Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bb833041adfed42b6a3ef2a35959c1b1b7ec6fac87c9be3548d8be65091b43
+oid sha256:6de335e9da31c8fe10429221eb63294b11b9cd7809e8cb120d08d2b43989b9ab
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769c965d71315065d6a2bf11b3587d15c515c2ddccef1e3c359b7c3985c89ed3
+oid sha256:35d0a14ecd99356278387b8d9edb962d827a5ff49a2705f070a311a580d4396b
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69797e619b7f76fc3c65d1346887cd92f6a036b8a8ff866da9ca1a335d274133
+oid sha256:e64b28e054193eaeff0d625fef705a5122942e1a18af84585e7031e05f4d367e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de10e3ea9e9f590bd00b7f01055683747e52076430fd0eff98a7f3083d4ae0fc
+oid sha256:bf1f1d71c2538f4e6c4311b28c8abb9dab5ee4ce70ffee85f9b380b76dcf0420
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0703761950135231,
-  "best_model_checkpoint": "doc-topic-model_eval-04_train-00/checkpoint-2000",
-  "epoch": 0.9861932938856016,
+  "best_metric": 0.057249072939157486,
+  "best_model_checkpoint": "doc-topic-model_eval-04_train-00/checkpoint-3000",
+  "epoch": 1.4792899408284024,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,32 @@
       "eval_samples_per_second": 664.948,
       "eval_steps_per_second": 2.623,
       "step": 2000
+    },
+    {
+      "epoch": 1.232741617357002,
+      "grad_norm": 0.31390729546546936,
+      "learning_rate": 1.9753451676528602e-05,
+      "loss": 0.0684,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4792899408284024,
+      "grad_norm": 0.40165144205093384,
+      "learning_rate": 1.9704142011834322e-05,
+      "loss": 0.0622,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4792899408284024,
+      "eval_accuracy": 0.982317296916684,
+      "eval_f1": 0.10215092439392849,
+      "eval_loss": 0.057249072939157486,
+      "eval_precision": 0.8442330558858502,
+      "eval_recall": 0.05436447166921899,
+      "eval_runtime": 14.4254,
+      "eval_samples_per_second": 562.413,
+      "eval_steps_per_second": 2.218,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -87,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45292254069672.0,
+  "total_flos": 67836285147672.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null