Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890abeeecfac3ee4906db72e869dddfa13a5d1f29a30899ea0f29e9df998867a
+oid sha256:a84312584c3875cbd03f320c933adcf7985f27d690331bb87832f234b7638341
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14aead3b58b5ed7c3680187d775bc8cef17b8a9351b84a4750461996cfb529bf
+oid sha256:0512069259479a917e677af4c5a44ea42f1e12d7f1ac19ccdf4994f36c917bcf
 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:c3c3f1ac50882defeade258e77931f3038c02d6276451a81f8ef210f495feca4
+oid sha256:1600bc22796954bbfe2cfe1a5708dbdc0d32592a1fa22b6a9c5489c11d5fbd8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.038809314370155334,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-00/checkpoint-11000",
-  "epoch": 5.424063116370808,
+  "best_metric": 0.03742339462041855,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-00/checkpoint-12000",
+  "epoch": 5.9171597633136095,
   "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": 566.716,
       "eval_steps_per_second": 2.236,
       "step": 11000
+    },
+    {
+      "epoch": 5.670611439842209,
+      "grad_norm": 0.4685238003730774,
+      "learning_rate": 1.886597633136095e-05,
+      "loss": 0.0297,
+      "step": 11500
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "grad_norm": 0.46912193298339844,
+      "learning_rate": 1.881666666666667e-05,
+      "loss": 0.0299,
+      "step": 12000
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "eval_accuracy": 0.987516476040648,
+      "eval_f1": 0.6071364852809991,
+      "eval_loss": 0.03742339462041855,
+      "eval_precision": 0.7340379637618637,
+      "eval_recall": 0.5176452692424703,
+      "eval_runtime": 14.2866,
+      "eval_samples_per_second": 567.665,
+      "eval_steps_per_second": 2.24,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
@@ -321,7 +347,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 249047798220576.0,
+  "total_flos": 271696516523352.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null