Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e219836db331fb2c22e167af2c158d700560aae27dc6a75c160dae363c629cd1
+oid sha256:d0a3a9ed1385ba2a9486987fb064d61e322c4b33a584269d83c319b3e60a9b07
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d088274e6e4b583afe59f323ed350eaf66dca870661c394c8ede6293508ee82e
+oid sha256:33e7221101e4a7fade7ddd4b88da7c505da46d19376708b1c05f8d12428b2803
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:babf9cef0f970e1cd241f9533a5b0bc052a39fc9df617e7f31209a9691bd42d1
+oid sha256:557e474a226d303e26d6758a2eb18bb0bbe3b1a451146f9953c40e79b727f273
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f5541cd8b8cc2355cb28b7b43b87c2e735f1841d8477f8ed4c15392845734c
+oid sha256:1723a4b1c943236de3935bcf77e35b80aec5d8ffd41a734f2052202a2aabea88
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024,
+  "epoch": 0.028,
   "eval_steps": 1000,
-  "global_step": 60,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -367,13 +367,73 @@
       "learning_rate": 8.421052631578948e-05,
       "loss": 1.5684,
       "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 1.6735,
+      "step": 61
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8e-05,
+      "loss": 1.5827,
+      "step": 62
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 1.5755,
+      "step": 63
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 1.3339,
+      "step": 64
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 1.4373,
+      "step": 65
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.157894736842105e-05,
+      "loss": 1.9484,
+      "step": 66
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.947368421052632e-05,
+      "loss": 1.5517,
+      "step": 67
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.736842105263159e-05,
+      "loss": 1.5427,
+      "step": 68
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.526315789473685e-05,
+      "loss": 1.689,
+      "step": 69
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 1.5722,
+      "step": 70
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 3532725037301760.0,
+  "total_flos": 4233108315045888.0,
   "trial_name": null,
   "trial_params": null
 }