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:b3eabbb052abdcc42b9bfbeefee5cce2a9d410b1063d80f95caabee38131e566
+oid sha256:3d4e0322331d9088e78fd7a022c4b6947934337338189a1646ea0cab447c7ddd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dffa326da514f62e1e1b7da3ecadd62cc306e077786c8ac09dd5fca0f42b321
+oid sha256:b475effe5fb64ef33c755fea8e1518aae7f53f7c48700f0202e161c93231ffbf
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad06d6575ee59e74108d9c4f8816f7974dab7778222a92e7eb26ff08be09916f
+oid sha256:b8bb943b78597438abebef0ec790b3e252eb54101d94eb6c899d1de02c649b6a
 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": 0.037678975131876416,
+  "epoch": 0.07535795026375283,
   "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": 0.1978,
       "step": 25
+    },
+    {
+      "epoch": 0.03918613413715147,
+      "grad_norm": 0.3882005214691162,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.1296,
+      "step": 26
+    },
+    {
+      "epoch": 0.04069329314242653,
+      "grad_norm": 0.4310823082923889,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.1181,
+      "step": 27
+    },
+    {
+      "epoch": 0.04069329314242653,
+      "eval_loss": 0.18763834238052368,
+      "eval_runtime": 123.6029,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 0.566,
+      "step": 27
+    },
+    {
+      "epoch": 0.04220045214770158,
+      "grad_norm": 0.5565463304519653,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.2201,
+      "step": 28
+    },
+    {
+      "epoch": 0.04370761115297664,
+      "grad_norm": 0.3672766387462616,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.0876,
+      "step": 29
+    },
+    {
+      "epoch": 0.0452147701582517,
+      "grad_norm": 0.3959539234638214,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0997,
+      "step": 30
+    },
+    {
+      "epoch": 0.04672192916352675,
+      "grad_norm": 0.38439688086509705,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.1038,
+      "step": 31
+    },
+    {
+      "epoch": 0.04822908816880181,
+      "grad_norm": 0.6091885566711426,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.1196,
+      "step": 32
+    },
+    {
+      "epoch": 0.04973624717407687,
+      "grad_norm": 0.4755226671695709,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.1388,
+      "step": 33
+    },
+    {
+      "epoch": 0.05124340617935192,
+      "grad_norm": 0.504368007183075,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.1114,
+      "step": 34
+    },
+    {
+      "epoch": 0.05275056518462698,
+      "grad_norm": 0.35794878005981445,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0983,
+      "step": 35
+    },
+    {
+      "epoch": 0.05425772418990203,
+      "grad_norm": 0.5445522665977478,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.1758,
+      "step": 36
+    },
+    {
+      "epoch": 0.05425772418990203,
+      "eval_loss": 0.17182248830795288,
+      "eval_runtime": 123.5947,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 0.566,
+      "step": 36
+    },
+    {
+      "epoch": 0.05576488319517709,
+      "grad_norm": 0.563473105430603,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0778,
+      "step": 37
+    },
+    {
+      "epoch": 0.05727204220045215,
+      "grad_norm": 0.7104746699333191,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.2217,
+      "step": 38
+    },
+    {
+      "epoch": 0.0587792012057272,
+      "grad_norm": 0.3592125177383423,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0769,
+      "step": 39
+    },
+    {
+      "epoch": 0.06028636021100226,
+      "grad_norm": 0.3523983061313629,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0896,
+      "step": 40
+    },
+    {
+      "epoch": 0.06179351921627732,
+      "grad_norm": 0.31311479210853577,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0581,
+      "step": 41
+    },
+    {
+      "epoch": 0.06330067822155237,
+      "grad_norm": 0.44165709614753723,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0845,
+      "step": 42
+    },
+    {
+      "epoch": 0.06480783722682742,
+      "grad_norm": 1.0613696575164795,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.266,
+      "step": 43
+    },
+    {
+      "epoch": 0.06631499623210249,
+      "grad_norm": 0.5340938568115234,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.1391,
+      "step": 44
+    },
+    {
+      "epoch": 0.06782215523737754,
+      "grad_norm": 0.46894630789756775,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0675,
+      "step": 45
+    },
+    {
+      "epoch": 0.06782215523737754,
+      "eval_loss": 0.15676920115947723,
+      "eval_runtime": 123.5469,
+      "eval_samples_per_second": 4.525,
+      "eval_steps_per_second": 0.567,
+      "step": 45
+    },
+    {
+      "epoch": 0.0693293142426526,
+      "grad_norm": 0.3855697810649872,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0871,
+      "step": 46
+    },
+    {
+      "epoch": 0.07083647324792766,
+      "grad_norm": 3.673552989959717,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.34,
+      "step": 47
+    },
+    {
+      "epoch": 0.07234363225320271,
+      "grad_norm": 0.46040230989456177,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0978,
+      "step": 48
+    },
+    {
+      "epoch": 0.07385079125847777,
+      "grad_norm": 0.4494129717350006,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.1389,
+      "step": 49
+    },
+    {
+      "epoch": 0.07535795026375283,
+      "grad_norm": 0.6942574977874756,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.2822,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.672342053624218e+16,
+  "total_flos": 7.381778471426458e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null