Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf75e9f7d313d527240ac551355e534391d99f81884f733e019c5dcebe82e55b
+oid sha256:8725196c2f79209246c12a790ee169423016258c3022f5f27e4fea285bf1cb3e
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d25c396353aecdb4280688541fb3749f41820f123cf2b5100ea7a9d50de74bb1
+oid sha256:ddb7433355ac0f8a2d80f5c7bb5e3d022707d482f7f0280b8af45643c6de474e
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd9eab2552fff04796cac197a350c170210977f4c82c1a504ecd3da12163e05
+oid sha256:ed490e04c6dbbc7419c7365a93701b5d2a1915c9651cc1654bfd578cd611575f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4451191425323486,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 2.4199516773223877,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.5100182149362478,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,13 +91,27 @@
       "eval_samples_per_second": 28.987,
       "eval_steps_per_second": 3.627,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 2.426,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 2.4199516773223877,
+      "eval_runtime": 206.0859,
+      "eval_samples_per_second": 30.444,
+      "eval_steps_per_second": 3.809,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.763801617342464e+16,
+  "total_flos": 2.055883980423168e+16,
   "trial_name": null,
   "trial_params": null
 }