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:c6654ec142bf8709363917f4fb46f9b18031ac28b9333e5cb8f38f43e33e50b9
+oid sha256:864d6f31b08d9917321da7b041e730e709a95988224c40549462b9061b8ceacd
 size 75012288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b0c8b7e52ff85dcbc2f0b99687ed697c2985a726fdce31fd350a84b1969431
+oid sha256:d30c24e7b6c5d6d68d4d36de8bcb738ca6b809e2da60e9e52d3f4d367f6cd9cd
 size 38034724

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889d0cc867cbfb43ba68c124df826b0b034aee4977d4e2bcbed5aec2b804c16c
+oid sha256:34a39a74283cd7442cd8c578574c3e2f695a82d81222275b0c418dc60bf965cc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6108f4faef547664ffc49f24479d791d4a8a5a6cda6f7c8b0f62fd8408e62a4f
+oid sha256:ca97dd6e0a879cf37203c8ac4ac76e2c0890a9a7dd8fadcb1eb1d709bf1c03dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.038,
+  "epoch": 0.048,
   "eval_steps": 1000,
-  "global_step": 95,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -577,13 +577,163 @@
       "learning_rate": 7.482993197278913e-05,
       "loss": 1.753,
       "step": 95
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.346938775510205e-05,
+      "loss": 1.8511,
+      "step": 96
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.210884353741498e-05,
+      "loss": 1.96,
+      "step": 97
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.074829931972789e-05,
+      "loss": 1.8998,
+      "step": 98
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.938775510204082e-05,
+      "loss": 2.0674,
+      "step": 99
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.802721088435374e-05,
+      "loss": 1.8385,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.9221,
+      "step": 101
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.530612244897959e-05,
+      "loss": 1.9015,
+      "step": 102
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.394557823129253e-05,
+      "loss": 2.0576,
+      "step": 103
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.258503401360545e-05,
+      "loss": 2.1968,
+      "step": 104
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.122448979591838e-05,
+      "loss": 2.1305,
+      "step": 105
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.9863945578231295e-05,
+      "loss": 1.7918,
+      "step": 106
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.850340136054422e-05,
+      "loss": 1.8854,
+      "step": 107
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 1.8177,
+      "step": 108
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.5782312925170065e-05,
+      "loss": 2.1727,
+      "step": 109
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.4421768707483e-05,
+      "loss": 1.8914,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.3061224489795926e-05,
+      "loss": 1.7695,
+      "step": 111
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.170068027210885e-05,
+      "loss": 1.8377,
+      "step": 112
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.034013605442177e-05,
+      "loss": 2.294,
+      "step": 113
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.89795918367347e-05,
+      "loss": 2.0519,
+      "step": 114
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 2.1649,
+      "step": 115
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.625850340136055e-05,
+      "loss": 2.1548,
+      "step": 116
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.4897959183673474e-05,
+      "loss": 2.0267,
+      "step": 117
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.35374149659864e-05,
+      "loss": 2.036,
+      "step": 118
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.217687074829932e-05,
+      "loss": 1.8979,
+      "step": 119
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.0816326530612245e-05,
+      "loss": 1.6725,
+      "step": 120
     }
   ],
   "logging_steps": 1,
   "max_steps": 150,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 5026926877999104.0,
+  "total_flos": 6341073926553600.0,
   "trial_name": null,
   "trial_params": null
 }