Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef874c4e583779c091a7b359ad98755608a67b4a354ff62aa6f203206efed04
+oid sha256:548e69bc4348cced48a9ab52acfcf35504755cce6b8ed4acc3297d9b42a4766b
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7eac815d45bb4fd23791a7a83f0d2a076666ede14350634daa752c963c1e370
+oid sha256:dbb4668008b0c2d1bcf93d76f40d3cc759bac20c1dc7adb009f521aed880442d
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1128d67de3d4d8e3dd8bc8b4bca4f59bef7d1d2c35b978700b48aaaa3a3cb733
+oid sha256:6b7e320b5a2475507aebb5f1ef7a9c98d12600ef0165cc1de949f181761d986b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d4e0d33a262ad4f64c2ce77b757798ccbd7d82035d16a8a99e7def08d07a9c
+oid sha256:28e35c5a0c1eb4f922a2e3785d5afca45020e4d0fc6713cc20aea6ed31f143e1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03965826332569122,
-  "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-9000",
-  "epoch": 4.437869822485207,
+  "best_metric": 0.03886643052101135,
+  "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-10000",
+  "epoch": 4.930966469428008,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,32 @@
       "eval_samples_per_second": 558.891,
       "eval_steps_per_second": 2.205,
       "step": 9000
+    },
+    {
+      "epoch": 4.684418145956608,
+      "grad_norm": 0.5737874507904053,
+      "learning_rate": 1.906311637080868e-05,
+      "loss": 0.0358,
+      "step": 9500
+    },
+    {
+      "epoch": 4.930966469428008,
+      "grad_norm": 0.42196542024612427,
+      "learning_rate": 1.90138067061144e-05,
+      "loss": 0.0344,
+      "step": 10000
+    },
+    {
+      "epoch": 4.930966469428008,
+      "eval_accuracy": 0.9869849908584548,
+      "eval_f1": 0.5743684820393975,
+      "eval_loss": 0.03886643052101135,
+      "eval_precision": 0.730746550300743,
+      "eval_recall": 0.4731215638362859,
+      "eval_runtime": 14.4599,
+      "eval_samples_per_second": 560.863,
+      "eval_steps_per_second": 2.213,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -269,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 203593330777860.0,
+  "total_flos": 226198515779244.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null