初始化项目，由ModelHub XC社区提供模型
Model: simonneupane/controlled-food-recipe-generation Source: Original Platform
This commit is contained in:
ModelHub XC
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50256,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 1024,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": null,
|
||||
"n_layer": 12,
|
||||
"n_positions": 1024,
|
||||
"reorder_and_upcast_attn": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"scale_attn_by_inverse_layer_idx": false,
|
||||
"scale_attn_weights": true,
|
||||
"summary_activation": null,
|
||||
"summary_first_dropout": 0.1,
|
||||
"summary_proj_to_labels": true,
|
||||
"summary_type": "cls_index",
|
||||
"summary_use_proj": true,
|
||||
"task_specific_params": {
|
||||
"text-generation": {
|
||||
"do_sample": true,
|
||||
"max_length": 50
|
||||
}
|
||||
},
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50270
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,53 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: mit
|
||||
base_model: gpt2
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: controlled-food-recipe-generation
|
||||
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. -->
|
||||
|
||||
# controlled-food-recipe-generation
|
||||
|
||||
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
||||
|
||||
## 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: 3e-05
|
||||
- train_batch_size: 16
|
||||
- eval_batch_size: 32
|
||||
- seed: 42
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 32
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: linear
|
||||
- lr_scheduler_warmup_steps: 100
|
||||
- num_epochs: 3
|
||||
- mixed_precision_training: Native AMP
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.52.4
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 3.6.0
|
||||
- Tokenizers 0.21.1
|
||||
Binary file not shown.
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,127 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"50256": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50257": {
|
||||
"content": "<INPUT_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": "<NEXT_INPUT>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": "<INPUT_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": "<TITLE_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": "<TITLE_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": "<INGR_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": "<NEXT_INGR>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": "<INGR_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": "<INSTR_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": "<NEXT_STEP>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": "<INSTR_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": "<RECIPE_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": "<RECIPE_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 1024,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.03187200203980813,
|
||||
"eval_steps": 500,
|
||||
"global_step": 2000,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.007968000509952033,
|
||||
"grad_norm": 118279.4375,
|
||||
"learning_rate": 2.9936381561814055e-05,
|
||||
"loss": 1.2421,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.015936001019904066,
|
||||
"grad_norm": 93984.2109375,
|
||||
"learning_rate": 2.9856659208197584e-05,
|
||||
"loss": 0.7745,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 0.023904001529856098,
|
||||
"grad_norm": 78285.7578125,
|
||||
"learning_rate": 2.9776936854581113e-05,
|
||||
"loss": 0.73,
|
||||
"step": 1500
|
||||
},
|
||||
{
|
||||
"epoch": 0.03187200203980813,
|
||||
"grad_norm": 72728.3359375,
|
||||
"learning_rate": 2.9697214500964642e-05,
|
||||
"loss": 0.7087,
|
||||
"step": 2000
|
||||
}
|
||||
],
|
||||
"logging_steps": 500,
|
||||
"max_steps": 188253,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 1000,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 4180672512000000.0,
|
||||
"train_batch_size": 16,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a90f40534f604576f9df857da789f69f5554f078113862b5cc7a65d322544c44
|
||||
size 497814144
|
||||
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ca7d086830480ea81f7fbc4697a77f87cfdd80e26cccb0695f6a8eba0263b548
|
||||
size 995722170
|
||||
Binary file not shown.
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.52.4"
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"<INGR_END>": 50264,
|
||||
"<INGR_START>": 50262,
|
||||
"<INPUT_END>": 50259,
|
||||
"<INPUT_START>": 50257,
|
||||
"<INSTR_END>": 50267,
|
||||
"<INSTR_START>": 50265,
|
||||
"<NEXT_INGR>": 50263,
|
||||
"<NEXT_INPUT>": 50258,
|
||||
"<NEXT_STEP>": 50266,
|
||||
"<RECIPE_END>": 50269,
|
||||
"<RECIPE_START>": 50268,
|
||||
"<TITLE_END>": 50261,
|
||||
"<TITLE_START>": 50260
|
||||
}
|
||||
Binary file not shown.
