Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610ba9980a82114bff6956c9ff90959aa6e9376248c7df34a4bd522af37a0de8
+oid sha256:fa7ac714911be233fc1605afc3623d8786ad5dcc3962fcd1a2c1a39c5e55a947
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab77640d2a05a648a25a7c0d95839fed11feeefdaf0a6b9667805717e06a555
+oid sha256:2e191f78d073e717c81095ccd8b198bf364b62a50bbd49ac5e12ac417342f421
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4cfe991b3ad712baa288a77dd6f044c8861d31b30f3c0de8fe14a274bb7d623
+oid sha256:e4745157d57379500f6988e7b527195578954ed7a772118d1422d086b38a374f
 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": 1.9635978937149048,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 1.9280308485031128,
+  "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": 11.357,
       "eval_steps_per_second": 1.421,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 1.9447,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 1.9280308485031128,
+      "eval_runtime": 552.7859,
+      "eval_samples_per_second": 11.35,
+      "eval_steps_per_second": 1.42,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.5637373372419277e+17,
+  "total_flos": 1.822689416777564e+17,
   "trial_name": null,
   "trial_params": null
 }