trained model
Browse files- README.md +82 -0
- checkpoint-3684/config.json +61 -0
- checkpoint-3684/generation_config.json +7 -0
- checkpoint-3684/optimizer.pt +3 -0
- checkpoint-3684/pytorch_model.bin +3 -0
- checkpoint-3684/rng_state.pth +3 -0
- checkpoint-3684/scheduler.pt +3 -0
- checkpoint-3684/trainer_state.json +84 -0
- checkpoint-3684/training_args.bin +3 -0
- checkpoint-9210/config.json +61 -0
- checkpoint-9210/generation_config.json +7 -0
- checkpoint-9210/optimizer.pt +3 -0
- checkpoint-9210/pytorch_model.bin +3 -0
- checkpoint-9210/rng_state.pth +3 -0
- checkpoint-9210/scheduler.pt +3 -0
- checkpoint-9210/trainer_state.json +189 -0
- checkpoint-9210/training_args.bin +3 -0
- config.json +61 -0
- generation_config.json +7 -0
- logs/1677934194.5926976/events.out.tfevents.1677934194.a56124cabdee.197.1 +3 -0
- logs/events.out.tfevents.1677934194.a56124cabdee.197.0 +3 -0
- logs/events.out.tfevents.1677946363.a56124cabdee.197.2 +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +107 -0
- tokenizer.json +0 -0
- tokenizer_config.json +113 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- samsum
|
7 |
+
metrics:
|
8 |
+
- rouge
|
9 |
+
model-index:
|
10 |
+
- name: flan-t5-base-samsum
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Sequence-to-sequence Language Modeling
|
14 |
+
type: text2text-generation
|
15 |
+
dataset:
|
16 |
+
name: samsum
|
17 |
+
type: samsum
|
18 |
+
config: samsum
|
19 |
+
split: test
|
20 |
+
args: samsum
|
21 |
+
metrics:
|
22 |
+
- name: Rouge1
|
23 |
+
type: rouge
|
24 |
+
value: 47.2663
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# flan-t5-base-samsum
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the samsum dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 1.3716
|
35 |
+
- Rouge1: 47.2663
|
36 |
+
- Rouge2: 23.5327
|
37 |
+
- Rougel: 39.6491
|
38 |
+
- Rougelsum: 43.3169
|
39 |
+
- Gen Len: 17.3907
|
40 |
+
|
41 |
+
## Model description
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Intended uses & limitations
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training and evaluation data
|
50 |
+
|
51 |
+
More information needed
|
52 |
+
|
53 |
+
## Training procedure
|
54 |
+
|
55 |
+
### Training hyperparameters
|
56 |
+
|
57 |
+
The following hyperparameters were used during training:
|
58 |
+
- learning_rate: 5e-05
|
59 |
+
- train_batch_size: 8
|
60 |
+
- eval_batch_size: 8
|
61 |
+
- seed: 42
|
62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
+
- lr_scheduler_type: linear
|
64 |
+
- num_epochs: 5
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
70 |
+
| 1.4379 | 1.0 | 1842 | 1.3805 | 47.1438 | 23.6153 | 39.6699 | 43.5505 | 17.1197 |
|
71 |
+
| 1.3559 | 2.0 | 3684 | 1.3716 | 47.2663 | 23.5327 | 39.6491 | 43.3169 | 17.3907 |
|
72 |
+
| 1.2783 | 3.0 | 5526 | 1.3721 | 47.4896 | 23.7684 | 39.7733 | 43.4494 | 17.1832 |
|
73 |
+
| 1.2378 | 4.0 | 7368 | 1.3757 | 47.9122 | 24.0531 | 40.2225 | 43.996 | 17.3053 |
|
74 |
+
| 1.1983 | 5.0 | 9210 | 1.3751 | 47.8507 | 24.0061 | 40.231 | 43.8698 | 17.3040 |
|
75 |
+
|
76 |
+
|
77 |
+
### Framework versions
|
78 |
+
|
79 |
+
- Transformers 4.26.1
|
80 |
+
- Pytorch 1.13.1+cu116
|
81 |
+
- Datasets 2.10.1
|
82 |
+
- Tokenizers 0.13.2
|
checkpoint-3684/config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-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 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
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,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"tie_word_embeddings": false,
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.26.1",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32128
|
61 |
+
}
|
checkpoint-3684/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.26.1"
|
7 |
+
}
|
