Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00442fabdef9cd6f6ee4abe9204a060029a1252062ddcd6f91a8414bb26bacae
+oid sha256:07b243e91650d984cd48a780a2307484fafefa2aab286b75ebba7e3a7a12a164
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d4584fafec5159597aabea55c8e28bba967cde557f22454be501e72e9f24eb
+oid sha256:cb7805dab37f9d6c59626322bc9a5fccb4d5a892fedcd30a7dd092c8d9446589
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1668bafc1fac3c40e5cf2fd65429ae578b48a366f50cc4885b2a5966b36e3dea
+oid sha256:2d880e5bb61f695737bb8ab52d42681f045639984678ecc79e639583358afa74
 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": 0.9840803742408752,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 2.0,
+  "best_metric": 0.9801441431045532,
+  "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": 5.446,
       "eval_steps_per_second": 0.683,
       "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 0.8378,
+      "step": 1600
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 0.9801441431045532,
+      "eval_runtime": 355.2231,
+      "eval_samples_per_second": 5.433,
+      "eval_steps_per_second": 0.681,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.240820711718666e+17,
+  "total_flos": 4.523634737775329e+17,
   "trial_name": null,
   "trial_params": null
 }