Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2c7f8a4ed21ccfa9124972bb6565f42e77a90dc33b333ccf177f72c3db3dd3
+oid sha256:1230569206b348fb781d50e417d12f3585dee67c5c5703842a76d1573f5d7bc1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6088dc64cbe0ac01faadfae0eaed9a2310d161874529eebd4f42e66e32db7ca2
+oid sha256:0ada9045c87e11f497cf400c9c350bfa2d70d3138123d6ca4b0eb3d1d6aae116
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146eb5506064fb4ca3bcd461d553541c18c3ad661a9fffff0c43399202ffb137
+oid sha256:766ec007f8a0827b4a22e5c46eb9f4b04e997c9016bb19983b438ca028a07183
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5638d3c6abe10668193456baecbe88e2a7a80e3ab2e23c2f753dd99e2ddc2467
+oid sha256:dbb73fc3e17c35c263f3c872b3582d1d07b93edeca3b172479c74fcbd6cd5cc3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ca6a10bf1a8dd7587f60576e0017d28e3d7190095a2b23aaa57aad2ecfcd7e5
+oid sha256:4609fb06478300119ea5fdb62ed8588f536a0def941c2d2ca4447729af4707ea
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bca20e85bb4c9fe024050b4ce0513f921870d198211baeb02b2ecb4aeaa4c0f
+oid sha256:18c6a163d87daf9f41745c8452db562c72f11a42abaef2cbb3e4debc7d21f612
 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": 0.08196721311475409,
+  "epoch": 0.1092896174863388,
   "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": 4.8847,
       "step": 75
+    },
+    {
+      "epoch": 0.08306010928961749,
+      "grad_norm": 0.7232154011726379,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.9066,
+      "step": 76
+    },
+    {
+      "epoch": 0.08415300546448087,
+      "grad_norm": 0.6170682907104492,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 4.923,
+      "step": 77
+    },
+    {
+      "epoch": 0.08524590163934426,
+      "grad_norm": 0.49551859498023987,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 4.9564,
+      "step": 78
+    },
+    {
+      "epoch": 0.08633879781420765,
+      "grad_norm": 0.46370407938957214,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 4.9055,
+      "step": 79
+    },
+    {
+      "epoch": 0.08743169398907104,
+      "grad_norm": 0.5205159783363342,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.8709,
+      "step": 80
+    },
+    {
+      "epoch": 0.08852459016393442,
+      "grad_norm": 0.6012383699417114,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 4.9006,
+      "step": 81
+    },
+    {
+      "epoch": 0.08852459016393442,
+      "eval_loss": 4.908712387084961,
+      "eval_runtime": 55.644,
+      "eval_samples_per_second": 55.37,
+      "eval_steps_per_second": 1.743,
+      "step": 81
+    },
+    {
+      "epoch": 0.08961748633879782,
+      "grad_norm": 0.6838329434394836,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 5.003,
+      "step": 82
+    },
+    {
+      "epoch": 0.0907103825136612,
+      "grad_norm": 0.6821178793907166,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 4.9449,
+      "step": 83
+    },
+    {
+      "epoch": 0.09180327868852459,
+      "grad_norm": 0.5011351108551025,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 4.8949,
+      "step": 84
+    },
+    {
+      "epoch": 0.09289617486338798,
+      "grad_norm": 0.6648871898651123,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.8848,
+      "step": 85
+    },
+    {
+      "epoch": 0.09398907103825137,
+      "grad_norm": 0.5797678828239441,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.8899,
+      "step": 86
+    },
+    {
+      "epoch": 0.09508196721311475,
+      "grad_norm": 0.9921677112579346,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 4.984,
+      "step": 87
+    },
+    {
+      "epoch": 0.09617486338797815,
+      "grad_norm": 0.5813995599746704,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 4.8188,
+      "step": 88
+    },
+    {
+      "epoch": 0.09726775956284153,
+      "grad_norm": 0.5218381285667419,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 4.8906,
+      "step": 89
+    },
+    {
+      "epoch": 0.09836065573770492,
+      "grad_norm": 0.8028129935264587,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.8837,
+      "step": 90
+    },
+    {
+      "epoch": 0.09836065573770492,
+      "eval_loss": 4.907496929168701,
+      "eval_runtime": 55.6919,
+      "eval_samples_per_second": 55.322,
+      "eval_steps_per_second": 1.742,
+      "step": 90
+    },
+    {
+      "epoch": 0.0994535519125683,
+      "grad_norm": 0.45788004994392395,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 4.8955,
+      "step": 91
+    },
+    {
+      "epoch": 0.1005464480874317,
+      "grad_norm": 0.4592156708240509,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 4.8768,
+      "step": 92
+    },
+    {
+      "epoch": 0.10163934426229508,
+      "grad_norm": 0.5255284309387207,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 4.9354,
+      "step": 93
+    },
+    {
+      "epoch": 0.10273224043715846,
+      "grad_norm": 0.7076261043548584,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 4.8474,
+      "step": 94
+    },
+    {
+      "epoch": 0.10382513661202186,
+      "grad_norm": 0.6252774000167847,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 4.8941,
+      "step": 95
+    },
+    {
+      "epoch": 0.10491803278688525,
+      "grad_norm": 0.45233267545700073,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 4.8658,
+      "step": 96
+    },
+    {
+      "epoch": 0.10601092896174863,
+      "grad_norm": 0.4194464683532715,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 4.8726,
+      "step": 97
+    },
+    {
+      "epoch": 0.10710382513661203,
+      "grad_norm": 0.4344501495361328,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 4.8811,
+      "step": 98
+    },
+    {
+      "epoch": 0.10819672131147541,
+      "grad_norm": 0.7105288505554199,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 4.962,
+      "step": 99
+    },
+    {
+      "epoch": 0.10819672131147541,
+      "eval_loss": 4.906777858734131,
+      "eval_runtime": 55.621,
+      "eval_samples_per_second": 55.393,
+      "eval_steps_per_second": 1.744,
+      "step": 99
+    },
+    {
+      "epoch": 0.1092896174863388,
+      "grad_norm": 0.42179667949676514,
+      "learning_rate": 0.0,
+      "loss": 4.9524,
+      "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": 2.496450742064251e+17,
+  "total_flos": 3.34220225606058e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null