SebastianSchramm commited on
Commit
0b86ac2
1 Parent(s): 1b44892

Model save

Browse files
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: SebastianSchramm/opt-125m-sft-full
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: opt-125m-dpo-full
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
+ # opt-125m-dpo-full
15
+
16
+ This model is a fine-tuned version of [SebastianSchramm/opt-125m-sft-full](https://huggingface.co/SebastianSchramm/opt-125m-sft-full) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.6160
19
+ - Rewards/chosen: -0.9541
20
+ - Rewards/rejected: -2.0866
21
+ - Rewards/accuracies: 0.6765
22
+ - Rewards/margins: 1.1325
23
+ - Logps/rejected: -421.7949
24
+ - Logps/chosen: -541.3610
25
+ - Logits/rejected: -3.0587
26
+ - Logits/chosen: -3.1037
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 5e-07
46
+ - train_batch_size: 4
47
+ - eval_batch_size: 2
48
+ - seed: 42
49
+ - distributed_type: multi-GPU
50
+ - gradient_accumulation_steps: 2
51
+ - total_train_batch_size: 8
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_ratio: 0.1
55
+ - num_epochs: 3
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
61
+ | 1.0169 | 0.13 | 1000 | 0.6485 | -0.0512 | -0.1732 | 0.6145 | 0.1220 | -402.6611 | -532.3322 | -3.1391 | -3.1931 |
62
+ | 0.9048 | 0.26 | 2000 | 0.6264 | -0.5889 | -1.0870 | 0.6325 | 0.4981 | -411.7990 | -537.7092 | -3.0871 | -3.1417 |
63
+ | 0.8198 | 0.39 | 3000 | 0.6522 | -0.8130 | -1.5553 | 0.6365 | 0.7424 | -416.4820 | -539.9495 | -2.9890 | -3.0594 |
64
+ | 0.7973 | 0.52 | 4000 | 0.6435 | -0.7772 | -1.6280 | 0.6450 | 0.8509 | -417.2088 | -539.5912 | -3.0365 | -3.1002 |
65
+ | 0.7659 | 0.65 | 5000 | 0.6419 | -0.8487 | -1.7568 | 0.6480 | 0.9081 | -418.4963 | -540.3063 | -3.0726 | -3.1246 |
66
+ | 0.6425 | 0.77 | 6000 | 0.6379 | -0.9374 | -1.9026 | 0.6555 | 0.9652 | -419.9547 | -541.1942 | -3.1294 | -3.1712 |
67
+ | 0.709 | 0.9 | 7000 | 0.6275 | -0.8907 | -1.8643 | 0.6610 | 0.9735 | -419.5712 | -540.7272 | -3.0433 | -3.0959 |
68
+ | 0.5569 | 1.03 | 8000 | 0.6325 | -0.9352 | -1.9355 | 0.6625 | 1.0003 | -420.2840 | -541.1722 | -3.0149 | -3.0760 |
69
+ | 0.6507 | 1.16 | 9000 | 0.6215 | -0.9145 | -1.9276 | 0.6700 | 1.0132 | -420.2049 | -540.9644 | -2.9981 | -3.0595 |
70
+ | 0.5921 | 1.29 | 10000 | 0.6201 | -0.9696 | -2.0113 | 0.6695 | 1.0417 | -421.0416 | -541.5154 | -2.9905 | -3.0538 |
71
+ | 0.581 | 1.42 | 11000 | 0.6231 | -0.8880 | -1.9400 | 0.6685 | 1.0521 | -420.3290 | -540.6996 | -2.9769 | -3.0403 |
72
+ | 0.6955 | 1.55 | 12000 | 0.6200 | -0.8521 | -1.9201 | 0.6715 | 1.0680 | -420.1295 | -540.3407 | -2.9294 | -3.0003 |
73
+ | 0.6388 | 1.68 | 13000 | 0.6221 | -0.9373 | -2.0216 | 0.6735 | 1.0843 | -421.1445 | -541.1925 | -2.9834 | -3.0472 |
74
+ | 0.511 | 1.81 | 14000 | 0.6167 | -0.8495 | -1.9379 | 0.6715 | 1.0884 | -420.3077 | -540.3145 | -3.0078 | -3.0625 |
75
+ | 0.5239 | 1.94 | 15000 | 0.6158 | -0.8967 | -1.9849 | 0.6775 | 1.0882 | -420.7780 | -540.7867 | -3.0404 | -3.0908 |
76
+ | 0.5769 | 2.07 | 16000 | 0.6220 | -0.9706 | -2.0850 | 0.6695 | 1.1144 | -421.7786 | -541.5255 | -3.0230 | -3.0752 |
77
+ | 0.407 | 2.19 | 17000 | 0.6137 | -0.9421 | -2.0587 | 0.6755 | 1.1166 | -421.5154 | -541.2402 | -3.0224 | -3.0743 |
78
+ | 0.5732 | 2.32 | 18000 | 0.6119 | -0.8997 | -2.0121 | 0.6740 | 1.1124 | -421.0493 | -540.8169 | -3.0294 | -3.0811 |
79
+ | 0.6627 | 2.45 | 19000 | 0.6143 | -0.9421 | -2.0649 | 0.6755 | 1.1228 | -421.5779 | -541.2407 | -3.0363 | -3.0864 |
80
+ | 0.568 | 2.58 | 20000 | 0.6163 | -0.9679 | -2.0994 | 0.6780 | 1.1316 | -421.9230 | -541.4983 | -3.0553 | -3.1021 |
81
+ | 0.5467 | 2.71 | 21000 | 0.6156 | -0.9578 | -2.0832 | 0.6780 | 1.1254 | -421.7610 | -541.3981 | -3.0488 | -3.0957 |
