Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6e0b9abff5de5ccd43f31d61b787ba2aee3f96eaa4ec8f7a88de67923b4ff6
+oid sha256:1011ccee280f4d387b7dd49c756a3b568ea07513b6f0af636d7377d45f5a1c64
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f5c346306dbb56c79cf801333207f9051b4de312229513acea7d0caa4c1c29
+oid sha256:17c047531f5a9dc02e0b0a4ba57131ef7a75564a628a8ae0f4f2c224ba61b708
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e469cd070b89dc51e72ea70f1abc7b0604952145ad3690af2cb6285ddac0941
+oid sha256:49486dec9d2a122c787933aef8bb6360b19f8df93705d5491661116da481a185
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3263577222824097,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 2.0,
+  "best_metric": 1.319887638092041,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 2.1333333333333333,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 30.767,
       "eval_steps_per_second": 3.859,
       "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 1.3981,
+      "step": 1600
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.319887638092041,
+      "eval_runtime": 47.019,
+      "eval_samples_per_second": 30.86,
+      "eval_steps_per_second": 3.871,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.029365396013056e+16,
+  "total_flos": 5.364740266131456e+16,
   "trial_name": null,
   "trial_params": null
 }