Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328faf494edd10b13e41db154ed048b702c17b9ccbc5c23e546bdc1fe9922c7f
+oid sha256:53ce65206cf6ca0cf316938d51c6c033e151e1e6ac908945246c9b956f4a10d9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30fca5bb017a17ab092c6dd50cded3c8b8d747efde3211075d3e56b9cb117207
+oid sha256:059cf83137ad470f03a7369832c1c02c2e711f6619ff7818b16635ee7d869f38
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a202b6ef127b2f370e29b02a695f7e35fad888ae4707bbaedeec3926ad69a8
+oid sha256:169c733cf7764f1d968254c0dd657bf888f42fc96732223a4c949c1fbe9bd0bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bbe372fc24045f3af45b8a1f0a38bf204533a38daba940e611e0a4525dedf0a
+oid sha256:93721a0af79aa5eb1e01c404a6e6402b4f90a54ab1a62e1b2ab8d44938b03bd3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0018656716417910447,
+  "epoch": 0.0024875621890547263,
   "eval_steps": 1000,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -457,13 +457,163 @@
       "learning_rate": 5.894736842105263e-05,
       "loss": 1.5599,
       "step": 75
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.68421052631579e-05,
+      "loss": 1.3117,
+      "step": 76
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 1.5121,
+      "step": 77
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 1.6346,
+      "step": 78
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.052631578947369e-05,
+      "loss": 1.5391,
+      "step": 79
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.842105263157895e-05,
+      "loss": 1.6792,
+      "step": 80
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.6315789473684214e-05,
+      "loss": 1.6389,
+      "step": 81
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.421052631578947e-05,
+      "loss": 1.6191,
+      "step": 82
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 1.6297,
+      "step": 83
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4e-05,
+      "loss": 1.5525,
+      "step": 84
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.789473684210527e-05,
+      "loss": 1.4816,
+      "step": 85
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.578947368421053e-05,
+      "loss": 1.5453,
+      "step": 86
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 1.7132,
+      "step": 87
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 1.7889,
+      "step": 88
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.9473684210526314e-05,
+      "loss": 1.3749,
+      "step": 89
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.7368421052631583e-05,
+      "loss": 1.337,
+      "step": 90
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.5263157894736845e-05,
+      "loss": 1.4863,
+      "step": 91
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.3157894736842107e-05,
+      "loss": 1.4914,
+      "step": 92
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 1.3957,
+      "step": 93
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 1.4742,
+      "step": 94
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 1.6525,
+      "step": 95
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.4736842105263157e-05,
+      "loss": 1.6347,
+      "step": 96
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.2631578947368422e-05,
+      "loss": 1.5477,
+      "step": 97
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 1.318,
+      "step": 98
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 1.8458,
+      "step": 99
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.315789473684211e-06,
+      "loss": 2.0586,
+      "step": 100
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 4329984398917632.0,
+  "total_flos": 5587576318083072.0,
   "trial_name": null,
   "trial_params": null
 }