Training in progress, step 19000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78fc7c94ee3d7573ef34c05daa58a7e35af838f0c0129c1bdcc157185ed3c16f
+oid sha256:e29a49901521a90229a6d6bd1f78357ef074d640e55e549b59758c52f941978a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2101628d7dd606a727df930fd67a955492ade1cd3cadca8a3cd18e86721b873f
+oid sha256:10d73d12e9b5758fa83605c54e63cc7843dfb4d124a6ee579b82b9c67b08dc40
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d726261824dca226482287c3692aca4308c72033a864ea9dd8b4b643276b09
+oid sha256:749f77c3ba8aa807cee2275da408e206106b0440dd6eff1810df2b0ad7678ed8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12bb23042d4407d3a5038be22a7bc334732a1d0432e530de985398332ddb7de5
+oid sha256:89bf2412fc138a51f4062ab775917d39e54f436132316dc7fbb3694aabb37048
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.037335559725761414,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-01/checkpoint-15000",
-  "epoch": 8.875739644970414,
+  "epoch": 9.368836291913215,
   "eval_steps": 1000,
-  "global_step": 18000,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,6 +475,32 @@
       "eval_samples_per_second": 574.709,
       "eval_steps_per_second": 2.268,
       "step": 18000
+    },
+    {
+      "epoch": 9.122287968441814,
+      "grad_norm": 0.6406568288803101,
+      "learning_rate": 1.8175936883629194e-05,
+      "loss": 0.0198,
+      "step": 18500
+    },
+    {
+      "epoch": 9.368836291913215,
+      "grad_norm": 0.6294471621513367,
+      "learning_rate": 1.8126725838264302e-05,
+      "loss": 0.0183,
+      "step": 19000
+    },
+    {
+      "epoch": 9.368836291913215,
+      "eval_accuracy": 0.9877602505775472,
+      "eval_f1": 0.6299597223412461,
+      "eval_loss": 0.0388527438044548,
+      "eval_precision": 0.71640191014521,
+      "eval_recall": 0.5621319874588973,
+      "eval_runtime": 14.3395,
+      "eval_samples_per_second": 565.571,
+      "eval_steps_per_second": 2.232,
+      "step": 19000
     }
   ],
   "logging_steps": 500,
@@ -503,7 +529,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 407138463972036.0,
+  "total_flos": 429748313255712.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null