Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe07a554af711434a231e15c37571d0f1e82457f2ec78db6d2938268b9211a59
+oid sha256:fa51538c0fee57c20d3cf0e5731daee81d09fdaecb65b37354cbfbb0b5f8907b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f19738f88c071e37aae616cbf15ebb804f4421be27a0cda193c825e0e818bd9
+oid sha256:68efcc9d57f32ad2e4b4bce16e4b755288014677e1b23a6b972ef3ed184ea2a8
 size 63350356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3fbea5d1a6eda079b7b558d4de40c6d205a4bfa942ab3704e24899a9f2ac99
+oid sha256:3fa0224b8fb2b0426a129f41a0666ecf84d9b716217e39a5d1bf97eabc1d4486
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f2218f477430ebda5ecb5f72feb1185ee7e06c2f4fdb4f892b5ebe005568e9
+oid sha256:0a7277563b68f0a25594bd8f04a2297ddade7a93c1062f094bae84be2463e566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028,
+  "epoch": 0.034,
   "eval_steps": 1000,
-  "global_step": 70,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,13 +427,103 @@
       "learning_rate": 0.000108843537414966,
       "loss": 1.5901,
       "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00010748299319727892,
+      "loss": 2.1238,
+      "step": 71
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00010612244897959185,
+      "loss": 1.8808,
+      "step": 72
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 1.3648,
+      "step": 73
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001034013605442177,
+      "loss": 1.3667,
+      "step": 74
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00010204081632653062,
+      "loss": 1.3925,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00010068027210884355,
+      "loss": 1.8534,
+      "step": 76
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.931972789115646e-05,
+      "loss": 1.6686,
+      "step": 77
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.79591836734694e-05,
+      "loss": 1.5057,
+      "step": 78
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.659863945578231e-05,
+      "loss": 1.4539,
+      "step": 79
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 1.6102,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.387755102040817e-05,
+      "loss": 1.3404,
+      "step": 81
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.25170068027211e-05,
+      "loss": 1.5923,
+      "step": 82
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.115646258503402e-05,
+      "loss": 1.34,
+      "step": 83
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.979591836734695e-05,
+      "loss": 1.9159,
+      "step": 84
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.843537414965987e-05,
+      "loss": 1.5353,
+      "step": 85
     }
   ],
   "logging_steps": 1,
   "max_steps": 150,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 7958034868224000.0,
+  "total_flos": 9498160042721280.0,
   "trial_name": null,
   "trial_params": null
 }