s444465/projekt-glebokie
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

T5

Browse Source
This commit is contained in:
s444501 2023-02-12 15:22:23 +01:00
parent e6f8958b6a
commit a0a10fe18e
16 changed files with 136870 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5023
T5.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

62
models/t5_v1_1/README.md Normal file
View File

@ -0,0 +1,62 @@
---
language:
- text
- label
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
- accuracy
model-index:
- name: t5_v1_1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# t5_v1_1
This model is a fine-tuned version of [google/t5-v1_1-small](https://huggingface.co/google/t5-v1_1-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5495
- Bleu: 0.0
- Accuracy: 1.0
- Gen Len: 2.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2

24
models/t5_v1_1/all_results.json Normal file
View File

@ -0,0 +1,24 @@
{
"epoch": 1.0,
"eval_accuracy": 1.0,
"eval_bleu": 0.0,
"eval_gen_len": 2.0,
"eval_loss": 0.549530029296875,
"eval_runtime": 21.1323,
"eval_samples": 2000,
"eval_samples_per_second": 94.642,
"eval_steps_per_second": 11.83,
"predict_accuracy": 1.0,
"predict_bleu": 0.0,
"predict_gen_len": 2.0,
"predict_loss": 0.5152234435081482,
"predict_runtime": 20.0795,
"predict_samples": 2000,
"predict_samples_per_second": 99.604,
"predict_steps_per_second": 12.451,
"train_loss": 3.4401537475585937,
"train_runtime": 242.9807,
"train_samples": 16000,
"train_samples_per_second": 65.849,
"train_steps_per_second": 8.231
}

31
models/t5_v1_1/config.json Normal file
View File

@ -0,0 +1,31 @@
{
"_name_or_path": "google/t5-v1_1-small",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 1024,
"d_kv": 64,
"d_model": 512,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 8,
"num_heads": 6,
"num_layers": 8,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.26.1",
"use_cache": true,
"vocab_size": 32100
}

11
models/t5_v1_1/eval_results.json Normal file
View File

@ -0,0 +1,11 @@
{
"epoch": 1.0,
"eval_accuracy": 1.0,
"eval_bleu": 0.0,
"eval_gen_len": 2.0,
"eval_loss": 0.549530029296875,
"eval_runtime": 21.1323,
"eval_samples": 2000,
"eval_samples_per_second": 94.642,
"eval_steps_per_second": 11.83
}

2000
models/t5_v1_1/generated_predictions.txt Normal file
View File

File diff suppressed because it is too large Load Diff

7
models/t5_v1_1/generation_config.json Normal file
View File

@ -0,0 +1,7 @@
{
"_from_model_config": true,
"decoder_start_token_id": 0,
"eos_token_id": 1,
"pad_token_id": 0,
"transformers_version": "4.26.1"
}

10
models/t5_v1_1/predict_results.json Normal file
View File

@ -0,0 +1,10 @@
{
"predict_accuracy": 1.0,
"predict_bleu": 0.0,
"predict_gen_len": 2.0,
"predict_loss": 0.5152234435081482,
"predict_runtime": 20.0795,
"predict_samples": 2000,
"predict_samples_per_second": 99.604,
"predict_steps_per_second": 12.451
}

BIN
models/t5_v1_1/pytorch_model.bin Normal file
View File

Binary file not shown.

107
models/t5_v1_1/special_tokens_map.json Normal file
View File

@ -0,0 +1,107 @@
{
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"eos_token": "</s>",
"pad_token": "<pad>",
"unk_token": "<unk>"
}

BIN
models/t5_v1_1/spiece.model Normal file
View File

Binary file not shown.

129425
models/t5_v1_1/tokenizer.json Normal file
View File

File diff suppressed because one or more lines are too long

113
models/t5_v1_1/tokenizer_config.json Normal file
View File

@ -0,0 +1,113 @@
{
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"eos_token": "</s>",
"extra_ids": 100,
"model_max_length": 512,
"name_or_path": "google/t5-v1_1-small",
"pad_token": "<pad>",
"sp_model_kwargs": {},
"special_tokens_map_file": ".cache_training/models--google--t5-v1_1-small/snapshots/8a88af75516269158a3aa488d1abdfd3d5e4ee49/special_tokens_map.json",
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

8
models/t5_v1_1/train_results.json Normal file
View File

@ -0,0 +1,8 @@
{
"epoch": 1.0,
"train_loss": 3.4401537475585937,
"train_runtime": 242.9807,
"train_samples": 16000,
"train_samples_per_second": 65.849,
"train_steps_per_second": 8.231
}

49
models/t5_v1_1/trainer_state.json Normal file
View File

@ -0,0 +1,49 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.25,
"learning_rate": 3.7500000000000003e-05,
"loss": 10.2845,
"step": 500
},
{
"epoch": 0.5,
"learning_rate": 2.5e-05,
"loss": 1.4701,
"step": 1000
},
{
"epoch": 0.75,
"learning_rate": 1.25e-05,
"loss": 1.042,
"step": 1500
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.9641,
"step": 2000
},
{
"epoch": 1.0,
"step": 2000,
"total_flos": 289235175800832.0,
"train_loss": 3.4401537475585937,
"train_runtime": 242.9807,
"train_samples_per_second": 65.849,
"train_steps_per_second": 8.231
}
],
"max_steps": 2000,
"num_train_epochs": 1,
"total_flos": 289235175800832.0,
"trial_name": null,
"trial_params": null
}

BIN
models/t5_v1_1/training_args.bin Normal file
View File

Binary file not shown.