neuronstarml
commited on
Commit
•
6629ea7
1
Parent(s):
be0a049
Upload folder using huggingface_hub
Browse files- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- generation_config.json +18 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +49 -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 sha256:43a8911b58be7a9c990fc88be24a5808cf70572c9d815474f94e5e618e2ebcfc
|
3 |
+
size 93378688
|
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": "4.40.0"
|
18 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa727f15c4162e4cc509881876ee9bdb20fa7338736d17f7af7397115b030fa3
|
3 |
+
size 187031330
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f436a4fb471d5f202413a386718639e2b47231fc611f43c3b4967a2e017fff50
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9355a3b2de746183934ddba69f485e76b6eeb1785e61829c4786507295f00225
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.6,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
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": 16.487810134887695,
|
14 |
+
"learning_rate": 4.600000000000001e-05,
|
15 |
+
"loss": 2.5731,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.8,
|
20 |
+
"grad_norm": 14.608394622802734,
|
21 |
+
"learning_rate": 9.6e-05,
|
22 |
+
"loss": 0.7107,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.2,
|
27 |
+
"grad_norm": 12.708142280578613,
|
28 |
+
"learning_rate": 6.891891891891892e-05,
|
29 |
+
"loss": 0.5899,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.6,
|
34 |
+
"grad_norm": 12.00189208984375,
|
35 |
+
"learning_rate": 3.513513513513514e-05,
|
36 |
+
"loss": 0.4792,
|
37 |
+
"step": 100
|
38 |
+
}
|
39 |
+
],
|
40 |
+
"logging_steps": 25,
|
41 |
+
"max_steps": 124,
|
42 |
+
"num_input_tokens_seen": 0,
|
43 |
+
"num_train_epochs": 2,
|
44 |
+
"save_steps": 25,
|
45 |
+
"total_flos": 8017574019985728.0,
|
46 |
+
"train_batch_size": 2,
|
47 |
+
"trial_name": null,
|
48 |
+
"trial_params": null
|
49 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c157f0509fd949387ecf213906fffa4ce340a953489da18faecb55a951c533ba
|
3 |
+
size 5048
|