Upload folder using huggingface_hub
Browse files- config.json +7 -6
- eval/metric.first.answer.context.question.NoaCA14_base_quac_es.default.json +1 -0
- eval/samples.test.hyp.context.question.NoaCA14_base_quac_es.default.txt +0 -0
- eval/samples.validation.hyp.context.question.NoaCA14_base_quac_es.default.txt +0 -0
- pytorch_model.bin +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +2 -2
- trainer_config.json +1 -1
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "checkpoints_qg_ae/
|
3 |
"add_prefix": true,
|
4 |
"architectures": [
|
5 |
"MT5ForConditionalGeneration"
|
6 |
],
|
7 |
-
"d_ff":
|
8 |
"d_kv": 64,
|
9 |
-
"d_model":
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "gelu_new",
|
12 |
"dropout_rate": 0.1,
|
@@ -17,9 +17,10 @@
|
|
17 |
"is_gated_act": true,
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "mt5",
|
20 |
-
"num_decoder_layers":
|
21 |
-
"num_heads":
|
22 |
-
"num_layers":
|
|
|
23 |
"pad_token_id": 0,
|
24 |
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "checkpoints_qg_ae/model_onvcyh/epoch_2",
|
3 |
"add_prefix": true,
|
4 |
"architectures": [
|
5 |
"MT5ForConditionalGeneration"
|
6 |
],
|
7 |
+
"d_ff": 2048,
|
8 |
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "gelu_new",
|
12 |
"dropout_rate": 0.1,
|
|
|
17 |
"is_gated_act": true,
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "mt5",
|
20 |
+
"num_decoder_layers": 12,
|
21 |
+
"num_heads": 12,
|
22 |
+
"num_layers": 12,
|
23 |
+
"output_past": true,
|
24 |
"pad_token_id": 0,
|
25 |
"relative_attention_max_distance": 128,
|
26 |
"relative_attention_num_buckets": 32,
|
eval/metric.first.answer.context.question.NoaCA14_base_quac_es.default.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"validation": {"Bleu_1": 0.043064322604203585, "Bleu_2": 0.03208874001887557, "Bleu_3": 0.027278203301308576, "Bleu_4": 0.02371109598812169}, "test": {"Bleu_1": 0.04605895448849715, "Bleu_2": 0.03535081604640602, "Bleu_3": 0.030419185987962664, "Bleu_4": 0.02658593730190876}}
|
eval/samples.test.hyp.context.question.NoaCA14_base_quac_es.default.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
eval/samples.validation.hyp.context.question.NoaCA14_base_quac_es.default.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
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 sha256:061e08c7b67c7416db99c3722f19747db565a5f3f6623686b2ea851a06ad8365
|
3 |
+
size 2329634869
|
tokenizer.json
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 sha256:6e6f102e00fd7c0bc8dbaf509bd484bf6a31063f5b496740f90b989b9baa1d1b
|
3 |
+
size 16315565
|
tokenizer_config.json
CHANGED
@@ -3,10 +3,10 @@
|
|
3 |
"eos_token": "</s>",
|
4 |
"extra_ids": 0,
|
5 |
"model_max_length": 1000000000000000019884624838656,
|
6 |
-
"name_or_path": "checkpoints_qg_ae/
|
7 |
"pad_token": "<pad>",
|
8 |
"sp_model_kwargs": {},
|
9 |
-
"special_tokens_map_file": "/home/
|
10 |
"tokenizer_class": "T5Tokenizer",
|
11 |
"unk_token": "<unk>"
|
12 |
}
|
|
|
3 |
"eos_token": "</s>",
|
4 |
"extra_ids": 0,
|
5 |
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"name_or_path": "checkpoints_qg_ae/model_onvcyh/epoch_2",
|
7 |
"pad_token": "<pad>",
|
8 |
"sp_model_kwargs": {},
|
9 |
+
"special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
|
10 |
"tokenizer_class": "T5Tokenizer",
|
11 |
"unk_token": "<unk>"
|
12 |
}
|
trainer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"dataset_path": "NoaCA14/
|
|
|
1 |
+
{"dataset_path": "NoaCA14/base_quac_es", "dataset_name": "default", "input_types": ["context", "context"], "output_types": ["question", "answer"], "prefix_types": ["qg", "ae"], "model": "lmqg/mt5-base-esquad-qg-ae", "max_length": 512, "max_length_output": 32, "epoch": 5, "batch": 24, "lr": 0.0001, "fp16": false, "random_seed": 42, "gradient_accumulation_steps": 4, "label_smoothing": 0.15}
|