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:a0c8c0564f4a5282f609e6ba4b4993c2d4bbdf018185601954af111bc3a2e38f
+oid sha256:d1095df55485e28fe8bae34151699b2f3c4cc5e7715422d3816aea806e6c762e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4ef84d1296eac2c080976e7c06fa07809ab6841b5f02897400daeaa5effa335
+oid sha256:07e1d52623dd72226079bfa03cb9efc8b3b678cb5c3fae3d4ddec31f33f9788e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dccf15704fbdf23856e1119baffae48b962f09fb2232cc45a115390986e7d5d
+oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
 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": 0.0012921232168699606,
+  "epoch": 0.0025842464337399213,
   "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": 0.1185,
       "step": 25
+    },
+    {
+      "epoch": 0.0013438081455447591,
+      "grad_norm": 0.9580687284469604,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.1054,
+      "step": 26
+    },
+    {
+      "epoch": 0.0013954930742195576,
+      "grad_norm": 1.408044695854187,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.1348,
+      "step": 27
+    },
+    {
+      "epoch": 0.0013954930742195576,
+      "eval_loss": 0.121719591319561,
+      "eval_runtime": 2000.6672,
+      "eval_samples_per_second": 8.144,
+      "eval_steps_per_second": 1.018,
+      "step": 27
+    },
+    {
+      "epoch": 0.001447178002894356,
+      "grad_norm": 0.9024913907051086,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.1044,
+      "step": 28
+    },
+    {
+      "epoch": 0.0014988629315691544,
+      "grad_norm": 0.8593191504478455,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.1124,
+      "step": 29
+    },
+    {
+      "epoch": 0.0015505478602439529,
+      "grad_norm": 0.6453657746315002,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0967,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016022327889187514,
+      "grad_norm": 1.0000425577163696,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.1054,
+      "step": 31
+    },
+    {
+      "epoch": 0.0016539177175935497,
+      "grad_norm": 0.9135391116142273,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.0017056026462683482,
+      "grad_norm": 0.6197313666343689,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0927,
+      "step": 33
+    },
+    {
+      "epoch": 0.0017572875749431466,
+      "grad_norm": 0.6528716683387756,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0811,
+      "step": 34
+    },
+    {
+      "epoch": 0.001808972503617945,
+      "grad_norm": 0.8095766305923462,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0757,
+      "step": 35
+    },
+    {
+      "epoch": 0.0018606574322927434,
+      "grad_norm": 1.3153815269470215,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.1376,
+      "step": 36
+    },
+    {
+      "epoch": 0.0018606574322927434,
+      "eval_loss": 0.09214772284030914,
+      "eval_runtime": 2000.5366,
+      "eval_samples_per_second": 8.144,
+      "eval_steps_per_second": 1.018,
+      "step": 36
+    },
+    {
+      "epoch": 0.001912342360967542,
+      "grad_norm": 0.6268633008003235,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0819,
+      "step": 37
+    },
+    {
+      "epoch": 0.00196402728964234,
+      "grad_norm": 0.5090088844299316,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0717,
+      "step": 38
+    },
+    {
+      "epoch": 0.002015712218317139,
+      "grad_norm": 0.9383134841918945,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.1401,
+      "step": 39
+    },
+    {
+      "epoch": 0.002067397146991937,
+      "grad_norm": 0.8806520700454712,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1129,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021190820756667355,
+      "grad_norm": 0.5183126330375671,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0686,
+      "step": 41
+    },
+    {
+      "epoch": 0.002170767004341534,
+      "grad_norm": 0.6590868830680847,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.1052,
+      "step": 42
+    },
+    {
+      "epoch": 0.0022224519330163325,
+      "grad_norm": 0.5947044491767883,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0758,
+      "step": 43
+    },
+    {
+      "epoch": 0.0022741368616911307,
+      "grad_norm": 0.739967942237854,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0799,
+      "step": 44
+    },
+    {
+      "epoch": 0.0023258217903659294,
+      "grad_norm": 0.8281837701797485,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0646,
+      "step": 45
+    },
+    {
+      "epoch": 0.0023258217903659294,
+      "eval_loss": 0.07997908443212509,
+      "eval_runtime": 2000.9661,
+      "eval_samples_per_second": 8.143,
+      "eval_steps_per_second": 1.018,
+      "step": 45
+    },
+    {
+      "epoch": 0.0023775067190407277,
+      "grad_norm": 0.5553789138793945,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.062,
+      "step": 46
+    },
+    {
+      "epoch": 0.002429191647715526,
+      "grad_norm": 0.5033071041107178,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0631,
+      "step": 47
+    },
+    {
+      "epoch": 0.0024808765763903247,
+      "grad_norm": 0.7486463785171509,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0951,
+      "step": 48
+    },
+    {
+      "epoch": 0.002532561505065123,
+      "grad_norm": 0.48908039927482605,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0559,
+      "step": 49
+    },
+    {
+      "epoch": 0.0025842464337399213,
+      "grad_norm": 0.45823943614959717,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0498,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.85471820890112e+16,
+  "total_flos": 3.70943641780224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null