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:f638890a0fd5e61ba951dfdcef9e6c7bb73c6166125a31822088f6ceb5ea0d9c
+oid sha256:4269d82abd9179a7a9024ce06b0ea2a05fb71f53202556a2609142877c205219
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b67c4ceb797c8b2d65804de27cac41070edf57caba516ed16c035a123a9a913
+oid sha256:e48e3a967b10047686c2d3922b6ee9568d73684d1db0da2e9bdaaafa4b43a69c
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a15a48c2fed1b3ecbaa40dea96f901573434defc9b6253fb93993c6c3a6af1
+oid sha256:33752213e91e5d9daaf41b0e911b3b2623b16a8672150d6b365a88ada68018bd
 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": 10.4172,
       "step": 25
+    },
+    {
+      "epoch": 0.18309859154929578,
+      "grad_norm": 0.2948496639728546,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3812,
+      "step": 26
+    },
+    {
+      "epoch": 0.19014084507042253,
+      "grad_norm": 0.29332059621810913,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3708,
+      "step": 27
+    },
+    {
+      "epoch": 0.19014084507042253,
+      "eval_loss": 10.388020515441895,
+      "eval_runtime": 0.5108,
+      "eval_samples_per_second": 234.929,
+      "eval_steps_per_second": 29.366,
+      "step": 27
+    },
+    {
+      "epoch": 0.19718309859154928,
+      "grad_norm": 0.28901439905166626,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3622,
+      "step": 28
+    },
+    {
+      "epoch": 0.20422535211267606,
+      "grad_norm": 0.2676180303096771,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3697,
+      "step": 29
+    },
+    {
+      "epoch": 0.2112676056338028,
+      "grad_norm": 0.3027353584766388,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3689,
+      "step": 30
+    },
+    {
+      "epoch": 0.21830985915492956,
+      "grad_norm": 0.3184084892272949,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3918,
+      "step": 31
+    },
+    {
+      "epoch": 0.22535211267605634,
+      "grad_norm": 0.28535696864128113,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3964,
+      "step": 32
+    },
+    {
+      "epoch": 0.2323943661971831,
+      "grad_norm": 0.278022825717926,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.399,
+      "step": 33
+    },
+    {
+      "epoch": 0.23943661971830985,
+      "grad_norm": 0.35305413603782654,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.3943,
+      "step": 34
+    },
+    {
+      "epoch": 0.24647887323943662,
+      "grad_norm": 0.3135928213596344,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3847,
+      "step": 35
+    },
+    {
+      "epoch": 0.2535211267605634,
+      "grad_norm": 0.36001405119895935,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3633,
+      "step": 36
+    },
+    {
+      "epoch": 0.2535211267605634,
+      "eval_loss": 10.378849029541016,
+      "eval_runtime": 0.5378,
+      "eval_samples_per_second": 223.129,
+      "eval_steps_per_second": 27.891,
+      "step": 36
+    },
+    {
+      "epoch": 0.2605633802816901,
+      "grad_norm": 0.3195047676563263,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3732,
+      "step": 37
+    },
+    {
+      "epoch": 0.2676056338028169,
+      "grad_norm": 0.293624609708786,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3915,
+      "step": 38
+    },
+    {
+      "epoch": 0.2746478873239437,
+      "grad_norm": 0.3025934100151062,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.3822,
+      "step": 39
+    },
+    {
+      "epoch": 0.28169014084507044,
+      "grad_norm": 0.2917957901954651,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.4043,
+      "step": 40
+    },
+    {
+      "epoch": 0.2887323943661972,
+      "grad_norm": 0.33415523171424866,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.3714,
+      "step": 41
+    },
+    {
+      "epoch": 0.29577464788732394,
+      "grad_norm": 0.35728704929351807,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3771,
+      "step": 42
+    },
+    {
+      "epoch": 0.3028169014084507,
+      "grad_norm": 0.3928280472755432,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.3508,
+      "step": 43
+    },
+    {
+      "epoch": 0.30985915492957744,
+      "grad_norm": 0.41211655735969543,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3447,
+      "step": 44
+    },
+    {
+      "epoch": 0.31690140845070425,
+      "grad_norm": 0.415772408246994,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3459,
+      "step": 45
+    },
+    {
+      "epoch": 0.31690140845070425,
+      "eval_loss": 10.36909294128418,
+      "eval_runtime": 0.4934,
+      "eval_samples_per_second": 243.209,
+      "eval_steps_per_second": 30.401,
+      "step": 45
+    },
+    {
+      "epoch": 0.323943661971831,
+      "grad_norm": 0.3777596056461334,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3796,
+      "step": 46
+    },
+    {
+      "epoch": 0.33098591549295775,
+      "grad_norm": 0.43159905076026917,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.3739,
+      "step": 47
+    },
+    {
+      "epoch": 0.3380281690140845,
+      "grad_norm": 0.38116705417633057,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.3504,
+      "step": 48
+    },
+    {
+      "epoch": 0.34507042253521125,
+      "grad_norm": 0.379307359457016,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.3412,
+      "step": 49
+    },
+    {
+      "epoch": 0.352112676056338,
+      "grad_norm": 0.34717878699302673,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3554,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1307561164800.0,
+  "total_flos": 2615122329600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null