Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f80b80fd9e02376dbd33c96d9dc6ac72d43f207948c07fe4a9c1116610e4d84
+oid sha256:e09d646bba6d9041d398b0b058297681b24a0453d619065b40f5930ff4131a03
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d1cbd5a3cc58d2e34a584f26648cafdd7399885014b48a08004b8c9ae83f667
+oid sha256:2b3533b2a958df3c2562afc2bece72acec9746762958d6e1383332746b572f87
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e511b972c396bd5ac07671d8be757f45bfe85b6eee968cfc163f5a6e683fab07
+oid sha256:f31dd9f29536312af5dc98dd2c0d0063677d337f66f041544e9f2f90dd802071
 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": 0.008165931732810714,
+  "epoch": 0.01633186346562143,
   "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": 10.3732,
       "step": 25
+    },
+    {
+      "epoch": 0.008492569002123142,
+      "grad_norm": 0.04129215329885483,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.374,
+      "step": 26
+    },
+    {
+      "epoch": 0.008819206271435572,
+      "grad_norm": 0.0452185682952404,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3727,
+      "step": 27
+    },
+    {
+      "epoch": 0.008819206271435572,
+      "eval_loss": 10.374153137207031,
+      "eval_runtime": 21.406,
+      "eval_samples_per_second": 120.434,
+      "eval_steps_per_second": 15.089,
+      "step": 27
+    },
+    {
+      "epoch": 0.009145843540748,
+      "grad_norm": 0.04270987957715988,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3738,
+      "step": 28
+    },
+    {
+      "epoch": 0.009472480810060429,
+      "grad_norm": 0.05155440792441368,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3752,
+      "step": 29
+    },
+    {
+      "epoch": 0.009799118079372856,
+      "grad_norm": 0.0561983697116375,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3711,
+      "step": 30
+    },
+    {
+      "epoch": 0.010125755348685286,
+      "grad_norm": 0.042896758764982224,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3735,
+      "step": 31
+    },
+    {
+      "epoch": 0.010452392617997713,
+      "grad_norm": 0.04372115805745125,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3735,
+      "step": 32
+    },
+    {
+      "epoch": 0.010779029887310143,
+      "grad_norm": 0.06329807639122009,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3737,
+      "step": 33
+    },
+    {
+      "epoch": 0.01110566715662257,
+      "grad_norm": 0.04135838523507118,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.3743,
+      "step": 34
+    },
+    {
+      "epoch": 0.011432304425935,
+      "grad_norm": 0.04792993143200874,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3752,
+      "step": 35
+    },
+    {
+      "epoch": 0.011758941695247428,
+      "grad_norm": 0.05100570246577263,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3727,
+      "step": 36
+    },
+    {
+      "epoch": 0.011758941695247428,
+      "eval_loss": 10.373011589050293,
+      "eval_runtime": 22.204,
+      "eval_samples_per_second": 116.105,
+      "eval_steps_per_second": 14.547,
+      "step": 36
+    },
+    {
+      "epoch": 0.012085578964559857,
+      "grad_norm": 0.05363311618566513,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3726,
+      "step": 37
+    },
+    {
+      "epoch": 0.012412216233872285,
+      "grad_norm": 0.06147367134690285,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3733,
+      "step": 38
+    },
+    {
+      "epoch": 0.012738853503184714,
+      "grad_norm": 0.04945583641529083,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.373,
+      "step": 39
+    },
+    {
+      "epoch": 0.013065490772497142,
+      "grad_norm": 0.060909684747457504,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3728,
+      "step": 40
+    },
+    {
+      "epoch": 0.013392128041809571,
+      "grad_norm": 0.04293395206332207,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.3706,
+      "step": 41
+    },
+    {
+      "epoch": 0.013718765311121999,
+      "grad_norm": 0.0527237206697464,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3713,
+      "step": 42
+    },
+    {
+      "epoch": 0.014045402580434428,
+      "grad_norm": 0.06157221272587776,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.3747,
+      "step": 43
+    },
+    {
+      "epoch": 0.014372039849746856,
+      "grad_norm": 0.06624653190374374,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3736,
+      "step": 44
+    },
+    {
+      "epoch": 0.014698677119059285,
+      "grad_norm": 0.06559105962514877,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3704,
+      "step": 45
+    },
+    {
+      "epoch": 0.014698677119059285,
+      "eval_loss": 10.37177562713623,
+      "eval_runtime": 21.8679,
+      "eval_samples_per_second": 117.89,
+      "eval_steps_per_second": 14.771,
+      "step": 45
+    },
+    {
+      "epoch": 0.015025314388371713,
+      "grad_norm": 0.044589053839445114,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3708,
+      "step": 46
+    },
+    {
+      "epoch": 0.015351951657684142,
+      "grad_norm": 0.06341821700334549,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.3708,
+      "step": 47
+    },
+    {
+      "epoch": 0.01567858892699657,
+      "grad_norm": 0.04743089899420738,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.3722,
+      "step": 48
+    },
+    {
+      "epoch": 0.016005226196308998,
+      "grad_norm": 0.06420129537582397,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.375,
+      "step": 49
+    },
+    {
+      "epoch": 0.01633186346562143,
+      "grad_norm": 0.0634082779288292,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3699,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1569073397760.0,
+  "total_flos": 2981239455744.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null