@@ -0,0 +1 @@
|
||||
580e9f47845b23eb0c9d10be02202bd6ea7324fc
|
||||
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
@@ -0,0 +1,53 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: mit
|
||||
base_model: gpt2
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: controlled-food-recipe-generation
|
||||
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. -->
|
||||
|
||||
# controlled-food-recipe-generation
|
||||
|
||||
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
||||
|
||||
## 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: 3e-05
|
||||
- train_batch_size: 16
|
||||
- eval_batch_size: 32
|
||||
- seed: 42
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 32
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: linear
|
||||
- lr_scheduler_warmup_steps: 100
|
||||
- num_epochs: 3
|
||||
- mixed_precision_training: Native AMP
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.52.4
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 3.6.0
|
||||
- Tokenizers 0.21.1
|
||||
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"<INGR_END>": 50264,
|
||||
"<INGR_START>": 50262,
|
||||
"<INPUT_END>": 50259,
|
||||
"<INPUT_START>": 50257,
|
||||
"<INSTR_END>": 50267,
|
||||
"<INSTR_START>": 50265,
|
||||
"<NEXT_INGR>": 50263,
|
||||
"<NEXT_INPUT>": 50258,
|
||||
"<NEXT_STEP>": 50266,
|
||||
"<RECIPE_END>": 50269,
|
||||
"<RECIPE_START>": 50268,
|
||||
"<TITLE_END>": 50261,
|
||||
"<TITLE_START>": 50260
|
||||
}
|
||||
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50256,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 1024,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": null,
|
||||
"n_layer": 12,
|
||||
"n_positions": 1024,
|
||||
"reorder_and_upcast_attn": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"scale_attn_by_inverse_layer_idx": false,
|
||||
"scale_attn_weights": true,
|
||||
"summary_activation": null,
|
||||
"summary_first_dropout": 0.1,
|
||||
"summary_proj_to_labels": true,
|
||||
"summary_type": "cls_index",
|
||||
"summary_use_proj": true,
|
||||
"task_specific_params": {
|
||||
"text-generation": {
|
||||
"do_sample": true,
|
||||
"max_length": 50
|
||||
}
|
||||
},
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50270
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.52.4"
|
||||
}
|
||||
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"<INGR_END>": 50264,
|
||||
"<INGR_START>": 50262,
|
||||
"<INPUT_END>": 50259,
|
||||
"<INPUT_START>": 50257,
|
||||
"<INSTR_END>": 50267,
|
||||
"<INSTR_START>": 50265,
|
||||
"<NEXT_INGR>": 50263,
|
||||
"<NEXT_INPUT>": 50258,
|
||||
"<NEXT_STEP>": 50266,
|
||||
"<RECIPE_END>": 50269,
|
||||
"<RECIPE_START>": 50268,
|
||||
"<TITLE_END>": 50261,
|
||||
"<TITLE_START>": 50260
|
||||
}
|
||||
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50256,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 1024,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": null,
|
||||
"n_layer": 12,
|
||||
"n_positions": 1024,
|
||||
"reorder_and_upcast_attn": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"scale_attn_by_inverse_layer_idx": false,
|
||||
"scale_attn_weights": true,
|
||||
"summary_activation": null,
|
||||
"summary_first_dropout": 0.1,
|
||||
"summary_proj_to_labels": true,
|
||||
"summary_type": "cls_index",
|
||||
"summary_use_proj": true,
|
||||
"task_specific_params": {
|
||||
"text-generation": {
|
||||
"do_sample": true,
|
||||
"max_length": 50
|
||||
}
|
||||
},
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50270
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.52.4"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a90f40534f604576f9df857da789f69f5554f078113862b5cc7a65d322544c44
|
||||
size 497814144
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ca7d086830480ea81f7fbc4697a77f87cfdd80e26cccb0695f6a8eba0263b548
|
||||
size 995722170
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9613f165c7983300ac260c5256d2e40a5fddc234b9ea93fff078259d19e674dc
|
||||
size 14244
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
|
||||
size 988
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8225cd855d0baebe071863db33353181a98704ef920817b79ac4d578d92cfa31
|
||||
size 1064
|
||||
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,127 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"50256": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50257": {
|
||||
"content": "<INPUT_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": "<NEXT_INPUT>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": "<INPUT_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": "<TITLE_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": "<TITLE_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": "<INGR_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": "<NEXT_INGR>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": "<INGR_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": "<INSTR_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": "<NEXT_STEP>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": "<INSTR_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": "<RECIPE_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": "<RECIPE_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 1024,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.03187200203980813,
|
||||
"eval_steps": 500,
|
||||
"global_step": 2000,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.007968000509952033,
|
||||
"grad_norm": 118279.4375,
|
||||
"learning_rate": 2.9936381561814055e-05,
|
||||
"loss": 1.2421,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.015936001019904066,
|
||||
"grad_norm": 93984.2109375,
|
||||
"learning_rate": 2.9856659208197584e-05,
