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:d4e711fb5213b570fafbf2d24dc61266d78713353107789250289134e329196d
+oid sha256:280f24b69ed2f388e06fe78ab19f755b372c01f593abbb544fff93efa4098e07
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44519410a5f6e493e34ecdea966835658bdb192e9dd2db80bb8de17af1103000
+oid sha256:67b6a63014dfc8220d6c4ebd78976e4d61bf5ca40b12c9d8617dfaedb7bf006c
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6354a4b04feedc19b821f8af1464ec698fc5ee0df4728119ed85d846a048e2a
+oid sha256:926d0f02ed35ff822c8351520aea564c896c73584b204d9f89321ceacb12846d
 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": 1.2945491075515747,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.2894083261489868,
+  "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": 15.26,
       "eval_steps_per_second": 1.913,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 1.1119,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.2894083261489868,
+      "eval_runtime": 126.4649,
+      "eval_samples_per_second": 15.261,
+      "eval_steps_per_second": 1.914,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.4194150656786432e+16,
+  "total_flos": 1.7727133699817472e+16,
   "trial_name": null,
   "trial_params": null
 }