82
+ | 0.4785 | 2.84 | 22000 | 0.6160 | -0.9527 | -2.0818 | 0.6755 | 1.1290 | -421.7462 | -541.3470 | -3.0554 | -3.1020 |
83
+ | 0.4905 | 2.97 | 23000 | 0.6161 | -0.9537 | -2.0835 | 0.6770 | 1.1298 | -421.7638 | -541.3571 | -3.0583 | -3.1056 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.35.0
89
+ - Pytorch 2.1.0+cu121
90
+ - Datasets 2.14.6
91
+ - Tokenizers 0.14.1
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -3.1037471294403076,
4
+ "eval_logits/rejected": -3.058722734451294,
5
+ "eval_logps/chosen": -541.3610229492188,
6
+ "eval_logps/rejected": -421.7948913574219,
7
+ "eval_loss": 0.6159699559211731,
8
+ "eval_rewards/accuracies": 0.6765000224113464,
9
+ "eval_rewards/chosen": -0.9541231393814087,
10
+ "eval_rewards/margins": 1.1325011253356934,
11
+ "eval_rewards/rejected": -2.0866243839263916,
12
+ "eval_runtime": 348.052,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 5.746,
15
+ "eval_steps_per_second": 2.873,
16
+ "train_loss": 0.6616154855680051,
17
+ "train_runtime": 49213.1151,
18
+ "train_samples": 61966,
19
+ "train_samples_per_second": 3.777,
20
+ "train_steps_per_second": 0.472
21
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SebastianSchramm/opt-125m-sft-full",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 3072,
16
+ "hidden_size": 768,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.35.0",
28
+ "use_cache": false,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 768
31
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_logits/chosen": -3.1037471294403076,
4
+ "eval_logits/rejected": -3.058722734451294,
5
+ "eval_logps/chosen": -541.3610229492188,
6
+ "eval_logps/rejected": -421.7948913574219,
7
+ "eval_loss": 0.6159699559211731,
8
+ "eval_rewards/accuracies": 0.6765000224113464,
9
+ "eval_rewards/chosen": -0.9541231393814087,
10
+ "eval_rewards/margins": 1.1325011253356934,
11
+ "eval_rewards/rejected": -2.0866243839263916,
12
+ "eval_runtime": 348.052,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 5.746,
15
+ "eval_steps_per_second": 2.873
16
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.35.0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd4da52114bfcd3968f6a3354b4a55325ef7f075736a38eb9bdac266601925b1
3
+ size 250501160
runs/Dec06_12-53-25_sebastian-dell/events.out.tfevents.1701863614.sebastian-dell.1225710.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f4c1dc0aad16b94d8386736c82d31b24a9b972df98a17c9917417a32dd8a5b
3
+ size 836089
runs/Dec06_21-56-53_sebastian-dell/events.out.tfevents.1701896222.sebastian-dell.1239776.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab9f44a26a805e4832490c526a630b281ae038593bb53869aabd5af4e6344c2
3
+ size 1502699
runs/Dec06_21-56-53_sebastian-dell/events.out.tfevents.1701945783.sebastian-dell.1239776.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5d53e9586cf3a5b929f10a2339e20986defd79f702dbca27c314e5d6f68b82
3
+ size 841
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
24
+ "clean_up_tokenization_spaces": true,
25
+ "eos_token": "</s>",
26
+ "errors": "replace",
27
+ "model_max_length": 2048,
28
+ "pad_token": "<pad>",
29
+ "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "</s>"
31
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.6616154855680051,
4
+ "train_runtime": 49213.1151,
5
+ "train_samples": 61966,
6
+ "train_samples_per_second": 3.777,
7
+ "train_steps_per_second": 0.472
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eeccd5620680ef140999ffeab2a884aa75b3bb95ba2b1e1fa17921f7f043410
3
+ size 5688
vocab.json ADDED
The diff for this file is too large to render. See raw diff