Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92190f8b60e1b347a82cc983ab17dec13d6baf5d3c32a172584e661feca25fe3
+oid sha256:8484d47d9a1b122980dac6b46b9093a2dfee07d3da65e0d8135ac8c9bff6b77e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41cb0bd857552669c92c2590bc5e30ae850641ca043e849ddffa72cd4c0f66a4
+oid sha256:cbde67f0814fdb7d8517672cfc4ee4eb80fd3fbe4c5985a7394cf686cc3e46b4
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b959cb1ce422e3352f7139006f61ea00d94797d8f826a1d0563c117d182549
+oid sha256:39e1fa739be38c0ecc700b93383eddca8d0d8996f93a259e69da0b654f53164c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb15a5c4a887fb67eec53b267e92476bc5d195a8e876a263ade17c8374535c64
+oid sha256:b3650e20050569394f687cb7687f744dbcc6d34264abfcc372a6e5d276fd41be
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09277c658aac53de56a76c737235ffcec56e6d1ada247740097429f79a342cf
+oid sha256:8d4dc0c617abb57d140ce2555832dd04a7435a6f9ae9740dd2e5a4b43b8f7f68
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6585539bba2e47261c89e37f54fe8b8331de96f10b73c530b92078fd565040
+oid sha256:9fbeee0840ae5d96be4ffc3947fde5203010182245dac936eb2a32fc0b95136d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8620689655172413,
+  "epoch": 1.1494252873563218,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 1.0461,
       "step": 75
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 3.0415401458740234,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.0349,
+      "step": 76
+    },
+    {
+      "epoch": 0.8850574712643678,
+      "grad_norm": 2.195345163345337,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.0251,
+      "step": 77
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 2.426616668701172,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.9611,
+      "step": 78
+    },
+    {
+      "epoch": 0.9080459770114943,
+      "grad_norm": 2.147824764251709,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.9574,
+      "step": 79
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 2.656771183013916,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.8996,
+      "step": 80
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 2.546450614929199,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.9439,
+      "step": 81
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "eval_loss": 0.9282479286193848,
+      "eval_runtime": 4.5082,
+      "eval_samples_per_second": 64.771,
+      "eval_steps_per_second": 2.218,
+      "step": 81
+    },
+    {
+      "epoch": 0.9425287356321839,
+      "grad_norm": 2.3778107166290283,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0639,
+      "step": 82
+    },
+    {
+      "epoch": 0.9540229885057471,
+      "grad_norm": 2.096968650817871,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.9685,
+      "step": 83
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 2.37005615234375,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.8449,
+      "step": 84
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "grad_norm": 2.449625015258789,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1266,
+      "step": 85
+    },
+    {
+      "epoch": 0.9885057471264368,
+      "grad_norm": 2.3689582347869873,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.7579,
+      "step": 86
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.018507957458496,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.8983,
+      "step": 87
+    },
+    {
+      "epoch": 1.0114942528735633,
+      "grad_norm": 2.1007754802703857,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.9065,
+      "step": 88
+    },
+    {
+      "epoch": 1.0229885057471264,
+      "grad_norm": 2.1503047943115234,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.9619,
+      "step": 89
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 2.1539535522460938,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8945,
+      "step": 90
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "eval_loss": 0.9081452488899231,
+      "eval_runtime": 4.5144,
+      "eval_samples_per_second": 64.681,
+      "eval_steps_per_second": 2.215,
+      "step": 90
+    },
+    {
+      "epoch": 1.0459770114942528,
+      "grad_norm": 1.942844033241272,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.929,
+      "step": 91
+    },
+    {
+      "epoch": 1.0574712643678161,
+      "grad_norm": 2.309030532836914,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.7949,
+      "step": 92
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 1.807147741317749,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.6934,
+      "step": 93
+    },
+    {
+      "epoch": 1.0804597701149425,
+      "grad_norm": 1.9581191539764404,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8087,
+      "step": 94
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "grad_norm": 1.7313923835754395,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.7197,
+      "step": 95
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 2.4519922733306885,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.9069,
+      "step": 96
+    },
+    {
+      "epoch": 1.1149425287356323,
+      "grad_norm": 2.065762996673584,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.041,
+      "step": 97
+    },
+    {
+      "epoch": 1.1264367816091954,
+      "grad_norm": 2.0888917446136475,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.8069,
+      "step": 98
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 2.430549383163452,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.9178,
+      "step": 99
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "eval_loss": 0.9052245020866394,
+      "eval_runtime": 4.5334,
+      "eval_samples_per_second": 64.41,
+      "eval_steps_per_second": 2.206,
+      "step": 99
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 1.9606387615203857,
+      "learning_rate": 0.0,
+      "loss": 0.8569,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.225661850681344e+17,
+  "total_flos": 2.967549134241792e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null