Upload folder using huggingface_hub

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "LED_Layman/checkpoint-2640",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": null,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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": null,
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_length": null,
+  "min_length": null,
+  "model_type": "led",
+  "no_repeat_ngram_size": null,
+  "num_beams": null,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "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": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.48.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95040549a197c1af691552d062ad12f199423206a742644f323e7284a7bf279a
+size 1839478364

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b055a5ecec4210c4c586ec5df57818bb32a28ea70fe126b3aa03430bca0b0c
+size 3678901863

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d8c242e1ff0b364a979ee504b6e12a1b1016eff786e44de5eea7d6c8917cd7
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f03d8011b3231228d97a3d4221ed6abd8fd0aadaf71cd30401b21ac0a3defa
+size 1064

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,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 16384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 2639,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 117.37,
+      "eval_loss": 1.6928337812423706,
+      "eval_rouge1": 0.42757910674263067,
+      "eval_rouge2": 0.15720196581442164,
+      "eval_rougeL": 0.256418241790792,
+      "eval_rougeLsum": 0.35382355041095964,
+      "eval_runtime": 1351.6766,
+      "eval_samples_per_second": 0.74,
+      "eval_steps_per_second": 0.047,
+      "step": 377
+    },
+    {
+      "epoch": 1.3262599469496021,
+      "grad_norm": 3.7333056926727295,
+      "learning_rate": 2.8741879956059633e-06,
+      "loss": 1.7717,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 116.608,
+      "eval_loss": 1.6410094499588013,
+      "eval_rouge1": 0.4286897823447751,
+      "eval_rouge2": 0.15765392626100322,
+      "eval_rougeL": 0.25895063496135456,
+      "eval_rougeLsum": 0.3538857213392972,
+      "eval_runtime": 1170.2376,
+      "eval_samples_per_second": 0.855,
+      "eval_steps_per_second": 0.054,
+      "step": 754
+    },
+    {
+      "epoch": 2.6525198938992043,
+      "grad_norm": 4.453255653381348,
+      "learning_rate": 2.514178628889199e-06,
+      "loss": 1.5895,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 117.178,
+      "eval_loss": 1.6089894771575928,
+      "eval_rouge1": 0.42709156909402823,
+      "eval_rouge2": 0.1553778143480612,
+      "eval_rougeL": 0.25488136514137727,
+      "eval_rougeLsum": 0.3525718986787997,
+      "eval_runtime": 1384.4242,
+      "eval_samples_per_second": 0.722,
+      "eval_steps_per_second": 0.046,
+      "step": 1131
+    },
+    {
+      "epoch": 3.9787798408488064,
+      "grad_norm": 3.2527501583099365,
+      "learning_rate": 1.981320706041849e-06,
+      "loss": 1.5182,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 118.94,
+      "eval_loss": 1.597896933555603,
+      "eval_rouge1": 0.4321139550542189,
+      "eval_rouge2": 0.16019449900934246,
+      "eval_rougeL": 0.2577516929717559,
+      "eval_rougeLsum": 0.3566245729299692,
+      "eval_runtime": 1616.3945,
+      "eval_samples_per_second": 0.619,
+      "eval_steps_per_second": 0.039,
+      "step": 1508
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 116.603,
+      "eval_loss": 1.583080530166626,
+      "eval_rouge1": 0.43043600066735005,
+      "eval_rouge2": 0.16036196231543565,
+      "eval_rougeL": 0.2578722844279166,
+      "eval_rougeLsum": 0.35735455171087505,
+      "eval_runtime": 1754.8754,
+      "eval_samples_per_second": 0.57,
+      "eval_steps_per_second": 0.036,
+      "step": 1885
+    },
+    {
+      "epoch": 5.305039787798409,
+      "grad_norm": 3.344116687774658,
+      "learning_rate": 1.3651853437341204e-06,
+      "loss": 1.4547,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 116.67,
+      "eval_loss": 1.5650923252105713,
+      "eval_rouge1": 0.4348875537307479,
+      "eval_rouge2": 0.16312989568941516,
+      "eval_rougeL": 0.26082852541259915,
+      "eval_rougeLsum": 0.358369227586099,
+      "eval_runtime": 1733.5816,
+      "eval_samples_per_second": 0.577,
+      "eval_steps_per_second": 0.036,
+      "step": 2262
+    },
+    {
+      "epoch": 6.63129973474801,
+      "grad_norm": 3.3940606117248535,
+      "learning_rate": 7.721175674180988e-07,
+      "loss": 1.4188,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 117.259,
+      "eval_loss": 1.5626862049102783,
+      "eval_rouge1": 0.43666460369707594,
+      "eval_rouge2": 0.16469845252758708,
+      "eval_rougeL": 0.26181956536662193,
+      "eval_rougeLsum": 0.3620078400661802,
+      "eval_runtime": 1745.3989,
+      "eval_samples_per_second": 0.573,
+      "eval_steps_per_second": 0.036,
+      "step": 2639
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3770,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0123914662589235e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f34ec6b5ac1f76c3eb76409a66f3a1b6a46b9df800b05dcc12589e46fda25057
+size 5496