Instructions to use bobyres/mistral_label with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bobyres/mistral_label with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bofenghuang/vigogne-2-7b-instruct") model = PeftModel.from_pretrained(base_model, "bobyres/mistral_label") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- README.md +159 -0
- adapter_config.json +34 -0
- adapter_model.bin +3 -0
- added_tokens.json +3 -0
- checkpoint-117/README.md +204 -0
- checkpoint-117/adapter_config.json +34 -0
- checkpoint-117/adapter_model.safetensors +3 -0
- checkpoint-117/optimizer.pt +3 -0
- checkpoint-117/rng_state.pth +3 -0
- checkpoint-117/scheduler.pt +3 -0
- checkpoint-117/trainer_state.json +1000 -0
- checkpoint-117/training_args.bin +3 -0
- checkpoint-39/README.md +204 -0
- checkpoint-39/adapter_config.json +34 -0
- checkpoint-39/adapter_model.safetensors +3 -0
- checkpoint-39/optimizer.pt +3 -0
- checkpoint-39/rng_state.pth +3 -0
- checkpoint-39/scheduler.pt +3 -0
- checkpoint-39/trainer_state.json +350 -0
- checkpoint-39/training_args.bin +3 -0
- checkpoint-78/README.md +204 -0
- checkpoint-78/adapter_config.json +34 -0
- checkpoint-78/adapter_model.safetensors +3 -0
- checkpoint-78/optimizer.pt +3 -0
- checkpoint-78/rng_state.pth +3 -0
- checkpoint-78/scheduler.pt +3 -0
- checkpoint-78/trainer_state.json +679 -0
- checkpoint-78/training_args.bin +3 -0
- config.json +44 -0
- merged/added_tokens.json +3 -0
- merged/config.json +30 -0
- merged/generation_config.json +10 -0
- merged/pytorch_model-00001-of-00003.bin +3 -0
- merged/pytorch_model-00002-of-00003.bin +3 -0
- merged/pytorch_model-00003-of-00003.bin +3 -0
- merged/pytorch_model.bin.index.json +298 -0
- merged/special_tokens_map.json +24 -0
- merged/tokenizer.model +3 -0
- merged/tokenizer_config.json +52 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +52 -0
README.md
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
base_model: bofenghuang/vigogne-2-7b-instruct
|
| 6 |
+
model-index:
|
| 7 |
+
- name: qlora-out
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 15 |
+
<details><summary>See axolotl config</summary>
|
| 16 |
+
|
| 17 |
+
axolotl version: `0.4.0`
|
| 18 |
+
```yaml
|
| 19 |
+
base_model: bofenghuang/vigogne-2-7b-instruct
|
| 20 |
+
base_model_config: bofenghuang/vigogne-2-7b-instruct
|
| 21 |
+
model_type: LlamaForCausalLM
|
| 22 |
+
tokenizer_type: LlamaTokenizer
|
| 23 |
+
is_llama_derived_model: true
|
| 24 |
+
|
| 25 |
+
load_in_8bit: false
|
| 26 |
+
load_in_4bit: true
|
| 27 |
+
strict: false
|
| 28 |
+
|
| 29 |
+
datasets:
|
| 30 |
+
- path: bobyres/LabelV01
|
| 31 |
+
type: alpaca
|
| 32 |
+
|
| 33 |
+
dataset_prepared_path: last_run_prepared
|
| 34 |
+
val_set_size: 0.05
|
| 35 |
+
output_dir: ./qlora-out
|
| 36 |
+
adapter: qlora
|
| 37 |
+
lora_model_dir:
|
| 38 |
+
|
| 39 |
+
sequence_len: 4096
|
| 40 |
+
sample_packing: false
|
| 41 |
+
pad_to_sequence_len: true
|
| 42 |
+
|
| 43 |
+
lora_r: 32
|
| 44 |
+
lora_alpha: 16
|
| 45 |
+
lora_dropout: 0.05
|
| 46 |
+
lora_target_modules:
|
| 47 |
+
lora_target_linear: true
|
| 48 |
+
lora_fan_in_fan_out:
|
| 49 |
+
|
| 50 |
+
wandb_project: "finetune_labelisation_v011"
|
| 51 |
+
wandb_entity:
|
| 52 |
+
wandb_watch:
|
| 53 |
+
wandb_run_id:
|
| 54 |
+
wandb_log_model: "checkpoint"
|
| 55 |
+
|
| 56 |
+
gradient_accumulation_steps: 1
|
| 57 |
+
micro_batch_size: 1
|
| 58 |
+
num_epochs: 3
|
| 59 |
+
optimizer: paged_adamw_32bit
|
| 60 |
+
lr_scheduler: cosine
|
| 61 |
+
learning_rate: 0.0002
|
| 62 |
+
|
| 63 |
+
train_on_inputs: false
|
| 64 |
+
group_by_length: false
|
| 65 |
+
bf16: true
|
| 66 |
+
fp16: false
|
| 67 |
+
tf32: false
|
| 68 |
+
|
| 69 |
+
gradient_checkpointing: true
|
| 70 |
+
early_stopping_patience:
|
| 71 |
+
resume_from_checkpoint:
|
| 72 |
+
local_rank:
|
| 73 |
+
logging_steps: 1
|
| 74 |
+
xformers_attention:
|
| 75 |
+
flash_attention: true
|
| 76 |
+
|
| 77 |
+
warmup_steps: 10
|
| 78 |
+
eval_steps: 0.05
|
| 79 |
+
eval_table_size:
|
| 80 |
+
save_steps:
|
| 81 |
+
debug:
|
| 82 |
+
deepspeed:
|
| 83 |
+
weight_decay: 0.0
|
| 84 |
+
fsdp:
|
| 85 |
+
fsdp_config:
|
| 86 |
+
special_tokens:
|
| 87 |
+
bos_token: "<s>"
|
| 88 |
+
eos_token: "</s>"
|
| 89 |
+
unk_token: "<unk>"
|
| 90 |
+
|
| 91 |
+
```
|
| 92 |
+
|
| 93 |
+
</details><br>
|
| 94 |
+
|
| 95 |
+
# qlora-out
|
| 96 |
+
|
| 97 |
+
This model is a fine-tuned version of [bofenghuang/vigogne-2-7b-instruct](https://huggingface.co/bofenghuang/vigogne-2-7b-instruct) on the None dataset.
|
| 98 |
+
It achieves the following results on the evaluation set:
|
| 99 |
+
- Loss: 0.6592
|
| 100 |
+
|
| 101 |
+
## Model description
|
| 102 |
+
|
| 103 |
+
More information needed
|
| 104 |
+
|
| 105 |
+
## Intended uses & limitations
|
| 106 |
+
|
| 107 |
+
More information needed
|
| 108 |
+
|
| 109 |
+
## Training and evaluation data
|
| 110 |
+
|
| 111 |
+
More information needed
|
| 112 |
+
|
| 113 |
+
## Training procedure
|
| 114 |
+
|
| 115 |
+
### Training hyperparameters
|
| 116 |
+
|
| 117 |
+
The following hyperparameters were used during training:
|
| 118 |
+
- learning_rate: 0.0002
|
| 119 |
+
- train_batch_size: 1
|
| 120 |
+
- eval_batch_size: 1
|
| 121 |
+
- seed: 42
|
| 122 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 123 |
+
- lr_scheduler_type: cosine
|
| 124 |
+
- lr_scheduler_warmup_steps: 10
|
| 125 |
+
- num_epochs: 3
|
| 126 |
+
|
| 127 |
+
### Training results
|
| 128 |
+
|
| 129 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 130 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 131 |
+
| 1.0134 | 0.03 | 1 | 1.0981 |
|
| 132 |
+
| 0.972 | 0.15 | 6 | 1.0736 |
|
| 133 |
+
| 0.7982 | 0.31 | 12 | 0.8548 |
|
| 134 |
+
| 0.6944 | 0.46 | 18 | 0.7151 |
|
| 135 |
+
| 0.6808 | 0.62 | 24 | 0.6943 |
|
| 136 |
+
| 0.6763 | 0.77 | 30 | 0.6821 |
|
| 137 |
+
| 0.67 | 0.92 | 36 | 0.6764 |
|
| 138 |
+
| 0.6424 | 1.08 | 42 | 0.6730 |
|
| 139 |
+
| 0.6552 | 1.23 | 48 | 0.6780 |
|
| 140 |
+
| 0.6527 | 1.38 | 54 | 0.6690 |
|
| 141 |
+
| 0.6624 | 1.54 | 60 | 0.6632 |
|
| 142 |
+
| 0.6228 | 1.69 | 66 | 0.6625 |
|
| 143 |
+
| 0.6447 | 1.85 | 72 | 0.6617 |
|
| 144 |
+
| 0.6409 | 2.0 | 78 | 0.6599 |
|
| 145 |
+
| 0.6356 | 2.15 | 84 | 0.6589 |
|
| 146 |
+
| 0.648 | 2.31 | 90 | 0.6584 |
|
| 147 |
+
| 0.6254 | 2.46 | 96 | 0.6593 |
|
| 148 |
+
| 0.6167 | 2.62 | 102 | 0.6596 |
|
| 149 |
+
| 0.6451 | 2.77 | 108 | 0.6590 |
|
| 150 |
+
| 0.6144 | 2.92 | 114 | 0.6592 |
|
| 151 |
+
|
| 152 |
+
|
| 153 |
+
### Framework versions
|
| 154 |
+
|
| 155 |
+
- PEFT 0.11.0
|
| 156 |
+
- Transformers 4.39.0.dev0
|
| 157 |
+
- Pytorch 2.0.1+cu118
|
| 158 |
+
- Datasets 2.17.1
|
| 159 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bofenghuang/vigogne-2-7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f639f1af3f25b7351008689e4b9606f7f72fcfa0448341d7b0ca903a24be8bfb
|
| 3 |
+
size 844282325
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
checkpoint-117/README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: bofenghuang/vigogne-2-7b-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.11.0
|
checkpoint-117/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bofenghuang/vigogne-2-7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-117/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6acc8e3befe5ecbdc8e002ce4f98fb71de8ed145a725538f2284269452f8a3f8
|
| 3 |
+
size 844180648
|
checkpoint-117/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d25b2a4c0f6aca2aa0addb815dcd969553f4eb5031a4ddf81b131fc98dc55e4
|
| 3 |
+
size 639908165
|
checkpoint-117/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:924eb59ef423e249e235207616d4c9a0f37d2845336ee2273a901a150b556efd
|
| 3 |
+
size 14575
|
checkpoint-117/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce1c56cfee47dad49f17989a23abbcf9690fd7b649d25374cdccb77510dc1d23
|
| 3 |
+
size 627
|
checkpoint-117/trainer_state.json
ADDED
|
@@ -0,0 +1,1000 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 6,
|
| 6 |
+
"global_step": 117,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 0.08957596868276596,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 1.0134,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"eval_loss": 1.0981205701828003,
|
| 21 |
+
"eval_runtime": 2.5128,
|
| 22 |
+
"eval_samples_per_second": 1.194,
|
| 23 |
+
"eval_steps_per_second": 1.194,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05,
|
| 28 |
+
"grad_norm": 0.07771213352680206,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 0.9545,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"grad_norm": 0.1224137470126152,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 1.1733,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"grad_norm": 0.09190034121274948,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 0.9954,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13,
|
| 49 |
+
"grad_norm": 0.08263542503118515,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 0.9486,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.15,
|
| 56 |
+
