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:a5073bf21c34c40dbb93a9ead42d983bc797e25fd1548c06c21d9b82e1a4534e
+oid sha256:3eae2c909c0b188f49a6174da336a26b8164b53795806f0dc85846f5f04ecdd7
 size 3029024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62bf5b8b6e1bd2f3dd05037847704cee6389e9591b0ce2e9b34e6914131c1ac8
+oid sha256:b56b378748cad9a1f8656a0f8649e37e5290ef6a0fa18f2936ef649581a1a35d
 size 1663290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14289c55b030798cdd0a4c29ef9da4f71e2a6ed28602ce97ca413843f9bf81e6
+oid sha256:784084ca83b073e0e7a3fe1d78d5b6638cd532c397fbb70771b4126ed8891454
 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": 0.3418803418803419,
+  "epoch": 0.39886039886039887,
   "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": 117.126,
       "eval_steps_per_second": 15.036,
       "step": 30
+    },
+    {
+      "epoch": 0.37606837606837606,
+      "grad_norm": 4.130680084228516,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.4977,
+      "step": 33
+    },
+    {
+      "epoch": 0.39886039886039887,
+      "eval_loss": 2.408794641494751,
+      "eval_runtime": 1.2622,
+      "eval_samples_per_second": 117.256,
+      "eval_steps_per_second": 15.053,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 24856661852160.0,
+  "total_flos": 29271989944320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null