Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9a3eebd20610a414625152aa7649fe78157e0932fe978d3b69a7e01a071ed1
+oid sha256:7749c99a5652a55c87148f83508ce00852aec76c90029bc9e94f149c8d24c5b0
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ad2c13c5410c5b1f315e289142d62e696e4562e5f1b76eae3ef0536b1c7ccb
+oid sha256:491a3630e7f9b152d1a61ba589fac8eb7e0a1a38cd9ce551ff3c2db13b769018
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257882d778b7ee81778c5c372a17241451c183798e27c011c1764580527db4bc
+oid sha256:d909219cbdd70599a7be8a42aba4df5d7065f7b997b0075bce4834affe89f840
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b383cee6a8b310b70be569cfc8af334eaeb0c2fb37d6fe24dbd7ccca37a08dab
+oid sha256:cd937dc5ca4c62f5f5a023ee1555a7a5e140540c1dc517f73c54011163ae049e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.037335559725761414,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-01/checkpoint-15000",
-  "epoch": 7.889546351084813,
+  "epoch": 8.382642998027613,
   "eval_steps": 1000,
-  "global_step": 16000,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -423,6 +423,32 @@
       "eval_samples_per_second": 574.112,
       "eval_steps_per_second": 2.265,
       "step": 16000
+    },
+    {
+      "epoch": 8.136094674556213,
+      "grad_norm": 0.20288299024105072,
+      "learning_rate": 1.8373076923076926e-05,
+      "loss": 0.0214,
+      "step": 16500
+    },
+    {
+      "epoch": 8.382642998027613,
+      "grad_norm": 0.5671559572219849,
+      "learning_rate": 1.8323865877712033e-05,
+      "loss": 0.0205,
+      "step": 17000
+    },
+    {
+      "epoch": 8.382642998027613,
+      "eval_accuracy": 0.9875915926130646,
+      "eval_f1": 0.6300443693217832,
+      "eval_loss": 0.03755596652626991,
+      "eval_precision": 0.7040989799773328,
+      "eval_recall": 0.5700848818536361,
+      "eval_runtime": 14.1084,
+      "eval_samples_per_second": 574.834,
+      "eval_steps_per_second": 2.268,
+      "step": 17000
     }
   ],
   "logging_steps": 500,
@@ -451,7 +477,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 361937940787440.0,
+  "total_flos": 384458650453980.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null