Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feafb2107affe6fdf4c45264861a1909ef3735a26a9c5ada27dbc7dc8ba845d9
+oid sha256:7c195ef2273183f4c0ed39b5fe3ef7d5f221d76aafc2495d9e3b855a29db2373
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ccbbfeea057fc532f3d46d99f6f4f20db7279e6a5eb62846aee8e261f1d659b
+oid sha256:b559346292111e1c34646fb6546d2f989954ed4bb53e3cf7c5a61c137d217f6a
 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 sha256:6da7d5a2ae8f209d8c7dd162056a124c933df3dbc8839879a1816c27a0c4446e
+oid sha256:0752b93bbfb66aca0dca5fea88ad54ef891462c5e72f667cfb001794a6c88a96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.037108249962329865,
   "best_model_checkpoint": "doc-topic-model_eval-03_train-04/checkpoint-13000",
-  "epoch": 8.378511582060128,
+  "epoch": 8.871365204534253,
   "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": 551.952,
       "eval_steps_per_second": 2.178,
       "step": 17000
+    },
+    {
+      "epoch": 8.62493839329719,
+      "grad_norm": 0.2823368012905121,
+      "learning_rate": 1.8275308033514047e-05,
+      "loss": 0.0202,
+      "step": 17500
+    },
+    {
+      "epoch": 8.871365204534253,
+      "grad_norm": 0.374859094619751,
+      "learning_rate": 1.8226121241991132e-05,
+      "loss": 0.0204,
+      "step": 18000
+    },
+    {
+      "epoch": 8.871365204534253,
+      "eval_accuracy": 0.9877517468146322,
+      "eval_f1": 0.6369212671204101,
+      "eval_loss": 0.03813798725605011,
+      "eval_precision": 0.7080141976461797,
+      "eval_recall": 0.5788026878436163,
+      "eval_runtime": 14.6486,
+      "eval_samples_per_second": 553.637,
+      "eval_steps_per_second": 2.185,
+      "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": 385542059579694.0,
+  "total_flos": 408291319078542.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null