Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29bdd6dd99b89c77d6304028688587d1b8726526a52d214cd23379fdecaebbe
+oid sha256:75cff0201fb04f7e432cdd3591c2fd402738370e09f6d8455d837e5c3cba220d
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f09c406b05c324524d6a329f73f7a6945c206dde699341114fe910ad244dee5
+oid sha256:ca2ba0f1a59da394029688bd7f74cc19e6fd0e3ce1ba6f4ac6132838494c2786
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b7e320b5a2475507aebb5f1ef7a9c98d12600ef0165cc1de949f181761d986b
+oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d33ebaa07fbbf9d04ea7e6a7b80d3a50929ab3c541f194d4f807567dfec05d5
+oid sha256:d2f575d719835851124a9879abd7b08dea2c333d05d2e7d3bcd4c9a0a05b509d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.038497649133205414,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-04/checkpoint-10000",
-  "epoch": 4.928536224741252,
+  "best_metric": 0.037736039608716965,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-04/checkpoint-11000",
+  "epoch": 5.421389847215377,
   "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": 564.067,
       "eval_steps_per_second": 2.226,
       "step": 10000
+    },
+    {
+      "epoch": 5.1749630359783145,
+      "grad_norm": 0.3740977942943573,
+      "learning_rate": 1.8965007392804338e-05,
+      "loss": 0.0303,
+      "step": 10500
+    },
+    {
+      "epoch": 5.421389847215377,
+      "grad_norm": 0.37522149085998535,
+      "learning_rate": 1.891582060128142e-05,
+      "loss": 0.0295,
+      "step": 11000
+    },
+    {
+      "epoch": 5.421389847215377,
+      "eval_accuracy": 0.9871380585909265,
+      "eval_f1": 0.6012916831422169,
+      "eval_loss": 0.037736039608716965,
+      "eval_precision": 0.7108871805526699,
+      "eval_recall": 0.520974495622383,
+      "eval_runtime": 14.3748,
+      "eval_samples_per_second": 564.184,
+      "eval_steps_per_second": 2.226,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -295,7 +321,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 226752528864816.0,
+  "total_flos": 249475098303882.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null