Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75cff0201fb04f7e432cdd3591c2fd402738370e09f6d8455d837e5c3cba220d
+oid sha256:6f8ab0a83c340e798f7e62c92f5d1e136c3278a268c3fdb62acab74f0d0da40f
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2ba0f1a59da394029688bd7f74cc19e6fd0e3ce1ba6f4ac6132838494c2786
+oid sha256:28a52a2ec9e53a8a587adf9282e7a3c07a6f690e01d2512cf2198c882029e45f
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
+oid sha256:9a445c512a69801b68e319bfb3cb3702cfd8c222330cff7d4d1380aca05cd09b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f575d719835851124a9879abd7b08dea2c333d05d2e7d3bcd4c9a0a05b509d
+oid sha256:7e10a5ec83323055cf4ec6c11bd43e47c2440d47be4e380a83e7905438399849
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03710732236504555,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-04/checkpoint-11000",
-  "epoch": 5.421389847215377,
+  "epoch": 5.914243469689502,
   "eval_steps": 1000,
-  "global_step": 11000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -293,6 +293,32 @@
       "eval_samples_per_second": 566.794,
       "eval_steps_per_second": 2.236,
       "step": 11000
+    },
+    {
+      "epoch": 5.667816658452439,
+      "grad_norm": 0.3089052736759186,
+      "learning_rate": 1.886653523903401e-05,
+      "loss": 0.029,
+      "step": 11500
+    },
+    {
+      "epoch": 5.914243469689502,
+      "grad_norm": 0.3211393356323242,
+      "learning_rate": 1.8817249876786596e-05,
+      "loss": 0.0305,
+      "step": 12000
+    },
+    {
+      "epoch": 5.914243469689502,
+      "eval_accuracy": 0.9874158481794861,
+      "eval_f1": 0.5996302475537719,
+      "eval_loss": 0.03773079067468643,
+      "eval_precision": 0.7306593406593407,
+      "eval_recall": 0.50844995029441,
+      "eval_runtime": 14.1449,
+      "eval_samples_per_second": 573.35,
+      "eval_steps_per_second": 2.262,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
@@ -321,7 +347,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 249475098303882.0,
+  "total_flos": 272144546750178.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null