Training in progress, step 19000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25330a42b5c3150f58fd46529cb0e6268cde632c23da0680768e0a745ed4a81f
+oid sha256:ed7c9ee5f82ea171da9c8e025aacdd000fbbdd156711e258c6b8b5a101cb20dc
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ee9909c93f79ad6531d3437f170f468f4fc8bdd7bc22e2eaa681218b152798b
+oid sha256:9b6103c786fbf9c1e64a5888be9eb7bf7fe9f68122cb131b13bc67caf922ca4f
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d726261824dca226482287c3692aca4308c72033a864ea9dd8b4b643276b09
+oid sha256:749f77c3ba8aa807cee2275da408e206106b0440dd6eff1810df2b0ad7678ed8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12bb23042d4407d3a5038be22a7bc334732a1d0432e530de985398332ddb7de5
+oid sha256:754e9f3e7267c3e72aa1c61dcbe591c3b560529510e4f0b395bb9177f346edbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.037242207676172256,
   "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-14000",
-  "epoch": 8.875739644970414,
+  "epoch": 9.368836291913215,
   "eval_steps": 1000,
-  "global_step": 18000,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,6 +475,32 @@
       "eval_samples_per_second": 561.967,
       "eval_steps_per_second": 2.217,
       "step": 18000
+    },
+    {
+      "epoch": 9.122287968441814,
+      "grad_norm": 0.3819935917854309,
+      "learning_rate": 1.8175936883629194e-05,
+      "loss": 0.0194,
+      "step": 18500
+    },
+    {
+      "epoch": 9.368836291913215,
+      "grad_norm": 0.5073143243789673,
+      "learning_rate": 1.8126627218934914e-05,
+      "loss": 0.0177,
+      "step": 19000
+    },
+    {
+      "epoch": 9.368836291913215,
+      "eval_accuracy": 0.9877914310415692,
+      "eval_f1": 0.6353708093464273,
+      "eval_loss": 0.03860396519303322,
+      "eval_precision": 0.7155114882257603,
+      "eval_recall": 0.571374191092501,
+      "eval_runtime": 14.5627,
+      "eval_samples_per_second": 556.901,
+      "eval_steps_per_second": 2.197,
+      "step": 19000
     }
   ],
   "logging_steps": 500,
@@ -498,12 +524,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 407491394665464.0,
+  "total_flos": 430075849523328.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null