Hugging Face's logo

sumo43
/
zephyr-7b-sft-full

Text Generation
Transformers
TensorBoard
Safetensors
bit_llama
trl
sft
Generated from Trainer
conversational
Inference Endpoints
Model card Files Metrics Community
sumo43 commited on
Commit
5e60488
·
verified ·
1 Parent(s): df023aa

Training in progress, step 400

Browse files
Files changed (25) hide show
  1. README.md +63 -0
  2. added_tokens.json +4 -0
  3. all_results.json +8 -0
  4. config.json +29 -0
  5. generation_config.json +7 -0
  6. model.safetensors +3 -0
  7. runs/Mar21_00-23-42_07374fba148d/events.out.tfevents.1710980648.07374fba148d.7763.0 +3 -0
  8. runs/Mar21_00-29-31_07374fba148d/events.out.tfevents.1710980999.07374fba148d.7965.0 +3 -0
  9. runs/Mar21_00-31-53_07374fba148d/events.out.tfevents.1710981326.07374fba148d.8126.0 +3 -0
  10. runs/Mar21_00-39-50_07374fba148d/events.out.tfevents.1710981648.07374fba148d.8476.0 +3 -0
  11. runs/Mar21_00-41-26_07374fba148d/events.out.tfevents.1710981732.07374fba148d.8721.0 +3 -0
  12. runs/Mar21_00-47-01_07374fba148d/events.out.tfevents.1710982043.07374fba148d.8925.0 +3 -0
  13. runs/Mar21_00-55-01_07374fba148d/events.out.tfevents.1710982517.07374fba148d.9276.0 +3 -0
  14. runs/Mar21_00-55-57_07374fba148d/events.out.tfevents.1710982601.07374fba148d.9407.0 +3 -0
  15. runs/Mar21_00-58-07_07374fba148d/events.out.tfevents.1710982732.07374fba148d.9549.0 +3 -0
  16. runs/Mar21_01-00-09_07374fba148d/events.out.tfevents.1710982856.07374fba148d.9691.0 +3 -0
  17. runs/Mar21_01-01-51_07374fba148d/events.out.tfevents.1710982957.07374fba148d.9834.0 +3 -0
  18. runs/Mar21_01-03-08_07374fba148d/events.out.tfevents.1710983033.07374fba148d.9963.0 +3 -0
  19. special_tokens_map.json +28 -0
  20. tokenizer.json +0 -0
  21. tokenizer.model +3 -0
  22. tokenizer_config.json +62 -0
  23. train_results.json +8 -0
  24. trainer_state.json +73 -0
  25. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ datasets:
9
+ - generator
10
+ model-index:
11
+ - name: zephyr-7b-sft-full
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # zephyr-7b-sft-full
19
+
20
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the generator dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.1635
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - distributed_type: multi-GPU
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 1
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:---------------:|
55
+ | 1.1523 | 1.0 | 22 | 1.1635 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.39.0.dev0
61
+ - Pytorch 2.1.1+cu121
62
+ - Datasets 2.14.6
63
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32001,
3
+ "<|im_start|>": 32000
4
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.118579317222942,
4
+ "train_runtime": 83.4654,
5
+ "train_samples": 500,
6
+ "train_samples_per_second": 4.038,
7
+ "train_steps_per_second": 0.264
8
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
+ "architectures": [
4
+ "BitLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bits": 8,
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 5632,
15
+ "max_position_embeddings": 2048,
16
+ "model_type": "bit_llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.39.0.dev0",
27
+ "use_cache": false,
28
+ "vocab_size": 32002
29
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3a5dbfc54d340a21be435db4e995d99f79b039e0840313a725ccdbb3c3c79d1
3
+ size 2201749928
runs/Mar21_00-23-42_07374fba148d/events.out.tfevents.1710980648.07374fba148d.7763.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8668691a5c92d49fc226c4aa399523ae3c23449cfb3d63b60960ecf837570458
3
+ size 5564
runs/Mar21_00-29-31_07374fba148d/events.out.tfevents.1710980999.07374fba148d.7965.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e765a31a552363cb13637fe4abf7bd5fd31ef07cdf7f03bd027d1d69113135ac
3
+ size 4943
runs/Mar21_00-31-53_07374fba148d/events.out.tfevents.1710981326.07374fba148d.8126.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec64cbb3066b760b03c6c98a99d430f530b81ea0b6a9f4954201ff09c630f0db
3
+ size 4752
