loubnabnl HF staff commited on
Commit
20e85a3
1 Parent(s): b67e3b6

Model save

Browse files
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/cosmo2-1.7B-webinst-sc2
3
+ tags:
4
+ - trl
5
+ - dpo
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
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
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/xzcjqvtn)
16
+ # cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
17
+
18
+ This model is a fine-tuned version of [HuggingFaceTB/cosmo2-1.7B-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-1.7B-webinst-sc2) on an unknown dataset.
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: 5e-06
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 4
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 8
43
+ - gradient_accumulation_steps: 8
44
+ - total_train_batch_size: 128
45
+ - total_eval_batch_size: 32
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
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.42.3
58
+ - Pytorch 2.1.2
59
+ - Datasets 2.20.0
60
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9872958257713249,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.6753217893488267,
5
+ "train_runtime": 321.7901,
6
+ "train_samples": 8806,
7
+ "train_samples_per_second": 27.366,
8
+ "train_steps_per_second": 0.211
9
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/cosmo2-1.7B-webinst-sc2",
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": 8192,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 32,
20
+ "pad_token_id": 2,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": true,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.42.3",
28
+ "use_cache": false,
29
+ "vocab_size": 49152
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.42.3"
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:dfde9c7932c8a4b18f32f614820dc6f9a6d67c5699279d66e20b92d98ad5851a
3
+ size 3422777952
runs/Jul15_23-01-52_ip-26-0-171-168/events.out.tfevents.1721084661.ip-26-0-171-168.1537695.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e82e0a6588823112621478b95e6fc4db5d7bb0750bbc260d45a4f6d5eaa35c
3
+ size 10294
runs/Jul15_23-02-15_ip-26-0-175-34/events.out.tfevents.1721084673.ip-26-0-175-34.1294397.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee64781b1f43c757e014bacbcdc4b210d3b76ebe5fc1f4a63a28d24172c2419
3
+ size 10293
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "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 %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "model_max_length": 2048,
150
+ "pad_token": "<|im_end|>",
151
+ "tokenizer_class": "GPT2Tokenizer",
152
+ "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
154
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9872958257713249,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.6753217893488267,
5
+ "train_runtime": 321.7901,
6
+ "train_samples": 8806,
7
+ "train_samples_per_second": 27.366,
8
+ "train_steps_per_second": 0.211
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9872958257713249,
5
+ "eval_steps": 100,
6
+ "global_step": 68,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.014519056261343012,
13
+ "grad_norm": 2.5819620488760253,
14
+ "learning_rate": 7.142857142857143e-07,
15
+ "logits/chosen": 0.902682900428772,
16
+ "logits/rejected": 0.8661031723022461,
17
+ "logps/chosen": -125.2274169921875,
18
+ "logps/rejected": -145.89674377441406,
19
+ "loss": 0.6931,
20
+ "rewards/accuracies": 0.0,
21
+ "rewards/chosen": 0.0,
22
+ "rewards/margins": 0.0,
23
+ "rewards/rejected": 0.0,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.14519056261343014,
28
+ "grad_norm": 3.2242486672937045,
29
+ "learning_rate": 4.970219740227693e-06,
30
+ "logits/chosen": 0.8677890300750732,
31
+ "logits/rejected": 0.88941490650177,
32
+ "logps/chosen": -120.65478515625,
33
+ "logps/rejected": -149.0773468017578,
