Upload 10 files

data/hp_v3.4/all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 65251,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 558658048,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 1025143,
+    "train_mem_cpu_peaked_delta": 310156790,
+    "train_mem_gpu_alloc_delta": 2254198784,
+    "train_mem_gpu_peaked_delta": 6203317760,
+    "train_runtime": 126.2339,
+    "train_samples": 8633,
+    "train_samples_per_second": 4.111
+}

data/hp_v3.4/config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "examples/seq2seq/data/models/lcquad_v2",
+  "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
+    }
+  },
+  "transformers_version": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

data/hp_v3.4/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000209eb96b3f50b0f7419938c588405833661d56aa15faa1882d55ec9dc3ec3
+size 557985683

data/hp_v3.4/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}}

data/hp_v3.4/tokenizer_config.json

@@ -0,0 +1 @@
+{"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, "errors": "replace", "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, "name_or_path": "examples/seq2seq/data/models/lcquad_v2", "special_tokens_map_file": "examples/seq2seq/data/models/lcquad_v2/special_tokens_map.json"}

data/hp_v3.4/train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 65251,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 558658048,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 1025143,
+    "train_mem_cpu_peaked_delta": 310156790,
+    "train_mem_gpu_alloc_delta": 2254198784,
+    "train_mem_gpu_peaked_delta": 6203317760,
+    "train_runtime": 126.2339,
+    "train_samples": 8633,
+    "train_samples_per_second": 4.111
+}

data/hp_v3.4/trainer_state.json

@@ -0,0 +1,29 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 519,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.8304431599229288e-06,
+      "loss": 0.3103,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 519,
+      "total_flos": 1342070683845120.0,
+      "train_runtime": 126.2339,
+      "train_samples_per_second": 4.111
+    }
+  ],
+  "max_steps": 519,
+  "num_train_epochs": 3,
+  "total_flos": 1342070683845120.0,
+  "trial_name": null,
+  "trial_params": null
+}

data/hp_v3.4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6577c0683999cec9d0d69efb1c544dca50a15dc8b250d9d3cac808c85160ae6e
+size 2351