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:eccf4fe1bc6d19e6cd57bedab30ce1016e2478e3ec845c119ad279591f4e78bf
+oid sha256:81305f3c73dad6d3182e0486da55de2ab5f24272675d4793f32ca8c10cfe1c7d
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d10dfe414aa0daaf27ffcc891a158675d8cad00e25a5ea18e05828efb85ee58
+oid sha256:85dae8d46d4d06a33f10d7ca71e52cb6d2452e4f02e229c6db767f7005f54d49
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d755d5c040b6e3cdaaef4521c6499acce4c2354a0d81cb6941308c683712a33
+oid sha256:10b0f4f9d935debe1754d2bcdf6836577fd7f75677fdbebc826454f63e3fb737
 size 14244

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": 0.176056338028169,
+  "epoch": 0.352112676056338,
   "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": 1.449,
       "step": 25
+    },
+    {
+      "epoch": 0.18309859154929578,
+      "grad_norm": 6.838872909545898,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.8043,
+      "step": 26
+    },
+    {
+      "epoch": 0.19014084507042253,
+      "grad_norm": 7.476458549499512,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.0743,
+      "step": 27
+    },
+    {
+      "epoch": 0.19014084507042253,
+      "eval_loss": 0.8306647539138794,
+      "eval_runtime": 5.3176,
+      "eval_samples_per_second": 22.567,
+      "eval_steps_per_second": 2.821,
+      "step": 27
+    },
+    {
+      "epoch": 0.19718309859154928,
+      "grad_norm": 7.009374141693115,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.2197,
+      "step": 28
+    },
+    {
+      "epoch": 0.20422535211267606,
+      "grad_norm": 4.203879356384277,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.8692,
+      "step": 29
+    },
+    {
+      "epoch": 0.2112676056338028,
+      "grad_norm": 2.9395430088043213,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.6414,
+      "step": 30
+    },
+    {
+      "epoch": 0.21830985915492956,
+      "grad_norm": 4.54150915145874,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.6064,
+      "step": 31
+    },
+    {
+      "epoch": 0.22535211267605634,
+      "grad_norm": 3.4813199043273926,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.5703,
+      "step": 32
+    },
+    {
+      "epoch": 0.2323943661971831,
+      "grad_norm": 5.205654144287109,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.6502,
+      "step": 33
+    },
+    {
+      "epoch": 0.23943661971830985,
+      "grad_norm": 6.046175956726074,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.8305,
+      "step": 34
+    },
+    {
+      "epoch": 0.24647887323943662,
+      "grad_norm": 2.525583505630493,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.3965,
+      "step": 35
+    },
+    {
+      "epoch": 0.2535211267605634,
+      "grad_norm": 7.969776630401611,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.1048,
+      "step": 36
+    },
+    {
+      "epoch": 0.2535211267605634,
+      "eval_loss": 0.7210001349449158,
+      "eval_runtime": 5.2587,
+      "eval_samples_per_second": 22.819,
+      "eval_steps_per_second": 2.852,
+      "step": 36
+    },
+    {
+      "epoch": 0.2605633802816901,
+      "grad_norm": 2.2472925186157227,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.3476,
+      "step": 37
+    },
+    {
+      "epoch": 0.2676056338028169,
+      "grad_norm": 3.452265739440918,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.7696,
+      "step": 38
+    },
+    {
+      "epoch": 0.2746478873239437,
+      "grad_norm": 2.057129144668579,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.4384,
+      "step": 39
+    },
+    {
+      "epoch": 0.28169014084507044,
+      "grad_norm": 2.932300090789795,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.3321,
+      "step": 40
+    },
+    {
+      "epoch": 0.2887323943661972,
+      "grad_norm": 1.8168283700942993,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.4552,
+      "step": 41
+    },
+    {
+      "epoch": 0.29577464788732394,
+      "grad_norm": 1.3311522006988525,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.4102,
+      "step": 42
+    },
+    {
+      "epoch": 0.3028169014084507,
+      "grad_norm": 3.1506192684173584,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.5,
+      "step": 43
+    },
+    {
+      "epoch": 0.30985915492957744,
+      "grad_norm": 4.003086090087891,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.4761,
+      "step": 44
+    },
+    {
+      "epoch": 0.31690140845070425,
+      "grad_norm": 3.40531063079834,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.5122,
+      "step": 45
+    },
+    {
+      "epoch": 0.31690140845070425,
+      "eval_loss": 0.7483626008033752,
+      "eval_runtime": 5.2389,
+      "eval_samples_per_second": 22.905,
+      "eval_steps_per_second": 2.863,
+      "step": 45
+    },
+    {
+      "epoch": 0.323943661971831,
+      "grad_norm": 2.6020545959472656,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.3895,
+      "step": 46
+    },
+    {
+      "epoch": 0.33098591549295775,
+      "grad_norm": 2.6481332778930664,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.4633,
+      "step": 47
+    },
+    {
+      "epoch": 0.3380281690140845,
+      "grad_norm": 2.3728225231170654,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.7675,
+      "step": 48
+    },
+    {
+      "epoch": 0.34507042253521125,
+      "grad_norm": 2.0442349910736084,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.3868,
+      "step": 49
+    },
+    {
+      "epoch": 0.352112676056338,
+      "grad_norm": 1.7789822816848755,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.4195,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.63366161088512e+16,
+  "total_flos": 3.26732322177024e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null