Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f06716d5e39e3844b62b76246c7392c6c734c0213938b108fb5a9eacfdd9fde
+oid sha256:5114f14048578772bab27863bfc8b2d4da045637d3711af5a51525f66c447cc5
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7d10ccae7d40970506ebff49a96c6ffba1d50c51f47b4f62114311af953d83
+oid sha256:93eba1725ddee7ebc5c1af6d0155138382e88f73d0bbb2b8d4ca32bf6e522e0e
 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": 0.0375286303460598,
-  "best_model_checkpoint": "doc-topic-model_eval-04_train-02/checkpoint-10000",
-  "epoch": 4.930966469428008,
+  "best_metric": 0.03680593520402908,
+  "best_model_checkpoint": "doc-topic-model_eval-04_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": 559.558,
       "eval_steps_per_second": 2.207,
       "step": 10000
+    },
+    {
+      "epoch": 5.177514792899408,
+      "grad_norm": 0.4344967007637024,
+      "learning_rate": 1.896459566074951e-05,
+      "loss": 0.0306,
+      "step": 10500
+    },
+    {
+      "epoch": 5.424063116370808,
+      "grad_norm": 0.38051480054855347,
+      "learning_rate": 1.891528599605523e-05,
+      "loss": 0.0297,
+      "step": 11000
+    },
+    {
+      "epoch": 5.424063116370808,
+      "eval_accuracy": 0.987519675389718,
+      "eval_f1": 0.6078789227687514,
+      "eval_loss": 0.03680593520402908,
+      "eval_precision": 0.7259968102073365,
+      "eval_recall": 0.5228177641653905,
+      "eval_runtime": 14.3385,
+      "eval_samples_per_second": 565.819,
+      "eval_steps_per_second": 2.232,
+      "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