Pushed the IDEFICS2 fine-tuned model.
Browse files- checkpoint-25/adapter_config.json +26 -0
- checkpoint-25/adapter_model.safetensors +3 -0
- checkpoint-25/generation_config.json +18 -0
- checkpoint-25/optimizer.pt +3 -0
- checkpoint-25/rng_state.pth +3 -0
- checkpoint-25/scheduler.pt +3 -0
- checkpoint-25/trainer_state.json +63 -0
- checkpoint-25/training_args.bin +3 -0
checkpoint-25/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-25/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66cb8296ff4e56045a0ce937861c2d7526daffe451b49913960c7bf84a5e5969
|
3 |
+
size 93378688
|
checkpoint-25/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": "4.45.0.dev0"
|
18 |
+
}
|
checkpoint-25/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fda770a1980c81fafca345721359c5f0088d85bc30bc9ff8646d41d6a8ca5557
|
3 |
+
size 47425352
|
checkpoint-25/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8da04eb03f3a80fbaf8f9ea197d8b47abba625ad1e182174b952163d23cb3e2c
|
3 |
+
size 14244
|
checkpoint-25/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8531775f4e5c3819ae81b2ea1cfeb7e992dc0ca011334fb9ed6fb83e3392e473
|
3 |
+
size 1064
|
checkpoint-25/trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.7037037037037037,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 25,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.4814814814814814,
|
13 |
+
"grad_norm": 119.2230224609375,
|
14 |
+
"learning_rate": 6e-06,
|
15 |
+
"loss": 10.468,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.4814814814814814,
|
20 |
+
"eval_loss": 6.026649475097656,
|
21 |
+
"eval_runtime": 9.5208,
|
22 |
+
"eval_samples_per_second": 1.26,
|
23 |
+
"eval_steps_per_second": 0.63,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.962962962962963,
|
28 |
+
"grad_norm": 86.91220092773438,
|
29 |
+
"learning_rate": 2.0000000000000003e-06,
|
30 |
+
"loss": 3.5893,
|
31 |
+
"step": 20
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.962962962962963,
|
35 |
+
"eval_loss": 1.231614589691162,
|
36 |
+
"eval_runtime": 9.5301,
|
37 |
+
"eval_samples_per_second": 1.259,
|
38 |
+
"eval_steps_per_second": 0.63,
|
39 |
+
"step": 20
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 10,
|
43 |
+
"max_steps": 25,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 5,
|
46 |
+
"save_steps": 25,
|
47 |
+
"stateful_callbacks": {
|
48 |
+
"TrainerControl": {
|
49 |
+
"args": {
|
50 |
+
"should_epoch_stop": false,
|
51 |
+
"should_evaluate": false,
|
52 |
+
"should_log": false,
|
53 |
+
"should_save": true,
|
54 |
+
"should_training_stop": true
|
55 |
+
},
|
56 |
+
"attributes": {}
|
57 |
+
}
|
58 |
+
},
|
59 |
+
"total_flos": 2058382144087104.0,
|
60 |
+
"train_batch_size": 2,
|
61 |
+
"trial_name": null,
|
62 |
+
"trial_params": null
|
63 |
+
}
|
checkpoint-25/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a551b33fa98d3ba98a02936ff8826ff7fe6f0f72d858651a6fa0b2459bff3869
|
3 |
+
size 5176
|