End of training

checkpoint-11000/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c57e05d3f7e9c882e3cf561394a94532ce7d4df59b422bf335fad1498c1cc3e
-size 1134425553

checkpoint-11000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:edc6c1a25455a0ac08a6ba15e2bb0949f0e47c53b5d7e9f6781b4d75bdb78a0d
-size 14575

checkpoint-11000/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b1cf22c2871c42a245e6e913d024763352b9f1be40e2deb2b845f641c7d0252c
-size 557

checkpoint-11000/trainer_state.json

@@ -1,412 +0,0 @@
-{
-  "best_metric": 0.8849383152916955,
-  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-8500",
-  "epoch": 4.570004154549231,
-  "global_step": 11000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.21,
-      "learning_rate": 4.793934358122144e-05,
-      "loss": 0.7223,
-      "step": 500
-    },
-    {
-      "epoch": 0.21,
-      "eval_accuracy": 0.7741471103890881,
-      "eval_f1": 0.7741471103890881,
-      "eval_loss": 0.7764509916305542,
-      "eval_precision": 0.7741471103890881,
-      "eval_recall": 0.7741471103890881,
-      "eval_runtime": 33.2902,
-      "eval_samples_per_second": 61.64,
-      "eval_steps_per_second": 3.875,
-      "step": 500
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 4.5870378063980065e-05,
-      "loss": 0.4469,
-      "step": 1000
-    },
-    {
-      "epoch": 0.42,
-      "eval_accuracy": 0.8311511798105226,
-      "eval_f1": 0.8311511798105226,
-      "eval_loss": 0.5913723707199097,
-      "eval_precision": 0.8311511798105226,
-      "eval_recall": 0.8311511798105226,
-      "eval_runtime": 37.4699,
-      "eval_samples_per_second": 54.764,
-      "eval_steps_per_second": 3.443,
-      "step": 1000
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 4.3793103448275864e-05,
-      "loss": 0.3819,
-      "step": 1500
-    },
-    {
-      "epoch": 0.62,
-      "eval_accuracy": 0.8102330668639719,
-      "eval_f1": 0.8102330668639719,
-      "eval_loss": 0.8744572997093201,
-      "eval_precision": 0.8102330668639719,
-      "eval_recall": 0.8102330668639719,
-      "eval_runtime": 34.6123,
-      "eval_samples_per_second": 59.285,
-      "eval_steps_per_second": 3.727,
-      "step": 1500
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 4.171582883257167e-05,
-      "loss": 0.3361,
-      "step": 2000
-    },
-    {
-      "epoch": 0.83,
-      "eval_accuracy": 0.8337166846278812,
-      "eval_f1": 0.8337166846278812,
-      "eval_loss": 0.6990912556648254,
-      "eval_precision": 0.8337166846278812,
-      "eval_recall": 0.8337166846278812,
-      "eval_runtime": 38.6559,
-      "eval_samples_per_second": 53.084,
-      "eval_steps_per_second": 3.337,
-      "step": 2000
-    },
-    {
-      "epoch": 1.04,
-      "learning_rate": 3.964270876609888e-05,
-      "loss": 0.2784,
-      "step": 2500
-    },
-    {
-      "epoch": 1.04,
-      "eval_accuracy": 0.8119380418523106,
-      "eval_f1": 0.8119380418523107,
-      "eval_loss": 0.7512525320053101,
