Omkarp2403 commited on
Commit
0a606fd
·
verified ·
1 Parent(s): b30b56b

Pushed the IDEFICS2 fine-tuned model.

Browse files
checkpoint-25/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "HuggingFaceM4/idefics2-8b",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": false,
11
+ "init_lora_weights": "gaussian",
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 8,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
27
+ "task_type": null,
28
+ "trainable_token_indices": null,
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
checkpoint-25/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ddabc4179c4ce4494da49d07c62c7351b48cdcfd6dc08fef5b16b254552f5d3
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": "4.52.0.dev0"
18
+ }
checkpoint-25/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2e7188f6563d83a85693243253bd4209cf222e409192fc1d2967a52020c6af
3
+ size 187031330
checkpoint-25/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed3397b392a1fc35a99372c5743d1653a93a874bf09e19a46cdc9f89eda2810
3
+ size 14244
checkpoint-25/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef8f409b013c8bac4bd6d3a272e6812c5fb03ef9606ea54c01c2c7128bc8a993
3
+ size 988
checkpoint-25/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
3
+ size 1064
checkpoint-25/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.4,
6
+ "eval_steps": 500,
7
+ "global_step": 25,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.08,
14
+ "grad_norm": 12.403694152832031,
15
+ "learning_rate": 0.000168,
16
+ "loss": 4.6961,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.16,
21
+ "grad_norm": 5.873738765716553,
22
+ "learning_rate": 0.00012800000000000002,
23
+ "loss": 0.4301,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.24,
28
+ "grad_norm": 4.730180263519287,
29
+ "learning_rate": 8.800000000000001e-05,
30
+ "loss": 0.3415,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.32,
35
+ "grad_norm": 4.720490455627441,
36
+ "learning_rate": 4.8e-05,
37
+ "loss": 0.3146,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.4,
42
+ "grad_norm": 3.4999067783355713,
43
+ "learning_rate": 8.000000000000001e-06,
44
+ "loss": 0.2775,
45
+ "step": 25
46
+ }
47
+ ],
48
+ "logging_steps": 5,
49
+ "max_steps": 25,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 1,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "TrainerControl": {
55
+ "args": {
56
+ "should_epoch_stop": false,
57
+ "should_evaluate": false,
58
+ "should_log": false,
59
+ "should_save": true,
60
+ "should_training_stop": true
61
+ },
62
+ "attributes": {}
63
+ }
64
+ },
65
+ "total_flos": 1864609930455360.0,
66
+ "train_batch_size": 2,
67
+ "trial_name": null,
68
+ "trial_params": null
69
+ }
checkpoint-25/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96842efe8174cd654502546099fd82fc6016ef3ac8826c827ffaea3b6d16fe4b
3
+ size 5304
runs/May05_14-53-31_3dfa5c94652d/events.out.tfevents.1746456818.3dfa5c94652d.299.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d84c76f30e82dc41f55a9923e11c2bc51418be90f49d35d9d28417157691031
3
+ size 6378
runs/May05_14-54-55_3dfa5c94652d/events.out.tfevents.1746456899.3dfa5c94652d.299.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285fb41dbc29575cc0319ea9c2f2561cb9be18bdb5681a80de81700c2760a40a
3
+ size 7761