0315808467566967,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3776,
+      "step": 37
+    },
+    {
+      "epoch": 0.20765027322404372,
+      "grad_norm": 0.038899537175893784,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3754,
+      "step": 38
+    },
+    {
+      "epoch": 0.21311475409836064,
+      "grad_norm": 0.03773730248212814,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.3778,
+      "step": 39
+    },
+    {
+      "epoch": 0.2185792349726776,
+      "grad_norm": 0.04042154923081398,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3765,
+      "step": 40
+    },
+    {
+      "epoch": 0.22404371584699453,
+      "grad_norm": 0.039911359548568726,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.3754,
+      "step": 41
+    },
+    {
+      "epoch": 0.22950819672131148,
+      "grad_norm": 0.04403088241815567,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3759,
+      "step": 42
+    },
+    {
+      "epoch": 0.23497267759562843,
+      "grad_norm": 0.03892216086387634,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.3762,
+      "step": 43
+    },
+    {
+      "epoch": 0.24043715846994534,
+      "grad_norm": 0.038504015654325485,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3756,
+      "step": 44
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "grad_norm": 0.04363120719790459,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.376,
+      "step": 45
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "eval_loss": 10.375645637512207,
+      "eval_runtime": 0.8348,
+      "eval_samples_per_second": 737.924,
+      "eval_steps_per_second": 23.959,
+      "step": 45
+    },
+    {
+      "epoch": 0.25136612021857924,
+      "grad_norm": 0.043945375829935074,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3751,
+      "step": 46
+    },
+    {
+      "epoch": 0.2568306010928962,
+      "grad_norm": 0.04311802238225937,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.3757,
+      "step": 47
+    },
+    {
+      "epoch": 0.26229508196721313,
+      "grad_norm": 0.04382125660777092,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.3757,
+      "step": 48
+    },
+    {
+      "epoch": 0.2677595628415301,
+      "grad_norm": 0.04658404737710953,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.3758,
+      "step": 49
+    },
+    {
+      "epoch": 0.273224043715847,
+      "grad_norm": 0.045132722705602646,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3745,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10460489318400.0,
+  "total_flos": 20920978636800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null