model upload

README.md

@@ -1,3 +1,54 @@
 ---
-license: apache-2.0
+license: mit
+base_model: xlnet-base-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: mlm_modelxlnet
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mlm_modelxlnet
+
+This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1944
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.14.0

added_tokens.json

@@ -0,0 +1,11 @@
+{
+  "</s>": 2,
+  "<cls>": 3,
+  "<eod>": 7,
+  "<eop>": 8,
+  "<mask>": 6,
+  "<pad>": 5,
+  "<s>": 1,
+  "<sep>": 4,
+  "<unk>": 0
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.1944403648376465,
+    "eval_runtime": 83.9431,
+    "eval_samples": 3913,
+    "eval_samples_per_second": 46.615,
+    "eval_steps_per_second": 1.465,
+    "perplexity": 8.97497693843778,
+    "train_loss": 2.733830861908257,
+    "train_runtime": 14258.7293,
+    "train_samples": 97236,
+    "train_samples_per_second": 20.458,
+    "train_steps_per_second": 0.639
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "xlnet-base-cased",
+  "architectures": [
+    "XLNetLMHeadModel"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.1944403648376465,
+    "eval_runtime": 83.9431,
+    "eval_samples": 3913,
+    "eval_samples_per_second": 46.615,
+    "eval_steps_per_second": 1.465,
+    "perplexity": 8.97497693843778
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 5,
+  "transformers_version": "4.35.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d033e707658fed4d853c84e4ad79f34313ca6f018f7dab55f0c5d172c2b9d9
+size 467070345

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

tokenizer_config.json

@@ -0,0 +1,93 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "keep_accents": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.733830861908257,
+    "train_runtime": 14258.7293,
+    "train_samples": 97236,
+    "train_samples_per_second": 20.458,
+    "train_steps_per_second": 0.639
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.725786991334869e-05,
+      "loss": 3.0811,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.451573982669738e-05,
+      "loss": 2.9144,
+      "step": 1000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.177360974004607e-05,
+      "loss": 2.861,
+      "step": 1500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.903147965339476e-05,
+      "loss": 2.8143,
+      "step": 2000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.628934956674345e-05,
+      "loss": 2.7832,
+      "step": 2500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.354721948009214e-05,
+      "loss": 2.7602,
+      "step": 3000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.0805089393440825e-05,
+      "loss": 2.7305,
+      "step": 3500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.8062959306789516e-05,
+      "loss": 2.7235,
+      "step": 4000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5320829220138204e-05,
+      "loss": 2.7046,
+      "step": 4500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.2578699133486895e-05,
+      "loss": 2.6897,
+      "step": 5000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.9836569046835583e-05,
+      "loss": 2.6826,
+      "step": 5500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.709443896018427e-05,
+      "loss": 2.667,
+      "step": 6000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.4352308873532961e-05,
+      "loss": 2.6481,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.161017878688165e-05,
+      "loss": 2.647,
+      "step": 7000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 8.86804870023034e-06,
+      "loss": 2.644,
+      "step": 7500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.125918613579029e-06,
+      "loss": 2.6336,
+      "step": 8000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.3837885269277177e-06,
+      "loss": 2.6286,
+      "step": 8500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 6.416584402764068e-07,
+      "loss": 2.6227,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "step": 9117,
+      "total_flos": 8.259990898448794e+16,
+      "train_loss": 2.733830861908257,
+      "train_runtime": 14258.7293,
+      "train_samples_per_second": 20.458,
+      "train_steps_per_second": 0.639
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9117,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 8.259990898448794e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8d522da8ef5686d8996b01d3597d015f38658e4c113bec3a712d467725673f
+size 4155