Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84312584c3875cbd03f320c933adcf7985f27d690331bb87832f234b7638341
+oid sha256:8735d2e1c53fa856dfc9969a49ba3f211797bc86a889b9c72bf12ef517cd8500
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0512069259479a917e677af4c5a44ea42f1e12d7f1ac19ccdf4994f36c917bcf
+oid sha256:01127c9de53af7661c659a9b05e5fe0b35aa187ea4a4a78f5aee56c8629a2308
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a445c512a69801b68e319bfb3cb3702cfd8c222330cff7d4d1380aca05cd09b
+oid sha256:a9b5b8eb805933fe8f900e32fd375bcc66cfa8e06b254a11fc2a80b5c9b6018d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1600bc22796954bbfe2cfe1a5708dbdc0d32592a1fa22b6a9c5489c11d5fbd8c
+oid sha256:5ac5cca03c5fb2105d752b6c1034ca2d26b6b19fd729ff034cb671359a651884
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03742339462041855,
   "best_model_checkpoint": "doc-topic-model_eval-02_train-00/checkpoint-12000",
-  "epoch": 5.9171597633136095,
+  "epoch": 6.410256410256411,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -319,6 +319,32 @@
       "eval_samples_per_second": 567.665,
       "eval_steps_per_second": 2.24,
       "step": 12000
+    },
+    {
+      "epoch": 6.16370808678501,
+      "grad_norm": 0.3353117108345032,
+      "learning_rate": 1.876735700197239e-05,
+      "loss": 0.0276,
+      "step": 12500
+    },
+    {
+      "epoch": 6.410256410256411,
+      "grad_norm": 0.2552751898765564,
+      "learning_rate": 1.8718145956607497e-05,
+      "loss": 0.0265,
+      "step": 13000
+    },
+    {
+      "epoch": 6.410256410256411,
+      "eval_accuracy": 0.9874682880507958,
+      "eval_f1": 0.6134813778632628,
+      "eval_loss": 0.03768361359834671,
+      "eval_precision": 0.7213199013157895,
+      "eval_recall": 0.533693337389717,
+      "eval_runtime": 14.3396,
+      "eval_samples_per_second": 565.567,
+      "eval_steps_per_second": 2.232,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
@@ -347,7 +373,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 271696516523352.0,
+  "total_flos": 294355599897888.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null