Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14b092cdf5b91d7fea51c845d5d9744584ab4667c35dd3bce3976ae1b719e6f6
+oid sha256:a4e844362d2b758b1a5b342be2a9247b24f01e38556c931d26bd6b6a9ad4cd67
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a3b2ee2dd3f38a12bf4d3a8e79bfed41289cc81a507cf28c25cd1978aab538
+oid sha256:62a173dc3d8cc29aa2f07f96bc55ee4491554e5053df89fc02e2705436badbb7
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9db3df1f7e3c6108cf2455f42014ea709c97a495fd74faf2761323ee28fc169
+oid sha256:bd8a24a385cb71560f44319d7f96b3f5db0ea1776994de824c1079951b7246d9
 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": 1.0332194566726685,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.0276169776916504,
+  "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": 5.461,
       "eval_steps_per_second": 0.685,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.8814,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.0276169776916504,
+      "eval_runtime": 353.0472,
+      "eval_samples_per_second": 5.467,
+      "eval_steps_per_second": 0.685,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1319907133059891e+17,
+  "total_flos": 1.4137479027061555e+17,
   "trial_name": null,
   "trial_params": null
 }