Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d916f763b88a4c9cc4e48b750eaaa3c02a7aa7f4b905e4929de0173321eefb5a
+oid sha256:08617865067656e4e06231828eda918e8826650a2df85095a7f188ce116a569f
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196470881ccffda5f09abb08b182fb954fa27df4fdb381f4d8c4c95ee886374a
+oid sha256:a45f02833ebb33791018baa83236ad742f0ef70f3806ddf68a0e6e16b7ed245f
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ade8cbdb5c0dd1f6c03e792fe42b4b1893a6c42ae7b8ee252e85a63008e936
+oid sha256:257882d778b7ee81778c5c372a17241451c183798e27c011c1764580527db4bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba7656f2677e9d4a517320301deeaf9502c6f8f9c04d35a107ff5b3063e9135
+oid sha256:b383cee6a8b310b70be569cfc8af334eaeb0c2fb37d6fe24dbd7ccca37a08dab
 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": 7.396449704142012,
+  "epoch": 7.889546351084813,
   "eval_steps": 1000,
-  "global_step": 15000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,32 @@
       "eval_samples_per_second": 565.864,
       "eval_steps_per_second": 2.233,
       "step": 15000
+    },
+    {
+      "epoch": 7.642998027613412,
+      "grad_norm": 0.23438788950443268,
+      "learning_rate": 1.8471696252465485e-05,
+      "loss": 0.0234,
+      "step": 15500
+    },
+    {
+      "epoch": 7.889546351084813,
+      "grad_norm": 0.3130985498428345,
+      "learning_rate": 1.8422386587771205e-05,
+      "loss": 0.0241,
+      "step": 16000
+    },
+    {
+      "epoch": 7.889546351084813,
+      "eval_accuracy": 0.9877928483353884,
+      "eval_f1": 0.6227828143476547,
+      "eval_loss": 0.03809000924229622,
+      "eval_precision": 0.7287822878228782,
+      "eval_recall": 0.5437026841018582,
+      "eval_runtime": 14.2635,
+      "eval_samples_per_second": 568.582,
+      "eval_steps_per_second": 2.243,
+      "step": 16000
     }
   ],
   "logging_steps": 500,
@@ -420,12 +446,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 338224211361324.0,
+  "total_flos": 360703978994412.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null