Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +28 -0
- pytorch_model.bin +3 -0
- runs/Nov11_12-48-54_vorace/1636631417.9499168/events.out.tfevents.1636631417.vorace +3 -0
- runs/Nov11_12-48-54_vorace/events.out.tfevents.1636631412.vorace +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-small",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 1024,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "mt5",
|
17 |
+
"num_decoder_layers": 8,
|
18 |
+
"num_heads": 6,
|
19 |
+
"num_layers": 8,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"relative_attention_num_buckets": 32,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"tokenizer_class": "T5Tokenizer",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.12.3",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250112
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8c87fc1aaf540dea0fad6018398918c9d96458acd47e3e5cb77dcfdb8d169e7
|
3 |
+
size 1200770885
|
runs/Nov11_12-48-54_vorace/1636631417.9499168/events.out.tfevents.1636631417.vorace
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b07eed050963a974ff99fb74855690bda1258ffaa75696ef39989b196e49879a
|
3 |
+
size 4606
|
runs/Nov11_12-48-54_vorace/events.out.tfevents.1636631412.vorace
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03847edadb773ac6831c674dd71f6dec97b32c9fb9214d42d26554b6863acd0f
|
3 |
+
size 431
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/data/.cache/hf/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8a6ef404b46c68e4026a40b24a34ddcb81fa7fb68fb180ffada8bb60afd5a1f
|
3 |
+
size 2991
|