Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738cd3e9b291e2363591fbe3ff9af6e052cab8bf5571b499e700f4d982e70c6a
+oid sha256:e33276c9ecbc2df58cdad065b9f2bffe4ad2e09fbebb38a734a6b5e1fb7c8ba2
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10f70109671073bf3537c88ab8b8eb853571b93bd5fdc09ef614079402b2553
+oid sha256:e46d7e9135196a1dbd5a30e63c77906d9bf25fe20c49c22048b8392f0326ad64
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b156be7230eb92a2c766e47652dc4dae9df7b1f8b521d4e9ecfbf2a31c902a2
+oid sha256:20f5e974d9a5182c0220936ec7ed26d0817f1e2d86d0852117aad18130cf4452
 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": 1.0397064685821533,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.02787184715271,
+  "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": 2.661,
       "eval_steps_per_second": 0.334,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.8549,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.02787184715271,
+      "eval_runtime": 726.5869,
+      "eval_samples_per_second": 2.656,
+      "eval_steps_per_second": 0.333,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.03701644752896e+17,
+  "total_flos": 1.2948397906255872e+17,
   "trial_name": null,
   "trial_params": null
 }