Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f4bb689bd65373ef6717dc634345f6cc7c0c2626a9a5a94183aae7778d8c17f
+oid sha256:bd1e4d09eb2419c4b5c4d9da974d153ab051bebe15cd566b81c560f87258feda
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34dd07745789cd80f6a5b25be9100fc1110ebc44c2ab224f9dc2b548036856c9
+oid sha256:242f2dbca9744b0128482ac838b792502a16494ad677adea668a7c6898a30a07
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028655e510a909aa7d6085e69d23b85f281b9fdd6d7a66b5175d2c3d8b80ca35
+oid sha256:4267e22d8a64de946137e693a74aa29d7c65d83f9a227b17a42126683108c273
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
+oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4017506837844849,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.3869292736053467,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.6666666666666666,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 12.916,
       "eval_steps_per_second": 1.62,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 1.1554,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.3869292736053467,
+      "eval_runtime": 112.4263,
+      "eval_samples_per_second": 12.906,
+      "eval_steps_per_second": 1.619,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.549292795076608e+16,
+  "total_flos": 3.186244674256896e+16,
   "trial_name": null,
   "trial_params": null
 }