MuhammadRozaq2001
commited on
Commit
•
718a714
1
Parent(s):
3a26a09
Upload folder using huggingface_hub
Browse files- checkpoint-20/adapter_config.json +26 -0
- checkpoint-20/adapter_model.safetensors +3 -0
- checkpoint-20/generation_config.json +18 -0
- checkpoint-20/optimizer.pt +3 -0
- checkpoint-20/rng_state.pth +3 -0
- checkpoint-20/scheduler.pt +3 -0
- checkpoint-20/trainer_state.json +61 -0
- checkpoint-20/training_args.bin +3 -0
checkpoint-20/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 |
+
}
|
checkpoint-20/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0617e2ec2b2dc7c1e543bd0ec51ed82440af4808e85f58ba84dc227a441bf07
|
3 |
+
size 93378688
|
checkpoint-20/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": "4.42.0.dev0"
|
18 |
+
}
|
checkpoint-20/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1446410878df711718bb45d3e61de71bc75d152a36378b2903b18fa2cbe9b8f0
|
3 |
+
size 187031330
|
checkpoint-20/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57250ac10f6af1fbfcd73a494327da1fbfbcf5a2af4d70ff6d7849bcd0c5a51d
|
3 |
+
size 14244
|
checkpoint-20/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dccdb0ae3490e3b9673ef1d9ca654f432566fd335a557c64707b28c0d453262
|
3 |
+
size 1064
|
checkpoint-20/trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.016263468184590364,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 20,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.004065867046147591,
|
13 |
+
"grad_norm": 1.4972760677337646,
|
14 |
+
"learning_rate": 9.959316517493899e-05,
|
15 |
+
"loss": 0.0619,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.008131734092295182,
|
20 |
+
"grad_norm": 1.9904061555862427,
|
21 |
+
"learning_rate": 9.918633034987795e-05,
|
22 |
+
"loss": 0.0764,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.012197601138442773,
|
27 |
+
"grad_norm": 1.7890241146087646,
|
28 |
+
"learning_rate": 9.877949552481694e-05,
|
29 |
+
"loss": 0.0757,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.016263468184590364,
|
34 |
+
"grad_norm": 1.857191562652588,
|
35 |
+
"learning_rate": 9.83726606997559e-05,
|
36 |
+
"loss": 0.0837,
|
37 |
+
"step": 20
|
38 |
+
}
|
39 |
+
],
|
40 |
+
"logging_steps": 5,
|
41 |
+
"max_steps": 1229,
|
42 |
+
"num_input_tokens_seen": 0,
|
43 |
+
"num_train_epochs": 1,
|
44 |
+
"save_steps": 10,
|
45 |
+
"stateful_callbacks": {
|
46 |
+
"TrainerControl": {
|
47 |
+
"args": {
|
48 |
+
"should_epoch_stop": false,
|
49 |
+
"should_evaluate": false,
|
50 |
+
"should_log": false,
|
51 |
+
"should_save": true,
|
52 |
+
"should_training_stop": false
|
53 |
+
},
|
54 |
+
"attributes": {}
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"total_flos": 361084771808640.0,
|
58 |
+
"train_batch_size": 1,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": null
|
61 |
+
}
|
checkpoint-20/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f267c12e6fd0265a2329de727d79d6f7f57ec8e1e8e68fd5e86812fbfa930875
|
3 |
+
size 5112
|