Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8597ba8588e80536d0b893868fc9ae64230e638d9993645f32eb20c896c673
+oid sha256:91736c796bc4263501fa7cd7cd1bcd62439f1c00315399c6d9e6bca024e414a4
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6602f8a616fc18a69ba091297b722ca624d6a490b23f87388c0a8f8de8155169
+oid sha256:f9ad549d3a51a76634e39b96ee8355c778692be909ad75176c4dea1e9fffa600
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ae9dae747fc095dc62b8a6f8ae99e3da9d6af6fa630374a81e071054e9be93
+oid sha256:4e60fe04b267e89119e991b6e26de5b8f4e8261a99d4810247e04890dd5e6fdf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a433bba38d16cc1737102e6745c4d0f07c63ed160a7e013a9c72ad376fab3c1
+oid sha256:5c2e3172e51a233117e8409439d15569fac6e64c157dd01fdb0a9ccba8b6afb0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5333333333333333,
+  "epoch": 0.8,
   "eval_steps": 9,
-  "global_step": 24,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,29 @@
       "learning_rate": 6.264666911958404e-05,
       "loss": 0.689,
       "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.47360849380493164,
+      "eval_runtime": 15.691,
+      "eval_samples_per_second": 19.31,
+      "eval_steps_per_second": 2.422,
+      "step": 27
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.3193366229534149,
+      "learning_rate": 2.7137883834768073e-05,
+      "loss": 0.4522,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.4535110592842102,
+      "eval_runtime": 15.7131,
+      "eval_samples_per_second": 19.283,
+      "eval_steps_per_second": 2.418,
+      "step": 36
     }
   ],
   "logging_steps": 10,
@@ -64,7 +87,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.691722416986522e+16,
+  "total_flos": 1.0037583625479782e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null