Training in progress, step 100
Browse files- config.json +48 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pszemraj/mega-ar-small-4096-NC-simplewiki-v1",
|
| 3 |
+
"activation": "silu",
|
| 4 |
+
"add_lm_hidden_dense_layer": false,
|
| 5 |
+
"add_token_type_embeddings": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"MegaForCausalLM"
|
| 8 |
+
],
|
| 9 |
+
"attention_activation": "softmax",
|
| 10 |
+
"attention_probs_dropout_prob": 0.2,
|
| 11 |
+
"bidirectional": false,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"chunk_size": -1,
|
| 14 |
+
"classifier_dropout": null,
|
| 15 |
+
"dropout_prob": 0.1,
|
| 16 |
+
"ema_beta_range": 0.02,
|
| 17 |
+
"ema_delta_alpha_range": 0.2,
|
| 18 |
+
"ema_gamma_omega_range": 1.0,
|
| 19 |
+
"ema_projection_size": 16,
|
| 20 |
+
"eos_token_id": 0,
|
| 21 |
+
"hidden_dropout_prob": 0.2,
|
| 22 |
+
"hidden_size": 512,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 1024,
|
| 25 |
+
"is_decoder": true,
|
| 26 |
+
"max_positions": 4096,
|
| 27 |
+
"model_type": "mega",
|
| 28 |
+
"nffn_activation_dropout_prob": 0.1,
|
| 29 |
+
"nffn_hidden_size": 1024,
|
| 30 |
+
"norm_affine": true,
|
| 31 |
+
"normalization_type": "scalenorm",
|
| 32 |
+
"normalize_before_ffn": true,
|
| 33 |
+
"normalize_before_mega": true,
|
| 34 |
+
"num_attention_heads": 1,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"pad_token_id": null,
|
| 37 |
+
"relative_positional_bias": "rotary",
|
| 38 |
+
"shared_representation_size": 128,
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.33.1",
|
| 41 |
+
"truncation": null,
|
| 42 |
+
"type_vocab_size": 2,
|
| 43 |
+
"use_cache": true,
|
| 44 |
+
"use_chunking": false,
|
| 45 |
+
"use_feature_dropout": false,
|
| 46 |
+
"use_normalized_ffn": true,
|
| 47 |
+
"vocab_size": 50277
|
| 48 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95d4481e95b6b730d9ff8ab89dba527ac320a21933735cfa1a44625a444c8f18
|
| 3 |
+
size 259284978
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"max_length": 4096,
|
| 7 |
+
"model_max_length": 4096,
|
| 8 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:851b61f8deafcc146d27f9e7da2140ff1c907b9d1135451ec8c2ad333692d90f
|
| 3 |
+
size 4728
|