-      "eval_precision": 0.8119380418523106,
-      "eval_recall": 0.8119380418523106,
-      "eval_runtime": 33.6314,
-      "eval_samples_per_second": 61.014,
-      "eval_steps_per_second": 3.836,
-      "step": 2500
-    },
-    {
-      "epoch": 1.25,
-      "learning_rate": 3.756543415039468e-05,
-      "loss": 0.2377,
-      "step": 3000
-    },
-    {
-      "epoch": 1.25,
-      "eval_accuracy": 0.8165945537308391,
-      "eval_f1": 0.8165945537308391,
-      "eval_loss": 0.9047627449035645,
-      "eval_precision": 0.8165945537308391,
-      "eval_recall": 0.8165945537308391,
-      "eval_runtime": 39.8436,
-      "eval_samples_per_second": 51.501,
-      "eval_steps_per_second": 3.238,
-      "step": 3000
-    },
-    {
-      "epoch": 1.45,
-      "learning_rate": 3.548815953469049e-05,
-      "loss": 0.2401,
-      "step": 3500
-    },
-    {
-      "epoch": 1.45,
-      "eval_accuracy": 0.7939071271171446,
-      "eval_f1": 0.7939071271171445,
-      "eval_loss": 1.241086721420288,
-      "eval_precision": 0.7939071271171446,
-      "eval_recall": 0.7939071271171446,
-      "eval_runtime": 34.8048,
-      "eval_samples_per_second": 58.957,
-      "eval_steps_per_second": 3.706,
-      "step": 3500
-    },
-    {
-      "epoch": 1.66,
-      "learning_rate": 3.341088491898629e-05,
-      "loss": 0.2054,
-      "step": 4000
-    },
-    {
-      "epoch": 1.66,
-      "eval_accuracy": 0.8079812131057889,
-      "eval_f1": 0.8079812131057889,
-      "eval_loss": 1.1594407558441162,
-      "eval_precision": 0.8079812131057889,
-      "eval_recall": 0.8079812131057889,
-      "eval_runtime": 39.5136,
-      "eval_samples_per_second": 51.932,
-      "eval_steps_per_second": 3.265,
-      "step": 4000
-    },
-    {
-      "epoch": 1.87,
-      "learning_rate": 3.133361030328209e-05,
-      "loss": 0.1909,
-      "step": 4500
-    },
-    {
-      "epoch": 1.87,
-      "eval_accuracy": 0.8424747872802432,
-      "eval_f1": 0.842474787280243,
-      "eval_loss": 0.7545156478881836,
-      "eval_precision": 0.8424747872802432,
-      "eval_recall": 0.8424747872802432,
-      "eval_runtime": 35.061,
-      "eval_samples_per_second": 58.527,
-      "eval_steps_per_second": 3.679,
-      "step": 4500
-    },
-    {
-      "epoch": 2.08,
-      "learning_rate": 2.9256335687577903e-05,
-      "loss": 0.1704,
-      "step": 5000
-    },
-    {
-      "epoch": 2.08,
-      "eval_accuracy": 0.8317543549243216,
-      "eval_f1": 0.8317543549243216,
-      "eval_loss": 0.856721818447113,
-      "eval_precision": 0.8317543549243216,
-      "eval_recall": 0.8317543549243216,
-      "eval_runtime": 38.2513,
-      "eval_samples_per_second": 53.645,
-      "eval_steps_per_second": 3.372,
-      "step": 5000
-    },
-    {
-      "epoch": 2.29,
-      "learning_rate": 2.7179061071873702e-05,
-      "loss": 0.1294,
-      "step": 5500
-    },
-    {
-      "epoch": 2.29,
-      "eval_accuracy": 0.8489327821653182,
-      "eval_f1": 0.8489327821653182,
