Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:893e02f1eb9444af0c2b1107bb03e179c3a71f61f0c05123a0fbf9a8b2ef7168
+oid sha256:afbf9989a447bed277743dcb2ea80a7cb3fcb1bbaa95e58b211d2a73dfea0ffd
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c67beb0479a8c156cf2608384f833944771d4f2fd7d2f917a1dc37194716e4
+oid sha256:7f649395a4870f6a70a61bc31d55a3c65cb309a97ffaec5349d10a193cffa235
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
+oid sha256:9a445c512a69801b68e319bfb3cb3702cfd8c222330cff7d4d1380aca05cd09b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3c3f1ac50882defeade258e77931f3038c02d6276451a81f8ef210f495feca4
+oid sha256:1600bc22796954bbfe2cfe1a5708dbdc0d32592a1fa22b6a9c5489c11d5fbd8c
 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": 5.424063116370808,
+  "best_metric": 0.03745245933532715,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-12000",
+  "epoch": 5.9171597633136095,
   "eval_steps": 1000,
-  "global_step": 11000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -293,6 +293,32 @@
       "eval_samples_per_second": 566.721,
       "eval_steps_per_second": 2.236,
       "step": 11000
+    },
+    {
+      "epoch": 5.670611439842209,
+      "grad_norm": 0.46541067957878113,
+      "learning_rate": 1.886597633136095e-05,
+      "loss": 0.0297,
+      "step": 11500
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "grad_norm": 0.41115203499794006,
+      "learning_rate": 1.881666666666667e-05,
+      "loss": 0.0297,
+      "step": 12000
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "eval_accuracy": 0.9876057655512565,
+      "eval_f1": 0.6050313897294611,
+      "eval_loss": 0.03745245933532715,
+      "eval_precision": 0.7389673433362753,
+      "eval_recall": 0.5121969870765466,
+      "eval_runtime": 14.1164,
+      "eval_samples_per_second": 574.507,
+      "eval_steps_per_second": 2.267,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
@@ -321,7 +347,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 248295812264388.0,
+  "total_flos": 271026414634068.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null