Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73bfa6440683109b8befa5ac0a80bbccce58a29dee9017c4fb7f5b434e057f5
+oid sha256:6525ba687a40964541835a306b046af7d20aa0da91707f063012412f5b447c72
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af94a070466463ae1ca32552955e1eb6c995e2a9156c5640b2f12fe6b28a93fb
+oid sha256:7a4f4c1b0653d2d7116e90a4522870f6aad26b28709dd24a1d4a1e3710a0a984
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4bc0fbdde4f390cae1da26df59eb2c832095420c66886351f99a6e9b7aa264e
+oid sha256:e6c760e18afd0b6280aeb7d401fe56fa9e714d09b578fad90d37a6e9ad6827b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25862068965517243,
+  "epoch": 0.3017241379310345,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,21 @@
       "eval_samples_per_second": 10.857,
       "eval_steps_per_second": 1.392,
       "step": 30
+    },
+    {
+      "epoch": 0.28448275862068967,
+      "grad_norm": 11.339786529541016,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.8155,
+      "step": 33
+    },
+    {
+      "epoch": 0.3017241379310345,
+      "eval_loss": 0.648213803768158,
+      "eval_runtime": 17.968,
+      "eval_samples_per_second": 10.853,
+      "eval_steps_per_second": 1.391,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.292994026962944e+16,
+  "total_flos": 5.008493031456768e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null