Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a5c29abd879857e94133216062f2304e9e5f3d67f8387577bfafc61dea2ae7
+oid sha256:b73129ebca2c646120815928821cbb094851aec7c75d360fdc327e43a8dfd8bd
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ee8cd479cfc025554e76f9ffe951b91d46c5257670871fb8d956f9c01127244
+oid sha256:1d4840536aa29f5c09dda6026ffb608789f5cc38ad4a770362804a0a0458c874
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748f1340fd9b0d57811f59fe041f609e22a6ddf5e0bc7260681bf17e3d449b1b
+oid sha256:5be7640a4620dca9ae692e481495dbb2e47e1c1397961515028b5584ebe5eb54
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
+oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0523083209991455,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.477231329690346,
+  "best_metric": 2.0382425785064697,
+  "best_model_checkpoint": "./outputs/checkpoint-3500",
+  "epoch": 2.5500910746812386,
   "eval_steps": 100,
-  "global_step": 3400,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,13 +483,27 @@
       "eval_samples_per_second": 30.522,
       "eval_steps_per_second": 3.819,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 2.001,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 2.0382425785064697,
+      "eval_runtime": 205.9189,
+      "eval_samples_per_second": 30.468,
+      "eval_steps_per_second": 3.812,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.919903936610304e+16,
+  "total_flos": 1.02120256014336e+17,
   "trial_name": null,
   "trial_params": null
 }