Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e8ffaebfd6ef605ed7a70d898584f2d78a8d777d3176ef4dce697bcdef898c
+oid sha256:47d9450ee32445570ac0f99bd61548d0db965a4e6edd93b15e3b6aaa0d756f1e
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d35e2adfee94a3f11af486d31ba30fb618502f9c1f33b283e9c6c61b50868f
+oid sha256:9f74756958baa31a23d6968c507d7850e8689def8038cd22b1d5acff64dbc0db
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ed4580c3880e0fb178fd3387bc120234bd8b0c5f80ab76ddf25a7512d7b4b3
+oid sha256:712d1e9e9623896c394d82d0be1b750fd445034b8cb9f0073258005a6df45273
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7100428e35f211c455e0edf66e71a9c6844c13e9f45aabcb2c136afe45ca3ce
+oid sha256:71d98b2235723fe888fb281dc5e6454bb5d9e489547cbc29dc5479c4d9a3698e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03805544227361679,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-10000",
-  "epoch": 4.930966469428008,
+  "best_metric": 0.03788253664970398,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-11000",
+  "epoch": 5.424063116370808,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,32 @@
       "eval_samples_per_second": 307.074,
       "eval_steps_per_second": 19.197,
       "step": 10000
+    },
+    {
+      "epoch": 5.177514792899408,
+      "grad_norm": 0.562140703201294,
+      "learning_rate": 9.644970414201184e-06,
+      "loss": 0.033,
+      "step": 10500
+    },
+    {
+      "epoch": 5.424063116370808,
+      "grad_norm": 0.41164836287498474,
+      "learning_rate": 9.151873767258384e-06,
+      "loss": 0.0316,
+      "step": 11000
+    },
+    {
+      "epoch": 5.424063116370808,
+      "eval_accuracy": 0.9873619910143572,
+      "eval_f1": 0.5883764944836819,
+      "eval_loss": 0.03788253664970398,
+      "eval_precision": 0.742254833449802,
+      "eval_recall": 0.4873441920929877,
+      "eval_runtime": 26.6635,
+      "eval_samples_per_second": 304.161,
+      "eval_steps_per_second": 19.015,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -286,7 +312,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 225936279463716.0,
+  "total_flos": 248295812264388.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null