Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6713f6182d04c10a6a657f5c56ed132011450ceb258ff29111c67b004575fa84
+oid sha256:4bbb77b7c972617d75a7ce25fa0d8ff5c92ed34162b2dc4f3f4ca2737fbd9480
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31ce9f90884bc6f3a768248786f19fca00c6a86f01c5f5a82a8aa1c40ed06924
+oid sha256:232e5e54e51e7973329847fa30ae7958daa3c537a32d706f03ee75f7bf6fe76d
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21fc10c89b6bf4996f991095eeccb628cd93f0fca248be4faaa47d5f808044d0
+oid sha256:f61491213d0f71c0e54a4d1cf06238749d8c8aeeb6a636e081ccade0a42c3757
 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": 0.04849660523763336,
+  "epoch": 0.09699321047526673,
   "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": 1.7639,
       "step": 25
+    },
+    {
+      "epoch": 0.0504364694471387,
+      "grad_norm": 3.310025930404663,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.3531,
+      "step": 26
+    },
+    {
+      "epoch": 0.052376333656644035,
+      "grad_norm": 2.69954776763916,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.1658,
+      "step": 27
+    },
+    {
+      "epoch": 0.052376333656644035,
+      "eval_loss": 1.3316627740859985,
+      "eval_runtime": 7.7784,
+      "eval_samples_per_second": 55.796,
+      "eval_steps_per_second": 7.071,
+      "step": 27
+    },
+    {
+      "epoch": 0.05431619786614937,
+      "grad_norm": 2.0734622478485107,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.3399,
+      "step": 28
+    },
+    {
+      "epoch": 0.05625606207565471,
+      "grad_norm": 2.7428479194641113,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.4039,
+      "step": 29
+    },
+    {
+      "epoch": 0.058195926285160036,
+      "grad_norm": 1.9327542781829834,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.9577,
+      "step": 30
+    },
+    {
+      "epoch": 0.06013579049466537,
+      "grad_norm": 2.079310417175293,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.9913,
+      "step": 31
+    },
+    {
+      "epoch": 0.06207565470417071,
+      "grad_norm": 2.0377795696258545,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.9515,
+      "step": 32
+    },
+    {
+      "epoch": 0.06401551891367604,
+      "grad_norm": 1.990349292755127,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.1051,
+      "step": 33
+    },
+    {
+      "epoch": 0.06595538312318137,
+      "grad_norm": 2.111757755279541,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.0754,
+      "step": 34
+    },
+    {
+      "epoch": 0.06789524733268672,
+      "grad_norm": 2.61749005317688,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.0685,
+      "step": 35
+    },
+    {
+      "epoch": 0.06983511154219205,
+      "grad_norm": 1.9351005554199219,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.8439,
+      "step": 36
+    },
+    {
+      "epoch": 0.06983511154219205,
+      "eval_loss": 0.8821842670440674,
+      "eval_runtime": 7.7414,
+      "eval_samples_per_second": 56.063,
+      "eval_steps_per_second": 7.105,
+      "step": 36
+    },
+    {
+      "epoch": 0.07177497575169738,
+      "grad_norm": 1.9722400903701782,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.9561,
+      "step": 37
+    },
+    {
+      "epoch": 0.07371483996120272,
+      "grad_norm": 2.1616642475128174,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.0384,
+      "step": 38
+    },
+    {
+      "epoch": 0.07565470417070805,
+      "grad_norm": 1.5446350574493408,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.7242,
+      "step": 39
+    },
+    {
+      "epoch": 0.07759456838021339,
+      "grad_norm": 1.5929559469223022,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.843,
+      "step": 40
+    },
+    {
+      "epoch": 0.07953443258971872,
+      "grad_norm": 1.5796291828155518,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.8905,
+      "step": 41
+    },
+    {
+      "epoch": 0.08147429679922405,
+      "grad_norm": 1.9490644931793213,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.7645,
+      "step": 42
+    },
+    {
+      "epoch": 0.08341416100872939,
+      "grad_norm": 1.8810855150222778,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.7698,
+      "step": 43
+    },
+    {
+      "epoch": 0.08535402521823472,
+      "grad_norm": 2.4278464317321777,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.795,
+      "step": 44
+    },
+    {
+      "epoch": 0.08729388942774007,
+      "grad_norm": 1.4299455881118774,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.5331,
+      "step": 45
+    },
+    {
+      "epoch": 0.08729388942774007,
+      "eval_loss": 0.6151111721992493,
+      "eval_runtime": 7.7408,
+      "eval_samples_per_second": 56.067,
+      "eval_steps_per_second": 7.105,
+      "step": 45
+    },
+    {
+      "epoch": 0.0892337536372454,
+      "grad_norm": 1.8526909351348877,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.7683,
+      "step": 46
+    },
+    {
+      "epoch": 0.09117361784675072,
+      "grad_norm": 1.4803686141967773,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.5607,
+      "step": 47
+    },
+    {
+      "epoch": 0.09311348205625607,
+      "grad_norm": 1.5188422203063965,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.4849,
+      "step": 48
+    },
+    {
+      "epoch": 0.0950533462657614,
+      "grad_norm": 1.1162447929382324,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.4439,
+      "step": 49
+    },
+    {
+      "epoch": 0.09699321047526673,
+      "grad_norm": 1.8776347637176514,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.575,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 645594775289856.0,
+  "total_flos": 1298131429883904.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null