"grad_norm": 0.09250061959028244,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 0.972,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15,
|
| 63 |
+
"eval_loss": 1.0735869407653809,
|
| 64 |
+
"eval_runtime": 2.5357,
|
| 65 |
+
"eval_samples_per_second": 1.183,
|
| 66 |
+
"eval_steps_per_second": 1.183,
|
| 67 |
+
"step": 6
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.18,
|
| 71 |
+
"grad_norm": 0.1398034691810608,
|
| 72 |
+
"learning_rate": 0.00014,
|
| 73 |
+
"loss": 1.0445,
|
| 74 |
+
"step": 7
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.21,
|
| 78 |
+
"grad_norm": 0.0993918851017952,
|
| 79 |
+
"learning_rate": 0.00016,
|
| 80 |
+
"loss": 0.9169,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.23,
|
| 85 |
+
"grad_norm": 0.07937725633382797,
|
| 86 |
+
"learning_rate": 0.00018,
|
| 87 |
+
"loss": 0.8462,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.26,
|
| 92 |
+
"grad_norm": 0.10001373291015625,
|
| 93 |
+
"learning_rate": 0.0002,
|
| 94 |
+
"loss": 0.8708,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.28,
|
| 99 |
+
"grad_norm": 0.1337287873029709,
|
| 100 |
+
"learning_rate": 0.00019995690062269984,
|
| 101 |
+
"loss": 0.86,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.31,
|
| 106 |
+
"grad_norm": 0.11684636771678925,
|
| 107 |
+
"learning_rate": 0.00019982763964192585,
|
| 108 |
+
"loss": 0.7982,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.31,
|
| 113 |
+
"eval_loss": 0.8548387885093689,
|
| 114 |
+
"eval_runtime": 2.5536,
|
| 115 |
+
"eval_samples_per_second": 1.175,
|
| 116 |
+
"eval_steps_per_second": 1.175,
|
| 117 |
+
"step": 12
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.33,
|
| 121 |
+
"grad_norm": 0.12103456258773804,
|
| 122 |
+
"learning_rate": 0.0001996123284790336,
|
| 123 |
+
"loss": 0.7906,
|
| 124 |
+
"step": 13
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.36,
|
| 128 |
+
"grad_norm": 0.1426106095314026,
|
| 129 |
+
"learning_rate": 0.00019931115272956405,
|
| 130 |
+
"loss": 0.7825,
|
| 131 |
+
"step": 14
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.38,
|
| 135 |
+
"grad_norm": 0.12367941439151764,
|
| 136 |
+
"learning_rate": 0.0001989243720032624,
|
| 137 |
+
"loss": 0.7341,
|
| 138 |
+
"step": 15
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.41,
|
| 142 |
+
"grad_norm": 0.10154826194047928,
|
| 143 |
+
"learning_rate": 0.00019845231970029773,
|
| 144 |
+
"loss": 0.7064,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.44,
|
| 149 |
+
"grad_norm": 0.13628405332565308,
|
| 150 |
+
"learning_rate": 0.0001978954027238763,
|
| 151 |
+
"loss": 0.6988,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.46,
|
| 156 |
+
"grad_norm": 0.11276472359895706,
|
| 157 |
+
"learning_rate": 0.0001972541011294959,
|
| 158 |
+
"loss": 0.6944,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.46,
|
| 163 |
+
"eval_loss": 0.7151015400886536,
|
| 164 |
+
"eval_runtime": 2.5734,
|
| 165 |
+
"eval_samples_per_second": 1.166,
|
| 166 |
+
"eval_steps_per_second": 1.166,
|
| 167 |
+
"step": 18
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.49,
|
| 171 |
+
"grad_norm": 0.13381372392177582,
|
| 172 |
+
"learning_rate": 0.00019652896771114414,
|
| 173 |
+
"loss": 0.6956,
|
| 174 |
+
"step": 19
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.51,
|
| 178 |
+
"grad_norm": 0.11248588562011719,
|
| 179 |
+
"learning_rate": 0.00019572062752479683,
|
| 180 |
+
"loss": 0.7155,
|
| 181 |
+
"step": 20
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.54,
|
| 185 |
+
"grad_norm": 0.17762312293052673,
|
| 186 |
+
"learning_rate": 0.00019482977734962753,
|
| 187 |
+
"loss": 0.7357,
|
| 188 |
+
"step": 21
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.56,
|
| 192 |
+
"grad_norm": 0.10546916723251343,
|
| 193 |
+
"learning_rate": 0.00019385718508739262,
|
| 194 |
+
"loss": 0.6691,
|
| 195 |
+
"step": 22
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.59,
|
| 199 |
+
"grad_norm": 0.3150898516178131,
|
| 200 |
+
"learning_rate": 0.00019280368910050942,
|
| 201 |
+
"loss": 0.7167,
|
| 202 |
+
"step": 23
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.62,
|
| 206 |
+
"grad_norm": 0.13151158392429352,
|
| 207 |
+
"learning_rate": 0.00019167019748939846,
|
| 208 |
+
"loss": 0.6808,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.62,
|
| 213 |
+
"eval_loss": 0.6942548751831055,
|
| 214 |
+
"eval_runtime": 2.5831,
|
| 215 |
+
"eval_samples_per_second": 1.161,
|
| 216 |
+
"eval_steps_per_second": 1.161,
|
| 217 |
+
"step": 24
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.64,
|
| 221 |
+
"grad_norm": 0.14906296133995056,
|
| 222 |
+
"learning_rate": 0.00019045768730971196,
|
| 223 |
+
"loss": 0.6762,
|
| 224 |
+
"step": 25
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.67,
|
| 228 |
+
"grad_norm": 0.19484123587608337,
|
| 229 |
+
"learning_rate": 0.00018916720373012426,
|
| 230 |
+
"loss": 0.6854,
|
| 231 |
+
"step": 26
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.69,
|
| 235 |
+
"grad_norm": 0.12819896638393402,
|
| 236 |
+
"learning_rate": 0.00018779985913140924,
|
| 237 |
+
"loss": 0.6873,
|
| 238 |
+
"step": 27
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.72,
|
| 242 |
+
"grad_norm": 0.21385614573955536,
|
| 243 |
+
"learning_rate": 0.00018635683214758214,
|
| 244 |
+
"loss": 0.6874,
|
| 245 |
+
"step": 28
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.74,
|
| 249 |
+
"grad_norm": 0.12286895513534546,
|
| 250 |
+
"learning_rate": 0.0001848393666499315,
|
| 251 |
+
"loss": 0.6843,
|
| 252 |
+
"step": 29
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.77,
|
| 256 |
+
"grad_norm": 0.08534862101078033,
|
| 257 |
+
"learning_rate": 0.00018324877067481783,
|
| 258 |
+
"loss": 0.6763,
|
| 259 |
+
"step": 30
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.77,
|
| 263 |
+
"eval_loss": 0.6821426749229431,
|
| 264 |
+
"eval_runtime": 2.5911,
|
| 265 |
+
"eval_samples_per_second": 1.158,
|
| 266 |
+
"eval_steps_per_second": 1.158,
|
| 267 |
+
"step": 30
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.79,
|
| 271 |
+
"grad_norm": 0.17990928888320923,
|
| 272 |
+
"learning_rate": 0.0001815864152961624,
|
| 273 |
+
"loss": 0.6789,
|
| 274 |
+
"step": 31
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.82,
|
| 278 |
+
"grad_norm": 0.12137839943170547,
|
| 279 |
+
"learning_rate": 0.0001798537334435986,
|
| 280 |
+
"loss": 0.6877,
|
| 281 |
+
"step": 32
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.85,
|
| 285 |
+
"grad_norm": 0.10240964591503143,
|
| 286 |
+
"learning_rate": 0.00017805221866730458,
|
| 287 |
+
"loss": 0.6725,
|
| 288 |
+
"step": 33
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.87,
|
| 292 |
+
"grad_norm": 0.14333295822143555,
|
| 293 |
+
"learning_rate": 0.00017618342385058145,
|
| 294 |
+
"loss": 0.6745,
|
| 295 |
+
"step": 34
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.9,
|
| 299 |
+
"grad_norm": 0.0904482752084732,
|
| 300 |
+
"learning_rate": 0.00017424895987128722,
|
| 301 |
+
"loss": 0.6894,
|
| 302 |
+
"step": 35
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.92,
|
| 306 |
+
"grad_norm": 0.11753042787313461,
|
| 307 |
+
"learning_rate": 0.00017225049421328023,
|
| 308 |
+
"loss": 0.67,
|
| 309 |
+
"step": 36
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.92,
|
| 313 |
+
"eval_loss": 0.6763580441474915,
|
| 314 |
+
"eval_runtime": 2.5955,
|
| 315 |
+
"eval_samples_per_second": 1.156,
|
| 316 |
+
"eval_steps_per_second": 1.156,
|
| 317 |
+
"step": 36
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.95,
|
| 321 |
+
"grad_norm": 0.13719823956489563,
|
| 322 |
+
"learning_rate": 0.00017018974952906884,
|
| 323 |
+
"loss": 0.6589,
|
| 324 |
+
"step": 37
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.97,
|
| 328 |
+
"grad_norm": 0.1040361225605011,
|
| 329 |
+
"learning_rate": 0.0001680685021549063,
|
| 330 |
+
"loss": 0.666,
|
| 331 |
+
"step": 38
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0,
|
| 335 |
+
"grad_norm": 0.07594098895788193,
|
| 336 |
+
"learning_rate": 0.00016588858057961113,
|
| 337 |
+
"loss": 0.645,
|
| 338 |
+
"step": 39
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.03,
|
| 342 |
+
"grad_norm": 0.08139798045158386,
|
| 343 |
+
"learning_rate": 0.0001636518638684325,
|
| 344 |
+
"loss": 0.6542,
|
| 345 |
+
"step": 40
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.05,
|
| 349 |
+
"grad_norm": 0.07313457876443863,
|
| 350 |
+
"learning_rate": 0.0001613602800433194,
|
| 351 |
+
"loss": 0.6458,
|
| 352 |
+
"step": 41
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.08,
|
| 356 |
+
"grad_norm": 0.07903215289115906,
|
| 357 |
+
"learning_rate": 0.00015901580442098968,
|
| 358 |
+
"loss": 0.6424,
|
| 359 |
+
"step": 42
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.08,
|
| 363 |
+
"eval_loss": 0.6730008125305176,
|
| 364 |
+
"eval_runtime": 2.5989,
|
| 365 |
+
"eval_samples_per_second": 1.154,
|
| 366 |
+
"eval_steps_per_second": 1.154,
|
| 367 |
+
"step": 42
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.1,
