Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b5e3d074c6d233b824116477cd45caa5f2af53ea01b79852be89a501cbc11a6
+oid sha256:b2165f31cfba6ec3e5328cc67a69cb5b39097ec028f45e2fedfd101fc6375156
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ee9cc242df46373729458c2a333a599ef680eeded9e36d27a47f326299a9bf
+oid sha256:4abc9afe5496661e2399ad8d95d2e9cb5302226edecf61697dca47f92ff3021c
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b03b85e31744d00cc2d94c7c6e3fa2c80dfeeb8c31f749966344ce5e50d86f7c
+oid sha256:b369a0932ccec8237a09ebf2a67d8d79f22ce21beabdc5233be8049c948d47de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552768df724b19ebb0b14b82f95a15767c10a28d5a12e1405c76a16dc8363389
+oid sha256:5f70577d3332038132a45fcd390ed0a612b35b6e960c6709d30d8c9e388d7322
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03880663216114044,
   "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-10000",
-  "epoch": 78.74015748031496,
+  "epoch": 86.61417322834646,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,32 @@
       "eval_samples_per_second": 571.941,
       "eval_steps_per_second": 2.257,
       "step": 10000
+    },
+    {
+      "epoch": 82.67716535433071,
+      "grad_norm": 0.1377759575843811,
+      "learning_rate": 2.4163385826771656e-06,
+      "loss": 0.0258,
+      "step": 10500
+    },
+    {
+      "epoch": 86.61417322834646,
+      "grad_norm": 0.1264483779668808,
+      "learning_rate": 2.2933070866141736e-06,
+      "loss": 0.0249,
+      "step": 11000
+    },
+    {
+      "epoch": 86.61417322834646,
+      "eval_accuracy": 0.9874484459373273,
+      "eval_f1": 0.6034745231485628,
+      "eval_loss": 0.0388496108353138,
+      "eval_precision": 0.7325796282204587,
+      "eval_recall": 0.5130567186905215,
+      "eval_runtime": 14.1595,
+      "eval_samples_per_second": 572.761,
+      "eval_steps_per_second": 2.26,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -286,7 +312,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4494270757217364.0,
+  "total_flos": 4943000108133576.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null