Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9defc3154fdea95dcde754dc6074c65a524e5878ecc93500741ff55c699b6b
+oid sha256:fd2f2df71d536915ef60315e21fbe46cdeb18d9b481ead51877daec615f239da
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:085d4296d6b78dd73ea78b5c376b87f1561a40cba5bb618f2d1119bca45c05aa
+oid sha256:74790248a0785731d68493991bf8b373659da4dc8141c0017ec04e4f84a2b3f1
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ade8cbdb5c0dd1f6c03e792fe42b4b1893a6c42ae7b8ee252e85a63008e936
+oid sha256:257882d778b7ee81778c5c372a17241451c183798e27c011c1764580527db4bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3bf1b4a06cfcf7ffbad3f6e707792c1da71ddc3c6fe8d02ca200ee95016b033
+oid sha256:b383cee6a8b310b70be569cfc8af334eaeb0c2fb37d6fe24dbd7ccca37a08dab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03718467801809311,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-13000",
-  "epoch": 7.396449704142012,
+  "epoch": 7.889546351084813,
   "eval_steps": 1000,
-  "global_step": 15000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,32 @@
       "eval_samples_per_second": 572.422,
       "eval_steps_per_second": 2.259,
       "step": 15000
+    },
+    {
+      "epoch": 7.642998027613412,
+      "grad_norm": 0.3158400058746338,
+      "learning_rate": 1.8471696252465485e-05,
+      "loss": 0.0226,
+      "step": 15500
+    },
+    {
+      "epoch": 7.889546351084813,
+      "grad_norm": 0.5647494196891785,
+      "learning_rate": 1.8422386587771205e-05,
+      "loss": 0.0237,
+      "step": 16000
+    },
+    {
+      "epoch": 7.889546351084813,
+      "eval_accuracy": 0.9877843445724733,
+      "eval_f1": 0.6255376460876744,
+      "eval_loss": 0.03789234161376953,
+      "eval_precision": 0.7242454728370221,
+      "eval_recall": 0.5505085264204328,
+      "eval_runtime": 14.1193,
+      "eval_samples_per_second": 574.389,
+      "eval_steps_per_second": 2.266,
+      "step": 16000
     }
   ],
   "logging_steps": 500,
@@ -425,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 338806210140648.0,
+  "total_flos": 361390664998512.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null