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:afd9a17ecfc6dd571be8b178ef014ecacf7c03eb9fa56076ec69f6dc444bfbc6
+oid sha256:dd9715f8f00c422557950dcd8b54a6c4ad84654ecbdd39fe12d52ae5a16b0b62
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d036a4b7d97aa453a173b443096d706f0f1ddd42fa5ae36d779b59baa4ed2ae3
+oid sha256:1a22642a4c45ea6855f7c0f2bfdd8ef33771f846feaa3512de4d5b5a645a0246
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79a0ac751cbc94760fe76ed12d4dbacb7ab37b5aad6ba68e1b9f106650a089c
+oid sha256:6cb68041964332a3b3198a537e05c170401d9ac4a5e4683bc7ba5017973f4ae1
 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": 0.7408167123794556,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 2.1333333333333333,
+  "best_metric": 0.721502423286438,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 2.6666666666666665,
   "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": 8.406,
       "eval_steps_per_second": 1.054,
       "step": 400
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 0.7819,
+      "step": 500
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 0.721502423286438,
+      "eval_runtime": 229.6082,
+      "eval_samples_per_second": 8.406,
+      "eval_steps_per_second": 1.054,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.81295203475456e+17,
+  "total_flos": 3.51635490349056e+17,
   "trial_name": null,
   "trial_params": null
 }