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:cc6fd4ca9cfaf2b3adb5e680f8e8362b5d0270b6cc5e00033ee6f1262a93ca56
+oid sha256:769ce4d056dc6b99c929d4f9cbe24d9c3ff41c8ee1f85470875a307c12f04bc5
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada3562e846f5d9e291af20d101d037a4f87496ad5c849b7e0db0622faedfa39
+oid sha256:340c0213ed1c8666acca6c73b65c894e1ce1a52b6ecd1e24ed6679c4c2c145f5
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0160325f3cfb2789544f924daf3b9721842346abd05e8dbfa142d277b468e99a
+oid sha256:ff117b2b37bde812847adc6eed8bdc759c3c07f5d1cbee1f5506533e03306f92
 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": 0.05235602094240838,
+  "epoch": 0.10471204188481675,
   "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": 2.9085,
       "step": 25
+    },
+    {
+      "epoch": 0.05445026178010471,
+      "grad_norm": 0.5642029047012329,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.8261,
+      "step": 26
+    },
+    {
+      "epoch": 0.05654450261780105,
+      "grad_norm": 0.6375811100006104,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.9975,
+      "step": 27
+    },
+    {
+      "epoch": 0.05654450261780105,
+      "eval_loss": 1.4399325847625732,
+      "eval_runtime": 54.4669,
+      "eval_samples_per_second": 7.399,
+      "eval_steps_per_second": 0.936,
+      "step": 27
+    },
+    {
+      "epoch": 0.05863874345549738,
+      "grad_norm": 0.5609163045883179,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.794,
+      "step": 28
+    },
+    {
+      "epoch": 0.060732984293193716,
+      "grad_norm": 0.6879402995109558,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.7103,
+      "step": 29
+    },
+    {
+      "epoch": 0.06282722513089005,
+      "grad_norm": 0.5450217127799988,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.7324,
+      "step": 30
+    },
+    {
+      "epoch": 0.06492146596858639,
+      "grad_norm": 0.6222276091575623,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.9903,
+      "step": 31
+    },
+    {
+      "epoch": 0.06701570680628273,
+      "grad_norm": 0.5290335416793823,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 2.8003,
+      "step": 32
+    },
+    {
+      "epoch": 0.06910994764397906,
+      "grad_norm": 0.643876850605011,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.7036,
+      "step": 33
+    },
+    {
+      "epoch": 0.0712041884816754,
+      "grad_norm": 0.6455150842666626,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.758,
+      "step": 34
+    },
+    {
+      "epoch": 0.07329842931937172,
+      "grad_norm": 0.6009905934333801,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.86,
+      "step": 35
+    },
+    {
+      "epoch": 0.07539267015706806,
+      "grad_norm": 0.5729888081550598,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.7763,
+      "step": 36
+    },
+    {
+      "epoch": 0.07539267015706806,
+      "eval_loss": 1.404931902885437,
+      "eval_runtime": 54.4896,
+      "eval_samples_per_second": 7.396,
+      "eval_steps_per_second": 0.936,
+      "step": 36
+    },
+    {
+      "epoch": 0.0774869109947644,
+      "grad_norm": 0.6812015175819397,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.8235,
+      "step": 37
+    },
+    {
+      "epoch": 0.07958115183246073,
+      "grad_norm": 0.5715813636779785,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.6603,
+      "step": 38
+    },
+    {
+      "epoch": 0.08167539267015707,
+      "grad_norm": 0.5004135966300964,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.7355,
+      "step": 39
+    },
+    {
+      "epoch": 0.08376963350785341,
+      "grad_norm": 0.5744718313217163,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.8711,
+      "step": 40
+    },
+    {
+      "epoch": 0.08586387434554973,
+      "grad_norm": 0.6692417860031128,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.6734,
+      "step": 41
+    },
+    {
+      "epoch": 0.08795811518324607,
+      "grad_norm": 0.601163923740387,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.7693,
+      "step": 42
+    },
+    {
+      "epoch": 0.09005235602094241,
+      "grad_norm": 0.5379462838172913,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.8922,
+      "step": 43
+    },
+    {
+      "epoch": 0.09214659685863874,
+      "grad_norm": 0.5941004753112793,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.5804,
+      "step": 44
+    },
+    {
+      "epoch": 0.09424083769633508,
+      "grad_norm": 0.5219014286994934,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.9221,
+      "step": 45
+    },
+    {
+      "epoch": 0.09424083769633508,
+      "eval_loss": 1.3878324031829834,
+      "eval_runtime": 54.4731,
+      "eval_samples_per_second": 7.398,
+      "eval_steps_per_second": 0.936,
+      "step": 45
+    },
+    {
+      "epoch": 0.09633507853403141,
+      "grad_norm": 0.6687893271446228,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.7832,
+      "step": 46
+    },
+    {
+      "epoch": 0.09842931937172775,
+      "grad_norm": 0.5477647185325623,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.6517,
+      "step": 47
+    },
+    {
+      "epoch": 0.10052356020942409,
+      "grad_norm": 0.5874961018562317,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.6161,
+      "step": 48
+    },
+    {
+      "epoch": 0.10261780104712041,
+      "grad_norm": 0.518980860710144,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.7782,
+      "step": 49
+    },
+    {
+      "epoch": 0.10471204188481675,
+      "grad_norm": 0.8065228462219238,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.7772,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.63366161088512e+16,
+  "total_flos": 3.26732322177024e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null