model added

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "allenai/led-base-16384",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_length": 512,
+  "min_length": 100,
+  "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": false,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 512,
+  "min_length": 100,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.1",
+  "use_cache": false
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27828bd459099037debc7d7fc15f3bd838fe5708e24adb56971a87df592c23b4
+size 1294928837

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1088439d617ab052769b4f600377c4751c5f2cf385f8a99114ae75cc12711001
+size 647680813

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6d85e067c5025030418017f3f05a841f5cbc46433e74ae2a8f345cba2abee6
+size 15533

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4499aa197f809857d3a669de2231065b32ddca1488b916b5a3246ae777b29b35
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb30bd65607b832286d3160842fb114601fbfcb019ccf215983158be482d379
+size 627

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 16384,
+  "name_or_path": "allenai/led-base-16384",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": "/home/pageocr/.cache/huggingface/hub/models--allenai--led-base-16384/snapshots/38335783885b338d93791936c54bb4be46bebed9/special_tokens_map.json",
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,384 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0321027287319422,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9193548387096775e-05,
+      "loss": 2.714,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.8387096774193554e-05,
+      "loss": 1.6354,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 1.7578704357147217,
+      "eval_rouge2_fmeasure": 0.0827,
+      "eval_rouge2_precision": 0.0554,
+      "eval_rouge2_recall": 0.1855,
+      "eval_runtime": 1288.6002,
+      "eval_samples_per_second": 0.388,
+      "eval_steps_per_second": 0.039,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.7580645161290326e-05,
+      "loss": 1.5202,
+      "step": 15
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.67741935483871e-05,
+      "loss": 1.5048,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 1.6580469608306885,
+      "eval_rouge2_fmeasure": 0.0917,
+      "eval_rouge2_precision": 0.0625,
+      "eval_rouge2_recall": 0.1921,
+      "eval_runtime": 1296.1289,
+      "eval_samples_per_second": 0.386,
+      "eval_steps_per_second": 0.039,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.596774193548387e-05,
+      "loss": 1.4322,
+      "step": 25
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.516129032258064e-05,
+      "loss": 1.4194,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 1.5461347103118896,
+      "eval_rouge2_fmeasure": 0.0919,
+      "eval_rouge2_precision": 0.0613,
+      "eval_rouge2_recall": 0.2071,
+      "eval_runtime": 1357.8126,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.037,
+      "step": 30
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.435483870967742e-05,
+      "loss": 1.3347,
+      "step": 35
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.3548387096774194e-05,
+      "loss": 1.3539,
+      "step": 40
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 1.5223164558410645,
+      "eval_rouge2_fmeasure": 0.0909,
+      "eval_rouge2_precision": 0.0606,
+      "eval_rouge2_recall": 0.2068,
+      "eval_runtime": 1335.0407,
+      "eval_samples_per_second": 0.375,
+      "eval_steps_per_second": 0.037,
+      "step": 40
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.2741935483870973e-05,
+      "loss": 1.351,
+      "step": 45
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.1935483870967746e-05,
+      "loss": 1.3326,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 1.483912706375122,
+      "eval_rouge2_fmeasure": 0.0902,
+      "eval_rouge2_precision": 0.0594,
+      "eval_rouge2_recall": 0.2113,
+      "eval_runtime": 1337.6258,
+      "eval_samples_per_second": 0.374,
+      "eval_steps_per_second": 0.037,
+      "step": 50
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.112903225806452e-05,
+      "loss": 1.2886,
+      "step": 55
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.032258064516129e-05,
+      "loss": 1.2789,
+      "step": 60
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 1.5512304306030273,
+      "eval_rouge2_fmeasure": 0.0954,
+      "eval_rouge2_precision": 0.0639,
+      "eval_rouge2_recall": 0.2123,
+      "eval_runtime": 1377.3491,
+      "eval_samples_per_second": 0.363,
+      "eval_steps_per_second": 0.036,
+      "step": 60
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.951612903225806e-05,
+      "loss": 1.2981,
+      "step": 65
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.870967741935484e-05,
+      "loss": 1.2861,
+      "step": 70
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 1.461083173751831,
+      "eval_rouge2_fmeasure": 0.098,
+      "eval_rouge2_precision": 0.0651,
+      "eval_rouge2_recall": 0.2234,
+      "eval_runtime": 1306.3575,
+      "eval_samples_per_second": 0.383,
