Training in progress, step 500
Browse files- .ipynb_checkpoints/README-checkpoint.md +56 -0
- .ipynb_checkpoints/config-checkpoint.json +42 -0
- .ipynb_checkpoints/generation_config-checkpoint.json +14 -0
- .ipynb_checkpoints/special_tokens_map-checkpoint.json +39 -0
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- runs/Dec28_21-30-49_192-222-57-66/events.out.tfevents.1735421450.192-222-57-66.9957.0 +3 -0
- runs/Dec28_21-42-33_192-222-57-66/events.out.tfevents.1735422153.192-222-57-66.11204.0 +3 -0
- training_args.bin +1 -1
.ipynb_checkpoints/README-checkpoint.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: llama3.1
|
4 |
+
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: PESTO-llama-base
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# PESTO-llama-base
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 1e-05
|
37 |
+
- train_batch_size: 1
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 8
|
41 |
+
- total_train_batch_size: 8
|
42 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 100
|
45 |
+
- num_epochs: 3
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- Transformers 4.47.1
|
54 |
+
- Pytorch 2.5.1
|
55 |
+
- Datasets 3.2.0
|
56 |
+
- Tokenizers 0.21.0
|
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"head_dim": 128,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 4096,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 14336,
|
19 |
+
"max_position_embeddings": 131072,
|
20 |
+
"mlp_bias": false,
|
21 |
+
"model_type": "llama",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_hidden_layers": 32,
|
24 |
+
"num_key_value_heads": 8,
|
25 |
+
"pad_token_id": 128004,
|
26 |
+
"pretraining_tp": 1,
|
27 |
+
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": {
|
29 |
+
"factor": 8.0,
|
30 |
+
"high_freq_factor": 4.0,
|
31 |
+
"low_freq_factor": 1.0,
|
32 |
+
"original_max_position_embeddings": 8192,
|
33 |
+
"rope_type": "llama3"
|
34 |
+
},
|
35 |
+
"rope_theta": 500000.0,
|
36 |
+
"tie_word_embeddings": false,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.47.1",
|
39 |
+
"unsloth_version": "2024.9",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 128258
|
42 |
+
}
|
.ipynb_checkpoints/generation_config-checkpoint.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
+
"max_length": 131072,
|
10 |
+
"pad_token_id": 128004,
|
11 |
+
"temperature": 0.6,
|
12 |
+
"top_p": 0.9,
|
13 |
+
"transformers_version": "4.47.1"
|
14 |
+
}
|
.ipynb_checkpoints/special_tokens_map-checkpoint.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|start_thinking_id|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|end_thinking_id|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": {
|
19 |
+
"content": "<|begin_of_text|>",
|
20 |
+
"lstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"rstrip": false,
|
23 |
+
"single_word": false
|
24 |
+
},
|
25 |
+
"eos_token": {
|
26 |
+
"content": "<|eot_id|>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
},
|
32 |
+
"pad_token": {
|
33 |
+
"content": "<|finetune_right_pad_id|>",
|
34 |
+
"lstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
}
|
39 |
+
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976715056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fab3fa9faac2ced7be74950f2579b392ecdb0b85c4862374ac7a331d867ec47
|
3 |
size 4976715056
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:624748535756b382557c9208d304064bf323ca7226c2d23d2a81b4c8f0091e2a
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0b8ff177ddd6bd870c319d1dab4491a6a4f6badd17d276dbd9a65a9e5c27099
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168155192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89cdd8741b7edb5e7ff52da7addcfee7855e5fb6c397860de65c88b3ad8806cb
|
3 |
size 1168155192
|
runs/Dec28_21-30-49_192-222-57-66/events.out.tfevents.1735421450.192-222-57-66.9957.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97a0ec33ddb5ee7f186998a59130899d69691b0a2583acd844e98f17489a3acf
|
3 |
+
size 5418
|
runs/Dec28_21-42-33_192-222-57-66/events.out.tfevents.1735422153.192-222-57-66.11204.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a3cc30f5b1d28ee8767d8ada76771984582cab02a0e10fee14012152e3ba1eb
|
3 |
+
size 6469
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c910fe4f83a5b00ed798c9954fbb7c70155102600ef9e1a1f3834713eaa9f2ea
|
3 |
size 5368
|