[Model] bart-base-rte

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "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,
+  "finetuning_task": "rte",
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "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,
+  "problem_type": "single_label_classification",
+  "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": "4.16.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b7c7768305accd7c1f2128daccd0c1c57c3105fde9d96e5638cfaf80f5b0d2
+size 1120266491

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d7ca032c427618f35d967258eeb531dfc8d79b06c91b7025078166a4129131
+size 560154805

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dfc892aaf71fbe9c1adda36a41fd7a175e3b1ce274ae124754cd1ea5ba880c
+size 14659

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a41c04481e2e5a5a0284f29aaf4b3af7454b0139b56ff9406045c1632c35bf9
+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>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base", "tokenizer_class": "BartTokenizer"}

trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 16.666666666666668,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.941571524513096e-05,
+      "loss": 0.682,
+      "step": 100
+    },
+    {
+      "epoch": 1.28,
+      "eval_accuracy": 0.7003610108303249,
+      "eval_loss": 0.6075819134712219,
+      "eval_runtime": 3.25,
+      "eval_samples_per_second": 85.23,
+      "eval_steps_per_second": 2.769,
+      "step": 100
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 2.7400940228341167e-05,
+      "loss": 0.5556,
+      "step": 200
+    },
+    {
+      "epoch": 2.56,
+      "eval_accuracy": 0.6967509025270758,
+      "eval_loss": 0.5837834477424622,
+      "eval_runtime": 1.0394,
+      "eval_samples_per_second": 266.512,
+      "eval_steps_per_second": 8.659,
+      "step": 200
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 2.538616521155138e-05,
+      "loss": 0.3956,
+      "step": 300
+    },
+    {
+      "epoch": 3.85,
+      "eval_accuracy": 0.7653429602888087,
+      "eval_loss": 0.5577418208122253,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 269.751,
+      "eval_steps_per_second": 8.764,
+      "step": 300
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 2.3371390194761586e-05,
+      "loss": 0.2705,
+      "step": 400
+    },
+    {
+      "epoch": 5.13,
+      "eval_accuracy": 0.7472924187725631,
+      "eval_loss": 0.7243108153343201,
+      "eval_runtime": 1.0048,
+      "eval_samples_per_second": 275.666,
+      "eval_steps_per_second": 8.957,
+      "step": 400
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 2.1356615177971793e-05,
+      "loss": 0.1431,
+      "step": 500
+    },
+    {
+      "epoch": 6.41,
+      "eval_accuracy": 0.7581227436823105,
+      "eval_loss": 1.279666781425476,
+      "eval_runtime": 1.01,
+      "eval_samples_per_second": 274.262,
+      "eval_steps_per_second": 8.911,
+      "step": 500
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 1.9341840161182e-05,
+      "loss": 0.1032,
+      "step": 600
+    },
+    {
+      "epoch": 7.69,
+      "eval_accuracy": 0.7617328519855595,
+      "eval_loss": 1.1039319038391113,
+      "eval_runtime": 1.0386,
+      "eval_samples_per_second": 266.696,
+      "eval_steps_per_second": 8.665,
+      "step": 600
+    },
+    {
+      "epoch": 8.97,
+      "learning_rate": 1.7327065144392212e-05,
+      "loss": 0.0787,
+      "step": 700
+    },
+    {
+      "epoch": 8.97,
+      "eval_accuracy": 0.7653429602888087,
+      "eval_loss": 1.4732542037963867,
+      "eval_runtime": 1.4811,
+      "eval_samples_per_second": 187.028,
+      "eval_steps_per_second": 6.077,
+      "step": 700
+    },
+    {
+      "epoch": 10.26,
+      "learning_rate": 1.531229012760242e-05,
+      "loss": 0.0543,
+      "step": 800
+    },
+    {
+      "epoch": 10.26,
+      "eval_accuracy": 0.776173285198556,
+      "eval_loss": 1.4965362548828125,
+      "eval_runtime": 0.9908,
+      "eval_samples_per_second": 279.574,
+      "eval_steps_per_second": 9.084,
+      "step": 800
+    },
+    {
+      "epoch": 11.54,
+      "learning_rate": 1.3297515110812627e-05,
+      "loss": 0.0411,
+      "step": 900
+    },
+    {
+      "epoch": 11.54,
+      "eval_accuracy": 0.7725631768953068,
+      "eval_loss": 1.4953675270080566,
+      "eval_runtime": 1.0282,
+      "eval_samples_per_second": 269.415,
+      "eval_steps_per_second": 8.754,
+      "step": 900
+    },
+    {
+      "epoch": 12.82,
+      "learning_rate": 1.1282740094022835e-05,
+      "loss": 0.0335,
+      "step": 1000
+    },
+    {
+      "epoch": 12.82,
+      "eval_accuracy": 0.7689530685920578,
+      "eval_loss": 1.7958177328109741,
+      "eval_runtime": 1.0152,
+      "eval_samples_per_second": 272.858,
+      "eval_steps_per_second": 8.865,
+      "step": 1000
+    },
+    {
+      "epoch": 14.1,
+      "learning_rate": 9.267965077233043e-06,
+      "loss": 0.0236,
+      "step": 1100
+    },
+    {
+      "epoch": 14.1,
+      "eval_accuracy": 0.779783393501805,
+      "eval_loss": 1.6150606870651245,
+      "eval_runtime": 2.5651,
+      "eval_samples_per_second": 107.987,
+      "eval_steps_per_second": 3.509,
+      "step": 1100
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 7.253190060443251e-06,
+      "loss": 0.0132,
+      "step": 1200
+    },
+    {
+      "epoch": 15.38,
+      "eval_accuracy": 0.776173285198556,
+      "eval_loss": 2.066054582595825,
+      "eval_runtime": 1.0235,
+      "eval_samples_per_second": 270.642,
+      "eval_steps_per_second": 8.793,
+      "step": 1200
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 5.238415043653459e-06,
+      "loss": 0.0233,
+      "step": 1300
+    },
+    {
+      "epoch": 16.67,
+      "eval_accuracy": 0.7906137184115524,
+      "eval_loss": 1.6857606172561646,
+      "eval_runtime": 2.6037,
+      "eval_samples_per_second": 106.386,
+      "eval_steps_per_second": 3.457,
+      "step": 1300
+    }
+  ],
+  "max_steps": 1560,
+  "num_train_epochs": 20,
+  "total_flos": 3182186931732480.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c958de8a3cda80cf087908ad00e45144b1e2ded05952ab4f8146f2571e3e2e
+size 2991