Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:007f6b24edc41404479f5bb854ec2cd4a1978cd2337d057ee563433199c9b77d
+oid sha256:01a7f69327d0024b24ca4ed51941c318f1fcbb752ff023875cfd2555eb1d6369
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef162a08746f5b07557989aa92c3ea24954b07ff9ead49acf3c7ae37695c9752
+oid sha256:5390d4be9fcf3c2edc2b58c9fbed59fe6b5b28381ee247eeca9a1370a2ee0abd
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b09a88054123c089ea7a12187c1a69bb1039c54e68994009c312791f99785e8
+oid sha256:a419c8171381ef52bb95c0db9d7dc0f3373840624ba9300b663743186a3ad699
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0230828523635864,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.7102272727272727,
+  "best_metric": 1.0142004489898682,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8522727272727273,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 12.001,
       "eval_steps_per_second": 1.504,
       "step": 500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002,
+      "loss": 1.1612,
+      "step": 600
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.0142004489898682,
+      "eval_runtime": 124.2613,
+      "eval_samples_per_second": 12.007,
+      "eval_steps_per_second": 1.505,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.80842883485696e+16,
+  "total_flos": 3.370874435518464e+16,
   "trial_name": null,
   "trial_params": null
 }