|
| 371 |
+
"grad_norm": 0.09322352707386017,
|
| 372 |
+
"learning_rate": 0.00015662045791023173,
|
| 373 |
+
"loss": 0.6567,
|
| 374 |
+
"step": 43
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.13,
|
| 378 |
+
"grad_norm": 0.07249985635280609,
|
| 379 |
+
"learning_rate": 0.00015417630526990615,
|
| 380 |
+
"loss": 0.6384,
|
| 381 |
+
"step": 44
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.15,
|
| 385 |
+
"grad_norm": 0.07686451077461243,
|
| 386 |
+
"learning_rate": 0.0001516854533291494,
|
| 387 |
+
"loss": 0.665,
|
| 388 |
+
"step": 45
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.18,
|
| 392 |
+
"grad_norm": 0.07324113696813583,
|
| 393 |
+
"learning_rate": 0.00014915004917131344,
|
| 394 |
+
"loss": 0.6297,
|
| 395 |
+
"step": 46
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.21,
|
| 399 |
+
"grad_norm": 0.09203895926475525,
|
| 400 |
+
"learning_rate": 0.00014657227828320635,
|
| 401 |
+
"loss": 0.6539,
|
| 402 |
+
"step": 47
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.23,
|
| 406 |
+
"grad_norm": 0.09338624030351639,
|
| 407 |
+
"learning_rate": 0.00014395436267123016,
|
| 408 |
+
"loss": 0.6552,
|
| 409 |
+
"step": 48
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.23,
|
| 413 |
+
"eval_loss": 0.6780009269714355,
|
| 414 |
+
"eval_runtime": 2.6045,
|
| 415 |
+
"eval_samples_per_second": 1.152,
|
| 416 |
+
"eval_steps_per_second": 1.152,
|
| 417 |
+
"step": 48
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.26,
|
| 421 |
+
"grad_norm": 0.0812142863869667,
|
| 422 |
+
"learning_rate": 0.00014129855894603886,
|
| 423 |
+
"loss": 0.6319,
|
| 424 |
+
"step": 49
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.28,
|
| 428 |
+
"grad_norm": 0.19316132366657257,
|
| 429 |
+
"learning_rate": 0.00013860715637736818,
|
| 430 |
+
"loss": 0.7,
|
| 431 |
+
"step": 50
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.31,
|
| 435 |
+
"grad_norm": 0.10698059946298599,
|
| 436 |
+
"learning_rate": 0.0001358824749207136,
|
| 437 |
+
"loss": 0.6725,
|
| 438 |
+
"step": 51
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.33,
|
| 442 |
+
"grad_norm": 0.14100198447704315,
|
| 443 |
+
"learning_rate": 0.00013312686321755761,
|
| 444 |
+
"loss": 0.6766,
|
| 445 |
+
"step": 52
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.36,
|
| 449 |
+
"grad_norm": 0.09599179029464722,
|
| 450 |
+
"learning_rate": 0.00013034269657086992,
|
| 451 |
+
"loss": 0.645,
|
| 452 |
+
"step": 53
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.38,
|
| 456 |
+
"grad_norm": 0.08999059349298477,
|
| 457 |
+
"learning_rate": 0.000127532374897626,
|
| 458 |
+
"loss": 0.6527,
|
| 459 |
+
"step": 54
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.38,
|
| 463 |
+
"eval_loss": 0.6689873337745667,
|
| 464 |
+
"eval_runtime": 2.6108,
|
| 465 |
+
"eval_samples_per_second": 1.149,
|
| 466 |
+
"eval_steps_per_second": 1.149,
|
| 467 |
+
"step": 54
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.41,
|
| 471 |
+
"grad_norm": 0.13835830986499786,
|
| 472 |
+
"learning_rate": 0.00012469832066010843,
|
| 473 |
+
"loss": 0.6561,
|
| 474 |
+
"step": 55
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.44,
|
| 478 |
+
"grad_norm": 0.10695886611938477,
|
| 479 |
+
"learning_rate": 0.00012184297677777463,
|
| 480 |
+
"loss": 0.6668,
|
| 481 |
+
"step": 56
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.46,
|
| 485 |
+
"grad_norm": 0.0739368349313736,
|
| 486 |
+
"learning_rate": 0.00011896880452149077,
|
| 487 |
+
"loss": 0.643,
|
| 488 |
+
"step": 57
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.49,
|
| 492 |
+
"grad_norm": 0.21791452169418335,
|
| 493 |
+
"learning_rate": 0.00011607828139194683,
|
| 494 |
+
"loss": 0.6768,
|
| 495 |
+
"step": 58
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.51,
|
| 499 |
+
"grad_norm": 0.06241246312856674,
|
| 500 |
+
"learning_rate": 0.00011317389898408189,
|
| 501 |
+
"loss": 0.6252,
|
| 502 |
+
"step": 59
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.54,
|
| 506 |
+
"grad_norm": 0.1302526593208313,
|
| 507 |
+
"learning_rate": 0.00011025816083936036,
|
| 508 |
+
"loss": 0.6624,
|
| 509 |
+
"step": 60
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.54,
|
| 513 |
+
"eval_loss": 0.6632375121116638,
|
| 514 |
+
"eval_runtime": 2.6043,
|
| 515 |
+
"eval_samples_per_second": 1.152,
|
| 516 |
+
"eval_steps_per_second": 1.152,
|
| 517 |
+
"step": 60
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.56,
|
| 521 |
+
"grad_norm": 0.11702455580234528,
|
| 522 |
+
"learning_rate": 0.0001073335802877504,
|
| 523 |
+
"loss": 0.6522,
|
| 524 |
+
"step": 61
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.59,
|
| 528 |
+
"grad_norm": 0.08904154598712921,
|
| 529 |
+
"learning_rate": 0.00010440267828126478,
|
| 530 |
+
"loss": 0.6472,
|
| 531 |
+
"step": 62
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.62,
|
| 535 |
+
"grad_norm": 0.08021406084299088,
|
| 536 |
+
"learning_rate": 0.00010146798122093166,
|
| 537 |
+
"loss": 0.6279,
|
| 538 |
+
"step": 63
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.64,
|
| 542 |
+
"grad_norm": 0.07384659349918365,
|
| 543 |
+
"learning_rate": 9.853201877906836e-05,
|
| 544 |
+
"loss": 0.6262,
|
| 545 |
+
"step": 64
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.67,
|
| 549 |
+
"grad_norm": 0.06457240134477615,
|
| 550 |
+
"learning_rate": 9.559732171873523e-05,
|
| 551 |
+
"loss": 0.64,
|
| 552 |
+
"step": 65
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.69,
|
| 556 |
+
"grad_norm": 0.07967618852853775,
|
| 557 |
+
"learning_rate": 9.266641971224963e-05,
|
| 558 |
+
"loss": 0.6228,
|
| 559 |
+
"step": 66
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.69,
|
| 563 |
+
"eval_loss": 0.6625072360038757,
|
| 564 |
+
"eval_runtime": 2.6047,
|
| 565 |
+
"eval_samples_per_second": 1.152,
|
| 566 |
+
"eval_steps_per_second": 1.152,
|
| 567 |
+
"step": 66
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.72,
|
| 571 |
+
"grad_norm": 0.09555868804454803,
|
| 572 |
+
"learning_rate": 8.974183916063968e-05,
|
| 573 |
+
"loss": 0.635,
|
| 574 |
+
"step": 67
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.74,
|
| 578 |
+
"grad_norm": 0.07187359035015106,
|
| 579 |
+
"learning_rate": 8.682610101591814e-05,
|
| 580 |
+
"loss": 0.6277,
|
| 581 |
+
"step": 68
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.77,
|
| 585 |
+
"grad_norm": 0.091610848903656,
|
| 586 |
+
"learning_rate": 8.392171860805319e-05,
|
| 587 |
+
"loss": 0.6649,
|
| 588 |
+
"step": 69
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.79,
|
| 592 |
+
"grad_norm": 0.065833680331707,
|
| 593 |
+
"learning_rate": 8.103119547850924e-05,
|
| 594 |
+
"loss": 0.6262,
|
| 595 |
+
"step": 70
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 1.82,
|
| 599 |
+
"grad_norm": 0.09459354728460312,
|
| 600 |
+
"learning_rate": 7.815702322222538e-05,
|
| 601 |
+
"loss": 0.6359,
|
| 602 |
+
"step": 71
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.85,
|
| 606 |
+
"grad_norm": 0.06780053675174713,
|
| 607 |
+
"learning_rate": 7.530167933989161e-05,
|
| 608 |
+
"loss": 0.6447,
|
| 609 |
+
"step": 72
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.85,
|
| 613 |
+
"eval_loss": 0.6616933941841125,
|
| 614 |
+
"eval_runtime": 2.607,
|
| 615 |
+
"eval_samples_per_second": 1.151,
|
| 616 |
+
"eval_steps_per_second": 1.151,
|
| 617 |
+
"step": 72
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.87,
|
| 621 |
+
"grad_norm": 0.0954224094748497,
|
| 622 |
+
"learning_rate": 7.246762510237403e-05,
|
| 623 |
+
"loss": 0.6636,
|
| 624 |
+
"step": 73
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.9,
|
| 628 |
+
"grad_norm": 0.0937703400850296,
|
| 629 |
+
"learning_rate": 6.96573034291301e-05,
|
| 630 |
+
"loss": 0.6381,
|
| 631 |
+
"step": 74
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.92,
|
| 635 |
+
"grad_norm": 0.10935033112764359,
|
| 636 |
+
"learning_rate": 6.687313678244242e-05,
|
| 637 |
+
"loss": 0.628,
|
| 638 |
+
"step": 75
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.95,
|
| 642 |
+
"grad_norm": 0.08154003322124481,
|
| 643 |
+
"learning_rate": 6.411752507928642e-05,
|
| 644 |
+
"loss": 0.6386,
|
| 645 |
+
"step": 76
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.97,
|
| 649 |
+
"grad_norm": 0.12196218967437744,
|
| 650 |
+
"learning_rate": 6.139284362263185e-05,
|
| 651 |
+
"loss": 0.6317,
|
| 652 |
+
"step": 77
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.0,
|
| 656 |
+
"grad_norm": 0.11538293212652206,
|
| 657 |
+
"learning_rate": 5.870144105396118e-05,
|
| 658 |
+
"loss": 0.6409,
|
| 659 |
+
"step": 78
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.0,
|
| 663 |
+
"eval_loss": 0.6598871350288391,
|
| 664 |
+
"eval_runtime": 2.6073,
|
| 665 |
+
"eval_samples_per_second": 1.151,
|
| 666 |
+
"eval_steps_per_second": 1.151,
|
| 667 |
+
"step": 78
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.03,
|
| 671 |
+
"grad_norm": 0.06518127769231796,
