Upload 13 files
Browse files- README.md +59 -0
- all_results.json +8 -0
- config.json +30 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- special_tokens_map.json +41 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- train_results.json +8 -0
- trainer_log.jsonl +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: other
|
4 |
+
base_model: tiiuae/Falcon3-1B-Instruct
|
5 |
+
tags:
|
6 |
+
- llama-factory
|
7 |
+
- full
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: falcon3-1B-inst-limo
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# falcon3-1B-inst-limo
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [../models/falcon3-1b-instruct](https://huggingface.co/../models/falcon3-1b-instruct) on the limo_dataset dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-06
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- num_devices: 2
|
44 |
+
- total_train_batch_size: 2
|
45 |
+
- total_eval_batch_size: 16
|
46 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- num_epochs: 15
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
|
53 |
+
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- Transformers 4.48.2
|
57 |
+
- Pytorch 2.6.0+cu124
|
58 |
+
- Datasets 3.2.0
|
59 |
+
- Tokenizers 0.21.0
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"total_flos": 42951348682752.0,
|
4 |
+
"train_loss": 0.5825496300423446,
|
5 |
+
"train_runtime": 29719.3629,
|
6 |
+
"train_samples_per_second": 0.412,
|
7 |
+
"train_steps_per_second": 0.206
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../models/falcon3-1b-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 11,
|
10 |
+
"head_dim": 256,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 2048,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 8192,
|
15 |
+
"max_position_embeddings": 8192,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 8,
|
19 |
+
"num_hidden_layers": 18,
|
20 |
+
"num_key_value_heads": 4,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-06,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 1000042,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.48.2",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 131072
|
30 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 11,
|
4 |
+
"eos_token_id": 11,
|
5 |
+
"transformers_version": "4.48.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6f8181a3b48780185c2a71ddda72ff070f3d970da8241a9cf12771468f063e9
|
3 |
+
size 3338836632
|
special_tokens_map.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
">>TITLE<<",
|
4 |
+
">>ABSTRACT<<",
|
5 |
+
">>INTRODUCTION<<",
|
6 |
+
">>SUMMARY<<",
|
7 |
+
">>COMMENT<<",
|
8 |
+
">>ANSWER<<",
|
9 |
+
">>QUESTION<<",
|
10 |
+
">>DOMAIN<<",
|
11 |
+
">>EMAIL_ADDRESS<<",
|
12 |
+
">>IP_ADDRESS<<",
|
13 |
+
"<|startoftext|>",
|
14 |
+
">>IP_ADDRESS_0<<",
|
15 |
+
">>IP_ADDRESS_1<<",
|
16 |
+
">>IP_ADDRESS_2<<",
|
17 |
+
">>IP_ADDRESS_3<<",
|
18 |
+
">>IP_ADDRESS_4<<",
|
19 |
+
">>IP_ADDRESS_5<<",
|
20 |
+
">>IP_ADDRESS_6<<",
|
21 |
+
">>IP_ADDRESS_7<<",
|
22 |
+
">>IP_ADDRESS_8<<",
|
23 |
+
">>IP_ADDRESS_9<<",
|
24 |
+
">>PASSWORD<<",
|
25 |
+
">>KEY<<"
|
26 |
+
],
|
27 |
+
"eos_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
},
|
34 |
+
"pad_token": {
|
35 |
+
"content": "<|pad|>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
}
|
41 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"total_flos": 42951348682752.0,
|
4 |
+
"train_loss": 0.5825496300423446,
|
5 |
+
"train_runtime": 29719.3629,
|
6 |
+
"train_samples_per_second": 0.412,
|
7 |
+
"train_steps_per_second": 0.206
|
8 |
+
}
|
trainer_log.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4c26c6da4c380210f3fd5dec5ac2ea64b15aef6972681cf8b436f52dbb8096e
|
3 |
+
size 7480
|
training_loss.png
ADDED
![]() |