Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:077445b126c15e88ae1e8de316ff6b3f4e2e2f7214784605950659b45dbfd75d
+oid sha256:75f25d8ad92f875a53659d2aa604eab54bc9083bbbead781aa5da3c192cfdc81
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4013ab06115cbb5f13e760d9d438c84425fa73fa2dd6ac8bce7320b64ced7c1c
+oid sha256:8883bcd809b17855f5bd75fa68a9ed04c375ce0e9e0384257d097e9cf8c0ddd9
 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:e3bf1b4a06cfcf7ffbad3f6e707792c1da71ddc3c6fe8d02ca200ee95016b033
+oid sha256:b383cee6a8b310b70be569cfc8af334eaeb0c2fb37d6fe24dbd7ccca37a08dab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0380592942237854,
   "best_model_checkpoint": "doc-topic-model_eval-02_train-01/checkpoint-14000",
-  "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": 551.288,
       "eval_steps_per_second": 2.175,
       "step": 15000
+    },
+    {
+      "epoch": 7.642998027613412,
+      "grad_norm": 0.3601667582988739,
+      "learning_rate": 1.8471696252465485e-05,
+      "loss": 0.0243,
+      "step": 15500
+    },
+    {
+      "epoch": 7.889546351084813,
+      "grad_norm": 0.4192611575126648,
+      "learning_rate": 1.8422386587771205e-05,
+      "loss": 0.0255,
+      "step": 16000
+    },
+    {
+      "epoch": 7.889546351084813,
+      "eval_accuracy": 0.9876312768400017,
+      "eval_f1": 0.6257237208903376,
+      "eval_loss": 0.038173139095306396,
+      "eval_precision": 0.7173763398564263,
+      "eval_recall": 0.5548372376026772,
+      "eval_runtime": 14.4228,
+      "eval_samples_per_second": 562.305,
+      "eval_steps_per_second": 2.219,
+      "step": 16000
     }
   ],
   "logging_steps": 500,
@@ -425,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 339302697077952.0,
+  "total_flos": 361937940787440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null