|
| 672 |
+
"learning_rate": 5.604563732876989e-05,
|
| 673 |
+
"loss": 0.6178,
|
| 674 |
+
"step": 79
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.05,
|
| 678 |
+
"grad_norm": 0.08378639072179794,
|
| 679 |
+
"learning_rate": 5.342772171679364e-05,
|
| 680 |
+
"loss": 0.6462,
|
| 681 |
+
"step": 80
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.08,
|
| 685 |
+
"grad_norm": 0.10916124284267426,
|
| 686 |
+
"learning_rate": 5.084995082868658e-05,
|
| 687 |
+
"loss": 0.6232,
|
| 688 |
+
"step": 81
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.1,
|
| 692 |
+
"grad_norm": 0.06721071153879166,
|
| 693 |
+
"learning_rate": 4.8314546670850594e-05,
|
| 694 |
+
"loss": 0.6251,
|
| 695 |
+
"step": 82
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.13,
|
| 699 |
+
"grad_norm": 0.07324420660734177,
|
| 700 |
+
"learning_rate": 4.58236947300939e-05,
|
| 701 |
+
"loss": 0.6463,
|
| 702 |
+
"step": 83
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.15,
|
| 706 |
+
"grad_norm": 0.058844875544309616,
|
| 707 |
+
"learning_rate": 4.3379542089768296e-05,
|
| 708 |
+
"loss": 0.6356,
|
| 709 |
+
"step": 84
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.15,
|
| 713 |
+
"eval_loss": 0.6589328646659851,
|
| 714 |
+
"eval_runtime": 2.6016,
|
| 715 |
+
"eval_samples_per_second": 1.153,
|
| 716 |
+
"eval_steps_per_second": 1.153,
|
| 717 |
+
"step": 84
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.18,
|
| 721 |
+
"grad_norm": 0.06990176439285278,
|
| 722 |
+
"learning_rate": 4.0984195579010357e-05,
|
| 723 |
+
"loss": 0.6094,
|
| 724 |
+
"step": 85
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.21,
|
| 728 |
+
"grad_norm": 0.06396197527647018,
|
| 729 |
+
"learning_rate": 3.863971995668062e-05,
|
| 730 |
+
"loss": 0.6133,
|
| 731 |
+
"step": 86
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.23,
|
| 735 |
+
"grad_norm": 0.08108431100845337,
|
| 736 |
+
"learning_rate": 3.634813613156753e-05,
|
| 737 |
+
"loss": 0.6282,
|
| 738 |
+
"step": 87
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.26,
|
| 742 |
+
"grad_norm": 0.07657407969236374,
|
| 743 |
+
"learning_rate": 3.41114194203889e-05,
|
| 744 |
+
"loss": 0.6153,
|
| 745 |
+
"step": 88
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.28,
|
| 749 |
+
"grad_norm": 0.10315506905317307,
|
| 750 |
+
"learning_rate": 3.193149784509375e-05,
|
| 751 |
+
"loss": 0.6127,
|
| 752 |
+
"step": 89
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.31,
|
| 756 |
+
"grad_norm": 0.08609894663095474,
|
| 757 |
+
"learning_rate": 2.9810250470931177e-05,
|
| 758 |
+
"loss": 0.648,
|
| 759 |
+
"step": 90
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.31,
|
| 763 |
+
"eval_loss": 0.6583991050720215,
|
| 764 |
+
"eval_runtime": 2.6062,
|
| 765 |
+
"eval_samples_per_second": 1.151,
|
| 766 |
+
"eval_steps_per_second": 1.151,
|
| 767 |
+
"step": 90
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.33,
|
| 771 |
+
"grad_norm": 0.11702079325914383,
|
| 772 |
+
"learning_rate": 2.77495057867198e-05,
|
| 773 |
+
"loss": 0.6091,
|
| 774 |
+
"step": 91
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.36,
|
| 778 |
+
"grad_norm": 0.07838897407054901,
|
| 779 |
+
"learning_rate": 2.57510401287128e-05,
|
| 780 |
+
"loss": 0.6157,
|
| 781 |
+
"step": 92
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.38,
|
| 785 |
+
"grad_norm": 0.08897637575864792,
|
| 786 |
+
"learning_rate": 2.381657614941858e-05,
|
| 787 |
+
"loss": 0.6243,
|
| 788 |
+
"step": 93
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.41,
|
| 792 |
+
"grad_norm": 0.08890639245510101,
|
| 793 |
+
"learning_rate": 2.1947781332695404e-05,
|
| 794 |
+
"loss": 0.6217,
|
| 795 |
+
"step": 94
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.44,
|
| 799 |
+
"grad_norm": 0.07756870985031128,
|
| 800 |
+
"learning_rate": 2.0146266556401405e-05,
|
| 801 |
+
"loss": 0.6292,
|
| 802 |
+
"step": 95
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.46,
|
| 806 |
+
"grad_norm": 0.0875290259718895,
|
| 807 |
+
"learning_rate": 1.8413584703837615e-05,
|
| 808 |
+
"loss": 0.6254,
|
| 809 |
+
"step": 96
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.46,
|
| 813 |
+
"eval_loss": 0.6592622399330139,
|
| 814 |
+
"eval_runtime": 2.6098,
|
| 815 |
+
"eval_samples_per_second": 1.15,
|
| 816 |
+
"eval_steps_per_second": 1.15,
|
| 817 |
+
"step": 96
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.49,
|
| 821 |
+
"grad_norm": 0.09376902878284454,
|
| 822 |
+
"learning_rate": 1.6751229325182195e-05,
|
| 823 |
+
"loss": 0.6332,
|
| 824 |
+
"step": 97
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.51,
|
| 828 |
+
"grad_norm": 0.07304065674543381,
|
| 829 |
+
"learning_rate": 1.5160633350068509e-05,
|
| 830 |
+
"loss": 0.6078,
|
| 831 |
+
"step": 98
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.54,
|
| 835 |
+
"grad_norm": 0.08924753963947296,
|
| 836 |
+
"learning_rate": 1.3643167852417893e-05,
|
| 837 |
+
"loss": 0.6466,
|
| 838 |
+
"step": 99
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.56,
|
| 842 |
+
"grad_norm": 0.07718851417303085,
|
| 843 |
+
"learning_rate": 1.2200140868590759e-05,
|
| 844 |
+
"loss": 0.6239,
|
| 845 |
+
"step": 100
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.59,
|
| 849 |
+
"grad_norm": 0.087765634059906,
|
| 850 |
+
"learning_rate": 1.0832796269875756e-05,
|
| 851 |
+
"loss": 0.6506,
|
| 852 |
+
"step": 101
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.62,
|
| 856 |
+
"grad_norm": 0.08246306329965591,
|
| 857 |
+
"learning_rate": 9.542312690288036e-06,
|
| 858 |
+
"loss": 0.6167,
|
| 859 |
+
"step": 102
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.62,
|
| 863 |
+
"eval_loss": 0.6595852375030518,
|
| 864 |
+
"eval_runtime": 2.6048,
|
| 865 |
+
"eval_samples_per_second": 1.152,
|
| 866 |
+
"eval_steps_per_second": 1.152,
|
| 867 |
+
"step": 102
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.64,
|
| 871 |
+
"grad_norm": 0.0889851450920105,
|
| 872 |
+
"learning_rate": 8.329802510601559e-06,
|
| 873 |
+
"loss": 0.6521,
|
| 874 |
+
"step": 103
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.67,
|
| 878 |
+
"grad_norm": 0.0997273325920105,
|
| 879 |
+
"learning_rate": 7.196310899490577e-06,
|
| 880 |
+
"loss": 0.6336,
|
| 881 |
+
"step": 104
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 2.69,
|
| 885 |
+
"grad_norm": 0.07945340126752853,
|
| 886 |
+
"learning_rate": 6.142814912607409e-06,
|
| 887 |
+
"loss": 0.61,
|
| 888 |
+
"step": 105
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 2.72,
|
| 892 |
+
"grad_norm": 0.08767939358949661,
|
| 893 |
+
"learning_rate": 5.170222650372469e-06,
|
| 894 |
+
"loss": 0.624,
|
| 895 |
+
"step": 106
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 2.74,
|
| 899 |
+
"grad_norm": 0.08095201849937439,
|
| 900 |
+
"learning_rate": 4.279372475203181e-06,
|
| 901 |
+
"loss": 0.6329,
|
| 902 |
+
"step": 107
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 2.77,
|
| 906 |
+
"grad_norm": 0.09164229035377502,
|
| 907 |
+
"learning_rate": 3.471032288855869e-06,
|
| 908 |
+
"loss": 0.6451,
|
| 909 |
+
"step": 108
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.77,
|
| 913 |
+
"eval_loss": 0.6590184569358826,
|
| 914 |
+
"eval_runtime": 2.6071,
|
| 915 |
+
"eval_samples_per_second": 1.151,
|
| 916 |
+
"eval_steps_per_second": 1.151,
|
| 917 |
+
"step": 108
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 2.79,
|
| 921 |
+
"grad_norm": 0.10341291129589081,
|
| 922 |
+
"learning_rate": 2.7458988705041157e-06,
|
| 923 |
+
"loss": 0.6233,
|
| 924 |
+
"step": 109
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.82,
|
| 928 |
+
"grad_norm": 0.07704948633909225,
|
| 929 |
+
"learning_rate": 2.104597276123721e-06,
|
| 930 |
+
"loss": 0.6221,
|
| 931 |
+
"step": 110
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 2.85,
|
| 935 |
+
"grad_norm": 0.0802367627620697,
|
| 936 |
+
"learning_rate": 1.547680299702281e-06,
|
| 937 |
+
"loss": 0.625,
|
| 938 |
+
"step": 111
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.87,
|
| 942 |
+
"grad_norm": 0.06989463418722153,
|
| 943 |
+
"learning_rate": 1.075627996737627e-06,
|
| 944 |
+
"loss": 0.6082,
|
| 945 |
+
"step": 112
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.9,
|
| 949 |
+
"grad_norm": 0.07511158287525177,
|
| 950 |
+
"learning_rate": 6.888472704359661e-07,
|
| 951 |
+
"loss": 0.6145,
|
| 952 |
+
"step": 113
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 2.92,
|
| 956 |
+
"grad_norm": 0.08162180334329605,
|
| 957 |
+
"learning_rate": 3.87671520966415e-07,
|
| 958 |
+
"loss": 0.6144,
|
| 959 |
+
"step": 114
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 2.92,
|
| 963 |
+
"eval_loss": 0.6592249274253845,
|
| 964 |
+
"eval_runtime": 2.6101,
|
| 965 |
+
"eval_samples_per_second": 1.149,
|
| 966 |
+
"eval_steps_per_second": 1.149,
|
| 967 |
+
"step": 114
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 2.95,
|
| 971 |
+
"grad_norm": 0.09939952194690704,
|
| 972 |
+
