Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: facebook/bart-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: cu-go-bart-base-gc
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# cu-go-bart-base-gc
+
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5455
+- Rouge1: 53.0097
+- Rouge2: 29.8987
+- Rougel: 37.7495
+- Rougelsum: 49.1744
+- Gen Len: 106.6047
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len  |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
+| No log        | 1.0   | 86   | 1.6037          | 51.0086 | 27.7443 | 35.7708 | 47.0373   | 108.2442 |
+| No log        | 2.0   | 172  | 1.5580          | 53.4388 | 29.9039 | 37.6105 | 49.6511   | 109.1163 |
+| No log        | 3.0   | 258  | 1.5455          | 53.0097 | 29.8987 | 37.7495 | 49.1744   | 106.6047 |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 106.6046511627907,
+    "eval_loss": 1.5455105304718018,
+    "eval_rouge1": 53.0097,
+    "eval_rouge2": 29.8987,
+    "eval_rougeL": 37.7495,
+    "eval_rougeLsum": 49.1744,
+    "eval_runtime": 22.3667,
+    "eval_samples": 86,
+    "eval_samples_per_second": 3.845,
+    "eval_steps_per_second": 0.984,
+    "train_loss": 1.6933694292408552,
+    "train_runtime": 106.8575,
+    "train_samples": 342,
+    "train_samples_per_second": 9.602,
+    "train_steps_per_second": 2.414
+}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "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": 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,
+  "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,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "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": "4.35.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 106.6046511627907,
+    "eval_loss": 1.5455105304718018,
+    "eval_rouge1": 53.0097,
+    "eval_rouge2": 29.8987,
+    "eval_rougeL": 37.7495,
+    "eval_rougeLsum": 49.1744,
+    "eval_runtime": 22.3667,
+    "eval_samples": 86,
+    "eval_samples_per_second": 3.845,
+    "eval_steps_per_second": 0.984
+}

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": "4.35.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac746d88baaa25afd53a7be6db688703a990ac8300abae1c8da284ac17ab11a5
+size 557971229

runs/Nov15_16-47-05_node0385.palmetto.clemson.edu/events.out.tfevents.1700084839.node0385.palmetto.clemson.edu.552224.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f80c364a1ca5dcc22ecd869a8f5c4cb17a8aede7a96355d60d7a1d4e639a71
+size 7295

runs/Nov15_16-47-05_node0385.palmetto.clemson.edu/events.out.tfevents.1700084972.node0385.palmetto.clemson.edu.552224.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43bf1958a7579f75994f9eba5549b876b5cbc451836e7b80eea0c1936eb0a4c
+size 613

runs/Nov15_16-51-10_node0385.palmetto.clemson.edu/events.out.tfevents.1700085074.node0385.palmetto.clemson.edu.552718.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ba0547fa5f97003be6f0787222c257a413b63e683e78d55dc9486fa9881727
+size 7337

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": 3.0,
+    "train_loss": 1.6933694292408552,
+    "train_runtime": 106.8575,
+    "train_samples": 342,
+    "train_samples_per_second": 9.602,
+    "train_steps_per_second": 2.414
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 258,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 108.24418604651163,
+      "eval_loss": 1.6037122011184692,
+      "eval_rouge1": 51.0086,
+      "eval_rouge2": 27.7443,
+      "eval_rougeL": 35.7708,
+      "eval_rougeLsum": 47.0373,
+      "eval_runtime": 22.6647,
+      "eval_samples_per_second": 3.794,
+      "eval_steps_per_second": 0.971,
+      "step": 86
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 109.11627906976744,
+      "eval_loss": 1.5580047369003296,
+      "eval_rouge1": 53.4388,
+      "eval_rouge2": 29.9039,
+      "eval_rougeL": 37.6105,
+      "eval_rougeLsum": 49.6511,
+      "eval_runtime": 22.5195,
+      "eval_samples_per_second": 3.819,
+      "eval_steps_per_second": 0.977,
+      "step": 172
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 106.6046511627907,
+      "eval_loss": 1.5455105304718018,
+      "eval_rouge1": 53.0097,
+      "eval_rouge2": 29.8987,
+      "eval_rougeL": 37.7495,
+      "eval_rougeLsum": 49.1744,
+      "eval_runtime": 22.4754,
+      "eval_samples_per_second": 3.826,
+      "eval_steps_per_second": 0.979,
+      "step": 258
+    },
+    {
+      "epoch": 3.0,
+      "step": 258,
+      "total_flos": 583436809912320.0,
+      "train_loss": 1.6933694292408552,
+      "train_runtime": 106.8575,
+      "train_samples_per_second": 9.602,
+      "train_steps_per_second": 2.414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 258,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 583436809912320.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49296446bbc98a85a43233f93231bf758e895adfe9494fda5b2a99c0f4235f39
+size 4347