Upload folder using huggingface_hub

config.json

@@ -0,0 +1,191 @@
+{
+  "_name_or_path": "patrickvonplaten/longformer2roberta-cnn_dailymail-fp16",
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "add_cross_attention": true,
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 514,
+    "min_length": 0,
+    "model_type": "roberta",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": false,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_mode": "longformer",
+    "attention_probs_dropout_prob": 0.1,
+    "attention_window": [
+      512,
+      512,
+      512,
+      512,
+      512,
+      512,
+      512,
+      512,
+      512,
+      512,
+      512,
+      512
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "ignore_attention_mask": false,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4098,
+    "min_length": 0,
+    "model_type": "longformer",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "onnx_export": false,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": false,
+    "return_dict_in_generate": false,
+    "sep_token_id": 2,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "max_length": 142,
+  "min_length": 56,
+  "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "pad_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2"
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "pad_token_id": 2,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb05608c8b8005f5087594c3a6f2330253362cb72fea03fb9cb16b9b1e09194
+size 1206970564

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2ebb1591ef1a20f8897488d28efa828009af1874a9a5e57860496060677d58
+size 2239409895

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e3eef43f957931c5614324f467dce8c5ea37af114c6a63121c406d42ad70a8
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea6e784ffec92ecfd0b1ceeed21fd8c7222a59e62100bb23df569ad3c19077d
+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": false,
+    "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 +1,57 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "unk_token": "<unk>",
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 397,
+  "global_step": 2384,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "eval_gen_len": 81.6102,
+      "eval_loss": 1.3396695852279663,
+      "eval_rouge1": 52.6908,
+      "eval_rouge2": 34.3367,
+      "eval_rougeL": 43.9351,
+      "eval_rougeLsum": 44.0153,
+      "eval_runtime": 41.4692,
+      "eval_samples_per_second": 1.423,
+      "eval_steps_per_second": 0.723,
+      "step": 397
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 6.220447063446045,
+      "learning_rate": 1.895763422818792e-05,
+      "loss": 0.719,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "eval_gen_len": 84.2203,
+      "eval_loss": 1.363059639930725,
+      "eval_rouge1": 54.543,
+      "eval_rouge2": 36.4199,
+      "eval_rougeL": 45.8273,
+      "eval_rougeLsum": 45.7925,
+      "eval_runtime": 42.2281,
+      "eval_samples_per_second": 1.397,
+      "eval_steps_per_second": 0.71,
+      "step": 794
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 8.490495681762695,
+      "learning_rate": 1.7908976510067115e-05,
+      "loss": 0.7459,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5,
+      "eval_gen_len": 85.2373,
+      "eval_loss": 1.3582559823989868,
+      "eval_rouge1": 53.2262,
+      "eval_rouge2": 34.8889,
+      "eval_rougeL": 44.1043,
+      "eval_rougeLsum": 44.0998,
+      "eval_runtime": 42.6328,
+      "eval_samples_per_second": 1.384,
+      "eval_steps_per_second": 0.704,
+      "step": 1191
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 6.794929027557373,
+      "learning_rate": 1.686031879194631e-05,
+      "loss": 0.7154,
+      "step": 1500
+    },
+    {
+      "epoch": 0.67,
+      "eval_gen_len": 83.7797,
+      "eval_loss": 1.3886514902114868,
+      "eval_rouge1": 54.9928,
+      "eval_rouge2": 37.1125,
+      "eval_rougeL": 46.4105,
+      "eval_rougeLsum": 46.4044,
+      "eval_runtime": 42.3464,
+      "eval_samples_per_second": 1.393,
+      "eval_steps_per_second": 0.708,
+      "step": 1588
+    },
+    {
+      "epoch": 0.83,
+      "eval_gen_len": 85.8814,
+      "eval_loss": 1.3405011892318726,
+      "eval_rouge1": 52.5543,
+      "eval_rouge2": 33.702,
+      "eval_rougeL": 42.9428,
+      "eval_rougeLsum": 43.0015,
+      "eval_runtime": 43.1199,
+      "eval_samples_per_second": 1.368,
+      "eval_steps_per_second": 0.696,
+      "step": 1985
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 8.691970825195312,
+      "learning_rate": 1.5811661073825504e-05,
+      "loss": 0.7507,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 81.7797,
+      "eval_loss": 1.3399206399917603,
+      "eval_rouge1": 52.4327,
+      "eval_rouge2": 34.1158,
+      "eval_rougeL": 43.2742,
+      "eval_rougeLsum": 43.1693,
+      "eval_runtime": 41.935,
+      "eval_samples_per_second": 1.407,
+      "eval_steps_per_second": 0.715,
+      "step": 2382
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 1192,
+  "total_flos": 5.17811143698432e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4e5ae08c2abdcb5ffb7b68b3ee7ae6c985193d6b10476bae766aeb2165fe26
+size 4984