Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615812c6039edc87981879f12b45c8ed7ba24244372a4eecfcdd795e5b7dd397
+oid sha256:66df5699efd6611e5991327fc49c95ca3324792f988e6c99913e34ed42ae7d77
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43084f1d31da6494bf35a40084f36d88a2ba83e069a262707dbf4ce6692c1144
+oid sha256:bd5ca36f7a09a88370d0e25f90316e2a25f5919de60e518bfe596c07e0124ed5
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3067b28aa64de4757065dd8a01a67d3704c9818184e3b87673b274005079225
+oid sha256:c2ade8cbdb5c0dd1f6c03e792fe42b4b1893a6c42ae7b8ee252e85a63008e936
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7770ab36fc118683d75ac831239ef224ccbc0c55abe600db074c2f5741fab05a
+oid sha256:ae7f535c7132d6f008b1726ba6d9ba2b6baa6c4e0ff67703b0f9cebcaada727c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03750571236014366,
   "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-13000",
-  "epoch": 6.899950714637752,
+  "epoch": 7.392804337111878,
   "eval_steps": 1000,
-  "global_step": 14000,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -371,6 +371,32 @@
       "eval_samples_per_second": 573.531,
       "eval_steps_per_second": 2.263,
       "step": 14000
+    },
+    {
+      "epoch": 7.146377525874815,
+      "grad_norm": 0.36695852875709534,
+      "learning_rate": 1.857092163627403e-05,
+      "loss": 0.0234,
+      "step": 14500
+    },
+    {
+      "epoch": 7.392804337111878,
+      "grad_norm": 0.36567145586013794,
+      "learning_rate": 1.852173484475111e-05,
+      "loss": 0.0228,
+      "step": 15000
+    },
+    {
+      "epoch": 7.392804337111878,
+      "eval_accuracy": 0.9877120625876951,
+      "eval_f1": 0.6165074309978769,
+      "eval_loss": 0.03786341845989227,
+      "eval_precision": 0.7366807610993658,
+      "eval_recall": 0.530042592029206,
+      "eval_runtime": 14.1212,
+      "eval_samples_per_second": 574.314,
+      "eval_steps_per_second": 2.266,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
@@ -399,7 +425,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 317495104348500.0,
+  "total_flos": 340203940067484.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null