Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c49986d638844e59d81a84676ed14577443b6b38b8144c2376fcc3653058bc
+oid sha256:16446d2047c62bc658ee72946bdeb292b8e578ca2a50f27a7d8f19ef7ebe7ffb
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45a2b9d529342642e23a88cf848020a9c526475581b16c9ee55101cb8632fb27
+oid sha256:8d1166092c985a1a43cdf46e12706afaeb57095bee437f14b8b134e68ebf2793
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff0d769c62ca0f1dfcc5ff54753cf1287953c9fd82927f62dbef8fb59b714db
+oid sha256:befb25161d36cdda0947a0d2c15fd4e0a62f3a19afc6f2b7e3d03c3e626c675d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
+oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4266287088394165,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.410528540611267,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.6666666666666666,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 30.75,
       "eval_steps_per_second": 3.857,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.410528540611267,
+      "eval_runtime": 47.2451,
+      "eval_samples_per_second": 30.712,
+      "eval_steps_per_second": 3.852,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.3414994804736e+16,
+  "total_flos": 1.676874350592e+16,
   "trial_name": null,
   "trial_params": null
 }