Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c4e12223c9e02784be077a85f42f0ecd8f82c0bbbf9ab8776fe645a5c48bbc
+oid sha256:6a9defc3154fdea95dcde754dc6074c65a524e5878ecc93500741ff55c699b6b
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a167a4311e62473be9bf6003390ecbbeb0ce22de8644770004b20a474eb4f3a5
+oid sha256:085d4296d6b78dd73ea78b5c376b87f1561a40cba5bb618f2d1119bca45c05aa
 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": 0.03718467801809311,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-13000",
-  "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": 566.983,
       "eval_steps_per_second": 2.237,
       "step": 14000
+    },
+    {
+      "epoch": 7.149901380670611,
+      "grad_norm": 0.20837119221687317,
+      "learning_rate": 1.8570315581854045e-05,
+      "loss": 0.0249,
+      "step": 14500
+    },
+    {
+      "epoch": 7.396449704142012,
+      "grad_norm": 0.23010149598121643,
+      "learning_rate": 1.8521005917159765e-05,
+      "loss": 0.0235,
+      "step": 15000
+    },
+    {
+      "epoch": 7.396449704142012,
+      "eval_accuracy": 0.9878296979746871,
+      "eval_f1": 0.6237897042716319,
+      "eval_loss": 0.03783150017261505,
+      "eval_precision": 0.7303036520311859,
+      "eval_recall": 0.5443909153475568,
+      "eval_runtime": 14.1679,
+      "eval_samples_per_second": 572.422,
+      "eval_steps_per_second": 2.259,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
@@ -399,7 +425,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 316297938560220.0,
+  "total_flos": 338806210140648.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null