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:a2c92d5a4e136e8e493c5db10fdc2185fb1701b7c210ac237d59ce915c10e363
+oid sha256:9ad4f6ffde5b05dc0eacad8c15aa197905f7b7d7592b83611335fafa9f49a121
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed986f4554250c4469fd3de76d1ad4fc5ced4607db72375809f2990ae9a797c0
+oid sha256:bcf7136e741013e15bc8ea4368966c1ba0e419594e2b1e751efe54db5dec8bfa
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d898b1b1c4d14959aa60c5fdb3718ea29e5c521107f6c1a9343b02f58f9f417
+oid sha256:da48438bf8b8db74f61cc2142eb4dc056d3871064431f52d89f8375957ad02b7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06140620202640467,
+  "epoch": 0.12281240405280934,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 3.522,
       "eval_steps_per_second": 1.766,
       "step": 25
+    },
+    {
+      "epoch": 0.06386245010746085,
+      "grad_norm": 0.1433115303516388,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0656,
+      "step": 26
+    },
+    {
+      "epoch": 0.06631869818851704,
+      "grad_norm": 0.25121065974235535,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1332,
+      "step": 27
+    },
+    {
+      "epoch": 0.06877494626957323,
+      "grad_norm": 0.26504987478256226,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0707,
+      "step": 28
+    },
+    {
+      "epoch": 0.07123119435062941,
+      "grad_norm": 0.1881726235151291,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.1291,
+      "step": 29
+    },
+    {
+      "epoch": 0.0736874424316856,
+      "grad_norm": 0.1683933287858963,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1258,
+      "step": 30
+    },
+    {
+      "epoch": 0.0761436905127418,
+      "grad_norm": 0.13583755493164062,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0848,
+      "step": 31
+    },
+    {
+      "epoch": 0.07859993859379798,
+      "grad_norm": 0.1867646425962448,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.096,
+      "step": 32
+    },
+    {
+      "epoch": 0.08105618667485416,
+      "grad_norm": 0.1443484127521515,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0913,
+      "step": 33
+    },
+    {
+      "epoch": 0.08351243475591034,
+      "grad_norm": 0.2707761228084564,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.1123,
+      "step": 34
+    },
+    {
+      "epoch": 0.08596868283696653,
+      "grad_norm": 0.13740448653697968,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0693,
+      "step": 35
+    },
+    {
+      "epoch": 0.08842493091802273,
+      "grad_norm": 0.16506795585155487,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.1096,
+      "step": 36
+    },
+    {
+      "epoch": 0.09088117899907891,
+      "grad_norm": 0.15797682106494904,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.1004,
+      "step": 37
+    },
+    {
+      "epoch": 0.0933374270801351,
+      "grad_norm": 0.10705221444368362,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0723,
+      "step": 38
+    },
+    {
+      "epoch": 0.09579367516119128,
+      "grad_norm": 0.14854738116264343,
+      "learning_rate": 5e-05,
+      "loss": 0.1063,
+      "step": 39
+    },
+    {
+      "epoch": 0.09824992324224746,
+      "grad_norm": 0.18394620716571808,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0951,
+      "step": 40
+    },
+    {
+      "epoch": 0.10070617132330366,
+      "grad_norm": 0.11826738715171814,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0775,
+      "step": 41
+    },
+    {
+      "epoch": 0.10316241940435984,
+      "grad_norm": 0.17405179142951965,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0898,
+      "step": 42
+    },
+    {
+      "epoch": 0.10561866748541603,
+      "grad_norm": 0.14838817715644836,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0919,
+      "step": 43
+    },
+    {
+      "epoch": 0.10807491556647221,
+      "grad_norm": 0.14697116613388062,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0919,
+      "step": 44
+    },
+    {
+      "epoch": 0.1105311636475284,
+      "grad_norm": 0.21143025159835815,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0925,
+      "step": 45
+    },
+    {
+      "epoch": 0.11298741172858459,
+      "grad_norm": 0.14245229959487915,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0942,
+      "step": 46
+    },
+    {
+      "epoch": 0.11544365980964078,
+      "grad_norm": 0.30137455463409424,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.1158,
+      "step": 47
+    },
+    {
+      "epoch": 0.11789990789069696,
+      "grad_norm": 0.13550423085689545,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.079,
+      "step": 48
+    },
+    {
+      "epoch": 0.12035615597175314,
+      "grad_norm": 0.13647057116031647,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0875,
+      "step": 49
+    },
+    {
+      "epoch": 0.12281240405280934,
+      "grad_norm": 0.18223483860492706,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0927,
+      "step": 50
+    },
+    {
+      "epoch": 0.12281240405280934,
+      "eval_loss": 0.09029460698366165,
+      "eval_runtime": 97.3669,
+      "eval_samples_per_second": 3.523,
+      "eval_steps_per_second": 1.767,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.969096967048397e+16,
+  "total_flos": 7.975288298274816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null