End of training

README.md

@@ -0,0 +1,51 @@
+---
+license: mit
+base_model: xlnet-base-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: xlnet-pretrained
+  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. -->
+
+# xlnet-pretrained
+
+This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
+
+## 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: 48
+- eval_batch_size: 8
+- seed: 1
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Tokenizers 0.15.0

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": "4.35.2",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b70d11045ed88b8a8a0ea4d3ab42b05b14b845984ec06d638384b360215ddc9
+size 467023808

runs/Jan05_07-18-44_d3e7d681efd2/events.out.tfevents.1704439132.d3e7d681efd2.843.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97304fd91b7928f87706c75862e2fecd7657a12b20760c468aacfa644acdc5c0
+size 4807

runs/Jan05_07-43-47_d3e7d681efd2/events.out.tfevents.1704440629.d3e7d681efd2.843.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062e4c4374754604f441f06183984edf2f4012fd48f3f94310672bcc308acc18
+size 7818

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:231edf89b781e3bd650beb94d14962eef97106cc3722fbe98e8b5780997f91ce
+size 4600