-      "eval_loss": 0.8485749959945679,
-      "eval_precision": 0.8489327821653182,
-      "eval_recall": 0.8489327821653182,
-      "eval_runtime": 33.5765,
-      "eval_samples_per_second": 61.114,
-      "eval_steps_per_second": 3.842,
-      "step": 5500
-    },
-    {
-      "epoch": 2.49,
-      "learning_rate": 2.5101786456169508e-05,
-      "loss": 0.134,
-      "step": 6000
-    },
-    {
-      "epoch": 2.49,
-      "eval_accuracy": 0.8573209374145502,
-      "eval_f1": 0.8573209374145502,
-      "eval_loss": 0.7681939005851746,
-      "eval_precision": 0.8573209374145502,
-      "eval_recall": 0.8573209374145502,
-      "eval_runtime": 39.5768,
-      "eval_samples_per_second": 51.849,
-      "eval_steps_per_second": 3.259,
-      "step": 6000
-    },
-    {
-      "epoch": 2.7,
-      "learning_rate": 2.302451184046531e-05,
-      "loss": 0.1354,
-      "step": 6500
-    },
-    {
-      "epoch": 2.7,
-      "eval_accuracy": 0.8255697994241689,
-      "eval_f1": 0.8255697994241689,
-      "eval_loss": 0.9870807528495789,
-      "eval_precision": 0.8255697994241689,
-      "eval_recall": 0.8255697994241689,
-      "eval_runtime": 34.6532,
-      "eval_samples_per_second": 59.215,
-      "eval_steps_per_second": 3.723,
-      "step": 6500
-    },
-    {
-      "epoch": 2.91,
-      "learning_rate": 2.0947237224761117e-05,
-      "loss": 0.1239,
-      "step": 7000
-    },
-    {
-      "epoch": 2.91,
-      "eval_accuracy": 0.8189268308375287,
-      "eval_f1": 0.8189268308375287,
-      "eval_loss": 1.1430405378341675,
-      "eval_precision": 0.8189268308375287,
-      "eval_recall": 0.8189268308375287,
-      "eval_runtime": 39.4751,
-      "eval_samples_per_second": 51.982,
-      "eval_steps_per_second": 3.268,
-      "step": 7000
-    },
-    {
-      "epoch": 3.12,
-      "learning_rate": 1.886996260905692e-05,
-      "loss": 0.1012,
-      "step": 7500
-    },
-    {
-      "epoch": 3.12,
-      "eval_accuracy": 0.8385581702079747,
-      "eval_f1": 0.8385581702079747,
-      "eval_loss": 0.8271787166595459,
-      "eval_precision": 0.8385581702079747,
-      "eval_recall": 0.8385581702079747,
-      "eval_runtime": 33.307,
-      "eval_samples_per_second": 61.609,
-      "eval_steps_per_second": 3.873,
-      "step": 7500
-    },
-    {
-      "epoch": 3.32,
-      "learning_rate": 1.6792687993352722e-05,
-      "loss": 0.0788,
-      "step": 8000
-    },
-    {
-      "epoch": 3.32,
-      "eval_accuracy": 0.8364993324862074,
-      "eval_f1": 0.8364993324862076,
-      "eval_loss": 1.028805136680603,
-      "eval_precision": 0.8364993324862074,
-      "eval_recall": 0.8364993324862074,
-      "eval_runtime": 38.2117,
-      "eval_samples_per_second": 53.701,
-      "eval_steps_per_second": 3.376,
-      "step": 8000
-    },
-    {
-      "epoch": 3.53,
-      "learning_rate": 1.4715413377648527e-05,
-      "loss": 0.0802,
-      "step": 8500
-    },
-    {
-      "epoch": 3.53,
-      "eval_accuracy": 0.8849383152916955,