"learning_rate": 1.7236035807416395e-07,
|
| 973 |
+
"loss": 0.6421,
|
| 974 |
+
"step": 115
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.97,
|
| 978 |
+
"grad_norm": 0.07238510996103287,
|
| 979 |
+
"learning_rate": 4.309937730015978e-08,
|
| 980 |
+
"loss": 0.633,
|
| 981 |
+
"step": 116
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 3.0,
|
| 985 |
+
"grad_norm": 0.08950413763523102,
|
| 986 |
+
"learning_rate": 0.0,
|
| 987 |
+
"loss": 0.6353,
|
| 988 |
+
"step": 117
|
| 989 |
+
}
|
| 990 |
+
],
|
| 991 |
+
"logging_steps": 1,
|
| 992 |
+
"max_steps": 117,
|
| 993 |
+
"num_input_tokens_seen": 0,
|
| 994 |
+
"num_train_epochs": 3,
|
| 995 |
+
"save_steps": 500,
|
| 996 |
+
"total_flos": 1.9228613614239744e+16,
|
| 997 |
+
"train_batch_size": 1,
|
| 998 |
+
"trial_name": null,
|
| 999 |
+
"trial_params": null
|
| 1000 |
+
}
|
checkpoint-117/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec93f341aadc3a3ae6e610311a1c08ba41067179c0b0da5f660d4dc3168401cc
|
| 3 |
+
size 5115
|
checkpoint-39/README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: bofenghuang/vigogne-2-7b-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.11.0
|
checkpoint-39/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bofenghuang/vigogne-2-7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-39/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3325aede574be93fce7402f5846c7bea523bf5cfcd9df3ae45de6bd19e8fb3b
|
| 3 |
+
size 844180648
|
checkpoint-39/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4856756c933f85c250058c366d477abf2334b9f812558e7210cbb142c0c033c
|
| 3 |
+
size 639908165
|
checkpoint-39/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9e5137dc2372d6b28a833d934b3dfec4e810c5830880c6a87760e5e986bd707
|
| 3 |
+
size 14575
|
checkpoint-39/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ce203b17a489275b1bda54262ee27eafe34a6cbb0e8362e312875332c7dd10d
|
| 3 |
+
size 627
|
checkpoint-39/trainer_state.json
ADDED
|
@@ -0,0 +1,350 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 6,
|
| 6 |
+
"global_step": 39,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 0.08957596868276596,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 1.0134,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"eval_loss": 1.0981205701828003,
|
| 21 |
+
"eval_runtime": 2.5128,
|
| 22 |
+
"eval_samples_per_second": 1.194,
|
| 23 |
+
"eval_steps_per_second": 1.194,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05,
|
| 28 |
+
"grad_norm": 0.07771213352680206,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 0.9545,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"grad_norm": 0.1224137470126152,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 1.1733,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"grad_norm": 0.09190034121274948,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 0.9954,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13,
|
| 49 |
+
"grad_norm": 0.08263542503118515,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 0.9486,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.15,
|
| 56 |
+
"grad_norm": 0.09250061959028244,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 0.972,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15,
|
| 63 |
+
"eval_loss": 1.0735869407653809,
|
| 64 |
+
"eval_runtime": 2.5357,
|
| 65 |
+
"eval_samples_per_second": 1.183,
|
| 66 |
+
"eval_steps_per_second": 1.183,
|
| 67 |
+
"step": 6
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.18,
|
| 71 |
+
"grad_norm": 0.1398034691810608,
|
| 72 |
+
"learning_rate": 0.00014,
|
| 73 |
+
"loss": 1.0445,
|
| 74 |
+
"step": 7
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.21,
|
| 78 |
+
"grad_norm": 0.0993918851017952,
|
| 79 |
+
"learning_rate": 0.00016,
|
| 80 |
+
"loss": 0.9169,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.23,
|
| 85 |
+
"grad_norm": 0.07937725633382797,
|
| 86 |
+
"learning_rate": 0.00018,
|
| 87 |
+
"loss": 0.8462,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.26,
|
| 92 |
+
"grad_norm": 0.10001373291015625,
|
| 93 |
+
"learning_rate": 0.0002,
|
| 94 |
+
"loss": 0.8708,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.28,
|
| 99 |
+
"grad_norm": 0.1337287873029709,
|
| 100 |
+
"learning_rate": 0.00019995690062269984,
|
| 101 |
+
"loss": 0.86,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.31,
|
| 106 |
+
"grad_norm": 0.11684636771678925,
|
| 107 |
+
"learning_rate": 0.00019982763964192585,
|
| 108 |
+
"loss": 0.7982,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.31,
|
| 113 |
+
"eval_loss": 0.8548387885093689,
|
| 114 |
+
"eval_runtime": 2.5536,
|
| 115 |
+
"eval_samples_per_second": 1.175,
|
| 116 |
+
"eval_steps_per_second": 1.175,
|
| 117 |
+
"step": 12
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.33,
|
| 121 |
+
"grad_norm": 0.12103456258773804,
|
| 122 |
+
"learning_rate": 0.0001996123284790336,
|
| 123 |
+
"loss": 0.7906,
|
| 124 |
+
"step": 13
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.36,
|
| 128 |
+
"grad_norm": 0.1426106095314026,
|
| 129 |
+
"learning_rate": 0.00019931115272956405,
|
| 130 |
+
"loss": 0.7825,
|
| 131 |
+
"step": 14
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.38,
|
| 135 |
+
"grad_norm": 0.12367941439151764,
|
| 136 |
+
"learning_rate": 0.0001989243720032624,
|
| 137 |
+
"loss": 0.7341,
|
| 138 |
+
"step": 15
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.41,
|
| 142 |
+
"grad_norm": 0.10154826194047928,
|
| 143 |
+
"learning_rate": 0.00019845231970029773,
|
| 144 |
+
"loss": 0.7064,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.44,
|
| 149 |
+
"grad_norm": 0.13628405332565308,
|
| 150 |
+
"learning_rate": 0.0001978954027238763,
|
| 151 |
+
"loss": 0.6988,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.46,
|
| 156 |
+
"grad_norm": 0.11276472359895706,
|
| 157 |
+
"learning_rate": 0.0001972541011294959,
|
| 158 |
+
"loss": 0.6944,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.46,
|
| 163 |
+
"eval_loss": 0.7151015400886536,
|
| 164 |
+
"eval_runtime": 2.5734,
|
| 165 |
+
"eval_samples_per_second": 1.166,
|
| 166 |
+
"eval_steps_per_second": 1.166,
|
| 167 |
+
"step": 18
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.49,
|
| 171 |
+
"grad_norm": 0.13381372392177582,
|
| 172 |
+
"learning_rate": 0.00019652896771114414,
|
| 173 |
+
"loss": 0.6956,
|
| 174 |
+
"step": 19
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.51,
|
| 178 |
+
"grad_norm": 0.11248588562011719,
|
| 179 |
+
"learning_rate": 0.00019572062752479683,
|
| 180 |
+
"loss": 0.7155,
|
| 181 |
+
"step": 20
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.54,
|
| 185 |
+
"grad_norm": 0.17762312293052673,
|
| 186 |
+
"learning_rate": 0.00019482977734962753,
|
| 187 |
+
"loss": 0.7357,
|
| 188 |
+
"step": 21
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.56,
|
| 192 |
+
"grad_norm": 0.10546916723251343,
|
| 193 |
+
"learning_rate": 0.00019385718508739262,
|
| 194 |
+
"loss": 0.6691,
|
| 195 |
+
"step": 22
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.59,
|
| 199 |
+
"grad_norm": 0.3150898516178131,
|
| 200 |
+
"learning_rate": 0.00019280368910050942,
|
| 201 |
+
"loss": 0.7167,
|
| 202 |
+
"step": 23
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.62,
|
| 206 |
+
"grad_norm": 0.13151158392429352,
|
| 207 |
+
"learning_rate": 0.00019167019748939846,
|
| 208 |
+
"loss": 0.6808,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.62,
|
| 213 |
+
"eval_loss": 0.6942548751831055,
|
| 214 |
+
"eval_runtime": 2.5831,
|
| 215 |
+
"eval_samples_per_second": 1.161,
|
| 216 |
+
"eval_steps_per_second": 1.161,
|
| 217 |
+
"step": 24
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.64,
|
| 221 |
+
"grad_norm": 0.14906296133995056,
|
| 222 |
+
"learning_rate": 0.00019045768730971196,
|
| 223 |
+
"loss": 0.6762,
|
| 224 |
+
"step": 25
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.67,
|
| 228 |
+
"grad_norm": 0.19484123587608337,
|
| 229 |
+
"learning_rate": 0.00018916720373012426,
|
| 230 |
+
"loss": 0.6854,
|
| 231 |
+
"step": 26
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.69,
|
| 235 |
+
"grad_norm": 0.12819896638393402,
|
| 236 |
+
"learning_rate": 0.00018779985913140924,
|
| 237 |
+
"loss": 0.6873,
|
| 238 |
+
"step": 27
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.72,
|
| 242 |
+
"grad_norm": 0.21385614573955536,
|
| 243 |
+
"learning_rate": 0.00018635683214758214,
|
| 244 |
+
"loss": 0.6874,
|
| 245 |
+
"step": 28
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.74,
|
| 249 |
+
"grad_norm": 0.12286895513534546,
|
| 250 |
+
"learning_rate": 0.0001848393666499315,
|
| 251 |
+
"loss": 0.6843,
|
| 252 |
+
"step": 29
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.77,
|
| 256 |
+
"grad_norm": 0.08534862101078033,
|
| 257 |
+
"learning_rate": 0.00018324877067481783,
|
| 258 |
+
"loss": 0.6763,
|
| 259 |
+
"step": 30
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.77,
|
| 263 |
+
"eval_loss": 0.6821426749229431,
|
| 264 |
+
"eval_runtime": 2.5911,
|
| 265 |
+
"eval_samples_per_second": 1.158,
