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:e32ba736e7484a188370f304faff8702701ff5e87fa491b7197eb96fcac352d1
+oid sha256:374eb0f59bb2d241950909a07232e8845c33a4224de08983d56f5b6e8be8df1d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a292a2aa1fa0e35a552c95ef2a5170ecb6f4ea0ecaabb32211adb6aee84466
+oid sha256:70ba83338e8e97c0afb63d1f496ee83b2316b1c2502e4181341c2705d4805e58
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902bb6277fa9332254dbb09d997080ddfd5d2413b689c8efea4dbf0ed8526ba1
+oid sha256:5dd9eab2552fff04796cac197a350c170210977f4c82c1a504ecd3da12163e05
 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": 2.470156192779541,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.36429872495446264,
+  "best_metric": 2.4447057247161865,
+  "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": 5.462,
       "eval_steps_per_second": 0.683,
       "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 2.4445,
+      "step": 600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 2.4447057247161865,
+      "eval_runtime": 1011.8783,
+      "eval_samples_per_second": 6.2,
+      "eval_steps_per_second": 0.776,
+      "step": 600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.469294009229312e+16,
+  "total_flos": 1.763801617342464e+16,
   "trial_name": null,
   "trial_params": null
 }