Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d67b6d1e5ac08c55ca272dae5cef94538203ca81a7fd6189cc24a85e8020af1d
+oid sha256:8627ab63880fea3011447cb73f1dfbce83a72a704600888571a5d40e6758e417
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05dae8539f5c93edb2c67fdaaadbb3ffc382a05d59552d72ef43583b1403bbd1
+oid sha256:78b1bdef003d1399d3a6d37c6aa98d9120bd6ce3419fde88e8606366b6870ccd
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59436ee7d20f5ba0ec694086a8e3e4769ad9219178f69a9c92d3d97e58bb26b2
+oid sha256:b6598ba8d28457ca982679bb4678b929548195f1692dc85503bc0d791879d46e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3913403749465942,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 1.3872549533843994,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.2666666666666666,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 15.552,
       "eval_steps_per_second": 1.951,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 1.1354,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 1.3872549533843994,
+      "eval_runtime": 93.3779,
+      "eval_samples_per_second": 15.539,
+      "eval_steps_per_second": 1.949,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.356583872176128e+16,
+  "total_flos": 9.940658531844096e+16,
   "trial_name": null,
   "trial_params": null
 }