finetune bart

config.json

@@ -0,0 +1,74 @@
+{
+  "_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_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": "4.11.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96416e3d1183343edc4b774d748cbba25b56f6390ca48a86025d91f45cb91afe
+size 1115513461

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc653f4ee13ad952cecf19fa0c60ab678e506552dbf653025063b24873cfa066
+size 557979193

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec6f91e6c66c40ddf9215c66a5a489cfc2e8f9f1cb65622c9f580fa6ef2a2e9
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27cfed17e5d3a4b92744fc5e719235b700be5cf6ef9177a64a4958f203c9d962
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_file": "/home/Mousumi/.cache/huggingface/transformers/a878fcd69bba037c9b1b227f4213579ae43d0aaa9374e167bc6c5f41b1cfeb30.fc9576039592f026ad76a1c231b89aee8668488c671dfbe6616bab2ed298d730", "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}

trainer_state.json

@@ -0,0 +1,238 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9216,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2e-05,
+      "loss": 9.4747,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4e-05,
+      "loss": 8.5089,
+      "step": 4
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.9315068493150684e-05,
+      "loss": 7.7975,
+      "step": 6
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.794520547945205e-05,
+      "loss": 7.2748,
+      "step": 8
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.657534246575342e-05,
+      "loss": 6.738,
+      "step": 10
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.520547945205479e-05,
+      "loss": 6.4144,
+      "step": 12
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.383561643835617e-05,
+      "loss": 5.924,
+      "step": 14
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.2465753424657536e-05,
+      "loss": 5.4519,
+      "step": 16
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.1095890410958905e-05,
+      "loss": 4.9919,
+      "step": 18
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.9726027397260274e-05,
+      "loss": 4.614,
+      "step": 20
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.8356164383561644e-05,
+      "loss": 4.3804,
+      "step": 22
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.698630136986301e-05,
+      "loss": 4.1981,
+      "step": 24
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.561643835616438e-05,
+      "loss": 4.0104,
+      "step": 26
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.424657534246575e-05,
+      "loss": 3.8835,
+      "step": 28
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.287671232876712e-05,
+      "loss": 3.7094,
+      "step": 30
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.1506849315068496e-05,
+      "loss": 3.617,
+      "step": 32
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.0136986301369862e-05,
+      "loss": 3.5407,
+      "step": 34
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8767123287671234e-05,
+      "loss": 3.4392,
+      "step": 36
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.7397260273972603e-05,
+      "loss": 3.321,
+      "step": 38
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.6027397260273973e-05,
+      "loss": 3.3597,
+      "step": 40
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.4657534246575342e-05,
+      "loss": 3.1786,
+      "step": 42
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.328767123287671e-05,
+      "loss": 3.1039,
+      "step": 44
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.1917808219178083e-05,
+      "loss": 3.0302,
+      "step": 46
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2.0547945205479453e-05,
+      "loss": 3.0034,
+      "step": 48
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.9178082191780822e-05,
+      "loss": 2.9383,
+      "step": 50
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.780821917808219e-05,
+      "loss": 2.9056,
+      "step": 52
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.643835616438356e-05,
+      "loss": 2.8352,
+      "step": 54
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.5068493150684931e-05,
+      "loss": 2.802,
+      "step": 56
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.3698630136986302e-05,
+      "loss": 2.7235,
+      "step": 58
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.2328767123287671e-05,
+      "loss": 2.7205,
+      "step": 60
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.0958904109589042e-05,
+      "loss": 2.6843,
+      "step": 62
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.589041095890411e-06,
+      "loss": 2.6673,
+      "step": 64
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.21917808219178e-06,
+      "loss": 2.6858,
+      "step": 66
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 6.849315068493151e-06,
+      "loss": 2.6202,
+      "step": 68
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.479452054794521e-06,
+      "loss": 2.6411,
+      "step": 70
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 4.10958904109589e-06,
+      "loss": 2.6201,
+      "step": 72
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.7397260273972604e-06,
+      "loss": 2.6119,
+      "step": 74
+    }
+  ],
+  "max_steps": 78,
+  "num_train_epochs": 2,
+  "total_flos": 1.171669578153984e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67c85be9a8ab2d1487d8552ed9a94754687de694df211eb99908f470ce3a8fa
+size 2799