Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe68f4577286b85cbc5c6a48af902103215e6d0a6d1406ab180a643234b19700
+oid sha256:09d80a34fbc5d58d42acd0f85e14ad64d5e80ea79e6b3a99baa77dc28096cd49
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0177ee53022f715e3a3e89ac556dbf20c1d9fd7f663800df2375e52c0556c37
+oid sha256:10a29f71ece496f257a80282c8394a5ff491fb8ba779017209326db655fe39da
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40c0d9a49a814dc52082f9054fc2ffb694380fb521f25163384314e1e0b22ae
+oid sha256:1128d67de3d4d8e3dd8bc8b4bca4f59bef7d1d2c35b978700b48aaaa3a3cb733
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173f4a2433232f77939b4d77264600e6f898939c018c908fe5f061eb1c76ed9b
+oid sha256:f1d4e0d33a262ad4f64c2ce77b757798ccbd7d82035d16a8a99e7def08d07a9c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.040071167051792145,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-8000",
-  "epoch": 3.9447731755424065,
+  "best_metric": 0.03921710327267647,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-9000",
+  "epoch": 4.437869822485207,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -215,6 +215,32 @@
       "eval_samples_per_second": 565.521,
       "eval_steps_per_second": 2.231,
       "step": 8000
+    },
+    {
+      "epoch": 4.191321499013807,
+      "grad_norm": 0.39796024560928345,
+      "learning_rate": 1.916173570019724e-05,
+      "loss": 0.0348,
+      "step": 8500
+    },
+    {
+      "epoch": 4.437869822485207,
+      "grad_norm": 0.3643665313720703,
+      "learning_rate": 1.911242603550296e-05,
+      "loss": 0.0343,
+      "step": 9000
+    },
+    {
+      "epoch": 4.437869822485207,
+      "eval_accuracy": 0.9868985359354848,
+      "eval_f1": 0.5774364600475407,
+      "eval_loss": 0.03921710327267647,
+      "eval_precision": 0.7225717881249285,
+      "eval_recall": 0.48085268366958506,
+      "eval_runtime": 14.341,
+      "eval_samples_per_second": 565.513,
+      "eval_steps_per_second": 2.231,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -243,7 +269,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 180338255777124.0,
+  "total_flos": 202839790060908.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null