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:dc1f98f3daff695b396850a8fd2c653bbf591b72f35585af46240c78a3910e2d
+oid sha256:43823720485b7c0b0a6002e378db7856e3f0cd4a663dff54b4c8ac57399ee23a
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e0ba78e040e9d084a303c61531079748c2851e4cecb8a13795f0fbecc2b9ce
+oid sha256:a215aba06725b96bf2c4035f6b1a36fc2a79ac5e7fe2dc9348d69a7f3588e407
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e1dc5f769c4cbaa0ba676908c39cfb7cd49352afc3941d90d0685280366309
+oid sha256:db6358da13f324834878bd2b4485e5667664a0d92ed16a7f6a761dd9dea8cc65
 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": 2.4666266441345215,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 2.4440107345581055,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.5100182149362478,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,13 +91,27 @@
       "eval_samples_per_second": 30.259,
       "eval_steps_per_second": 3.786,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 2.4503,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 2.4440107345581055,
+      "eval_runtime": 205.5485,
+      "eval_samples_per_second": 30.523,
+      "eval_steps_per_second": 3.819,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.752346796949504e+16,
+  "total_flos": 2.042513200078848e+16,
   "trial_name": null,
   "trial_params": null
 }