Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec655a72dba81932329ab4f3afb82b4e0488e7cb4b4a4dbe5afb4947793e3534
+oid sha256:077445b126c15e88ae1e8de316ff6b3f4e2e2f7214784605950659b45dbfd75d
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9680331d95e21d10dceac05f9cf274119be88d64788f484e683d76f87c471e
+oid sha256:4013ab06115cbb5f13e760d9d438c84425fa73fa2dd6ac8bce7320b64ced7c1c
 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:e3bf1b4a06cfcf7ffbad3f6e707792c1da71ddc3c6fe8d02ca200ee95016b033
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0380592942237854,
   "best_model_checkpoint": "doc-topic-model_eval-02_train-01/checkpoint-14000",
-  "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": 565.751,
       "eval_steps_per_second": 2.232,
       "step": 14000
+    },
+    {
+      "epoch": 7.149901380670611,
+      "grad_norm": 0.42440325021743774,
+      "learning_rate": 1.8570216962524657e-05,
+      "loss": 0.0252,
+      "step": 14500
+    },
+    {
+      "epoch": 7.396449704142012,
+      "grad_norm": 0.5403586626052856,
+      "learning_rate": 1.8521005917159765e-05,
+      "loss": 0.0235,
+      "step": 15000
+    },
+    {
+      "epoch": 7.396449704142012,
+      "eval_accuracy": 0.9874016752412943,
+      "eval_f1": 0.6180880773361976,
+      "eval_loss": 0.038525186479091644,
+      "eval_precision": 0.7102794509726473,
+      "eval_recall": 0.5470794037115911,
+      "eval_runtime": 14.711,
+      "eval_samples_per_second": 551.288,
+      "eval_steps_per_second": 2.175,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
@@ -399,7 +425,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 316659679564644.0,
+  "total_flos": 339302697077952.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null