Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- runs/Jun13_19-57-03_1365898bf35c/1655150246.7589545/events.out.tfevents.1655150246.1365898bf35c.80.1 +3 -0
- runs/Jun13_19-57-03_1365898bf35c/events.out.tfevents.1655150246.1365898bf35c.80.0 +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 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "UBC-NLP/AraT5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dropout_rate": 0.1,
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"feed_forward_proj": "gated-gelu",
|
| 13 |
+
"gradient_checkpointing": false,
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"layer_norm_epsilon": 1e-06,
|
| 17 |
+
"model_type": "t5",
|
| 18 |
+
"num_decoder_layers": 12,
|
| 19 |
+
"num_heads": 12,
|
| 20 |
+
"num_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"relative_attention_max_distance": 128,
|
| 24 |
+
"relative_attention_num_buckets": 32,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.19.4",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 110080
|
| 29 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b84e3fa6f1ddc567260c0b1723bc56456e6cdf426dfb209f12a347b9035a68cb
|
| 3 |
+
size 1131177743
|
runs/Jun13_19-57-03_1365898bf35c/1655150246.7589545/events.out.tfevents.1655150246.1365898bf35c.80.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29fa580a3c4fee573e0f3434cb8863926466b04bb11ae0b9d4c9ae86778f4b3e
|
| 3 |
+
size 5444
|
runs/Jun13_19-57-03_1365898bf35c/events.out.tfevents.1655150246.1365898bf35c.80.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a45d3c35a6fe0b1948aef68dcb0eac2d1efea5d3051b6932a9cd5873fda82ec2
|
| 3 |
+
size 4355
|
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 sha256:5c7ae4407451bf02b459edec774d0539a06615005dd34d5c85c5c06765ff1606
|
| 3 |
+
size 2435308
|
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": "/root/.cache/huggingface/transformers/3b52be683fa2fd36463d04d51871966137133d8c4fc7663ff2a20cb4f3549c18.b02fba13e4584f40329b20be0bad88c2ef97b5fda7d9f4f69b1cb3a620568a86", "name_or_path": "UBC-NLP/AraT5-base", "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 sha256:83b686ca1c6f22683df67d414d22ae85a0af13d8a0daabfd273bd2c4fc5fada6
|
| 3 |
+
size 3311
|