Huấn luyện GPT-2 hoàn tất toàn bộ 3 giai đoạn!
Browse files- config.json +41 -41
- generation_config.json +6 -6
config.json
CHANGED
|
@@ -1,41 +1,41 @@
|
|
| 1 |
-
{
|
| 2 |
-
"activation_function": "gelu_new",
|
| 3 |
-
"add_cross_attention": false,
|
| 4 |
-
"architectures": [
|
| 5 |
-
"GPT2LMHeadModel"
|
| 6 |
-
],
|
| 7 |
-
"attn_pdrop": 0.1,
|
| 8 |
-
"bos_token_id": 0,
|
| 9 |
-
"dtype": "float32",
|
| 10 |
-
"embd_pdrop": 0.1,
|
| 11 |
-
"eos_token_id": 0,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"layer_norm_epsilon": 1e-05,
|
| 14 |
-
"model_type": "gpt2",
|
| 15 |
-
"n_ctx": 1024,
|
| 16 |
-
"n_embd": 768,
|
| 17 |
-
"n_head": 12,
|
| 18 |
-
"n_inner": null,
|
| 19 |
-
"n_layer": 12,
|
| 20 |
-
"n_positions": 1024,
|
| 21 |
-
"pad_token_id": 0,
|
| 22 |
-
"reorder_and_upcast_attn": false,
|
| 23 |
-
"resid_pdrop": 0.1,
|
| 24 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
-
"scale_attn_weights": true,
|
| 26 |
-
"summary_activation": null,
|
| 27 |
-
"summary_first_dropout": 0.1,
|
| 28 |
-
"summary_proj_to_labels": true,
|
| 29 |
-
"summary_type": "cls_index",
|
| 30 |
-
"summary_use_proj": true,
|
| 31 |
-
"task_specific_params": {
|
| 32 |
-
"text-generation": {
|
| 33 |
-
"do_sample": true,
|
| 34 |
-
"max_length": 50
|
| 35 |
-
}
|
| 36 |
-
},
|
| 37 |
-
"tie_word_embeddings": true,
|
| 38 |
-
"transformers_version": "5.
|
| 39 |
-
"use_cache": false,
|
| 40 |
-
"vocab_size": 32000
|
| 41 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"tie_word_embeddings": true,
|
| 38 |
+
"transformers_version": "5.15.0",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 32000
|
| 41 |
+
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 50256,
|
| 4 |
-
"eos_token_id": 50256,
|
| 5 |
-
"transformers_version": "5.
|
| 6 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.15.0"
|
| 6 |
+
}
|