Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf9b6e2348e02def5a3b8c1a9f88e25e47905d4bc78b4bae2354609bb70b4a0
+oid sha256:0f06716d5e39e3844b62b76246c7392c6c734c0213938b108fb5a9eacfdd9fde
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f52a6863a831a5bec4df1e55c57cf22df385efea497b5ad5f467b270cb55440
+oid sha256:6e7d10ccae7d40970506ebff49a96c6ffba1d50c51f47b4f62114311af953d83
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1128d67de3d4d8e3dd8bc8b4bca4f59bef7d1d2c35b978700b48aaaa3a3cb733
+oid sha256:6b7e320b5a2475507aebb5f1ef7a9c98d12600ef0165cc1de949f181761d986b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d4e0d33a262ad4f64c2ce77b757798ccbd7d82035d16a8a99e7def08d07a9c
+oid sha256:28e35c5a0c1eb4f922a2e3785d5afca45020e4d0fc6713cc20aea6ed31f143e1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03866717591881752,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-9000",
-  "epoch": 4.437869822485207,
+  "best_metric": 0.03805249184370041,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-10000",
+  "epoch": 4.930966469428008,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,32 @@
       "eval_samples_per_second": 573.27,
       "eval_steps_per_second": 2.262,
       "step": 9000
+    },
+    {
+      "epoch": 4.684418145956608,
+      "grad_norm": 0.4473079442977905,
+      "learning_rate": 1.906311637080868e-05,
+      "loss": 0.0336,
+      "step": 9500
+    },
+    {
+      "epoch": 4.930966469428008,
+      "grad_norm": 0.4554208219051361,
+      "learning_rate": 1.90138067061144e-05,
+      "loss": 0.0337,
+      "step": 10000
+    },
+    {
+      "epoch": 4.930966469428008,
+      "eval_accuracy": 0.9872131751633431,
+      "eval_f1": 0.5864882207351728,
+      "eval_loss": 0.03805249184370041,
+      "eval_precision": 0.7368421052631579,
+      "eval_recall": 0.48709554625047585,
+      "eval_runtime": 14.2923,
+      "eval_samples_per_second": 567.44,
+      "eval_steps_per_second": 2.239,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -269,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 203241954845196.0,
+  "total_flos": 225936279463716.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null