Training in progress, step 300, checkpoint

checkpoint-300/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b7bb401476ebfbf2e8d0b5e97dd9c68db699225b6dad3e7e19f9f90e71a406
+oid sha256:8de3c8c8f3a40d30b88eda3ccdc2516425d7d0dc954f63b9f66d81a7558ef54f
 size 1134332228

checkpoint-300/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:806b5590df5eacf0e364e1d2cfc685c70bcde7502ccb2167522a02f1cd8609b2
+oid sha256:2cc47348c702a0022af13c041848d24df2c6443e1bb3c48fd00e490f3319bb92
 size 2265924830

checkpoint-300/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4db699f5a908a76019280de7040e381ed9a7cbb9f2235667408906676ef0f74
+oid sha256:fc421c8fddea08151d7ad39805822c2e21285c984f139055f5044a28cf0c6db0
 size 14244

checkpoint-300/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7c50a05266a85b811971ca72b8ca026a9db934c96e888c16f97cf4c8777acae
+oid sha256:52994157dc052c931eef58e1d32a903316896aaa193ff6d3c5495b1a13852974
 size 1064

checkpoint-300/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683eb7c7eca2f8d4661f33cb19ad5dcb7c826bbc4256f314d42c7d9d3ac93240
-size 17083001
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

checkpoint-300/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7865890784233485,
-  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-300",
+  "best_metric": 0.7496182139399324,
+  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-200",
   "epoch": 0.15991471215351813,
   "eval_steps": 100,
   "global_step": 300,
@@ -10,37 +10,37 @@
   "log_history": [
     {
       "epoch": 0.053304904051172705,
-      "eval_accuracy": 0.6912373860880154,
-      "eval_f1": 0.6912373860880154,
-      "eval_loss": 0.8656882047653198,
-      "eval_precision": 0.6912373860880154,
-      "eval_recall": 0.6912373860880154,
-      "eval_runtime": 41.8245,
-      "eval_samples_per_second": 38.422,
-      "eval_steps_per_second": 2.415,
+      "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,
       "step": 100
     },
     {
       "epoch": 0.10660980810234541,
-      "eval_accuracy": 0.7121482827113298,
-      "eval_f1": 0.7121482827113298,
-      "eval_loss": 0.856532096862793,
-      "eval_precision": 0.7121482827113298,
-      "eval_recall": 0.7121482827113298,
-      "eval_runtime": 42.6291,
-      "eval_samples_per_second": 37.697,
-      "eval_steps_per_second": 2.369,
+      "eval_accuracy": 0.7496182139399323,
+      "eval_f1": 0.7496182139399324,
+      "eval_loss": 0.673028290271759,
+      "eval_precision": 0.7496182139399323,
+      "eval_recall": 0.7496182139399323,
+      "eval_runtime": 42.4041,
+      "eval_samples_per_second": 37.897,
+      "eval_steps_per_second": 2.382,
       "step": 200
     },
     {
       "epoch": 0.15991471215351813,
-      "eval_accuracy": 0.7865890784233484,
-      "eval_f1": 0.7865890784233485,
-      "eval_loss": 0.6567804217338562,
-      "eval_precision": 0.7865890784233484,
-      "eval_recall": 0.7865890784233484,
-      "eval_runtime": 41.1268,
-      "eval_samples_per_second": 39.074,
+      "eval_accuracy": 0.7356044197350954,
+      "eval_f1": 0.7356044197350955,
+      "eval_loss": 0.6603901982307434,
+      "eval_precision": 0.7356044197350954,
+      "eval_recall": 0.7356044197350954,
+      "eval_runtime": 41.1176,
+      "eval_samples_per_second": 39.083,
       "eval_steps_per_second": 2.456,
       "step": 300
     }
@@ -62,7 +62,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 667613373235200.0,
+  "total_flos": 890151164313600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-300/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d884d25b9a0a1975c8ad8cdce24ef6b7c329f16153a80771adc673a879e2c8c3
+oid sha256:623a05d696ac4fa501371203f02f03749bacbe9ec22f5e54f15d14e9636da808
 size 5304