Upload 13 files

README.md

@@ -1,3 +1,53 @@
 ---
-license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- customized
+model-index:
+- name: finetune_jingzhan
+  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. -->
+
+# finetune_jingzhan
+
+This model is a fine-tuned version of [/home/sxx/LMFlow/models/gpt2](https://huggingface.co//home/sxx/LMFlow/models/gpt2) on the customized 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 0.01
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.28.0.dev0
+- Pytorch 2.0.0+cu117
+- Datasets 2.10.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.01,
+    "train_loss": 1.2590427150974026,
+    "train_runtime": 57.7633,
+    "train_samples": 7656,
+    "train_samples_per_second": 1.325,
+    "train_steps_per_second": 1.333
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/home/sxx/LMFlow/models/gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0f8b6111f851faa24b085f56eebab6a9a58d7c474c5f5e9422cbe73af5e1f7
+size 261515901

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.01,
+    "train_loss": 1.2590427150974026,
+    "train_runtime": 57.7633,
+    "train_samples": 7656,
+    "train_samples_per_second": 1.325,
+    "train_steps_per_second": 1.333
+}

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.010057471264367816,
+  "global_step": 77,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.4805194805194807e-05,
+      "loss": 1.4342,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.610389610389611e-06,
+      "loss": 1.3017,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.415584415584416e-06,
+      "loss": 1.3118,
+      "step": 60
+    },
+    {
+      "epoch": 0.01,
+      "step": 77,
+      "total_flos": 28330426368.0,
+      "train_loss": 1.2590427150974026,
+      "train_runtime": 57.7633,
+      "train_samples_per_second": 1.325,
+      "train_steps_per_second": 1.333
+    }
+  ],
+  "max_steps": 77,
+  "num_train_epochs": 1,
+  "total_flos": 28330426368.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbdbe9ab8f4bc2bfc735311db7391f4ccb1cf40f56bb8e99ac788b2c4a49b7d
+size 4859