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:a238883fdcd8f8d15373eff2ba18cfe68f8d86d5e3373892ee1ce3c441e94967
+oid sha256:24aa8fe98f15c1c7f71131fe55d2e56dcae4e611ca7851c2c74bf457de2ba2ec
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b1026d036b5e1ac59733e68010beddab9666bf46c48f061deac84505be85fa
+oid sha256:93d6a2f3f6d5058b6429598ed7ea42e1b050fa2afb952d2e21818a1d82d58be5
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd5f96a0c54d9c7fc696cd2de657ab87643082dd5b551287b669ca224896764
+oid sha256:68d8240f8b64502e023794a3da2d8c6aa526ac0f753e37b389fdd87097fabd55
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b163f39dfe27dc2b3dbffe608a672c5c24782a59c01d78ba19fb42e537b1c880
+oid sha256:f117663bca47e6dbbfa0c77eb3eb3ed1ed85a3dd0c9f866227e737a73eb5c422
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c2e9f653665898599ba92c14fead2834af70cd76abf31d5deed9f0b6254a84
+oid sha256:7a7d87a0b1f18c774b632725605bde69fd2b07215dcf9ac48e19e6caa47a6c61
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b04fb1bf3df1d2f6147ab7478673cead0a366e5db2e2dbeb350bb77196eaef95
+oid sha256:f3daeca24213bd8e7f686bd89b9bb6ba8b6995471fd68b15febf485beb753100
 size 15024

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": 0.34965034965034963,
+  "epoch": 0.6993006993006993,
   "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": 10.376,
       "step": 25
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.01983753964304924,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3778,
+      "step": 26
+    },
+    {
+      "epoch": 0.3776223776223776,
+      "grad_norm": 0.018628032878041267,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3774,
+      "step": 27
+    },
+    {
+      "epoch": 0.3776223776223776,
+      "eval_loss": 10.377577781677246,
+      "eval_runtime": 0.2695,
+      "eval_samples_per_second": 890.527,
+      "eval_steps_per_second": 29.684,
+      "step": 27
+    },
+    {
+      "epoch": 0.3916083916083916,
+      "grad_norm": 0.01745915226638317,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3772,
+      "step": 28
+    },
+    {
+      "epoch": 0.40559440559440557,
+      "grad_norm": 0.018339073285460472,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3751,
+      "step": 29
+    },
+    {
+      "epoch": 0.4195804195804196,
+      "grad_norm": 0.015603472478687763,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3766,
+      "step": 30
+    },
+    {
+      "epoch": 0.43356643356643354,
+      "grad_norm": 0.020217476412653923,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.377,
+      "step": 31
+    },
+    {
+      "epoch": 0.44755244755244755,
+      "grad_norm": 0.020117416977882385,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3755,
+      "step": 32
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.01999656856060028,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3776,
+      "step": 33
+    },
+    {
+      "epoch": 0.4755244755244755,
+      "grad_norm": 0.021135497838258743,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.376,
+      "step": 34
+    },
+    {
+      "epoch": 0.48951048951048953,
+      "grad_norm": 0.020801398903131485,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3757,
+      "step": 35
+    },
+    {
+      "epoch": 0.5034965034965035,
+      "grad_norm": 0.023042971268296242,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3766,
+      "step": 36
+    },
+    {
+      "epoch": 0.5034965034965035,
+      "eval_loss": 10.376969337463379,
+      "eval_runtime": 0.2663,
+      "eval_samples_per_second": 901.284,
+      "eval_steps_per_second": 30.043,
+      "step": 36
+    },
+    {
+      "epoch": 0.5174825174825175,
+      "grad_norm": 0.021229099482297897,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3766,
+      "step": 37
+    },
+    {
+      "epoch": 0.5314685314685315,
+      "grad_norm": 0.022592877969145775,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3744,
+      "step": 38
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.02457505464553833,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.377,
+      "step": 39
+    },
+    {
+      "epoch": 0.5594405594405595,
+      "grad_norm": 0.023601705208420753,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3756,
+      "step": 40
+    },
+    {
+      "epoch": 0.5734265734265734,
+      "grad_norm": 0.02284586802124977,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.3771,
+      "step": 41
+    },
+    {
+      "epoch": 0.5874125874125874,
+      "grad_norm": 0.021345047280192375,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3756,
+      "step": 42
+    },
+    {
+      "epoch": 0.6013986013986014,
+      "grad_norm": 0.02439739555120468,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.375,
+      "step": 43
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.02309122122824192,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3761,
+      "step": 44
+    },
+    {
+      "epoch": 0.6293706293706294,
+      "grad_norm": 0.02600119635462761,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3761,
+      "step": 45
+    },
+    {
+      "epoch": 0.6293706293706294,
+      "eval_loss": 10.376312255859375,
+      "eval_runtime": 0.2799,
+      "eval_samples_per_second": 857.336,
+      "eval_steps_per_second": 28.578,
+      "step": 45
+    },
+    {
+      "epoch": 0.6433566433566433,
+      "grad_norm": 0.02472044713795185,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3767,
+      "step": 46
+    },
+    {
+      "epoch": 0.6573426573426573,
+      "grad_norm": 0.026171980425715446,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.3751,
+      "step": 47
+    },
+    {
+      "epoch": 0.6713286713286714,
+      "grad_norm": 0.025832511484622955,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.3763,
+      "step": 48
+    },
+    {
+      "epoch": 0.6853146853146853,
+      "grad_norm": 0.028169607743620872,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.3757,
+      "step": 49
+    },
+    {
+      "epoch": 0.6993006993006993,
+      "grad_norm": 0.029072731733322144,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3751,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7897669435392.0,
+  "total_flos": 15690733977600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null