Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1a8485baffd4ccd87e49f0cc204b7132e6855e9c887531d30e8568099ec14e8
+oid sha256:8f4359c1517246af96cbb77a51d15f3c3fe03854ab7915f723c33b443e34d216
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f3181fb02820176b6253acf7ac9d567410dc54bd05e6078be7f052a3be504f
+oid sha256:716d5fb25e010e30850dcffa64c89f1b4587923e439afa9f67f4ab5529a26dff
 size 63350356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8f61387f66c53bbe2e89961f3144d563083860b3648a351be094db0e238f002
+oid sha256:b6fb1601e233c6ad038b6e0c4965ded53aaf9e2605d4ccc35f715a367a525a09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb1788e6a1bc90172eb379091d3d6012641cdbceff45f62df18ceefa4d2ee278
+oid sha256:ca97dd6e0a879cf37203c8ac4ac76e2c0890a9a7dd8fadcb1eb1d709bf1c03dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.042,
+  "epoch": 0.048,
   "eval_steps": 1000,
-  "global_step": 105,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -637,13 +637,103 @@
       "learning_rate": 6.122448979591838e-05,
       "loss": 1.8219,
       "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.9863945578231295e-05,
+      "loss": 1.385,
+      "step": 106
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.850340136054422e-05,
+      "loss": 1.6358,
+      "step": 107
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 1.5059,
+      "step": 108
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.5782312925170065e-05,
+      "loss": 1.6794,
+      "step": 109
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.4421768707483e-05,
+      "loss": 1.4888,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.3061224489795926e-05,
+      "loss": 1.3177,
+      "step": 111
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.170068027210885e-05,
+      "loss": 1.5026,
+      "step": 112
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.034013605442177e-05,
+      "loss": 1.8063,
+      "step": 113
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.89795918367347e-05,
+      "loss": 1.8037,
+      "step": 114
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.6401,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.625850340136055e-05,
+      "loss": 1.7781,
+      "step": 116
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.4897959183673474e-05,
+      "loss": 1.7268,
+      "step": 117
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.35374149659864e-05,
+      "loss": 1.6482,
+      "step": 118
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.217687074829932e-05,
+      "loss": 1.5628,
+      "step": 119
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.0816326530612245e-05,
+      "loss": 1.3526,
+      "step": 120
     }
   ],
   "logging_steps": 1,
   "max_steps": 150,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 1.299196538486784e+16,
+  "total_flos": 1.45548167589888e+16,
   "trial_name": null,
   "trial_params": null
 }