Commit
•
d8e8b51
1
Parent(s):
52e5e09
added model checkpoint
Browse files- config.json +77 -0
- events.out.tfevents.1619142848.GPU-Server.4861.0 +0 -0
- pytorch_model.bin +3 -0
- spm-default-16k.model +3 -0
- spm-default-16k.vocab +0 -0
- training.logs +0 -0
config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": ["ReformerModelWithLMHead"],
|
| 3 |
+
"attention_head_size": 64,
|
| 4 |
+
"attn_layers": [
|
| 5 |
+
"local",
|
| 6 |
+
"lsh",
|
| 7 |
+
"local",
|
| 8 |
+
"lsh",
|
| 9 |
+
"local",
|
| 10 |
+
"lsh",
|
| 11 |
+
"local",
|
| 12 |
+
"lsh",
|
| 13 |
+
"local",
|
| 14 |
+
"lsh",
|
| 15 |
+
"local",
|
| 16 |
+
"lsh",
|
| 17 |
+
"local",
|
| 18 |
+
"lsh",
|
| 19 |
+
"local",
|
| 20 |
+
"lsh",
|
| 21 |
+
"local",
|
| 22 |
+
"lsh",
|
| 23 |
+
"local",
|
| 24 |
+
"lsh",
|
| 25 |
+
"local",
|
| 26 |
+
"lsh",
|
| 27 |
+
"local",
|
| 28 |
+
"lsh",
|
| 29 |
+
"local",
|
| 30 |
+
"lsh",
|
| 31 |
+
"local",
|
| 32 |
+
"lsh",
|
| 33 |
+
"local",
|
| 34 |
+
"lsh",
|
| 35 |
+
"local",
|
| 36 |
+
"lsh",
|
| 37 |
+
"local",
|
| 38 |
+
"lsh",
|
| 39 |
+
"local",
|
| 40 |
+
"lsh"
|
| 41 |
+
],
|
| 42 |
+
"axial_norm_std": 1.0,
|
| 43 |
+
"axial_pos_embds": true,
|
| 44 |
+
"axial_pos_embds_dim": [512, 768],
|
| 45 |
+
"axial_pos_shape": [16, 32],
|
| 46 |
+
"chunk_size_lm_head": 0,
|
| 47 |
+
"eos_token_id": 2,
|
| 48 |
+
"feed_forward_size": 512,
|
| 49 |
+
"hash_seed": null,
|
| 50 |
+
"hidden_act": "relu",
|
| 51 |
+
"hidden_dropout_prob": 0.05,
|
| 52 |
+
"hidden_size": 1280,
|
| 53 |
+
"initializer_range": 0.02,
|
| 54 |
+
"is_decoder": true,
|
| 55 |
+
"layer_norm_eps": 1e-12,
|
| 56 |
+
"local_attention_probs_dropout_prob": 0.05,
|
| 57 |
+
"local_attn_chunk_length": 64,
|
| 58 |
+
"local_num_chunks_after": 0,
|
| 59 |
+
"local_num_chunks_before": 1,
|
| 60 |
+
"lsh_attention_probs_dropout_prob": 0.0,
|
| 61 |
+
"lsh_attn_chunk_length": 64,
|
| 62 |
+
"lsh_num_chunks_after": 0,
|
| 63 |
+
"lsh_num_chunks_before": 1,
|
| 64 |
+
"max_position_embeddings": 512,
|
| 65 |
+
"model_type": "reformer",
|
| 66 |
+
"n_positions": 512,
|
| 67 |
+
"num_attention_heads": 20,
|
| 68 |
+
"num_buckets": 32,
|
| 69 |
+
"num_hashes": 1,
|
| 70 |
+
"num_hidden_layers": 36,
|
| 71 |
+
"pad_token_id": 0,
|
| 72 |
+
"tie_word_embeddings": false,
|
| 73 |
+
"tokenizer": "default",
|
| 74 |
+
"transformers_version": "4.5.0",
|
| 75 |
+
"use_cache": true,
|
| 76 |
+
"vocab_size": 16000
|
| 77 |
+
}
|
events.out.tfevents.1619142848.GPU-Server.4861.0
ADDED
|
Binary file (2.31 MB). View file
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d45ddf5114046326c29e5ce19d195a3acb90273924cbf434d2d2f8df02e68a1
|
| 3 |
+
size 1261701064
|
spm-default-16k.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5682bb73fbe4efee67a087751ce4d2bc801e0fec4f0753bc5a871a4ef725bb25
|
| 3 |
+
size 10521992
|
spm-default-16k.vocab
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training.logs
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|