34
+ "loss": 0.6925,
35
+ "rewards/accuracies": 0.4097222089767456,
36
+ "rewards/chosen": 0.0005513947107829154,
37
+ "rewards/margins": -0.0005504629807546735,
38
+ "rewards/rejected": 0.001101857633329928,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.29038112522686027,
43
+ "grad_norm": 4.0763010346326904,
44
+ "learning_rate": 4.460299516441777e-06,
45
+ "logits/chosen": 1.0478929281234741,
46
+ "logits/rejected": 1.0530675649642944,
47
+ "logps/chosen": -115.20359802246094,
48
+ "logps/rejected": -142.4711456298828,
49
+ "loss": 0.6887,
50
+ "rewards/accuracies": 0.543749988079071,
51
+ "rewards/chosen": -0.007147049065679312,
52
+ "rewards/margins": 0.007046631071716547,
53
+ "rewards/rejected": -0.014193681068718433,
54
+ "step": 20
55
+ },
56
+ {
57
+ "epoch": 0.4355716878402904,
58
+ "grad_norm": 2.868995154924774,
59
+ "learning_rate": 3.441819734087963e-06,
60
+ "logits/chosen": 1.0493364334106445,
61
+ "logits/rejected": 1.0137263536453247,
62
+ "logps/chosen": -115.47831726074219,
63
+ "logps/rejected": -145.4583282470703,
64
+ "loss": 0.681,
65
+ "rewards/accuracies": 0.53125,
66
+ "rewards/chosen": -0.013122054748237133,
67
+ "rewards/margins": 0.018696457147598267,
68
+ "rewards/rejected": -0.031818509101867676,
69
+ "step": 30
70
+ },
71
+ {
72
+ "epoch": 0.5807622504537205,
73
+ "grad_norm": 2.4635583297317165,
74
+ "learning_rate": 2.1790041121336223e-06,
75
+ "logits/chosen": 1.2130175828933716,
76
+ "logits/rejected": 1.1768478155136108,
77
+ "logps/chosen": -154.19398498535156,
78
+ "logps/rejected": -181.88272094726562,
79
+ "loss": 0.6762,
80
+ "rewards/accuracies": 0.581250011920929,
81
+ "rewards/chosen": -0.04483573138713837,
82
+ "rewards/margins": 0.041850604116916656,
83
+ "rewards/rejected": -0.08668633550405502,
84
+ "step": 40
85
+ },
86
+ {
87
+ "epoch": 0.7259528130671506,
88
+ "grad_norm": 3.188683944287027,
89
+ "learning_rate": 9.994642986290797e-07,
90
+ "logits/chosen": 1.3518016338348389,
91
+ "logits/rejected": 1.2714142799377441,
92
+ "logps/chosen": -131.69985961914062,
93
+ "logps/rejected": -161.8300018310547,
94
+ "loss": 0.6622,
95
+ "rewards/accuracies": 0.6499999761581421,
96
+ "rewards/chosen": -0.011605720035731792,
97
+ "rewards/margins": 0.06830872595310211,
98
+ "rewards/rejected": -0.07991443574428558,
99
+ "step": 50
100
+ },
101
+ {
102
+ "epoch": 0.8711433756805808,
103
+ "grad_norm": 3.3445679325076476,
104
+ "learning_rate": 2.092077387824884e-07,
105
+ "logits/chosen": 1.367594838142395,
106
+ "logits/rejected": 1.2992292642593384,
107
+ "logps/chosen": -121.10174560546875,
108
+ "logps/rejected": -139.6844940185547,
109
+ "loss": 0.6612,
110
+ "rewards/accuracies": 0.612500011920929,
111
+ "rewards/chosen": -0.017885591834783554,
112
+ "rewards/margins": 0.07065734267234802,
113
+ "rewards/rejected": -0.08854293823242188,
114
+ "step": 60
115
+ },
116
+ {
117
+ "epoch": 0.9872958257713249,
118
+ "step": 68,
119
+ "total_flos": 0.0,
120
+ "train_loss": 0.6753217893488267,
121
+ "train_runtime": 321.7901,
122
+ "train_samples_per_second": 27.366,
123
+ "train_steps_per_second": 0.211
124
+ }
125
+ ],
126
+ "logging_steps": 10,
127
+ "max_steps": 68,
128
+ "num_input_tokens_seen": 0,
129
+ "num_train_epochs": 1,
130
+ "save_steps": 500,
131
+ "stateful_callbacks": {
132
+ "TrainerControl": {
133
+ "args": {
134
+ "should_epoch_stop": false,
135
+ "should_evaluate": false,
136
+ "should_log": false,
137
+ "should_save": false,
138
+ "should_training_stop": false
139
+ },
140
+ "attributes": {}
141
+ }
142
+ },
143
+ "total_flos": 0.0,
144
+ "train_batch_size": 2,
145
+ "trial_name": null,
146
+ "trial_params": null
147
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b25ccae881ba196be8b387a16231814d8703fa97b48eec0cb4de8739146b4e3
3
+ size 6520
vocab.json ADDED
The diff for this file is too large to render. See raw diff