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:fa5909f0a9994c40cc63ab73d78a9b828af0471a2a3983463378f2ac8e9d44a7
+oid sha256:83409419a26e54eec6ac5fdba7d817d4bc5c396d0f0d9fc46676b5f028867df7
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7c11257e50ab93e4ac86192837132e542b18318988b37567f67604518ac8db
+oid sha256:a8e2c9d77a06d9d880ff9870bf22cfdac221a1d65de8b0372ca7e70ed54a6190
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff68bc1413209b0087a6b2cf9fed69a476793fcd5e396a94dfdeb01c5356ea6
+oid sha256:bd02f143f7f3623496ceb4789d51e487857b4fe6db678fd0ec9d179938869bae
 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": 1.0153926610946655,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.0099254846572876,
+  "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": 5.462,
       "eval_steps_per_second": 0.685,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.8684,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.0099254846572876,
+      "eval_runtime": 353.3411,
+      "eval_samples_per_second": 5.462,
+      "eval_steps_per_second": 0.685,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.9797272643079373e+17,
+  "total_flos": 2.2622081570707046e+17,
   "trial_name": null,
   "trial_params": null
 }