model v1

config.json

@@ -0,0 +1,100 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "adapters": {
+    "adapters": {
+      "narrativeqa": "b1017368d7a97b11"
+    },
+    "config_map": {
+      "b1017368d7a97b11": {
+        "adapter_residual_before_ln": false,
+        "cross_adapter": false,
+        "inv_adapter": null,
+        "inv_adapter_reduction_factor": null,
+        "leave_out": [],
+        "ln_after": false,
+        "ln_before": false,
+        "mh_adapter": true,
+        "non_linearity": "swish",
+        "original_ln_after": true,
+        "original_ln_before": false,
+        "output_adapter": true,
+        "reduction_factor": 16,
+        "residual_before_ln": true
+      }
+    },
+    "fusion_config_map": {},
+    "fusions": {}
+  },
+  "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_length": 100,
+  "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": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c29e771c485cc43397918e6abe52ceab229e6ed30fe18f146aa3c6a6c1ea23e
+size 50862209

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb816166887207b7ea21185d167d6da0ba177f41baa00d82e300ed39c7a9637c
+size 1651044481

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f048bad90a2efb6cc0c5721b0518c125372847ef3b924127f0af48435cc1fd7
+size 14567

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2365d2f7d6d17d401755b5d0e71791ff68b94486ddb37364e00319aeebc6c91
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f8dcdd3dcb257460bce686c7aeef55f57856948c8e140ec3c404003f819b53
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large", "tokenizer_class": "BartTokenizer"}

trainer_state.json

@@ -0,0 +1,278 @@
+{
+  "best_metric": 5.976424694061279,
+  "best_model_checkpoint": "saved_models/narrativeqa_adaptertune/checkpoint-4092",
+  "epoch": 1.9996335654085746,
+  "global_step": 4092,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.968067774519389e-05,
+      "loss": 10.6425,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.935483870967742e-05,
+      "loss": 6.447,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.902899967416097e-05,
+      "loss": 6.2146,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.870316063864451e-05,
+      "loss": 6.1529,
+      "step": 400
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.837732160312806e-05,
+      "loss": 6.1086,
+      "step": 500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.80514825676116e-05,
+      "loss": 6.0845,
+      "step": 600
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.772564353209514e-05,
+      "loss": 6.065,
+      "step": 700
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.73998044965787e-05,
+      "loss": 6.0532,
+      "step": 800
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.707396546106225e-05,
+      "loss": 6.0406,
+      "step": 900
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.674812642554578e-05,
+      "loss": 6.0327,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.642228739002933e-05,
+      "loss": 6.023,
+      "step": 1100
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.609644835451288e-05,
+      "loss": 6.0156,
+      "step": 1200
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.577060931899642e-05,
+      "loss": 6.0196,
+      "step": 1300
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.544477028347996e-05,
+      "loss": 6.0088,
+      "step": 1400
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.51189312479635e-05,
+      "loss": 6.0029,
+      "step": 1500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.479309221244705e-05,
+      "loss": 6.0015,
+      "step": 1600
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.446725317693061e-05,
+      "loss": 6.0022,
+      "step": 1700
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.414141414141415e-05,
+      "loss": 5.9995,
+      "step": 1800
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.381557510589769e-05,
+      "loss": 5.9931,
+      "step": 1900
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.348973607038124e-05,
+      "loss": 5.9961,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.981632232666016,
+      "eval_rouge1": 0.4942,
+      "eval_rouge2": 0.2497,
+      "eval_rougeL": 0.489,
+      "eval_runtime": 642.0603,
+      "eval_samples_per_second": 10.781,
+      "eval_steps_per_second": 2.696,
+      "step": 2046
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.316389703486478e-05,
+      "loss": 6.0409,
+      "step": 2100
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.283805799934833e-05,
+      "loss": 5.9926,
+      "step": 2200
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 9.251221896383187e-05,
+      "loss": 5.9925,
+      "step": 2300
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 9.218963831867058e-05,
+      "loss": 5.9883,
+      "step": 2400
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 9.186379928315413e-05,
+      "loss": 5.9822,
+      "step": 2500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 9.153796024763767e-05,
+      "loss": 5.9871,
+      "step": 2600
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 9.121212121212121e-05,
+      "loss": 5.9836,
+      "step": 2700
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 9.088628217660477e-05,
+      "loss": 5.9832,
+      "step": 2800
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 9.05604431410883e-05,
+      "loss": 5.9885,
+      "step": 2900
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 9.023460410557186e-05,
+      "loss": 5.9866,
+      "step": 3000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 8.99087650700554e-05,
+      "loss": 5.9802,
+      "step": 3100
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 8.958292603453894e-05,
+      "loss": 5.9789,
+      "step": 3200
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 8.925708699902249e-05,
+      "loss": 5.9857,
+      "step": 3300
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.893124796350603e-05,
+      "loss": 5.9781,
+      "step": 3400
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.860540892798957e-05,
+      "loss": 5.9747,
+      "step": 3500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 8.827956989247312e-05,
+      "loss": 5.9757,
+      "step": 3600
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 8.795373085695668e-05,
+      "loss": 5.9775,
+      "step": 3700
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 8.762789182144022e-05,
+      "loss": 5.9787,
+      "step": 3800
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 8.730205278592376e-05,
+      "loss": 5.9827,
+      "step": 3900
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 8.69762137504073e-05,
+      "loss": 5.9755,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.976424694061279,
+      "eval_rouge1": 0.5089,
+      "eval_rouge2": 0.2563,
+      "eval_rougeL": 0.5034,
+      "eval_runtime": 639.6582,
+      "eval_samples_per_second": 10.821,
+      "eval_steps_per_second": 2.706,
+      "step": 4092
+    }
+  ],
+  "max_steps": 30690,
+  "num_train_epochs": 15,
+  "total_flos": 1.727047442376622e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceffd1a1b30d80d345b19e5563597de905436a28d7790560a5c1b9f15ab3cda7
+size 2991