Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d091ae8d05dd0ffb4e38968e5fb78261e43049094a134911a5cbaea2b6bf7a5a
+oid sha256:c41265f9920783a5a84cfe44c3bb367dfa635ab8d97bfec55cc560632190e590
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c2c8bb4d51d0d5fbfe02927395f3fda7e44ecd66645795ccc8eaa8a13807c2
+oid sha256:73e0267258c5346e8d50445e28f13662c5f37ac7095267ab854ceb9a7395e834
 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:d1898603f15858e1d30e0a114324bbe68b42a24ba79cd3917f2f7dd67be95b4c
+oid sha256:046f36a4f886839ef562bc29cbdb24226b9e49f224c3433541f83d2a6ddde8eb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.07024028897285461,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-2000",
-  "epoch": 0.9857072449482503,
+  "best_metric": 0.05670051649212837,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-3000",
+  "epoch": 1.4785608674223756,
   "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": 667.356,
       "eval_steps_per_second": 2.633,
       "step": 2000
+    },
+    {
+      "epoch": 1.232134056185313,
+      "grad_norm": 0.36931222677230835,
+      "learning_rate": 1.975357318876294e-05,
+      "loss": 0.0682,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4785608674223756,
+      "grad_norm": 0.3769352436065674,
+      "learning_rate": 1.9704287826515527e-05,
+      "loss": 0.0618,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4785608674223756,
+      "eval_accuracy": 0.9827912184474964,
+      "eval_f1": 0.1751358695652174,
+      "eval_loss": 0.05670051649212837,
+      "eval_precision": 0.8199745547073791,
+      "eval_recall": 0.09803772436872528,
+      "eval_runtime": 14.2669,
+      "eval_samples_per_second": 568.448,
+      "eval_steps_per_second": 2.243,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -87,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45379320672456.0,
+  "total_flos": 68043845709666.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null