Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e0c2b2ba57bf3d75c6ff64cd2b326f70df60ba3b0a6e3cf3cd76a1e5c608f82
+oid sha256:782d68c77b317b289b6d064726556dfc03f3a29ebd9c21d70aa692d258d8b94c
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb6a47ca22611ab801c52bbae0e78809ac2af77715a321c08bb9de63d261eff
+oid sha256:de90258827ac1c1224a803c0178e47d2d8107e47d789509d370e78f588aeaa3e
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f457745713f161f2c9c72594b4115f8e0ef6a04ac90fe2d21af45c8cbff77ec8
+oid sha256:7da9f1139f61cc766662dec9be1a789e9af6ce81829e82037fdc4fc6fe2c5c18
 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": 0.02868617326448652,
+  "epoch": 0.05737234652897304,
   "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": 0.0404,
       "step": 25
+    },
+    {
+      "epoch": 0.02983362019506598,
+      "grad_norm": 0.21312940120697021,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0374,
+      "step": 26
+    },
+    {
+      "epoch": 0.03098106712564544,
+      "grad_norm": 0.22618572413921356,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0365,
+      "step": 27
+    },
+    {
+      "epoch": 0.03098106712564544,
+      "eval_loss": 0.035865794867277145,
+      "eval_runtime": 41.9598,
+      "eval_samples_per_second": 17.493,
+      "eval_steps_per_second": 2.193,
+      "step": 27
+    },
+    {
+      "epoch": 0.0321285140562249,
+      "grad_norm": 0.3117932081222534,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.032,
+      "step": 28
+    },
+    {
+      "epoch": 0.03327596098680436,
+      "grad_norm": 0.46760082244873047,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.05,
+      "step": 29
+    },
+    {
+      "epoch": 0.03442340791738382,
+      "grad_norm": 0.23990069329738617,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0301,
+      "step": 30
+    },
+    {
+      "epoch": 0.03557085484796328,
+      "grad_norm": 0.2261684387922287,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0329,
+      "step": 31
+    },
+    {
+      "epoch": 0.03671830177854274,
+      "grad_norm": 0.24604563415050507,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0472,
+      "step": 32
+    },
+    {
+      "epoch": 0.0378657487091222,
+      "grad_norm": 0.24846573173999786,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0262,
+      "step": 33
+    },
+    {
+      "epoch": 0.03901319563970167,
+      "grad_norm": 0.17995569109916687,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0224,
+      "step": 34
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 0.20148605108261108,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0374,
+      "step": 35
+    },
+    {
+      "epoch": 0.04130808950086059,
+      "grad_norm": 0.30979934334754944,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0442,
+      "step": 36
+    },
+    {
+      "epoch": 0.04130808950086059,
+      "eval_loss": 0.02968555875122547,
+      "eval_runtime": 41.7385,
+      "eval_samples_per_second": 17.586,
+      "eval_steps_per_second": 2.204,
+      "step": 36
+    },
+    {
+      "epoch": 0.042455536431440045,
+      "grad_norm": 0.17189563810825348,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0296,
+      "step": 37
+    },
+    {
+      "epoch": 0.04360298336201951,
+      "grad_norm": 0.21490830183029175,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0275,
+      "step": 38
+    },
+    {
+      "epoch": 0.04475043029259897,
+      "grad_norm": 0.16300365328788757,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0229,
+      "step": 39
+    },
+    {
+      "epoch": 0.04589787722317843,
+      "grad_norm": 0.19255292415618896,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.02,
+      "step": 40
+    },
+    {
+      "epoch": 0.04704532415375789,
+      "grad_norm": 0.2177131623029709,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0259,
+      "step": 41
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 0.1485728919506073,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0197,
+      "step": 42
+    },
+    {
+      "epoch": 0.04934021801491681,
+      "grad_norm": 0.1863524615764618,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0288,
+      "step": 43
+    },
+    {
+      "epoch": 0.05048766494549627,
+      "grad_norm": 0.2662622034549713,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0342,
+      "step": 44
+    },
+    {
+      "epoch": 0.05163511187607573,
+      "grad_norm": 0.1945541799068451,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0282,
+      "step": 45
+    },
+    {
+      "epoch": 0.05163511187607573,
+      "eval_loss": 0.026803946122527122,
+      "eval_runtime": 41.84,
+      "eval_samples_per_second": 17.543,
+      "eval_steps_per_second": 2.199,
+      "step": 45
+    },
+    {
+      "epoch": 0.052782558806655194,
+      "grad_norm": 0.18604616820812225,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0327,
+      "step": 46
+    },
+    {
+      "epoch": 0.05393000573723465,
+      "grad_norm": 0.18346279859542847,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0252,
+      "step": 47
+    },
+    {
+      "epoch": 0.055077452667814115,
+      "grad_norm": 0.11086254566907883,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.02,
+      "step": 48
+    },
+    {
+      "epoch": 0.05622489959839357,
+      "grad_norm": 0.1600019931793213,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0261,
+      "step": 49
+    },
+    {
+      "epoch": 0.05737234652897304,
+      "grad_norm": 0.19246770441532135,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0247,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4112820920647680.0,
+  "total_flos": 8322414098251776.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null