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:e755e05f2e661730e6335d0b6ec22d4887981239b89d261b90b552bcb56f44e8
+oid sha256:b64d74e79aae9d1ccf5119bf5934a597572dd633b3c363863d20a6df81e31aa2
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fbf6d07da4341f35d344c00662062a880306bc34449b122f5647791d7c9b654
+oid sha256:69c4fd1c816e41aee5ea31a357b563620c35f6f7570c9840a262b78b29a65949
 size 313998650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7a50abe1f8d1700cf9926279eae51749ab652d6a6d68007814a868a75c2f926
+oid sha256:7bf6e2a58c61d475445667dd025fa2d042c8e1b2a88048290fc79ad802251df6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009556118304744612,
+  "epoch": 0.019112236609489224,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 9.261,
       "eval_steps_per_second": 4.63,
       "step": 25
+    },
+    {
+      "epoch": 0.009938363036934397,
+      "grad_norm": 5.4715962409973145,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 2.5455,
+      "step": 26
+    },
+    {
+      "epoch": 0.010320607769124182,
+      "grad_norm": 5.549165725708008,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.5844,
+      "step": 27
+    },
+    {
+      "epoch": 0.010702852501313967,
+      "grad_norm": 5.676646709442139,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 2.7422,
+      "step": 28
+    },
+    {
+      "epoch": 0.011085097233503751,
+      "grad_norm": 5.423862934112549,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 2.4021,
+      "step": 29
+    },
+    {
+      "epoch": 0.011467341965693535,
+      "grad_norm": 6.854278087615967,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.1846,
+      "step": 30
+    },
+    {
+      "epoch": 0.01184958669788332,
+      "grad_norm": 5.748988628387451,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.633,
+      "step": 31
+    },
+    {
+      "epoch": 0.012231831430073104,
+      "grad_norm": 5.561115741729736,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 2.2951,
+      "step": 32
+    },
+    {
+      "epoch": 0.012614076162262889,
+      "grad_norm": 5.736785411834717,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 2.2345,
+      "step": 33
+    },
+    {
+      "epoch": 0.012996320894452674,
+      "grad_norm": 5.680880546569824,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 2.535,
+      "step": 34
+    },
+    {
+      "epoch": 0.013378565626642459,
+      "grad_norm": 5.533990859985352,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.159,
+      "step": 35
+    },
+    {
+      "epoch": 0.013760810358832242,
+      "grad_norm": 6.057872295379639,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 2.066,
+      "step": 36
+    },
+    {
+      "epoch": 0.014143055091022027,
+      "grad_norm": 6.172090530395508,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 2.301,
+      "step": 37
+    },
+    {
+      "epoch": 0.014525299823211811,
+      "grad_norm": 4.52834415435791,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 1.3066,
+      "step": 38
+    },
+    {
+      "epoch": 0.014907544555401596,
+      "grad_norm": 5.488335132598877,
+      "learning_rate": 5e-05,
+      "loss": 2.1805,
+      "step": 39
+    },
+    {
+      "epoch": 0.015289789287591381,
+      "grad_norm": 5.258327960968018,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 1.64,
+      "step": 40
+    },
+    {
+      "epoch": 0.015672034019781164,
+      "grad_norm": 6.46604585647583,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 2.6909,
+      "step": 41
+    },
+    {
+      "epoch": 0.01605427875197095,
+      "grad_norm": 6.989088535308838,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8893,
+      "step": 42
+    },
+    {
+      "epoch": 0.016436523484160734,
+      "grad_norm": 4.715562343597412,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.3926,
+      "step": 43
+    },
+    {
+      "epoch": 0.01681876821635052,
+      "grad_norm": 5.3317975997924805,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 1.7183,
+      "step": 44
+    },
+    {
+      "epoch": 0.017201012948540303,
+      "grad_norm": 4.577286720275879,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3585,
+      "step": 45
+    },
+    {
+      "epoch": 0.01758325768073009,
+      "grad_norm": 6.528746128082275,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 2.253,
+      "step": 46
+    },
+    {
+      "epoch": 0.017965502412919873,
+      "grad_norm": 5.994633674621582,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.0534,
+      "step": 47
+    },
+    {
+      "epoch": 0.018347747145109658,
+      "grad_norm": 8.008041381835938,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.4081,
+      "step": 48
+    },
+    {
+      "epoch": 0.01872999187729944,
+      "grad_norm": 9.006482124328613,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 2.7403,
+      "step": 49
+    },
+    {
+      "epoch": 0.019112236609489224,
+      "grad_norm": 17.78826904296875,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 4.5138,
+      "step": 50
+    },
+    {
+      "epoch": 0.019112236609489224,
+      "eval_loss": 2.8716228008270264,
+      "eval_runtime": 238.2191,
+      "eval_samples_per_second": 9.252,
+      "eval_steps_per_second": 4.626,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9934148626022400.0,
+  "total_flos": 1.98682972520448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null