Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ecb0e7e871d247340910e9c43dc76ecf1f1f7fb9caab19a424362d56858048
+oid sha256:7ed9faaac264e4441cfd4a3e95b97c89c1e30d8119f5e8a8bdf478127284b4ab
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9e98f3e8018ef9402f8bed7bad02205b0d0d4167f1c684c350e8463b92c7bd
+oid sha256:af14e3810a989c86d9cd1f1509eea0deeb1368c7649e64e86b966b1caa372132
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a6492d1b5c194543f2b211b57f9ad8cc03582b9b8fe48eb7a61392100f57c6
+oid sha256:d60e0505be6747b50a677a0e3b039e2ad98d67bfaffddade49b1dc6f03872291
 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": 1.3629770278930664,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.3554208278656006,
+  "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": 12.905,
       "eval_steps_per_second": 1.619,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 1.1184,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.3554208278656006,
+      "eval_runtime": 112.4809,
+      "eval_samples_per_second": 12.9,
+      "eval_steps_per_second": 1.618,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.455201325768704e+16,
+  "total_flos": 5.087703920173056e+16,
   "trial_name": null,
   "trial_params": null
 }