Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685403cf0d21e69897f616252e2adb5839f7d33817f17f8624c9d7899f0f9d32
+oid sha256:717789acec531724bbca5228348513f55140ef32652cda04a35cafa2030681f6
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af0a4fddd0b2c5095934b301be929badb16883ad5522c121d61cc04abe8f5e50
+oid sha256:9932a466a26a1112fd43990abcc3b532fb793b8b13d6ca0d0a08f88973b6a181
 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": 2.3991127014160156,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.5828779599271403,
+  "best_metric": 2.3775434494018555,
+  "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": 6.016,
       "eval_steps_per_second": 0.753,
       "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 2.3697,
+      "step": 900
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 2.3775434494018555,
+      "eval_runtime": 1384.392,
+      "eval_samples_per_second": 4.532,
+      "eval_steps_per_second": 0.567,
+      "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
 }