VictorSanh commited on
Commit
c132090
1 Parent(s): 429cec8

End of training

Browse files
Files changed (22) hide show
  1. README.md +58 -0
  2. adapter_config.json +25 -0
  3. adapter_model.safetensors +3 -0
  4. generation_config.json +7 -0
  5. runs/Apr12_03-10-00_ip-26-0-172-142/events.out.tfevents.1712891409.ip-26-0-172-142.3378547.0 +3 -0
  6. runs/Apr12_03-18-29_ip-26-0-172-142/events.out.tfevents.1712892006.ip-26-0-172-142.3381974.0 +3 -0
  7. runs/Apr12_03-44-05_ip-26-0-172-142/events.out.tfevents.1712893713.ip-26-0-172-142.3386329.0 +3 -0
  8. runs/Apr12_03-44-05_ip-26-0-172-142/events.out.tfevents.1712894071.ip-26-0-172-142.3386329.1 +3 -0
  9. runs/Apr12_03-44-05_ip-26-0-172-142/events.out.tfevents.1712894136.ip-26-0-172-142.3386329.2 +3 -0
  10. runs/Apr12_04-05-56_ip-26-0-172-142/events.out.tfevents.1712894762.ip-26-0-172-142.3390614.0 +3 -0
  11. runs/Apr12_04-07-59_ip-26-0-172-142/events.out.tfevents.1712894912.ip-26-0-172-142.3393448.0 +3 -0
  12. runs/Apr12_04-10-48_ip-26-0-172-142/events.out.tfevents.1712895058.ip-26-0-172-142.3394636.0 +3 -0
  13. runs/Apr12_04-12-00_ip-26-0-172-142/events.out.tfevents.1712895128.ip-26-0-172-142.3395679.0 +3 -0
  14. runs/Apr12_04-13-29_ip-26-0-172-142/events.out.tfevents.1712895215.ip-26-0-172-142.3396422.0 +3 -0
  15. runs/Apr12_04-14-23_ip-26-0-172-142/events.out.tfevents.1712895270.ip-26-0-172-142.3397376.0 +3 -0
  16. runs/Apr12_04-15-31_ip-26-0-172-142/events.out.tfevents.1712895337.ip-26-0-172-142.3398108.0 +3 -0
  17. runs/Apr12_04-16-23_ip-26-0-172-142/events.out.tfevents.1712895389.ip-26-0-172-142.3398799.0 +3 -0
  18. runs/Apr12_04-19-35_ip-26-0-172-142/events.out.tfevents.1712895577.ip-26-0-172-142.3400061.0 +3 -0
  19. runs/Apr12_04-20-52_ip-26-0-172-142/events.out.tfevents.1712895659.ip-26-0-172-142.3400695.0 +3 -0
  20. runs/Apr12_04-22-02_ip-26-0-172-142/events.out.tfevents.1712895726.ip-26-0-172-142.3401497.0 +3 -0
  21. runs/Apr12_04-26-40_ip-26-0-172-142/events.out.tfevents.1712896004.ip-26-0-172-142.3403103.0 +3 -0
  22. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: HuggingFaceM4/idefics2-8b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: idefics2-8b-docvqa-finetuned
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # idefics2-8b-docvqa-finetuned
15
+
16
+ This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 8
40
+ - total_train_batch_size: 64
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 50
44
+ - num_epochs: 1
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 1.0 | 10 | 2.8948 |
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.39.0.dev0
56
+ - Pytorch 2.1.2+cu118
57
+ - Datasets 2.14.7
58
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 8,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
22
+ "task_type": null,
23
+ "use_dora": false,
24
+ "use_rslora": false
25
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87645649280a6bb8348644625c1ec2b2a02932f724eaa0389185d3f90ee7ef47
3
+ size 93378208
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
runs/Apr12_03-10-00_ip-26-0-172-142/events.out.tfevents.1712891409.ip-26-0-172-142.3378547.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65eea661fc20d5310f31901fd5a858004b5134fed9cc80434f3127d807650406
3
+ size 10342
runs/Apr12_03-18-29_ip-26-0-172-142/events.out.tfevents.1712892006.ip-26-0-172-142.3381974.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c86d3bfc7318891182cbcac17b21c3ad393672296d1e799bfd9c3998e3ce5c1
3
+ size 10342
