Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56fa8d7be178ee2386ff1c1a4bc67f182a8721dd4331e4bcc991769a3cb39771
+oid sha256:5a59f4ac2413b276b1fc59cac830c1fb123fedd28c879a5b1c259b76870ecb7f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf7ce8c645cdcb3a14cbd1a171eb563fe5a6b76f293a0e6b93b3e135be3f44fe
+oid sha256:2cc93434cb48f32b17e88e2596cc8aaec326f46a7c9d6f9069617bf00ab825a9
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf66005e5e6a4f3553669f4e9894b69e1bc5f9207c5bf2c3d2ce3aab9394607
+oid sha256:5e2584adcfe5878130368943010052e98d7f9569785b451bb350577d373a1f2f
 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": 2.4297590255737305,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.5828779599271403,
+  "best_metric": 2.4085500240325928,
+  "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": 30.325,
       "eval_steps_per_second": 3.794,
       "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 2.3922,
+      "step": 900
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 2.4085500240325928,
+      "eval_runtime": 206.8407,
+      "eval_samples_per_second": 30.333,
+      "eval_steps_per_second": 3.795,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.333865205776384e+16,
+  "total_flos": 2.625477585518592e+16,
   "trial_name": null,
   "trial_params": null
 }