Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2165f31cfba6ec3e5328cc67a69cb5b39097ec028f45e2fedfd101fc6375156
+oid sha256:d1c5d02bf9b01e0c5f1540f954297d63621fbdac6f6c570ec5765a1db7c15b64
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abc9afe5496661e2399ad8d95d2e9cb5302226edecf61697dca47f92ff3021c
+oid sha256:48f3019f5bcc0d2eea7266f4548fb320a29faca7083d50ded305c123dd9b8a16
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b369a0932ccec8237a09ebf2a67d8d79f22ce21beabdc5233be8049c948d47de
+oid sha256:008375a0cc671d0e1c0f8976d480a3388a0d027af1650425d6c4d02940510b98
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f70577d3332038132a45fcd390ed0a612b35b6e960c6709d30d8c9e388d7322
+oid sha256:82024a11f598f8b76f243f46b3e14fa06e234755e8f77084e55d553c6e34a0d3
 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": 86.61417322834646,
+  "epoch": 94.48818897637796,
   "eval_steps": 1000,
-  "global_step": 11000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -293,6 +293,32 @@
       "eval_samples_per_second": 572.761,
       "eval_steps_per_second": 2.26,
       "step": 11000
+    },
+    {
+      "epoch": 90.55118110236221,
+      "grad_norm": 0.1424516886472702,
+      "learning_rate": 2.1702755905511812e-06,
+      "loss": 0.0241,
+      "step": 11500
+    },
+    {
+      "epoch": 94.48818897637796,
+      "grad_norm": 0.16246256232261658,
+      "learning_rate": 2.0472440944881893e-06,
+      "loss": 0.0234,
+      "step": 12000
+    },
+    {
+      "epoch": 94.48818897637796,
+      "eval_accuracy": 0.9874186827671244,
+      "eval_f1": 0.6064985150050978,
+      "eval_loss": 0.038960497826337814,
+      "eval_precision": 0.7259125636672326,
+      "eval_recall": 0.5208222306813856,
+      "eval_runtime": 14.1182,
+      "eval_samples_per_second": 574.434,
+      "eval_steps_per_second": 2.267,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
@@ -312,7 +338,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4943000108133576.0,
+  "total_flos": 5391592640102556.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null