Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:729e80fa5a56dddbd3568280b599de97dd67e128d29037ea40e0f66ca464de3c
+oid sha256:bd53468f08ccb39d41344bba9104ceffb549f0f68a1935f381aef0aa8e44c0a1
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa1107da0888b5e93317a9497854d5ca8456d301e6972adbc4c34a63b106699
+oid sha256:99e0c4c123698d20b20d25c0bf40a5d83f33571e56290b7cb4a998cc892254bb
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd2d2d356a6c3709632f8060658d88927b3077f687f92ce543110b675e2b8961
+oid sha256:661132494b4c0506032580f9c35d6510ed068b7fc40b99aabcb38637ceecc016
 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": 0.01552312946289972,
+  "epoch": 0.03104625892579944,
   "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": 0.105,
       "step": 25
+    },
+    {
+      "epoch": 0.01614405464141571,
+      "grad_norm": 0.08792968839406967,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.1057,
+      "step": 26
+    },
+    {
+      "epoch": 0.016764979819931698,
+      "grad_norm": 0.11934582889080048,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.3323,
+      "step": 27
+    },
+    {
+      "epoch": 0.016764979819931698,
+      "eval_loss": 0.08386289328336716,
+      "eval_runtime": 196.8416,
+      "eval_samples_per_second": 6.889,
+      "eval_steps_per_second": 0.864,
+      "step": 27
+    },
+    {
+      "epoch": 0.017385904998447686,
+      "grad_norm": 0.10690551996231079,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.2852,
+      "step": 28
+    },
+    {
+      "epoch": 0.018006830176963674,
+      "grad_norm": 0.10729014128446579,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.1705,
+      "step": 29
+    },
+    {
+      "epoch": 0.018627755355479666,
+      "grad_norm": 0.08282957226037979,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.1005,
+      "step": 30
+    },
+    {
+      "epoch": 0.019248680533995654,
+      "grad_norm": 0.0728306695818901,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.1307,
+      "step": 31
+    },
+    {
+      "epoch": 0.019869605712511642,
+      "grad_norm": 0.09638900309801102,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.1735,
+      "step": 32
+    },
+    {
+      "epoch": 0.02049053089102763,
+      "grad_norm": 0.16475456953048706,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.1015,
+      "step": 33
+    },
+    {
+      "epoch": 0.02111145606954362,
+      "grad_norm": 0.06533080339431763,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.1143,
+      "step": 34
+    },
+    {
+      "epoch": 0.02173238124805961,
+      "grad_norm": 0.10168042778968811,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.1452,
+      "step": 35
+    },
+    {
+      "epoch": 0.022353306426575598,
+      "grad_norm": 0.07452461123466492,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.1062,
+      "step": 36
+    },
+    {
+      "epoch": 0.022353306426575598,
+      "eval_loss": 0.0813056007027626,
+      "eval_runtime": 196.8112,
+      "eval_samples_per_second": 6.89,
+      "eval_steps_per_second": 0.864,
+      "step": 36
+    },
+    {
+      "epoch": 0.022974231605091586,
+      "grad_norm": 0.07804828137159348,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.1323,
+      "step": 37
+    },
+    {
+      "epoch": 0.023595156783607574,
+      "grad_norm": 0.08380841463804245,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.1257,
+      "step": 38
+    },
+    {
+      "epoch": 0.024216081962123565,
+      "grad_norm": 0.10386836528778076,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.1927,
+      "step": 39
+    },
+    {
+      "epoch": 0.024837007140639553,
+      "grad_norm": 0.08352355659008026,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.215,
+      "step": 40
+    },
+    {
+      "epoch": 0.02545793231915554,
+      "grad_norm": 0.202205091714859,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.1606,
+      "step": 41
+    },
+    {
+      "epoch": 0.02607885749767153,
+      "grad_norm": 0.08188100904226303,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0946,
+      "step": 42
+    },
+    {
+      "epoch": 0.02669978267618752,
+      "grad_norm": 0.07515822350978851,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.1653,
+      "step": 43
+    },
+    {
+      "epoch": 0.02732070785470351,
+      "grad_norm": 0.09081997722387314,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.1845,
+      "step": 44
+    },
+    {
+      "epoch": 0.027941633033219497,
+      "grad_norm": 0.09180609881877899,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.1406,
+      "step": 45
+    },
+    {
+      "epoch": 0.027941633033219497,
+      "eval_loss": 0.07980942726135254,
+      "eval_runtime": 196.6543,
+      "eval_samples_per_second": 6.895,
+      "eval_steps_per_second": 0.864,
+      "step": 45
+    },
+    {
+      "epoch": 0.028562558211735485,
+      "grad_norm": 0.09287755936384201,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.1577,
+      "step": 46
+    },
+    {
+      "epoch": 0.029183483390251473,
+      "grad_norm": 0.043771930038928986,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0785,
+      "step": 47
+    },
+    {
+      "epoch": 0.029804408568767465,
+      "grad_norm": 0.04385403171181679,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0575,
+      "step": 48
+    },
+    {
+      "epoch": 0.030425333747283453,
+      "grad_norm": 0.07490763813257217,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.2689,
+      "step": 49
+    },
+    {
+      "epoch": 0.03104625892579944,
+      "grad_norm": 0.07791085541248322,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.1212,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.284351662718976e+16,
+  "total_flos": 1.2632181625061376e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null