Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e579fef1b7fd0038c9762b3c4fbb2d4563a550ba39f4cad986867eee7d3381
+oid sha256:3ef874c4e583779c091a7b359ad98755608a67b4a354ff62aa6f203206efed04
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165717be452493be82c0e50980d64b28838a8e1ad86c8ce5d28ffc1cf050c018
+oid sha256:e7eac815d45bb4fd23791a7a83f0d2a076666ede14350634daa752c963c1e370
 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": 0.04098295420408249,
-  "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-8000",
-  "epoch": 3.9447731755424065,
+  "best_metric": 0.03965826332569122,
+  "best_model_checkpoint": "doc-topic-model_eval-03_train-01/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": 560.87,
       "eval_steps_per_second": 2.213,
       "step": 8000
+    },
+    {
+      "epoch": 4.191321499013807,
+      "grad_norm": 0.41485270857810974,
+      "learning_rate": 1.916173570019724e-05,
+      "loss": 0.0361,
+      "step": 8500
+    },
+    {
+      "epoch": 4.437869822485207,
+      "grad_norm": 0.4282112717628479,
+      "learning_rate": 1.911242603550296e-05,
+      "loss": 0.0349,
+      "step": 9000
+    },
+    {
+      "epoch": 4.437869822485207,
+      "eval_accuracy": 0.9867851524299502,
+      "eval_f1": 0.5692506698697218,
+      "eval_loss": 0.03965826332569122,
+      "eval_precision": 0.7205847953216374,
+      "eval_recall": 0.4704489920586439,
+      "eval_runtime": 14.5109,
+      "eval_samples_per_second": 558.891,
+      "eval_steps_per_second": 2.205,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -243,7 +269,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 181076248886436.0,
+  "total_flos": 203593330777860.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null