Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b433288e6f4c8a585318a1780bbd9df8cfd615404e95eb9ca74a6e09187331
+oid sha256:6f4010505f15810acfbd5bf653aa353d6c76f926e157555c8b67b1bc78576bd8
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec91e22b6906152779015a71ae88395cfc9a88318675083944ab160e73b3cbb
+oid sha256:85c6bc2e32807329e95ef065cb1cd4c33cf684cde54566b4e4734bb482e3d4bf
 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": 0.07067307829856873,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-01/checkpoint-2000",
-  "epoch": 0.9861932938856016,
+  "best_metric": 0.057456616312265396,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-01/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": 661.789,
       "eval_steps_per_second": 2.611,
       "step": 2000
+    },
+    {
+      "epoch": 1.232741617357002,
+      "grad_norm": 0.43946701288223267,
+      "learning_rate": 1.9753451676528602e-05,
+      "loss": 0.0696,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4792899408284024,
+      "grad_norm": 0.4252438545227051,
+      "learning_rate": 1.9704142011834322e-05,
+      "loss": 0.0628,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4792899408284024,
+      "eval_accuracy": 0.9822313873889196,
+      "eval_f1": 0.1224889759921607,
+      "eval_loss": 0.057456616312265396,
+      "eval_precision": 0.7682177348551361,
+      "eval_recall": 0.066550045634317,
+      "eval_runtime": 14.2849,
+      "eval_samples_per_second": 567.732,
+      "eval_steps_per_second": 2.24,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -87,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45294327084024.0,
+  "total_flos": 67986578688192.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null