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:cb298ef3b2d33c9609574bf9a6bc3eadcd47f4a080033de66898ba844f34895c
+oid sha256:d39c2e3e3e05d0d8680af4d647278498d825ed89c7cd2f3bae9032794b15fde1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8c230c6b3ae142fdbd37a2b853f06213963a8e7cf626395e2f629011b66942
+oid sha256:7ebe4fefb1e33b3ba752909679975821ae178b6c326004a0eda1846754476c9f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e9b243df93fca8e540c85b8c141b058b63f5a8d46754cc3dd7c5514038fddbd
+oid sha256:65d9923ac95d4aa4a298bd8ed065c1e1d7f9c926e4f6149f930b0b873ca9c5f4
 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": 0.06476683937823834,
+  "epoch": 0.12953367875647667,
   "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": 2.432,
       "step": 25
+    },
+    {
+      "epoch": 0.06735751295336788,
+      "grad_norm": 6.06044864654541,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.6466,
+      "step": 26
+    },
+    {
+      "epoch": 0.06994818652849741,
+      "grad_norm": 5.624882698059082,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.5609,
+      "step": 27
+    },
+    {
+      "epoch": 0.06994818652849741,
+      "eval_loss": 1.9685734510421753,
+      "eval_runtime": 35.2965,
+      "eval_samples_per_second": 9.208,
+      "eval_steps_per_second": 1.162,
+      "step": 27
+    },
+    {
+      "epoch": 0.07253886010362694,
+      "grad_norm": 5.412827968597412,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.9472,
+      "step": 28
+    },
+    {
+      "epoch": 0.07512953367875648,
+      "grad_norm": 8.074312210083008,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.8224,
+      "step": 29
+    },
+    {
+      "epoch": 0.07772020725388601,
+      "grad_norm": 10.367136001586914,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.7846,
+      "step": 30
+    },
+    {
+      "epoch": 0.08031088082901554,
+      "grad_norm": 5.971827507019043,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.8626,
+      "step": 31
+    },
+    {
+      "epoch": 0.08290155440414508,
+      "grad_norm": 6.0518975257873535,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.9026,
+      "step": 32
+    },
+    {
+      "epoch": 0.08549222797927461,
+      "grad_norm": 7.365506172180176,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.6508,
+      "step": 33
+    },
+    {
+      "epoch": 0.08808290155440414,
+      "grad_norm": 7.813849925994873,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.2382,
+      "step": 34
+    },
+    {
+      "epoch": 0.09067357512953368,
+      "grad_norm": 6.097650527954102,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.8182,
+      "step": 35
+    },
+    {
+      "epoch": 0.09326424870466321,
+      "grad_norm": 8.286858558654785,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.0077,
+      "step": 36
+    },
+    {
+      "epoch": 0.09326424870466321,
+      "eval_loss": 1.8582597970962524,
+      "eval_runtime": 35.2881,
+      "eval_samples_per_second": 9.21,
+      "eval_steps_per_second": 1.162,
+      "step": 36
+    },
+    {
+      "epoch": 0.09585492227979274,
+      "grad_norm": 7.306047439575195,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.754,
+      "step": 37
+    },
+    {
+      "epoch": 0.09844559585492228,
+      "grad_norm": 8.38849925994873,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.59,
+      "step": 38
+    },
+    {
+      "epoch": 0.10103626943005181,
+      "grad_norm": 5.015171527862549,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.272,
+      "step": 39
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 7.593957901000977,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.1336,
+      "step": 40
+    },
+    {
+      "epoch": 0.10621761658031088,
+      "grad_norm": 9.562592506408691,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.4349,
+      "step": 41
+    },
+    {
+      "epoch": 0.10880829015544041,
+      "grad_norm": 7.189981937408447,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.827,
+      "step": 42
+    },
+    {
+      "epoch": 0.11139896373056994,
+      "grad_norm": 5.631102561950684,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.5876,
+      "step": 43
+    },
+    {
+      "epoch": 0.11398963730569948,
+      "grad_norm": 5.808564186096191,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.7378,
+      "step": 44
+    },
+    {
+      "epoch": 0.11658031088082901,
+      "grad_norm": 6.575247764587402,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.4891,
+      "step": 45
+    },
+    {
+      "epoch": 0.11658031088082901,
+      "eval_loss": 1.8105183839797974,
+      "eval_runtime": 35.2968,
+      "eval_samples_per_second": 9.208,
+      "eval_steps_per_second": 1.162,
+      "step": 45
+    },
+    {
+      "epoch": 0.11917098445595854,
+      "grad_norm": 6.088664531707764,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.4166,
+      "step": 46
+    },
+    {
+      "epoch": 0.12176165803108809,
+      "grad_norm": 5.614904403686523,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.6618,
+      "step": 47
+    },
+    {
+      "epoch": 0.12435233160621761,
+      "grad_norm": 5.483867645263672,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.0089,
+      "step": 48
+    },
+    {
+      "epoch": 0.12694300518134716,
+      "grad_norm": 5.806712627410889,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.3856,
+      "step": 49
+    },
+    {
+      "epoch": 0.12953367875647667,
+      "grad_norm": 6.254551410675049,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.0932,
+      "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