martimfasantos commited on
Commit
3dc1d21
1 Parent(s): c3189f5

End of training

Browse files
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ tags:
5
+ - xcomet_xl_xxl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: cpo-xcomet-xl_xxl-inc7b-10p-shuff-5e-7-full-tiny
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # cpo-xcomet-xl_xxl-inc7b-10p-shuff-5e-7-full-tiny
16
+
17
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the Unbabel/TowerAligned-v0.1 dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 2.5861
20
+ - Nll Loss: 0.9631
21
+ - Logps/best: -93.9342
22
+ - Rewards/chosen: -9.3934
23
+ - Rewards/rejected: -8.9617
24
+ - Rewards/accuracies: 0.4760
25
+ - Rewards/margins: -0.4317
26
+ - Logps/rejected: -89.6171
27
+ - Logps/chosen: -93.9342
28
+ - Logits/rejected: -1.8016
29
+ - Logits/chosen: -1.9358
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 5e-07
49
+ - train_batch_size: 1
50
+ - eval_batch_size: 4
51
+ - seed: 42
52
+ - gradient_accumulation_steps: 16
53
+ - total_train_batch_size: 16
54
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
55
+ - lr_scheduler_type: linear
56
+ - lr_scheduler_warmup_ratio: 0.1
57
+ - num_epochs: 3
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Nll Loss | Logps/best | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:----------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
+ | 2.9692 | 0.1063 | 100 | 2.8057 | 1.0649 | -103.2722 | -10.3272 | -9.7340 | 0.4600 | -0.5932 | -97.3398 | -103.2722 | -1.8268 | -1.9640 |
64
+ | 3.0031 | 0.2127 | 200 | 2.7925 | 1.0588 | -102.7081 | -10.2708 | -9.6860 | 0.4580 | -0.5848 | -96.8598 | -102.7081 | -1.8260 | -1.9630 |
65
+ | 2.7823 | 0.3190 | 300 | 2.7675 | 1.0456 | -101.5052 | -10.1505 | -9.5824 | 0.4600 | -0.5681 | -95.8241 | -101.5052 | -1.8242 | -1.9611 |
66
+ | 2.8692 | 0.4254 | 400 | 2.7382 | 1.0320 | -100.2503 | -10.0250 | -9.4771 | 0.4580 | -0.5479 | -94.7710 | -100.2503 | -1.8210 | -1.9575 |
67
+ | 3.1882 | 0.5317 | 500 | 2.7126 | 1.0203 | -99.1754 | -9.9175 | -9.3884 | 0.4580 | -0.5291 | -93.8843 | -99.1754 | -1.8185 | -1.9548 |
68
+ | 2.8104 | 0.6381 | 600 | 2.6920 | 1.0101 | -98.2426 | -9.8243 | -9.3098 | 0.4640 | -0.5144 | -93.0982 | -98.2426 | -1.8161 | -1.9520 |
69
+ | 3.127 | 0.7444 | 700 | 2.6735 | 1.0018 | -97.4806 | -9.7481 | -9.2466 | 0.4680 | -0.5015 | -92.4660 | -97.4806 | -1.8148 | -1.9505 |
70
+ | 2.5488 | 0.8508 | 800 | 2.6599 | 0.9951 | -96.8657 | -9.6866 | -9.1952 | 0.4640 | -0.4914 | -91.9516 | -96.8657 | -1.8113 | -1.9467 |
71
+ | 2.9106 | 0.9571 | 900 | 2.6461 | 0.9892 | -96.3278 | -9.6328 | -9.1532 | 0.4700 | -0.4795 | -91.5325 | -96.3278 | -1.8107 | -1.9459 |
72
+ | 2.7349 | 1.0635 | 1000 | 2.6355 | 0.9845 | -95.8978 | -9.5898 | -9.1181 | 0.4660 | -0.4717 | -91.1811 | -95.8978 | -1.8091 | -1.9442 |
73
+ | 2.607 | 1.1698 | 1100 | 2.6258 | 0.9802 | -95.4924 | -9.5492 | -9.0851 | 0.4660 | -0.4642 | -90.8505 | -95.4924 | -1.8079 | -1.9429 |
74
+ | 2.5949 | 1.2762 | 1200 | 2.6187 | 0.9772 | -95.2189 | -9.5219 | -9.0638 | 0.4660 | -0.4581 | -90.6378 | -95.2189 | -1.8067 | -1.9415 |
