Training in progress, step 3300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8b5642561b3b9fabfd1aaf1fa969a3044a37fcf5023d5b01a3fdb15d3b2c51
+oid sha256:632cb7fe2984f32e86c13864a1dce0833da54120304a9c2914d21e5f6966e30a
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f545629542c6116b51b84b52b07ca997046ac4e872e65c4ec330241c173db297
+oid sha256:9f47fbecfcd21436c1f1d65dff4e5cf34dd137cc52b4cce67892d99af888cf1e
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1cdd076b217373af7247c4e5586438d32391ac0523ee9c4ea56789d6d16d28
+oid sha256:4990b57e009f07924326e7ab4d50989339930d6a542dfcc59f2ec6a0cb45c651
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
+oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.139963388442993,
-  "best_model_checkpoint": "./outputs/checkpoint-3200",
-  "epoch": 2.3315118397085612,
+  "best_metric": 2.128814935684204,
+  "best_model_checkpoint": "./outputs/checkpoint-3300",
+  "epoch": 2.4043715846994536,
   "eval_steps": 100,
-  "global_step": 3200,
+  "global_step": 3300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,13 +455,27 @@
       "eval_samples_per_second": 30.546,
       "eval_steps_per_second": 3.822,
       "step": 3200
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 2.0835,
+      "step": 3300
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 2.128814935684204,
+      "eval_runtime": 205.0918,
+      "eval_samples_per_second": 30.591,
+      "eval_steps_per_second": 3.828,
+      "step": 3300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.113803498211328e+16,
+  "total_flos": 9.39792070812672e+16,
   "trial_name": null,
   "trial_params": null
 }