Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5a51c5be9fa15b3c5938d0499fabf85a5c7ec8877625564840fe26251d0510
+oid sha256:7d3e1f8b0cec562fb4467971ece65fe9b94eb3ea2eab8bb408b42cc3a0990f80
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:159e95f1842cb435bd6e9ec78d73edf6bce950999da2f0ba9283761629adb3d9
+oid sha256:f3af11427625f8329b704add0a16af887bc5b36ef53e0207553c8fcc14b088a3
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11aa39861938632d003f66031819c4dee0ab0456aa564ddd824501c0c83d2596
+oid sha256:b6053380893400c5dade000ca2c1b057384a8b90a1c04643c48140a2351ddf03
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9869917631149292,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8522727272727273,
+  "best_metric": 1.9750773906707764,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.9943181818181818,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,20 @@
       "eval_samples_per_second": 27.675,
       "eval_steps_per_second": 3.469,
       "step": 600
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002,
+      "loss": 2.133,
+      "step": 700
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.9750773906707764,
+      "eval_runtime": 53.9551,
+      "eval_samples_per_second": 27.653,
+      "eval_steps_per_second": 3.466,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.824958403960832e+16,
+  "total_flos": 2.129173542494208e+16,
   "trial_name": null,
   "trial_params": null
 }