Upload folder using huggingface_hub
Browse files- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- generation_config.json +18 -0
- optimizer.pt +3 -0
- preprocessor_config.json +26 -0
- processor_config.json +5 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +53 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +73 -0
- trainer_state.json +82 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "HuggingFaceM4/idefics2-8b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": false,
|
8 |
+
"init_lora_weights": "gaussian",
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 8,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
|
23 |
+
"task_type": null,
|
24 |
+
"use_dora": false,
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4efec4a3facfcd8249d8a13a5173c7ccd7e902b067a500624e759ba872dc04c
|
3 |
+
size 93378688
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<end_of_utterance>": 32002,
|
3 |
+
"<fake_token_around_image>": 32000,
|
4 |
+
"<image>": 32001
|
5 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bad_words_ids": [
|
4 |
+
[
|
5 |
+
32000
|
6 |
+
],
|
7 |
+
[
|
8 |
+
32001
|
9 |
+
]
|
10 |
+
],
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"eos_token_id": [
|
13 |
+
2,
|
14 |
+
32002
|
15 |
+
],
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"transformers_version": "4.42.4"
|
18 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cbf963cb42fa93060a25cf421fe73b7ad8100bc0cab5e4b24dbfb4d4ef3b225
|
3 |
+
size 187031330
|
preprocessor_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": true,
|
3 |
+
"do_image_splitting": false,
|
4 |
+
"do_normalize": true,
|
5 |
+
"do_pad": true,
|
6 |
+
"do_rescale": true,
|
7 |
+
"do_resize": true,
|
8 |
+
"image_mean": [
|
9 |
+
0.5,
|
10 |
+
0.5,
|
11 |
+
0.5
|
12 |
+
],
|
13 |
+
"image_processor_type": "Idefics2ImageProcessor",
|
14 |
+
"image_std": [
|
15 |
+
0.5,
|
16 |
+
0.5,
|
17 |
+
0.5
|
18 |
+
],
|
19 |
+
"processor_class": "Idefics2Processor",
|
20 |
+
"resample": 2,
|
21 |
+
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": {
|
23 |
+
"longest_edge": 980,
|
24 |
+
"shortest_edge": 378
|
25 |
+
}
|
26 |
+
}
|
processor_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_template": "{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
|
3 |
+
"image_seq_len": 64,
|
4 |
+
"processor_class": "Idefics2Processor"
|
5 |
+
}
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33e2410aacf23e3cdf94e9dfe07fc0fb036174d3916b636e4f8f88278c1a6e25
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4d286adb908f4f36cbeb933b1839730cf9babc3fcf94fc7bbea51e1ff27974d
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<fake_token_around_image>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<image>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<end_of_utterance>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"bos_token": {
|
26 |
+
"content": "<s>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
},
|
32 |
+
"eos_token": {
|
33 |
+
"content": "</s>",
|
34 |
+
"lstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
},
|
39 |
+
"pad_token": {
|
40 |
+
"content": "<unk>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": false,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"unk_token": {
|
47 |
+
"content": "<unk>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false
|
52 |
+
}
|
53 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
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": "<fake_token_around_image>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<image>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<end_of_utterance>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
}
|
54 |
+
},
|
55 |
+
"additional_special_tokens": [
|
56 |
+
"<fake_token_around_image>",
|
57 |
+
"<image>",
|
58 |
+
"<end_of_utterance>"
|
59 |
+
],
|
60 |
+
"bos_token": "<s>",
|
61 |
+
"clean_up_tokenization_spaces": false,
|
62 |
+
"do_image_splitting": false,
|
63 |
+
"eos_token": "</s>",
|
64 |
+
"legacy": false,
|
65 |
+
"model_max_length": 1000000000000000019884624838656,
|
66 |
+
"pad_token": "<unk>",
|
67 |
+
"processor_class": "Idefics2Processor",
|
68 |
+
"sp_model_kwargs": {},
|
69 |
+
"spaces_between_special_tokens": false,
|
70 |
+
"tokenizer_class": "LlamaTokenizer",
|
71 |
+
"unk_token": "<unk>",
|
72 |
+
"use_default_system_prompt": true
|
73 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.8,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 175,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.4,
|
13 |
+
"grad_norm": 7.9200921058654785,
|
14 |
+
"learning_rate": 4.8e-05,
|
15 |
+
"loss": 5.7051,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.8,
|
20 |
+
"grad_norm": 3.6645238399505615,
|
21 |
+
"learning_rate": 9.6e-05,
|
22 |
+
"loss": 0.2689,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.2,
|
27 |
+
"grad_norm": 4.637652397155762,
|
28 |
+
"learning_rate": 8.83838383838384e-05,
|
29 |
+
"loss": 0.2192,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.6,
|
34 |
+
"grad_norm": 3.7763524055480957,
|
35 |
+
"learning_rate": 7.575757575757576e-05,
|
36 |
+
"loss": 0.1836,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 2.0,
|
41 |
+
"grad_norm": 3.533644437789917,
|
42 |
+
"learning_rate": 6.313131313131313e-05,
|
43 |
+
"loss": 0.1687,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 2.4,
|
48 |
+
"grad_norm": 1.9909617900848389,
|
49 |
+
"learning_rate": 5.050505050505051e-05,
|
50 |
+
"loss": 0.0919,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 2.8,
|
55 |
+
"grad_norm": 2.7650041580200195,
|
56 |
+
"learning_rate": 3.787878787878788e-05,
|
57 |
+
"loss": 0.0918,
|
58 |
+
"step": 175
|
59 |
+
}
|
60 |
+
],
|
61 |
+
"logging_steps": 25,
|
62 |
+
"max_steps": 248,
|
63 |
+
"num_input_tokens_seen": 0,
|
64 |
+
"num_train_epochs": 4,
|
65 |
+
"save_steps": 25,
|
66 |
+
"stateful_callbacks": {
|
67 |
+
"TrainerControl": {
|
68 |
+
"args": {
|
69 |
+
"should_epoch_stop": false,
|
70 |
+
"should_evaluate": false,
|
71 |
+
"should_log": false,
|
72 |
+
"should_save": true,
|
73 |
+
"should_training_stop": false
|
74 |
+
},
|
75 |
+
"attributes": {}
|
76 |
+
}
|
77 |
+
},
|
78 |
+
"total_flos": 1.4019041661178752e+16,
|
79 |
+
"train_batch_size": 2,
|
80 |
+
"trial_name": null,
|
81 |
+
"trial_params": null
|
82 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb8a1f2e9795515487d4d491fa36433c29b6baba7cf3119c847240a658a0f764
|
3 |
+
size 5112
|