Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb0fea2624417a134bf4d806943d46d0df84b8139af66969b3d20c485697b36
+oid sha256:a14ba6d631b491aedf133a76099b0070972351da82405b18ac3450de34336449
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23e6f0ae672e0e5eaa99adb8fa3b78c30b98b9dbbdc3615e50c6852a0f626cb7
+oid sha256:73ea4bb0360117a07d4f6423fa49546e2503080cd4f5396d578fe653c6c03609
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b7e320b5a2475507aebb5f1ef7a9c98d12600ef0165cc1de949f181761d986b
+oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e35c5a0c1eb4f922a2e3785d5afca45020e4d0fc6713cc20aea6ed31f143e1
+oid sha256:c3c3f1ac50882defeade258e77931f3038c02d6276451a81f8ef210f495feca4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.037819646298885345,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-10000",
-  "epoch": 4.930966469428008,
+  "best_metric": 0.03748522698879242,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/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": 561.004,
       "eval_steps_per_second": 2.214,
       "step": 10000
+    },
+    {
+      "epoch": 5.177514792899408,
+      "grad_norm": 0.27451589703559875,
+      "learning_rate": 1.896459566074951e-05,
+      "loss": 0.0309,
+      "step": 10500
+    },
+    {
+      "epoch": 5.424063116370808,
+      "grad_norm": 0.49061715602874756,
+      "learning_rate": 1.891528599605523e-05,
+      "loss": 0.0305,
+      "step": 11000
+    },
+    {
+      "epoch": 5.424063116370808,
+      "eval_accuracy": 0.9875278143912014,
+      "eval_f1": 0.5959595959595959,
+      "eval_loss": 0.03748522698879242,
+      "eval_precision": 0.7457198667126278,
+      "eval_recall": 0.4962911982870689,
+      "eval_runtime": 14.4209,
+      "eval_samples_per_second": 562.38,
+      "eval_steps_per_second": 2.219,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -295,7 +321,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 225449121090996.0,
+  "total_flos": 248019064848396.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null