Training in progress, step 125, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4359c1517246af96cbb77a51d15f3c3fe03854ab7915f723c33b443e34d216
+oid sha256:91f0641905b1c19b0ecaa2a7ceb18b2c90f2be1ef403b744548a10b42099c29b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:716d5fb25e010e30850dcffa64c89f1b4587923e439afa9f67f4ab5529a26dff
+oid sha256:e8f1eb4803dee39452a7d8e542ed53dc56b427b0041f610ece0e60ce4e76d009
 size 63350356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6fb1601e233c6ad038b6e0c4965ded53aaf9e2605d4ccc35f715a367a525a09
+oid sha256:31effdf2171c741dae121b4011867918622e8542baaa5be309e0403ba4b6a679
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca97dd6e0a879cf37203c8ac4ac76e2c0890a9a7dd8fadcb1eb1d709bf1c03dc
+oid sha256:5c5810ebf48e1cd08b1da484cd43f42f5cd1b4a4451e8333eb82845cd321c500
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.048,
+  "epoch": 0.05,
   "eval_steps": 1000,
-  "global_step": 120,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,13 +727,43 @@
       "learning_rate": 4.0816326530612245e-05,
       "loss": 1.3526,
       "step": 120
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.945578231292517e-05,
+      "loss": 1.3096,
+      "step": 121
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.809523809523809e-05,
+      "loss": 1.6429,
+      "step": 122
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.673469387755102e-05,
+      "loss": 1.4119,
+      "step": 123
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.5374149659863946e-05,
+      "loss": 1.4932,
+      "step": 124
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.401360544217687e-05,
+      "loss": 1.8325,
+      "step": 125
     }
   ],
   "logging_steps": 1,
   "max_steps": 150,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 1.45548167589888e+16,
+  "total_flos": 1.543232634445824e+16,
   "trial_name": null,
   "trial_params": null
 }