Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6e4c082d501bb224875391fdd6f736743339d832506372e5f2a45e8349fbd0
+oid sha256:5e5dae4b3133c3f1d3efbdf27e0b0a1cc71a740c2c00020260a63f989bd18734
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ee97ef702ef9363b2415621655d881418155e00011968ab6d3657d60ea8dd3
+oid sha256:6f8ac8204defe6ef0c5d6edea76bb19a294188ace298b136e00f4156c8ed67c8
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5fc3c50cdd89b756fc18d24145f32808900a648c88164f9eaa35dda3ef94be5
+oid sha256:62994a63c57db4bd735bcd0bf8e74e5ec2c1419980ea0d4b68540e5b92d2a32f
 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": 0.0485319097306479,
+  "epoch": 0.07279786459597185,
   "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": 10.578,
       "eval_steps_per_second": 5.289,
       "step": 50
+    },
+    {
+      "epoch": 0.04950254792526086,
+      "grad_norm": 14.676257133483887,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 16.5266,
+      "step": 51
+    },
+    {
+      "epoch": 0.050473186119873815,
+      "grad_norm": 16.664396286010742,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 15.4079,
+      "step": 52
+    },
+    {
+      "epoch": 0.051443824314486776,
+      "grad_norm": 14.102425575256348,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 17.3366,
+      "step": 53
+    },
+    {
+      "epoch": 0.05241446250909974,
+      "grad_norm": 13.748454093933105,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 15.3754,
+      "step": 54
+    },
+    {
+      "epoch": 0.05338510070371269,
+      "grad_norm": 12.722488403320312,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 15.9749,
+      "step": 55
+    },
+    {
+      "epoch": 0.05435573889832565,
+      "grad_norm": 15.23315715789795,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 17.2161,
+      "step": 56
+    },
+    {
+      "epoch": 0.055326377092938604,
+      "grad_norm": 14.689871788024902,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 17.5618,
+      "step": 57
+    },
+    {
+      "epoch": 0.056297015287551565,
+      "grad_norm": 16.280412673950195,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 18.4658,
+      "step": 58
+    },
+    {
+      "epoch": 0.057267653482164525,
+      "grad_norm": 13.941516876220703,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 15.9958,
+      "step": 59
+    },
+    {
+      "epoch": 0.05823829167677748,
+      "grad_norm": 16.41193962097168,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 19.0942,
+      "step": 60
+    },
+    {
+      "epoch": 0.05920892987139044,
+      "grad_norm": 17.583078384399414,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 17.5917,
+      "step": 61
+    },
+    {
+      "epoch": 0.0601795680660034,
+      "grad_norm": 11.958739280700684,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 15.9693,
+      "step": 62
+    },
+    {
+      "epoch": 0.061150206260616354,
+      "grad_norm": 13.119291305541992,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 15.9703,
+      "step": 63
+    },
+    {
+      "epoch": 0.062120844455229314,
+      "grad_norm": 14.385025978088379,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 17.2932,
+      "step": 64
+    },
+    {
+      "epoch": 0.06309148264984227,
+      "grad_norm": 14.750713348388672,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 18.0548,
+      "step": 65
+    },
+    {
+      "epoch": 0.06406212084445523,
+      "grad_norm": 13.296215057373047,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 16.307,
+      "step": 66
+    },
+    {
+      "epoch": 0.06503275903906819,
+      "grad_norm": 13.6669282913208,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 17.0559,
+      "step": 67
+    },
+    {
+      "epoch": 0.06600339723368115,
+      "grad_norm": 16.986690521240234,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 19.5746,
+      "step": 68
+    },
+    {
+      "epoch": 0.06697403542829411,
+      "grad_norm": 16.449094772338867,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 20.126,
+      "step": 69
+    },
+    {
+      "epoch": 0.06794467362290706,
+      "grad_norm": 12.487732887268066,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 15.3881,
+      "step": 70
+    },
+    {
+      "epoch": 0.06891531181752002,
+      "grad_norm": 19.560585021972656,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 16.7532,
+      "step": 71
+    },
+    {
+      "epoch": 0.06988595001213298,
+      "grad_norm": 14.803143501281738,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 17.8502,
+      "step": 72
+    },
+    {
+      "epoch": 0.07085658820674594,
+      "grad_norm": 14.384745597839355,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 18.2168,
+      "step": 73
+    },
+    {
+      "epoch": 0.0718272264013589,
+      "grad_norm": 16.81536102294922,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 19.9418,
+      "step": 74
+    },
+    {
+      "epoch": 0.07279786459597185,
+      "grad_norm": 15.681601524353027,
+      "learning_rate": 0.0,
+      "loss": 18.5786,
+      "step": 75
+    },
+    {
+      "epoch": 0.07279786459597185,
+      "eval_loss": 2.282241106033325,
+      "eval_runtime": 82.1445,
+      "eval_samples_per_second": 10.567,
+      "eval_steps_per_second": 5.283,
+      "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": 6.57388096978944e+16,
+  "total_flos": 9.86082145468416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null