Training in progress, step 23000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e1b1b9a71fe12de2625aafe17d204c9050cc3b840be974ca9c154f33792600
+oid sha256:930d03daaada0ff5224634c3dea06f9de32e18a2542da3cc088b00a8e4bd551d
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de8a2a93ff5926b05c525f10bff0e9f5f76a365488c859fb45e61589c17c031
+oid sha256:efea08f3c6c6a9a3a89f4c5e8bbac3cd91ffecea14d84ceb27b8ebcf88f2570f
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0428752c882180c63455dd1c620a454ed081701fa3221b2bfb3bfd35c2f26755
+oid sha256:6967da4512793ef6e21426b52cd19c3eb4b1b256a3d6b476438f0ef1f49d148a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3511d924992961c141b1c147de496d4fa246a86a10dc3bf0866f556b584511e1
+oid sha256:150212d20150d1c5b5ff61b4eed271faa1889b1591145619dfddb6c46eaf02ea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0308150053024292,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-22000",
-  "epoch": 2.7123659228208608,
+  "best_metric": 0.030529338866472244,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-23000",
+  "epoch": 2.8356552829490815,
   "eval_steps": 1000,
-  "global_step": 22000,
+  "global_step": 23000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -579,6 +579,32 @@
       "eval_samples_per_second": 297.38,
       "eval_steps_per_second": 18.589,
       "step": 22000
+    },
+    {
+      "epoch": 2.774010602884971,
+      "grad_norm": 0.4057904779911041,
+      "learning_rate": 1.445197879423006e-05,
+      "loss": 0.0311,
+      "step": 22500
+    },
+    {
+      "epoch": 2.8356552829490815,
+      "grad_norm": 0.42312464118003845,
+      "learning_rate": 1.432868943410184e-05,
+      "loss": 0.03,
+      "step": 23000
+    },
+    {
+      "epoch": 2.8356552829490815,
+      "eval_accuracy": 0.9892851626215002,
+      "eval_f1": 0.6722157194260199,
+      "eval_loss": 0.030529338866472244,
+      "eval_precision": 0.776231477773328,
+      "eval_recall": 0.592782322807554,
+      "eval_runtime": 27.2694,
+      "eval_samples_per_second": 297.439,
+      "eval_steps_per_second": 18.592,
+      "step": 23000
     }
   ],
   "logging_steps": 500,
@@ -586,7 +612,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 497722453857792.0,
+  "total_flos": 520245754792272.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null