Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97b55733a1680a3856188a0784564a3672e1b23f298481b76a58a6c2bfb6dc6e
+oid sha256:2c21edf7efa81a4878910a518886bb4a1b05b410d95b1405560da876c2d46bde
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6922b3cc91be5a7d9adb82e4b31e92c9031b6eda94de10432d94bf5db39943f9
+oid sha256:6b0c9e46c26ea557c69791eb1e2794e4dacd0f3e6087d9aa0d71d970a1f8158a
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60391f039986d463d1b8eae9b77fcda050ab137f474c9c67cf4fe317d8dc171a
+oid sha256:4d9612296f4eca8e13bbedc9b337afa02330878ec8a1d77abcf11946476abfc6
 size 14244

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": 0.28922631959508316,
+  "epoch": 0.43383947939262474,
   "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": 8.974,
       "eval_steps_per_second": 4.487,
       "step": 50
+    },
+    {
+      "epoch": 0.2950108459869848,
+      "grad_norm": 3.044539213180542,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.491,
+      "step": 51
+    },
+    {
+      "epoch": 0.3007953723788865,
+      "grad_norm": 8.76490592956543,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 3.5022,
+      "step": 52
+    },
+    {
+      "epoch": 0.3065798987707881,
+      "grad_norm": 11.707574844360352,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 3.6092,
+      "step": 53
+    },
+    {
+      "epoch": 0.3123644251626898,
+      "grad_norm": 12.732514381408691,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.4725,
+      "step": 54
+    },
+    {
+      "epoch": 0.31814895155459144,
+      "grad_norm": 7.573165416717529,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 3.3587,
+      "step": 55
+    },
+    {
+      "epoch": 0.32393347794649313,
+      "grad_norm": 5.776604652404785,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 3.2847,
+      "step": 56
+    },
+    {
+      "epoch": 0.3297180043383948,
+      "grad_norm": 9.322304725646973,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.4005,
+      "step": 57
+    },
+    {
+      "epoch": 0.33550253073029646,
+      "grad_norm": 1.8316805362701416,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 3.2024,
+      "step": 58
+    },
+    {
+      "epoch": 0.34128705712219815,
+      "grad_norm": 1.2074944972991943,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.1161,
+      "step": 59
+    },
+    {
+      "epoch": 0.3470715835140998,
+      "grad_norm": 6.147497653961182,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.7194,
+      "step": 60
+    },
+    {
+      "epoch": 0.35285610990600147,
+      "grad_norm": 5.360683917999268,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 3.3806,
+      "step": 61
+    },
+    {
+      "epoch": 0.3586406362979031,
+      "grad_norm": 3.081329345703125,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 3.1167,
+      "step": 62
+    },
+    {
+      "epoch": 0.3644251626898048,
+      "grad_norm": 6.260736465454102,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.4621,
+      "step": 63
+    },
+    {
+      "epoch": 0.37020968908170643,
+      "grad_norm": 1.834079623222351,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 3.1454,
+      "step": 64
+    },
+    {
+      "epoch": 0.3759942154736081,
+      "grad_norm": 3.3285751342773438,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 3.2656,
+      "step": 65
+    },
+    {
+      "epoch": 0.38177874186550975,
+      "grad_norm": 6.730548858642578,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.4244,
+      "step": 66
+    },
+    {
+      "epoch": 0.38756326825741144,
+      "grad_norm": 2.947965145111084,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.161,
+      "step": 67
+    },
+    {
+      "epoch": 0.3933477946493131,
+      "grad_norm": 5.567538261413574,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 3.3722,
+      "step": 68
+    },
+    {
+      "epoch": 0.39913232104121477,
+      "grad_norm": 4.872069358825684,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.388,
+      "step": 69
+    },
+    {
+      "epoch": 0.4049168474331164,
+      "grad_norm": 0.6829429864883423,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 3.0004,
+      "step": 70
+    },
+    {
+      "epoch": 0.4107013738250181,
+      "grad_norm": 2.973910093307495,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 3.2397,
+      "step": 71
+    },
+    {
+      "epoch": 0.4164859002169197,
+      "grad_norm": 2.918032646179199,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.1185,
+      "step": 72
+    },
+    {
+      "epoch": 0.4222704266088214,
+      "grad_norm": 3.0201897621154785,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 3.418,
+      "step": 73
+    },
+    {
+      "epoch": 0.42805495300072305,
+      "grad_norm": 2.436922550201416,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 3.2234,
+      "step": 74
+    },
+    {
+      "epoch": 0.43383947939262474,
+      "grad_norm": 5.052024841308594,
+      "learning_rate": 0.0,
+      "loss": 3.3554,
+      "step": 75
+    },
+    {
+      "epoch": 0.43383947939262474,
+      "eval_loss": NaN,
+      "eval_runtime": 16.2973,
+      "eval_samples_per_second": 8.959,
+      "eval_steps_per_second": 4.479,
+      "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": 7.46010452164608e+16,
+  "total_flos": 1.119015678246912e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null