fine-tuned 16-fold MBTI classifier

checkpoint-17500/config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

checkpoint-17500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b9898d12316086420a0716106435c976080c9beba55580bdf7c364861cdc81
+size 93584149

checkpoint-17500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e92435cfefc360a88297fd6232aae1014995dbd85fed81e1ac79b69b8ed977
+size 46797739

checkpoint-17500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6077cc822c626f39a548d319a5014ba9fb607ae2809276d8055c7589759fa5e5
+size 14657

checkpoint-17500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1943902b01c5006061d1b3c3377e5df8ad6016474efcca36ec96358c450f91a
+size 623

checkpoint-17500/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

checkpoint-17500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

checkpoint-17500/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "albert-base-v2",
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-17500/trainer_state.json

@@ -0,0 +1,298 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.84251968503937,
+  "global_step": 17500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.943757030371204e-05,
+      "loss": 2.7683,
+      "step": 500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8875140607424075e-05,
+      "loss": 2.7344,
+      "step": 1000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.831271091113611e-05,
+      "loss": 2.7195,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.712266206741333,
+      "eval_runtime": 91.7259,
+      "eval_samples_per_second": 174.433,
+      "eval_steps_per_second": 10.902,
+      "step": 1778
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.7750281214848145e-05,
+      "loss": 2.6796,
+      "step": 2000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.7187851518560182e-05,
+      "loss": 2.6488,
+      "step": 2500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.6625421822272215e-05,
+      "loss": 2.6372,
+      "step": 3000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.6062992125984255e-05,
+      "loss": 2.6415,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.652708053588867,
+      "eval_runtime": 91.7276,
+      "eval_samples_per_second": 174.43,
+      "eval_steps_per_second": 10.902,
+      "step": 3556
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.550056242969629e-05,
+      "loss": 2.5601,
+      "step": 4000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.4938132733408325e-05,
+      "loss": 2.5407,
+      "step": 4500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.437570303712036e-05,
+      "loss": 2.5308,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.6422665119171143,
+      "eval_runtime": 91.7218,
+      "eval_samples_per_second": 174.441,
+      "eval_steps_per_second": 10.903,
+      "step": 5334
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 1.3813273340832395e-05,
+      "loss": 2.4873,
+      "step": 5500
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 1.3250843644544434e-05,
+      "loss": 2.3694,
+      "step": 6000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.2688413948256469e-05,
+      "loss": 2.3697,
+      "step": 6500
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 1.2125984251968505e-05,
+      "loss": 2.3628,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.685481548309326,
+      "eval_runtime": 91.7025,
+      "eval_samples_per_second": 174.477,
+      "eval_steps_per_second": 10.905,
+      "step": 7112
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 1.156355455568054e-05,
+      "loss": 2.1747,
+      "step": 7500
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 1.1001124859392579e-05,
+      "loss": 2.1037,
+      "step": 8000
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 1.0438695163104614e-05,
+      "loss": 2.1293,
+      "step": 8500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.817112445831299,
+      "eval_runtime": 91.7137,
+      "eval_samples_per_second": 174.456,
+      "eval_steps_per_second": 10.904,
+      "step": 8890
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 9.876265466816649e-06,
+      "loss": 2.0307,
+      "step": 9000
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 9.313835770528684e-06,
+      "loss": 1.7546,
+      "step": 9500
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 8.75140607424072e-06,
+      "loss": 1.752,
+      "step": 10000
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 8.188976377952757e-06,
+      "loss": 1.7463,
+      "step": 10500
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.0516531467437744,
+      "eval_runtime": 91.7177,
+      "eval_samples_per_second": 174.448,
+      "eval_steps_per_second": 10.903,
+      "step": 10668
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 7.626546681664793e-06,
+      "loss": 1.4932,
+      "step": 11000
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 7.064116985376829e-06,
+      "loss": 1.3659,
+      "step": 11500
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 6.501687289088865e-06,
+      "loss": 1.3485,
+      "step": 12000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.350566864013672,
+      "eval_runtime": 91.704,
+      "eval_samples_per_second": 174.474,
+      "eval_steps_per_second": 10.905,
+      "step": 12446
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 5.9392575928009e-06,
+      "loss": 1.3203,
+      "step": 12500
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 5.376827896512936e-06,
+      "loss": 1.0176,
+      "step": 13000
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 4.814398200224972e-06,
+      "loss": 0.9999,
+      "step": 13500
+    },
+    {
+      "epoch": 7.87,
+      "learning_rate": 4.251968503937008e-06,
+      "loss": 0.9889,
+      "step": 14000
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.6804659366607666,
+      "eval_runtime": 91.7068,
+      "eval_samples_per_second": 174.469,
+      "eval_steps_per_second": 10.904,
+      "step": 14224
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 3.689538807649044e-06,
+      "loss": 0.8533,
+      "step": 14500
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 3.12710911136108e-06,
+      "loss": 0.7315,
+      "step": 15000
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 2.5646794150731156e-06,
+      "loss": 0.7194,
+      "step": 15500
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.002249718785152e-06,
+      "loss": 0.7069,
+      "step": 16000
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.918808698654175,
+      "eval_runtime": 91.7922,
+      "eval_samples_per_second": 174.307,
+      "eval_steps_per_second": 10.894,
+      "step": 16002
+    },
+    {
+      "epoch": 9.28,
+      "learning_rate": 1.4398200224971882e-06,
+      "loss": 0.5375,
+      "step": 16500
+    },
+    {
+      "epoch": 9.56,
+      "learning_rate": 8.77390326209224e-07,
+      "loss": 0.533,
+      "step": 17000
+    },
+    {
+      "epoch": 9.84,
+      "learning_rate": 3.149606299212599e-07,
+      "loss": 0.5276,
+      "step": 17500
+    }
+  ],
+  "max_steps": 17780,
+  "num_train_epochs": 10,
+  "total_flos": 9948470041336704.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-17500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89dbca91b1a91d9cc84ccf2eca657cabe66ae6337d1891e925c2989736e53cd1
+size 3503