Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66df5699efd6611e5991327fc49c95ca3324792f988e6c99913e34ed42ae7d77
+oid sha256:a70104e7a602b7beb6cdb5f82e63553c1542797c2a14628cd9e9bd62225b3517
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd5ca36f7a09a88370d0e25f90316e2a25f5919de60e518bfe596c07e0124ed5
+oid sha256:5b0bfbec5d5b0f625a6583ae8349d17995c8d548305f249dbe94d5630dd4283a
 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:ae7f535c7132d6f008b1726ba6d9ba2b6baa6c4e0ff67703b0f9cebcaada727c
+oid sha256:30b33ca44a0afbaac8fba4219410a4b0716db16d80a594374cc1a02724225c0e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03731473535299301,
   "best_model_checkpoint": "doc-topic-model_eval-01_train-04/checkpoint-13000",
-  "epoch": 7.392804337111878,
+  "epoch": 7.885657959586003,
   "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": 557.927,
       "eval_steps_per_second": 2.201,
       "step": 15000
+    },
+    {
+      "epoch": 7.639231148348941,
+      "grad_norm": 0.5829640626907349,
+      "learning_rate": 1.84724494825037e-05,
+      "loss": 0.0236,
+      "step": 15500
+    },
+    {
+      "epoch": 7.885657959586003,
+      "grad_norm": 0.470248281955719,
+      "learning_rate": 1.8423164120256285e-05,
+      "loss": 0.0235,
+      "step": 16000
+    },
+    {
+      "epoch": 7.885657959586003,
+      "eval_accuracy": 0.987211757869524,
+      "eval_f1": 0.6269175108538351,
+      "eval_loss": 0.03801080584526062,
+      "eval_precision": 0.6860633484162896,
+      "eval_recall": 0.5771602588503997,
+      "eval_runtime": 14.5422,
+      "eval_samples_per_second": 557.687,
+      "eval_steps_per_second": 2.2,
+      "step": 16000
     }
   ],
   "logging_steps": 500,
@@ -425,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 340203940067484.0,
+  "total_flos": 362872352006604.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null