checkpoint-3684/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2494a087a30ef6722c70a85c8a4eb3a1d417d42c3ec4c1947940cee57d89b73f
|
3 |
+
size 1980790149
|
checkpoint-3684/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64d5135680d01f4bfb475174c86a691a51df898e6509547f2cfe1f517bc14168
|
3 |
+
size 990408885
|
checkpoint-3684/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d1241f30548488a75615b17b77298425868e3da42b741eadbf23aef3d7b4ca5
|
3 |
+
size 14575
|
checkpoint-3684/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90ebdb43dd363a0fc40428e9841b1804a0a8114634194edc2598d9a2dca06af0
|
3 |
+
size 627
|
checkpoint-3684/trainer_state.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.3715944290161133,
|
3 |
+
"best_model_checkpoint": "flan-t5-base-samsum/checkpoint-3684",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 3684,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.27,
|
12 |
+
"learning_rate": 4.728555917480999e-05,
|
13 |
+
"loss": 1.4811,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.54,
|
18 |
+
"learning_rate": 4.457111834961998e-05,
|
19 |
+
"loss": 1.4545,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.81,
|
24 |
+
"learning_rate": 4.185667752442997e-05,
|
25 |
+
"loss": 1.4379,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"eval_gen_len": 17.11965811965812,
|
31 |
+
"eval_loss": 1.3805454969406128,
|
32 |
+
"eval_rouge1": 47.1438,
|
33 |
+
"eval_rouge2": 23.6153,
|
34 |
+
"eval_rougeL": 39.6699,
|
35 |
+
"eval_rougeLsum": 43.5505,
|
36 |
+
"eval_runtime": 126.1042,
|
37 |
+
"eval_samples_per_second": 6.495,
|
38 |
+
"eval_steps_per_second": 0.817,
|
39 |
+
"step": 1842
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.09,
|
43 |
+
"learning_rate": 3.914223669923996e-05,
|
44 |
+
"loss": 1.4094,
|
45 |
+
"step": 2000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.36,
|
49 |
+
"learning_rate": 3.642779587404995e-05,
|
50 |
+
"loss": 1.3318,
|
51 |
+
"step": 2500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.63,
|
55 |
+
"learning_rate": 3.3713355048859935e-05,
|
56 |
+
"loss": 1.3396,
|
57 |
+
"step": 3000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.9,
|
61 |
+
"learning_rate": 3.099891422366993e-05,
|
62 |
+
"loss": 1.3559,
|
63 |
+
"step": 3500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.0,
|
67 |
+
"eval_gen_len": 17.39072039072039,
|
68 |
+
"eval_loss": 1.3715944290161133,
|
69 |
+
"eval_rouge1": 47.2663,
|
70 |
+
"eval_rouge2": 23.5327,
|
71 |
+
"eval_rougeL": 39.6491,
|
72 |
+
"eval_rougeLsum": 43.3169,
|
73 |
+
"eval_runtime": 125.9833,
|
74 |
+
"eval_samples_per_second": 6.501,
|
75 |
+
"eval_steps_per_second": 0.818,
|
76 |
+
"step": 3684
|
77 |
+
}
|
78 |
+
],
|
79 |
+
"max_steps": 9210,
|
80 |
+
"num_train_epochs": 5,
|
81 |
+
"total_flos": 2.017569063252787e+16,
|
82 |
+
"trial_name": null,
|
83 |
+
"trial_params": null
|
84 |
+
}
|
checkpoint-3684/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:284069f9e3c9a282d12a661d1d2d20b36615bce8274dd9c52c4244b1bab4cc83
|
3 |
+
size 3643
|
checkpoint-9210/config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-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 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
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,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"tie_word_embeddings": false,
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.26.1",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32128
|
61 |
+
}
|
checkpoint-9210/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.26.1"
|
7 |
+
}
|
checkpoint-9210/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f947523173359a2b69116aa00f75acc3f6b6a8ccd1371dbe2b6e66a002286952
|
3 |
+
size 1980790149
|
checkpoint-9210/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a347c2d01c24ef2eb140c02023ea53ceadc912b0348780bc3e086b928db77db
