Commit ·
c8417d3
1
Parent(s): c149f91
Upload 3 files
Browse files- config.json +39 -0
- parameters.json +40 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 4,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"output_hidden_states": true,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.1,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"task_specific_params": {
|
| 31 |
+
"text-generation": {
|
| 32 |
+
"do_sample": true,
|
| 33 |
+
"max_length": 50
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"transformers_version": "4.27.4",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50260
|
| 39 |
+
}
|
parameters.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"force": true,
|
| 3 |
+
"dump_path": "serialization_dir/codegpt_intrain_06-06-2023_14-14-15",
|
| 4 |
+
"data_file": "data/binarized_text.gpt2.pickle",
|
| 5 |
+
"student_config": "training_configs/codegpt.json",
|
| 6 |
+
"student_pretrained_weights": null,
|
| 7 |
+
"teacher_name": "microsoft/CodeGPT-small-py-adaptedGPT2",
|
| 8 |
+
"temperature": 2.0,
|
| 9 |
+
"alpha_ce": 0.33,
|
| 10 |
+
"alpha_clm": 0.33,
|
| 11 |
+
"alpha_mse": 0.0,
|
| 12 |
+
"alpha_cos": 0.33,
|
| 13 |
+
"restrict_ce_to_mask": false,
|
| 14 |
+
"freeze_pos_embs": true,
|
| 15 |
+
"n_epoch": 1,
|
| 16 |
+
"batch_size": 6,
|
| 17 |
+
"group_by_size": true,
|
| 18 |
+
"gradient_accumulation_steps": 50,
|
| 19 |
+
"warmup_prop": 0.05,
|
| 20 |
+
"weight_decay": 0.0,
|
| 21 |
+
"learning_rate": 0.0005,
|
| 22 |
+
"adam_epsilon": 1e-06,
|
| 23 |
+
"max_grad_norm": 5.0,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"fp16": false,
|
| 26 |
+
"fp16_opt_level": "O1",
|
| 27 |
+
"n_gpu": 1,
|
| 28 |
+
"local_rank": 0,
|
| 29 |
+
"seed": 56,
|
| 30 |
+
"log_interval": 500,
|
| 31 |
+
"checkpoint_interval": 5850,
|
| 32 |
+
"n_nodes": 1,
|
| 33 |
+
"node_id": 0,
|
| 34 |
+
"global_rank": 0,
|
| 35 |
+
"world_size": 1,
|
| 36 |
+
"n_gpu_per_node": 1,
|
| 37 |
+
"multi_gpu": false,
|
| 38 |
+
"is_master": true,
|
| 39 |
+
"multi_node": false
|
| 40 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6df5599c9e6f752fbdcb4d570c50b0c96f526bc82440d218e3c1efd1ad6ecba6
|
| 3 |
+
size 275173029
|