Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40e2abc797e770c0783bb4f4e58709545091c5c4243e7b0f1cc8900c4c179a7f
+oid sha256:49908c6b3a97869b28d3107cd8ede521c11f0540d75bf57e64890e1b42a681d8
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abee8f95f340dfe01d344aaff64323a816c943331f6304c89b5c4f77e0a2c8fe
+oid sha256:f37bfd767a7944f522f8b0967bd0b7c7dfe12f1a9adfde5992bc86f6d2dfc4fe
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c451f916508297d3207f2dab1c39b19208c892726d699392b564615e2b984b
+oid sha256:c677e9a5a7f527c7d59e3734e6ea532e988e424c79842c29a15f61acb3d85678
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee802392f623a24841bae03e3b1a90568251d05c67f2dfba666ec36a6359794
+oid sha256:bc53ec4ee360520441164c72c89b9d8c72fa6dd1be6626eb79abc2dc4e85148b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.21147018671035767,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-1000",
-  "epoch": 7.874015748031496,
+  "best_metric": 0.10989262908697128,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-2000",
+  "epoch": 15.748031496062993,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -33,6 +33,32 @@
       "eval_samples_per_second": 684.36,
       "eval_steps_per_second": 2.7,
       "step": 1000
+    },
+    {
+      "epoch": 11.811023622047244,
+      "grad_norm": 0.3979816138744354,
+      "learning_rate": 1.157726377952756e-06,
+      "loss": 0.1864,
+      "step": 1500
+    },
+    {
+      "epoch": 15.748031496062993,
+      "grad_norm": 0.2547377347946167,
+      "learning_rate": 1.126968503937008e-06,
+      "loss": 0.1321,
+      "step": 2000
+    },
+    {
+      "epoch": 15.748031496062993,
+      "eval_accuracy": 0.981383845685049,
+      "eval_f1": 0.0,
+      "eval_loss": 0.10989262908697128,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 11.8538,
+      "eval_samples_per_second": 684.169,
+      "eval_steps_per_second": 2.7,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -52,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 449829603283536.0,
+  "total_flos": 898582275611208.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null