Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4d25015615ff2be6baec1b75d7e1f5d44288b28f9a7c13bbbd79d5ac52075c
+oid sha256:1437ab9c205f3c6289456bd0eedb93f8c33a13345c2cbd131f8eb95272b80839
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6a8c0a35c0744bd3d9feb491d63b5998fd8fb699863467f2f163c578f4bae9
+oid sha256:96a45b512adaad4c9a9163be5c9a27e03c592347d8d527827267be50339b9108
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b708b72239765e2913894959f4b9fc75f2825e61f1491eda436ca51a25bef5f1
+oid sha256:cca3a7099dea147630d4f997ed815413f0ae73f258d866a6a2fb054f2568bdf7
 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": 1.011763572692871,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.0014097690582275,
+  "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": 2.645,
       "eval_steps_per_second": 0.332,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.8276,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.0014097690582275,
+      "eval_runtime": 726.8878,
+      "eval_samples_per_second": 2.655,
+      "eval_steps_per_second": 0.333,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.81363638199296e+17,
+  "total_flos": 2.0717810165526528e+17,
   "trial_name": null,
   "trial_params": null
 }