Upload 12 files

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.6782714297499838,
+    "train_runtime": 520.4144,
+    "train_samples": 2211,
+    "train_samples_per_second": 42.485,
+    "train_steps_per_second": 10.626
+}

config.json

@@ -0,0 +1,74 @@
+{
+  "_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": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "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": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "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": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "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": "4.37.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d998d280b93a3a05f19e570045b0f7f0e786b8cab31d88ce3e88ca4d620ea1c
+size 1625426996

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 +1,57 @@
+{
+  "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": true,
+      "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": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.6782714297499838,
+    "train_runtime": 520.4144,
+    "train_samples": 2211,
+    "train_samples_per_second": 42.485,
+    "train_steps_per_second": 10.626
+}

trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 5530,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.547920433996384e-05,
+      "loss": 2.5146,
+      "step": 500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.095840867992767e-05,
+      "loss": 1.4992,
+      "step": 1000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 3.6437613019891505e-05,
+      "loss": 1.0354,
+      "step": 1500
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 3.191681735985534e-05,
+      "loss": 0.7357,
+      "step": 2000
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 2.7396021699819167e-05,
+      "loss": 0.5078,
+      "step": 2500
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 2.2875226039783005e-05,
+      "loss": 0.3726,
+      "step": 3000
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 1.8354430379746836e-05,
+      "loss": 0.2824,
+      "step": 3500
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 1.383363471971067e-05,
+      "loss": 0.1955,
+      "step": 4000
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 9.312839059674505e-06,
+      "loss": 0.1599,
+      "step": 4500
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 4.792043399638336e-06,
+      "loss": 0.1064,
+      "step": 5000
+    },
+    {
+      "epoch": 9.95,
+      "learning_rate": 2.7124773960217e-07,
+      "loss": 0.088,
+      "step": 5500
+    },
+    {
+      "epoch": 10.0,
+      "step": 5530,
+      "total_flos": 1766784934699008.0,
+      "train_loss": 0.6782714297499838,
+      "train_runtime": 520.4144,
+      "train_samples_per_second": 42.485,
+      "train_steps_per_second": 10.626
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5530,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1766784934699008.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d09d469bf7a27f2f82c2f61a7bf07c0acb8054eebb66836e86fb6ca5051f7ff
+size 4920