[Model] bart-base-cola

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": "cola",
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "unacceptable",
+    "1": "acceptable"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "acceptable": 1,
+    "unacceptable": 0
+  },
+  "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 sha256:847dd3b004891e595d7791c01019d2983f77384d50c9f6abc227c64e74bb98bf
+size 1120266491

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85bb0f3b54c44af4b79a488efde4248a095de99fbe08d638d992b9af06f627b
+size 560154805

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7715ad3397c0c55c7b0871bf46cea42f26454b4139462854c332a4f6619eba6
+size 14659

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e0189f63e54dfab03937ea72158839b1c69101258a3d6704f3be974933751e
+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 +1,181 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.208955223880597,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.92749244712991e-05,
+      "loss": 0.5968,
+      "step": 200
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.5482025742530823,
+      "eval_matthews_correlation": 0.4044551659076911,
+      "eval_runtime": 7.0014,
+      "eval_samples_per_second": 148.97,
+      "eval_steps_per_second": 4.713,
+      "step": 200
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.8066465256797584e-05,
+      "loss": 0.4748,
+      "step": 400
+    },
+    {
+      "epoch": 1.49,
+      "eval_loss": 0.7374169826507568,
+      "eval_matthews_correlation": 0.295093127326412,
+      "eval_runtime": 4.195,
+      "eval_samples_per_second": 248.628,
+      "eval_steps_per_second": 7.866,
+      "step": 400
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.685800604229608e-05,
+      "loss": 0.4165,
+      "step": 600
+    },
+    {
+      "epoch": 2.24,
+      "eval_loss": 0.7154484391212463,
+      "eval_matthews_correlation": 0.4656950548188858,
+      "eval_runtime": 4.0204,
+      "eval_samples_per_second": 259.424,
+      "eval_steps_per_second": 8.208,
+      "step": 600
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 3.564954682779456e-05,
+      "loss": 0.3461,
+      "step": 800
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 0.5880667567253113,
+      "eval_matthews_correlation": 0.4966579188966687,
+      "eval_runtime": 4.1325,
+      "eval_samples_per_second": 252.389,
+      "eval_steps_per_second": 7.985,
+      "step": 800
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 3.4441087613293056e-05,
+      "loss": 0.2666,
+      "step": 1000
+    },
+    {
+      "epoch": 3.73,
+      "eval_loss": 0.6024960875511169,
+      "eval_matthews_correlation": 0.5243351914860497,
+      "eval_runtime": 4.2714,
+      "eval_samples_per_second": 244.185,
+      "eval_steps_per_second": 7.726,
+      "step": 1000
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 3.323262839879154e-05,
+      "loss": 0.233,
+      "step": 1200
+    },
+    {
+      "epoch": 4.48,
+      "eval_loss": 0.7757831811904907,
+      "eval_matthews_correlation": 0.5180330680945964,
+      "eval_runtime": 5.4027,
+      "eval_samples_per_second": 193.052,
+      "eval_steps_per_second": 6.108,
+      "step": 1200
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 3.2024169184290035e-05,
+      "loss": 0.2067,
+      "step": 1400
+    },
+    {
+      "epoch": 5.22,
+      "eval_loss": 0.8261585831642151,
+      "eval_matthews_correlation": 0.4812305179480984,
+      "eval_runtime": 4.5778,
+      "eval_samples_per_second": 227.84,
+      "eval_steps_per_second": 7.209,
+      "step": 1400
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 3.081570996978852e-05,
+      "loss": 0.174,
+      "step": 1600
+    },
+    {
+      "epoch": 5.97,
+      "eval_loss": 1.0030035972595215,
+      "eval_matthews_correlation": 0.4690871215881841,
+      "eval_runtime": 4.1699,
+      "eval_samples_per_second": 250.124,
+      "eval_steps_per_second": 7.914,
+      "step": 1600
+    },
+    {
+      "epoch": 6.72,
+      "learning_rate": 2.9607250755287014e-05,
+      "loss": 0.1504,
+      "step": 1800
+    },
+    {
+      "epoch": 6.72,
+      "eval_loss": 1.007808804512024,
+      "eval_matthews_correlation": 0.505928717066083,
+      "eval_runtime": 5.5718,
+      "eval_samples_per_second": 187.193,
+      "eval_steps_per_second": 5.923,
+      "step": 1800
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 2.83987915407855e-05,
+      "loss": 0.1261,
+      "step": 2000
+    },
+    {
+      "epoch": 7.46,
+      "eval_loss": 1.0862607955932617,
+      "eval_matthews_correlation": 0.4929950873963667,
+      "eval_runtime": 4.1938,
+      "eval_samples_per_second": 248.698,
+      "eval_steps_per_second": 7.869,
+      "step": 2000
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 2.719033232628399e-05,
+      "loss": 0.1141,
+      "step": 2200
+    },
+    {
+      "epoch": 8.21,
+      "eval_loss": 0.9651995301246643,
+      "eval_matthews_correlation": 0.5632084517291658,
+      "eval_runtime": 4.2997,
+      "eval_samples_per_second": 242.575,
+      "eval_steps_per_second": 7.675,
+      "step": 2200
+    }
+  ],
+  "max_steps": 6700,
+  "num_train_epochs": 25,
+  "total_flos": 5382361281024000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21a436b6e8570df92e245a5b6f68672b3b1e04d27eed2a48a376a683ef2c570
+size 2991