Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1cbb26c77bdd11b36482bc270b8c0a4e7a62a2232b00bd25d82d2b56ce9d8c
+oid sha256:6b93cc327305cb2797063eb09bd10f6c29672eb24765a303f74aab4d3e4f90ad
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33082566925f313648e53bff28b4b27c2bf5a0db666be841cf6868e256abdce0
+oid sha256:41b446f984dffebd1b5b2b55823ae399565b61f07ee724284c5c50aa01030a14
 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": 0.07000521570444107,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-2000",
-  "epoch": 0.9861932938856016,
+  "best_metric": 0.05673361197113991,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/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": 671.442,
       "eval_steps_per_second": 2.649,
       "step": 2000
+    },
+    {
+      "epoch": 1.232741617357002,
+      "grad_norm": 0.3765203356742859,
+      "learning_rate": 1.9753451676528602e-05,
+      "loss": 0.068,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4792899408284024,
+      "grad_norm": 0.3380969762802124,
+      "learning_rate": 1.9704142011834322e-05,
+      "loss": 0.0621,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4792899408284024,
+      "eval_accuracy": 0.982086823419363,
+      "eval_f1": 0.07304730473047305,
+      "eval_loss": 0.05673361197113991,
+      "eval_precision": 0.8924731182795699,
+      "eval_recall": 0.03808212892865336,
+      "eval_runtime": 14.4231,
+      "eval_samples_per_second": 562.293,
+      "eval_steps_per_second": 2.219,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -87,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45024835218264.0,
+  "total_flos": 67624319430180.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null