Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d7589d55f5679df8891a5fc7c6cdbf090b49ea71d1fe85a3059ab55ab4f099
+oid sha256:004c098edfc42563b7f39ab50fdaa454b76fd74ae68b823ce0af3f1a60a71e04
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c38d213ea7bd9cdd4a4ebf9d67f90453e92c97734de63dbb175632a40102d0
+oid sha256:f8052bc0201e14f6f0de89b7ba6f59aa8ebd9d2e7138b25cf3625b58f247642f
 size 101184122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f302da87234d60be2732930a367f7b678905c7b7dabfefb0c922f3ce081e531
+oid sha256:87d0232b9ccff07686cfc810ec869769f203462f49e711f71027440d829ee580
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bd2159125d0f907db16bbcac1721766456bd376415594212d2347f8417e92e
+oid sha256:da58c16ff4044ab803801ef38f08c583eaf5db01211f9109b9c9a6d6b1533ded
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102b7033be1746e3436dc55ed1b2ec55cee011e51f513564ad09f6ed1963a535
+oid sha256:f4a33f582f8be3b5e163b7e3e4e25f954414d05c290f00ab0b23182a29c2d18a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f764f48945785d61e1926877c9eb9b8dced79b9923fd18d60c995acb5d36dcd5
+oid sha256:2ca70537e176d98e3af0ed7ec7090d20b849a4d977ef176a82942c5ef1fe44d8
 size 15024

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": 0.014496955639315743,
+  "epoch": 0.028993911278631487,
   "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": 1.4522,
       "step": 25
+    },
+    {
+      "epoch": 0.015076833864888374,
+      "grad_norm": 8.444914817810059,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.5577,
+      "step": 26
+    },
+    {
+      "epoch": 0.015656712090461003,
+      "grad_norm": 7.327353477478027,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.3477,
+      "step": 27
+    },
+    {
+      "epoch": 0.015656712090461003,
+      "eval_loss": 1.423840880393982,
+      "eval_runtime": 40.8199,
+      "eval_samples_per_second": 142.284,
+      "eval_steps_per_second": 4.459,
+      "step": 27
+    },
+    {
+      "epoch": 0.016236590316033632,
+      "grad_norm": 6.450318336486816,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.4958,
+      "step": 28
+    },
+    {
+      "epoch": 0.016816468541606264,
+      "grad_norm": 9.28383731842041,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.3026,
+      "step": 29
+    },
+    {
+      "epoch": 0.017396346767178893,
+      "grad_norm": 5.914642810821533,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.0721,
+      "step": 30
+    },
+    {
+      "epoch": 0.017976224992751522,
+      "grad_norm": 9.958087921142578,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.5877,
+      "step": 31
+    },
+    {
+      "epoch": 0.01855610321832415,
+      "grad_norm": 6.798673152923584,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.1855,
+      "step": 32
+    },
+    {
+      "epoch": 0.01913598144389678,
+      "grad_norm": 5.9564080238342285,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.9376,
+      "step": 33
+    },
+    {
+      "epoch": 0.019715859669469413,
+      "grad_norm": 5.725466728210449,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.9963,
+      "step": 34
+    },
+    {
+      "epoch": 0.02029573789504204,
+      "grad_norm": 4.877532958984375,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.9964,
+      "step": 35
+    },
+    {
+      "epoch": 0.02087561612061467,
+      "grad_norm": 4.750855445861816,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.8929,
+      "step": 36
+    },
+    {
+      "epoch": 0.02087561612061467,
+      "eval_loss": 0.9391872882843018,
+      "eval_runtime": 23.6538,
+      "eval_samples_per_second": 245.542,
+      "eval_steps_per_second": 7.694,
+      "step": 36
+    },
+    {
+      "epoch": 0.0214554943461873,
+      "grad_norm": 5.508659839630127,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7948,
+      "step": 37
+    },
+    {
+      "epoch": 0.022035372571759932,
+      "grad_norm": 7.987123012542725,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.144,
+      "step": 38
+    },
+    {
+      "epoch": 0.02261525079733256,
+      "grad_norm": 6.456543445587158,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.9506,
+      "step": 39
+    },
+    {
+      "epoch": 0.02319512902290519,
+      "grad_norm": 4.936232566833496,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.8443,
+      "step": 40
+    },
+    {
+      "epoch": 0.02377500724847782,
+      "grad_norm": 6.812432289123535,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.8619,
+      "step": 41
+    },
+    {
+      "epoch": 0.024354885474050448,
+      "grad_norm": 5.089122295379639,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.9488,
+      "step": 42
+    },
+    {
+      "epoch": 0.02493476369962308,
+      "grad_norm": 11.766944885253906,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.8397,
+      "step": 43
+    },
+    {
+      "epoch": 0.02551464192519571,
+      "grad_norm": 16.602333068847656,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.2066,
+      "step": 44
+    },
+    {
+      "epoch": 0.02609452015076834,
+      "grad_norm": 9.7608060836792,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.8558,
+      "step": 45
+    },
+    {
+      "epoch": 0.02609452015076834,
+      "eval_loss": 0.8418027758598328,
+      "eval_runtime": 20.5838,
+      "eval_samples_per_second": 282.163,
+      "eval_steps_per_second": 8.842,
+      "step": 45
+    },
+    {
+      "epoch": 0.026674398376340967,
+      "grad_norm": 5.098090171813965,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.8448,
+      "step": 46
+    },
+    {
+      "epoch": 0.0272542766019136,
+      "grad_norm": 9.583770751953125,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.0719,
+      "step": 47
+    },
+    {
+      "epoch": 0.02783415482748623,
+      "grad_norm": 8.428434371948242,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.0309,
+      "step": 48
+    },
+    {
+      "epoch": 0.028414033053058858,
+      "grad_norm": 7.223377704620361,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.9004,
+      "step": 49
+    },
+    {
+      "epoch": 0.028993911278631487,
+      "grad_norm": 5.00840950012207,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.8982,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.02936877203456e+16,
+  "total_flos": 2.05873754406912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null