Training in progress, step 1200, checkpoint

checkpoint-1200/config.json

@@ -0,0 +1,56 @@
+{
+  "_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": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-1200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950a61e38936e0f6e87e0ebcf9081829b10a954f58470eba8e5197fdd525b99d
+size 1134332228

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117113ffb5a365f05c466c4871a9138fb5aaa0c0058d24fbe063756a2219069c
+size 2265924830

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27128e9b30eef364e38b288b261d13d1e3f8eebd91a5f08b6a5baf56c18c3a88
+size 14244

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17cbc4b94c13728274f913c6d05d9d8aa9fd0e8ca8a98d162d90fcce3965d9e6
+size 1064

checkpoint-1200/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

checkpoint-1200/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-1200/trainer_state.json

@@ -0,0 +1,191 @@
+{
+  "best_metric": 0.88568377134758,
+  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-1200",
+  "epoch": 0.6396588486140725,
+  "eval_steps": 100,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.053304904051172705,
+      "eval_accuracy": 0.6684599798377034,
+      "eval_f1": 0.6684599798377034,
+      "eval_loss": 0.9209221005439758,
+      "eval_precision": 0.6684599798377034,
+      "eval_recall": 0.6684599798377034,
+      "eval_runtime": 41.8743,
+      "eval_samples_per_second": 38.377,
+      "eval_steps_per_second": 2.412,
+      "step": 100
+    },
+    {
+      "epoch": 0.10660980810234541,
+      "eval_accuracy": 0.8154451176300318,
+      "eval_f1": 0.8154451176300318,
+      "eval_loss": 0.6488999724388123,
+      "eval_precision": 0.8154451176300318,
+      "eval_recall": 0.8154451176300318,
+      "eval_runtime": 44.2144,
+      "eval_samples_per_second": 36.346,
+      "eval_steps_per_second": 2.284,
+      "step": 200
+    },
+    {
+      "epoch": 0.15991471215351813,
+      "eval_accuracy": 0.7420323994130975,
+      "eval_f1": 0.7420323994130975,
+      "eval_loss": 0.7198283076286316,
+      "eval_precision": 0.7420323994130975,
+      "eval_recall": 0.7420323994130975,
+      "eval_runtime": 41.064,
+      "eval_samples_per_second": 39.134,
+      "eval_steps_per_second": 2.46,
+      "step": 300
+    },
+    {
+      "epoch": 0.21321961620469082,
+      "eval_accuracy": 0.7961212532564105,
+      "eval_f1": 0.7961212532564104,
+      "eval_loss": 0.5486767292022705,
+      "eval_precision": 0.7961212532564105,
+      "eval_recall": 0.7961212532564105,
+      "eval_runtime": 43.0362,
+      "eval_samples_per_second": 37.341,
+      "eval_steps_per_second": 2.347,
+      "step": 400
+    },
+    {
+      "epoch": 0.26652452025586354,
+      "grad_norm": 8.946574211120605,
+      "learning_rate": 1.4722814498933904e-05,
+      "loss": 0.736,
+      "step": 500
+    },
+    {
+      "epoch": 0.26652452025586354,
+      "eval_accuracy": 0.8669088803936639,
+      "eval_f1": 0.8669088803936638,
+      "eval_loss": 0.44298624992370605,
+      "eval_precision": 0.8669088803936639,
+      "eval_recall": 0.8669088803936639,
+      "eval_runtime": 42.8219,
+      "eval_samples_per_second": 37.527,
+      "eval_steps_per_second": 2.359,
+      "step": 500
+    },
+    {
+      "epoch": 0.31982942430703626,
+      "eval_accuracy": 0.8614091648617086,
+      "eval_f1": 0.8614091648617086,
+      "eval_loss": 0.4405972361564636,
+      "eval_precision": 0.8614091648617086,
+      "eval_recall": 0.8614091648617086,
+      "eval_runtime": 46.0068,
+      "eval_samples_per_second": 34.93,
+      "eval_steps_per_second": 2.195,
+      "step": 600
+    },
+    {
+      "epoch": 0.373134328358209,
+      "eval_accuracy": 0.865092277441185,
+      "eval_f1": 0.865092277441185,
+      "eval_loss": 0.41120249032974243,
+      "eval_precision": 0.865092277441185,
+      "eval_recall": 0.865092277441185,
+      "eval_runtime": 43.2183,
+      "eval_samples_per_second": 37.183,
+      "eval_steps_per_second": 2.337,
+      "step": 700
+    },
+    {
+      "epoch": 0.42643923240938164,
+      "eval_accuracy": 0.8710710970485193,
+      "eval_f1": 0.8710710970485193,
+      "eval_loss": 0.41007000207901,
+      "eval_precision": 0.8710710970485193,
+      "eval_recall": 0.8710710970485193,
+      "eval_runtime": 41.5981,
+      "eval_samples_per_second": 38.632,
+      "eval_steps_per_second": 2.428,
+      "step": 800
+    },
+    {
+      "epoch": 0.47974413646055436,
+      "eval_accuracy": 0.8397596494555182,
+      "eval_f1": 0.8397596494555181,
+      "eval_loss": 0.469059020280838,
+      "eval_precision": 0.8397596494555182,
+      "eval_recall": 0.8397596494555182,
+      "eval_runtime": 42.8271,
+      "eval_samples_per_second": 37.523,
+      "eval_steps_per_second": 2.358,
+      "step": 900
+    },
+    {
+      "epoch": 0.5330490405117271,
+      "grad_norm": 1.78385591506958,
+      "learning_rate": 9.392324093816631e-06,
+      "loss": 0.4575,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5330490405117271,
+      "eval_accuracy": 0.8009322566800083,
+      "eval_f1": 0.8009322566800084,
+      "eval_loss": 0.4894373416900635,
+      "eval_precision": 0.8009322566800083,
+      "eval_recall": 0.8009322566800083,
+      "eval_runtime": 45.5517,
+      "eval_samples_per_second": 35.279,
+      "eval_steps_per_second": 2.217,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5863539445628998,
+      "eval_accuracy": 0.8552706438959147,
+      "eval_f1": 0.8552706438959147,
+      "eval_loss": 0.427526593208313,
+      "eval_precision": 0.8552706438959147,
+      "eval_recall": 0.8552706438959147,
+      "eval_runtime": 41.1754,
+      "eval_samples_per_second": 39.028,
+      "eval_steps_per_second": 2.453,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6396588486140725,
+      "eval_accuracy": 0.88568377134758,
+      "eval_f1": 0.88568377134758,
+      "eval_loss": 0.3613550066947937,
+      "eval_precision": 0.88568377134758,
+      "eval_recall": 0.88568377134758,
+      "eval_runtime": 43.3876,
+      "eval_samples_per_second": 37.038,
+      "eval_steps_per_second": 2.328,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1876,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2670453492940800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310ed091c3918a1d9ebfef484979290e5f98817614fea477d6988c3c827bc379
+size 5304