Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6157b83d3ad04fbacce2164dc09995d5b7ec64a269194f09f28ec4576456b04a
+oid sha256:a29bdd6dd99b89c77d6304028688587d1b8726526a52d214cd23379fdecaebbe
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779e39f46a015cc88c42b8580783cf0c7efbd1969b44e5eebd7272323cd66825
+oid sha256:1f09c406b05c324524d6a329f73f7a6945c206dde699341114fe910ad244dee5
 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:c1c594171daced1aeade37a70493521e5eab91ea5bc7c6a38065d07e548360fc
+oid sha256:8d33ebaa07fbbf9d04ea7e6a7b80d3a50929ab3c541f194d4f807567dfec05d5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.038919780403375626,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-9000",
-  "epoch": 4.435682602267127,
+  "best_metric": 0.038509998470544815,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-10000",
+  "epoch": 4.928536224741252,
   "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": 568.258,
       "eval_steps_per_second": 2.242,
       "step": 9000
+    },
+    {
+      "epoch": 4.68210941350419,
+      "grad_norm": 0.31547975540161133,
+      "learning_rate": 1.9063578117299164e-05,
+      "loss": 0.0328,
+      "step": 9500
+    },
+    {
+      "epoch": 4.928536224741252,
+      "grad_norm": 0.307452529668808,
+      "learning_rate": 1.9014292755051752e-05,
+      "loss": 0.0337,
+      "step": 10000
+    },
+    {
+      "epoch": 4.928536224741252,
+      "eval_accuracy": 0.9873194721997818,
+      "eval_f1": 0.581505215398288,
+      "eval_loss": 0.038509998470544815,
+      "eval_precision": 0.7551937796136557,
+      "eval_recall": 0.472771524186188,
+      "eval_runtime": 14.3086,
+      "eval_samples_per_second": 566.79,
+      "eval_steps_per_second": 2.236,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -269,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 204191913672000.0,
+  "total_flos": 226752528864816.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null