|
||||
"loss": 0.7745,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 0.023904001529856098,
|
||||
"grad_norm": 78285.7578125,
|
||||
"learning_rate": 2.9776936854581113e-05,
|
||||
"loss": 0.73,
|
||||
"step": 1500
|
||||
},
|
||||
{
|
||||
"epoch": 0.03187200203980813,
|
||||
"grad_norm": 72728.3359375,
|
||||
"learning_rate": 2.9697214500964642e-05,
|
||||
"loss": 0.7087,
|
||||
"step": 2000
|
||||
}
|
||||
],
|
||||
"logging_steps": 500,
|
||||
"max_steps": 188253,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 1000,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 4180672512000000.0,
|
||||
"train_batch_size": 16,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c2e7fcb26e3e3848d243625e49f36d2273fbe5c83ece34d46111c33604627a5b
|
||||
size 5368
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:da95de961c5fb3d0a3f1731fe1c2359a0c7bf25b33787bc95384f23fe090c360
|
||||
size 11353
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2a2bcf27210ecac6445b4fe91ea33ce8d1ef0fe1e674dface52bc3202cc443cf
|
||||
size 25286
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a955400898c05287b5b58720427850d09aa1706c6a220d4c70d8cc3f13652102
|
||||
size 5081
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:347dd1c2c3debc6a8720f970d8c810dd55f20054ed1295e0429bba74aea735c9
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:de511e2aff8aec50f56506a4d453b836ad0c2e858090c2a7f49c427fc8db70de
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:78095757d924d052f6a0cabf736b3f929c822728ce9e7dcffc693d93e41a7a7e
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:27617536009dd3c4482fd830ce731581dea0c8c34026aa83f068c40e235dee85
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:26657b4265609dbd747f23010ec98e121811337d0c8f206ba2295767266b7c14
|
||||
size 5142
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:84635da10e4293ca98e4ab09219c605aff6a9e2063436d7c931fb11bd501e73d
|
||||
size 5142
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cc65cb7013b8f2509e3def68792a819e824f8fd3fa9e417ec5982b1afb8a503f
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1ec921edbc45bb131a96af962a7f4000785f6eade03411f7facd811fb3e4d3bd
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:69dd7768d90060fd258e03f09c5cb49f5458593c5c9fb6cb986f98f9614b4f71
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e57b35d1df50f788c981d90d40c4f5f8c18d2c72e1ff6ddbf92466411f5bae8f
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ec13d99b79a44c4a0f2c21aeec46b3361a26e8f77ebe1b4f68bc8fa672281dfc
|
||||
size 5142
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7981afeb9a7c96521b6f80565900669f7e5913c5b5b95ba5ef7d1f2116f80e59
|
||||
size 5142
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:723923dc88275cf797b3f9935b358330cd419cbfe97ccce20ca661ac1bd9fd7e
|
||||
size 5142
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:632879f94a9617b4774956b467f692fd563b1312e0424fdc77165c739dbf3158
|
||||
size 5142
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:739a6fc016aab02b7ce054e6e14a8c9a4bff35d40bed122d2e04dca553a4e4a2
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:55546c8438f3abe1f326db166051de9ea92100eb39a408f3d23d12308b93982e
|
||||
size 5154
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aa2e2ab14339aa47825765627f5db692d6145b68ab9a117b6da268fe73d3666d
|
||||
size 5142
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fb993ae6193faa55e2f015730eb53f8965f772dcb73c6e8d12da00dbb33a0adb
|
||||
size 8566
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0cf3cc064fb09acf40a630cecc6d594e3b5f3ac925b81485ab2e4553a2972f3d
|
||||
size 5728
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8513af429315a463a6608a71ff04870f4d60144db6d139be5adb1cca64d81be3
|
||||
size 31743
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8ae418bdfaf505ce47938674537dd3c25e6de7e4056595d73809edacaa0c1439
|
||||
size 18972
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a11630ce9819438a76859567230a0a7560f20acd371d269c582e5d04723f5ac0
|
||||
size 22283
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4ba16ef1de147cd1aba034ed860027f464b2069e2aab00f268fe509181d818c1
|
||||
size 35527
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:674c7b15319bcc941ba9a7433a5590e72cd408db8f47dd76b3606ede6cae0fa7
|
||||
size 35527
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a90f40534f604576f9df857da789f69f5554f078113862b5cc7a65d322544c44
|
||||
size 497814144
|
||||
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,127 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"50256": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50257": {
|
||||
"content": "<INPUT_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": "<NEXT_INPUT>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": "<INPUT_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": "<TITLE_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": "<TITLE_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": "<INGR_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": "<NEXT_INGR>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": "<INGR_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": "<INSTR_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": "<NEXT_STEP>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": "<INSTR_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": "<RECIPE_START>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": "<RECIPE_END>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 1024,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c2e7fcb26e3e3848d243625e49f36d2273fbe5c83ece34d46111c33604627a5b
|
||||
size 5368
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user