|
| 266 |
+
"eval_steps_per_second": 1.158,
|
| 267 |
+
"step": 30
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.79,
|
| 271 |
+
"grad_norm": 0.17990928888320923,
|
| 272 |
+
"learning_rate": 0.0001815864152961624,
|
| 273 |
+
"loss": 0.6789,
|
| 274 |
+
"step": 31
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.82,
|
| 278 |
+
"grad_norm": 0.12137839943170547,
|
| 279 |
+
"learning_rate": 0.0001798537334435986,
|
| 280 |
+
"loss": 0.6877,
|
| 281 |
+
"step": 32
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.85,
|
| 285 |
+
"grad_norm": 0.10240964591503143,
|
| 286 |
+
"learning_rate": 0.00017805221866730458,
|
| 287 |
+
"loss": 0.6725,
|
| 288 |
+
"step": 33
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.87,
|
| 292 |
+
"grad_norm": 0.14333295822143555,
|
| 293 |
+
"learning_rate": 0.00017618342385058145,
|
| 294 |
+
"loss": 0.6745,
|
| 295 |
+
"step": 34
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.9,
|
| 299 |
+
"grad_norm": 0.0904482752084732,
|
| 300 |
+
"learning_rate": 0.00017424895987128722,
|
| 301 |
+
"loss": 0.6894,
|
| 302 |
+
"step": 35
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.92,
|
| 306 |
+
"grad_norm": 0.11753042787313461,
|
| 307 |
+
"learning_rate": 0.00017225049421328023,
|
| 308 |
+
"loss": 0.67,
|
| 309 |
+
"step": 36
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.92,
|
| 313 |
+
"eval_loss": 0.6763580441474915,
|
| 314 |
+
"eval_runtime": 2.5955,
|
| 315 |
+
"eval_samples_per_second": 1.156,
|
| 316 |
+
"eval_steps_per_second": 1.156,
|
| 317 |
+
"step": 36
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.95,
|
| 321 |
+
"grad_norm": 0.13719823956489563,
|
| 322 |
+
"learning_rate": 0.00017018974952906884,
|
| 323 |
+
"loss": 0.6589,
|
| 324 |
+
"step": 37
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.97,
|
| 328 |
+
"grad_norm": 0.1040361225605011,
|
| 329 |
+
"learning_rate": 0.0001680685021549063,
|
| 330 |
+
"loss": 0.666,
|
| 331 |
+
"step": 38
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0,
|
| 335 |
+
"grad_norm": 0.07594098895788193,
|
| 336 |
+
"learning_rate": 0.00016588858057961113,
|
| 337 |
+
"loss": 0.645,
|
| 338 |
+
"step": 39
|
| 339 |
+
}
|
| 340 |
+
],
|
| 341 |
+
"logging_steps": 1,
|
| 342 |
+
"max_steps": 117,
|
| 343 |
+
"num_input_tokens_seen": 0,
|
| 344 |
+
"num_train_epochs": 3,
|
| 345 |
+
"save_steps": 500,
|
| 346 |
+
"total_flos": 6409537871413248.0,
|
| 347 |
+
"train_batch_size": 1,
|
| 348 |
+
"trial_name": null,
|
| 349 |
+
"trial_params": null
|
| 350 |
+
}
|
checkpoint-39/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec93f341aadc3a3ae6e610311a1c08ba41067179c0b0da5f660d4dc3168401cc
|
| 3 |
+
size 5115
|
checkpoint-78/README.md
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: bofenghuang/vigogne-2-7b-instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
### Framework versions
|
| 203 |
+
|
| 204 |
+
- PEFT 0.11.0
|
checkpoint-78/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bofenghuang/vigogne-2-7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-78/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf62552c89b8a9944f73d75f810f49a2d764b97998e6911352cc714de1a2b049
|
| 3 |
+
size 844180648
|
checkpoint-78/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40f2cd4143652f789359cf3a61f1436141920d43ccf0bfa70849414d9beeed14
|
| 3 |
+
size 639908165
|
checkpoint-78/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82106bea0a8a754add1d7e899e4dc1f4431bc3b4ff4abfa3136a688f4964b4cf
|
| 3 |
+
size 14575
|
checkpoint-78/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b78fd7900888162fc2f991fff9a35115e46eaf4801d11c1c93ea25e08303be2
|
| 3 |
+
size 627
|
checkpoint-78/trainer_state.json
ADDED
|
@@ -0,0 +1,679 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 6,
|
| 6 |
+
"global_step": 78,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 0.08957596868276596,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 1.0134,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"eval_loss": 1.0981205701828003,
|
| 21 |
+
"eval_runtime": 2.5128,
|
| 22 |
+
"eval_samples_per_second": 1.194,
|
| 23 |
+
"eval_steps_per_second": 1.194,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05,
|
| 28 |
+
"grad_norm": 0.07771213352680206,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 0.9545,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"grad_norm": 0.1224137470126152,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 1.1733,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"grad_norm": 0.09190034121274948,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 0.9954,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13,
|
| 49 |
+
"grad_norm": 0.08263542503118515,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 0.9486,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.15,
|
| 56 |
+
"grad_norm": 0.09250061959028244,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 0.972,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15,
|
| 63 |
+
"eval_loss": 1.0735869407653809,
|
| 64 |
+
"eval_runtime": 2.5357,
|
| 65 |
+
"eval_samples_per_second": 1.183,
|
| 66 |
+
"eval_steps_per_second": 1.183,
|
| 67 |
+
"step": 6
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.18,
|
| 71 |
+
"grad_norm": 0.1398034691810608,
|
| 72 |
+
"learning_rate": 0.00014,
|
| 73 |
+
"loss": 1.0445,
|
| 74 |
+
"step": 7
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.21,
|
| 78 |
+
"grad_norm": 0.0993918851017952,
|
| 79 |
+
"learning_rate": 0.00016,
|
| 80 |
+
"loss": 0.9169,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.23,
|
| 85 |
+
"grad_norm": 0.07937725633382797,
|
| 86 |
+
"learning_rate": 0.00018,
|
| 87 |
+
"loss": 0.8462,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.26,
|
| 92 |
+
"grad_norm": 0.10001373291015625,
|
| 93 |
+
"learning_rate": 0.0002,
|
| 94 |
+
"loss": 0.8708,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.28,
|
| 99 |
+
"grad_norm": 0.1337287873029709,
|
| 100 |
+
"learning_rate": 0.00019995690062269984,
|
| 101 |
+
"loss": 0.86,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.31,
|
| 106 |
+
"grad_norm": 0.11684636771678925,
|
| 107 |
+
"learning_rate": 0.00019982763964192585,
|
| 108 |
+
"loss": 0.7982,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.31,
|
| 113 |
+
"eval_loss": 0.8548387885093689,
|
| 114 |
+
"eval_runtime": 2.5536,
|
| 115 |
+
"eval_samples_per_second": 1.175,
|
| 116 |
+
"eval_steps_per_second": 1.175,
|
| 117 |
+
"step": 12
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.33,
|
| 121 |
+
"grad_norm": 0.12103456258773804,
|
| 122 |
+
"learning_rate": 0.0001996123284790336,
|
| 123 |
+
"loss": 0.7906,
|
| 124 |
+
"step": 13
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.36,
|
| 128 |
+
"grad_norm": 0.1426106095314026,
|
| 129 |
+
"learning_rate": 0.00019931115272956405,
|
| 130 |
+
"loss": 0.7825,
|
| 131 |
+
"step": 14
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.38,
|
| 135 |
+
"grad_norm": 0.12367941439151764,
|
| 136 |
+
"learning_rate": 0.0001989243720032624,
|
| 137 |
+
"loss": 0.7341,
|
| 138 |
+
"step": 15
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.41,
|
| 142 |
+
"grad_norm": 0.10154826194047928,
|
| 143 |
+
"learning_rate": 0.00019845231970029773,
|
| 144 |
+
"loss": 0.7064,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.44,
|
| 149 |
+
"grad_norm": 0.13628405332565308,
|
| 150 |
+
"learning_rate": 0.0001978954027238763,
|
| 151 |
+
"loss": 0.6988,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.46,
|
| 156 |
+
"grad_norm": 0.11276472359895706,
|
| 157 |
+
"learning_rate": 0.0001972541011294959,
|
| 158 |
+
"loss": 0.6944,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.46,
|
| 163 |
+
"eval_loss": 0.7151015400886536,
|
| 164 |
+
"eval_runtime": 2.5734,
|
| 165 |
+
"eval_samples_per_second": 1.166,
|
| 166 |
+
"eval_steps_per_second": 1.166,
|
| 167 |
+
"step": 18
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.49,
|
| 171 |
+
"grad_norm": 0.13381372392177582,
|
| 172 |
+
"learning_rate": 0.00019652896771114414,
|
| 173 |
+
"loss": 0.6956,
|
| 174 |
+
"step": 19
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.51,
|
| 178 |
+
"grad_norm": 0.11248588562011719,
|
| 179 |
+
"learning_rate": 0.00019572062752479683,
|
| 180 |
+
"loss": 0.7155,
|
| 181 |
+
"step": 20
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.54,
|
| 185 |
+
"grad_norm": 0.17762312293052673,
|
| 186 |
+
"learning_rate": 0.00019482977734962753,
|
| 187 |
+
"loss": 0.7357,
|
| 188 |
+
"step": 21
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.56,
|
| 192 |
+
"grad_norm": 0.10546916723251343,
|
| 193 |
+
"learning_rate": 0.00019385718508739262,
|
| 194 |
+
"loss": 0.6691,
|
| 195 |
+
"step": 22
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.59,
|
| 199 |
+
"grad_norm": 0.3150898516178131,
|
| 200 |
+
"learning_rate": 0.00019280368910050942,
|
| 201 |
+
"loss": 0.7167,
|
| 202 |
+
"step": 23
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.62,
|
| 206 |
