YYYYYYibo commited on
Commit
c4a0a32
1 Parent(s): 2af4926

Model save

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - dpo
7
+ - generated_from_trainer
8
+ base_model: alignment-handbook/zephyr-7b-sft-full
9
+ model-index:
10
+ - name: zephyr-7b-lora-64-no-quant-2k
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # zephyr-7b-lora-64-no-quant-2k
18
+
19
+ This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-06
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - gradient_accumulation_steps: 32
45
+ - total_train_batch_size: 256
46
+ - total_eval_batch_size: 8
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 1
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - PEFT 0.7.1
59
+ - Transformers 4.36.2
60
+ - Pytorch 2.1.2+cu121
61
+ - Datasets 2.14.6
62
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 128,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 64,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "k_proj",
23
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "o_proj",
27
+ "gate_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0f62d1495564fb433db0952da2b481bda7646df9ae9a53e5725e6d572a64b4
3
+ size 335605144
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6621483755417359,
4
+ "train_runtime": 6542.6499,
5
+ "train_samples": 20000,
6
+ "train_samples_per_second": 3.057,
7
+ "train_steps_per_second": 0.012
8
+ }
runs/Apr27_03-18-42_orion/events.out.tfevents.1714188096.orion.4026123.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ef1cb6f9c0e388e61c5aa1472d7e72db54c08079827cb71baf907680678b61b
3
+ size 9918
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "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 %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6621483755417359,
4
+ "train_runtime": 6542.6499,
5
+ "train_samples": 20000,
6
+ "train_samples_per_second": 3.057,
7
+ "train_steps_per_second": 0.012
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9984,
5
+ "eval_steps": 100,
6
+ "global_step": 78,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 6.25e-07,
14
+ "logits/chosen": -2.882505416870117,
15
+ "logits/rejected": -2.8317012786865234,
16
+ "logps/chosen": -292.0869140625,
17
+ "logps/rejected": -281.9166259765625,
18
+ "loss": 0.6931,
19
+ "rewards/accuracies": 0.0,
20
+ "rewards/chosen": 0.0,
21
+ "rewards/margins": 0.0,
22
+ "rewards/rejected": 0.0,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.13,
27
+ "learning_rate": 4.989935734988098e-06,
28
+ "logits/chosen": -2.760279893875122,
29
+ "logits/rejected": -2.7416226863861084,
30
+ "logps/chosen": -269.30419921875,
31
+ "logps/rejected": -258.9988098144531,
32
+ "loss": 0.692,
33
+ "rewards/accuracies": 0.5208333134651184,
34
+ "rewards/chosen": -0.0003755867655854672,
35
+ "rewards/margins": 0.0020193441305309534,
36
+ "rewards/rejected": -0.0023949304595589638,
37
+ "step": 10
38
+ },
39
+ {
40
+ "epoch": 0.26,
41
+ "learning_rate": 4.646121984004666e-06,
42
+ "logits/chosen": -2.7458298206329346,
43
+ "logits/rejected": -2.6916747093200684,
44
+ "logps/chosen": -292.1165771484375,
45
+ "logps/rejected": -262.5185546875,
46
+ "loss": 0.6832,
47
+ "rewards/accuracies": 0.667187511920929,
48
+ "rewards/chosen": 0.0018152827396988869,
49
+ "rewards/margins": 0.019987957552075386,
50
+ "rewards/rejected": -0.018172672018408775,
51
+ "step": 20
52
+ },
53
+ {
54
+ "epoch": 0.38,
55
+ "learning_rate": 3.8772424536302565e-06,
56
+ "logits/chosen": -2.7215728759765625,
57
+ "logits/rejected": -2.6702420711517334,
58
+ "logps/chosen": -277.44805908203125,
59
+ "logps/rejected": -274.95843505859375,
60
+ "loss": 0.6721,
61
+ "rewards/accuracies": 0.676562488079071,
62
+ "rewards/chosen": 0.019489800557494164,
63
+ "rewards/margins": 0.04290051385760307,
64
+ "rewards/rejected": -0.02341071143746376,
65
+ "step": 30
66
+ },
67
+ {
68
+ "epoch": 0.51,
69
+ "learning_rate": 2.835583164544139e-06,
70
+ "logits/chosen": -2.7158000469207764,
71
+ "logits/rejected": -2.6738948822021484,
72
+ "logps/chosen": -264.43963623046875,
73
+ "logps/rejected": -257.14398193359375,
74
+ "loss": 0.6625,
75
+ "rewards/accuracies": 0.6343749761581421,
76
+ "rewards/chosen": 0.0011910212924703956,
77
+ "rewards/margins": 0.05646045133471489,
78
+ "rewards/rejected": -0.055269431322813034,
79
+ "step": 40
80
+ },
81
+ {
82
+ "epoch": 0.64,
83
+ "learning_rate": 1.7274575140626318e-06,
84
+ "logits/chosen": -2.67500638961792,
85
+ "logits/rejected": -2.6178138256073,
86
+ "logps/chosen": -276.2191467285156,
87
+ "logps/rejected": -270.31317138671875,
88
+ "loss": 0.6502,
89
+ "rewards/accuracies": 0.6875,
90
+ "rewards/chosen": -0.02652786299586296,
91
+ "rewards/margins": 0.08806131035089493,
92
+ "rewards/rejected": -0.11458916962146759,
93
+ "step": 50
94
+ },
95
+ {
96
+ "epoch": 0.77,
97
+ "learning_rate": 7.723433775328385e-07,
98
+ "logits/chosen": -2.65384840965271,
99
+ "logits/rejected": -2.599376916885376,
100
+ "logps/chosen": -279.11370849609375,
101
+ "logps/rejected": -260.7146911621094,
102
+ "loss": 0.6465,
103
+ "rewards/accuracies": 0.699999988079071,
104
+ "rewards/chosen": -0.02440836653113365,
105
+ "rewards/margins": 0.11430301517248154,
106
+ "rewards/rejected": -0.1387113779783249,
107
+ "step": 60
108
+ },
109
+ {
110
+ "epoch": 0.9,
111
+ "learning_rate": 1.59412823400657e-07,
112
+ "logits/chosen": -2.668872833251953,
113
+ "logits/rejected": -2.5930261611938477,
114
+ "logps/chosen": -283.5231628417969,
115
+ "logps/rejected": -279.5673828125,
116
+ "loss": 0.6429,
117
+ "rewards/accuracies": 0.692187488079071,
118
+ "rewards/chosen": -0.021219942718744278,
119
+ "rewards/margins": 0.12081662565469742,
120
+ "rewards/rejected": -0.1420365869998932,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 1.0,
125
+ "step": 78,
126
+ "total_flos": 0.0,
127
+ "train_loss": 0.6621483755417359,
128
+ "train_runtime": 6542.6499,
129
+ "train_samples_per_second": 3.057,
130
+ "train_steps_per_second": 0.012
131
+ }
132
+ ],
133
+ "logging_steps": 10,
134
+ "max_steps": 78,
135
+ "num_input_tokens_seen": 0,
136
+ "num_train_epochs": 1,
137
+ "save_steps": 100,
138
+ "total_flos": 0.0,
139
+ "train_batch_size": 2,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1191bf04f62e6037ae00c31b57ca4b7979413d7a896864548a64cd7f739b5ddc
3
+ size 4920