Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b93cc327305cb2797063eb09bd10f6c29672eb24765a303f74aab4d3e4f90ad
+oid sha256:1e9b2d6969dd83bc1c43996563873904653a70fa8a0de29bcd1b7f7ddd8775f7
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41b446f984dffebd1b5b2b55823ae399565b61f07ee724284c5c50aa01030a14
+oid sha256:05d78afae041207d004fc4f244d7c3f8f3af6e6fe32125d24890dd0317f62e40
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64b28e054193eaeff0d625fef705a5122942e1a18af84585e7031e05f4d367e
+oid sha256:f8a5b7fde4c37eeccbe4aca8abd49518b2e855ca1720563c5af4866d40338cb0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf1f1d71c2538f4e6c4311b28c8abb9dab5ee4ce70ffee85f9b380b76dcf0420
+oid sha256:c4834ce2586dc426079f90c930b0e0d6ec21ad9d8a256946c64bb3fc73152baa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.05700037255883217,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-3000",
-  "epoch": 1.4792899408284024,
+  "best_metric": 0.049796320497989655,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-4000",
+  "epoch": 1.972386587771203,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,32 @@
       "eval_samples_per_second": 567.375,
       "eval_steps_per_second": 2.239,
       "step": 3000
+    },
+    {
+      "epoch": 1.725838264299803,
+      "grad_norm": 0.3490855395793915,
+      "learning_rate": 1.965483234714004e-05,
+      "loss": 0.056,
+      "step": 3500
+    },
+    {
+      "epoch": 1.972386587771203,
+      "grad_norm": 0.4068734347820282,
+      "learning_rate": 1.9605522682445763e-05,
+      "loss": 0.0542,
+      "step": 4000
+    },
+    {
+      "epoch": 1.972386587771203,
+      "eval_accuracy": 0.9839533993792253,
+      "eval_f1": 0.2863985881759738,
+      "eval_loss": 0.049796320497989655,
+      "eval_precision": 0.8319296960820213,
+      "eval_recall": 0.17297297297297298,
+      "eval_runtime": 14.4691,
+      "eval_samples_per_second": 560.505,
+      "eval_steps_per_second": 2.212,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -113,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 67624319430180.0,
+  "total_flos": 90160058450772.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null