Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f49c46fc02975a8bcfad45e5a8dfb4264dc7f7e5fe1f7927bf0228959114e677
+oid sha256:98617680d962c5113705e2fbad186edd60eeedfd294fa6fa24932d2327dfa47f
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e254ff0234e4863ebedc13e8f132a91ede7f26982d93888d6f3556126a451f62
+oid sha256:f7bfefb58a92140d2482dbcb2f412ecf1fdbdfec6f5ea8b787a6d35eaec393b7
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b5b8eb805933fe8f900e32fd375bcc66cfa8e06b254a11fc2a80b5c9b6018d
+oid sha256:b3067b28aa64de4757065dd8a01a67d3704c9818184e3b87673b274005079225
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac5cca03c5fb2105d752b6c1034ca2d26b6b19fd729ff034cb671359a651884
+oid sha256:33ec0c6c7881febe86af83de0fd1c05de3d6b8cdacbf1d5a88958d9ee8777f33
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0374138318002224,
   "best_model_checkpoint": "doc-topic-model_eval-02_train-03/checkpoint-11000",
-  "epoch": 6.410256410256411,
+  "epoch": 6.903353057199211,
   "eval_steps": 1000,
-  "global_step": 13000,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -345,6 +345,32 @@
       "eval_samples_per_second": 564.544,
       "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": 0.9876737956545771,
+      "eval_f1": 0.6152280670707428,
+      "eval_loss": 0.037624698132276535,
+      "eval_precision": 0.7353781068217874,
+      "eval_recall": 0.5288256769090356,
+      "eval_runtime": 14.2425,
+      "eval_samples_per_second": 569.424,
+      "eval_steps_per_second": 2.247,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
@@ -373,7 +399,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 292968753296400.0,
+  "total_flos": 315603997005888.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null