Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587606c149b035129feeb08516742eaa4dd15a83c452d067f67f0e2371926c91
+oid sha256:121b800df78bbd1f97b4e692be6b02e6c48919239400a28b59daec6f0765c4e6
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1d5c74203ad116a506045f4e86499f6fd913f0334a4eac1a1c3e7d9f90383d
+oid sha256:7ab58a9acbbbd7e1de089885beae7a60e291c50156230d4bbd032612aaf7433a
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d909219cbdd70599a7be8a42aba4df5d7065f7b997b0075bce4834affe89f840
+oid sha256:74d726261824dca226482287c3692aca4308c72033a864ea9dd8b4b643276b09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd937dc5ca4c62f5f5a023ee1555a7a5e140540c1dc517f73c54011163ae049e
+oid sha256:12bb23042d4407d3a5038be22a7bc334732a1d0432e530de985398332ddb7de5
 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": 8.382642998027613,
+  "epoch": 8.875739644970414,
   "eval_steps": 1000,
-  "global_step": 17000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -449,6 +449,32 @@
       "eval_samples_per_second": 572.267,
       "eval_steps_per_second": 2.258,
       "step": 17000
+    },
+    {
+      "epoch": 8.629191321499015,
+      "grad_norm": 0.44110924005508423,
+      "learning_rate": 1.8274556213017754e-05,
+      "loss": 0.0209,
+      "step": 17500
+    },
+    {
+      "epoch": 8.875739644970414,
+      "grad_norm": 0.5276309847831726,
+      "learning_rate": 1.822524654832347e-05,
+      "loss": 0.0208,
+      "step": 18000
+    },
+    {
+      "epoch": 8.875739644970414,
+      "eval_accuracy": 0.9874413594682313,
+      "eval_f1": 0.631083725384071,
+      "eval_loss": 0.03931192308664322,
+      "eval_precision": 0.6926521659660025,
+      "eval_recall": 0.579567179016594,
+      "eval_runtime": 14.1285,
+      "eval_samples_per_second": 574.016,
+      "eval_steps_per_second": 2.265,
+      "step": 18000
     }
   ],
   "logging_steps": 500,
@@ -472,12 +498,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 383935214330100.0,
+  "total_flos": 406579786604172.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null