Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f4fdcf5e3b4417a0329873432857b3b77f67093dc5db64b204950775fb4072
+oid sha256:a19f761e30bf830087770b48019218736fd5b299fc345ac2a9e749fe3a0c0f30
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46c3b077e8f82b7fbb71de478ed3942ec8bcdd6fc58d64032966d9ad607ebe0
+oid sha256:0ace67a63ab5e8241fbb758d52c5ad501256cdd48ca70fd3daad6abc6c98c0c2
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83d451a7d2201b5472bb63276fd396f894278db57fcb29bd3dd23fcc3da5182
+oid sha256:902bb6277fa9332254dbb09d997080ddfd5d2413b689c8efea4dbf0ed8526ba1
 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": 2.4987542629241943,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.29143897996357016,
+  "best_metric": 2.4730148315429688,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.36429872495446264,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,13 +63,27 @@
       "eval_samples_per_second": 30.492,
       "eval_steps_per_second": 3.815,
       "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 2.4703,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 2.4730148315429688,
+      "eval_runtime": 205.8153,
+      "eval_samples_per_second": 30.484,
+      "eval_steps_per_second": 3.814,
+      "step": 500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.17553968451584e+16,
+  "total_flos": 1.469294009229312e+16,
   "trial_name": null,
   "trial_params": null
 }