Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374eb0f59bb2d241950909a07232e8845c33a4224de08983d56f5b6e8be8df1d
+oid sha256:685403cf0d21e69897f616252e2adb5839f7d33817f17f8624c9d7899f0f9d32
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ba83338e8e97c0afb63d1f496ee83b2316b1c2502e4181341c2705d4805e58
+oid sha256:af0a4fddd0b2c5095934b301be929badb16883ad5522c121d61cc04abe8f5e50
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd9eab2552fff04796cac197a350c170210977f4c82c1a504ecd3da12163e05
+oid sha256:41eb3cc90529708ec3050e7a2a3e956faee68b39027a1409168255234e541c3d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4447057247161865,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 2.3991127014160156,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 0.5828779599271403,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,13 +91,41 @@
       "eval_samples_per_second": 6.2,
       "eval_steps_per_second": 0.776,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 2.4269,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 2.4192888736724854,
+      "eval_runtime": 1320.0264,
+      "eval_samples_per_second": 4.753,
+      "eval_steps_per_second": 0.595,
+      "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 2.4054,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 2.3991127014160156,
+      "eval_runtime": 1042.8122,
+      "eval_samples_per_second": 6.016,
+      "eval_steps_per_second": 0.753,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.763801617342464e+16,
+  "total_flos": 2.349160133935104e+16,
   "trial_name": null,
   "trial_params": null
 }