Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b243e91650d984cd48a780a2307484fafefa2aab286b75ebba7e3a7a12a164
+oid sha256:96ffde2b90673c714d52bceec69378ae95e14ce6de2ee0fd0760ad45f0c0fee6
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb7805dab37f9d6c59626322bc9a5fccb4d5a892fedcd30a7dd092c8d9446589
+oid sha256:70cce5e59bcd2a74ec3b9f4b861b367749c1b0ed2949f0c87c30534325dce43a
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d880e5bb61f695737bb8ab52d42681f045639984678ecc79e639583358afa74
+oid sha256:0eb73b134a129617820e93a4630f6c7e447cc6d5f8021ee7120ae17f44e4c73e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9801441431045532,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 0.9762414693832397,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.2666666666666666,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 5.433,
       "eval_steps_per_second": 0.681,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 0.8418,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 0.9762414693832397,
+      "eval_runtime": 354.5929,
+      "eval_samples_per_second": 5.443,
+      "eval_steps_per_second": 0.682,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.523634737775329e+17,
+  "total_flos": 4.807017024378716e+17,
   "trial_name": null,
   "trial_params": null
 }