Model save

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: facebook/rag-sequence-nq
+tags:
+- generated_from_trainer
+datasets:
+- cqa_v1
+model-index:
+- name: rag_sequence_nq_on_cqa
+  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. -->
+
+# rag_sequence_nq_on_cqa
+
+This model is a fine-tuned version of [facebook/rag-sequence-nq](https://huggingface.co/facebook/rag-sequence-nq) on the cqa_v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 31.3296
+
+## 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: 3e-05
+- train_batch_size: 12
+- eval_batch_size: 12
+- seed: 47
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 1536
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: polynomial
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 6
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.9968 | 17   | 41.6343         |
+| No log        | 1.9936 | 34   | 36.0718         |
+| No log        | 2.9968 | 51   | 33.7388         |
+| No log        | 3.9936 | 68   | 32.4122         |
+| No log        | 4.9904 | 85   | 31.6654         |
+| No log        | 5.9872 | 102  | 31.3296         |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,228 @@
+{
+  "_name_or_path": "facebook/rag-sequence-nq",
+  "architectures": [
+    "RagSequenceForGeneration"
+  ],
+  "bad_words_ids": [
+    [
+      0,
+      0
+    ]
+  ],
+  "dataset": "wiki_dpr",
+  "dataset_revision": null,
+  "dataset_split": "train",
+  "do_deduplication": true,
+  "do_marginalize": false,
+  "doc_sep": " // ",
+  "exclude_bos_score": false,
+  "forced_eos_token_id": 2,
+  "generator": {
+    "_name_or_path": "",
+    "_num_labels": 3,
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_bias_logits": false,
+    "add_cross_attention": false,
+    "add_final_layer_norm": false,
+    "architectures": [
+      "BartForConditionalGeneration"
+    ],
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classif_dropout": 0.0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 12,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "extra_pos_embeddings": 2,
+    "finetuning_task": null,
+    "force_bos_token_to_be_generated": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "init_std": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1024,
+    "min_length": 0,
+    "model_type": "bart",
+    "no_repeat_ngram_size": 0,
+    "normalize_before": false,
+    "normalize_embedding": true,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": " ",
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "static_position_embeddings": false,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 142,
+        "min_length": 56,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4
+      }
+    },
+    "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,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "index_name": "exact",
+  "index_path": null,
+  "is_encoder_decoder": true,
+  "label_smoothing": 0.0,
+  "max_combined_length": 300,
+  "max_length": 50,
+  "min_length": 1,
+  "model_type": "rag",
+  "n_docs": 5,
+  "num_beams": 4,
+  "output_retrieved": false,
+  "passages_path": null,
+  "question_encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "DPRQuestionEncoder"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "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": null,
+    "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": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "dpr",
+    "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": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 0,
+    "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": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "reduce_loss": false,
+  "retrieval_batch_size": 8,
+  "retrieval_vector_size": 768,
+  "title_sep": " / ",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "use_dummy_dataset": true,
+  "vocab_size": null
+}

generation_config.json

@@ -0,0 +1,18 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      0,
+      0
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 50,
+  "min_length": 1,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.40.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6285b9bbc25ee5b95f98e544d11309706f1705f567ecba995f9688528c8d1744
+size 2061032996

runs/Aug03_00-02-02_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722614523.autodl-container-85074c9f82-4dcdba1e.3581.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a26d2144b33a4109d5b059420aea3a8f64929c19e6c4fa5e1779260991a2c2f6
+size 10034

runs/Aug03_00-11-34_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722615095.autodl-container-85074c9f82-4dcdba1e.6126.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df69255e13c2c936b2eff900ad85fb8fd8f5ea1d7b61b366a250f47dbbced83
+size 10034

runs/Aug03_00-20-29_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722615630.autodl-container-85074c9f82-4dcdba1e.8501.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a7f985b8004238c8f1c2183bd552548c5682091b6b32ff4121d7e47bc6d961
+size 10034

runs/Aug03_00-23-24_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722615805.autodl-container-85074c9f82-4dcdba1e.10573.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2298a1dd9e6c29137cc78b138e30a5bdbb5e8daee996024ae524441980808a7
+size 10034

runs/Aug03_00-25-37_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722615938.autodl-container-85074c9f82-4dcdba1e.12618.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75aa853234b7936dac19428e05ef2f4aed074928258d80af0f24563b6ee64244
+size 10036

runs/Aug03_00-31-22_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722616283.autodl-container-85074c9f82-4dcdba1e.14995.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846c0833493cc2bf2bc478c399fd8fecd7b7116e74b61d54c1e7c67a2e9018af
+size 10036

runs/Aug03_00-33-11_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722616392.autodl-container-85074c9f82-4dcdba1e.16535.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0cb28505626a1e3bbc5d4be9eb56af2d4d26b7882219ea034aa8fee98cff93
+size 10036

runs/Aug03_00-36-51_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722616612.autodl-container-85074c9f82-4dcdba1e.18583.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef89c69ad0e7a2e75ef32425b9df2d599325cc115e8a45488d3f1ec4f80b412
+size 10036

runs/Aug03_00-43-28_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722617008.autodl-container-85074c9f82-4dcdba1e.20779.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f43bce0a912b73eae888f2bdeb83a6c9119cacaabbcb4954cc2a31bddff76d
+size 10302

runs/Aug03_01-34-25_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722620065.autodl-container-85074c9f82-4dcdba1e.960181.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7008ec59b614fedd0b086aeb480c3100fc259c5f3170730f9b16cba1ea75e186
+size 10828

runs/Aug03_03-38-12_autodl-container-85074c9f82-4dcdba1e/events.out.tfevents.1722627496.autodl-container-85074c9f82-4dcdba1e.845721.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8152e036a54af1f92e08a420990092229622713c95edca75b65e56483713adda
+size 11442

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1454b09a4c6e2b59da66db904e177fed21fdb012457d4e75b3f6ff7aa16f4f47
+size 4667