Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40836a859b2cdb7b8277d38e75ae6a3e3b1af4560318b7a45e6b5828b1a17d4d
+oid sha256:2c1b16b748c6a7b5ea4f6ee7c5b4dc21ac3ece52e22b8375bcdbfadcda3560a1
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e231fe7841d08f0fcbec5c9e0801379a00de3ae16a076fcaec79eab59a36faa
+oid sha256:765f8c0511f7ed625cfa1cf33f354a07a3e70c69b3f8fc19ed1233dfcf311c3d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cfaf422c3607cab8ab925751360ef6b2209d09d20c7d5a51cd9f13ec5aa92b2
+oid sha256:c27825f80e934c9a8d3c9b5a430cbea7a1b4ba4344dc4a816cbff7a8b52fb3a7
 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": 0.9654238224029541,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 2.1306818181818183,
+  "best_metric": 0.9602729082107544,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 2.2727272727272725,
   "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": 12.425,
       "eval_steps_per_second": 1.557,
       "step": 1500
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 0.9602729082107544,
+      "eval_runtime": 120.231,
+      "eval_samples_per_second": 12.409,
+      "eval_steps_per_second": 1.555,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.435041115203584e+16,
+  "total_flos": 9.000052792141824e+16,
   "trial_name": null,
   "trial_params": null
 }