Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed574e6146e933eb3a3ee7c8db9b460d874216c1e941646df36a6c42ad2d82fe
+oid sha256:784619966569654c1096fb81eebce432699a2de0b3c41084eb413002eb3613b2
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b222d9016496fffa03a3616511b831738289197202235dd1f567066cdbfa317
+oid sha256:a0163dd19e33027451329a11df232114840545d8c7e740df6d9e0616de5bbfd2
 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 sha256:90f812a1b6a357735ef9df3af32728c85d0df9e178f3a70d3bbfd9db194d6d6c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.037242207676172256,
   "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-14000",
-  "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": 557.887,
       "eval_steps_per_second": 2.201,
       "step": 16000
+    },
+    {
+      "epoch": 8.136094674556213,
+      "grad_norm": 0.2590983510017395,
+      "learning_rate": 1.8373076923076926e-05,
+      "loss": 0.0219,
+      "step": 16500
+    },
+    {
+      "epoch": 8.382642998027613,
+      "grad_norm": 0.6246200203895569,
+      "learning_rate": 1.8323767258382646e-05,
+      "loss": 0.0215,
+      "step": 17000
+    },
+    {
+      "epoch": 8.382642998027613,
+      "eval_accuracy": 0.9875504910923083,
+      "eval_f1": 0.6240691603184114,
+      "eval_loss": 0.03826015442609787,
+      "eval_precision": 0.7126380607956212,
+      "eval_recall": 0.5550818424057861,
+      "eval_runtime": 14.5306,
+      "eval_samples_per_second": 558.131,
+      "eval_steps_per_second": 2.202,
+      "step": 17000
     }
   ],
   "logging_steps": 500,
@@ -451,7 +477,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 362359799208072.0,
+  "total_flos": 384839566841160.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null