End of training

README.md

@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+base_model: facebook/bart-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: BARTModel_for_Ecommerce
+  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. -->
+
+# BARTModel_for_Ecommerce
+
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6400
+- Rouge1: 0.3515
+- Rouge2: 0.2381
+- Rougel: 0.3187
+- Rougelsum: 0.3187
+- Gen Len: 20.0
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| No log        | 1.0   | 27   | 3.5206          | 0.3072 | 0.1595 | 0.26   | 0.26      | 20.0    |
+| No log        | 2.0   | 54   | 2.3786          | 0.3139 | 0.1747 | 0.268  | 0.2681    | 20.0    |
+| No log        | 3.0   | 81   | 1.8443          | 0.3328 | 0.2038 | 0.2924 | 0.2932    | 20.0    |
+| No log        | 4.0   | 108  | 1.4537          | 0.3276 | 0.2076 | 0.2887 | 0.2892    | 20.0    |
+| No log        | 5.0   | 135  | 1.1480          | 0.3301 | 0.212  | 0.292  | 0.2924    | 20.0    |
+| No log        | 6.0   | 162  | 0.9457          | 0.3465 | 0.2292 | 0.3084 | 0.3091    | 20.0    |
+| No log        | 7.0   | 189  | 0.8317          | 0.345  | 0.2253 | 0.3074 | 0.3078    | 20.0    |
+| No log        | 8.0   | 216  | 0.7544          | 0.3456 | 0.2293 | 0.3121 | 0.3124    | 20.0    |
+| No log        | 9.0   | 243  | 0.7076          | 0.3601 | 0.246  | 0.3278 | 0.3276    | 20.0    |
+| No log        | 10.0  | 270  | 0.6817          | 0.3464 | 0.2358 | 0.3139 | 0.3139    | 20.0    |
+| No log        | 11.0  | 297  | 0.6609          | 0.3586 | 0.2407 | 0.3235 | 0.3241    | 20.0    |
+| No log        | 12.0  | 324  | 0.6557          | 0.3563 | 0.2432 | 0.3226 | 0.3227    | 20.0    |
+| No log        | 13.0  | 351  | 0.6451          | 0.3511 | 0.238  | 0.3192 | 0.3195    | 20.0    |
+| No log        | 14.0  | 378  | 0.6430          | 0.3516 | 0.2385 | 0.3182 | 0.3183    | 20.0    |
+| No log        | 15.0  | 405  | 0.6400          | 0.3515 | 0.2381 | 0.3187 | 0.3187    | 20.0    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

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": "4.35.2",
+  "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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61674a1e13b1576b5b32b2369cab442bd76a3b6f8271c832d4b5dfcd8615412a
+size 557912620

runs/Dec26_16-03-09_25cffca0aae5/events.out.tfevents.1703606590.25cffca0aae5.325.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92679cf84aaa42fa0174c729b58862612d93600b3e21267aa78b9110fd9d5855
+size 13651

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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81f6fcbf9f3b74015ba76bf42119f30779f73874098aef652fac7fb9215eebc
+size 4728