runs/Mar21_00-39-50_07374fba148d/events.out.tfevents.1710981648.07374fba148d.8476.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c3ec3b9237b0479fc1f29fbe7dd28b541dc21d8167106213c700cd8a370dfa
3
+ size 4945
runs/Mar21_00-41-26_07374fba148d/events.out.tfevents.1710981732.07374fba148d.8721.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f2bfa1bc7d292120311cef6e64d88b25339e4576b8165e602666386870467b
3
+ size 5773
runs/Mar21_00-47-01_07374fba148d/events.out.tfevents.1710982043.07374fba148d.8925.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76e247d9ac4aeade9317ff5c53d9703f08ed00815d6cc0477ab085d751f0cb02
3
+ size 6370
runs/Mar21_00-55-01_07374fba148d/events.out.tfevents.1710982517.07374fba148d.9276.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec33d829cb82f0f65db9488096a924b06cf5e0fea48a723859d56eb396a0c8a
3
+ size 4928
runs/Mar21_00-55-57_07374fba148d/events.out.tfevents.1710982601.07374fba148d.9407.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855f6eba748a8dac0daaf8e81bce367008a0130e68330e1dbd620c4fb369c775
3
+ size 4738
runs/Mar21_00-58-07_07374fba148d/events.out.tfevents.1710982732.07374fba148d.9549.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb753b8a5533feb703d59e2105818f29de2946a464db695d9d0137e0d3ae2d3
3
+ size 4738
runs/Mar21_01-00-09_07374fba148d/events.out.tfevents.1710982856.07374fba148d.9691.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b38d3bc71d9519660971983f848047b782b0a884b52e7dc4522a1df8cfe2cfd
3
+ size 4738
runs/Mar21_01-01-51_07374fba148d/events.out.tfevents.1710982957.07374fba148d.9834.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74dba94e46516aa0fb809e5f90b322e26c0422018182a1da7e767b1470c0c286
3
+ size 4738
runs/Mar21_01-03-08_07374fba148d/events.out.tfevents.1710983033.07374fba148d.9963.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e9520105e0d21992270472c0e28fb307864a2e69204f89e51721c9618112581
3
+ size 5359
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<|im_start|>",
48
+ "<|im_end|>"
49
+ ],
50
+ "bos_token": "<|im_start|>",
51
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "<|im_end|>",
54
+ "legacy": false,
55
+ "model_max_length": 2048,
56
+ "pad_token": "<|im_end|>",
57
+ "padding_side": "right",
58
+ "sp_model_kwargs": {},
59
+ "tokenizer_class": "LlamaTokenizer",
60
+ "unk_token": "<unk>",
61
+ "use_default_system_prompt": false
62
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.118579317222942,
4
+ "train_runtime": 83.4654,
5
+ "train_samples": 500,
6
+ "train_samples_per_second": 4.038,
7
+ "train_steps_per_second": 0.264
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 22,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 1.6328125,
14
+ "learning_rate": 6.666666666666667e-06,
15
+ "loss": 1.1519,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.23,
20
+ "grad_norm": 1.4765625,
21
+ "learning_rate": 1.9458172417006347e-05,
22
+ "loss": 1.0777,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.45,
27
+ "grad_norm": 1.296875,
28
+ "learning_rate": 1.4016954246529697e-05,
29
+ "loss": 1.1219,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.68,
34
+ "grad_norm": 1.203125,
35
+ "learning_rate": 5.983045753470308e-06,
36
+ "loss": 1.1349,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.91,
41
+ "grad_norm": 1.2265625,
42
+ "learning_rate": 5.418275829936537e-07,
43
+ "loss": 1.1523,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_loss": 1.1635206937789917,
49
+ "eval_runtime": 19.2725,
50
+ "eval_samples_per_second": 18.057,
51
+ "eval_steps_per_second": 2.283,
52
+ "step": 22
53
+ },
54
+ {
55
+ "epoch": 1.0,
56
+ "step": 22,
57
+ "total_flos": 4283973723226112.0,
58
+ "train_loss": 1.118579317222942,
59
+ "train_runtime": 83.4654,
60
+ "train_samples_per_second": 4.038,
61
+ "train_steps_per_second": 0.264
62
+ }
63
+ ],
64
+ "logging_steps": 5,
65
+ "max_steps": 22,
66
+ "num_input_tokens_seen": 0,
67
+ "num_train_epochs": 1,
68
+ "save_steps": 100,
69
+ "total_flos": 4283973723226112.0,
70
+ "train_batch_size": 16,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3757be4cfcebb5edf13b43528f6b2b0efd2d01a2f1b157ec6e43b21a6fb7b4
3
+ size 4984