+
"grad_norm": 0.13151158392429352,
|
| 207 |
+
"learning_rate": 0.00019167019748939846,
|
| 208 |
+
"loss": 0.6808,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.62,
|
| 213 |
+
"eval_loss": 0.6942548751831055,
|
| 214 |
+
"eval_runtime": 2.5831,
|
| 215 |
+
"eval_samples_per_second": 1.161,
|
| 216 |
+
"eval_steps_per_second": 1.161,
|
| 217 |
+
"step": 24
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.64,
|
| 221 |
+
"grad_norm": 0.14906296133995056,
|
| 222 |
+
"learning_rate": 0.00019045768730971196,
|
| 223 |
+
"loss": 0.6762,
|
| 224 |
+
"step": 25
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.67,
|
| 228 |
+
"grad_norm": 0.19484123587608337,
|
| 229 |
+
"learning_rate": 0.00018916720373012426,
|
| 230 |
+
"loss": 0.6854,
|
| 231 |
+
"step": 26
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.69,
|
| 235 |
+
"grad_norm": 0.12819896638393402,
|
| 236 |
+
"learning_rate": 0.00018779985913140924,
|
| 237 |
+
"loss": 0.6873,
|
| 238 |
+
"step": 27
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.72,
|
| 242 |
+
"grad_norm": 0.21385614573955536,
|
| 243 |
+
"learning_rate": 0.00018635683214758214,
|
| 244 |
+
"loss": 0.6874,
|
| 245 |
+
"step": 28
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.74,
|
| 249 |
+
"grad_norm": 0.12286895513534546,
|
| 250 |
+
"learning_rate": 0.0001848393666499315,
|
| 251 |
+
"loss": 0.6843,
|
| 252 |
+
"step": 29
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.77,
|
| 256 |
+
"grad_norm": 0.08534862101078033,
|
| 257 |
+
"learning_rate": 0.00018324877067481783,
|
| 258 |
+
"loss": 0.6763,
|
| 259 |
+
"step": 30
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.77,
|
| 263 |
+
"eval_loss": 0.6821426749229431,
|
| 264 |
+
"eval_runtime": 2.5911,
|
| 265 |
+
"eval_samples_per_second": 1.158,
|
| 266 |
+
"eval_steps_per_second": 1.158,
|
| 267 |
+
"step": 30
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.79,
|
| 271 |
+
"grad_norm": 0.17990928888320923,
|
| 272 |
+
"learning_rate": 0.0001815864152961624,
|
| 273 |
+
"loss": 0.6789,
|
| 274 |
+
"step": 31
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.82,
|
| 278 |
+
"grad_norm": 0.12137839943170547,
|
| 279 |
+
"learning_rate": 0.0001798537334435986,
|
| 280 |
+
"loss": 0.6877,
|
| 281 |
+
"step": 32
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.85,
|
| 285 |
+
"grad_norm": 0.10240964591503143,
|
| 286 |
+
"learning_rate": 0.00017805221866730458,
|
| 287 |
+
"loss": 0.6725,
|
| 288 |
+
"step": 33
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.87,
|
| 292 |
+
"grad_norm": 0.14333295822143555,
|
| 293 |
+
"learning_rate": 0.00017618342385058145,
|
| 294 |
+
"loss": 0.6745,
|
| 295 |
+
"step": 34
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.9,
|
| 299 |
+
"grad_norm": 0.0904482752084732,
|
| 300 |
+
"learning_rate": 0.00017424895987128722,
|
| 301 |
+
"loss": 0.6894,
|
| 302 |
+
"step": 35
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.92,
|
| 306 |
+
"grad_norm": 0.11753042787313461,
|
| 307 |
+
"learning_rate": 0.00017225049421328023,
|
| 308 |
+
"loss": 0.67,
|
| 309 |
+
"step": 36
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.92,
|
| 313 |
+
"eval_loss": 0.6763580441474915,
|
| 314 |
+
"eval_runtime": 2.5955,
|
| 315 |
+
"eval_samples_per_second": 1.156,
|
| 316 |
+
"eval_steps_per_second": 1.156,
|
| 317 |
+
"step": 36
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.95,
|
| 321 |
+
"grad_norm": 0.13719823956489563,
|
| 322 |
+
"learning_rate": 0.00017018974952906884,
|
| 323 |
+
"loss": 0.6589,
|
| 324 |
+
"step": 37
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.97,
|
| 328 |
+
"grad_norm": 0.1040361225605011,
|
| 329 |
+
"learning_rate": 0.0001680685021549063,
|
| 330 |
+
"loss": 0.666,
|
| 331 |
+
"step": 38
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0,
|
| 335 |
+
"grad_norm": 0.07594098895788193,
|
| 336 |
+
"learning_rate": 0.00016588858057961113,
|
| 337 |
+
"loss": 0.645,
|
| 338 |
+
"step": 39
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.03,
|
| 342 |
+
"grad_norm": 0.08139798045158386,
|
| 343 |
+
"learning_rate": 0.0001636518638684325,
|
| 344 |
+
"loss": 0.6542,
|
| 345 |
+
"step": 40
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.05,
|
| 349 |
+
"grad_norm": 0.07313457876443863,
|
| 350 |
+
"learning_rate": 0.0001613602800433194,
|
| 351 |
+
"loss": 0.6458,
|
| 352 |
+
"step": 41
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.08,
|
| 356 |
+
"grad_norm": 0.07903215289115906,
|
| 357 |
+
"learning_rate": 0.00015901580442098968,
|
| 358 |
+
"loss": 0.6424,
|
| 359 |
+
"step": 42
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.08,
|
| 363 |
+
"eval_loss": 0.6730008125305176,
|
| 364 |
+
"eval_runtime": 2.5989,
|
| 365 |
+
"eval_samples_per_second": 1.154,
|
| 366 |
+
"eval_steps_per_second": 1.154,
|
| 367 |
+
"step": 42
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.1,
|
| 371 |
+
"grad_norm": 0.09322352707386017,
|
| 372 |
+
"learning_rate": 0.00015662045791023173,
|
| 373 |
+
"loss": 0.6567,
|
| 374 |
+
"step": 43
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.13,
|
| 378 |
+
"grad_norm": 0.07249985635280609,
|
| 379 |
+
"learning_rate": 0.00015417630526990615,
|
| 380 |
+
"loss": 0.6384,
|
| 381 |
+
"step": 44
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.15,
|
| 385 |
+
"grad_norm": 0.07686451077461243,
|
| 386 |
+
"learning_rate": 0.0001516854533291494,
|
| 387 |
+
"loss": 0.665,
|
| 388 |
+
"step": 45
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.18,
|
| 392 |
+
"grad_norm": 0.07324113696813583,
|
| 393 |
+
"learning_rate": 0.00014915004917131344,
|
| 394 |
+
"loss": 0.6297,
|
| 395 |
+
"step": 46
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.21,
|
| 399 |
+
"grad_norm": 0.09203895926475525,
|
| 400 |
+
"learning_rate": 0.00014657227828320635,
|
| 401 |
+
"loss": 0.6539,
|
| 402 |
+
"step": 47
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.23,
|
| 406 |
+
"grad_norm": 0.09338624030351639,
|
| 407 |
+
"learning_rate": 0.00014395436267123016,
|
| 408 |
+
"loss": 0.6552,
|
| 409 |
+
"step": 48
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.23,
|
| 413 |
+
"eval_loss": 0.6780009269714355,
|
| 414 |
+
"eval_runtime": 2.6045,
|
| 415 |
+
"eval_samples_per_second": 1.152,
|
| 416 |
+
"eval_steps_per_second": 1.152,
|
| 417 |
+
"step": 48
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.26,
|
| 421 |
+
"grad_norm": 0.0812142863869667,
|
| 422 |
+
"learning_rate": 0.00014129855894603886,
|
| 423 |
+
"loss": 0.6319,
|
| 424 |
+
"step": 49
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.28,
|
| 428 |
+
"grad_norm": 0.19316132366657257,
|
| 429 |
+
"learning_rate": 0.00013860715637736818,
|
| 430 |
+
"loss": 0.7,
|
| 431 |
+
"step": 50
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.31,
|
| 435 |
+
"grad_norm": 0.10698059946298599,
|
| 436 |
+
"learning_rate": 0.0001358824749207136,
|
| 437 |
+
"loss": 0.6725,
|
| 438 |
+
"step": 51
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.33,
|
| 442 |
+
"grad_norm": 0.14100198447704315,
|
| 443 |
+
"learning_rate": 0.00013312686321755761,
|
| 444 |
+
"loss": 0.6766,
|
| 445 |
+
"step": 52
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.36,
|
| 449 |
+
"grad_norm": 0.09599179029464722,
|
| 450 |
+
"learning_rate": 0.00013034269657086992,
|
| 451 |
+
"loss": 0.645,
|
| 452 |
+
"step": 53
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.38,
|
| 456 |
+
"grad_norm": 0.08999059349298477,
|
| 457 |
+
"learning_rate": 0.000127532374897626,
|
| 458 |
+
"loss": 0.6527,
|
| 459 |
+
"step": 54
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.38,
|
| 463 |
+
"eval_loss": 0.6689873337745667,
|
| 464 |
+
"eval_runtime": 2.6108,
|
| 465 |
+
"eval_samples_per_second": 1.149,
|
| 466 |
+
"eval_steps_per_second": 1.149,
|
| 467 |
+
"step": 54
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.41,
|
| 471 |
+
"grad_norm": 0.13835830986499786,
|
| 472 |
+
"learning_rate": 0.00012469832066010843,
|
| 473 |
+
"loss": 0.6561,
|
| 474 |
+
"step": 55
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.44,
|
| 478 |
+
"grad_norm": 0.10695886611938477,
|
| 479 |
+
"learning_rate": 0.00012184297677777463,
|
| 480 |
+
"loss": 0.6668,
|
| 481 |
+
"step": 56
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.46,
|
| 485 |
+
"grad_norm": 0.0739368349313736,
|
| 486 |
+
"learning_rate": 0.00011896880452149077,
|
| 487 |
+
"loss": 0.643,
|
| 488 |
+
"step": 57
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.49,
|
| 492 |
+
"grad_norm": 0.21791452169418335,
|
| 493 |
+
"learning_rate": 0.00011607828139194683,
|
| 494 |
+
"loss": 0.6768,
|
| 495 |
+
"step": 58
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.51,
|
| 499 |
+
"grad_norm": 0.06241246312856674,
|
| 500 |
+
"learning_rate": 0.00011317389898408189,
|
| 501 |
+
"loss": 0.6252,
|
| 502 |
+
"step": 59
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.54,
|
| 506 |
+
"grad_norm": 0.1302526593208313,
|
| 507 |
+
"learning_rate": 0.00011025816083936036,
