Training in progress, step 4100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d34f51b826488b7a68e04dd1ad9a2012437084c8afce13bedeacdd8049d3779
+oid sha256:da61c9bd0ee9b310143e532757e8421c597cdff3ac3375c6cb3419037251596b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa3baf33adc9b53e289ad704c1565aa54a2d162d348032a671476fad7d07bb7
+oid sha256:3b51fa149e965f0d4cfd591eecc927348a71037dfc95356b1cf729899c5b61b1
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ef6c3858e7d84aa5f4da6d612efb7619c9f1a991da1e501295c2a72877c544
+oid sha256:ae8ecb1d7e34eae942eaf84679636cb08f247f9d84a52bdede4840acdcb4d717
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
+oid sha256:f55ebe991e4838deda9ff3044672335e03697b65b3fe0753cca61998e974ee51
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.053968906402588,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9143897996357016,
+  "best_metric": 2.044205904006958,
+  "best_model_checkpoint": "./outputs/checkpoint-4100",
+  "epoch": 2.987249544626594,
   "eval_steps": 100,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,13 +567,27 @@
       "eval_samples_per_second": 30.492,
       "eval_steps_per_second": 3.815,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 2.0268,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 2.044205904006958,
+      "eval_runtime": 205.9228,
+      "eval_samples_per_second": 30.468,
+      "eval_steps_per_second": 3.812,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1387458434336768e+17,
+  "total_flos": 1.1671768877819904e+17,
   "trial_name": null,
   "trial_params": null
 }