-      "eval_f1": 0.8849383152916955,
-      "eval_loss": 0.719699501991272,
-      "eval_precision": 0.8849383152916955,
-      "eval_recall": 0.8849383152916955,
-      "eval_runtime": 34.4056,
-      "eval_samples_per_second": 59.641,
-      "eval_steps_per_second": 3.749,
-      "step": 8500
-    },
-    {
-      "epoch": 3.74,
-      "learning_rate": 1.263813876194433e-05,
-      "loss": 0.0861,
-      "step": 9000
-    },
-    {
-      "epoch": 3.74,
-      "eval_accuracy": 0.8319634556304386,
-      "eval_f1": 0.8319634556304386,
-      "eval_loss": 1.1419589519500732,
-      "eval_precision": 0.8319634556304386,
-      "eval_recall": 0.8319634556304386,
-      "eval_runtime": 39.7118,
-      "eval_samples_per_second": 51.672,
-      "eval_steps_per_second": 3.248,
-      "step": 9000
-    },
-    {
-      "epoch": 3.95,
-      "learning_rate": 1.0560864146240134e-05,
-      "loss": 0.0639,
-      "step": 9500
-    },
-    {
-      "epoch": 3.95,
-      "eval_accuracy": 0.8585272876421483,
-      "eval_f1": 0.8585272876421483,
-      "eval_loss": 0.9562506079673767,
-      "eval_precision": 0.8585272876421483,
-      "eval_recall": 0.8585272876421483,
-      "eval_runtime": 33.8854,
-      "eval_samples_per_second": 60.557,
-      "eval_steps_per_second": 3.807,
-      "step": 9500
-    },
-    {
-      "epoch": 4.15,
-      "learning_rate": 8.483589530535937e-06,
-      "loss": 0.0464,
-      "step": 10000
-    },
-    {
-      "epoch": 4.15,
-      "eval_accuracy": 0.8510961702401442,
-      "eval_f1": 0.8510961702401442,
-      "eval_loss": 1.0767754316329956,
-      "eval_precision": 0.8510961702401442,
-      "eval_recall": 0.8510961702401442,
-      "eval_runtime": 38.7314,
-      "eval_samples_per_second": 52.98,
-      "eval_steps_per_second": 3.331,
-      "step": 10000
-    },
-    {
-      "epoch": 4.36,
-      "learning_rate": 6.406314914831742e-06,
-      "loss": 0.0412,
-      "step": 10500
-    },
-    {
-      "epoch": 4.36,
-      "eval_accuracy": 0.8439143652185103,
-      "eval_f1": 0.8439143652185103,
-      "eval_loss": 1.1184284687042236,
-      "eval_precision": 0.8439143652185103,
-      "eval_recall": 0.8439143652185103,
-      "eval_runtime": 34.8108,
-      "eval_samples_per_second": 58.947,
-      "eval_steps_per_second": 3.706,
-      "step": 10500
-    },
-    {
-      "epoch": 4.57,
-      "learning_rate": 4.333194848358953e-06,
-      "loss": 0.039,
-      "step": 11000
-    },
-    {
-      "epoch": 4.57,
-      "eval_accuracy": 0.8635778739283588,
-      "eval_f1": 0.8635778739283588,
-      "eval_loss": 0.9634060263633728,
-      "eval_precision": 0.8635778739283588,
-      "eval_recall": 0.8635778739283588,
-      "eval_runtime": 39.6244,
-      "eval_samples_per_second": 51.786,
-      "eval_steps_per_second": 3.256,
-      "step": 11000
-    }
-  ],
-  "max_steps": 12035,
-  "num_train_epochs": 5,
-  "total_flos": 1.835352614695219e+16,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-11500/config.json