runs/Apr12_03-44-05_ip-26-0-172-142/events.out.tfevents.1712893713.ip-26-0-172-142.3386329.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4184accddad6a3f8fbb7a43a78c7b1d531b4811559ff6a621e5821e91c289b
3
+ size 10342
runs/Apr12_03-44-05_ip-26-0-172-142/events.out.tfevents.1712894071.ip-26-0-172-142.3386329.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5920251b7ebaf1284303709afbeff6b4fc867e80ce47fb7f99558fd36d1fe1
3
+ size 10342
runs/Apr12_03-44-05_ip-26-0-172-142/events.out.tfevents.1712894136.ip-26-0-172-142.3386329.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d390c74db1d116bf86ec8974d9d94669df8b14cc5a788e20121dd579a6591278
3
+ size 10342
runs/Apr12_04-05-56_ip-26-0-172-142/events.out.tfevents.1712894762.ip-26-0-172-142.3390614.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2988cdee4ce1f4a717f286fb25c3ab36345d36a7c5f2f878ca4ef5fe3ca2c2c
3
+ size 10343
runs/Apr12_04-07-59_ip-26-0-172-142/events.out.tfevents.1712894912.ip-26-0-172-142.3393448.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca2ed0fa7f301d46b36d4e0789cff97f89e7e6910d65e90af85df8409bab1e1b
3
+ size 10343
runs/Apr12_04-10-48_ip-26-0-172-142/events.out.tfevents.1712895058.ip-26-0-172-142.3394636.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c122b6ea4c3b849b7c86b08026166afa8d73ab9966e4c0b899ccd9d35f761032
3
+ size 10343
runs/Apr12_04-12-00_ip-26-0-172-142/events.out.tfevents.1712895128.ip-26-0-172-142.3395679.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e9037e56324389328ae0534433c8e8316e32e855712ce94d07592f5d635309a
3
+ size 10343
runs/Apr12_04-13-29_ip-26-0-172-142/events.out.tfevents.1712895215.ip-26-0-172-142.3396422.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59a59c810a0a5dab5093942ccd6cef62e9034fdfcda68d18edde5a5cb4bfbbf9
3
+ size 10342
runs/Apr12_04-14-23_ip-26-0-172-142/events.out.tfevents.1712895270.ip-26-0-172-142.3397376.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a29cc69d2d3dd68af7fa6c3c62ade5cf82bbd6c8cc85a0ecba5914cdc388b2
3
+ size 10342
runs/Apr12_04-15-31_ip-26-0-172-142/events.out.tfevents.1712895337.ip-26-0-172-142.3398108.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46798bc0232c0af4f0a894820732b51cf9be1474b5625741980ff4120e81d273
3
+ size 10342
runs/Apr12_04-16-23_ip-26-0-172-142/events.out.tfevents.1712895389.ip-26-0-172-142.3398799.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea1c4c242cbc7fc488d8a4b46962379061056c70b2e2439f932f394345aef12
3
+ size 10342
runs/Apr12_04-19-35_ip-26-0-172-142/events.out.tfevents.1712895577.ip-26-0-172-142.3400061.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4244554bae20e777342012dd0c5b44d8928c411adfa536efc41414bd8df534c3
3
+ size 10342
runs/Apr12_04-20-52_ip-26-0-172-142/events.out.tfevents.1712895659.ip-26-0-172-142.3400695.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd3a88972080571fca0ba00c6059a4b52a99a4b0da635b5d38d224027d1b005
3
+ size 10342
runs/Apr12_04-22-02_ip-26-0-172-142/events.out.tfevents.1712895726.ip-26-0-172-142.3401497.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6818054f084aea3e2cc3204988c956c896e922c3ad312f03b1e15ebd894c1f
3
+ size 10342
runs/Apr12_04-26-40_ip-26-0-172-142/events.out.tfevents.1712896004.ip-26-0-172-142.3403103.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ed0a1ddcaed6c29df6ec5e484e0cb2491795b61d48b48dd5d2e9c1715ca991f
3
+ size 10549
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d178bc820978d9f99fcd5c1060b9317bd70802f6ed98f7067818cbcda49c91c
3
+ size 4984