|
| 508 |
+
"loss": 0.6624,
|
| 509 |
+
"step": 60
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.54,
|
| 513 |
+
"eval_loss": 0.6632375121116638,
|
| 514 |
+
"eval_runtime": 2.6043,
|
| 515 |
+
"eval_samples_per_second": 1.152,
|
| 516 |
+
"eval_steps_per_second": 1.152,
|
| 517 |
+
"step": 60
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.56,
|
| 521 |
+
"grad_norm": 0.11702455580234528,
|
| 522 |
+
"learning_rate": 0.0001073335802877504,
|
| 523 |
+
"loss": 0.6522,
|
| 524 |
+
"step": 61
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.59,
|
| 528 |
+
"grad_norm": 0.08904154598712921,
|
| 529 |
+
"learning_rate": 0.00010440267828126478,
|
| 530 |
+
"loss": 0.6472,
|
| 531 |
+
"step": 62
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.62,
|
| 535 |
+
"grad_norm": 0.08021406084299088,
|
| 536 |
+
"learning_rate": 0.00010146798122093166,
|
| 537 |
+
"loss": 0.6279,
|
| 538 |
+
"step": 63
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.64,
|
| 542 |
+
"grad_norm": 0.07384659349918365,
|
| 543 |
+
"learning_rate": 9.853201877906836e-05,
|
| 544 |
+
"loss": 0.6262,
|
| 545 |
+
"step": 64
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.67,
|
| 549 |
+
"grad_norm": 0.06457240134477615,
|
| 550 |
+
"learning_rate": 9.559732171873523e-05,
|
| 551 |
+
"loss": 0.64,
|
| 552 |
+
"step": 65
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.69,
|
| 556 |
+
"grad_norm": 0.07967618852853775,
|
| 557 |
+
"learning_rate": 9.266641971224963e-05,
|
| 558 |
+
"loss": 0.6228,
|
| 559 |
+
"step": 66
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.69,
|
| 563 |
+
"eval_loss": 0.6625072360038757,
|
| 564 |
+
"eval_runtime": 2.6047,
|
| 565 |
+
"eval_samples_per_second": 1.152,
|
| 566 |
+
"eval_steps_per_second": 1.152,
|
| 567 |
+
"step": 66
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.72,
|
| 571 |
+
"grad_norm": 0.09555868804454803,
|
| 572 |
+
"learning_rate": 8.974183916063968e-05,
|
| 573 |
+
"loss": 0.635,
|
| 574 |
+
"step": 67
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.74,
|
| 578 |
+
"grad_norm": 0.07187359035015106,
|
| 579 |
+
"learning_rate": 8.682610101591814e-05,
|
| 580 |
+
"loss": 0.6277,
|
| 581 |
+
"step": 68
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.77,
|
| 585 |
+
"grad_norm": 0.091610848903656,
|
| 586 |
+
"learning_rate": 8.392171860805319e-05,
|
| 587 |
+
"loss": 0.6649,
|
| 588 |
+
"step": 69
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.79,
|
| 592 |
+
"grad_norm": 0.065833680331707,
|
| 593 |
+
"learning_rate": 8.103119547850924e-05,
|
| 594 |
+
"loss": 0.6262,
|
| 595 |
+
"step": 70
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 1.82,
|
| 599 |
+
"grad_norm": 0.09459354728460312,
|
| 600 |
+
"learning_rate": 7.815702322222538e-05,
|
| 601 |
+
"loss": 0.6359,
|
| 602 |
+
"step": 71
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.85,
|
| 606 |
+
"grad_norm": 0.06780053675174713,
|
| 607 |
+
"learning_rate": 7.530167933989161e-05,
|
| 608 |
+
"loss": 0.6447,
|
| 609 |
+
"step": 72
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.85,
|
| 613 |
+
"eval_loss": 0.6616933941841125,
|
| 614 |
+
"eval_runtime": 2.607,
|
| 615 |
+
"eval_samples_per_second": 1.151,
|
| 616 |
+
"eval_steps_per_second": 1.151,
|
| 617 |
+
"step": 72
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.87,
|
| 621 |
+
"grad_norm": 0.0954224094748497,
|
| 622 |
+
"learning_rate": 7.246762510237403e-05,
|
| 623 |
+
"loss": 0.6636,
|
| 624 |
+
"step": 73
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.9,
|
| 628 |
+
"grad_norm": 0.0937703400850296,
|
| 629 |
+
"learning_rate": 6.96573034291301e-05,
|
| 630 |
+
"loss": 0.6381,
|
| 631 |
+
"step": 74
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.92,
|
| 635 |
+
"grad_norm": 0.10935033112764359,
|
| 636 |
+
"learning_rate": 6.687313678244242e-05,
|
| 637 |
+
"loss": 0.628,
|
| 638 |
+
"step": 75
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.95,
|
| 642 |
+
"grad_norm": 0.08154003322124481,
|
| 643 |
+
"learning_rate": 6.411752507928642e-05,
|
| 644 |
+
"loss": 0.6386,
|
| 645 |
+
"step": 76
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.97,
|
| 649 |
+
"grad_norm": 0.12196218967437744,
|
| 650 |
+
"learning_rate": 6.139284362263185e-05,
|
| 651 |
+
"loss": 0.6317,
|
| 652 |
+
"step": 77
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.0,
|
| 656 |
+
"grad_norm": 0.11538293212652206,
|
| 657 |
+
"learning_rate": 5.870144105396118e-05,
|
| 658 |
+
"loss": 0.6409,
|
| 659 |
+
"step": 78
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.0,
|
| 663 |
+
"eval_loss": 0.6598871350288391,
|
| 664 |
+
"eval_runtime": 2.6073,
|
| 665 |
+
"eval_samples_per_second": 1.151,
|
| 666 |
+
"eval_steps_per_second": 1.151,
|
| 667 |
+
"step": 78
|
| 668 |
+
}
|
| 669 |
+
],
|
| 670 |
+
"logging_steps": 1,
|
| 671 |
+
"max_steps": 117,
|
| 672 |
+
"num_input_tokens_seen": 0,
|
| 673 |
+
"num_train_epochs": 3,
|
| 674 |
+
"save_steps": 500,
|
| 675 |
+
"total_flos": 1.2819075742826496e+16,
|
| 676 |
+
"train_batch_size": 1,
|
| 677 |
+
"trial_name": null,
|
| 678 |
+
"trial_params": null
|
| 679 |
+
}
|
checkpoint-78/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec93f341aadc3a3ae6e610311a1c08ba41067179c0b0da5f660d4dc3168401cc
|
| 3 |
+
size 5115
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bofenghuang/vigogne-2-7b-instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_length": 4096,
|
| 15 |
+
"max_position_embeddings": 4096,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 32,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"quantization_config": {
|
| 23 |
+
"_load_in_4bit": true,
|
| 24 |
+
"_load_in_8bit": false,
|
| 25 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 26 |
+
"bnb_4bit_quant_type": "nf4",
|
| 27 |
+
"bnb_4bit_use_double_quant": true,
|
| 28 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 29 |
+
"llm_int8_has_fp16_weight": false,
|
| 30 |
+
"llm_int8_skip_modules": null,
|
| 31 |
+
"llm_int8_threshold": 6.0,
|
| 32 |
+
"load_in_4bit": true,
|
| 33 |
+
"load_in_8bit": false,
|
| 34 |
+
"quant_method": "bitsandbytes"
|
| 35 |
+
},
|
| 36 |
+
"rms_norm_eps": 1e-05,
|
| 37 |
+
"rope_scaling": null,
|
| 38 |
+
"rope_theta": 10000.0,
|
| 39 |
+
"tie_word_embeddings": false,
|
| 40 |
+
"torch_dtype": "float16",
|
| 41 |
+
"transformers_version": "4.39.0.dev0",
|
| 42 |
+
"use_cache": false,
|
| 43 |
+
"vocab_size": 32001
|
| 44 |
+
}
|
merged/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
merged/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bofenghuang/vigogne-2-7b-instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_length": 4096,
|
| 15 |
+
"max_position_embeddings": 4096,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 32,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.39.0.dev0",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"vocab_size": 32001
|
| 30 |
+
}
|
merged/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"temperature": 0.9,
|
| 8 |
+
"top_p": 0.6,
|
| 9 |
+
"transformers_version": "4.39.0.dev0"
|
| 10 |
+
}
|
merged/pytorch_model-00001-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a501f49b4c58501efca6c3e4a8498a7309842706ba5753999499d26bd6be0e1
|
| 3 |
+
size 4939018290
|
merged/pytorch_model-00002-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05f1ac32c14826058810523ddadecad794bfaa793e337889f111092f1234d4c9
|
| 3 |
+
size 4947416538
|
merged/pytorch_model-00003-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd67ca940bc317794c1778cedff20e34a07195f6223369c834305b524401587e
|
| 3 |
+
size 3590514937
|
merged/pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13476847616
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 296 |
+
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
| 297 |
+
}
|
| 298 |
+
}
|
merged/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
merged/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
merged/tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"clean_up_tokenization_spaces": false,
|
| 41 |
+
"eos_token": "</s>",
|
| 42 |
+
"legacy": false,
|
| 43 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 44 |
+
"pad_token": "</s>",
|
| 45 |
+
"padding_side": "right",
|
| 46 |
+
"sp_model_kwargs": {},
|
| 47 |
+
"spaces_between_special_tokens": false,
|
| 48 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 49 |
+
"unk_token": "<unk>",
|
| 50 |
+
"use_default_system_prompt": false,
|
| 51 |
+
"use_fast": true
|
| 52 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"clean_up_tokenization_spaces": false,
|
| 41 |
+
"eos_token": "</s>",
|
| 42 |
+
"legacy": false,
|
| 43 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 44 |
+
"pad_token": "</s>",
|
| 45 |
+
"padding_side": "right",
|
| 46 |
+
"sp_model_kwargs": {},
|
| 47 |
+
"spaces_between_special_tokens": false,
|
| 48 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 49 |
+
"unk_token": "<unk>",
|
| 50 |
+
"use_default_system_prompt": false,
|
| 51 |
+
"use_fast": true
|
| 52 |
+
}
|