Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80fa3a57d9708cddd9142d3819011418aedaa524c0b53b7c786d849cb8e3c617
+oid sha256:b467182b3f39c711333689719f2fbf2a4878d5a4dc2cda8fa8513993a651ed96
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d237a9a2cb2bf345606e0f288a49c7998e790371004a83437ab48963c73264
+oid sha256:231d8c44f11ef67e5b6089bfe8b0859477cd6bf58c04d03a89192d6ae7a3fa04
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0d220e3ffb9cbe7aa8b7ee81ee25441366727f842c08121cff70e1f43b7a50
+oid sha256:f1f4d93675d93c1e706d0c3cd29c485df32f3cf1ea8f3c5183b0143d179f636b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:350b7a6f8159717ef2af74e68b6e9c8ed2775fab22debcfdf6f728bfa1bef4ad
+oid sha256:ff3806b6ededc075c4c89012dc49cff3604a5f3bc56562d72a0f71b6ec838696
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005755064456721915,
+  "epoch": 0.01151012891344383,
   "eval_steps": 1000,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,13 +157,163 @@
       "learning_rate": 0.00015789473684210527,
       "loss": 1.4316,
       "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00015578947368421052,
+      "loss": 1.5606,
+      "step": 26
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001536842105263158,
+      "loss": 1.7435,
+      "step": 27
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00015157894736842108,
+      "loss": 1.2904,
+      "step": 28
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014947368421052633,
+      "loss": 1.7799,
+      "step": 29
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 1.3407,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 1.7537,
+      "step": 31
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001431578947368421,
+      "loss": 1.6549,
+      "step": 32
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014105263157894736,
+      "loss": 1.8332,
+      "step": 33
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013894736842105264,
+      "loss": 1.4519,
+      "step": 34
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 1.7497,
+      "step": 35
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013473684210526317,
+      "loss": 1.8566,
+      "step": 36
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013263157894736842,
+      "loss": 1.5518,
+      "step": 37
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001305263157894737,
+      "loss": 1.2759,
+      "step": 38
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00012842105263157895,
+      "loss": 1.5634,
+      "step": 39
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 1.3718,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 1.2056,
+      "step": 41
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00012210526315789474,
+      "loss": 1.3365,
+      "step": 42
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00012,
+      "loss": 1.5912,
+      "step": 43
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00011789473684210525,
+      "loss": 1.5067,
+      "step": 44
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 1.8345,
+      "step": 45
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001136842105263158,
+      "loss": 1.5727,
+      "step": 46
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00011157894736842105,
+      "loss": 1.5058,
+      "step": 47
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00010947368421052633,
+      "loss": 1.5746,
+      "step": 48
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00010736842105263158,
+      "loss": 1.4634,
+      "step": 49
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 1.6622,
+      "step": 50
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 505946473365504.0,
+  "total_flos": 1012834322104320.0,
   "trial_name": null,
   "trial_params": null
 }