Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a14ba6d631b491aedf133a76099b0070972351da82405b18ac3450de34336449
+oid sha256:d916f763b88a4c9cc4e48b750eaaa3c02a7aa7f4b905e4929de0173321eefb5a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ea4bb0360117a07d4f6423fa49546e2503080cd4f5396d578fe653c6c03609
+oid sha256:196470881ccffda5f09abb08b182fb954fa27df4fdb381f4d8c4c95ee886374a
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
+oid sha256:c2ade8cbdb5c0dd1f6c03e792fe42b4b1893a6c42ae7b8ee252e85a63008e936
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3c3f1ac50882defeade258e77931f3038c02d6276451a81f8ef210f495feca4
+oid sha256:8ba7656f2677e9d4a517320301deeaf9502c6f8f9c04d35a107ff5b3063e9135
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03748522698879242,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-11000",
-  "epoch": 5.424063116370808,
+  "epoch": 7.396449704142012,
   "eval_steps": 1000,
-  "global_step": 11000,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -293,6 +293,110 @@
       "eval_samples_per_second": 562.38,
       "eval_steps_per_second": 2.219,
       "step": 11000
+    },
+    {
+      "epoch": 5.670611439842209,
+      "grad_norm": 0.42573484778404236,
+      "learning_rate": 1.886597633136095e-05,
+      "loss": 0.0299,
+      "step": 11500
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "grad_norm": 0.4632101058959961,
+      "learning_rate": 1.881666666666667e-05,
+      "loss": 0.0295,
+      "step": 12000
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "eval_accuracy": 0.98739175418456,
+      "eval_f1": 0.6050084361957198,
+      "eval_loss": 0.03783571720123291,
+      "eval_precision": 0.7213340391741663,
+      "eval_recall": 0.5209910529938059,
+      "eval_runtime": 14.4511,
+      "eval_samples_per_second": 561.202,
+      "eval_steps_per_second": 2.214,
+      "step": 12000
+    },
+    {
+      "epoch": 6.16370808678501,
+      "grad_norm": 0.5974611043930054,
+      "learning_rate": 1.876735700197239e-05,
+      "loss": 0.0271,
+      "step": 12500
+    },
+    {
+      "epoch": 6.410256410256411,
+      "grad_norm": 0.42065271735191345,
+      "learning_rate": 1.8718145956607497e-05,
+      "loss": 0.0271,
+      "step": 13000
+    },
+    {
+      "epoch": 6.410256410256411,
+      "eval_accuracy": 0.9876794648298539,
+      "eval_f1": 0.6048097467836523,
+      "eval_loss": 0.037606410682201385,
+      "eval_precision": 0.7457399103139013,
+      "eval_recall": 0.5086793607096429,
+      "eval_runtime": 14.3596,
+      "eval_samples_per_second": 564.778,
+      "eval_steps_per_second": 2.228,
+      "step": 13000
+    },
+    {
+      "epoch": 6.65680473372781,
+      "grad_norm": 0.7562135457992554,
+      "learning_rate": 1.8668836291913217e-05,
+      "loss": 0.0265,
+      "step": 13500
+    },
+    {
+      "epoch": 6.903353057199211,
+      "grad_norm": 0.5237112641334534,
+      "learning_rate": 1.8619526627218937e-05,
+      "loss": 0.0257,
+      "step": 14000
+    },
+    {
+      "epoch": 6.903353057199211,
+      "eval_accuracy": 0.9874909647519027,
+      "eval_f1": 0.6067896284415931,
+      "eval_loss": 0.0378677099943161,
+      "eval_precision": 0.7268651937239834,
+      "eval_recall": 0.520761642578573,
+      "eval_runtime": 14.2708,
+      "eval_samples_per_second": 568.292,
+      "eval_steps_per_second": 2.242,
+      "step": 14000
+    },
+    {
+      "epoch": 7.149901380670611,
+      "grad_norm": 0.38859695196151733,
+      "learning_rate": 1.8570216962524657e-05,
+      "loss": 0.0239,
+      "step": 14500
+    },
+    {
+      "epoch": 7.396449704142012,
+      "grad_norm": 0.276382178068161,
+      "learning_rate": 1.8520907297830377e-05,
+      "loss": 0.0234,
+      "step": 15000
+    },
+    {
+      "epoch": 7.396449704142012,
+      "eval_accuracy": 0.9875901753192454,
+      "eval_f1": 0.6246248821058047,
+      "eval_loss": 0.037667978554964066,
+      "eval_precision": 0.7108010537613426,
+      "eval_recall": 0.5570849583237746,
+      "eval_runtime": 14.3321,
+      "eval_samples_per_second": 565.864,
+      "eval_steps_per_second": 2.233,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
@@ -321,7 +425,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 248019064848396.0,
+  "total_flos": 338224211361324.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null