Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e67697f17e762619d981408d2c71213bc441ad7cf1cf26ca548b44e867a02e2
+oid sha256:daeff66861b1bb8e10a8a4b2fa5e26b2fa62e76b005ca8f6d1bffcb21e484468
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb923cfc0bb479c66e20a0e80bcad9d4d6b8bea4df056cad549097d0cb9773d
+oid sha256:1dc394bf6a456a93edba920f41515ccacd7970b2357a1a999c146b87824f5b61
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79831184d8761b439426d827835dea90620ef2d98de95a117a27f25e53c50d7
+oid sha256:582cc8aa49e974392bd5e2d05cf5ba08f75171157c53dcab0e4535c2ffe7f1a1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd2462d84b9c409f788dc59014621b5a1ac687f3218c1e0a848f9d86c104ada
+oid sha256:ac7168470c28b8d1453aa8203d3ac0f545c244271c557db1477c67cec1a51b1f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c97c56889b7108d6d31aeaf250f192497f7caf503f5c065f132a2336c8664bb
+oid sha256:92f62274c64db0e75f1633db5764e473cdabbeff16531739a667790dfb829936
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693201ad908e9d330de7b26df110922666167694ac9de34f9d74986fe338af43
+oid sha256:2beafe063a4930fec9331cef5daac16773c6fc5997aaef353ee7760ea3c12727
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008531877226286714,
+  "epoch": 0.012797815839430071,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 732.69,
       "eval_steps_per_second": 91.605,
       "step": 50
+    },
+    {
+      "epoch": 0.008702514770812448,
+      "grad_norm": 0.12032278627157211,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3626,
+      "step": 51
+    },
+    {
+      "epoch": 0.008873152315338183,
+      "grad_norm": 0.1271769106388092,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 10.3652,
+      "step": 52
+    },
+    {
+      "epoch": 0.009043789859863916,
+      "grad_norm": 0.141665980219841,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 10.3599,
+      "step": 53
+    },
+    {
+      "epoch": 0.009214427404389651,
+      "grad_norm": 0.13702242076396942,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.36,
+      "step": 54
+    },
+    {
+      "epoch": 0.009385064948915386,
+      "grad_norm": 0.1380140483379364,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3587,
+      "step": 55
+    },
+    {
+      "epoch": 0.009555702493441119,
+      "grad_norm": 0.13641560077667236,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 10.3608,
+      "step": 56
+    },
+    {
+      "epoch": 0.009726340037966854,
+      "grad_norm": 0.13100895285606384,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3616,
+      "step": 57
+    },
+    {
+      "epoch": 0.009896977582492588,
+      "grad_norm": 0.12846271693706512,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 10.3619,
+      "step": 58
+    },
+    {
+      "epoch": 0.010067615127018321,
+      "grad_norm": 0.13571766018867493,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3567,
+      "step": 59
+    },
+    {
+      "epoch": 0.010238252671544056,
+      "grad_norm": 0.13997390866279602,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3581,
+      "step": 60
+    },
+    {
+      "epoch": 0.010408890216069791,
+      "grad_norm": 0.1389489769935608,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 10.3575,
+      "step": 61
+    },
+    {
+      "epoch": 0.010579527760595526,
+      "grad_norm": 0.13576483726501465,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 10.3604,
+      "step": 62
+    },
+    {
+      "epoch": 0.010750165305121259,
+      "grad_norm": 0.13779397308826447,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3585,
+      "step": 63
+    },
+    {
+      "epoch": 0.010920802849646994,
+      "grad_norm": 0.1366213858127594,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 10.3575,
+      "step": 64
+    },
+    {
+      "epoch": 0.011091440394172728,
+      "grad_norm": 0.13486158847808838,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 10.3585,
+      "step": 65
+    },
+    {
+      "epoch": 0.011262077938698462,
+      "grad_norm": 0.13139954209327698,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3606,
+      "step": 66
+    },
+    {
+      "epoch": 0.011432715483224196,
+      "grad_norm": 0.12867534160614014,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3581,
+      "step": 67
+    },
+    {
+      "epoch": 0.011603353027749931,
+      "grad_norm": 0.13455729186534882,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 10.3612,
+      "step": 68
+    },
+    {
+      "epoch": 0.011773990572275664,
+      "grad_norm": 0.1373881995677948,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.358,
+      "step": 69
+    },
+    {
+      "epoch": 0.011944628116801399,
+      "grad_norm": 0.12862622737884521,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 10.3565,
+      "step": 70
+    },
+    {
+      "epoch": 0.012115265661327134,
+      "grad_norm": 0.13009482622146606,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3591,
+      "step": 71
+    },
+    {
+      "epoch": 0.012285903205852869,
+      "grad_norm": 0.1357179880142212,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3593,
+      "step": 72
+    },
+    {
+      "epoch": 0.012456540750378602,
+      "grad_norm": 0.12576642632484436,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 10.359,
+      "step": 73
+    },
+    {
+      "epoch": 0.012627178294904336,
+      "grad_norm": 0.11770795285701752,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 10.3594,
+      "step": 74
+    },
+    {
+      "epoch": 0.012797815839430071,
+      "grad_norm": 0.1474674642086029,
+      "learning_rate": 0.0,
+      "loss": 10.359,
+      "step": 75
+    },
+    {
+      "epoch": 0.012797815839430071,
+      "eval_loss": 10.35882568359375,
+      "eval_runtime": 29.264,
+      "eval_samples_per_second": 674.549,
+      "eval_steps_per_second": 84.336,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 21517679984640.0,
+  "total_flos": 32289884995584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null