Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7ac714911be233fc1605afc3623d8786ad5dcc3962fcd1a2c1a39c5e55a947
+oid sha256:ebcd56ecae3f56ec1b8e94d2dc7a00a4a049334e064007f096b9cc278ba21282
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e191f78d073e717c81095ccd8b198bf364b62a50bbd49ac5e12ac417342f421
+oid sha256:1896c1cc252d8463f6b7fc743213578c3b18cfe469801ebf2a8ffc2f0241aa98
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4745157d57379500f6988e7b527195578954ed7a772118d1422d086b38a374f
+oid sha256:92ee4bdd7de760b82e132b6c2a923dfa3044fc52b2a20c9ec24faeaadc49fdef
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
+oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9280308485031128,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 1.8917897939682007,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 0.5828779599271403,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,13 +105,27 @@
       "eval_samples_per_second": 11.35,
       "eval_steps_per_second": 1.42,
       "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 1.9024,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 1.8917897939682007,
+      "eval_runtime": 553.0559,
+      "eval_samples_per_second": 11.344,
+      "eval_steps_per_second": 1.419,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.822689416777564e+17,
+  "total_flos": 2.0826998776253645e+17,
   "trial_name": null,
   "trial_params": null
 }