Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68cf996cde4bfac6a0041d9f80daa25bf25c11b1cf02f535d0f7e22f95d6e4f6
+oid sha256:49872c67a9db00a8298fe5f875867f243b983d7de0e3dd432f53a8bcc43bcb66
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96c61b6c86a1f66567b309eefb18226e4f2057e63efac97184880812c1601bb
+oid sha256:02e65255ba45e0191b110b66b90ee0361036e1efbe29ebe812981960321384b9
 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": 0.06615250557661057,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-2000",
-  "epoch": 0.9861932938856016,
+  "best_metric": 0.05494347959756851,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/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": 683.543,
       "eval_steps_per_second": 2.697,
       "step": 2000
+    },
+    {
+      "epoch": 1.232741617357002,
+      "grad_norm": 0.4058854281902313,
+      "learning_rate": 1.9753451676528602e-05,
+      "loss": 0.0654,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4792899408284024,
+      "grad_norm": 0.4402715861797333,
+      "learning_rate": 1.9704142011834322e-05,
+      "loss": 0.0596,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4792899408284024,
+      "eval_accuracy": 0.9825927973128109,
+      "eval_f1": 0.1370151770657673,
+      "eval_loss": 0.05494347959756851,
+      "eval_precision": 0.8441558441558441,
+      "eval_recall": 0.07455838495067676,
+      "eval_runtime": 14.1809,
+      "eval_samples_per_second": 571.895,
+      "eval_steps_per_second": 2.257,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -87,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45150252586560.0,
+  "total_flos": 67737816965952.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null