[Model] roberta-base-mrpc

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/mnt/lustre/zhangyunchen/transformers/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "mrpc",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067cd089de4dcc88812b86b91426d3a755bbda66d34cb2d62ea14027f770449a
+size 997304355

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80971b6c8251520f777c4dfb9d7688bdb64e130bd9694fbf0ccc5eb7b0768a8
+size 498679699

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd2f89b9973336dd382188a8697155183310fa5fb2c8f9679e296ae996f46061
+size 14659

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8395222c8dc331faa742bb05c15249792dfc4e1e6325c0607e91eb2cdbf54562
+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/roberta-base", "tokenizer_class": "RobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,135 @@
+{
+  "best_metric": 0.9044117647058824,
+  "best_model_checkpoint": "./fp32_3e_5/models/mrpc-roberta-base/checkpoint-700",
+  "epoch": 6.086956521739131,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.9139685476410734e-05,
+      "loss": 0.5703,
+      "step": 100
+    },
+    {
+      "epoch": 0.87,
+      "eval_accuracy": 0.8578431372549019,
+      "eval_combined_score": 0.8771358543417367,
+      "eval_f1": 0.8964285714285715,
+      "eval_loss": 0.34303969144821167,
+      "eval_runtime": 6.6616,
+      "eval_samples_per_second": 61.247,
+      "eval_steps_per_second": 1.951,
+      "step": 100
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.6364477335800183e-05,
+      "loss": 0.3621,
+      "step": 200
+    },
+    {
+      "epoch": 1.74,
+      "eval_accuracy": 0.8823529411764706,
+      "eval_combined_score": 0.8990712074303405,
+      "eval_f1": 0.9157894736842105,
+      "eval_loss": 0.32112017273902893,
+      "eval_runtime": 2.2189,
+      "eval_samples_per_second": 183.876,
+      "eval_steps_per_second": 5.859,
+      "step": 200
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 2.358926919518964e-05,
+      "loss": 0.2587,
+      "step": 300
+    },
+    {
+      "epoch": 2.61,
+      "eval_accuracy": 0.8529411764705882,
+      "eval_combined_score": 0.8756231306081754,
+      "eval_f1": 0.8983050847457628,
+      "eval_loss": 0.42085549235343933,
+      "eval_runtime": 2.3421,
+      "eval_samples_per_second": 174.202,
+      "eval_steps_per_second": 5.551,
+      "step": 300
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 2.0814061054579094e-05,
+      "loss": 0.1777,
+      "step": 400
+    },
+    {
+      "epoch": 3.48,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.35459786653518677,
+      "eval_runtime": 2.2787,
+      "eval_samples_per_second": 179.046,
+      "eval_steps_per_second": 5.705,
+      "step": 400
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 1.8038852913968547e-05,
+      "loss": 0.1116,
+      "step": 500
+    },
+    {
+      "epoch": 4.35,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9032765737874097,
+      "eval_f1": 0.9192982456140351,
+      "eval_loss": 0.5677690505981445,
+      "eval_runtime": 2.0042,
+      "eval_samples_per_second": 203.57,
+      "eval_steps_per_second": 6.486,
+      "step": 500
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 1.5263644773358002e-05,
+      "loss": 0.0879,
+      "step": 600
+    },
+    {
+      "epoch": 5.22,
+      "eval_accuracy": 0.8774509803921569,
+      "eval_combined_score": 0.8954728950403692,
+      "eval_f1": 0.9134948096885814,
+      "eval_loss": 0.5992270112037659,
+      "eval_runtime": 2.1523,
+      "eval_samples_per_second": 189.563,
+      "eval_steps_per_second": 6.04,
+      "step": 600
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 1.2488436632747456e-05,
+      "loss": 0.0643,
+      "step": 700
+    },
+    {
+      "epoch": 6.09,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.9176926080166581,
+      "eval_f1": 0.9309734513274337,
+      "eval_loss": 0.5864008069038391,
+      "eval_runtime": 2.0987,
+      "eval_samples_per_second": 194.406,
+      "eval_steps_per_second": 6.194,
+      "step": 700
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 10,
+  "total_flos": 1468685911019520.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3bd3365e983cb7fca13ac172cb46455cfd98ededf724963b871ac5d163fcfc2
+size 3055