Upload 10 files

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": "INTP",
+    "1": "ISTP",
+    "2": "ENTP",
+    "3": "ESTP",
+    "4": "INFP",
+    "5": "ISFP",
+    "6": "ENFP",
+    "7": "ESFP",
+    "8": "INTJ",
+    "9": "ISTJ",
+    "10": "ENTJ",
+    "11": "ESTJ",
+    "12": "INFJ",
+    "13": "ISFJ",
+    "14": "ENFJ",
+    "15": "ESFJ"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "INTP": 0,
+    "ISTP": 1,
+    "ENTJ": 10,
+    "ESTJ": 11,
+    "INFJ": 12,
+    "ISFJ": 13,
+    "ENFJ": 14,
+    "ESFJ": 15,
+    "ENTP": 2,
+    "ESTP": 3,
+    "INFP": 4,
+    "ISFP": 5,
+    "ENFP": 6,
+    "ESFP": 7,
+    "INTJ": 8,
+    "ISTJ": 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
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b74c5e232bf904305f1e1f800cf0dcbfdf99a4434908cc6c0f4d0fed3b5dfc
+size 93584149

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082516957a9fe7383c32b8fff025245a4f62c116bc7e59c88abcb552b4f541cc
+size 46797739

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d136840ca3b1d61213c4b1444da6787b357e4ebbb50606cfe85687a691d69448
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbaa9be744d43d7447b6fdf879400534163304c6a3a483d44e7e8dd776b927ce
+size 623

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>"
+}

spiece.model

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

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>"
+}

trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.5,
+  "global_step": 13000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.95e-05,
+      "loss": 2.5291,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9e-05,
+      "loss": 2.5099,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8500000000000002e-05,
+      "loss": 2.4884,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.8e-05,
+      "loss": 2.487,
+      "step": 2000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 2.4754,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.7e-05,
+      "loss": 2.465,
+      "step": 3000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.65e-05,
+      "loss": 2.4567,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.4565,
+      "step": 4000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.55e-05,
+      "loss": 2.4296,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.4324,
+      "step": 5000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.45e-05,
+      "loss": 2.4161,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.4e-05,
+      "loss": 2.4061,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.4308149814605713,
+      "eval_runtime": 90.0551,
+      "eval_samples_per_second": 177.669,
+      "eval_steps_per_second": 11.104,
+      "step": 6000
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 2.349,
+      "step": 6500
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 2.3544,
+      "step": 7000
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.25e-05,
+      "loss": 2.3463,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2e-05,
+      "loss": 2.3461,
+      "step": 8000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.4396936893463135,
+      "eval_runtime": 90.0717,
+      "eval_samples_per_second": 177.636,
+      "eval_steps_per_second": 11.102,
+      "step": 8000
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 1.15e-05,
+      "loss": 2.2347,
+      "step": 8500
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 2.2444,
+      "step": 9000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 1.0500000000000001e-05,
+      "loss": 2.2319,
+      "step": 9500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1e-05,
+      "loss": 2.2281,
+      "step": 10000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.4722118377685547,
+      "eval_runtime": 90.0452,
+      "eval_samples_per_second": 177.689,
+      "eval_steps_per_second": 11.106,
+      "step": 10000
+    },
+    {
+      "epoch": 5.25,
+      "learning_rate": 9.5e-06,
+      "loss": 2.0556,
+      "step": 10500
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 9e-06,
+      "loss": 2.0456,
+      "step": 11000
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 8.5e-06,
+      "loss": 2.0644,
+      "step": 11500
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.0578,
+      "step": 12000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.577911376953125,
+      "eval_runtime": 90.5865,
+      "eval_samples_per_second": 176.627,
+      "eval_steps_per_second": 11.039,
+      "step": 12000
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.804,
+      "step": 12500
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 7e-06,
+      "loss": 1.8018,
+      "step": 13000
+    }
+  ],
+  "max_steps": 20000,
+  "num_train_epochs": 10,
+  "total_flos": 6495300778518528.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29567d7fad5f03a4a693b0c19a34e63372710260a7f0a5c557787e9c6f5d46e3
+size 3503