+      "eval_steps_per_second": 0.038,
+      "step": 70
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.7903225806451614e-05,
+      "loss": 1.3188,
+      "step": 75
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.7096774193548386e-05,
+      "loss": 1.2977,
+      "step": 80
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 1.4521564245224,
+      "eval_rouge2_fmeasure": 0.1013,
+      "eval_rouge2_precision": 0.0677,
+      "eval_rouge2_recall": 0.2272,
+      "eval_runtime": 1315.4665,
+      "eval_samples_per_second": 0.38,
+      "eval_steps_per_second": 0.038,
+      "step": 80
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.6290322580645165e-05,
+      "loss": 1.3004,
+      "step": 85
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.548387096774194e-05,
+      "loss": 1.2403,
+      "step": 90
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 1.4190800189971924,
+      "eval_rouge2_fmeasure": 0.1044,
+      "eval_rouge2_precision": 0.0695,
+      "eval_rouge2_recall": 0.2376,
+      "eval_runtime": 1335.9699,
+      "eval_samples_per_second": 0.374,
+      "eval_steps_per_second": 0.037,
+      "step": 90
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.467741935483872e-05,
+      "loss": 1.2567,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.387096774193548e-05,
+      "loss": 1.2235,
+      "step": 100
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.4258784055709839,
+      "eval_rouge2_fmeasure": 0.0988,
+      "eval_rouge2_precision": 0.0658,
+      "eval_rouge2_recall": 0.2201,
+      "eval_runtime": 1320.053,
+      "eval_samples_per_second": 0.379,
+      "eval_steps_per_second": 0.038,
+      "step": 100
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.306451612903226e-05,
+      "loss": 1.1957,
+      "step": 105
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 1.2944,
+      "step": 110
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.3971573114395142,
+      "eval_rouge2_fmeasure": 0.1008,
+      "eval_rouge2_precision": 0.0668,
+      "eval_rouge2_recall": 0.2303,
+      "eval_runtime": 1291.1344,
+      "eval_samples_per_second": 0.387,
+      "eval_steps_per_second": 0.039,
+      "step": 110
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.1451612903225806e-05,
+      "loss": 1.236,
+      "step": 115
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.0645161290322585e-05,
+      "loss": 1.2184,
+      "step": 120
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 1.4044127464294434,
+      "eval_rouge2_fmeasure": 0.1045,
+      "eval_rouge2_precision": 0.0688,
+      "eval_rouge2_recall": 0.2434,
+      "eval_runtime": 1297.8926,
+      "eval_samples_per_second": 0.385,
+      "eval_steps_per_second": 0.039,
+      "step": 120
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.9838709677419357e-05,
+      "loss": 1.1964,
+      "step": 125
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 1.2579,
+      "step": 130
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 1.3979231119155884,
+      "eval_rouge2_fmeasure": 0.102,
+      "eval_rouge2_precision": 0.0678,
+      "eval_rouge2_recall": 0.2317,
+      "eval_runtime": 1320.6473,
+      "eval_samples_per_second": 0.379,
+      "eval_steps_per_second": 0.038,
+      "step": 130
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.822580645161291e-05,
+      "loss": 1.2123,
+      "step": 135
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.7419354838709678e-05,
+      "loss": 1.1875,
+      "step": 140
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 1.431972861289978,
+      "eval_rouge2_fmeasure": 0.104,
+      "eval_rouge2_precision": 0.0694,
+      "eval_rouge2_recall": 0.2333,
+      "eval_runtime": 1301.699,
+      "eval_samples_per_second": 0.384,
+      "eval_steps_per_second": 0.038,
+      "step": 140
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.661290322580645e-05,
+      "loss": 1.2311,
+      "step": 145
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.5806451612903226e-05,
+      "loss": 1.2116,
+      "step": 150
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 1.417688012123108,
+      "eval_rouge2_fmeasure": 0.1034,
+      "eval_rouge2_precision": 0.069,
+      "eval_rouge2_recall": 0.2334,
+      "eval_runtime": 1305.2333,
+      "eval_samples_per_second": 0.383,
+      "eval_steps_per_second": 0.038,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5e-05,
+      "loss": 1.2515,
+      "step": 155
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.4193548387096777e-05,
+      "loss": 1.3298,
+      "step": 160
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 1.4143891334533691,
+      "eval_rouge2_fmeasure": 0.105,
+      "eval_rouge2_precision": 0.0705,
+      "eval_rouge2_recall": 0.2332,
+      "eval_runtime": 1300.2169,
+      "eval_samples_per_second": 0.385,
+      "eval_steps_per_second": 0.038,
+      "step": 160
+    }
+  ],
+  "max_steps": 310,
+  "num_train_epochs": 2,
+  "total_flos": 6.944926835146752e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d6c1ba810340f1ba107a1c7330596235f02ceb1b093166f4c61abdb54ea19f
+size 3579