75
+ | 3.0028 | 1.3825 | 1300 | 2.6133 | 0.9745 | -94.9713 | -9.4971 | -9.0415 | 0.4660 | -0.4556 | -90.4151 | -94.9713 | -1.8062 | -1.9409 |
76
+ | 2.5891 | 1.4889 | 1400 | 2.6075 | 0.9720 | -94.7468 | -9.4747 | -9.0242 | 0.4700 | -0.4505 | -90.2418 | -94.7468 | -1.8062 | -1.9409 |
77
+ | 2.5647 | 1.5952 | 1500 | 2.6035 | 0.9701 | -94.5637 | -9.4564 | -9.0103 | 0.4640 | -0.4460 | -90.1033 | -94.5637 | -1.8044 | -1.9389 |
78
+ | 2.566 | 1.7016 | 1600 | 2.5974 | 0.9682 | -94.3869 | -9.4387 | -8.9984 | 0.4660 | -0.4403 | -89.9837 | -94.3869 | -1.8037 | -1.9382 |
79
+ | 2.4615 | 1.8079 | 1700 | 2.5960 | 0.9672 | -94.3052 | -9.4305 | -8.9899 | 0.4760 | -0.4406 | -89.8987 | -94.3052 | -1.8029 | -1.9373 |
80
+ | 2.5336 | 1.9143 | 1800 | 2.5936 | 0.9662 | -94.2071 | -9.4207 | -8.9834 | 0.4700 | -0.4373 | -89.8344 | -94.2071 | -1.8026 | -1.9369 |
81
+ | 2.7186 | 2.0206 | 1900 | 2.5908 | 0.9653 | -94.1252 | -9.4125 | -8.9777 | 0.4820 | -0.4349 | -89.7766 | -94.1252 | -1.8021 | -1.9364 |
82
+ | 2.6496 | 2.1270 | 2000 | 2.5912 | 0.9646 | -94.0712 | -9.4071 | -8.9704 | 0.4700 | -0.4367 | -89.7039 | -94.0712 | -1.8020 | -1.9363 |
83
+ | 2.4786 | 2.2333 | 2100 | 2.5882 | 0.9642 | -94.0305 | -9.4031 | -8.9690 | 0.4820 | -0.4340 | -89.6904 | -94.0305 | -1.8022 | -1.9365 |
84
+ | 2.5261 | 2.3396 | 2200 | 2.5871 | 0.9636 | -93.9762 | -9.3976 | -8.9653 | 0.4720 | -0.4323 | -89.6528 | -93.9762 | -1.8015 | -1.9357 |
85
+ | 2.4197 | 2.4460 | 2300 | 2.5855 | 0.9634 | -93.9605 | -9.3961 | -8.9653 | 0.4720 | -0.4308 | -89.6529 | -93.9605 | -1.8015 | -1.9357 |
86
+ | 2.9723 | 2.5523 | 2400 | 2.5863 | 0.9633 | -93.9504 | -9.3950 | -8.9631 | 0.4760 | -0.4319 | -89.6311 | -93.9504 | -1.8016 | -1.9358 |
87
+ | 2.4721 | 2.6587 | 2500 | 2.5864 | 0.9634 | -93.9537 | -9.3954 | -8.9651 | 0.4740 | -0.4302 | -89.6514 | -93.9537 | -1.8014 | -1.9356 |
88
+ | 2.8984 | 2.7650 | 2600 | 2.5856 | 0.9630 | -93.9154 | -9.3915 | -8.9610 | 0.4700 | -0.4305 | -89.6100 | -93.9154 | -1.8014 | -1.9356 |
89
+ | 3.0422 | 2.8714 | 2700 | 2.5848 | 0.9630 | -93.9148 | -9.3915 | -8.9617 | 0.4800 | -0.4298 | -89.6169 | -93.9148 | -1.8015 | -1.9357 |
90
+ | 2.6226 | 2.9777 | 2800 | 2.5861 | 0.9631 | -93.9342 | -9.3934 | -8.9617 | 0.4760 | -0.4317 | -89.6171 | -93.9342 | -1.8016 | -1.9358 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.41.2
96
+ - Pytorch 2.1.2
97
+ - Datasets 2.20.0
98
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "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": "4.41.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
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": "4.41.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb4cdee2aca37b087aa8a80d84c22c9fd6779a5ee8b36627d3c56bc2c19a4e9
3
+ size 2200119864
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "[PAD]",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "[PAD]",
36
+ "padding_side": "left",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0679d255030fbbcaf5dbce3c1e7b54b9f5cf09b8c52dbfc1f17740f4625e9995
3
+ size 5240