Upload folder using huggingface_hub

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "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,
+  "forced_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
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": null,
+  "normalize_before": false,
+  "num_beams": null,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "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:b8770fb82fec082fc4d4b893093aba13de800ccc1b48acb183a6c26d6ac4effe
+size 1625426996

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b992018e3b8c3a4bf100e3d8b3c8f6d93141f34fb9f7d55d8a14f487b5a5679
+size 3250759951

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d4364ec9a1b053d9c846510711a88d8d2ccc60a3ae80a56aff6b89855e8e7c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8251667053b6be27c7ad9b5d412233e9117fb4d34df2a3df45aff58917bfed6d
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 1.693805456161499,
+  "best_model_checkpoint": "./BART/checkpoint-3080",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 3080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.8580667972564697,
+      "eval_rouge1": 15.4451,
+      "eval_rouge2": 7.2478,
+      "eval_rougeL": 13.17,
+      "eval_rougeLsum": 14.0774,
+      "eval_runtime": 9.1697,
+      "eval_samples_per_second": 10.905,
+      "eval_steps_per_second": 0.763,
+      "step": 440
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 3.0643959045410156,
+      "learning_rate": 1.9843637462342498e-05,
+      "loss": 1.9394,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.7797517776489258,
+      "eval_rouge1": 15.3282,
+      "eval_rouge2": 7.1147,
+      "eval_rougeL": 13.0747,
+      "eval_rougeLsum": 14.2107,
+      "eval_runtime": 9.0361,
+      "eval_samples_per_second": 11.067,
+      "eval_steps_per_second": 0.775,
+      "step": 880
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 5.788974761962891,
+      "learning_rate": 1.937447803209855e-05,
+      "loss": 1.6636,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.7304754257202148,
+      "eval_rouge1": 15.6545,
+      "eval_rouge2": 6.9151,
+      "eval_rougeL": 13.0932,
+      "eval_rougeLsum": 14.3822,
+      "eval_runtime": 9.2209,
+      "eval_samples_per_second": 10.845,
+      "eval_steps_per_second": 0.759,
+      "step": 1320
+    },
+    {
+      "epoch": 3.409090909090909,
+      "grad_norm": 3.81870698928833,
+      "learning_rate": 1.860742027003944e-05,
+      "loss": 1.5132,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.7133750915527344,
+      "eval_rouge1": 16.2201,
+      "eval_rouge2": 8.0653,
+      "eval_rougeL": 14.0536,
+      "eval_rougeLsum": 15.088,
+      "eval_runtime": 7.0109,
+      "eval_samples_per_second": 14.264,
+      "eval_steps_per_second": 0.998,
+      "step": 1760
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 2.5344793796539307,
+      "learning_rate": 1.756683942425267e-05,
+      "loss": 1.404,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.7092199325561523,
+      "eval_rouge1": 16.1558,
+      "eval_rouge2": 7.4414,
+      "eval_rougeL": 13.6423,
+      "eval_rougeLsum": 14.6771,
+      "eval_runtime": 7.0032,
+      "eval_samples_per_second": 14.279,
+      "eval_steps_per_second": 1.0,
+      "step": 2200
+    },
+    {
+      "epoch": 5.681818181818182,
+      "grad_norm": 2.570192575454712,
+      "learning_rate": 1.6285802647599156e-05,
+      "loss": 1.3153,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.6954882144927979,
+      "eval_rouge1": 15.8485,
+      "eval_rouge2": 7.8577,
+      "eval_rougeL": 13.518,
+      "eval_rougeLsum": 14.7491,
+      "eval_runtime": 6.9893,
+      "eval_samples_per_second": 14.308,
+      "eval_steps_per_second": 1.002,
+      "step": 2640
+    },
+    {
+      "epoch": 6.818181818181818,
+      "grad_norm": 2.7792255878448486,
+      "learning_rate": 1.4805018203243235e-05,
+      "loss": 1.2473,
+      "step": 3000
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 21.0,
+      "eval_loss": 1.693805456161499,
+      "eval_rouge1": 17.0591,
+      "eval_rouge2": 8.3853,
+      "eval_rougeL": 14.3266,
+      "eval_rougeLsum": 15.6269,
+      "eval_runtime": 6.9975,
+      "eval_samples_per_second": 14.291,
+      "eval_steps_per_second": 1.0,
+      "step": 3080
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 4,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0664321746993152e+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 sha256:36a09e97da930f814b813ad95c6fd7306060672dc182a2987c3618064af56792
+size 5432