|
3 |
+
size 990408885
|
checkpoint-9210/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cf6e93a4e7fe6ae5ae14554422bf566aa38c9ac53a8c7a2fee4b6f98be8703d
|
3 |
+
size 14575
|
checkpoint-9210/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0267870383c524bbb1cb9861088cd0dfa247c749b7b742a2bbfe961ece51d2f1
|
3 |
+
size 627
|
checkpoint-9210/trainer_state.json
ADDED
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.3715944290161133,
|
3 |
+
"best_model_checkpoint": "flan-t5-base-samsum/checkpoint-3684",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 9210,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.27,
|
12 |
+
"learning_rate": 4.728555917480999e-05,
|
13 |
+
"loss": 1.4811,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.54,
|
18 |
+
"learning_rate": 4.457111834961998e-05,
|
19 |
+
"loss": 1.4545,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.81,
|
24 |
+
"learning_rate": 4.185667752442997e-05,
|
25 |
+
"loss": 1.4379,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"eval_gen_len": 17.11965811965812,
|
31 |
+
"eval_loss": 1.3805454969406128,
|
32 |
+
"eval_rouge1": 47.1438,
|
33 |
+
"eval_rouge2": 23.6153,
|
34 |
+
"eval_rougeL": 39.6699,
|
35 |
+
"eval_rougeLsum": 43.5505,
|
36 |
+
"eval_runtime": 126.1042,
|
37 |
+
"eval_samples_per_second": 6.495,
|
38 |
+
"eval_steps_per_second": 0.817,
|
39 |
+
"step": 1842
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.09,
|
43 |
+
"learning_rate": 3.914223669923996e-05,
|
44 |
+
"loss": 1.4094,
|
45 |
+
"step": 2000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.36,
|
49 |
+
"learning_rate": 3.642779587404995e-05,
|
50 |
+
"loss": 1.3318,
|
51 |
+
"step": 2500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.63,
|
55 |
+
"learning_rate": 3.3713355048859935e-05,
|
56 |
+
"loss": 1.3396,
|
57 |
+
"step": 3000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.9,
|
61 |
+
"learning_rate": 3.099891422366993e-05,
|
62 |
+
"loss": 1.3559,
|
63 |
+
"step": 3500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.0,
|
67 |
+
"eval_gen_len": 17.39072039072039,
|
68 |
+
"eval_loss": 1.3715944290161133,
|
69 |
+
"eval_rouge1": 47.2663,
|
70 |
+
"eval_rouge2": 23.5327,
|
71 |
+
"eval_rougeL": 39.6491,
|
72 |
+
"eval_rougeLsum": 43.3169,
|
73 |
+
"eval_runtime": 125.9833,
|
74 |
+
"eval_samples_per_second": 6.501,
|
75 |
+
"eval_steps_per_second": 0.818,
|
76 |
+
"step": 3684
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 2.17,
|
80 |
+
"learning_rate": 2.8284473398479917e-05,
|
81 |
+
"loss": 1.3123,
|
82 |
+
"step": 4000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 2.44,
|
86 |
+
"learning_rate": 2.5570032573289905e-05,
|
87 |
+
"loss": 1.2724,
|
88 |
+
"step": 4500
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 2.71,
|
92 |
+
"learning_rate": 2.2855591748099893e-05,
|
93 |
+
"loss": 1.2815,
|
94 |
+
"step": 5000
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 2.99,
|
98 |
+
"learning_rate": 2.0141150922909884e-05,
|
99 |
+
"loss": 1.2783,
|
100 |
+
"step": 5500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 3.0,
|
104 |
+
"eval_gen_len": 17.183150183150182,
|
105 |
+
"eval_loss": 1.3721352815628052,
|
106 |
+
"eval_rouge1": 47.4896,
|
107 |
+
"eval_rouge2": 23.7684,
|
108 |
+
"eval_rougeL": 39.7733,
|
109 |
+
"eval_rougeLsum": 43.4494,
|
110 |
+
"eval_runtime": 125.6835,
|
111 |
+
"eval_samples_per_second": 6.516,
|
112 |
+
"eval_steps_per_second": 0.82,
|
113 |
+
"step": 5526
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 3.26,
|
117 |
+
"learning_rate": 1.742671009771987e-05,
|
118 |
+
"loss": 1.2228,
|
119 |
+
"step": 6000
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 3.53,
|
123 |
+
"learning_rate": 1.471226927252986e-05,
|
124 |
+
"loss": 1.243,
|
125 |
+
"step": 6500
