Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd3ab3eb30a49973be571038e2d20de3fc7ebfd8cb24687706e7abed37b9f34
+oid sha256:29bb3f7942c2eb3b874802b3ea92fe85d018443c8952c3f3662a252d74b77cff
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd74fbfdf70cac8c38a1b40205d826def132941ea475a5e3b519f03cf1502802
+oid sha256:e9ef267bf72eef7066eb6f544c4613a25ba21619a89a12b8ad0beb9b5587024d
 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": 0.03873027116060257,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-9000",
-  "epoch": 4.437869822485207,
+  "best_metric": 0.037975214421749115,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/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": 576.277,
       "eval_steps_per_second": 2.274,
       "step": 9000
+    },
+    {
+      "epoch": 4.684418145956608,
+      "grad_norm": 0.3353199064731598,
+      "learning_rate": 1.906311637080868e-05,
+      "loss": 0.034,
+      "step": 9500
+    },
+    {
+      "epoch": 4.930966469428008,
+      "grad_norm": 0.3929939270019531,
+      "learning_rate": 1.90138067061144e-05,
+      "loss": 0.0333,
+      "step": 10000
+    },
+    {
+      "epoch": 4.930966469428008,
+      "eval_accuracy": 0.9870771149567017,
+      "eval_f1": 0.5952951620062139,
+      "eval_loss": 0.037975214421749115,
+      "eval_precision": 0.7094044218766529,
+      "eval_recall": 0.5128087481838343,
+      "eval_runtime": 14.136,
+      "eval_samples_per_second": 573.711,
+      "eval_steps_per_second": 2.264,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -269,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 202839790060908.0,
+  "total_flos": 225449121090996.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null