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 +89 -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:d6c048e1d5e7740c13884b85679e66e39f906f27073b31104e764096b54f7de6
|
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": "4.43.0.dev0"
|
18 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:864c5f4d015d1f8914e51d4b9df46e60a48eada7bd98da426fd1e8e9e2cf7a2e
|
3 |
+
size 187031330
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d70931949b6d3a27257669c89a6123c4223fb272dd17148ccfbf14da0dae05f
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43b5c7f86ddff27e10a49b01685eabcb22f6385fb9b4a21baa8d04f5c96cc601
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.993142857142857,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 218,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.22857142857142856,
|
13 |
+
"grad_norm": 7.164783477783203,
|
14 |
+
"learning_rate": 5e-05,
|
15 |
+
"loss": 6.0925,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.45714285714285713,
|
20 |
+
"grad_norm": 0.9276559352874756,
|
21 |
+
"learning_rate": 0.0001,
|
22 |
+
"loss": 0.03,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6857142857142857,
|
27 |
+
"grad_norm": 2.69968581199646,
|
28 |
+
"learning_rate": 8.511904761904762e-05,
|
29 |
+
"loss": 0.0149,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.9142857142857143,
|
34 |
+
"grad_norm": 0.35357868671417236,
|
35 |
+
"learning_rate": 7.023809523809524e-05,
|
36 |
+
"loss": 0.0108,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.1428571428571428,
|
41 |
+
"grad_norm": 0.19637013971805573,
|
42 |
+
"learning_rate": 5.535714285714286e-05,
|
43 |
+
"loss": 0.0073,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.3714285714285714,
|
48 |
+
"grad_norm": 0.08578420430421829,
|
49 |
+
"learning_rate": 4.047619047619048e-05,
|
50 |
+
"loss": 0.0052,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.6,
|
55 |
+
"grad_norm": 0.17291192710399628,
|
56 |
+
"learning_rate": 2.5595238095238093e-05,
|
57 |
+
"loss": 0.0064,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.8285714285714287,
|
62 |
+
"grad_norm": 0.08965189754962921,
|
63 |
+
"learning_rate": 1.0714285714285714e-05,
|
64 |
+
"loss": 0.0049,
|
65 |
+
"step": 200
|
66 |
+
}
|
67 |
+
],
|
68 |
+
"logging_steps": 25,
|
69 |
+
"max_steps": 218,
|
70 |
+
"num_input_tokens_seen": 0,
|
71 |
+
"num_train_epochs": 2,
|
72 |
+
"save_steps": 25,
|
73 |
+
"stateful_callbacks": {
|
74 |
+
"TrainerControl": {
|
75 |
+
"args": {
|
76 |
+
"should_epoch_stop": false,
|
77 |
+
"should_evaluate": false,
|
78 |
+
"should_log": false,
|
79 |
+
"should_save": true,
|
80 |
+
"should_training_stop": true
|
81 |
+
},
|
82 |
+
"attributes": {}
|
83 |
+
}
|
84 |
+
},
|
85 |
+
"total_flos": 1.5553403260393152e+16,
|
86 |
+
"train_batch_size": 2,
|
87 |
+
"trial_name": null,
|
88 |
+
"trial_params": null
|
89 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16c21f4578c336b1ac3c368e6252ffb76a2849c0ef78aefb195040c32d8f55cf
|
3 |
+
size 5240
|