burtenshaw HF staff commited on
Commit
641e707
1 Parent(s): 9430ab6

Upload folder using huggingface_hub

Browse files
checkpoint-313/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen1.5-0.5B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2816,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 16,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.39.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
checkpoint-313/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.39.2"
6
+ }
checkpoint-313/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe626c1033f0b0b6486b1203488cd6db2994c96f78d31b57e17e8262e80f3d1
3
+ size 1239173352
checkpoint-313/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc73358597b82368e59eabbe96fa657b47ccab1cef03cb3e63f43a80751855a6
3
+ size 3712103162
checkpoint-313/pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88628f8605e07512111aa6e00bd0c7736ac7d5b8fdd3f8c61c9e1860ee33e49c
3
+ size 1239275353
checkpoint-313/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
3
+ size 15024
checkpoint-313/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
3
+ size 15024
checkpoint-313/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
3
+ size 15024
checkpoint-313/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
3
+ size 15024
checkpoint-313/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a3a847b2da5cc99667fb5595d3d91d25d426f2a3b3f1ec256909eaaddfc80b
3
+ size 1064
checkpoint-313/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1438744068145752,
3
+ "best_model_checkpoint": "./checkpoints/dpo-mix-7k/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-29-9-49/checkpoint-313",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 313,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "grad_norm": 616.0,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 15.2717,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.32,
20
+ "grad_norm": 5.59375,
21
+ "learning_rate": 5e-06,
22
+ "loss": 4.0109,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.48,
27
+ "grad_norm": 5.65625,
28
+ "learning_rate": 4.889350784534168e-06,
29
+ "loss": 1.2041,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.64,
34
+ "grad_norm": 4.90625,
35
+ "learning_rate": 4.5671977372432355e-06,
36
+ "loss": 1.1597,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.8,
41
+ "grad_norm": 43.5,
42
+ "learning_rate": 4.062057643681335e-06,
43
+ "loss": 1.1542,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.96,
48
+ "grad_norm": 9.8125,
49
+ "learning_rate": 3.4186451878908393e-06,
50
+ "loss": 1.1222,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "eval_loss": 1.1438744068145752,
56
+ "eval_runtime": 34.1359,
57
+ "eval_samples_per_second": 16.551,
58
+ "eval_steps_per_second": 1.055,
59
+ "step": 313
60
+ }
61
+ ],
62
+ "logging_steps": 50,
63
+ "max_steps": 626,
64
+ "num_input_tokens_seen": 0,
65
+ "num_train_epochs": 2,
66
+ "save_steps": 500,
67
+ "total_flos": 4744684177981440.0,
68
+ "train_batch_size": 4,
69
+ "trial_name": null,
70
+ "trial_params": null
71
+ }
checkpoint-313/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba636fcd247d639f405e2e00cd9717702cadada97437b5285147fee89e3f28e2
3
+ size 5048
checkpoint-626/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen1.5-0.5B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2816,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 16,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.39.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
checkpoint-626/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.39.2"
6
+ }
checkpoint-626/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a185c9e39289cfeff3becc2fc573647d493a99fe9f3049b8bd5a30289f58cdb5
3
+ size 1239173352
checkpoint-626/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc42aebd19be79450b587c0e9897708b3b44c7a15cef001e0df1407d17aba9b
3
+ size 3712103162
checkpoint-626/pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d4e0dbd3df02e78d9f7910dab327994aa80ab5d89ef3c9988908cc5f61c150
3
+ size 1239275353
