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:d400b185a0c396eb23cef9f0c6d63b5ee812b3b5b7e959da8649c8c623f1bbf8
+oid sha256:f6a07dc9f6d3b6b6c9fe0e4a09904c62c3262911cbf734454a249beb72130e78
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a9d0e2d590379e96436ebb3f22b220a4cb53dffd5fbc1c79d13c21ee3197d87
+oid sha256:61aceeef314c87236da6bea5ba9bd25e944c12d6a1db9c22b73100f2c67568cf
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60281c4008506649c7ada220785e38c906a536a16c271810e82687b16f02ad9e
+oid sha256:95e3024b90e00cf4151fee10d610544743e4f135eee8d4c57a1b90111d87f86c
 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": 1.3729456663131714,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.359381914138794,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 1.0666666666666667,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,6 +105,20 @@
       "eval_samples_per_second": 12.736,
       "eval_steps_per_second": 1.597,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 1.1179,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.359381914138794,
+      "eval_runtime": 151.6759,
+      "eval_samples_per_second": 12.725,
+      "eval_steps_per_second": 1.596,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.463977077374976e+16,
+  "total_flos": 5.0989814733312e+16,
   "trial_name": null,
   "trial_params": null
 }