Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c3e74ce3a575f8e842cba9328db79344df40398f56b67fa6375fa9ee06c5f88
+oid sha256:1fb49ad2962852fa948fe5f25affadde9bcd99ad695564a6a9463ee265e40db1
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc33b611ff966ffd489c9ac1e705ccaee059884904db6d7422a001612e5e2757
+oid sha256:154a9123225a4c0569c1288cf34bffc4e955e914fe3bd3f59d8e10728d986226
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
+oid sha256:9a445c512a69801b68e319bfb3cb3702cfd8c222330cff7d4d1380aca05cd09b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3c3f1ac50882defeade258e77931f3038c02d6276451a81f8ef210f495feca4
+oid sha256:1600bc22796954bbfe2cfe1a5708dbdc0d32592a1fa22b6a9c5489c11d5fbd8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03807613626122475,
   "best_model_checkpoint": "doc-topic-model_eval-04_train-01/checkpoint-11000",
-  "epoch": 5.424063116370808,
+  "epoch": 5.9171597633136095,
   "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": 563.744,
       "eval_steps_per_second": 2.224,
       "step": 11000
+    },
+    {
+      "epoch": 5.670611439842209,
+      "grad_norm": 0.4880998730659485,
+      "learning_rate": 1.886597633136095e-05,
+      "loss": 0.0321,
+      "step": 11500
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "grad_norm": 0.31077542901039124,
+      "learning_rate": 1.881666666666667e-05,
+      "loss": 0.0305,
+      "step": 12000
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "eval_accuracy": 0.987210819587125,
+      "eval_f1": 0.5974581939799332,
+      "eval_loss": 0.038143206387758255,
+      "eval_precision": 0.7153230112119594,
+      "eval_recall": 0.5129402756508422,
+      "eval_runtime": 14.3895,
+      "eval_samples_per_second": 563.816,
+      "eval_steps_per_second": 2.224,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
@@ -321,7 +347,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 248765350015116.0,
+  "total_flos": 271450346069052.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null