GenRL LC-QuAD 1.0 model upload

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_gen_len": 16.492,
+    "eval_loss": 1.3707971572875977,
+    "eval_rouge1": 87.4745,
+    "eval_rouge2": 75.8987,
+    "eval_rougeL": 80.4706,
+    "eval_rougeLsum": 80.5497,
+    "eval_runtime": 98.5514,
+    "eval_samples": 994,
+    "eval_samples_per_second": 10.086,
+    "train_runtime": 5930.4108,
+    "train_samples": 3995,
+    "train_samples_per_second": 1.685
+}

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "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": 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_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,
+  "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
+    }
+  },
+  "transformers_version": "4.5.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_gen_len": 16.492,
+    "eval_loss": 1.3707971572875977,
+    "eval_rouge1": 87.4745,
+    "eval_rouge2": 75.8987,
+    "eval_rougeL": 80.4706,
+    "eval_rougeLsum": 80.5497,
+    "eval_runtime": 98.5514,
+    "eval_samples": 994,
+    "eval_samples_per_second": 10.086
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206e09096f5a4eced41a90863d782a0e821b365ee7421951e37d83e0139ab97c
+size 1625569391

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"}

train_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 10.0,
+    "train_runtime": 5930.4108,
+    "train_samples": 3995,
+    "train_samples_per_second": 1.685
+}

trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 9990,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.74974974974975e-05,
+      "loss": 0.6173,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.4994994994994996e-05,
+      "loss": 0.4542,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.24924924924925e-05,
+      "loss": 0.2895,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.998998998998999e-05,
+      "loss": 0.2248,
+      "step": 2000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 3.7487487487487486e-05,
+      "loss": 0.1654,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.498498498498499e-05,
+      "loss": 0.1603,
+      "step": 3000
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 3.2482482482482486e-05,
+      "loss": 0.1201,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.9979979979979983e-05,
+      "loss": 0.1236,
+      "step": 4000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.7477477477477483e-05,
+      "loss": 0.094,
+      "step": 4500
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 2.4974974974974976e-05,
+      "loss": 0.0905,
+      "step": 5000
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 2.2472472472472473e-05,
+      "loss": 0.081,
+      "step": 5500
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 1.996996996996997e-05,
+      "loss": 0.0672,
+      "step": 6000
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 1.746746746746747e-05,
+      "loss": 0.0576,
+      "step": 6500
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 1.4964964964964966e-05,
+      "loss": 0.0536,
+      "step": 7000
+    },
+    {
+      "epoch": 7.51,
+      "learning_rate": 1.2462462462462463e-05,
+      "loss": 0.0356,
+      "step": 7500
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 9.959959959959962e-06,
+      "loss": 0.0344,
+      "step": 8000
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 7.457457457457457e-06,
+      "loss": 0.0231,
+      "step": 8500
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 4.954954954954955e-06,
+      "loss": 0.0246,
+      "step": 9000
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 2.4524524524524525e-06,
+      "loss": 0.0143,
+      "step": 9500
+    },
+    {
+      "epoch": 10.0,
+      "step": 9990,
+      "total_flos": 3.1793177520881664e+16,
+      "train_runtime": 5930.4108,
+      "train_samples_per_second": 1.685
+    }
+  ],
+  "max_steps": 9990,
+  "num_train_epochs": 10,
+  "total_flos": 3.1793177520881664e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a08effb2c5948cab2e534c1eb92c0fd912087e196d9478afb40d4c85820d11
+size 2415