checkpoint-626/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:418a5f105ae834c3075024076916b2a9475918fe034c12d0dd5b6d91f1aba467
3
+ size 15024
checkpoint-626/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e07ace389d24bc1307b74f42a1e7b8f0117b0db853e2df64ff3f15cb92916a2
3
+ size 15024
checkpoint-626/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6a990f346d7014dffb28fa2bc7d3b890bd3c53712503fce3656da48d3d6e50
3
+ size 15024
checkpoint-626/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95f356ca38179b05993f55daece0223e96fa10b9a1b9ea2102a739211333f63
3
+ size 15024
checkpoint-626/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:330af213ffd33b0966c84faa1ee759a9643efb15549b7ffb50aadfb93382d16e
3
+ size 1064
checkpoint-626/trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1383987665176392,
3
+ "best_model_checkpoint": "./checkpoints/dpo-mix-7k/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-29-9-49/checkpoint-626",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 626,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "grad_norm": 616.0,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 15.2717,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.32,
20
+ "grad_norm": 5.59375,
21
+ "learning_rate": 5e-06,
22
+ "loss": 4.0109,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.48,
27
+ "grad_norm": 5.65625,
28
+ "learning_rate": 4.889350784534168e-06,
29
+ "loss": 1.2041,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.64,
34
+ "grad_norm": 4.90625,
35
+ "learning_rate": 4.5671977372432355e-06,
36
+ "loss": 1.1597,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.8,
41
+ "grad_norm": 43.5,
42
+ "learning_rate": 4.062057643681335e-06,
43
+ "loss": 1.1542,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.96,
48
+ "grad_norm": 9.8125,
49
+ "learning_rate": 3.4186451878908393e-06,
50
+ "loss": 1.1222,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "eval_loss": 1.1438744068145752,
56
+ "eval_runtime": 34.1359,
57
+ "eval_samples_per_second": 16.551,
58
+ "eval_steps_per_second": 1.055,
59
+ "step": 313
60
+ },
61
+ {
62
+ "epoch": 1.12,
63
+ "grad_norm": 6.28125,
64
+ "learning_rate": 2.693914836635076e-06,
65
+ "loss": 1.0845,
66
+ "step": 350
67
+ },
68
+ {
69
+ "epoch": 1.28,
70
+ "grad_norm": 15.9375,
71
+ "learning_rate": 1.9520192657466286e-06,
72
+ "loss": 1.1293,
73
+ "step": 400
74
+ },
75
+ {
76
+ "epoch": 1.44,
77
+ "grad_norm": 15.5625,
78
+ "learning_rate": 1.2586306055266007e-06,
79
+ "loss": 1.1217,
80
+ "step": 450
81
+ },
82
+ {
83
+ "epoch": 1.6,
84
+ "grad_norm": 13.3125,
85
+ "learning_rate": 6.751271849879959e-07,
86
+ "loss": 1.1324,
87
+ "step": 500
88
+ },
89
+ {
90
+ "epoch": 1.76,
91
+ "grad_norm": 5.4375,
92
+ "learning_rate": 2.531603606941929e-07,
93
+ "loss": 1.163,
94
+ "step": 550
95
+ },
96
+ {
97
+ "epoch": 1.92,
98
+ "grad_norm": 6.15625,
99
+ "learning_rate": 3.0082371093766435e-08,
100
+ "loss": 1.1869,
101
+ "step": 600
102
+ },
103
+ {
104
+ "epoch": 2.0,
105
+ "eval_loss": 1.1383987665176392,
106
+ "eval_runtime": 34.1146,
107
+ "eval_samples_per_second": 16.562,
108
+ "eval_steps_per_second": 1.055,
109
+ "step": 626
110
+ }
111
+ ],
112
+ "logging_steps": 50,
113
+ "max_steps": 626,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 2,
116
+ "save_steps": 500,
117
+ "total_flos": 9489368339185664.0,
118
+ "train_batch_size": 4,
119
+ "trial_name": null,
120
+ "trial_params": null
121
+ }
checkpoint-626/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba636fcd247d639f405e2e00cd9717702cadada97437b5285147fee89e3f28e2
3
+ size 5048
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen1.5-0.5B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2816,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 16,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.39.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.39.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a185c9e39289cfeff3becc2fc573647d493a99fe9f3049b8bd5a30289f58cdb5
3
+ size 1239173352
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba636fcd247d639f405e2e00cd9717702cadada97437b5285147fee89e3f28e2
3
+ size 5048