Training in progress, step 4000
Browse files- config.json +2 -2
- model.safetensors +2 -2
- special_tokens_map.json +0 -25
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"decoder_attention_heads": 16,
|
| 22 |
"decoder_ffn_dim": 4096,
|
| 23 |
"decoder_layerdrop": 0.0,
|
| 24 |
-
"decoder_layers":
|
| 25 |
"decoder_start_token_id": null,
|
| 26 |
"diversity_penalty": 0.0,
|
| 27 |
"do_sample": false,
|
|
@@ -85,7 +85,7 @@
|
|
| 85 |
"typical_p": 1.0,
|
| 86 |
"use_bfloat16": false,
|
| 87 |
"use_cache": true,
|
| 88 |
-
"vocab_size":
|
| 89 |
},
|
| 90 |
"decoder_start_token_id": 0,
|
| 91 |
"encoder": {
|
|
|
|
| 21 |
"decoder_attention_heads": 16,
|
| 22 |
"decoder_ffn_dim": 4096,
|
| 23 |
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 8,
|
| 25 |
"decoder_start_token_id": null,
|
| 26 |
"diversity_penalty": 0.0,
|
| 27 |
"do_sample": false,
|
|
|
|
| 85 |
"typical_p": 1.0,
|
| 86 |
"use_bfloat16": false,
|
| 87 |
"use_cache": true,
|
| 88 |
+
"vocab_size": 50000
|
| 89 |
},
|
| 90 |
"decoder_start_token_id": 0,
|
| 91 |
"encoder": {
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9832f6905617187a9e1a22af29a2500dd8f9874f81bffb2e375fd74a7d13002c
|
| 3 |
+
size 625508024
|
special_tokens_map.json
CHANGED
|
@@ -1,8 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<s_iitcdip>",
|
| 4 |
-
"<s_synthdog>"
|
| 5 |
-
],
|
| 6 |
"bos_token": {
|
| 7 |
"content": "<s>",
|
| 8 |
"lstrip": false,
|
|
@@ -10,13 +6,6 @@
|
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false
|
| 12 |
},
|
| 13 |
-
"cls_token": {
|
| 14 |
-
"content": "<s>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false
|
| 19 |
-
},
|
| 20 |
"eos_token": {
|
| 21 |
"content": "</s>",
|
| 22 |
"lstrip": false,
|
|
@@ -24,13 +13,6 @@
|
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false
|
| 26 |
},
|
| 27 |
-
"mask_token": {
|
| 28 |
-
"content": "<mask>",
|
| 29 |
-
"lstrip": true,
|
| 30 |
-
"normalized": true,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false
|
| 33 |
-
},
|
| 34 |
"pad_token": {
|
| 35 |
"content": "<pad>",
|
| 36 |
"lstrip": false,
|
|
@@ -38,13 +20,6 @@
|
|
| 38 |
"rstrip": false,
|
| 39 |
"single_word": false
|
| 40 |
},
|
| 41 |
-
"sep_token": {
|
| 42 |
-
"content": "</s>",
|
| 43 |
-
"lstrip": false,
|
| 44 |
-
"normalized": false,
|
| 45 |
-
"rstrip": false,
|
| 46 |
-
"single_word": false
|
| 47 |
-
},
|
| 48 |
"unk_token": {
|
| 49 |
"content": "<unk>",
|
| 50 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
|
|
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"eos_token": {
|
| 10 |
"content": "</s>",
|
| 11 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"pad_token": {
|
| 17 |
"content": "<pad>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:424036b1b9b5b0f3db62cb298e148add77e78e1c6204a578d2f20ca94fa19b8d
|
| 3 |
size 4536
|