Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98617680d962c5113705e2fbad186edd60eeedfd294fa6fa24932d2327dfa47f
+oid sha256:d916f763b88a4c9cc4e48b750eaaa3c02a7aa7f4b905e4929de0173321eefb5a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7bfefb58a92140d2482dbcb2f412ecf1fdbdfec6f5ea8b787a6d35eaec393b7
+oid sha256:196470881ccffda5f09abb08b182fb954fa27df4fdb381f4d8c4c95ee886374a
 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 sha256:33ec0c6c7881febe86af83de0fd1c05de3d6b8cdacbf1d5a88958d9ee8777f33
+oid sha256:8ba7656f2677e9d4a517320301deeaf9502c6f8f9c04d35a107ff5b3063e9135
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.037347666919231415,
   "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-11000",
-  "epoch": 6.903353057199211,
+  "epoch": 7.396449704142012,
   "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": 558.263,
       "eval_steps_per_second": 2.203,
       "step": 14000
+    },
+    {
+      "epoch": 7.149901380670611,
+      "grad_norm": 0.38859695196151733,
+      "learning_rate": 1.8570216962524657e-05,
+      "loss": 0.0239,
+      "step": 14500
+    },
+    {
+      "epoch": 7.396449704142012,
+      "grad_norm": 0.276382178068161,
+      "learning_rate": 1.8520907297830377e-05,
+      "loss": 0.0234,
+      "step": 15000
+    },
+    {
+      "epoch": 7.396449704142012,
+      "eval_accuracy": 0.9875816715563304,
+      "eval_f1": 0.6242710120068611,
+      "eval_loss": 0.037651773542165756,
+      "eval_precision": 0.7146784486990673,
+      "eval_recall": 0.5541682527598021,
+      "eval_runtime": 14.1634,
+      "eval_samples_per_second": 572.603,
+      "eval_steps_per_second": 2.259,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
@@ -399,7 +425,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 315603997005888.0,
+  "total_flos": 338224211361324.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null