@@ -1,56 +0,0 @@
-{
-  "_name_or_path": "nielsr/lilt-xlm-roberta-base",
-  "architectures": [
-    "LiltForTokenClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "channel_shrink_ratio": 4,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "Caption",
-    "1": "Footnote",
-    "2": "Formula",
-    "3": "List-item",
-    "4": "Page-footer",
-    "5": "Page-header",
-    "6": "Picture",
-    "7": "Section-header",
-    "8": "Table",
-    "9": "Text",
-    "10": "Title"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "Caption": 0,
-    "Footnote": 1,
-    "Formula": 2,
-    "List-item": 3,
-    "Page-footer": 4,
-    "Page-header": 5,
-    "Picture": 6,
-    "Section-header": 7,
-    "Table": 8,
-    "Text": 9,
-    "Title": 10
-  },
-  "layer_norm_eps": 1e-05,
-  "max_2d_position_embeddings": 1024,
-  "max_position_embeddings": 514,
-  "model_type": "lilt",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
-}

checkpoint-11500/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a987de3ede3a55ee97ff63886937a088657c2157826f53d07345ccc9c7e5d778
-size 2265828101

checkpoint-11500/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0ec4d60da8dcded02dd5639d5b8b5174bf534b01c0f3a7ab99393164e017b39f
-size 627

checkpoint-11500/special_tokens_map.json

@@ -1,15 +0,0 @@
-{
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
-}

checkpoint-11500/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
-size 17082660

checkpoint-11500/tokenizer_config.json

@@ -1,20 +0,0 @@
-{
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 512,
-  "name_or_path": "nielsr/lilt-xlm-roberta-base",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
-}

checkpoint-11500/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2b3cb303483efa6f2dc51db1cfb9b16000da398e2d72673041025bfff104b3b8
-size 3643

{checkpoint-11000 → checkpoint-12000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a373613aeeb4d6be34886b231335f8c8f20879c526ba375b702a8ec78acc96a8
+oid sha256:0377763861e1565e68485e8f32b7a5c377a24284acd536ab0029416d61d03d48
 size 2265828101

{checkpoint-11500 → checkpoint-12000}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a336d572b84d95a1c812e645a72e90873027257b83cee92eef0d3a78890c576
+oid sha256:a9b13e786aeddc70907b9ab2ab994abb01bbd8b9fc1b605eb6d43b6bd26a7bf0
 size 1134425553

{checkpoint-11500 → checkpoint-12000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b8ef7d104554cd305a60fb7a5d256c7f82cfc12dc853397197d87e16ef1f65
+oid sha256:9977b81b71597a1403649a2cd7ca5af0ff76ea09f7cc4fd6954a25d51c950458
 size 14575

{checkpoint-11500 → checkpoint-12000}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee4f114f4e57c077eb75e91b7efc254c244508b080b0e6980415bdd75809aff
+oid sha256:ade8adec025aa8c55d5922c910484f65a4f9a8ee23da0b6291286fb7fdd6926a
 size 557

{checkpoint-11000 → checkpoint-12000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc076744799314c413b1a22fd57768d86453e79c6cbb2e75e964b3a373c4958
+oid sha256:2d9dec43e359a11ff94e53c08c39c3034d0df5115ac402825b9258dc21576cba
 size 627

{checkpoint-11500 → checkpoint-12000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 0.8849383152916955,
   "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-8500",
-  "epoch": 4.777731616119651,
-  "global_step": 11500,
+  "epoch": 4.985459077690071,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -420,11 +420,29 @@
       "eval_samples_per_second": 58.569,
       "eval_steps_per_second": 3.682,
       "step": 11500
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 1.7864561695056087e-07,
+      "loss": 0.0395,
+      "step": 12000
+    },
+    {
+      "epoch": 4.99,
+      "eval_accuracy": 0.8583503562754339,
+      "eval_f1": 0.8583503562754339,
+      "eval_loss": 1.0003422498703003,
+      "eval_precision": 0.8583503562754339,
+      "eval_recall": 0.8583503562754339,
+      "eval_runtime": 39.4996,
+      "eval_samples_per_second": 51.95,
+      "eval_steps_per_second": 3.266,
+      "step": 12000
     }
   ],
   "max_steps": 12035,
   "num_train_epochs": 5,
-  "total_flos": 1.918804286349619e+16,
+  "total_flos": 2.002255958004019e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a336d572b84d95a1c812e645a72e90873027257b83cee92eef0d3a78890c576
+oid sha256:e39c7d7515bc3fd9710bfa20bd4d1d7c408894096e55b518c4e64c07ac0ff33b
 size 1134425553

runs/Feb09_15-43-15_f1c8d3a96fe7/events.out.tfevents.1675957409.f1c8d3a96fe7.143.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b09326263f0fbe132c2f3bc4c0d88999487e384816c9a0719ad3719c72fd3d
-size 19096
+oid sha256:6995b72b1d777bdf7ca3001094bdb7626e66b36cb75e85a842900924e4a2f0d7
+size 20079