Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1ed433eed0de65ddb873dc24eaa4b681986f2fcfb7717aa071db5e84ee3d3c7
+oid sha256:658704b0960cd8fb8a36f35a83a39b3fa3040ded1e6dc2e913e967aeb684a70f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b45b3484b7bda022c107a83b893cce0c4b0523221f25289442a9c6276fd33d4a
+oid sha256:c31dd5016db31342a454363b8de91f8d9cf183e4a8c778154c57c45fbb48611f
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0990d8cdbc2bdd1880b9951298cbfae149ae47de29db9d5d340de0693addfd
+oid sha256:c5e1dc5f769c4cbaa0ba676908c39cfb7cd49352afc3941d90d0685280366309
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4982783794403076,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.36429872495446264,
+  "best_metric": 2.4732720851898193,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.4371584699453552,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,13 +77,27 @@
       "eval_samples_per_second": 30.364,
       "eval_steps_per_second": 3.799,
       "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 2.4681,
+      "step": 600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 2.4732720851898193,
+      "eval_runtime": 206.7564,
+      "eval_samples_per_second": 30.345,
+      "eval_steps_per_second": 3.797,
+      "step": 600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.459702746464256e+16,
+  "total_flos": 1.752346796949504e+16,
   "trial_name": null,
   "trial_params": null
 }