Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f9c5eeeae8ce3ef17b18f75633efed20a9f52e3954cc3eae7290ed5cf3a98d0
+oid sha256:5c6e0b9abff5de5ccd43f31d61b787ba2aee3f96eaa4ec8f7a88de67923b4ff6
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf283ddfb4b8f0719ef65d465da768aad3ba47c205aaae540177ed20826a22c
+oid sha256:19f5c346306dbb56c79cf801333207f9051b4de312229513acea7d0caa4c1c29
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28dcad9d6b90e39da9e1699982fa064dcb877d32535747f7a118dd2ac0fbfdd5
+oid sha256:8e469cd070b89dc51e72ea70f1abc7b0604952145ad3690af2cb6285ddac0941
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3307961225509644,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.8666666666666667,
+  "best_metric": 1.3263577222824097,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 2.0,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,20 @@
       "eval_samples_per_second": 30.79,
       "eval_steps_per_second": 3.862,
       "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 1.4336,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3263577222824097,
+      "eval_runtime": 47.1607,
+      "eval_samples_per_second": 30.767,
+      "eval_steps_per_second": 3.859,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.694619353776128e+16,
+  "total_flos": 5.029365396013056e+16,
   "trial_name": null,
   "trial_params": null
 }