Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6019239e44020360e257109b6287806352cbf8c318d2040956dcbe101857f478
+oid sha256:2d5eb7cc11e3c256dc178d6e3d42d26a1d058e6cae38d420c8c12f01faa46125
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf21922274d0f65a62a448134b516a52f13c28044ed1c7c727d9bd08ba20dfc0
+oid sha256:72d9c0fa3827b04803fb8cffcd22ef3a584cb270fb4ff319c03d9ae9c3da0402
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94090357d03fbde733ed6e7318d84e00f2b10c796d62523689596d7eb2b50a3
+oid sha256:d4ee5f7840dda9b1ed18450fe64bc768a3f9c9987dc535617c2dc434ebe00455
 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": 0.09765625,
+  "epoch": 0.1953125,
   "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": 0.1187,
       "step": 25
+    },
+    {
+      "epoch": 0.1015625,
+      "grad_norm": 0.18970464169979095,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.1302,
+      "step": 26
+    },
+    {
+      "epoch": 0.10546875,
+      "grad_norm": 0.13743029534816742,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.103,
+      "step": 27
+    },
+    {
+      "epoch": 0.10546875,
+      "eval_loss": 0.11523790657520294,
+      "eval_runtime": 37.6775,
+      "eval_samples_per_second": 5.733,
+      "eval_steps_per_second": 0.717,
+      "step": 27
+    },
+    {
+      "epoch": 0.109375,
+      "grad_norm": 0.16887696087360382,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0911,
+      "step": 28
+    },
+    {
+      "epoch": 0.11328125,
+      "grad_norm": 0.1817857027053833,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.1184,
+      "step": 29
+    },
+    {
+      "epoch": 0.1171875,
+      "grad_norm": 0.39407843351364136,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.1714,
+      "step": 30
+    },
+    {
+      "epoch": 0.12109375,
+      "grad_norm": 0.14840836822986603,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0822,
+      "step": 31
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.12886931002140045,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0924,
+      "step": 32
+    },
+    {
+      "epoch": 0.12890625,
+      "grad_norm": 0.131106898188591,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.1126,
+      "step": 33
+    },
+    {
+      "epoch": 0.1328125,
+      "grad_norm": 0.20917432010173798,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.1214,
+      "step": 34
+    },
+    {
+      "epoch": 0.13671875,
+      "grad_norm": 0.13371144235134125,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.1085,
+      "step": 35
+    },
+    {
+      "epoch": 0.140625,
+      "grad_norm": 0.16854634881019592,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.1154,
+      "step": 36
+    },
+    {
+      "epoch": 0.140625,
+      "eval_loss": 0.10245885699987411,
+      "eval_runtime": 37.6755,
+      "eval_samples_per_second": 5.733,
+      "eval_steps_per_second": 0.717,
+      "step": 36
+    },
+    {
+      "epoch": 0.14453125,
+      "grad_norm": 0.12487249076366425,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.109,
+      "step": 37
+    },
+    {
+      "epoch": 0.1484375,
+      "grad_norm": 0.1517653465270996,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0798,
+      "step": 38
+    },
+    {
+      "epoch": 0.15234375,
+      "grad_norm": 0.16995568573474884,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.1015,
+      "step": 39
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.09856864809989929,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1026,
+      "step": 40
+    },
+    {
+      "epoch": 0.16015625,
+      "grad_norm": 0.11969555914402008,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.099,
+      "step": 41
+    },
+    {
+      "epoch": 0.1640625,
+      "grad_norm": 0.1942385733127594,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.069,
+      "step": 42
+    },
+    {
+      "epoch": 0.16796875,
+      "grad_norm": 0.12041034549474716,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.1015,
+      "step": 43
+    },
+    {
+      "epoch": 0.171875,
+      "grad_norm": 0.1598462611436844,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0893,
+      "step": 44
+    },
+    {
+      "epoch": 0.17578125,
+      "grad_norm": 0.17382952570915222,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.1179,
+      "step": 45
+    },
+    {
+      "epoch": 0.17578125,
+      "eval_loss": 0.09511082619428635,
+      "eval_runtime": 37.6196,
+      "eval_samples_per_second": 5.742,
+      "eval_steps_per_second": 0.718,
+      "step": 45
+    },
+    {
+      "epoch": 0.1796875,
+      "grad_norm": 0.1521601378917694,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0992,
+      "step": 46
+    },
+    {
+      "epoch": 0.18359375,
+      "grad_norm": 0.18973639607429504,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0867,
+      "step": 47
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.1595524698495865,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.1163,
+      "step": 48
+    },
+    {
+      "epoch": 0.19140625,
+      "grad_norm": 0.2963557243347168,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0805,
+      "step": 49
+    },
+    {
+      "epoch": 0.1953125,
+      "grad_norm": 0.09695882350206375,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0806,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.578267055849472e+16,
+  "total_flos": 5.487081170141184e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null