Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:791af0f71e3a9b8e8ae2ddc2902b7686c5f69824bf9684c694143cc9c7a516b2
+oid sha256:f49c46fc02975a8bcfad45e5a8dfb4264dc7f7e5fe1f7927bf0228959114e677
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb49ff40fbf04fc597f1b5630850feb0b992849099b487836eadc12854f7d18d
+oid sha256:e254ff0234e4863ebedc13e8f132a91ede7f26982d93888d6f3556126a451f62
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a445c512a69801b68e319bfb3cb3702cfd8c222330cff7d4d1380aca05cd09b
+oid sha256:a9b5b8eb805933fe8f900e32fd375bcc66cfa8e06b254a11fc2a80b5c9b6018d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1600bc22796954bbfe2cfe1a5708dbdc0d32592a1fa22b6a9c5489c11d5fbd8c
+oid sha256:5ac5cca03c5fb2105d752b6c1034ca2d26b6b19fd729ff034cb671359a651884
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03706079348921776,
   "best_model_checkpoint": "doc-topic-model_eval-04_train-03/checkpoint-11000",
-  "epoch": 5.9171597633136095,
+  "epoch": 6.410256410256411,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -319,6 +319,32 @@
       "eval_samples_per_second": 564.195,
       "eval_steps_per_second": 2.225,
       "step": 12000
+    },
+    {
+      "epoch": 6.16370808678501,
+      "grad_norm": 0.5974611043930054,
+      "learning_rate": 1.876735700197239e-05,
+      "loss": 0.0271,
+      "step": 12500
+    },
+    {
+      "epoch": 6.410256410256411,
+      "grad_norm": 0.42065271735191345,
+      "learning_rate": 1.8718145956607497e-05,
+      "loss": 0.0271,
+      "step": 13000
+    },
+    {
+      "epoch": 6.410256410256411,
+      "eval_accuracy": 0.9878228641133643,
+      "eval_f1": 0.6095843742902567,
+      "eval_loss": 0.03712933510541916,
+      "eval_precision": 0.7493020658849805,
+      "eval_recall": 0.5137825421133231,
+      "eval_runtime": 14.6077,
+      "eval_samples_per_second": 555.394,
+      "eval_steps_per_second": 2.191,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
@@ -347,7 +373,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 270583826069916.0,
+  "total_flos": 292968753296400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null