Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6219c6f96c04c63ddbffee5fad2f0dbd62e9616ce460b4ec6c10b49932d48d46
+oid sha256:ed78b4c7caeb15dd57eea82a68cf3242c1e12d0a44d96297192b7f1f0f3aa8f2
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d08da7901afe79c41eb68eb63c0e7b7ea08a6cf21789ab0b9527eb44731bb92
+oid sha256:ba99e473e6e559ac96caa8d187be1a1e5d6e727cd5a960916ae204e03e107383
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41eb3cc90529708ec3050e7a2a3e956faee68b39027a1409168255234e541c3d
+oid sha256:be78a4950643aa2c0f7f3e14329f834829bfe49fb52a0d080a54375bd9ada6a0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4029204845428467,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.5828779599271403,
+  "best_metric": 2.3802640438079834,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 0.6557377049180327,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,13 +119,27 @@
       "eval_samples_per_second": 30.6,
       "eval_steps_per_second": 3.829,
       "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 2.3706,
+      "step": 900
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 2.3802640438079834,
+      "eval_runtime": 205.3365,
+      "eval_samples_per_second": 30.555,
+      "eval_steps_per_second": 3.823,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.349160133935104e+16,
+  "total_flos": 2.64265735974912e+16,
   "trial_name": null,
   "trial_params": null
 }