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 3.8,
|
129 |
+
"learning_rate": 1.1997828447339848e-05,
|
130 |
+
"loss": 1.2378,
|
131 |
+
"step": 7000
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 4.0,
|
135 |
+
"eval_gen_len": 17.305250305250304,
|
136 |
+
"eval_loss": 1.3757330179214478,
|
137 |
+
"eval_rouge1": 47.9122,
|
138 |
+
"eval_rouge2": 24.0531,
|
139 |
+
"eval_rougeL": 40.2225,
|
140 |
+
"eval_rougeLsum": 43.996,
|
141 |
+
"eval_runtime": 125.846,
|
142 |
+
"eval_samples_per_second": 6.508,
|
143 |
+
"eval_steps_per_second": 0.818,
|
144 |
+
"step": 7368
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 4.07,
|
148 |
+
"learning_rate": 9.283387622149838e-06,
|
149 |
+
"loss": 1.2306,
|
150 |
+
"step": 7500
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 4.34,
|
154 |
+
"learning_rate": 6.568946796959827e-06,
|
155 |
+
"loss": 1.2106,
|
156 |
+
"step": 8000
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.61,
|
160 |
+
"learning_rate": 3.854505971769816e-06,
|
161 |
+
"loss": 1.1991,
|
162 |
+
"step": 8500
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 4.89,
|
166 |
+
"learning_rate": 1.1400651465798045e-06,
|
167 |
+
"loss": 1.1983,
|
168 |
+
"step": 9000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 5.0,
|
172 |
+
"eval_gen_len": 17.304029304029303,
|
173 |
+
"eval_loss": 1.3750557899475098,
|
174 |
+
"eval_rouge1": 47.8507,
|
175 |
+
"eval_rouge2": 24.0061,
|
176 |
+
"eval_rougeL": 40.231,
|
177 |
+
"eval_rougeLsum": 43.8698,
|
178 |
+
"eval_runtime": 125.3005,
|
179 |
+
"eval_samples_per_second": 6.536,
|
180 |
+
"eval_steps_per_second": 0.822,
|
181 |
+
"step": 9210
|
182 |
+
}
|
183 |
+
],
|
184 |
+
"max_steps": 9210,
|
185 |
+
"num_train_epochs": 5,
|
186 |
+
"total_flos": 5.043922658131968e+16,
|
187 |
+
"trial_name": null,
|
188 |
+
"trial_params": null
|
189 |
+
}
|
checkpoint-9210/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:284069f9e3c9a282d12a661d1d2d20b36615bce8274dd9c52c4244b1bab4cc83
|
3 |
+
size 3643
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-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 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
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,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"tie_word_embeddings": false,
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.26.1",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32128
|
61 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.26.1"
|
7 |
+
}
|
logs/1677934194.5926976/events.out.tfevents.1677934194.a56124cabdee.197.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc92cf29078ed48916b393163f207fe4ebc71c935c7676777355e7b05a56c355
|
3 |
+
size 5895
|
logs/events.out.tfevents.1677934194.a56124cabdee.197.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b5b0835495d0128ba3b388c52743542e130ff0189c38418d8c9e2f027b0ebe0
|
3 |
+
size 10592
|
logs/events.out.tfevents.1677946363.a56124cabdee.197.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d71488265121125a7b3e4c6248c10cf8fa2937a16f136297f829bf3472c4b24d
|
3 |
+
size 565
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64d5135680d01f4bfb475174c86a691a51df898e6509547f2cfe1f517bc14168
|
3 |
+
size 990408885
|
special_tokens_map.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
107 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"extra_ids": 100,
|
106 |
+
"model_max_length": 512,
|
107 |
+
"name_or_path": "google/flan-t5-base",
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"sp_model_kwargs": {},
|
110 |
+
"special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
|
111 |
+
"tokenizer_class": "T5Tokenizer",
|
112 |
+
"unk_token": "<unk>"
|
113 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:284069f9e3c9a282d12a661d1d2d20b36615bce8274dd9c52c4244b1bab4cc83
|
3 |
+
size 3643
|