Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ddf43fe41893fc1b73374a7b5c5d5d9b8b7b60d31cb7f1871fc88aa82c4627a
+oid sha256:893e02f1eb9444af0c2b1107bb03e179c3a71f61f0c05123a0fbf9a8b2ef7168
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb4b733f058748cc0bb8363f38aeba96de47a889870c2c0781cad65fe3d42a30
+oid sha256:36c67beb0479a8c156cf2608384f833944771d4f2fd7d2f917a1dc37194716e4
 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": 0.037467557936906815,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-10000",
-  "epoch": 4.930966469428008,
+  "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": 576.991,
       "eval_steps_per_second": 2.277,
       "step": 10000
+    },
+    {
+      "epoch": 5.177514792899408,
+      "grad_norm": 0.302545428276062,
+      "learning_rate": 1.896459566074951e-05,
+      "loss": 0.0308,
+      "step": 10500
+    },
+    {
+      "epoch": 5.424063116370808,
+      "grad_norm": 0.3933587968349457,
+      "learning_rate": 1.891528599605523e-05,
+      "loss": 0.0293,
+      "step": 11000
+    },
+    {
+      "epoch": 5.424063116370808,
+      "eval_accuracy": 0.9876893858865882,
+      "eval_f1": 0.6104932735426009,
+      "eval_loss": 0.03747553750872612,
+      "eval_precision": 0.738046188875637,
+      "eval_recall": 0.5205322321633402,
+      "eval_runtime": 14.3104,
+      "eval_samples_per_second": 566.721,
+      "eval_steps_per_second": 2.236,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -295,7 +321,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 225936279463716.0,
+  "total_flos": 248295812264388.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null