Hugging Face's logo

isimorfizam
/
logs

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
isimorfizam commited on
Commit
9638e7c
·
verified ·
1 Parent(s): 5adff8f

End of training

Browse files
Files changed (12) hide show
  1. README.md +82 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. generation_config.json +7 -0
  5. runs/Apr03_11-58-29_driver-77548c5448-n2rds/events.out.tfevents.1712145518.driver-77548c5448-n2rds.2740.0 +3 -0
  6. runs/Apr03_12-25-46_driver-548f4dfd-hr96f/events.out.tfevents.1712147150.driver-548f4dfd-hr96f.3252.0 +3 -0
  7. runs/Apr03_12-26-58_driver-548f4dfd-hr96f/events.out.tfevents.1712147222.driver-548f4dfd-hr96f.3252.1 +3 -0
  8. runs/Apr03_12-48-23_driver-6fc58c79cc-xl4ll/events.out.tfevents.1712148511.driver-6fc58c79cc-xl4ll.3492.0 +3 -0
  9. runs/Apr03_12-49-16_driver-6fc58c79cc-xl4ll/events.out.tfevents.1712148563.driver-6fc58c79cc-xl4ll.3492.1 +3 -0
  10. runs/Apr03_12-49-40_driver-6fc58c79cc-xl4ll/events.out.tfevents.1712148584.driver-6fc58c79cc-xl4ll.3492.2 +3 -0
  11. runs/Apr03_12-49-53_driver-6fc58c79cc-xl4ll/events.out.tfevents.1712148596.driver-6fc58c79cc-xl4ll.3492.3 +3 -0
  12. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: gemma
3
+ base_model: google/gemma-2b-it
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: logs
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
+ # logs
15
+
16
+ This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.6513
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0002
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_ratio: 0.03
45
+ - num_epochs: 2
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 3.1035 | 0.08 | 112 | 3.1213 |
53
+ | 3.0698 | 0.17 | 224 | 3.0171 |
54
+ | 3.0451 | 0.25 | 336 | 2.9717 |
55
+ | 2.8939 | 0.33 | 448 | 2.9336 |
56
+ | 2.8892 | 0.42 | 560 | 2.9099 |
57
+ | 2.8566 | 0.5 | 672 | 2.8757 |
58
+ | 2.8654 | 0.58 | 784 | 2.8486 |
59
+ | 2.8261 | 0.67 | 896 | 2.8291 |
60
+ | 2.8868 | 0.75 | 1008 | 2.7998 |
61
+ | 2.819 | 0.84 | 1120 | 2.7781 |
62
+ | 2.8064 | 0.92 | 1232 | 2.7543 |
63
+ | 2.761 | 1.0 | 1344 | 2.7338 |
64
+ | 2.3883 | 1.09 | 1456 | 2.7416 |
65
+ | 2.3511 | 1.17 | 1568 | 2.7239 |
66
+ | 2.3174 | 1.25 | 1680 | 2.7140 |
67
+ | 2.3234 | 1.34 | 1792 | 2.7004 |
68
+ | 2.3364 | 1.42 | 1904 | 2.6826 |
69
+ | 2.3079 | 1.5 | 2016 | 2.6718 |
70
+ | 2.2965 | 1.59 | 2128 | 2.6649 |
71
+ | 2.2233 | 1.67 | 2240 | 2.6626 |
72
+ | 2.2199 | 1.75 | 2352 | 2.6590 |
73
+ | 2.3126 | 1.84 | 2464 | 2.6526 |
74
+ | 2.2602 | 1.92 | 2576 | 2.6513 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.39.3
80
+ - Pytorch 2.0.0+cu117
81
+ - Datasets 2.16.0
82
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2b-it",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": false,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "o_proj",
25
+ "gate_proj",
26
+ "up_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebbcd8f654f927a34934eeff1e3790bd92a88fb72dd137865e276a51b69cc47f
3
+ size 313820248
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.3"
7
+ }
runs/Apr03_11-58-29_driver-77548c5448-n2rds/events.out.tfevents.1712145518.driver-77548c5448-n2rds.2740.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1769e9da4dcd2b6afd3b2a81da0146af8029c5274872dde0b95013082b322e10
3
+ size 4184
runs/Apr03_12-25-46_driver-548f4dfd-hr96f/events.out.tfevents.1712147150.driver-548f4dfd-hr96f.3252.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8ad484568e443b89f4832f4a72c4634305db529b09213ac78187f34bd4fbf8
3
+ size 5120
runs/Apr03_12-26-58_driver-548f4dfd-hr96f/events.out.tfevents.1712147222.driver-548f4dfd-hr96f.3252.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f686df8aea92f417160da9c1a4cccdc37b74d63162784888459eb80c0c0881
3
+ size 5120
runs/Apr03_12-48-23_driver-6fc58c79cc-xl4ll/events.out.tfevents.1712148511.driver-6fc58c79cc-xl4ll.3492.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a27cf99d2bcfdf744e24452d5a46a16b8c2fd749785dc057229b9fc58c1ace
3
+ size 5536
runs/Apr03_12-49-16_driver-6fc58c79cc-xl4ll/events.out.tfevents.1712148563.driver-6fc58c79cc-xl4ll.3492.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a610fa6d74cfaec0ff0b01ab3d7c79bb95888ac9913d5322263ad800a02d7b9e
3
+ size 5123
runs/Apr03_12-49-40_driver-6fc58c79cc-xl4ll/events.out.tfevents.1712148584.driver-6fc58c79cc-xl4ll.3492.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9f4b80d4b764117a414ba46ecd29befb7de6428cc34a8bf9f72ea5d3bbe561d
3
+ size 5122
runs/Apr03_12-49-53_driver-6fc58c79cc-xl4ll/events.out.tfevents.1712148596.driver-6fc58c79cc-xl4ll.3492.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9310b3ff65cbb7418c600d26fd6bf9ee84c81590c0ff07c022a30d389024348
3
+ size 34261
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d94773e611d4d24e7daadeb2d9303f9264db5cdb756290b354112e92f8687a
3
+ size 4411