Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2f2df71d536915ef60315e21fbe46cdeb18d9b481ead51877daec615f239da
+oid sha256:587606c149b035129feeb08516742eaa4dd15a83c452d067f67f0e2371926c91
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74790248a0785731d68493991bf8b373659da4dc8141c0017ec04e4f84a2b3f1
+oid sha256:0c1d5c74203ad116a506045f4e86499f6fd913f0334a4eac1a1c3e7d9f90383d
 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": 0.03718467801809311,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-13000",
-  "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": 574.389,
       "eval_steps_per_second": 2.266,
       "step": 16000
+    },
+    {
+      "epoch": 8.136094674556213,
+      "grad_norm": 0.2036384493112564,
+      "learning_rate": 1.8373076923076926e-05,
+      "loss": 0.0216,
+      "step": 16500
+    },
+    {
+      "epoch": 8.382642998027613,
+      "grad_norm": 0.1960095316171646,
+      "learning_rate": 1.8323865877712033e-05,
+      "loss": 0.0205,
+      "step": 17000
+    },
+    {
+      "epoch": 8.382642998027613,
+      "eval_accuracy": 0.987797100216846,
+      "eval_f1": 0.6324282786885246,
+      "eval_loss": 0.038331326097249985,
+      "eval_precision": 0.7158596694694114,
+      "eval_recall": 0.5664143152099105,
+      "eval_runtime": 14.1717,
+      "eval_samples_per_second": 572.267,
+      "eval_steps_per_second": 2.258,
+      "step": 17000
     }
   ],
   "logging_steps": 500,
@@ -451,7 +477,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 361390664998512.0,
+  "total_flos": 383935214330100.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null