Training in progress, step 100, checkpoint

checkpoint-100/config.json

@@ -49,7 +49,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.42.3",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

checkpoint-100/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ac01a6723c4cfc073d371469b86263f57d0f96bf0b51007655fbd386d93ec4
+oid sha256:cf326ccbf301f6b051aff791be97e018cbb01de72bfb49acbd3a646e36e6e43c
 size 1134332228

checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d897d8a3b233bb233a83cd93532aff62f62ebbce3aedfc6cb620d2fe976d25
-size 2265924830
+oid sha256:ce122551bf9e26d643e3d68f11aae2ef4bbefefad8e142e3f8906962b2759c16
+size 2268900866

checkpoint-100/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02d7f8a121f30fb9b0ad40f94139d1ae8d48000ff897e19a9df84688a69e15c
+oid sha256:19a42098527814cfd5612497796c7e824b2111c9bf7a97cc6374712d30dca610
 size 14244

checkpoint-100/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.7157016379370577,
+  "best_metric": 0.6321578647928374,
   "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-100",
   "epoch": 0.053304904051172705,
   "eval_steps": 100,
@@ -10,14 +10,14 @@
   "log_history": [
     {
       "epoch": 0.053304904051172705,
-      "eval_accuracy": 0.7157016379370577,
-      "eval_f1": 0.7157016379370577,
-      "eval_loss": 0.8210025429725647,
-      "eval_precision": 0.7157016379370577,
-      "eval_recall": 0.7157016379370577,
-      "eval_runtime": 40.0037,
-      "eval_samples_per_second": 40.171,
-      "eval_steps_per_second": 2.525,
+      "eval_accuracy": 0.6321578647928374,
+      "eval_f1": 0.6321578647928374,
+      "eval_loss": 0.9594171643257141,
+      "eval_precision": 0.6321578647928374,
+      "eval_recall": 0.6321578647928374,
+      "eval_runtime": 69.4219,
+      "eval_samples_per_second": 23.148,
+      "eval_steps_per_second": 0.735,
       "step": 100
     }
   ],
@@ -38,8 +38,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 445075582156800.0,
-  "train_batch_size": 8,
+  "total_flos": 222537791078400.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-100/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623a05d696ac4fa501371203f02f03749bacbe9ec22f5e54f15d14e9636da808
+oid sha256:2544ef83614d223e3dbe1cbe496bce99a66932dd46abc19142f548bbc4c106c4
 size 5304